@comment{{This file has been generated by bib2bib 1.97}}
@comment{{Command line: bib2bib ../bibli.bib -c 'subject:"prot" or keywords:"prot"' -ob tmp.bib}}
@article{Ala2008Prediction,
author = {Ala, U. and Piro, R.M. and Grassi, E. and Damasco, C. and Silengo,
L. and Oti, M. and Provero, P. and Di Cunto, F.},
title = {Prediction of human disease genes by human-mouse conserved coexpression
analysis.},
journal = {PLoS Comput. Biol.},
year = {2008},
volume = {4},
pages = {e1000043},
number = {3},
month = {Mar},
abstract = {BACKGROUND: Even in the post-genomic era, the identification of candidate
genes within loci associated with human genetic diseases is a very
demanding task, because the critical region may typically contain
hundreds of positional candidates. Since genes implicated in similar
phenotypes tend to share very similar expression profiles, high throughput
gene expression data may represent a very important resource to identify
the best candidates for sequencing. However, so far, gene coexpression
has not been used very successfully to prioritize positional candidates.
METHODOLOGY/PRINCIPAL FINDINGS: We show that it is possible to reliably
identify disease-relevant relationships among genes from massive
microarray datasets by concentrating only on genes sharing similar
expression profiles in both human and mouse. Moreover, we show systematically
that the integration of human-mouse conserved coexpression with a
phenotype similarity map allows the efficient identification of disease
genes in large genomic regions. Finally, using this approach on 850
OMIM loci characterized by an unknown molecular basis, we propose
high-probability candidates for 81 genetic diseases. CONCLUSION:
Our results demonstrate that conserved coexpression, even at the
human-mouse phylogenetic distance, represents a very strong criterion
to predict disease-relevant relationships among human genes.},
doi = {10.1371/journal.pcbi.1000043},
institution = {Molecular Biotechnology Center, Department of Genetics, Biology and
Biochemistry, University of Turin, Turin, Italy.},
keywords = {Algorithms; Animals; Biological Markers; Chromosome Mapping; Conserved
Sequence; Diagnosis, Computer-Assisted; Gene Expression Profiling;
Genetic Diseases, Inborn; Genetic Predisposition to Disease; Humans;
Mice; Proteome},
owner = {mordelet},
pmid = {18369433},
timestamp = {2010.09.28},
url = {http://dx.doi.org/10.1371/journal.pcbi.1000043}
}
@article{Anderson2003new,
author = {Anderson, D.C. and Li, W. and Payan, D.G. and Noble, W.S.},
title = {A new algorithm for the evaluation of shotgun peptide sequencing
in proteomics: support vector machine classification of peptide {{MS}/{MS}}
spectra and {SEQUEST} scores.},
journal = {J {P}roteome {R}es},
year = {2003},
volume = {2},
pages = {137-146},
number = {2},
abstract = {Shotgun tandem mass spectrometry-based peptide sequencing using programs
such as {SEQUEST} allows high-throughput identification of peptides,
which in turn allows the identification of corresponding proteins.
{W}e have applied a machine learning algorithm, called the support
vector machine, to discriminate between correctly and incorrectly
identified peptides using {SEQUEST} output. {E}ach peptide was characterized
by {SEQUEST}-calculated features such as delta {C}n and {X}corr,
measurements such as precursor ion current and mass, and additional
calculated parameters such as the fraction of matched {MS}/{MS} peaks.
{T}he trained {SVM} classifier performed significantly better than
previous cutoff-based methods at separating positive from negative
peptides. {P}ositive and negative peptides were more readily distinguished
in training set data acquired on a {QTOF}, compared to an ion trap
mass spectrometer. {T}he use of 13 features, including four new parameters,
significantly improved the separation between positive and negative
peptides. {U}se of the support vector machine and these additional
parameters resulted in a more accurate interpretation of peptide
{MS}/{MS} spectra and is an important step toward automated interpretation
of peptide tandem mass spectrometry data in proteomics.},
pdf = {../local/Anderson2003new.pdf},
file = {Anderson2003new.pdf:local/Anderson2003new.pdf:PDF},
keywords = {biosvm proteomics},
owner = {jeanphilippevert}
}
@article{Arakawa2003Application,
author = {M. Arakawa and K. Hasegawa and K. Funatsu},
title = {{A}pplication of the novel molecular alignment method using the {H}opfield
{N}eural {N}etwork to 3{D}-{QSAR}.},
journal = {J Chem Inf Comput Sci},
year = {2003},
volume = {43},
pages = {1396--1402},
number = {5},
abstract = {Recently, we investigated and proposed the novel molecular alignment
method with the Hopfield Neural Network (HNN). Molecules are represented
by four kinds of chemical properties (hydrophobic group, hydrogen-bonding
acceptor, hydrogen-bonding donor, and hydrogen-bonding donor/acceptor),
and then those properties between two molecules correspond to each
other using HNN. The 12 pairs of enzyme-inhibitors were used for
validation, and our method could successfully reproduce the real
molecular alignments obtained from X-ray crystallography. In this
paper, we apply the molecular alignment method to three-dimensional
quantitative structure-activity relationship (3D-QSAR) analysis.
The two data sets (human epidermal growth factor receptor-2 inhibitors
and cyclooxygenase-2 inhibitors) were investigated to validate our
method. As a result, the robust and predictive 3D-QSAR models were
successfully obtained in both data sets.},
doi = {10.1021/ci030005q},
keywords = {Chemical, Cyclooxygenase 2, Cyclooxygenase 2 Inhibitors, Cyclooxygenase
Inhibitors, Databases, Enzyme Inhibitors, Epidermal Growth Factor,
Factual, Humans, Isoenzymes, Membrane Proteins, Models, Molecular,
Neural Networks (Computer), Prostaglandin-Endoperoxide Synthases,
Quantitative Structure-Activity Relationship, Receptor, 14502472},
owner = {mahe},
pmid = {14502472},
timestamp = {2006.08.22},
url = {http://dx.doi.org/10.1021/ci030005q}
}
@article{Aranda2010IntAct,
author = {B. Aranda and P. Achuthan and Y. Alam-Faruque and I. Armean and A.
Bridge and C. Derow and M. Feuermann and A. T. Ghanbarian and S.
Kerrien and J. Khadake and J. Kerssemakers and C. Leroy and M. Menden
and M. Michaut and L. Montecchi-Palazzi and S. N. Neuhauser and S.
Orchard and V. Perreau and B. Roechert and K. van Eijk and H. Hermjakob},
title = {The IntAct molecular interaction database in 2010.},
journal = {Nucleic Acids Res},
year = {2010},
volume = {38},
pages = {D525--D531},
number = {Database issue},
month = {Jan},
abstract = {IntAct is an open-source, open data molecular interaction database
and toolkit. Data is abstracted from the literature or from direct
data depositions by expert curators following a deep annotation model
providing a high level of detail. As of September 2009, IntAct contains
over 200.000 curated binary interaction evidences. In response to
the growing data volume and user requests, IntAct now provides a
two-tiered view of the interaction data. The search interface allows
the user to iteratively develop complex queries, exploiting the detailed
annotation with hierarchical controlled vocabularies. Results are
provided at any stage in a simplified, tabular view. Specialized
views then allows 'zooming in' on the full annotation of interactions,
interactors and their properties. IntAct source code and data are
freely available at http://www.ebi.ac.uk/intact.},
doi = {10.1093/nar/gkp878},
institution = {EMBL Outstation, European Bioinformatics Institute, Wellcome Trust
Genome Campus Hinxton, Cambridge CB10 1SD, UK.},
keywords = {Animals; Computational Biology; Databases, Genetic; Databases, Protein;
False Positive Reactions; Humans; Information Storage and Retrieval;
Internet; Programming Languages; Protein Interaction Mapping; Protein
Structure, Tertiary; Proteins; Software; User-Computer Interface;
Vocabulary, Controlled},
owner = {fantine},
pii = {gkp878},
pmid = {19850723},
timestamp = {2010.10.21},
url = {http://dx.doi.org/10.1093/nar/gkp878}
}
@article{Asefa2005Support,
author = {Tirusew Asefa and Mariush Kemblowski and Gilberto Urroz and Mac McKee},
title = {Support vector machines ({SVM}s) for monitoring network design.},
journal = {Ground {W}ater},
year = {2005},
volume = {43},
pages = {413-22},
number = {3},
abstract = {In this paper we present a hydrologic application of a new statistical
learning methodology called support vector machines ({SVM}s). {SVM}s
are based on minimization of a bound on the generalized error (risk)
model, rather than just the mean square error over a training set.
{D}ue to {M}ercer's conditions on the kernels, the corresponding
optimization problems are convex and hence have no local minima.
{I}n this paper, {SVM}s are illustratively used to reproduce the
behavior of {M}onte {C}arlo-based flow and transport models that
are in turn used in the design of a ground water contamination detection
monitoring system. {T}he traditional approach, which is based on
solving transient transport equations for each new configuration
of a conductivity field, is too time consuming in practical applications.
{T}hus, there is a need to capture the behavior of the transport
phenomenon in random media in a relatively simple manner. {T}he objective
of the exercise is to maximize the probability of detecting contaminants
that exceed some regulatory standard before they reach a compliance
boundary, while minimizing cost (i.e., number of monitoring wells).
{A}pplication of the method at a generic site showed a rather promising
performance, which leads us to believe that {SVM}s could be successfully
employed in other areas of hydrology. {T}he {SVM} was trained using
510 monitoring configuration samples generated from 200 {M}onte {C}arlo
flow and transport realizations. {T}he best configurations of well
networks selected by the {SVM} were identical with the ones obtained
from the physical model, but the reliabilities provided by the respective
networks differ slightly.},
doi = {10.1111/j.1745-6584.2005.0050.x},
pdf = {../local/Asefa2005Support.pdf},
file = {Asefa2005Support.pdf:local/Asefa2005Support.pdf:PDF},
keywords = {Adult, Aged, Aging, Algorithms, Apoptosis, Artificial Intelligence,
Automated, Computer-Assisted, Female, Foot, Gait, Gene Expression
Profiling, Humans, Image Interpretation, Male, Neoplasms, Non-U.S.
Gov't, Oligonucleotide Array Sequence Analysis, Pattern Recognition,
Polymerase Chain Reaction, Proteins, Reproducibility of Results,
Research Support, Sensitivity and Specificity, Subcellular Fractions,
Unknown Primary, 15882333},
pii = {GWAT50},
url = {http://dx.doi.org/10.1111/j.1745-6584.2005.0050.x}
}
@article{Attwood2003PRINTS,
author = {T. K. Attwood and P. Bradley and D. R. Flower and A. Gaulton and
N. Maudling and A. L. Mitchell and G. Moulton and A. Nordle and K.
Paine and P. Taylor and A. Uddin and C. Zygouri},
title = {PRINTS and its automatic supplement, prePRINTS.},
journal = {Nucleic Acids Res.},
year = {2003},
volume = {31},
pages = {400--402},
number = {1},
month = {Jan},
abstract = {The PRINTS database houses a collection of protein fingerprints. These
may be used to assign uncharacterised sequences to known families
and hence to infer tentative functions. The September 2002 release
(version 36.0) includes 1800 fingerprints, encoding approximately
11 000 motifs, covering a range of globular and membrane proteins,
modular polypeptides and so on. In addition to its continued steady
growth, we report here the development of an automatic supplement,
prePRINTS, designed to increase the coverage of the resource and
reduce some of the manual burdens inherent in its maintenance. The
databases are accessible for interrogation and searching at http://www.bioinf.man.ac.uk/dbbrowser/PRINTS/.},
keywords = {Amino Acid Motifs; Animals; Automation; Conserved Sequence; Databases,
Protein; Proteins; Software},
owner = {laurent},
pmid = {12520033},
timestamp = {2007.09.22}
}
@article{Bagga2005Quantitative,
author = {Harmohina Bagga and David S Greenfield and William J Feuer},
title = {Quantitative assessment of atypical birefringence images using scanning
laser polarimetry with variable corneal compensation.},
journal = {Am {J} {O}phthalmol},
year = {2005},
volume = {139},
pages = {437-46},
number = {3},
month = {Mar},
abstract = {P{URPOSE}: {T}o define the clinical characteristics of atypical birefringence
images and to describe a quantitative method for their identification.
{DESIGN}: {P}rospective, comparative, clinical observational study.
{METHODS}: {N}ormal and glaucomatous eyes underwent complete examination,
standard automated perimetry, scanning laser polarimetry with variable
corneal compensation ({GD}x-{VCC}), and optical coherence tomography
({OCT}) of the macula, peripapillary retinal nerve fiber layer ({RNFL}),
and optic disk. {E}yes were classified into two groups: normal birefringence
pattern ({NBP}) and atypical birefringence pattern ({ABP}). {C}linical,
functional, and structural characteristics were assessed separately.
{A} multiple logistic regression model was used to predict eyes with
{ABP} on the basis of a quantitative scan score generated by a support
vector machine ({SVM}) with {GD}x-{VCC}. {RESULTS}: {S}ixty-five
eyes of 65 patients were enrolled. {ABP} images were observed in
5 of 20 (25\%) normal eyes and 23 of 45 (51\%) glaucomatous eyes.
{C}ompared with eyes with {NBP}, glaucomatous eyes with {ABP} demonstrated
significantly lower {SVM} scores ({P} < .0001, < 0.0001, 0.008, 0.03,
and 0.03, respectively) and greater temporal, mean, inferior, and
nasal {RNFL} thickness using {GD}x-{VCC}; and a weaker correlation
with {OCT} generated {RNFL} thickness ({R}(2) = .75 vs .27). {ABP}
images were significantly correlated with older age ({R}(2) = .16,
{P} = .001). {T}he {SVM} score was the only significant ({P} < .0001)
predictor of {ABP} images and provided high discriminating power
between eyes with {NBP} and {ABP} (area under the receiver operator
characteristic curve = 0.98). {CONCLUSIONS}: {ABP} images exist in
a subset of normal and glaucomatous eyes, are associated with older
patient age, and produce an artifactual increase in {RNFL} thickness
using {GD}x-{VCC}. {T}he {SVM} score is highly predictive of {ABP}
images.},
doi = {10.1016/j.ajo.2004.10.019},
pdf = {../local/Bagga2005Quantitative.pdf},
file = {Bagga2005Quantitative.pdf:locql/Bagga2005Quantitative.pdf:PDF},
keywords = {80 and over, Adult, Aged, Algorithms, Amino Acids, Animals, Area Under
Curve, Artifacts, Automated, Birefringence, Brain Chemistry, Brain
Neoplasms, Comparative Study, Computer-Assisted, Cornea, Cross-Sectional
Studies, Decision Trees, Diagnosis, Diagnostic Imaging, Diagnostic
Techniques, Discriminant Analysis, Evolution, Face, Female, Genetic,
Glaucoma, Humans, Intraocular Pressure, Lasers, Least-Squares Analysis,
Magnetic Resonance Imaging, Magnetic Resonance Spectroscopy, Male,
Middle Aged, Models, Molecular, Nerve Fibers, Non-U.S. Gov't, Numerical
Analysis, Ophthalmological, Optic Nerve Diseases, Optical Coherence,
P.H.S., Pattern Recognition, Photic Stimulation, Prospective Studies,
Protein, ROC Curve, Regression Analysis, Research Support, Retinal
Ganglion Cells, Sensitivity and Specificity, Sequence Analysis, Statistics,
Tomography, U.S. Gov't, Visual Fields, beta-Lactamases, 15767051},
pii = {S0002-9394(04)01265-6},
url = {http://dx.doi.org/10.1016/j.ajo.2004.10.019}
}
@article{Bagirov2003New,
author = {A. M. Bagirov and B. Ferguson and S. Ivkovic and G. Saunders and
J. Yearwood},
title = {New algorithms for multi-class cancer diagnosis using tumor gene
expression signatures.},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {1800-7},
number = {14},
month = {Sep},
abstract = {M{OTIVATION}: {T}he increasing use of {DNA} microarray-based tumor
gene expression profiles for cancer diagnosis requires mathematical
methods with high accuracy for solving clustering, feature selection
and classification problems of gene expression data. {RESULTS}: {N}ew
algorithms are developed for solving clustering, feature selection
and classification problems of gene expression data. {T}he clustering
algorithm is based on optimization techniques and allows the calculation
of clusters step-by-step. {T}his approach allows us to find as many
clusters as a data set contains with respect to some tolerance. {F}eature
selection is crucial for a gene expression database. {O}ur feature
selection algorithm is based on calculating overlaps of different
genes. {T}he database used, contains over 16 000 genes and this number
is considerably reduced by feature selection. {W}e propose a classification
algorithm where each tissue sample is considered as the center of
a cluster which is a ball. {T}he results of numerical experiments
confirm that the classification algorithm in combination with the
feature selection algorithm perform slightly better than the published
results for multi-class classifiers based on support vector machines
for this data set. {AVAILABILITY}: {A}vailable on request from the
authors.},
pdf = {../local/Bagirov2003New.pdf},
file = {Bagirov2003New.pdf:local/Bagirov2003New.pdf:PDF},
keywords = {Algorithms, Amino Acid Sequence, Anion Exchange Resins, Antigen-Antibody
Complex, Artificial Intelligence, Automated, Automatic Data Processing,
Biological, Blood Cells, Chemical, Chromatography, Cluster Analysis,
Comparative Study, Computational Biology, Computer Simulation, Computer-Assisted,
DNA, Data Interpretation, Databases, Decision Making, Decision Trees,
Diffusion Magnetic Resonance Imaging, English Abstract, Epitopes,
Expert Systems, Factual, Fuzzy Logic, Gene Expression Profiling,
Gene Expression Regulation, Gene Targeting, Genetic, Genome, Histocompatibility
Antigens Class I, Humans, Image Interpretation, Image Processing,
In Vitro, Indicators and Reagents, Information Storage and Retrieval,
Ion Exchange, Least-Squares Analysis, Liver Cirrhosis, Magnetic Resonance
Imaging, Male, Models, Molecular Sequence Data, Neoplasms, Neoplastic,
Neural Networks (Computer), Non-P.H.S., Non-U.S. Gov't, Nonl, Nucleic
Acid Conformation, Oligonucleotide Array Sequence Analysis, P.H.S.,
Pattern Recognition, Pro, Prostatic Neoplasms, Protein, Protein Binding,
Protein Interaction Mapping, Proteins, Quantitative Structure-Activity
Relationship, RNA, ROC Curve, Reproducibility of Results, Research
Support, Sensitivity and Specificity, Sequence Alignment, Sequence
Analysis, Severity of Illness Index, Statistical, Structure-Activity
Relationship, Subtraction Technique, T-Lymphocyte, Transcription
Factors, Transfer, Treatment Outcome, Tumor Markers, U.S. Gov't,
User-Computer Interface, inear Dynamics, teome, 14512351},
url = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/19/14/1800}
}
@article{Bagos2005Evaluation,
author = {Pantelis G Bagos and Theodore D Liakopoulos and Stavros J Hamodrakas},
title = {Evaluation of methods for predicting the topology of beta-barrel
outer membrane proteins and a consensus prediction method.},
journal = {B{MC} {B}ioinformatics},
year = {2005},
volume = {6},
pages = {7},
number = {1},
month = {Jan},
abstract = {B{ACKGROUND}: {P}rediction of the transmembrane strands and topology
of beta-barrel outer membrane proteins is of interest in current
bioinformatics research. {S}everal methods have been applied so far
for this task, utilizing different algorithmic techniques and a number
of freely available predictors exist. {T}he methods can be grossly
divided to those based on {H}idden {M}arkov {M}odels ({HMM}s), on
{N}eural {N}etworks ({NN}s) and on {S}upport {V}ector {M}achines
({SVM}s). {I}n this work, we compare the different available methods
for topology prediction of beta-barrel outer membrane proteins. {W}e
evaluate their performance on a non-redundant dataset of 20 beta-barrel
outer membrane proteins of gram-negative bacteria, with structures
known at atomic resolution. {A}lso, we describe, for the first time,
an effective way to combine the individual predictors, at will, to
a single consensus prediction method. {RESULTS}: {W}e assess the
statistical significance of the performance of each prediction scheme
and conclude that {H}idden {M}arkov {M}odel based methods, {HMM}-{B}2{TMR},
{P}rof{TMB} and {PRED}-{TMBB}, are currently the best predictors,
according to either the per-residue accuracy, the segments overlap
measure ({SOV}) or the total number of proteins with correctly predicted
topologies in the test set. {F}urthermore, we show that the available
predictors perform better when only transmembrane beta-barrel domains
are used for prediction, rather than the precursor full-length sequences,
even though the {HMM}-based predictors are not influenced significantly.
{T}he consensus prediction method performs significantly better than
each individual available predictor, since it increases the accuracy
up to 4\% regarding {SOV} and up to 15\% in correctly predicted topologies.
{CONCLUSIONS}: {T}he consensus prediction method described in this
work, optimizes the predicted topology with a dynamic programming
algorithm and is implemented in a web-based application freely available
to non-commercial users at http://bioinformatics.biol.uoa.gr/{C}on{BBPRED}.},
doi = {10.1186/1471-2105-6-7},
pdf = {../local/Bagos2005Evaluation.pdf},
file = {Bagos2005Evaluation.pdf:local/Bagos2005Evaluation.pdf:PDF},
keywords = {Algorithms, Cell Nucleus, Cytoplasm, Databases, Genetic Vectors, Humans,
Internet, Mitochondria, Models, Non-U.S. Gov't, Peptides, Protein,
Proteins, Proteomics, Reproducibility of Results, Research Support,
Software, Theoretical, 15647112},
pii = {1471-2105-6-7},
url = {http://dx.doi.org/10.1186/1471-2105-6-7}
}
@article{Ballesteros2001G,
author = {J. Ballesteros and K. Palczewski},
title = {G protein-coupled receptor drug discovery: implications from the
crystal structure of rhodopsin.},
journal = {Curr. Opin. Drug Discov. Devel.},
year = {2001},
volume = {4},
pages = {561--574},
number = {5},
month = {Sep},
abstract = {G protein-coupled receptors (GPCRs) are a functionally diverse group
of membrane proteins that play a critical role in signal transduction.
Because of the lack of a high-resolution structure, the heptahelical
transmembrane bundle within the N-terminal extracellular and C-terminal
intracellular region of these receptors has initially been modeled
based on the high-resolution structure of bacterial retinal-binding
protein, bacteriorhodopsin. However, the low-resolution structure
of rhodopsin, a prototypical GPCR, revealed that there is a minor
relationship between GPCRs and bacteriorhodopsins. The high-resolution
crystal structure of the rhodopsin ground state and further refinements
of the model provide the first structural information about the entire
organization of the polypeptide chain and post-translational moieties.
These studies provide a structural template for Family 1 GPCRs that
has the potential to significantly improve structure-based approaches
to GPCR drug discovery.},
keywords = {Amino Acid Sequence; Animals; Crystallography, X-Ray; Drug Design;
GTP-Binding Proteins; Humans; Models, Molecular; Molecular Sequence
Data; Receptors, Drug; Rhodopsin},
owner = {laurent},
pmid = {12825452},
timestamp = {2007.09.22}
}
@article{Bantscheff2007Quantitative,
author = {Marcus Bantscheff and Markus Schirle and Gavain Sweetman and Jens
Rick and Bernhard Kuster},
title = {Quantitative mass spectrometry in proteomics: a critical review.},
journal = {Anal Bioanal Chem},
year = {2007},
volume = {389},
pages = {1017--1031},
number = {4},
month = {Oct},
abstract = {The quantification of differences between two or more physiological
states of a biological system is among the most important but also
most challenging technical tasks in proteomics. In addition to the
classical methods of differential protein gel or blot staining by
dyes and fluorophores, mass-spectrometry-based quantification methods
have gained increasing popularity over the past five years. Most
of these methods employ differential stable isotope labeling to create
a specific mass tag that can be recognized by a mass spectrometer
and at the same time provide the basis for quantification. These
mass tags can be introduced into proteins or peptides (i) metabolically,
(ii) by chemical means, (iii) enzymatically, or (iv) provided by
spiked synthetic peptide standards. In contrast, label-free quantification
approaches aim to correlate the mass spectrometric signal of intact
proteolytic peptides or the number of peptide sequencing events with
the relative or absolute protein quantity directly. In this review,
we critically examine the more commonly used quantitative mass spectrometry
methods for their individual merits and discuss challenges in arriving
at meaningful interpretations of quantitative proteomic data.},
doi = {10.1007/s00216-007-1486-6},
institution = {Cellzome AG, Meyerhofstrasse 1, 69254, Heidelberg, Germany.},
keywords = {Automatic Data Processing; Isotope Labeling; Mass Spectrometry; Peptides;
Proteins; Proteome; Proteomics; Reference Standards},
owner = {phupe},
pmid = {17668192},
timestamp = {2010.08.13},
url = {http://dx.doi.org/10.1007/s00216-007-1486-6}
}
@article{Baumgartner2004Supervised,
author = {Baumgartner, C. and Bohm, C. and Baumgartner, D. and Marini, G. and
Weinberger, K. and Olgemoller, B. and Liebl, B. and Roscher, A. A.},
title = {Supervised machine learning techniques for the classification of
metabolic disorders in newborns},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {2985-2996},
number = {17},
abstract = {Motivation: {D}uring the {B}avarian newborn screening programme all
newborns have been tested for about 20 inherited metabolic disorders.
{O}wing to the amount and complexity of the generated experimental
data, machine learning techniques provide a promising approach to
investigate novel patterns in high-dimensional metabolic data which
form the source for constructing classification rules with high discriminatory
power. {R}esults: {S}ix machine learning techniques have been investigated
for their classification accuracy focusing on two metabolic disorders,
phenylketo nuria ({PKU}) and medium-chain acyl-{C}o{A} dehydrogenase
deficiency ({MCADD}). {L}ogistic regression analysis led to superior
classification rules (sensitivity >96.8%, specificity >99.98%) compared
to all investigated algorithms. {I}ncluding novel constellations
of metabolites into the models, the positive predictive value could
be strongly increased ({PKU} 71.9% versus 16.2%, {MCADD} 88.4% versus
54.6% compared to the established diagnostic markers). {O}ur results
clearly prove that the mined data confirm the known and indicate
some novel metabolic patterns which may contribute to a better understanding
of newborn metabolism. {A}vailability: {WEKA} machine learning package:
www.cs.waikato.ac.nz/~ml/weka and statistical software package {ADE}-4:
http://pbil.univ-lyon1.fr/{ADE}-4},
doi = {10.1093/bioinformatics/bth343},
pdf = {../local/Baumgartner2004Supervised.pdf},
file = {Baumgartner2004Supervised.pdf:local/Baumgartner2004Supervised.pdf:PDF},
keywords = {biosvm proteomics},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/20/17/2985}
}
@article{Begg2005Support,
author = {Rezaul K Begg and Marimuthu Palaniswami and Brendan Owen},
title = {Support vector machines for automated gait classification.},
journal = {I{EEE} {T}rans {B}iomed {E}ng},
year = {2005},
volume = {52},
pages = {828-38},
number = {5},
month = {May},
abstract = {Ageing influences gait patterns causing constant threats to control
of locomotor balance. {A}utomated recognition of gait changes has
many advantages including, early identification of at-risk gait and
monitoring the progress of treatment outcomes. {I}n this paper, we
apply an artificial intelligence technique [support vector machines
({SVM})] for the automatic recognition of young-old gait types from
their respective gait-patterns. {M}inimum foot clearance ({MFC})
data of 30 young and 28 elderly participants were analyzed using
a {PEAK}-2{D} motion analysis system during a 20-min continuous walk
on a treadmill at self-selected walking speed. {G}ait features extracted
from individual {MFC} histogram-plot and {P}oincaré-plot images
were used to train the {SVM}. {C}ross-validation test results indicate
that the generalization performance of the {SVM} was on average 83.3\%
(+/-2.9) to recognize young and elderly gait patterns, compared to
a neural network's accuracy of 75.0+/-5.0\%. {A} "hill-climbing"
feature selection algorithm demonstrated that a small subset (3-5)
of gait features extracted from {MFC} plots could differentiate the
gait patterns with 90\% accuracy. {P}erformance of the gait classifier
was evaluated using areas under the receiver operating characteristic
plots. {I}mproved performance of the classifier was evident when
trained with reduced number of selected good features and with radial
basis function kernel. {T}hese results suggest that {SVM}s can function
as an efficient gait classifier for recognition of young and elderly
gait patterns, and has the potential for wider applications in gait
identification for falls-risk minimization in the elderly.},
doi = {10.1109/TBME.2005.845241},
pdf = {../local/Begg2005Support.pdf},
file = {Begg2005Support.pdf:local/Begg2005Support.pdf:PDF},
keywords = {Adult, Aged, Aging, Algorithms, Apoptosis, Artificial Intelligence,
Automated, Computer-Assisted, Female, Foot, Gait, Gene Expression
Profiling, Humans, Image Interpretation, Male, Neoplasms, Non-U.S.
Gov't, Oligonucleotide Array Sequence Analysis, Pattern Recognition,
Polymerase Chain Reaction, Proteins, Reproducibility of Results,
Research Support, Sensitivity and Specificity, Subcellular Fractions,
Unknown Primary, 15887532},
url = {http://dx.doi.org/10.1109/TBME.2005.845241}
}
@article{Bern2004Automatic,
author = {Bern, M. and Goldberg, D. and McDonald, W. H. and Yates, J. R., III},
title = {Automatic {Q}uality {A}ssessment of {P}eptide {T}andem {M}ass {S}pectra},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {i49-i54},
number = {Suppl. 1},
abstract = {Motivation: {A} powerful proteomics methodology couples high-performance
liquid chromatography ({HPLC}) with tandem mass spectrometry and
database-search software, such as {SEQUEST}. {S}uch a set-up, however,
produces a large number of spectra, many of which are of too poor
quality to be useful. {H}ence a filter that eliminates poor spectra
before the database search can significantly improve throughput and
robustness. {M}oreover, spectra judged to be of high quality, but
that cannot be identified by database search, are prime candidates
for still more computationally intensive methods, such as de novo
sequencing or wider database searches including post-translational
modifications. {R}esults: {W}e report on two different approaches
to assessing spectral quality prior to identification: binary classification,
which predicts whether or not {SEQUEST} will be able to make an identification,
and statistical regression, which predicts a more universal quality
metric involving the number of b- and y-ion peaks. {T}he best of
our binary classifiers can eliminate over 75% of the unidentifiable
spectra while losing only 10% of the identifiable spectra. {S}tatistical
regression can pick out spectra of modified peptides that can be
identified by a de novo program but not by {SEQUEST}. {I}n a section
of independent interest, we discuss intensity normalization of mass
spectra.},
pdf = {../local/Bern2004Automatic.pdf},
file = {Bern2004Automatic.pdf:local/Bern2004Automatic.pdf:PDF},
keywords = {biosvm proteomics},
owner = {jeanphilippevert},
url = {http://bioinformatics.oupjournals.org/cgi/content/abstract/20/suppl_1/i49}
}
@article{Bernardo2005Chemogenomica,
author = {di Bernardo, D. and Thompson, M.J. and Gardner, T.S. and Chobot,
S.E. and Eastwood, E.L. and Wojtovich, A.P. and Elliott, S.J. and
Schaus, S.E. and Collins, J.J.},
title = {Chemogenomic profiling on a genome-wide scale using reverse-engineered
gene networks.},
journal = {Nat Biotechnol},
year = {2005},
volume = {23},
pages = {377--383},
number = {3},
month = {Mar},
abstract = {A major challenge in drug discovery is to distinguish the molecular
targets of a bioactive compound from the hundreds to thousands of
additional gene products that respond indirectly to changes in the
activity of the targets. Here, we present an integrated computational-experimental
approach for computing the likelihood that gene products and associated
pathways are targets of a compound. This is achieved by filtering
the mRNA expression profile of compound-exposed cells using a reverse-engineered
model of the cell's gene regulatory network. We apply the method
to a set of 515 whole-genome yeast expression profiles resulting
from a variety of treatments (compounds, knockouts and induced expression),
and correctly enrich for the known targets and associated pathways
in the majority of compounds examined. We demonstrate our approach
with PTSB, a growth inhibitory compound with a previously unknown
mode of action, by predicting and validating thioredoxin and thioredoxin
reductase as its target.},
doi = {10.1038/nbt1075},
institution = {Telethon Institute for Genetics and Medicine, Naples, Italy.},
keywords = {Algorithms; Artificial Intelligence; Computer Simulation; Drug Delivery
Systems; Drug Design; Gene Expression Profiling; Gene Expression
Regulation; Models, Biological; Models, Statistical; Protein Engineering;
Protein Interaction Mapping; Saccharomyces cerevisiae; Saccharomyces
cerevisiae Proteins; Signal Transduction; Thioredoxin-Disulfide Reductase;
Thioredoxins},
owner = {fantine},
pii = {nbt1075},
pmid = {15765094},
timestamp = {2010.10.21},
url = {http://dx.doi.org/10.1038/nbt1075}
}
@article{Bernstein1977Protein,
author = {F. C. Bernstein and T. F. Koetzle and G. J. Williams and E. F. Meyer
and M. D. Brice and J. R. Rodgers and O. Kennard and T. Shimanouchi
and M. Tasumi},
title = {The Protein Data Bank: a computer-based archival file for macromolecular
structures.},
journal = {J. Mol. Biol.},
year = {1977},
volume = {112},
pages = {535--542},
number = {3},
month = {May},
keywords = {Computers; Great Britain; Information Systems; Japan; Protein Conformation;
Proteins; United States},
owner = {bricehoffmann},
pmid = {875032},
timestamp = {2009.02.13}
}
@article{Bhasin2003MHCBN,
author = {Manoj Bhasin and Harpreet Singh and G. P S Raghava},
title = {{MHCBN}: a comprehensive database of {MHC} binding and non-binding
peptides.},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {665--666},
number = {5},
month = {Mar},
abstract = {MHCBN is a comprehensive database of Major Histocompatibility Complex
(MHC) binding and non-binding peptides compiled from published literature
and existing databases. The latest version of the database has 19
777 entries including 17 129 MHC binders and 2648 MHC non-binders
for more than 400 MHC molecules. The database has sequence and structure
data of (a) source proteins of peptides and (b) MHC molecules. MHCBN
has a number of web tools that include: (i) mapping of peptide on
query sequence; (ii) search on any field; (iii) creation of data
sets; and (iv) online data submission. The database also provides
hypertext links to major databases like SWISS-PROT, PDB, IMGT/HLA-DB,
GenBank and PUBMED.},
keywords = {Amino Acid Sequence; Binding Sites; Database Management Systems; Databases,
Protein; Histocompatibility Antigens; Information Storage and Retrieval;
Macromolecular Substances; Major Histocompatibility Complex; Molecular
Sequence Data; Peptide Fragments; Peptides; Protein Binding; Protein
Conformation; Sequence Alignment; Sequence Analysis, Protein; Structure-Activity
Relationship; User-Computer Interface},
owner = {laurent},
pmid = {12651731},
timestamp = {2007.01.30}
}
@article{Bhavani2006Substructure-based,
author = {S. Bhavani and A. Nagargadde and A. Thawani and V. Sridhar and N.
Chandra},
title = {Substructure-based support vector machine classifiers for prediction
of adverse effects in diverse classes of drugs.},
journal = {J. Chem. Inform. Model.},
year = {2006},
volume = {46},
pages = {2478--2486},
number = {6},
abstract = {Unforeseen adverse effects exhibited by drugs contribute heavily to
late-phase failure and even withdrawal of marketed drugs. Torsade
de pointes (TdP) is one such important adverse effect, which causes
cardiac arrhythmia and, in some cases, sudden death, making it crucial
for potential drugs to be screened for torsadogenicity. The need
to tap the power of computational approaches for the prediction of
adverse effects such as TdP is increasingly becoming evident. The
availability of screening data including those in organized databases
greatly facilitates exploration of newer computational approaches.
In this paper, we report the development of a prediction method based
on a support machine vector algorithm. The method uses a combination
of descriptors, encoding both the type of toxicophore as well as
the position of the toxicophore in the drug molecule, thus considering
both the pharmacophore and the three-dimensional shape information
of the molecule. For delineating toxicophores, a novel pattern-recognition
method that utilizes substructures within a molecule has been developed.
The results obtained using the hybrid approach have been compared
with those available in the literature for the same data set. An
improvement in prediction accuracy is clearly seen, with the accuracy
reaching up to 97\% in predicting compounds that can cause TdP and
90\% for predicting compounds that do not cause TdP. The generic
nature of the method has been demonstrated with four data sets available
for carcinogenicity, where prediction accuracies were significantly
higher, with a best receiver operating characteristics (ROC) value
of 0.81 as against a best ROC value of 0.7 reported in the literature
for the same data set. Thus, the method holds promise for wide applicability
in toxicity prediction.},
doi = {10.1021/ci060128l},
keywords = {Algorithms; Carcinogens; Chemistry, Pharmaceutical; Computational
Biology; Drug Evaluation, Preclinical; Drug Industry; Humans; Models,
Chemical; Models, Statistical; Neural Networks (Computer); Pattern
Recognition, Automated; ROC Curve; Sequence Analysis, Protein; Software;
Torsades de Pointes},
owner = {laurent},
pmid = {17125188},
timestamp = {2007.09.18},
url = {http://dx.doi.org/10.1021/ci060128l}
}
@article{Bleicher2003Hit,
author = {K. H. Bleicher and H.-J. B{\"o}hm and K. M{\"u}ller and A. I. Alanine},
title = {{H}it and lead generation: beyond high-throughput screening.},
journal = {Nat Rev Drug Discov},
year = {2003},
volume = {2},
pages = {369--378},
number = {5},
month = {May},
abstract = {The identification of small-molecule modulators of protein function,
and the process of transforming these into high-content lead series,
are key activities in modern drug discovery. The decisions taken
during this process have far-reaching consequences for success later
in lead optimization and even more crucially in clinical development.
Recently, there has been an increased focus on these activities due
to escalating downstream costs resulting from high clinical failure
rates. In addition, the vast emerging opportunities from efforts
in functional genomics and proteomics demands a departure from the
linear process of identification, evaluation and refinement activities
towards a more integrated parallel process. This calls for flexible,
fast and cost-effective strategies to meet the demands of producing
high-content lead series with improved prospects for clinical success.},
doi = {10.1038/nrd1086},
keywords = {Amino Acid Motifs, Combinatorial Chemistry Techniques, Drug Design,
Drug Evaluation, Genomics, Preclinical, Proteomics, 12750740},
owner = {mahe},
pii = {nrd1086},
pmid = {12750740},
timestamp = {2006.08.15},
url = {http://dx.doi.org/10.1038/nrd1086}
}
@article{Bock2007Effective,
author = {Mary Ellen Bock and Claudio Garutti and Conettina Guerra},
title = {Effective labeling of molecular surface points for cavity detection
and location of putative binding sites.},
journal = {Comput Syst Bioinformatics Conf},
year = {2007},
volume = {6},
pages = {263--274},
abstract = {We present a method for detecting and comparing cavities on protein
surfaces that is useful for protein binding site recognition. The
method is based on a representation of the protein structures by
a collection of spin-images and their associated spin-image profiles.
Results of the cavity detection procedure are presented for a large
set of non-redundant proteins and compared with SURFNET-ConSurf.
Our comparison method is used to find a surface region in one cavity
of a protein that is geometrically similar to a surface region in
the cavity of another protein. Such a finding would be an indication
that the two regions likely bind to the same ligand. Our overall
approach for cavity detection and comparison is benchmarked on several
pairs of known complexes, obtaining a good coverage of the atoms
of the binding sites.},
institution = {Department of Statistics, Purdue University 150 N. University Street,
West Lafayette, IN 47907-2067, USA. mbock@purdue.edu},
keywords = {Binding Sites; Computer Simulation; Models, Chemical; Models, Molecular;
Protein Binding; Protein Conformation; Protein Folding; Proteins,
chemistry/ultrastructure; Sequence Analysis, Protein, methods; Surface
Properties},
owner = {bricehoffmann},
pii = {9781860948732_0028},
pmid = {17951830},
timestamp = {2009.02.13}
}
@article{Bostroem2001Reproducing,
author = {J. Bostr\"om},
title = {Reproducing the conformations of protein-bound ligands: a critical
evaluation of several popular conformational searching tools.},
journal = {J Comput Aided Mol Des},
year = {2001},
volume = {15},
pages = {1137--1152},
number = {12},
month = {Dec},
abstract = {Several programs (Catalyst, Confort, Flo99, MacroModel, and Omega)
that are commonly used to generate conformational ensembles have
been tested for their ability to reproduce bioactive conformations.
The ligands from thirty-two different ligand-protein complexes determined
by high-resolution (< 2.0 A) X-ray crystallography have been analyzed.
The Low-Mode Conformational Search method (with AMBER* and the GB/SA
hydration model), as implemented in MacroModel, was found to perform
better than the other algorithms. The rule-based method Omega, which
is orders of magnitude faster than the other methods, also gave reasonable
results but were found to be dependent on the input structure. The
methods supporting diverse sampling (Catalyst, Confort) performed
least well. For the seven ligands in the set having eight or more
rotatable bonds, none of the bioactive conformations were ever found,
save for one exception (Flo99). These ligands do not bind in a local
minimum conformation according to AMBER*\GB/SA. Taking these last
two observations together, it is clear that geometrically similar
structures should be collected in order to increase the probability
of finding the bioactive conformation among the generated ensembles.
Factors influencing bioactive conformational retrieval have been
identified and are discussed.},
keywords = {Algorithms; Crystallography, X-Ray; Ligands; Models, Molecular; Molecular
Conformation; Protein Binding; Quantum Theory; Software},
owner = {laurent},
pmid = {12160095},
timestamp = {2008.01.16}
}
@article{Bowd2002Comparing,
author = {Christopher Bowd and Kwokleung Chan and Linda M Zangwill and Michael
H Goldbaum and Te-Won Lee and Terrence J Sejnowski and Robert N Weinreb},
title = {Comparing neural networks and linear discriminant functions for glaucoma
detection using confocal scanning laser ophthalmoscopy of the optic
disc.},
journal = {Invest {O}phthalmol {V}is {S}ci},
year = {2002},
volume = {43},
pages = {3444-54},
number = {11},
month = {Nov},
abstract = {P{URPOSE}: {T}o determine whether neural network techniques can improve
differentiation between glaucomatous and nonglaucomatous eyes, using
the optic disc topography parameters of the {H}eidelberg {R}etina
{T}omograph ({HRT}; {H}eidelberg {E}ngineering, {H}eidelberg, {G}ermany).
{METHODS}: {W}ith the {HRT}, one eye was imaged from each of 108
patients with glaucoma (defined as having repeatable visual field
defects with standard automated perimetry) and 189 subjects without
glaucoma (no visual field defects with healthy-appearing optic disc
and retinal nerve fiber layer on clinical examination) and the optic
nerve topography was defined by 17 global and 66 regional {HRT} parameters.
{W}ith all the {HRT} parameters used as input, receiver operating
characteristic ({ROC}) curves were generated for the classification
of eyes, by three neural network techniques: linear and {G}aussian
support vector machines ({SVM} linear and {SVM} {G}aussian, respectively)
and a multilayer perceptron ({MLP}), as well as four previously proposed
linear discriminant functions ({LDF}s) and one {LDF} developed on
the current data with all {HRT} parameters used as input. {RESULTS}:
{T}he areas under the {ROC} curves for {SVM} linear and {SVM} {G}aussian
were 0.938 and 0.945, respectively; for {MLP}, 0.941; for the current
{LDF}, 0.906; and for the best previously proposed {LDF}, 0.890.
{W}ith the use of forward selection and backward elimination optimization
techniques, the areas under the {ROC} curves for {SVM} {G}aussian
and the current {LDF} were increased to approximately 0.96. {CONCLUSIONS}:
{T}rained neural networks, with global and regional {HRT} parameters
used as input, improve on previously proposed {HRT} parameter-based
{LDF}s for discriminating between glaucomatous and nonglaucomatous
eyes. {T}he performance of both neural networks and {LDF}s can be
improved with optimization of the features in the input. {N}eural
network analyses show promise for increasing diagnostic accuracy
of tests for glaucoma.},
pdf = {../local/Bowd2002Comparing.pdf},
file = {Bowd2002Comparing.pdf:local/Bowd2002Comparing.pdf:PDF},
keywords = {Acute, Algorithms, Animals, Anion Exchange Resins, Artificial Intelligence,
Automated, Base Pair Mismatch, Base Pairing, Base Sequence, Biological,
Biosensing Techniques, Carcinoma, Chemical, Chromatography, Citric
Acid Cycle, Classification, Cluster Analysis, Comparative Study,
Computational Biology, Computer-Assisted, Cystadenoma, DNA, Databases,
Decision Making, Diagnosis, Differential, Discriminant Analysis,
Drug, Drug Design, Electrostatics, Eukaryotic Cells, Factual, Feasibility
Studies, Female, Gene Expression, Gene Expression Profiling, Gene
Expression Regulation, Genes, Genetic, Genetic Heterogeneity, Genetic
Markers, Glaucoma, Hemolysins, Humans, Internet, Intraocular Pressure,
Ion Exchange, Lasers, Leukemia, Ligands, Likelihood Functions, Logistic
Models, Lung Neoplasms, Lymphocytic, Lymphoma, Markov Chains, Mathematics,
Messenger, Models, Molecular, Molecular Probe Techniques, Molecular
Sequence Data, Nanotechnology, Neoplasm, Neoplasms, Neoplastic, Neural
Networks (Computer), Non-P.H.S., Non-Small-Cell Lung, Non-U.S. Gov't,
Nucleic Acid Conformation, Nucleic Acid Hybridization, Observer Variation,
Oligonucleotide Array Sequence Analysis, Open-Angle, Ophthalmoscopy,
Optic Disk, Ovarian Neoplasms, P.H.S., Pattern Recognition, Probability,
Probability Learning, Protein Binding, Protein Conformation, Proteins,
Quality Control, Quantum Theory, RNA, RNA Splicing, ROC Curve, Receptors,
Reference Values, Regression Analysis, Reproducibility of Results,
Research Support, Robotics, Saccharomyces cerevisiae Proteins, Sensitivity
and Specificity, Sequence Analysis, Signal Processing, Software,
Statistical, Stomach Neoplasms, Structural, Structure-Activity Relationship,
Thermodynamics, Transcription, Tumor Markers, U.S. Gov't, 12407155},
url = {http://www.iovs.org/cgi/content/abstract/43/11/3444}
}
@article{Bowd2004Confocal,
author = {Christopher Bowd and Linda M Zangwill and Felipe A Medeiros and Jiucang
Hao and Kwokleung Chan and Te-Won Lee and Terrence J Sejnowski and
Michael H Goldbaum and Pamela A Sample and Jonathan G Crowston and
Robert N Weinreb},
title = {Confocal scanning laser ophthalmoscopy classifiers and stereophotograph
evaluation for prediction of visual field abnormalities in glaucoma-suspect
eyes.},
journal = {Invest {O}phthalmol {V}is {S}ci},
year = {2004},
volume = {45},
pages = {2255-62},
number = {7},
month = {Jul},
abstract = {P{URPOSE}: {T}o determine whether {H}eidelberg {R}etina {T}omograph
({HRT}; {H}eidelberg {E}ngineering, {D}ossenheim, {G}ermany) classification
techniques and investigational support vector machine ({SVM}) analyses
can detect optic disc abnormalities in glaucoma-suspect eyes before
the development of visual field abnormalities. {METHODS}: {G}laucoma-suspect
eyes (n = 226) were classified as converts or nonconverts based on
the development of repeatable (either two or three consecutive) standard
automated perimetry ({SAP})-detected abnormalities over the course
of the study (mean follow-up, approximately 4.5 years). {H}azard
ratios for development of {SAP} abnormalities were calculated based
on baseline classification results, follow-up time, and end point
status (convert, nonconvert). {C}lassification techniques applied
were {HRT} classification ({HRTC}), {M}oorfields {R}egression {A}nalysis,
forward-selection optimized {SVM} ({SVM} fwd) and backward elimination-optimized
{SVM} ({SVM} back) analysis of {HRT} data, and stereophotograph assessment.
{RESULTS}: {U}nivariate analyses indicated that all classification
techniques were predictors of the development of two repeatable abnormal
{SAP} results, with hazards ratios (95\% confidence interval [{CI}])
ranging from 1.32 (1.00-1.75) for {HRTC} to 2.0 (1.48-2.76) for stereophotograph
assessment (all {P} < or = 0.05). {O}nly {SVM} ({SVM} fwd and {SVM}
back) analysis of {HRT} data and stereophotograph assessment were
univariate predictors of the development of three repeatable abnormal
{SAP} results, with hazard ratios (95\% {CI}) ranging from 1.73 (1.16-2.82)
for {SVM} fwd to 1.82 (1.19-3.12) for {SVM} back (both {P} < 0.007).
{M}ultivariate analyses including each classification technique individually
in a model with age, baseline {SAP} pattern standard deviation [{PSD}],
and baseline {IOP} indicated that all classification techniques except
{HRTC} ({P} = 0.06) were predictors of the development of two repeatable
abnormal {SAP} results with hazards ratios ranging from 1.30 (0.99,
1.73) for {HRTC} to 1.90 (1.37, 2.69) for stereophotograph assessment.
{O}nly {SVM} ({SVM} fwd and {SVM} back) analysis of {HRT} data and
stereophotograph assessment were significant predictors of the development
of three repeatable abnormal {SAP} results in multivariate analyses;
hazard ratios of 1.57 (1.03, 2.59) and 1.70 (1.18, 2.51), respectively.
{SAP} {PSD} was a significant predictor of two repeatable abnormal
{SAP} results in multivariate models with all classification techniques,
with hazard ratios ranging from 3.31 (1.39, 7.89) to 4.70 (2.02,
10.93) per 1-d{B} increase. {CONCLUSIONS}: {HRT} classifications
techniques and stereophotograph assessment can detect optic disc
topography abnormalities in glaucoma-suspect eyes before the development
of {SAP} abnormalities. {T}hese data support strongly the importance
of optic disc examination for early glaucoma diagnosis.},
doi = {10.1167/iovs.03-1087},
pdf = {../local/Bowd2004Confocal.pdf},
file = {Bowd2004Confocal.pdf:local/Bowd2004Confocal.pdf:PDF},
keywords = {80 and over, Adolescent, Adult, Aged, Algorithms, Artificial Intelligence,
Auditory, Benchmarking, Binding Sites, Brain Stem, Breast Diseases,
Chemical, Child, Chromosomes, Comparative Study, Computational Biology,
Computer Simulation, Computer-Assisted, Data Interpretation, Databases,
Diagnosis, Diagnostic Errors, Differential, Drug Resistance, Electroencephalography,
Epilepsy, Evoked Potentials, Female, Forecasting, Gene Expression,
Gene Expression Profiling, Genetic, Genotype, Glaucoma, Greece, HIV
Protease Inhibitors, HIV-1, Human, Humans, Infant, Information Management,
Information Storage and Retrieval, Intraocular Pressure, Kinetics,
Language Development Disorders, Lasers, Least-Squares Analysis, Linear
Models, Male, Microbial Sensitivity Tests, Middle Aged, Models, Molecular,
Monitoring, Nephroblastoma, Non-U.S. Gov't, Nonlinear Dynamics, Ocular
Hypertension, Oligonucleotide Array Sequence Analysis, Ophthalmoscopy,
Optic Disk, Optic Nerve Diseases, P.H.S., Pair 1, Perimetry, Periodicals,
Phosphorylation, Phosphotransferases, Photography, Physiologic, Point
Mutation, Preschool, Prognosis, Protein, Proteins, Pyrimidinones,
Reaction Time, Recurrence, Reproducibility of Results, Research Support,
Reverse Transcriptase Inhibitors, Sensitivity and Specificity, Sequence
Alignment, Sequence Analysis, Signal Processing, Software, Sound
Localization, Statistical, Stochastic Processes, Structure-Activity
Relationship, Theoretical, Time Factors, U.S. Gov't, Viral, Vision
Disorders, Visual Fields, 15223803},
url = {http://dx.doi.org/10.1167/iovs.03-1087}
}
@article{Briggs2001Histone,
author = {S. D. Briggs and M. Bryk and B. D. Strahl and W. L. Cheung and J.
K. Davie and S. Y. Dent and F. Winston and C. D. Allis},
title = {Histone H3 lysine 4 methylation is mediated by Set1 and required
for cell growth and rDNA silencing in Saccharomyces cerevisiae.},
journal = {Genes Dev},
year = {2001},
volume = {15},
pages = {3286--3295},
number = {24},
month = {Dec},
abstract = {Histone methylation is known to be associated with both transcriptionally
active and repressive chromatin states. Recent studies have identified
SET domain-containing proteins such as SUV39H1 and Clr4 as mediators
of H3 lysine 9 (Lys9) methylation and heterochromatin formation.
Interestingly, H3 Lys9 methylation is not observed from bulk histones
isolated from asynchronous populations of Saccharomyces cerevisiae
or Tetrahymena thermophila. In contrast, H3 lysine 4 (Lys4) methylation
is a predominant modification in these smaller eukaryotes. To identify
the responsible methyltransferase(s) and to gain insight into the
function of H3 Lys4 methylation, we have developed a histone H3 Lys4
methyl-specific antiserum. With this antiserum, we show that deletion
of SET1, but not of other putative SET domain-containing genes, in
S. cerevisiae, results in the complete abolishment of H3 Lys4 methylation
in vivo. Furthermore, loss of H3 Lys4 methylation in a set1 Delta
strain can be rescued by SET1. Analysis of histone H3 mutations at
Lys4 revealed a slow-growth defect similar to a set1 Delta strain.
Chromatin immunoprecipitation assays show that H3 Lys4 methylation
is present at the rDNA locus and that Set1-mediated H3 Lys4 methylation
is required for repression of RNA polymerase II transcription within
rDNA. Taken together, these data suggest that Set1-mediated H3 Lys4
methylation is required for normal cell growth and transcriptional
silencing.},
doi = {10.1101/gad.940201},
institution = {Department of Biochemistry and Molecular Genetics, University of
Virginia Health System, Charlottesville, Virginia 22908, USA.},
keywords = {Animals; Antibody Formation; Blotting, Western; Cell Division; DNA
Primers, chemistry; DNA, Bacterial, genetics; DNA, Ribosomal, genetics;
DNA-Binding Proteins, metabolism; Fungal Proteins, metabolism; Gene
Silencing; Genetic Vectors; Heterochromatin, chemistry/metabolism;
Histone-Lysine N-Methyltransferase; Histones, metabolism; Lysine,
metabolism; Methylation; Methyltransferases, genetics/metabolism;
Mutation; Nucleosomes, chemistry/metabolism; Polymerase Chain Reaction;
Precipitin Tests; Protein Methyltransferases; RNA Polymerase III,
metabolism; Rabbits; Saccharomyces cerevisiae Proteins; Saccharomyces
cerevisiae, genetics; Transcription Factors, metabolism},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pmid = {11751634},
timestamp = {2010.11.23},
url = {http://dx.doi.org/10.1101/gad.940201}
}
@article{Briggs2002Gene,
author = {Scott D Briggs and Tiaojiang Xiao and Zu-Wen Sun and Jennifer A Caldwell
and Jeffrey Shabanowitz and Donald F Hunt and C. David Allis and
Brian D Strahl},
title = {Gene silencing: trans-histone regulatory pathway in chromatin.},
journal = {Nature},
year = {2002},
volume = {418},
pages = {498},
number = {6897},
month = {Aug},
abstract = {The fundamental unit of eukaryotic chromatin, the nucleosome, consists
of genomic DNA wrapped around the conserved histone proteins H3,
H2B, H2A and H4, all of which are variously modified at their amino-
and carboxy-terminal tails to influence the dynamics of chromatin
structure and function -- for example, conjugation of histone H2B
with ubiquitin controls the outcome of methylation at a specific
lysine residue (Lys 4) on histone H3, which regulates gene silencing
in the yeast Saccharomyces cerevisiae. Here we show that ubiquitination
of H2B is also necessary for the methylation of Lys 79 in H3, the
only modification known to occur away from the histone tails, but
that not all methylated lysines in H3 are regulated by this 'trans-histone'
pathway because the methylation of Lys 36 in H3 is unaffected. Given
that gene silencing is regulated by the methylation of Lys 4 and
Lys 79 in histone H3, we suggest that H2B ubiquitination acts as
a master switch that controls the site-selective histone methylation
patterns responsible for this silencing.},
doi = {10.1038/nature00970},
institution = {Department of Biochemistry and Molecular Genetics, University of
Virginia Health System, Charlottesville, Virginia 22908, USA.},
keywords = {Chromatin, chemistry/metabolism; Gene Expression Regulation, Fungal;
Gene Silencing; Histone-Lysine N-Methyltransferase; Histones, chemistry/metabolism;
Ligases, metabolism; Methylation; Models, Biological; Nuclear Proteins,
metabolism; Saccharomyces cerevisiae Proteins; Saccharomyces cerevisiae,
genetics/metabolism; Ubiquitin, metabolism; Ubiquitin-Conjugating
Enzymes},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {nature00970},
pmid = {12152067},
timestamp = {2010.11.23},
url = {http://dx.doi.org/10.1038/nature00970}
}
@article{Brusic2002Prediction,
author = {Brusic, V. and Petrovsky, N. and Zhang, G. and Bajic, V. B.},
title = {{P}rediction of promiscuous peptides that bind {HLA} class {I} molecules.},
journal = {Immunol. Cell Biol.},
year = {2002},
volume = {80},
pages = {280--285},
number = {3},
month = {Jun},
abstract = {Promiscuous T-cell epitopes make ideal targets for vaccine development.
We report here a computational system, MULTIPRED, for the prediction
of peptide binding to the HLA-A2 supertype. It combines a novel representation
of peptide/MHC interactions with a hidden Markov model as the prediction
algorithm. MULTIPREDis both sensitive and specific, and demonstrates
high accuracy of peptide-binding predictions for HLA-A*0201, *0204,
and *0205 alleles, good accuracy for *0206 allele, and marginal accuracy
for *0203 allele. MULTIPREDreplaces earlier requirements for individual
prediction models for each HLA allelic variant and simplifies computational
aspects of peptide-binding prediction. Preliminary testing indicates
that MULTIPRED can predict peptide binding to HLA-A2 supertype molecules
with high accuracy, including those allelic variants for which no
experimental binding data are currently available.},
keywords = {Algorithms, Amino Acid Motifs, Amino Acid Sequence, Antigen-Antibody
Complex, Automated, Binding Sites, Computational Biology, Drug Delivery
Systems, Drug Design, Epitopes, Forecasting, Genes, HLA Antigens,
HLA-A Antigens, HLA-A2 Antigen, HLA-DR Antigens, Humans, Internet,
MHC Class I, Markov Chains, Molecular Sequence Data, Neural Networks
(Computer), Pattern Recognition, Peptide Fragments, Peptides, Protein,
Protein Binding, Protein Interaction Mapping, Sensitivity and Specificity,
Sequence Analysis, Software, T-Lymphocyte, User-Computer Interface,
Viral Vaccines, 12067415},
pii = {1088},
pmid = {12067415},
timestamp = {2007.01.25}
}
@article{Bryk2002Evidence,
author = {Mary Bryk and Scott D Briggs and Brian D Strahl and M. Joan Curcio
and C. David Allis and Fred Winston},
title = {Evidence that Set1, a factor required for methylation of histone
H3, regulates rDNA silencing in S. cerevisiae by a Sir2-independent
mechanism.},
journal = {Curr Biol},
year = {2002},
volume = {12},
pages = {165--170},
number = {2},
month = {Jan},
abstract = {Several types of histone modifications have been shown to control
transcription. Recent evidence suggests that specific combinations
of these modifications determine particular transcription patterns.
The histone modifications most recently shown to play critical roles
in transcription are arginine-specific and lysine-specific methylation.
Lysine-specific histone methyltransferases all contain a SET domain,
a conserved 130 amino acid motif originally identified in polycomb-
and trithorax-group proteins from Drosophila. Members of the SU(VAR)3-9
family of SET-domain proteins methylate K9 of histone H3. Methylation
of H3 has also been shown to occur at K4. Several studies have suggested
a correlation between K4-methylated H3 and active transcription.
In this paper, we provide evidence that K4-methylated H3 is required
in a negative role, rDNA silencing in Saccharomyces cerevisiae. In
a screen for rDNA silencing mutants, we identified a mutation in
SET1, previously shown to regulate silencing at telomeres and HML.
Recent work has shown that Set1 is a member of a complex and is required
for methylation of K4 of H3 at several genomic locations. In addition,
we demonstrate that a K4R change in H3, which prevents K4 methylation,
impairs rDNA silencing, indicating that Set1 regulates rDNA silencing,
directly or indirectly, via H3 methylation. Furthermore, we present
several lines of evidence that the role of Set1 in rDNA silencing
is distinct from that of the histone deacetylase Sir2. Together,
these results suggest that Set1-dependent H3 methylation is required
for rDNA silencing in a Sir2-independent fashion.},
institution = {Department of Genetics, Harvard Medical School, 200 Longwood Avenue,
Boston, MA 02115, USA.},
keywords = {Acetylation; DNA Methylation; DNA, Ribosomal, genetics; DNA-Binding
Proteins, metabolism; Drosophila Proteins; Fungal Proteins, metabolism;
Gene Silencing; Histone Deacetylases, metabolism; Histone-Lysine
N-Methyltransferase; Histones, metabolism; Mutation; Saccharomyces
cerevisiae Proteins; Saccharomyces cerevisiae, metabolism; Silent
Information Regulator Proteins, Saccharomyces cerevisiae; Sirtuin
2; Sirtuins; Trans-Activators, metabolism; Transcription Factors,
metabolism},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {S0960982201006522},
pmid = {11818070},
timestamp = {2010.11.23}
}
@article{Bui2006Structural,
author = {Bui, H.-H. and Schiewe, A. J. and von Grafenstein, H. and Haworth,
I. S.},
title = {{S}tructural prediction of peptides binding to {MHC} class {I} molecules.},
journal = {Proteins},
year = {2006},
volume = {63},
pages = {43--52},
number = {1},
month = {Apr},
abstract = {Peptide binding to class I major histocompatibility complex (MHCI)
molecules is a key step in the immune response and the structural
details of this interaction are of importance in the design of peptide
vaccines. Algorithms based on primary sequence have had success in
predicting potential antigenic peptides for MHCI, but such algorithms
have limited accuracy and provide no structural information. Here,
we present an algorithm, PePSSI (peptide-MHC prediction of structure
through solvated interfaces), for the prediction of peptide structure
when bound to the MHCI molecule, HLA-A2. The algorithm combines sampling
of peptide backbone conformations and flexible movement of MHC side
chains and is unique among other prediction algorithms in its incorporation
of explicit water molecules at the peptide-MHC interface. In an initial
test of the algorithm, PePSSI was used to predict the conformation
of eight peptides bound to HLA-A2, for which X-ray data are available.
Comparison of the predicted and X-ray conformations of these peptides
gave RMSD values between 1.301 and 2.475 A. Binding conformations
of 266 peptides with known binding affinities for HLA-A2 were then
predicted using PePSSI. Structural analyses of these peptide-HLA-A2
conformations showed that peptide binding affinity is positively
correlated with the number of peptide-MHC contacts and negatively
correlated with the number of interfacial water molecules. These
results are consistent with the relatively hydrophobic binding nature
of the HLA-A2 peptide binding interface. In summary, PePSSI is capable
of rapid and accurate prediction of peptide-MHC binding conformations,
which may in turn allow estimation of MHCI-peptide binding affinity.},
doi = {10.1002/prot.20870},
keywords = {Algorithms, Amino Acid Sequence, Antigens, Artificial Intelligence,
Automated, Binding Sites, Chemical, Computational Biology, Computer
Simulation, Crystallog, Crystallography, Electrostatics, Genes, Genetic,
HLA Antigens, Histocompatibility Antigens Class I, Humans, Hydrogen
Bonding, Ligands, MHC Class I, Major Histocompatibility Complex,
Models, Molecular, Molecular Conformation, Molecular Sequence Data,
Pattern Recognition, Peptides, Protein, Protein Binding, Protein
Conformation, Proteomics, Quantitative Structure-Activity Relationship,
Sequence Alignment, Sequence Analysis, Software, Structural Homology,
Structure-Activity Relationship, Thermodynamics, Water, X-Ray, X-Rays,
raphy, 16447245},
pmid = {16447245},
timestamp = {2007.01.25},
url = {http://dx.doi.org/10.1002/prot.20870}
}
@article{Bui2005Automated,
author = {Huynh-Hoa Bui and John Sidney and Bjoern Peters and Muthuraman Sathiamurthy
and Asabe Sinichi and Kelly-Anne Purton and Bianca R Moth\'e and
Francis V Chisari and David I Watkins and Alessandro Sette},
title = {Automated generation and evaluation of specific MHC binding predictive
tools: ARB matrix applications.},
journal = {Immunogenetics},
year = {2005},
volume = {57},
pages = {304--314},
number = {5},
month = {Jun},
abstract = {Prediction of which peptides can bind major histocompatibility complex
(MHC) molecules is commonly used to assist in the identification
of T cell epitopes. However, because of the large numbers of different
MHC molecules of interest, each associated with different predictive
tools, tool generation and evaluation can be a very resource intensive
task. A methodology commonly used to predict MHC binding affinity
is the matrix or linear coefficients method. Herein, we described
Average Relative Binding (ARB) matrix methods that directly predict
IC(50) values allowing combination of searches involving different
peptide sizes and alleles into a single global prediction. A computer
program was developed to automate the generation and evaluation of
ARB predictive tools. Using an in-house MHC binding database, we
generated a total of 85 and 13 MHC class I and class II matrices,
respectively. Results from the automated evaluation of tool efficiency
are presented. We anticipate that this automation framework will
be generally applicable to the generation and evaluation of large
numbers of MHC predictive methods and tools, and will be of value
to centralize and rationalize the process of evaluation of MHC predictions.
MHC binding predictions based on ARB matrices were made available
at http://epitope.liai.org:8080/matrix web server.},
doi = {10.1007/s00251-005-0798-y},
keywords = {Animals; Binding Sites; Computer Simulation; Databases, Protein; Epitopes;
Histocompatibility Antigens; Humans; Major Histocompatibility Complex;
Models, Biological; Protein Binding},
owner = {laurent},
pmid = {15868141},
timestamp = {2007.07.12},
url = {http://dx.doi.org/10.1007/s00251-005-0798-y}
}
@article{Bulyk2006DNA,
author = {Martha L Bulyk},
title = {{DNA} microarray technologies for measuring protein-{DNA} interactions.},
journal = {Curr Opin Biotechnol},
year = {2006},
volume = {17},
pages = {422--430},
number = {4},
month = {Aug},
abstract = {DNA-binding proteins have key roles in many cellular processes, including
transcriptional regulation and replication. Microarray-based technologies
permit the high-throughput identification of binding sites and enable
the functional roles of these binding proteins to be elucidated.
In particular, microarray readout either of chromatin immunoprecipitated
DNA-bound proteins (ChIP-chip) or of DNA adenine methyltransferase
fusion proteins (DamID) enables the identification of in vivo genomic
target sites of proteins. A complementary approach to analyse the
in vitro binding of proteins directly to double-stranded DNA microarrays
(protein binding microarrays; PBMs), permits rapid characterization
of their DNA binding site sequence specificities. Recent advances
in DNA microarray synthesis technologies have facilitated the definition
of DNA-binding sites at much higher resolution and coverage, and
advances in these and emerging technologies will further increase
the efficiencies of these exciting new approaches.},
doi = {10.1016/j.copbio.2006.06.015},
institution = {Division of Genetics, Department of Medicine, Harvard/MIT Division
of Health Sciences and Technology (HST), Brigham and Women's Hospital
and Harvard Medical School, Boston, MA 02115, USA. mlbulyk@receptor.med.harvard.edu},
keywords = {Animals; Chromatin Immunoprecipitation, methods; Cross-Linking Reagents,
chemistry; DNA, analysis/chemistry/metabolism; DNA-Binding Proteins,
analysis/genetics/metabolism; Humans; Oligonucleotide Array Sequence
Analysis, methods; Protein Binding},
language = {eng},
medline-pst = {ppublish},
owner = {philippe},
pii = {S0958-1669(06)00099-1},
pmid = {16839757},
timestamp = {2010.08.05},
url = {http://dx.doi.org/10.1016/j.copbio.2006.06.015}
}
@article{Buus2003Sensitive,
author = {S. Buus and S. L. Lauem{\o}ller and P. Worning and C. Kesmir and
T. Frimurer and S. Corbet and A. Fomsgaard and J. Hilden and A. Holm
and S. Brunak},
title = {Sensitive quantitative predictions of peptide-{MHC} binding by a
'Query by Committee' artificial neural network approach.},
journal = {Tissue Antigens},
year = {2003},
volume = {62},
pages = {378--384},
number = {5},
month = {Nov},
abstract = {We have generated Artificial Neural Networks (ANN) capable of performing
sensitive, quantitative predictions of peptide binding to the MHC
class I molecule, HLA-A*0204. We have shown that such quantitative
ANN are superior to conventional classification ANN, that have been
trained to predict binding vs non-binding peptides. Furthermore,
quantitative ANN allowed a straightforward application of a 'Query
by Committee' (QBC) principle whereby particularly information-rich
peptides could be identified and subsequently tested experimentally.
Iterative training based on QBC-selected peptides considerably increased
the sensitivity without compromising the efficiency of the prediction.
This suggests a general, rational and unbiased approach to the development
of high quality predictions of epitopes restricted to this and other
HLA molecules. Due to their quantitative nature, such predictions
will cover a wide range of MHC-binding affinities of immunological
interest, and they can be readily integrated with predictions of
other events involved in generating immunogenic epitopes. These predictions
have the capacity to perform rapid proteome-wide searches for epitopes.
Finally, it is an example of an iterative feedback loop whereby advanced,
computational bioinformatics optimize experimental strategy, and
vice versa.},
keywords = {HLA-A Antigens; Humans; Neural Networks (Computer); Peptides; Protein
Binding; Proteome; Research Support, Non-U.S. Gov't; Research Support,
U.S. Gov't, P.H.S.},
owner = {jacob},
pii = {112},
pmid = {14617044},
timestamp = {2006.08.30}
}
@article{Causier2004Studying,
author = {Barry Causier},
title = {Studying the interactome with the yeast two-hybrid system and mass
spectrometry.},
journal = {Mass Spectrom Rev},
year = {2004},
volume = {23},
pages = {350--367},
number = {5},
abstract = {Protein interactions are crucial to the life of a cell. The analysis
of such interactions is allowing biologists to determine the function
of uncharacterized proteins and the genes that encode them. The yeast
two-hybrid system has become one of the most popular and powerful
tools to study protein-protein interactions. With the advent of proteomics,
the two-hybrid system has found a niche in interactome mapping. However,
it is clear that only by combining two-hybrid data with that from
complementary approaches such as mass spectrometry (MS) can the interactome
be analyzed in full. This review introduces the yeast two-hybrid
system to those unfamiliar with the technique, and discusses how
it can be used in combination with MS to unravel the network of protein
interactions that occur in a cell.},
doi = {10.1002/mas.10080},
institution = {School of Biology, University of Leeds, Leeds LS2 9JT, United Kingdom.
b.e.causier@leeds.ac.uk},
keywords = {Genes, Fungal; Genome; Mass Spectrometry; Proteins; Proteomics; Yeasts},
owner = {phupe},
pmid = {15264234},
timestamp = {2010.08.31},
url = {http://dx.doi.org/10.1002/mas.10080}
}
@article{Chan2003Detection,
author = {Ian Chan and William Wells and Robert V Mulkern and Steven Haker
and Jianqing Zhang and Kelly H Zou and Stephan E Maier and Clare
M C Tempany},
title = {Detection of prostate cancer by integration of line-scan diffusion,
{T}2-mapping and {T}2-weighted magnetic resonance imaging; a multichannel
statistical classifier.},
journal = {Med {P}hys},
year = {2003},
volume = {30},
pages = {2390-8},
number = {9},
month = {Sep},
abstract = {A multichannel statistical classifier for detecting prostate cancer
was developed and validated by combining information from three different
magnetic resonance ({MR}) methodologies: {T}2-weighted, {T}2-mapping,
and line scan diffusion imaging ({LSDI}). {F}rom these {MR} sequences,
four different sets of image intensities were obtained: {T}2-weighted
({T}2{W}) from {T}2-weighted imaging, {A}pparent {D}iffusion {C}oefficient
({ADC}) from {LSDI}, and proton density ({PD}) and {T}2 ({T}2 {M}ap)
from {T}2-mapping imaging. {M}anually segmented tumor labels from
a radiologist, which were validated by biopsy results, served as
tumor "ground truth." {T}extural features were extracted from the
images using co-occurrence matrix ({CM}) and discrete cosine transform
({DCT}). {A}natomical location of voxels was described by a cylindrical
coordinate system. {A} statistical jack-knife approach was used to
evaluate our classifiers. {S}ingle-channel maximum likelihood ({ML})
classifiers were based on 1 of the 4 basic image intensities. {O}ur
multichannel classifiers: support vector machine ({SVM}) and {F}isher
linear discriminant ({FLD}), utilized five different sets of derived
features. {E}ach classifier generated a summary statistical map that
indicated tumor likelihood in the peripheral zone ({PZ}) of the prostate
gland. {T}o assess classifier accuracy, the average areas under the
receiver operator characteristic ({ROC}) curves over all subjects
were compared. {O}ur best {FLD} classifier achieved an average {ROC}
area of 0.839(+/-0.064), and our best {SVM} classifier achieved an
average {ROC} area of 0.761(+/-0.043). {T}he {T}2{W} {ML} classifier,
our best single-channel classifier, only achieved an average {ROC}
area of 0.599(+/-0.146). {C}ompared to the best single-channel {ML}
classifier, our best multichannel {FLD} and {SVM} classifiers have
statistically superior {ROC} performance ({P}=0.0003 and 0.0017,
respectively) from pairwise two-sided t-test. {B}y integrating the
information from multiple images and capturing the textural and anatomical
features in tumor areas, summary statistical maps can potentially
aid in image-guided prostate biopsy and assist in guiding and controlling
delivery of localized therapy under image guidance.},
pdf = {../local/Chan2003Detection.pdf},
file = {Chan2003Detection.pdf:local/Chan2003Detection.pdf:PDF},
keywords = {Algorithms, Anion Exchange Resins, Antigen-Antibody Complex, Artificial
Intelligence, Automated, Automatic Data Processing, Biological, Blood
Cells, Chemical, Chromatography, Cluster Analysis, Comparative Study,
Computational Biology, Computer Simulation, Computer-Assisted, Data
Interpretation, Databases, Decision Making, Decision Trees, Diffusion
Magnetic Resonance Imaging, English Abstract, Epitopes, Expert Systems,
Factual, Fuzzy Logic, Gene Expression Profiling, Gene Expression
Regulation, Gene Targeting, Genome, Histocompatibility Antigens Class
I, Humans, Image Interpretation, Image Processing, In Vitro, Indicators
and Reagents, Information Storage and Retrieval, Ion Exchange, Least-Squares
Analysis, Liver Cirrhosis, Magnetic Resonance Imaging, Male, Models,
Neural Networks (Computer), Non-P.H.S., Non-U.S. Gov't, Nonl, Nucleic
Acid Conformation, P.H.S., Pattern Recognition, Pro, Prostatic Neoplasms,
Protein, Protein Binding, Protein Interaction Mapping, Proteins,
Quantitative Structure-Activity Relationship, RNA, ROC Curve, Reproducibility
of Results, Research Support, Sensitivity and Specificity, Sequence
Analysis, Severity of Illness Index, Statistical, Structure-Activity
Relationship, Subtraction Technique, T-Lymphocyte, Transcription
Factors, Transfer, Treatment Outcome, U.S. Gov't, User-Computer Interface,
inear Dynamics, teome, 14528961}
}
@article{Chan2002Comparison,
author = {Kwokleung Chan and Te-Won Lee and Pamela A Sample and Michael H Goldbaum
and Robert N Weinreb and Terrence J Sejnowski},
title = {Comparison of machine learning and traditional classifiers in glaucoma
diagnosis.},
journal = {I{EEE} {T}rans {B}iomed {E}ng},
year = {2002},
volume = {49},
pages = {963-74},
number = {9},
month = {Sep},
abstract = {Glaucoma is a progressive optic neuropathy with characteristic structural
changes in the optic nerve head reflected in the visual field. {T}he
visual-field sensitivity test is commonly used in a clinical setting
to evaluate glaucoma. {S}tandard automated perimetry ({SAP}) is a
common computerized visual-field test whose output is amenable to
machine learning. {W}e compared the performance of a number of machine
learning algorithms with {STATPAC} indexes mean deviation, pattern
standard deviation, and corrected pattern standard deviation. {T}he
machine learning algorithms studied included multilayer perceptron
({MLP}), support vector machine ({SVM}), and linear ({LDA}) and quadratic
discriminant analysis ({QDA}), {P}arzen window, mixture of {G}aussian
({MOG}), and mixture of generalized {G}aussian ({MGG}). {MLP} and
{SVM} are classifiers that work directly on the decision boundary
and fall under the discriminative paradigm. {G}enerative classifiers,
which first model the data probability density and then perform classification
via {B}ayes' rule, usually give deeper insight into the structure
of the data space. {W}e have applied {MOG}, {MGG}, {LDA}, {QDA},
and {P}arzen window to the classification of glaucoma from {SAP}.
{P}erformance of the various classifiers was compared by the areas
under their receiver operating characteristic curves and by sensitivities
(true-positive rates) at chosen specificities (true-negative rates).
{T}he machine-learning-type classifiers showed improved performance
over the best indexes from {STATPAC}. {F}orward-selection and backward-elimination
methodology further improved the classification rate and also has
the potential to reduce testing time by diminishing the number of
visual-field location measurements.},
doi = {10.1109/TBME.2002.802012},
pdf = {../local/Chan2002Comparison.pdf},
file = {Chan2002Comparison.pdf:local/Chan2002Comparison.pdf:PDF},
keywords = {Acute, Algorithms, Animals, Anion Exchange Resins, Artificial Intelligence,
Automated, Base Pair Mismatch, Base Pairing, Base Sequence, Biological,
Biosensing Techniques, Carcinoma, Chemical, Chromatography, Citric
Acid Cycle, Classification, Cluster Analysis, Comparative Study,
Computational Biology, Computer-Assisted, Cystadenoma, DNA, Databases,
Decision Making, Diagnosis, Differential, Discriminant Analysis,
Drug, Drug Design, Electrostatics, Epitopes, Eukaryotic Cells, Factual,
False Negative Reactions, False Positive Reactions, Feasibility Studies,
Female, Gene Expression, Gene Expression Profiling, Gene Expression
Regulation, Genes, Genetic, Genetic Heterogeneity, Genetic Markers,
Glaucoma, HLA Antigens, Hemolysins, Histocompatibility Antigens Class
I, Humans, Internet, Intraocular Pressure, Ion Exchange, Lasers,
Leukemia, Ligands, Likelihood Functions, Logistic Models, Lung Neoplasms,
Lymphocytic, Lymphoma, Markov Chains, Mathematics, Messenger, Models,
Molecular, Molecular Probe Techniques, Molecular Sequence Data, Nanotechnology,
Neoplasm, Neoplasms, Neoplastic, Neural Networks (Computer), Neurological,
Non-P.H.S., Non-Small-Cell Lung, Non-U.S. Gov't, Nucleic Acid Conformation,
Nucleic Acid Hybridization, Observer Variation, Oligonucleotide Array
Sequence Analysis, Open-Angle, Ophthalmoscopy, Optic Disk, Optic
Nerve Diseases, Ovarian Neoplasms, P.H.S., Pattern Recognition, Peptides,
Perimetry, Predictive Value of Tests, Probability, Probability Learning,
Protein, Protein Binding, Protein Conformation, Proteins, Quality
Control, Quantum Theory, RNA, RNA Splicing, ROC Curve, Receptors,
Reference Values, Regression Analysis, Reproducibility of Results,
Research Support, Robotics, Saccharomyces cerevisiae Proteins, Sensitivity
and Specificity, Sequence Analysis, Signal Processing, Software,
Statistical, Stomach Neoplasms, Structural, Structure-Activity Relationship,
T-Lymphocyte, Thermodynamics, Transcription, Tumor Markers, U.S.
Gov't, 12214886},
url = {http://dx.doi.org/10.1109/TBME.2002.802012}
}
@article{Chenna2003Multiple,
author = {Chenna, R. and Sugawara, H. and Koike, T. and Lopez, R. and Gibson,
T. J. and Higgins, D. G. and Thompson, J. D.},
title = {Multiple sequence alignment with the {Clustal} series of programs.},
journal = {Nucleic Acids Res.},
year = {2003},
volume = {31},
pages = {3497--3500},
number = {13},
month = {Jul},
abstract = {The Clustal series of programs are widely used in molecular biology
for the multiple alignment of both nucleic acid and protein sequences
and for preparing phylogenetic trees. The popularity of the programs
depends on a number of factors, including not only the accuracy of
the results, but also the robustness, portability and user-friendliness
of the programs. New features include NEXUS and FASTA format output,
printing range numbers and faster tree calculation. Although, Clustal
was originally developed to run on a local computer, numerous Web
servers have been set up, notably at the EBI (European Bioinformatics
Institute) (http://www.ebi.ac.uk/clustalw/).},
keywords = {Algorithms; Amino Acid Sequence; Internet; Nucleic Acids; Phylogeny;
Sequence Alignment; Sequence Analysis; Sequence Analysis, Protein;
Software},
owner = {laurent},
pmid = {12824352},
timestamp = {2008.01.15}
}
@article{Chou2001Prediction,
author = {Chou, K.-C.},
title = {Prediction of protein signal sequences and their cleavage sites},
journal = {Protein. {S}truct. {F}unct. {G}enet.},
year = {2001},
volume = {42},
pages = {136--139},
pdf = {../local/chou01.pdf},
file = {chou01.pdf:local/chou01.pdf:PDF},
subject = {bioprot},
url = {http://www3.interscience.wiley.com/cgi-bin/abstract/75504759/START}
}
@article{Chou2001Using,
author = {Chou, K.-C.},
title = {Using subsite coupling to predict signal peptides},
journal = {Protein {E}ng.},
year = {2001},
volume = {14},
pages = {75--79},
number = {2},
pdf = {../local/chou01b.pdf},
file = {chou01b.pdf:local/chou01b.pdf:PDF},
subject = {bioprot},
url = {http://protein.oupjournals.org/cgi/content/abstract/14/2/75}
}
@article{Choudhary2010Decoding,
author = {Chunaram Choudhary and Matthias Mann},
title = {Decoding signalling networks by mass spectrometry-based proteomics.},
journal = {Nat Rev Mol Cell Biol},
year = {2010},
volume = {11},
pages = {427--439},
number = {6},
month = {Jun},
abstract = {Signalling networks regulate essentially all of the biology of cells
and organisms in normal and disease states. Signalling is often studied
using antibody-based techniques such as western blots. Large-scale
'precision proteomics' based on mass spectrometry now enables the
system-wide characterization of signalling events at the levels of
post-translational modifications, protein-protein interactions and
changes in protein expression. This technology delivers accurate
and unbiased information about the quantitative changes of thousands
of proteins and their modifications in response to any perturbation.
Current studies focus on phosphorylation, but acetylation, methylation,
glycosylation and ubiquitylation are also becoming amenable to investigation.
Large-scale proteomics-based signalling research will fundamentally
change our understanding of signalling networks.},
doi = {10.1038/nrm2900},
institution = {The Novo Nordisk Foundation Center for Protein Research, Faculty
of Health Sciences, University of Copenhagen, 2200 Copenhagen, Denmark.
chuna.choudhary@cpr.ku.dk},
keywords = {Animals; Humans; Mass Spectrometry; Protein Processing, Post-Translational;
Proteome; Proteomics; Signal Transduction},
owner = {phupe},
pii = {nrm2900},
pmid = {20461098},
timestamp = {2010.08.13},
url = {http://dx.doi.org/10.1038/nrm2900}
}
@article{Citri2006MolCelBiol,
author = {Ami Citri and Yosef Yarden},
title = {EGF-ERBB signalling: towards the systems level.},
journal = {Nat Rev Mol Cell Biol},
year = {2006},
volume = {7},
pages = {505--516},
number = {7},
month = {Jul},
abstract = {Signalling through the ERBB/HER receptors is intricately involved
in human cancer and already serves as a target for several cancer
drugs. Because of its inherent complexity, it is useful to envision
ERBB signalling as a bow-tie-configured, evolvable network, which
shares modularity, redundancy and control circuits with robust biological
and engineered systems. Because network fragility is an inevitable
trade-off of robustness, systems-level understanding is expected
to generate therapeutic opportunities to intercept aberrant network
activation.},
doi = {10.1038/nrm1962},
institution = {Department of Biological Regulation, the Weizmann Institute of Science,
1 Hertzl Street, Rehovot 76100, Israel.},
keywords = {Animals; Endocytosis, physiology; Epidermal Growth Factor, metabolism;
Feedback, Physiological; Humans; Ligands; Models, Molecular; Oncogene
Proteins v-erbB, genetics/metabolism; Phosphatidylinositol 3-Kinases,
metabolism; Protein Conformation; Receptor, Epidermal Growth Factor,
chemistry/genetics/metabolism; Signal Transduction, physiology},
language = {eng},
medline-pst = {ppublish},
owner = {Andrei Zinovyev},
pii = {nrm1962},
pmid = {16829981},
timestamp = {2011.04.08},
url = {http://dx.doi.org/10.1038/nrm1962}
}
@article{Cohen2004application,
author = {Gilles Cohen and M\'elanie Hilario and Hugo Sax and Stéphane Hugonnet
and Christian Pellegrini and Antoine Geissbuhler},
title = {An application of one-class support vector machine to nosocomial
infection detection.},
journal = {Medinfo},
year = {2004},
volume = {11},
pages = {716-20},
number = {Pt 1},
abstract = {Nosocomial infections ({NI}s)---those acquired in health care settings---are
among the major causes of increased mortality among hospitalized
patients. {T}hey are a significant burden for patients and health
authorities alike; it is thus important to monitor and detect them
through an effective surveillance system. {T}his paper describes
a retrospective analysis of a prevalence survey of {NI}s done in
the {G}eneva {U}niversity {H}ospital. {O}ur goal is to identify patients
with one or more {NI}s on the basis of clinical and other data collected
during the survey. {I}n this two-class classification task, the main
difficulty lies in the significant imbalance between positive or
infected (11\%) and negative (89\%) cases. {T}o cope with class imbalance,
we investigate one-class {SVM}s which can be trained to distinguish
two classes on the basis of examples from a single class (in this
case, only "normal" or non infected patients). {T}he infected ones
are then identified as "abnormal" cases or outliers that deviate
significantly from the normal profile. {E}xperimental results are
encouraging: whereas standard 2-class {SVM}s scored a baseline sensitivity
of 50.6\% on this problem, the one-class approach increased sensitivity
to as much as 92.6\%. {T}hese results are comparable to those obtained
by the authors in a previous study on asymmetrical soft margin {SVM}s;
they suggest that one-class {SVM}s can provide an effective and efficient
way of overcoming data imbalance in classification problems.},
keywords = {Aged, Air, Algorithms, Amino Acids, Animals, Area Under Curve, Artifacts,
Artificial Intelligence, Atrial, Automated, Canada, Carotid Stenosis,
Cerebrovascular Accident, Cerebrovascular Circulation, Comparative
Study, Computer-Assisted, Cross Infection, Cysteine, Data Collection,
Decision Trees, Dementia, Diagnosis, Disulfides, Doppler, Embolism,
Expert Systems, Extramural, Factor Analysis, Female, Gene Expression,
Gene Expression Profiling, Health Status, Heart Septal Defects, Hospitals,
Humans, Infection Control, Intracranial Embolism, Male, Models, Molecular,
Myocardial Infarction, N.I.H., Neoplasms, Neural Networks (Computer),
Non-U.S. Gov't, Oligonucleotide Array Sequence Analysis, Oxidation-Reduction,
P.H.S., Pattern Recognition, Population Surveillance, Prevalence,
Prognosis, Protein Binding, Protein Folding, Proteins, ROC Curve,
Research Support, Retrospective Studies, Sensitivity and Specificity,
Software, Statistical, Switzerland, Transcranial, Treatment Outcome,
U.S. Gov't, Ultrasonography, University, 15360906},
pii = {D040004219}
}
@article{Cole2005Comparing,
author = {Jason C Cole and Christopher W Murray and J. Willem M Nissink and
Richard D Taylor and Robin Taylor},
title = {Comparing protein-ligand docking programs is difficult.},
journal = {Proteins},
year = {2005},
volume = {60},
pages = {325--332},
number = {3},
month = {Aug},
abstract = {There is currently great interest in comparing protein-ligand docking
programs. A review of recent comparisons shows that it is difficult
to draw conclusions of general applicability. Statistical hypothesis
testing is required to ensure that differences in pose-prediction
success rates and enrichment rates are significant. Numerical measures
such as root-mean-square deviation need careful interpretation and
may profitably be supplemented by interaction-based measures and
visual inspection of dockings. Test sets must be of appropriate diversity
and of good experimental reliability. The effects of crystal-packing
interactions may be important. The method used for generating starting
ligand geometries and positions may have an appreciable effect on
docking results. For fair comparison, programs must be given search
problems of equal complexity (e.g. binding-site regions of the same
size) and approximately equal time in which to solve them. Comparisons
based on rescoring require local optimization of the ligand in the
space of the new objective function. Re-implementations of published
scoring functions may give significantly different results from the
originals. Ostensibly minor details in methodology may have a profound
influence on headline success rates.},
doi = {10.1002/prot.20497},
institution = {Cambridge Crystallographic Data Centre, Cambridge, United Kingdom.},
keywords = {Algorithms; Artificial Intelligence; Binding Sites; Computational
Biology, methods; Computer Simulation; Crystallization; Crystallography,
X-Ray; Databases, Protein; Ligands; Models, Molecular; Molecular
Structure; Programming Languages; Protein Binding; Proteins, chemistry;
Proteomics, methods; Reproducibility of Results; Software},
owner = {bricehoffmann},
pmid = {15937897},
timestamp = {2009.02.13},
url = {http://dx.doi.org/10.1002/prot.20497}
}
@article{Doennes2002Prediction,
author = {Pierre D\"onnes and Arne Elofsson},
title = {Prediction of {MHC} class {I} binding peptides, using {SVMHC}.},
journal = {BMC Bioinformatics},
year = {2002},
volume = {3},
pages = {25},
month = {Sep},
abstract = {BACKGROUND: T-cells are key players in regulating a specific immune
response. Activation of cytotoxic T-cells requires recognition of
specific peptides bound to Major Histocompatibility Complex (MHC)
class I molecules. MHC-peptide complexes are potential tools for
diagnosis and treatment of pathogens and cancer, as well as for the
development of peptide vaccines. Only one in 100 to 200 potential
binders actually binds to a certain MHC molecule, therefore a good
prediction method for MHC class I binding peptides can reduce the
number of candidate binders that need to be synthesized and tested.
RESULTS: Here, we present a novel approach, SVMHC, based on support
vector machines to predict the binding of peptides to MHC class I
molecules. This method seems to perform slightly better than two
profile based methods, SYFPEITHI and HLA_BIND. The implementation
of SVMHC is quite simple and does not involve any manual steps, therefore
as more data become available it is trivial to provide prediction
for more MHC types. SVMHC currently contains prediction for 26 MHC
class I types from the MHCPEP database or alternatively 6 MHC class
I types from the higher quality SYFPEITHI database. The prediction
models for these MHC types are implemented in a public web service
available at http://www.sbc.su.se/svmhc/. CONCLUSIONS: Prediction
of MHC class I binding peptides using Support Vector Machines, shows
high performance and is easy to apply to a large number of MHC class
I types. As more peptide data are put into MHC databases, SVMHC can
easily be updated to give prediction for additional MHC class I types.
We suggest that the number of binding peptides needed for SVM training
is at least 20 sequences.},
keywords = {Animals; Artificial Intelligence; Comparative Study; Computational
Biology; Databases, Protein; Epitopes, T-Lymphocyte; HLA Antigens;
Histocompatibility Antigens Class I; Humans; Peptides; Predictive
Value of Tests; Protein Binding; Research Support, Non-U.S. Gov't;
Sensitivity and Specificity},
owner = {jacob},
pmid = {12225620},
timestamp = {2006.08.30}
}
@article{Dalton2007Evaluation,
author = {James A R Dalton and Richard M Jackson},
title = {An evaluation of automated homology modelling methods at low target
template sequence similarity.},
journal = {Bioinformatics},
year = {2007},
volume = {23},
pages = {1901--1908},
number = {15},
month = {Aug},
abstract = {MOTIVATION: There are two main areas of difficulty in homology modelling
that are particularly important when sequence identity between target
and template falls below 50\%: sequence alignment and loop building.
These problems become magnified with automatic modelling processes,
as there is no human input to correct mistakes. As such we have benchmarked
several stand-alone strategies that could be implemented in a workflow
for automated high-throughput homology modelling. These include three
new sequence-structure alignment programs: 3D-Coffee, Staccato and
SAlign, plus five homology modelling programs and their respective
loop building methods: Builder, Nest, Modeller, SegMod/ENCAD and
Swiss-Model. The SABmark database provided 123 targets with at least
five templates from the same SCOP family and sequence identities
http://dx.doi.org/10.1093/bioinformatics/btm262}
}
@article{Darbellay2004Solid,
author = {Georges A Darbellay and Rebecca Duff and Jean-Marc Vesin and Paul-André
Despland and Dirk W Droste and Carlos Molina and Joachim Serena and
Roman Sztajzel and Patrick Ruchat and Theodoros Karapanayiotides
and Afksendyios Kalangos and Julien Bogousslavsky and Erich B Ringelstein
and Gérald Devuyst},
title = {Solid or gaseous circulating brain emboli: are they separable by
transcranial ultrasound?},
journal = {J {C}ereb {B}lood {F}low {M}etab},
year = {2004},
volume = {24},
pages = {860-8},
number = {8},
month = {Aug},
abstract = {High-intensity transient signals ({HITS}) detected by transcranial
{D}oppler ({TCD}) ultrasound may correspond to artifacts or to microembolic
signals, the latter being either solid or gaseous emboli. {T}he goal
of this study was to assess what can be achieved with an automatic
signal processing system for artifact/microembolic signals and solid/gas
differentiation in different clinical situations. {T}he authors studied
3,428 {HITS} in vivo in a multicenter study, i.e., 1,608 artifacts
in healthy subjects, 649 solid emboli in stroke patients with a carotid
stenosis, and 1,171 gaseous emboli in stroke patients with patent
foramen ovale. {T}hey worked with the dual-gate {TCD} combined to
three types of statistical classifiers: binary decision trees ({BDT}),
artificial neural networks ({ANN}), and support vector machines ({SVM}).
{T}he sensitivity and specificity to separate artifacts from microembolic
signals by {BDT} reached was 94\% and 97\%, respectively. {F}or the
discrimination between solid and gaseous emboli, the classifier achieved
a sensitivity and specificity of 81\% and 81\% for {BDT}, 84\% and
84\% for {ANN}, and 86\% and 86\% for {SVM}, respectively. {T}he
current results for artifact elimination and solid/gas differentiation
are already useful to extract data for future prospective clinical
studies.},
keywords = {Air, Algorithms, Amino Acids, Animals, Artifacts, Atrial, Carotid
Stenosis, Cerebrovascular Accident, Cerebrovascular Circulation,
Comparative Study, Cysteine, Decision Trees, Disulfides, Doppler,
Embolism, Heart Septal Defects, Humans, Intracranial Embolism, Models,
Molecular, Neural Networks (Computer), Non-U.S. Gov't, Oxidation-Reduction,
Protein Binding, Protein Folding, Proteins, Research Support, Sensitivity
and Specificity, Transcranial, Ultrasonography, 15362716}
}
@article{Debouck1999DNA,
author = {C. Debouck and P. N. Goodfellow},
title = {{DNA} microarrays in drug discovery and development.},
journal = {Nat. Genet.},
year = {1999},
volume = {21},
pages = {48--50},
number = {1 Suppl},
month = {Jan},
abstract = {DNA microarrays can be used to measure the expression patterns of
thousands of genes in parallel, generating clues to gene function
that can help to identify appropriate targets for therapeutic intervention.
They can also be used to monitor changes in gene expression in response
to drug treatments. Here, we discuss the different ways in which
microarray analysis is likely to affect drug discovery.},
doi = {10.1038/4475},
keywords = {Agricultural, Alleles, Alternaria, Amino Acid, Amino Acid Chloromethyl
Ketones, Amino Acid Sequence, Animal, Animals, Apoptosis, Asthma,
Bacteria, Base Sequence, Binding Sites, Biotechnology, Blotting,
Bone Density, Bone Matrix, Bone and Bones, CCR5, Camptothecin, Caspases,
Cathepsins, Cell Surface, Central America, Chloroplast, Chondrocytes,
Chromosome Mapping, Chromosomes, Cloning, Cluster Analysis, Collagen,
Comparative Study, Coumarins, Crops, Crystallography, DNA, DNA Primers,
Dipeptides, Disease, Disease Models, Drug Design, Drug Evaluation,
Drug Industry, Enzyme Activation, Enzyme Inhibitors, Escherichia
coli, Evolution, Exons, Expressed Sequence Tags, Female, Fetus, Fluorescent
Dyes, Food Microbiology, Founder Effect, GTP-Binding Proteins, Gene
Expression, Gene Frequency, Gene Library, Genes, Genetic, Genetic
Predisposition to Disease, Genome, Geography, Growth Plate, Haplotypes,
Hordeum, Human, Humans, Inclusion Bodies, Injections, Intraperitoneal,
Introns, Isatin, Knockout, Male, Membrane Proteins, Messenger, Mice,
Models, Molecular, Molecular Sequence Data, Molecular Structure,
Mutation, Mycotoxins, Neutrophils, Non-U.S. Gov't, Northern, Oligonucleotide
Array Sequence Analysis, Osteoarthritis, Osteochondrodysplasias,
Osteoclasts, Osteopetrosis, Pair 15, Phaseolus, Polymorphism, Preclinical,
Pregnancy, Promoter Regions (Genetics), Protein Precursors, Proteomics,
RNA, Receptors, Recombinant Fusion Proteins, Recombinant Proteins,
Research Support, Restriction Fragment Length, Ribosomal Proteins,
Sequence Alignment, Sequence Analysis, Sequence Homology, South America,
Species Specificity, Splenomegaly, Sulfonamides, Synteny, Tissue
Distribution, Transcription, Trichothecenes, X-Ray, 9915501},
owner = {piedro},
pmid = {9915501},
timestamp = {2006.08.11},
url = {http://dx.doi.org/10.1038/4475}
}
@article{Dekker2002Capturing,
author = {Job Dekker and Karsten Rippe and Martijn Dekker and Nancy Kleckner},
title = {Capturing chromosome conformation.},
journal = {Science},
year = {2002},
volume = {295},
pages = {1306--1311},
number = {5558},
month = {Feb},
abstract = {We describe an approach to detect the frequency of interaction between
any two genomic loci. Generation of a matrix of interaction frequencies
between sites on the same or different chromosomes reveals their
relative spatial disposition and provides information about the physical
properties of the chromatin fiber. This methodology can be applied
to the spatial organization of entire genomes in organisms from bacteria
to human. Using the yeast Saccharomyces cerevisiae, we could confirm
known qualitative features of chromosome organization within the
nucleus and dynamic changes in that organization during meiosis.
We also analyzed yeast chromosome III at the G1 stage of the cell
cycle. We found that chromatin is highly flexible throughout. Furthermore,
functionally distinct AT- and GC-rich domains were found to exhibit
different conformations, and a population-average 3D model of chromosome
III could be determined. Chromosome III emerges as a contorted ring.},
doi = {10.1126/science.1067799},
institution = {Department of Molecular and Cellular Biology, Harvard University,
Cambridge, MA 02138, USA. jdekker@fas.harvard.edu},
keywords = {AT Rich Sequence; Cell Fractionation; Cell Nucleus; Centromere; Chromatin;
Chromosomes, Fungal; Cross-Linking Reagents; Deoxyribonuclease EcoRI;
Formaldehyde; G1 Phase; GC Rich Sequence; Genome, Fungal; Mathematics;
Meiosis; Mitosis; Polymerase Chain Reaction; Protein Conformation;
Saccharomyces cerevisiae; Telomere},
owner = {phupe},
pii = {295/5558/1306},
pmid = {11847345},
timestamp = {2010.08.11},
url = {http://dx.doi.org/10.1126/science.1067799}
}
@article{Dhingra2005Substantial,
author = {Vikas Dhingra and Mukta Gupta and Tracy Andacht and Zhen F Fu},
title = {New frontiers in proteomics research: a perspective.},
journal = {Int. J. Pharm.},
year = {2005},
volume = {299},
pages = {1--18},
number = {1-2},
month = {Aug},
abstract = {Substantial advances have been made in the fundamental understanding
of human biology, ranging from DNA structure to identification of
diseases associated with genetic abnormalities. Genome sequence information
is becoming available in unprecedented amounts. The absence of a
direct functional correlation between gene transcripts and their
corresponding proteins, however, represents a significant roadblock
for improving the efficiency of biological discoveries. The success
of proteomics depends on the ability to identify and analyze protein
products in a cell or tissue and, this is reliant on the application
of several key technologies. Proteomics is in its exponential growth
phase. Two-dimensional electrophoresis complemented with mass spectrometry
provides a global view of the state of the proteins from the sample.
Proteins identification is a requirement to understand their functional
diversity. Subtle difference in protein structure and function can
contribute to complexity and diversity of life. This review focuses
on the progress and the applications of proteomics science with special
reference to integration of the evolving technologies involved to
address biological questions.},
doi = {10.1016/j.ijpharm.2005.04.010},
institution = {Department of Pathology, University of Georgia, Athens, GA 30602,
USA. vdhingra@vet.uga.edu},
keywords = {Computational Biology; Electrophoresis, Gel, Two-Dimensional; Humans;
Peptide Mapping; Protein Interaction Mapping; Proteomics; Spectrometry,
Mass, Matrix-Assisted Laser Desorption-Ionization},
owner = {ljacob},
pii = {S0378-5173(05)00226-7},
pmid = {15979831},
timestamp = {2009.09.14},
url = {http://dx.doi.org/10.1016/j.ijpharm.2005.04.010}
}
@article{Diekman2003Hybrid,
author = {Casey Diekman and Wei He and Nagabhushana Prabhu and Harvey Cramer},
title = {Hybrid methods for automated diagnosis of breast tumors.},
journal = {Anal {Q}uant {C}ytol {H}istol},
year = {2003},
volume = {25},
pages = {183-90},
number = {4},
month = {Aug},
abstract = {O{BJECTIVE}: {T}o design and analyze a new family of hybrid methods
for the diagnosis of breast tumors using fine needle aspirates. {STUDY}
{DESIGN}: {W}e present a radically new approach to the design of
diagnosis systems. {I}n the new approach, a nonlinear classifier
with high sensitivity but low specificity is hybridized with a linear
classifier having low sensitivity but high specificity. {D}ata from
the {W}isconsin {B}reast {C}ancer {D}atabase are used to evaluate,
computationally, the performance of the hybrid classifiers. {RESULTS}:
{T}he diagnosis scheme obtained by hybridizing the nonlinear classifier
ellipsoidal multisurface method ({EMSM}) with the linear classifier
proximal support vector machine ({PSVM}) was found to have a mean
sensitivity of 97.36\% and a mean specificity of 95.14\% and was
found to yield a 2.44\% improvement in the reliability of positive
diagnosis over that of {EMSM} at the expense of 0.4\% degradation
in the reliability of negative diagnosis, again compared to {EMSM}.
{A}t the 95\% confidence level we can trust the hybrid method to
be 96.19-98.53\% correct in its malignant diagnosis of new tumors
and 93.57-96.71\% correct in its benign diagnosis. {CONCLUSION}:
{H}ybrid diagnosis schemes represent a significant paradigm shift
and provide a promising new technique to improve the specificity
of nonlinear classifiers without seriously affecting the high sensitivity
of nonlinear classifiers.},
keywords = {Algorithms, Amino Acid Sequence, Amino Acids, Anion Exchange Resins,
Antigen-Antibody Complex, Artificial Intelligence, Automated, Automatic
Data Processing, Benchmarking, Biological, Biological Markers, Biopsy,
Blood Cells, Blood Proteins, Breast Neoplasms, Cell Line, Cellular
Structures, Chemical, Chromatography, Chromosome Aberrations, Cluster
Analysis, Colonic Neoplasms, Comparative Study, Computational Biology,
Computer Simulation, Computer-Assisted, Computing Methodologies,
DNA, Data Interpretation, Databases, Decision Making, Decision Trees,
Diagnosis, Diffusion Magnetic Resonance Imaging, Disease, English
Abstract, Epitopes, Expert Systems, Factual, Female, Fine-Needle,
Fusion, Fuzzy Logic, Gene Expression Profiling, Gene Expression Regulation,
Gene Targeting, Genetic, Genome, Histocompatibility Antigens Class
I, Humans, Hydrogen Bonding, Hydrophobicity, Image Interpretation,
Image Processing, In Vitro, Indicators and Reagents, Information
Storage and Retrieval, Ion Exchange, Least-Squares Analysis, Leiomyosarcoma,
Liver Cirrhosis, Lung Neoplasms, Magnetic Resonance Imaging, Male,
Mass, Mathematical Computing, Matrix-Assisted Laser Desorption-Ionization,
Models, Molecular, Molecular Sequence Data, Neoplasm Proteins, Neoplasms,
Neoplastic, Nephroblastoma, Neural Networks (Computer), Non-P.H.S.,
Non-U.S. Gov't, Nonl, Nucleic Acid Conformation, Nucleic Acid Hybridization,
Oligonucleotide Array Sequence Analysis, Oncogene Proteins, Ovarian
Neoplasms, P.H.S., Pattern Recognition, Predictive Value of Tests,
Pro, Prostatic Neoplasms, Protein, Protein Binding, Protein Interaction
Mapping, Protein Structure, Proteins, Quantitative Structure-Activity
Relationship, RNA, ROC Curve, Reproducibility of Results, Research
Support, Rhabdomyosarcoma, Secondary, Sensitivity and Specificity,
Sequence Alignment, Sequence Analysis, Severity of Illness Index,
Software, Solubility, Spectrometry, Statistical, Structure-Activity
Relationship, Subcellular Fractions, Subtraction Technique, T-Lymphocyte,
Tissue Distribution, Transcription Factors, Transfer, Treatment Outcome,
Tumor, Tumor Markers, U.S. Gov't, User-Computer Interface, inear
Dynamics, teome, 12961824}
}
@article{Ding2005Minimum,
author = {Chris Ding and Hanchuan Peng},
title = {Minimum redundancy feature selection from microarray gene expression
data.},
journal = {J {B}ioinform {C}omput {B}iol},
year = {2005},
volume = {3},
pages = {185-205},
number = {2},
month = {Apr},
abstract = {How to selecting a small subset out of the thousands of genes in microarray
data is important for accurate classification of phenotypes. {W}idely
used methods typically rank genes according to their differential
expressions among phenotypes and pick the top-ranked genes. {W}e
observe that feature sets so obtained have certain redundancy and
study methods to minimize it. {W}e propose a minimum redundancy -
maximum relevance ({MRMR}) feature selection framework. {G}enes selected
via {MRMR} provide a more balanced coverage of the space and capture
broader characteristics of phenotypes. {T}hey lead to significantly
improved class predictions in extensive experiments on 6 gene expression
data sets: {NCI}, {L}ymphoma, {L}ung, {C}hild {L}eukemia, {L}eukemia,
and {C}olon. {I}mprovements are observed consistently among 4 classification
methods: {N}aive {B}ayes, {L}inear discriminant analysis, {L}ogistic
regression, and {S}upport vector machines. {SUPPLIMENTARY}: {T}he
top 60 {MRMR} genes for each of the datasets are listed in http://crd.lbl.gov/~cding/{MRMR}/.
{M}ore information related to {MRMR} methods can be found at http://www.hpeng.net/.},
keywords = {Adult, Aged, Aging, Algorithms, Animals, Apoptosis, Artificial Intelligence,
Automated, Biological, Bone Marrow, Breast Neoplasms, Classification,
Cluster Analysis, Comparative Study, Computer Simulation, Computer-Assisted,
Diagnosis, Dose-Response Relationship, Drug, Female, Foot, Gait,
Gene Expression Profiling, Gene Expression Regulation, Gene Silencing,
Genetic Vectors, Humans, Image Interpretation, Information Storage
and Retrieval, Kidney, Liver, Logistic Models, Male, Messenger, Models,
Myocardium, Neoplasms, Non-U.S. Gov't, Oligonucleotide Array Sequence
Analysis, Pattern Recognition, Pharmaceutical Preparations, Polymerase
Chain Reaction, Principal Component Analysis, Proteins, RNA, Rats,
Reproducibility of Results, Research Support, Sensitivity and Specificity,
Small Interfering, Sprague-Dawley, Statistical, Subcellular Fractions,
Unknown Primary, 15852500},
pii = {S0219720005001004}
}
@article{Dong2005Prediction,
author = {Hai-Long Dong and Yan-Fang Sui},
title = {Prediction of {HLA}-{A2}-restricted {CTL} epitope specific to {HCC}
by {SYFPEITHI} combined with polynomial method.},
journal = {World J Gastroenterol},
year = {2005},
volume = {11},
pages = {208--211},
number = {2},
month = {Jan},
abstract = {AIM: To predict the HLA-A2-restricted CTL epitopes of tumor antigens
associated with hepatocellular carcinoma (HCC). METHODS: MAGE-1,
MAGE-3, MAGE-8, P53 and AFP were selected as objective antigens in
this study for the close association with HCC. The HLA-A*0201 restricted
CTL epitopes of objective tumor antigens were predicted by SYFPEITHI
prediction method combined with the polynomial quantitative motifs
method. The threshold of polynomial scores was set to -24. RESULTS:
The SYFPEITHI prediction values of all possible nonamers of a given
protein sequence were added together and the ten high-scoring peptides
of each protein were chosen for further analysis in primary prediction.
Thirty-five candidates of CTL epitopes (nonamers) derived from the
primary prediction results were selected by analyzing with the polynomial
method and compared with reported CTL epitopes. CONCLUSION: The combination
of SYFPEITHI prediction method and polynomial method can improve
the prediction efficiency and accuracy. These nonamers may be useful
in the design of therapeutic peptide vaccine for HCC and as immunotherapeutic
strategies against HCC after identified by immunology experiment.},
keywords = {Amino Acid Sequence; Carcinoma, Hepatocellular; Databases, Protein;
Epitopes; HLA-A2 Antigen; Humans; Liver Neoplasms; Major Histocompatibility
Complex; Research Support, Non-U.S. Gov't; T-Lymphocytes, Cytotoxic},
owner = {jacob},
pmid = {15633217},
timestamp = {2006.08.30}
}
@article{Dong2005Fast,
author = {Jian-xiong Dong and Adam Krzyzak and Ching Y Suen},
title = {Fast {SVM} training algorithm with decomposition on very large data
sets.},
journal = {I{EEE} {T}rans {P}attern {A}nal {M}ach {I}ntell},
year = {2005},
volume = {27},
pages = {603-18},
number = {4},
month = {Apr},
abstract = {Training a support vector machine on a data set of huge size with
thousands of classes is a challenging problem. {T}his paper proposes
an efficient algorithm to solve this problem. {T}he key idea is to
introduce a parallel optimization step to quickly remove most of
the nonsupport vectors, where block diagonal matrices are used to
approximate the original kernel matrix so that the original problem
can be split into hundreds of subproblems which can be solved more
efficiently. {I}n addition, some effective strategies such as kernel
caching and efficient computation of kernel matrix are integrated
to speed up the training process. {O}ur analysis of the proposed
algorithm shows that its time complexity grows linearly with the
number of classes and size of the data set. {I}n the experiments,
many appealing properties of the proposed algorithm have been investigated
and the results show that the proposed algorithm has a much better
scaling capability than {L}ibsvm, {SVM}light, and {SVMT}orch. {M}oreover,
the good generalization performances on several large databases have
also been achieved.},
keywords = {Algorithms, Animals, Antibiotics, Antineoplastic, Artificial Intelligence,
Automated, Automatic Data Processing, Butadienes, Chloroplasts, Comparative
Study, Computer Simulation, Computer-Assisted, Database Management
Systems, Databases, Diagnosis, Disinfectants, Dose-Response Relationship,
Drug, Drug Toxicity, Electrodes, Electroencephalography, Ethylamines,
Expert Systems, Factual, Feedback, Fungicides, Gene Expression Profiling,
Genes, Genetic Markers, Humans, Image Enhancement, Image Interpretation,
Implanted, Industrial, Information Storage and Retrieval, Kidney,
Kidney Tubules, MEDLINE, Male, Mercuric Chloride, Microarray Analysis,
Molecular Biology, Motor Cortex, Movement, Natural Language Processing,
Neural Networks (Computer), Non-P.H.S., Non-U.S. Gov't, Numerical
Analysis, Pattern Recognition, Plant Proteins, Predictive Value of
Tests, Proteins, Proteome, Proximal, Puromycin Aminonucleoside, Rats,
Reproducibility of Results, Research Support, Sensitivity and Specificity,
Signal Processing, Sprague-Dawley, Subcellular Fractions, Terminology,
Therapy, Time Factors, Toxicogenetics, U.S. Gov't, User-Computer
Interface, 15794164}
}
@article{Dover2002Methylation,
author = {Jim Dover and Jessica Schneider and Mary Anne Tawiah-Boateng and
Adam Wood and Kimberly Dean and Mark Johnston and Ali Shilatifard},
title = {Methylation of histone H3 by COMPASS requires ubiquitination of histone
H2B by Rad6.},
journal = {J Biol Chem},
year = {2002},
volume = {277},
pages = {28368--28371},
number = {32},
month = {Aug},
abstract = {The DNA of eukaryotes is wrapped around nucleosomes and packaged into
chromatin. Covalent modifications of the histone proteins that comprise
the nucleosome alter chromatin structure and have major effects on
gene expression. Methylation of lysine 4 of histone H3 by COMPASS
is required for silencing of genes located near chromosome telomeres
and within the rDNA (Krogan, N. J, Dover, J., Khorrami, S., Greenblatt,
J. F., Schneider, J., Johnston, M., and Shilatifard, A. (2002) J.
Biol. Chem. 277, 10753-10755; Briggs, S. D., Bryk, M., Strahl, B.
D., Cheung, W. L., Davie, J. K., Dent, S. Y., Winston, F., and Allis,
C. D. (2001) Genes. Dev. 15, 3286-3295). To learn about the mechanism
of histone methylation, we surveyed the genome of the yeast Saccharomyces
cerevisiae for genes necessary for this process. By analyzing approximately
4800 mutant strains, each deleted for a different non-essential gene,
we discovered that the ubiquitin-conjugating enzyme Rad6 is required
for methylation of lysine 4 of histone H3. Ubiquitination of histone
H2B on lysine 123 is the signal for the methylation of histone H3,
which leads to silencing of genes located near telomeres.},
doi = {10.1074/jbc.C200348200},
institution = {Department of Biochemistry, Saint Louis University School of Medicine,
St. Louis, Missouri 63104, USA.},
keywords = {DNA, Ribosomal, metabolism; Electrophoresis, Polyacrylamide Gel; Gene
Silencing; Histones, metabolism; Ligases, metabolism; Lysine, metabolism;
Methylation; Models, Biological; Mutation; Saccharomyces cerevisiae
Proteins; Saccharomyces cerevisiae, genetics; Ubiquitin, metabolism;
Ubiquitin-Conjugating Enzymes},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {C200348200},
pmid = {12070136},
timestamp = {2010.11.23},
url = {http://dx.doi.org/10.1074/jbc.C200348200}
}
@article{Doyle2005PlosBiol,
author = {John Doyle and Marie Csete},
title = {Motifs, control, and stability.},
journal = {PLoS Biol},
year = {2005},
volume = {3},
pages = {e392},
number = {11},
month = {Nov},
doi = {10.1371/journal.pbio.0030392},
institution = {Department of Control and Dynamical Systems, California Institute
of Technology, Pasadena, California, United States of America. doyle@caltech.edu},
keywords = {Amino Acid Motifs; Bacterial Physiological Phenomena; Bacterial Proteins,
chemistry; Escherichia coli, metabolism; Genes, Bacterial; Genes,
Plant; Glycolysis; Heat-Shock Proteins, chemistry; Models, Biological;
Models, Theoretical; Molecular Chaperones, chemistry; Plant Proteins,
chemistry; Protein Interaction Mapping; Protein Structure, Tertiary;
Transcription Factors, chemistry; Transcription, Genetic},
language = {eng},
medline-pst = {ppublish},
owner = {Andrei Zinovyev},
pii = {05-PLBI-P-0948},
pmid = {16277557},
timestamp = {2011.04.08},
url = {http://dx.doi.org/10.1371/journal.pbio.0030392}
}
@article{Doytchinova2004Identifying,
author = {Irini A Doytchinova and Pingping Guan and Darren R Flower},
title = {Identifying human {MHC} supertypes using bioinformatic methods.},
journal = {J. Immunol.},
year = {2004},
volume = {172},
pages = {4314--4323},
number = {7},
month = {Apr},
abstract = {Classification of MHC molecules into supertypes in terms of peptide-binding
specificities is an important issue, with direct implications for
the development of epitope-based vaccines with wide population coverage.
In view of extremely high MHC polymorphism (948 class I and 633 class
II HLA alleles) the experimental solution of this task is presently
impossible. In this study, we describe a bioinformatics strategy
for classifying MHC molecules into supertypes using information drawn
solely from three-dimensional protein structure. Two chemometric
techniques-hierarchical clustering and principal component analysis-were
used independently on a set of 783 HLA class I molecules to identify
supertypes based on structural similarities and molecular interaction
fields calculated for the peptide binding site. Eight supertypes
were defined: A2, A3, A24, B7, B27, B44, C1, and C4. The two techniques
gave 77\% consensus, i.e., 605 HLA class I alleles were classified
in the same supertype by both methods. The proposed strategy allowed
"supertype fingerprints" to be identified. Thus, the A2 supertype
fingerprint is Tyr(9)/Phe(9), Arg(97), and His(114) or Tyr(116);
the A3-Tyr(9)/Phe(9)/Ser(9), Ile(97)/Met(97) and Glu(114) or Asp(116);
the A24-Ser(9) and Met(97); the B7-Asn(63) and Leu(81); the B27-Glu(63)
and Leu(81); for B44-Ala(81); the C1-Ser(77); and the C4-Asn(77).},
keywords = {Alleles; Amino Acid Motifs; Binding Sites; Computational Biology;
DNA Fingerprinting; HLA Antigens; HLA-A Antigens; HLA-B Antigens;
HLA-C Antigens; Histocompatibility Antigens Class I; Histocompatibility
Testing; Humans; Multigene Family; Protein Interaction Mapping},
owner = {laurent},
pmid = {15034046},
timestamp = {2007.01.03}
}
@article{Dreiseitl2001comparison,
author = {S. Dreiseitl and L. Ohno-Machado and H. Kittler and S. Vinterbo and
H. Billhardt and M. Binder},
title = {A comparison of machine learning methods for the diagnosis of pigmented
skin lesions.},
journal = {J {B}iomed {I}nform},
year = {2001},
volume = {34},
pages = {28-36},
number = {1},
month = {Feb},
abstract = {We analyze the discriminatory power of k-nearest neighbors, logistic
regression, artificial neural networks ({ANN}s), decision tress,
and support vector machines ({SVM}s) on the task of classifying pigmented
skin lesions as common nevi, dysplastic nevi, or melanoma. {T}hree
different classification tasks were used as benchmarks: the dichotomous
problem of distinguishing common nevi from dysplastic nevi and melanoma,
the dichotomous problem of distinguishing melanoma from common and
dysplastic nevi, and the trichotomous problem of correctly distinguishing
all three classes. {U}sing {ROC} analysis to measure the discriminatory
power of the methods shows that excellent results for specific classification
problems in the domain of pigmented skin lesions can be achieved
with machine-learning methods. {O}n both dichotomous and trichotomous
tasks, logistic regression, {ANN}s, and {SVM}s performed on about
the same level, with k-nearest neighbors and decision trees performing
worse.},
doi = {10.1006/jbin.2001.1004},
pdf = {../local/Dreiseitl2001comparison.pdf},
file = {Dreiseitl2001comparison.pdf:local/Dreiseitl2001comparison.pdf:PDF},
keywords = {Algorithms, Amino Acid Sequence, Artificial Intelligence, Biological,
Cell Compartmentation, Comparative Study, Computer Simulation, Computer-Assisted,
Decision Trees, Diagnosis, Discriminant Analysis, Humans, Logistic
Models, Melanoma, Models, Neural Networks (Computer), Nevus, Non-U.S.
Gov't, Organelles, P.H.S., Pigmented, Predictive Value of Tests,
Proteins, Reproducibility of Results, Research Support, Skin Diseases,
Skin Neoplasms, Skin Pigmentation, U.S. Gov't, 11376540},
url = {http://dx.doi.org/10.1006/jbin.2001.1004}
}
@article{Early1998Polychemotherapy,
author = {{Early Breast Cancer Trialists’ Collaborative Group}},
title = {Polychemotherapy for early breast cancer: an overview of the randomised
trials. Early Breast Cancer Trialists' Collaborative Group.},
journal = {Lancet},
year = {1998},
volume = {352},
pages = {930--942},
number = {9132},
month = {Sep},
abstract = {There have been many randomised trials of adjuvant prolonged polychemotherapy
among women with early breast cancer, and an updated overview of
their results is presented.In 1995, information was sought on each
woman in any randomised trial that began before 1990 and involved
treatment groups that differed only with respect to the chemotherapy
regimens that were being compared. Analyses involved about 18,000
women in 47 trials of prolonged polychemotherapy versus no chemotherapy,
about 6000 in 11 trials of longer versus shorter polychemotherapy,
and about 6000 in 11 trials of anthracycline-containing regimens
versus CMF (cyclophosphamide, methotrexate, and fluorouracil).For
recurrence, polychemotherapy produced substantial and highly significant
proportional reductions both among women aged under 50 at randomisation
(35\% [SD 4] reduction; 2p<0.00001) and among those aged 50-69 (20\%
[SD 3] reduction; 2p<0.00001); few women aged 70 or over had been
studied. For mortality, the reductions were also significant both
among women aged under 50 (27\% [SD 5] reduction; 2p<0.00001) and
among those aged 50-69 (11\% [SD 3] reduction; 2p=0.0001). The recurrence
reductions emerged chiefly during the first 5 years of follow-up,
whereas the difference in survival grew throughout the first 10 years.
After standardisation for age and time since randomisation, the proportional
reductions in risk were similar for women with node-negative and
node-positive disease. Applying the proportional mortality reduction
observed in all women aged under 50 at randomisation would typically
change a 10-year survival of 71\% for those with node-negative disease
to 78\% (an absolute benefit of 7\%), and of 42\% for those with
node-positive disease to 53\% (an absolute benefit of 11\%). The
smaller proportional mortality reduction observed in all women aged
50-69 at randomisation would translate into smaller absolute benefits,
changing a 10-year survival of 67\% for those with node-negative
disease to 69\% (an absolute gain of 2\%) and of 46\% for those with
node-positive disease to 49\% (an absolute gain of 3\%). The age-specific
benefits of polychemotherapy appeared to be largely irrespective
of menopausal status at presentation, oestrogen receptor status of
the primary tumour, and of whether adjuvant tamoxifen had been given.
In terms of other outcomes, there was a reduction of about one-fifth
(2p=0.05) in contralateral breast cancer, which has already been
included in the analyses of recurrence, and no apparent adverse effect
on deaths from causes other than breast cancer (death rate ratio
0.89 [SD 0.09]). The directly randomised comparisons of longer versus
shorter durations of polychemotherapy did not indicate any survival
advantage with the use of more than about 3-6 months of polychemotherapy.
By contrast, directly randomised comparisons did suggest that, compared
with CMF alone, the anthracycline-containing regimens studied produced
somewhat greater effects on recurrence (2p=0.006) and mortality (69\%
vs 72\% 5-year survival; log-rank 2p=0.02). But this comparison is
one of many that could have been selected for emphasis, the 99\%
CI reaches zero, and the results of several of the relevant trials
are not yet available.Some months of adjuvant polychemotherapy (eg,
with CMF or an anthracycline-containing regimen) typically produces
an absolute improvement of about 7-11\% in 10-year survival for women
aged under 50 at presentation with early breast cancer, and of about
2-3\% for those aged 50-69 (unless their prognosis is likely to be
extremely good even without such treatment). Treatment decisions
involve consideration not only of improvements in cancer recurrence
and survival but also of adverse side-effects of treatment, and this
report makes no recommendations as to who should or should not be
treated.},
keywords = {Adult; Aged; Antineoplastic Combined Chemotherapy Protocols, therapeutic
use; Breast Neoplasms, chemistry/drug therapy/mortality; Chemotherapy,
Adjuvant; Drug Administration Schedule; Female; Humans; Lymphatic
Metastasis; Menopause; Middle Aged; Neoplasm Recurrence, Local; Randomized
Controlled Trials as Topic; Receptors, Estrogen, analysis; Tamoxifen,
administration /&/ dosage},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {S0140673698033017},
pmid = {9752815},
timestamp = {2012.03.01}
}
@article{Ehlers2005NBS1,
author = {Justis P Ehlers and J. William Harbour},
title = {N{BS}1 expression as a prognostic marker in uveal melanoma.},
journal = {Clin. {C}ancer {R}es.},
year = {2005},
volume = {11},
pages = {1849-53},
number = {5},
month = {Mar},
abstract = {P{URPOSE}: {U}p to half of uveal melanoma patients die of metastatic
disease. {T}reatment of the primary eye tumor does not improve survival
in high-risk patients due to occult micrometastatic disease, which
is present at the time of eye tumor diagnosis but is not detected
and treated until months to years later. {H}ere, we use microarray
gene expression data to identify a new prognostic marker. {EXPERIMENTAL}
{DESIGN}: {M}icroarray gene expression profiles were analyzed in
25 primary uveal melanomas. {T}umors were ranked by support vector
machine ({SVM}) and by cytologic severity. {N}bs1 protein expression
was assessed by quantitative immunohistochemistry in 49 primary uveal
melanomas. {S}urvival was assessed using {K}aplan-{M}eier life-table
analysis. {RESULTS}: {E}xpression of the {N}ijmegen breakage syndrome
({NBS}1) gene correlated strongly with {SVM} and cytologic tumor
rankings ({P} < 0.0001). {F}urther, immunohistochemistry expression
of the {N}bs1 protein correlated strongly with both {SVM} and cytologic
rankings ({P} < 0.0001). {T}he 6-year actuarial survival was 100\%
in patients with low immunohistochemistry expression of {N}bs1 and
22\% in those with high {N}bs1 expression ({P} = 0.01). {CONCLUSIONS}:
{NBS}1 is a strong predictor of uveal melanoma survival and potentially
could be used as a clinical marker for guiding clinical management.},
doi = {10.1158/1078-0432.CCR-04-2054},
pdf = {../local/Ehlers2005NBS1.pdf},
file = {Ehlers2005NBS1.pdf:local/Ehlers2005NBS1.pdf:PDF},
keywords = {80 and over, Adult, Aged, Algorithms, Amino Acid Sequence, Amino Acids,
Analysis of Variance, Animals, Area Under Curve, Artifacts, Automated,
Bacteriophage T4, Base Sequence, Biological, Birefringence, Brain
Chemistry, Brain Neoplasms, Cell Cycle Proteins, Comparative Study,
Computational Biology, Computer-Assisted, Cornea, Cross-Sectional
Studies, Databases, Decision Trees, Diagnosis, Diagnostic Imaging,
Diagnostic Techniques, Discriminant Analysis, Evolution, Extramural,
Face, Female, Gene Expression Profiling, Genetic, Glaucoma, Humans,
Immunohistochemistry, Intraocular Pressure, Lasers, Least-Squares
Analysis, Likelihood Functions, Magnetic Resonance Imaging, Magnetic
Resonance Spectroscopy, Male, Markov Chains, Melanoma, Middle Aged,
Models, Molecular, Mutation, N.I.H., Nerve Fibers, Non-P.H.S., Non-U.S.
Gov't, Nuclear Proteins, Nucleic Acid, Nucleic Acid Conformation,
Numerical Analysis, Oligonucleotide Array Sequence Analysis, Ophthalmological,
Optic Nerve Diseases, Optical Coherence, P.H.S., Pattern Recognition,
Photic Stimulation, Polymorphism, Prognosis, Prospective Studies,
Protein, Protein Structure, Proteins, RNA, ROC Curve, Regression
Analysis, Reproducibility of Results, Research Support, Retinal Ganglion
Cells, Secondary, Sensitivity and Specificity, Sequence Analysis,
Single Nucleotide, Single-Stranded Conformational, Software, Statistics,
Survival Analysis, Tertiary, Tomography, Tumor Markers, U.S. Gov't,
Untranslated, Uveal Neoplasms, Visual Fields, beta-Lactamases, 15756009},
pii = {11/5/1849},
url = {http://clincancerres.aacrjournals.org/cgi/content/abstract/11/5/1849}
}
@article{Ekins2002Towards,
author = {S. Ekins and B. Boulanger and P. W. Swaan and M. A. Z. Hupcey},
title = {{T}owards a new age of virtual {ADME}/{TOX} and multidimensional
drug discovery.},
journal = {J Comput Aided Mol Des},
year = {2002},
volume = {16},
pages = {381--401},
number = {5-6},
abstract = {With the continual pressure to ensure follow-up molecules to billion
dollar blockbuster drugs, there is a hurdle in profitability and
growth for pharmaceutical companies in the next decades. With each
success and failure we increasingly appreciate that a key to the
success of synthesized molecules through the research and development
process is the possession of drug-like properties. These properties
include an adequate bioactivity as well as adequate solubility, an
ability to cross critical membranes (intestinal and sometimes blood-brain
barrier), reasonable metabolic stability and of course safety in
humans. Dependent on the therapeutic area being investigated it might
also be desirable to avoid certain enzymes or transporters to circumvent
potential drug-drug interactions. It may also be important to limit
the induction of these same proteins that can result in further toxicities.
We have clearly moved the assessment of in vitro absorption, distribution,
metabolism, excretion and toxicity (ADME/TOX) parameters much earlier
in the discovery organization than a decade ago with the inclusion
of higher throughput systems. We are also now faced with huge amounts
of ADME/TOX data for each molecule that need interpretation and also
provide a valuable resource for generating predictive computational
models for future drug discovery. The present review aims to show
what tools exist today for visualizing and modeling ADME/TOX data,
what tools need to be developed, and how both the present and future
tools are valuable for virtual filtering using ADME/TOX and bioactivity
properties in parallel as a viable addition to present practices.},
keywords = {ATP-Binding Cassette Transporters, Algorithms, Animals, Biological,
Biological Availability, Computer Simulation, Drug Design, Drug Evaluation,
Drug Industry, Gene Expression Profiling, Humans, Models, Organic
Anion Transporters, P.H.S., Pharmaceutical, Pharmaceutical Preparations,
Pharmacogenetics, Pharmacokinetics, Preclinical, Proteomics, Research
Support, Software, Systems Biology, Technology, Toxicity Tests, U.S.
Gov't, 12489686},
owner = {mahe},
pmid = {12489686},
timestamp = {2006.08.16}
}
@article{Theres2006Structural,
author = {Theres Fagerberg and Jean-Charles Cerottini and Olivier Michielin},
title = {{S}tructural prediction of peptides bound to {MHC} class {I}.},
journal = {J. Mol. Biol.},
year = {2006},
volume = {356},
pages = {521--546},
number = {2},
month = {Feb},
abstract = {An ab initio structure prediction approach adapted to the peptide-major
histocompatibility complex (MHC) class I system is presented. Based
on structure comparisons of a large set of peptide-MHC class I complexes,
a molecular dynamics protocol is proposed using simulated annealing
(SA) cycles to sample the conformational space of the peptide in
its fixed MHC environment. A set of 14 peptide-human leukocyte antigen
(HLA) A0201 and 27 peptide-non-HLA A0201 complexes for which X-ray
structures are available is used to test the accuracy of the prediction
method. For each complex, 1000 peptide conformers are obtained from
the SA sampling. A graph theory clustering algorithm based on heavy
atom root-mean-square deviation (RMSD) values is applied to the sampled
conformers. The clusters are ranked using cluster size, mean effective
or conformational free energies, with solvation free energies computed
using Generalized Born MV 2 (GB-MV2) and Poisson-Boltzmann (PB) continuum
models. The final conformation is chosen as the center of the best-ranked
cluster. With conformational free energies, the overall prediction
success is 83\% using a 1.00 Angstroms crystal RMSD criterion for
main-chain atoms, and 76\% using a 1.50 Angstroms RMSD criterion
for heavy atoms. The prediction success is even higher for the set
of 14 peptide-HLA A0201 complexes: 100\% of the peptides have main-chain
RMSD values < or =1.00 Angstroms and 93\% of the peptides have heavy
atom RMSD values < or =1.50 Angstroms. This structure prediction
method can be applied to complexes of natural or modified antigenic
peptides in their MHC environment with the aim to perform rational
structure-based optimizations of tumor vaccines.},
doi = {10.1016/j.jmb.2005.11.059},
keywords = {, Algorithms, Amino Acid Sequence, Antibodies, Artificial Intelligence,
Automated, Binding Sites, Chemical, Computer Simulation, Databases,
Epitope Mapping, Genes, HLA-A Antigens, HLA-DQ Antigens, Histocompatibility
Antigens Class I, Humans, Immunoassay, Immunological, MHC Class I,
Models, Molecular, Molecular Sequence Data, Pattern Recognition,
Peptides, Protein, Protein Binding, Protein Conformation, Protein
Interaction Mapping, Protein Structure, Sequence Alignment, Sequence
Analysis, Software, Tertiary, Water, 16368108},
pii = {S0022-2836(05)01462-2},
pmid = {16368108},
timestamp = {2007.01.25},
url = {http://dx.doi.org/10.1016/j.jmb.2005.11.059}
}
@article{Faugeras2004Variational,
author = {Olivier Faugeras and Geoffray Adde and Guillaume Charpiat and Christophe
Chefd'hotel and Maureen Clerc and Thomas Deneux and Rachid Deriche
and Gerardo Hermosillo and Renaud Keriven and Pierre Kornprobst and
Jan Kybic and Christophe Lenglet and Lucero Lopez-Perez and Théo
Papadopoulo and Jean-Philippe Pons and Florent Segonne and Bertrand
Thirion and David Tschumperlé and Thierry Viéville and Nicolas
Wotawa},
title = {Variational, geometric, and statistical methods for modeling brain
anatomy and function.},
journal = {Neuroimage},
year = {2004},
volume = {23 Suppl 1},
pages = {S46-55},
abstract = {We survey the recent activities of the {O}dyssée {L}aboratory in
the area of the application of mathematics to the design of models
for studying brain anatomy and function. {W}e start with the problem
of reconstructing sources in {MEG} and {EEG}, and discuss the variational
approach we have developed for solving these inverse problems. {T}his
motivates the need for geometric models of the head. {W}e present
a method for automatically and accurately extracting surface meshes
of several tissues of the head from anatomical magnetic resonance
({MR}) images. {A}natomical connectivity can be extracted from diffusion
tensor magnetic resonance images but, in the current state of the
technology, it must be preceded by a robust estimation and regularization
stage. {W}e discuss our work based on variational principles and
show how the results can be used to track fibers in the white matter
({WM}) as geodesics in some {R}iemannian space. {W}e then go to the
statistical modeling of functional magnetic resonance imaging (f{MRI})
signals from the viewpoint of their decomposition in a pseudo-deterministic
and stochastic part that we then use to perform clustering of voxels
in a way that is inspired by the theory of support vector machines
and in a way that is grounded in information theory. {M}ultimodal
image matching is discussed next in the framework of image statistics
and partial differential equations ({PDE}s) with an eye on registering
f{MRI} to the anatomy. {T}he paper ends with a discussion of a new
theory of random shapes that may prove useful in building anatomical
and functional atlases.},
doi = {10.1016/j.neuroimage.2004.07.015},
pdf = {../local/Faugeras2004Variational.pdf},
file = {Faugeras2004Variational.pdf:local/Faugeras2004Variational.pdf:PDF},
keywords = {Adolescent, Adult, Algorithms, Anatomic, Bacterial Proteins, Brain,
Brain Mapping, Comparative Study, Computer Simulation, Computer-Assisted,
Diffusion Magnetic Resonance Imaging, Facial Asymmetry, Facial Expression,
Facial Paralysis, Female, Gene Expression Profiling, Gram-Negative
Bacteria, Gram-Positive Bacteria, Humans, Image Interpretation, Magnetoencephalography,
Male, Middle Aged, Models, Motion, Neural Pathways, Non-U.S. Gov't,
Photography, Protein, Proteome, Research Support, Retina, Sequence
Alignment, Sequence Analysis, Severity of Illness Index, Software,
Statistical, Subcellular Fractions, 15501100},
pii = {S1053-8119(04)00380-5},
url = {http://dx.doi.org/10.1016/j.neuroimage.2004.07.015}
}
@article{Formosa2003Changing,
author = {T. Formosa},
title = {Changing the DNA landscape: putting a SPN on chromatin.},
journal = {Curr Top Microbiol Immunol},
year = {2003},
volume = {274},
pages = {171--201},
abstract = {In eukaryotic cells, transcription and replication each occur on DNA
templates that are incorporated into nucleosomes. Formation of chromatin
generally limits accessibility of specific DNA sequences and inhibits
progression of polymerases as they copy information from the DNA.
The processes that select sites for initiating either transcription
or replication are therefore strongly influenced by factors that
modulate the properties of chromatin proteins. Further, in order
to elongate their products, both DNA and RNA polymerases must be
able to overcome the inhibition presented by chromatin (Lipford and
Bell 2001; Workman and Kingston 1998). One way to adjust the properties
of chromatin proteins is to covalently modify them by adding or removing
chemical moieties. Both histone and non-histone chromatin proteins
are altered by acetylation, methylation, and other changes, and the
'nucleosome modifying' complexes that perform these reactions are
important components of pathways of transcriptional regulation (Cote
2002; Orphanides and Reinberg 2000; Roth et al. 2001; Strahl and
Allis 2000; Workman and Kingston 1998). Another way to alter the
effects of nucleosomes is to change the position of the histone octamers
relative to specific DNA sequences (Orphanides and Reinberg 2000;
Verrijzer 2002; Wang 2002; Workman and Kingston 1998). Since the
ability of a sequence to be bound by specific proteins can vary significantly
whether the sequence is in the linkers between nucleosomes or at
various positions within a nucleosome, 'nucleosome remodeling' complexes
that rearrange nucleosome positioning are also important regulators
of transcription. Since the DNA replication machinery has to encounter
many of the same challenges posed by chromatin, it seems likely that
modifying and remodeling complexes also act during duplication of
the genome, but most of the current information on these factors
relates to regulation of transcription. This chapter describes the
factor known variously as FACT in humans, where it promotes elongation
of RNA polymerase II on nucleosomal templates in vitro (Orphanides
et al. 1998, 1999), DUF in frogs, where it is needed for DNA replication
in oocyte extracts (Okuhara et al. 1999), and CP or SPN in yeast,
where it is linked in vivo to both transcription and replication
(Brewster et al. 2001; Formosa et al. 2001). Like the nucleosome
modifying and remodeling complexes, it is broadly conserved among
eukaryotes, affects a wide range of processes that utilize chromatin,
and directly alters the properties of nucleosomes. However, it does
not have nucleosome modifying or standard ATP-dependent remodeling
activity, and therefore represents a third class of chromatin modulating
factors. It is also presently unique in the extensive connections
it displays with both transcription and replication: FACT/DUF/CP/SPN
appears to modify nucleosomes in a way that is directly important
for the efficient functioning of both RNA polymerases and DNA polymerases.
While less is known about the mechanisms it uses to promote its functions
than for other factors that affect chromatin, it is clearly an essential
part of the complex mixture of activities that modulate access to
DNA within chromatin. Physical and genetic interactions suggest that
FACT/DUF/CP/SPN affects multiple pathways within replication and
transcription as a member of several distinct complexes. Some of
the interactions are easy to assimilate into models for replication
or transcription, such as direct binding to DNA polymerase alpha
(Wittmeyer and Formosa 1997; Wittmeyer et al. 1999), association
with nucleosome modifying complexes (John et al. 2000), and interaction
with factors that participate in elongation of RNA Polymerase II
(Gavin et al. 2002; Squazzo et al. 2002). Others are more surprising
such as an association with the 19S complex that regulates the function
of the 20S proteasome (Ferdous et al. 2001; Xu et al. 1995), and
the indication that FACT/DUF/CP/SPN can act as a specificity factor
for casein kinase II (Keller et al. 2001). This chapter reviews the
varied approaches that have each revealed different aspects of the
function of FACT/DUF/CP/SPN, and presents a picture of a factor that
can both alter nucleosomes and orchestrate the assembly or activity
of a broad range of complexes that act upon chromatin.},
institution = {University of Utah, Biochemistry, 20 N 1900 E RM 211, Salt Lake City,
UT 84132-3201, USA. Tim.Formosa@hsc.utah.edu},
keywords = {Animals; Cell Cycle Proteins, metabolism; Chromatin, metabolism; DNA,
metabolism; Eukaryotic Cells, metabolism; Gene Expression Regulation;
Humans; Saccharomyces cerevisiae Proteins; Transcription Factors,
metabolism; Transcription, Genetic; Transcriptional Elongation Factors},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pmid = {12596908},
timestamp = {2010.11.23}
}
@article{Fullwood2009oestrogen-receptor-alpha-bound,
author = {Melissa J Fullwood and Mei Hui Liu and You Fu Pan and Jun Liu and
Han Xu and Yusoff Bin Mohamed and Yuriy L Orlov and Stoyan Velkov
and Andrea Ho and Poh Huay Mei and Elaine G Y Chew and Phillips Yao
Hui Huang and Willem-Jan Welboren and Yuyuan Han and Hong Sain Ooi
and Pramila N Ariyaratne and Vinsensius B Vega and Yanquan Luo and
Peck Yean Tan and Pei Ye Choy and K. D Senali Abayratna Wansa and
Bing Zhao and Kar Sian Lim and Shi Chi Leow and Jit Sin Yow and Roy
Joseph and Haixia Li and Kartiki V Desai and Jane S Thomsen and Yew
Kok Lee and R. Krishna Murthy Karuturi and Thoreau Herve and Guillaume
Bourque and Hendrik G Stunnenberg and Xiaoan Ruan and Valere Cacheux-Rataboul
and Wing-Kin Sung and Edison T Liu and Chia-Lin Wei and Edwin Cheung
and Yijun Ruan},
title = {An oestrogen-receptor-alpha-bound human chromatin interactome.},
journal = {Nature},
year = {2009},
volume = {462},
pages = {58--64},
number = {7269},
month = {Nov},
abstract = {Genomes are organized into high-level three-dimensional structures,
and DNA elements separated by long genomic distances can in principle
interact functionally. Many transcription factors bind to regulatory
DNA elements distant from gene promoters. Although distal binding
sites have been shown to regulate transcription by long-range chromatin
interactions at a few loci, chromatin interactions and their impact
on transcription regulation have not been investigated in a genome-wide
manner. Here we describe the development of a new strategy, chromatin
interaction analysis by paired-end tag sequencing (ChIA-PET) for
the de novo detection of global chromatin interactions, with which
we have comprehensively mapped the chromatin interaction network
bound by oestrogen receptor alpha (ER-alpha) in the human genome.
We found that most high-confidence remote ER-alpha-binding sites
are anchored at gene promoters through long-range chromatin interactions,
suggesting that ER-alpha functions by extensive chromatin looping
to bring genes together for coordinated transcriptional regulation.
We propose that chromatin interactions constitute a primary mechanism
for regulating transcription in mammalian genomes.},
doi = {10.1038/nature08497},
institution = {Genome Institute of Singapore, Agency for Science, Technology and
Research, Singapore 138672.},
keywords = {Binding Sites; Cell Line; Chromatin; Chromatin Immunoprecipitation;
Cross-Linking Reagents; Estrogen Receptor alpha; Formaldehyde; Genome,
Human; Humans; Promoter Regions, Genetic; Protein Binding; Reproducibility
of Results; Sequence Analysis, DNA; Transcription, Genetic; Transcriptional
Activation},
owner = {phupe},
pii = {nature08497},
pmid = {19890323},
timestamp = {2010.08.26},
url = {http://dx.doi.org/10.1038/nature08497}
}
@article{Garcia2007Organismal,
author = {Benjamin A Garcia and Sandra B Hake and Robert L Diaz and Monika
Kauer and Stephanie A Morris and Judith Recht and Jeffrey Shabanowitz
and Nilamadhab Mishra and Brian D Strahl and C. David Allis and Donald
F Hunt},
title = {Organismal differences in post-translational modifications in histones
H3 and H4.},
journal = {J Biol Chem},
year = {2007},
volume = {282},
pages = {7641--7655},
number = {10},
month = {Mar},
abstract = {Post-translational modifications (PTMs) of histones play an important
role in many cellular processes, notably gene regulation. Using a
combination of mass spectrometric and immunobiochemical approaches,
we show that the PTM profile of histone H3 differs significantly
among the various model organisms examined. Unicellular eukaryotes,
such as Saccharomyces cerevisiae (yeast) and Tetrahymena thermophila
(Tet), for example, contain more activation than silencing marks
as compared with mammalian cells (mouse and human), which are generally
enriched in PTMs more often associated with gene silencing. Close
examination reveals that many of the better-known modified lysines
(Lys) can be either methylated or acetylated and that the overall
modification patterns become more complex from unicellular eukaryotes
to mammals. Additionally, novel species-specific H3 PTMs from wild-type
asynchronously grown cells are also detected by mass spectrometry.
Our results suggest that some PTMs are more conserved than previously
thought, including H3K9me1 and H4K20me2 in yeast and H3K27me1, -me2,
and -me3 in Tet. On histone H4, methylation at Lys-20 showed a similar
pattern as H3 methylation at Lys-9, with mammals containing more
methylation than the unicellular organisms. Additionally, modification
profiles of H4 acetylation were very similar among the organisms
examined.},
doi = {10.1074/jbc.M607900200},
institution = {Department of Chemistry, University of Virginia, Charlottesville,
Virginia 22901, USA.},
keywords = {Acetylation; Animals; Hela Cells; Histones, chemistry/metabolism;
Humans; Methylation; Mice; NIH 3T3 Cells; Protein Processing, Post-Translational;
Saccharomyces cerevisiae, metabolism; Species Specificity; Tandem
Mass Spectrometry; Tetrahymena, metabolism},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {M607900200},
pmid = {17194708},
timestamp = {2010.11.23},
url = {http://dx.doi.org/10.1074/jbc.M607900200}
}
@article{Gavin2002Functionala,
author = {Anne-Claude Gavin and Markus Bösche and Roland Krause and Paola
Grandi and Martina Marzioch and Andreas Bauer and Jörg Schultz and
Jens M Rick and Anne-Marie Michon and Cristina-Maria Cruciat and
Marita Remor and Christian Höfert and Malgorzata Schelder and Miro
Brajenovic and Heinz Ruffner and Alejandro Merino and Karin Klein
and Manuela Hudak and David Dickson and Tatjana Rudi and Volker Gnau
and Angela Bauch and Sonja Bastuck and Bettina Huhse and Christina
Leutwein and Marie-Anne Heurtier and Richard R Copley and Angela
Edelmann and Erich Querfurth and Vladimir Rybin and Gerard Drewes
and Manfred Raida and Tewis Bouwmeester and Peer Bork and Bertrand
Seraphin and Bernhard Kuster and Gitte Neubauer and Giulio Superti-Furga},
title = {Functional organization of the yeast proteome by systematic analysis
of protein complexes.},
journal = {Nature},
year = {2002},
volume = {415},
pages = {141-7},
number = {6868},
month = {Jan},
abstract = {Most cellular processes are carried out by multiprotein complexes.
{T}he identification and analysis of their components provides insight
into how the ensemble of expressed proteins (proteome) is organized
into functional units. {W}e used tandem-affinity purification ({TAP})
and mass spectrometry in a large-scale approach to characterize multiprotein
complexes in {S}accharomyces cerevisiae. {W}e processed 1,739 genes,
including 1,143 human orthologues of relevance to human biology,
and purified 589 protein assemblies. {B}ioinformatic analysis of
these assemblies defined 232 distinct multiprotein complexes and
proposed new cellular roles for 344 proteins, including 231 proteins
with no previous functional annotation. {C}omparison of yeast and
human complexes showed that conservation across species extends from
single proteins to their molecular environment. {O}ur analysis provides
an outline of the eukaryotic proteome as a network of protein complexes
at a level of organization beyond binary interactions. {T}his higher-order
map contains fundamental biological information and offers the context
for a more reasoned and informed approach to drug discovery.},
doi = {10.1038/415141a},
pdf = {../local/gavi02.pdf},
file = {gavi02.pdf:local/gavi02.pdf:PDF},
keywords = {Affinity, Affinity Labels, Amino Acid Sequence, Animals, Cell Cycle
Proteins, Cells, Chromatography, Cloning, Comparative Study, Cultured,
DNA, DNA Damage, DNA Repair, Electrospray Ionization, Fungal, Gene
Targeting, Genetic, Humans, Macromolecular Substances, Mass, Matrix-Assisted
Laser Desorption-Ionization, Mitosis, Molecular, Molecular Sequence
Data, Non-P.H.S., Non-U.S. Gov't, P.H.S., Phosphoric Monoester Hydrolases,
Protein Binding, Protein Interaction Mapping, Protein Kinases, Proteome,
Proteomics, Recombinant Fusion Proteins, Research Support, Ribonucleoproteins,
Ribosomes, Saccharomyces cerevisiae, Saccharomyces cerevisiae Proteins,
Sensitivity and Specificity, Sequence Alignment, Signal Transduction,
Species Specificity, Spectrometry, Spectrum Analysis, Transcription,
U.S. Gov't, 11805813},
owner = {vert},
pii = {415141a},
url = {http://dx.doi.org/10.1038/415141a}
}
@article{Ge2003Reducing,
author = {Xijin Ge and Shuichi Tsutsumi and Hiroyuki Aburatani and Shuichi
Iwata},
title = {Reducing false positives in molecular pattern recognition.},
journal = {Genome {I}nform {S}er {W}orkshop {G}enome {I}nform},
year = {2003},
volume = {14},
pages = {34-43},
abstract = {In the search for new cancer subtypes by gene expression profiling,
it is essential to avoid misclassifying samples of unknown subtypes
as known ones. {I}n this paper, we evaluated the false positive error
rates of several classification algorithms through a 'null test'
by presenting classifiers a large collection of independent samples
that do not belong to any of the tumor types in the training dataset.
{T}he benchmark dataset is available at www2.genome.rcast.u-tokyo.ac.jp/pm/.
{W}e found that k-nearest neighbor ({KNN}) and support vector machine
({SVM}) have very high false positive error rates when fewer genes
(<100) are used in prediction. {T}he error rate can be partially
reduced by including more genes. {O}n the other hand, prototype matching
({PM}) method has a much lower false positive error rate. {S}uch
robustness can be achieved without loss of sensitivity by introducing
suitable measures of prediction confidence. {W}e also proposed a
cluster-and-select technique to select genes for classification.
{T}he nonparametric {K}ruskal-{W}allis {H} test is employed to select
genes differentially expressed in multiple tumor types. {T}o reduce
the redundancy, we then divided these genes into clusters with similar
expression patterns and selected a given number of genes from each
cluster. {T}he reliability of the new algorithm is tested on three
public datasets.},
keywords = {Amino Acid Sequence, Amino Acids, Animals, Automated, Base Sequence,
Bayes Theorem, Biological, Carbohydrate Conformation, Carbohydrate
Sequence, Cattle, Computational Biology, Computer Simulation, Crystallography,
DNA, Databases, Factual, False Positive Reactions, Gene Expression
Profiling, Genes, Genetic, Genetic Techniques, Genome, Histocompatibility
Antigens Class I, Human, Humans, Introns, Least-Squares Analysis,
MHC Class I, Major Histocompatibility Complex, Markov Chains, Messenger,
Mice, Models, Monosaccharides, Neoplasms, Non-U.S. Gov't, Nonparametric,
Pattern Recognition, Peptides, Phylogeny, Plants, Poly A, Polysaccharides,
Predictive Value of Tests, Protein, Protein Structure, Proteins,
RNA, Rats, Reproducibility of Results, Research Support, Saccharomyces
cerevisiae, Secondary, Sequence Alignment, Software, Species Specificity,
Statistics, Theoretical, X-Ray, 15706518}
}
@article{Gehlenborg2010Visualization,
author = {Nils Gehlenborg and Seán I O'Donoghue and Nitin S Baliga and Alexander
Goesmann and Matthew A Hibbs and Hiroaki Kitano and Oliver Kohlbacher
and Heiko Neuweger and Reinhard Schneider and Dan Tenenbaum and Anne-Claude
Gavin},
title = {Visualization of omics data for systems biology.},
journal = {Nat Methods},
year = {2010},
volume = {7},
pages = {S56--S68},
number = {3 Suppl},
month = {Mar},
abstract = {High-throughput studies of biological systems are rapidly accumulating
a wealth of 'omics'-scale data. Visualization is a key aspect of
both the analysis and understanding of these data, and users now
have many visualization methods and tools to choose from. The challenge
is to create clear, meaningful and integrated visualizations that
give biological insight, without being overwhelmed by the intrinsic
complexity of the data. In this review, we discuss how visualization
tools are being used to help interpret protein interaction, gene
expression and metabolic profile data, and we highlight emerging
new directions.},
doi = {10.1038/nmeth.1436},
institution = {European Bioinformatics Institute, Cambridge, UK.},
keywords = {Genomics; Image Processing, Computer-Assisted; Mass Spectrometry;
Metabolomics; Nuclear Magnetic Resonance, Biomolecular; Protein Binding;
Proteomics; Systems Biology},
language = {eng},
medline-pst = {ppublish},
owner = {philippe},
pii = {nmeth.1436},
pmid = {20195258},
timestamp = {2010.07.27},
url = {http://dx.doi.org/10.1038/nmeth.1436}
}
@article{Gether2000Uncovering,
author = {U. Gether},
title = {Uncovering molecular mechanisms involved in activation of G protein-coupled
receptors.},
journal = {Endocr Rev},
year = {2000},
volume = {21},
pages = {90--113},
number = {1},
month = {Feb},
abstract = {G protein-coupled, seven-transmembrane segment receptors (GPCRs or
7TM receptors), with more than 1000 different members, comprise the
largest superfamily of proteins in the body. Since the cloning of
the first receptors more than a decade ago, extensive experimental
work has uncovered multiple aspects of their function and challenged
many traditional paradigms. However, it is only recently that we
are beginning to gain insight into some of the most fundamental questions
in the molecular function of this class of receptors. How can, for
example, so many chemically diverse hormones, neurotransmitters,
and other signaling molecules activate receptors believed to share
a similar overall tertiary structure? What is the nature of the physical
changes linking agonist binding to receptor activation and subsequent
transduction of the signal to the associated G protein on the cytoplasmic
side of the membrane and to other putative signaling pathways? The
goal of the present review is to specifically address these questions
as well as to depict the current awareness about GPCR structure-function
relationships in general.},
keywords = {Animals; GTP-Binding Proteins; Humans; Ligands; Models, Biological;
Molecular Conformation; Receptors, Cell Surface},
owner = {laurent},
pmid = {10696571},
timestamp = {2007.09.22}
}
@article{Girosi1998Equivalence,
author = {Girosi},
title = {An {E}quivalence {B}etween {S}parse {A}pproximation and {S}upport
{V}ector {M}achines.},
journal = {Neural {C}omput},
year = {1998},
volume = {10},
pages = {1455-80},
number = {6},
month = {Jul},
abstract = {This article shows a relationship between two different approximation
techniques: the support vector machines ({SVM}), proposed by {V}.
{V}apnik (1995) and a sparse approximation scheme that resembles
the basis pursuit denoising algorithm ({C}hen, 1995; {C}hen, {D}onoho,
and {S}aunders, 1995). {SVM} is a technique that can be derived from
the structural risk minimization principle ({V}apnik, 1982) and can
be used to estimate the parameters of several different approximation
schemes, including radial basis functions, algebraic and trigonometric
polynomials, {B}-splines, and some forms of multilayer perceptrons.
{B}asis pursuit denoising is a sparse approximation technique in
which a function is reconstructed by using a small number of basis
functions chosen from a large set (the dictionary). {W}e show that
if the data are noiseless, the modified version of basis pursuit
denoising proposed in this article is equivalent to {SVM} in the
following sense: if applied to the same data set, the two techniques
give the same solution, which is obtained by solving the same quadratic
programming problem. {I}n the appendix, we present a derivation of
the {SVM} technique in one framework of regularization theory, rather
than statistical learning theory, establishing a connection between
{SVM}, sparse approximation, and regularization theory.},
keywords = {Algorithms, Automated, Biometry, Computers, DNA, Databases, Factual,
Fungal, Fungal Proteins, GTP-Binding Proteins, Gene Expression, Genes,
Learning, Markov Chains, Models, Neural Networks (Computer), Neurological,
Non-P.H.S., Non-U.S. Gov't, Nucleic Acid Hybridization, Open Reading
Frames, P.H.S., Pattern Recognition, Protein, Protein Structure,
Proteins, Reproducibility of Results, Research Support, Saccharomyces
cerevisiae, Sequence Alignment, Sequence Analysis, Software, Statistical,
Tertiary, U.S. Gov't, 9698353}
}
@article{Glaser2006Method,
author = {Glaser, F. and Morris, R. J. and Najmanovich, R. J. and Laskowski,
R. A. and Thornton, J. M. },
title = {A method for localizing ligand binding pockets in protein structures.},
journal = {Proteins},
year = {2006},
volume = {62},
pages = {479--488},
number = {2},
month = {February},
abstract = {The accurate identification of ligand binding sites in protein structures
can be valuable in determining protein function. Once the binding
site is known, it becomes easier to perform in silico and experimental
procedures that may allow the ligand type and the protein function
to be determined. For example, binding pocket shape analysis relies
heavily on the correct localization of the ligand binding site. We
have developed SURFNET-ConSurf, a modular, two-stage method for identifying
the location and shape of potential ligand binding pockets in protein
structures. In the first stage, the SURFNET program identifies clefts
in the protein surface that are potential binding sites. In the second
stage, these clefts are trimmed in size by cutting away regions distant
from highly conserved residues, as defined by the ConSurf-HSSP database.
The largest clefts that remain tend to be those where ligands bind.
To test the approach, we analyzed a nonredundant set of 244 protein
structures from the PDB and found that SURFNET-ConSurf identifies
a ligand binding pocket in 75\% of them. The trimming procedure reduces
the original cleft volumes by 30\% on average, while still encompassing
an average 87\% of the ligand volume. From the analysis of the results
we conclude that for those cases in which the ligands are found in
large, highly conserved clefts, the combined SURFNET-ConSurf method
gives pockets that are a better match to the ligand shape and location.
We also show that this approach works better for enzymes than for
nonenzyme proteins.},
address = {European Bioinformatics Institute, European Molecular Biology Laboratory,
Wellcome Trust Genome Campus, Hinxton, Cambridge, United Kingdom.
fabian@ebi.ac.uk},
citeulike-article-id = {472870},
doi = {http://dx.doi.org/10.1002/prot.20769},
issn = {1097-0134},
keywords = {ligand-volume, protein-ligand, surface},
posted-at = {2006-01-20 20:31:25},
priority = {2},
url = {http://dx.doi.org/10.1002/prot.20769}
}
@article{Glotsos2004Automated,
author = {Dimitris Glotsos and Panagiota Spyridonos and Dionisis Cavouras and
Panagiota Ravazoula and Petroula-Arampantoni Dadioti and George Nikiforidis},
title = {Automated segmentation of routinely hematoxylin-eosin-stained microscopic
images by combining support vector machine clustering and active
contour models.},
journal = {Anal {Q}uant {C}ytol {H}istol},
year = {2004},
volume = {26},
pages = {331-40},
number = {6},
month = {Dec},
abstract = {O{BJECTIVE}: {T}o develop a method for the automated segmentation
of images of routinely hematoxylin-eosin ({H}-{E})-stained microscopic
sections to guarantee correct results in computer-assisted microscopy.
{STUDY} {DESIGN}: {C}linical material was composed 50 {H}-{E}-stained
biopsies of astrocytomas and 50 {H}-{E}-stained biopsies of urinary
bladder cancer. {T}he basic idea was to use a support vector machine
clustering ({SVMC}) algorithm to provide gross segmentation of regions
holding nuclei and subsequently to refine nuclear boundary detection
with active contours. {T}he initialization coordinates of the active
contour model were defined using a {SVMC} pixel-based classification
algorithm that discriminated nuclear regions from the surrounding
tissue. {S}tarting from the boundaries of these regions, the snake
fired and propagated until converging to nuclear boundaries. {RESULTS}:
{T}he method was validated for 2 different types of {H}-{E}-stained
images. {R}esults were evaluated by 2 histopathologists. {O}n average,
94\% of nuclei were correctly delineated. {CONCLUSION}: {T}he proposed
algorithm could be of value in computer-based systems for automated
interpretation of microscopic images.},
keywords = {Adenosinetriphosphatase, Adolescent, Adult, Algorithms, Amino Acid
Sequence, Amino Acids, Animals, Astrocytoma, Automated, Automation,
Base Sequence, Bayes Theorem, Biological, Biopsy, Bladder Neoplasms,
Breast Neoplasms, Carbohydrate Conformation, Carbohydrate Sequence,
Cattle, Cell Cycle Proteins, Cell Nucleus, Computational Biology,
Computer Simulation, Computer-Assisted, Crystallography, DNA, Databases,
Diagnosis, Differential, Eosine Yellowish-(YS), Exoribonucleases,
Factual, False Negative Reactions, False Positive Reactions, Female,
Gene Expression, Gene Expression Profiling, Genes, Genetic, Genetic
Techniques, Genetic Vectors, Genome, Hematoxylin, Histocompatibility
Antigens Class I, Human, Humans, Image Interpretation, Image Processing,
Introns, Least-Squares Analysis, MHC Class I, Major Histocompatibility
Complex, Markov Chains, Messenger, Mice, Middle Aged, Models, Molecular
Structure, Monosaccharides, Multigene Family, Mutation, Neoplasms,
Neural Networks (Computer), Non-P.H.S., Non-U.S. Gov't, Nonparametric,
Nucleotidyltransferases, Observer Variation, Oligonucleotide Array
Sequence Analysis, P.H.S., Pattern Recognition, Peptides, Phenotype,
Phylogeny, Plants, Poly A, Polysaccharides, Predictive Value of Tests,
Protein, Protein Biosynthesis, Protein Kinase Inhibitors, Protein
Structure, Proteins, RNA, RNA Helicases, RNA Splicing, Rats, Reproducibility
of Results, Research Support, Retrospective Studies, Saccharomyces
cerevisiae, Saccharomyces cerevisiae Proteins, Secondary, Sensitivity
and Specificity, Sequence Alignment, Software, Species Specificity,
Staining and Labeling, Statistics, Theoretical, Transcription, U.S.
Gov't, Ultrasonography, X-Ray, 15678615}
}
@article{Glotsos2004Computer-based,
author = {Dimitris Glotsos and Panagiota Spyridonos and Panagiotis Petalas
and Dionisis Cavouras and Panagiota Ravazoula and Petroula-Arampatoni
Dadioti and Ioanna Lekka and George Nikiforidis},
title = {Computer-based malignancy grading of astrocytomas employing a support
vector machine classifier, the {WHO} grading system and the regular
hematoxylin-eosin diagnostic staining procedure.},
journal = {Anal {Q}uant {C}ytol {H}istol},
year = {2004},
volume = {26},
pages = {77-83},
number = {2},
month = {Apr},
abstract = {O{BJECTIVE}: {T}o investigate and develop an automated technique for
astrocytoma malignancy grading compatible with the clinical routine.
{STUDY} {DESIGN}: {O}ne hundred forty biopsies of astrocytomas were
collected from 2 hospitals. {T}he degree of tumor malignancy was
defined as low or high according to the {W}orld {H}ealth {O}rganization
grading system. {F}rom each biopsy, images were digitized and segmented
to isolate nuclei from background tissue. {M}orphologic and textural
nuclear features were quantified to encode tumor malignancy. {E}ach
case was represented by a 40-dimensional feature vector. {A}n exhaustive
search procedure in feature space was utilized to determine the best
feature combination that resulted in the smallest classification
error. {L}ow and high grade tumors were discriminated using support
vector machines ({SVM}s). {T}o evaluate the system performance, all
available data were split randomly into training and test sets. {RESULTS}:
{T}he best vector combination consisted of 3 textural and 2 morphologic
features. {L}ow and high grade cases were discriminated with an accuracy
of 90.7\% and 88.9\%, respectively, using an {SVM} classifier with
polynomial kernel of degree 2. {CONCLUSION}: {T}he proposed methodology
was based on standards that are common in daily clinical practice
and might be used in parallel with conventional grading as a second-opinion
tool to reduce subjectivity in the classification of astrocytomas.},
keywords = {Amino Acids, Antibodies, Artificial Intelligence, Astrocytoma, Biological,
Biopsy, Brain, Brain Mapping, Brain Neoplasms, Calibration, Comparative
Study, Computational Biology, Computer-Assisted, Cysteine, Cystine,
Electrodes, Electroencephalography, Eosine Yellowish-(YS), Evoked
Potentials, Female, Hematoxylin, Horseradish Peroxidase, Humans,
Image Processing, Imagery (Psychotherapy), Imagination, Laterality,
Male, Monoclonal, Movement, Neoplasms, Non-P.H.S., Non-U.S. Gov't,
P.H.S., Perception, Principal Component Analysis, Protein, Protein
Array Analysis, Proteins, Research Support, Sensitivity and Specificity,
Sequence Analysis, Software, Tumor Markers, U.S. Gov't, User-Computer
Interface, World Health Organization, 15131894}
}
@article{Golland2005Detection,
author = {Polina Golland and W. Eric L Grimson and Martha E Shenton and Ron
Kikinis},
title = {Detection and analysis of statistical differences in anatomical shape.},
journal = {Med {I}mage {A}nal},
year = {2005},
volume = {9},
pages = {69-86},
number = {1},
month = {Feb},
abstract = {We present a computational framework for image-based analysis and
interpretation of statistical differences in anatomical shape between
populations. {A}pplications of such analysis include understanding
developmental and anatomical aspects of disorders when comparing
patients versus normal controls, studying morphological changes caused
by aging, or even differences in normal anatomy, for example, differences
between genders. {O}nce a quantitative description of organ shape
is extracted from input images, the problem of identifying differences
between the two groups can be reduced to one of the classical questions
in machine learning of constructing a classifier function for assigning
new examples to one of the two groups while making as few misclassifications
as possible. {T}he resulting classifier must be interpreted in terms
of shape differences between the two groups back in the image domain.
{W}e demonstrate a novel approach to such interpretation that allows
us to argue about the identified shape differences in anatomically
meaningful terms of organ deformation. {G}iven a classifier function
in the feature space, we derive a deformation that corresponds to
the differences between the two classes while ignoring shape variability
within each class. {B}ased on this approach, we present a system
for statistical shape analysis using distance transforms for shape
representation and the support vector machines learning algorithm
for the optimal classifier estimation and demonstrate it on artificially
generated data sets, as well as real medical studies.},
doi = {10.1016/j.media.2004.07.003},
keywords = {Algorithms, Amino Acid, Artificial Intelligence, Ascomycota, Automated,
Base Sequence, Chromosome Mapping, Codon, Colonic Neoplasms, Comparative
Study, Computer-Assisted, Crystallography, DNA, DNA Primers, Databases,
Diagnostic Imaging, Gene Expression Profiling, Hordeum, Host-Parasite
Relations, Humans, Image Interpretation, Informatics, Kinetics, Magnetic
Resonance Spectroscopy, Models, Nanotechnology, Non-P.H.S., Non-U.S.
Gov't, Oligonucleotide Array Sequence Analysis, P.H.S., Pattern Recognition,
Plant, Plants, Predictive Value of Tests, Protein, Research Support,
Selection (Genetics), Sequence Alignment, Sequence Analysis, Sequence
Homology, Skin, Software, Statistical, Theoretical, Thermodynamics,
U.S. Gov't, Viral Proteins, X-Ray, 15581813},
pii = {S1361-8415(04)00059-3},
url = {http://dx.doi.org/10.1016/j.media.2004.07.003}
}
@article{Graumann2004Applicability,
author = {Johannes Graumann and Leslie A Dunipace and Jae Hong Seol and W.
Hayes McDonald and John R Yates and Barbara J Wold and Raymond J
Deshaies},
title = {Applicability of tandem affinity purification {M}ud{PIT} to pathway
proteomics in yeast.},
journal = {Mol {C}ell {P}roteomics},
year = {2004},
volume = {3},
pages = {226-37},
number = {3},
month = {Mar},
abstract = {A combined multidimensional chromatography-mass spectrometry approach
known as "{M}ud{PIT}" enables rapid identification of proteins that
interact with a tagged bait while bypassing some of the problems
associated with analysis of polypeptides excised from {SDS}-polyacrylamide
gels. {H}owever, the reproducibility, success rate, and applicability
of {M}ud{PIT} to the rapid characterization of dozens of proteins
have not been reported. {W}e show here that {M}ud{PIT} reproducibly
identified bona fide partners for budding yeast {G}cn5p. {A}dditionally,
we successfully applied {M}ud{PIT} to rapidly screen through a collection
of tagged polypeptides to identify new protein interactions. {T}wenty-five
proteins involved in transcription and progression through mitosis
were modified with a new tandem affinity purification ({TAP}) tag.
{TAP}-{M}ud{PIT} analysis of 22 yeast strains that expressed these
tagged proteins uncovered known or likely interacting partners for
21 of the baits, a figure that compares favorably with traditional
approaches. {T}he proteins identified here comprised 102 previously
known and 279 potential physical interactions. {E}ven for the intensively
studied {S}wi2p/{S}nf2p, the catalytic subunit of the {S}wi/{S}nf
chromatin remodeling complex, our analysis uncovered a new interacting
protein, {R}tt102p. {R}eciprocal tagging and {TAP}-{M}ud{PIT} analysis
of {R}tt102p revealed subunits of both the {S}wi/{S}nf and {RSC}
complexes, identifying {R}tt102p as a common interactor with, and
possible integral component of, these chromatin remodeling machines.
{O}ur experience indicates it is feasible for an investigator working
with a single ion trap instrument in a conventional molecular/cellular
biology laboratory to carry out proteomic characterization of a pathway,
organelle, or process (i.e. "pathway proteomics") by systematic application
of {TAP}-{M}ud{PIT}.},
doi = {10.1074/mcp.M300099-MCP200},
pdf = {../local/Graumann2004Applicability.pdf},
file = {Graumann2004Applicability.pdf:local/Graumann2004Applicability.pdf:PDF},
keywords = {Affinity Labels, Comparative Study, Electrospray Ionization, Genetic,
Mass, Mitosis, Non-P.H.S., Non-U.S. Gov't, P.H.S., Protein Interaction
Mapping, Proteome, Proteomics, Research Support, Saccharomyces cerevisiae,
Saccharomyces cerevisiae Proteins, Signal Transduction, Spectrometry,
Transcription, U.S. Gov't, 14660704},
owner = {vert},
pii = {M300099-MCP200},
url = {http://dx.doi.org/10.1074/mcp.M300099-MCP200}
}
@article{Gulukota1997Two,
author = {K. Gulukota and J. Sidney and A. Sette and C. DeLisi},
title = {Two complementary methods for predicting peptides binding major histocompatibility
complex molecules.},
journal = {J. Mol. Biol.},
year = {1997},
volume = {267},
pages = {1258--1267},
number = {5},
month = {Apr},
abstract = {Peptides that bind to major histocompatibility complex products (MHC)
are known to exhibit certain sequence motifs which, though common,
are neither necessary nor sufficient for binding: MHCs bind certain
peptides that do not have the characteristic motifs and only about
30\% of the peptides having the required motif, bind. In order to
develop and test more accurate methods we measured the binding affinity
of 463 nonamer peptides to HLA-A2.1. We describe two methods for
predicting whether a given peptide will bind to an MHC and apply
them to these peptides. One method is based on simulating a neural
network and another, called the polynomial method, is based on statistical
parameter estimation assuming independent binding of the side-chains
of residues. We compare these methods with each other and with standard
motif-based methods. The two methods are complementary, and both
are superior to sequence motifs. The neural net is superior to simple
motif searches in eliminating false positives. Its behavior can be
coarsely tuned to the strength of binding desired and it is extendable
in a straightforward fashion to other alleles. The polynomial method,
on the other hand, has high sensitivity and is a superior method
for eliminating false negatives. We discuss the validity of the independent
binding assumption in such predictions.},
doi = {10.1006/jmbi.1997.0937},
keywords = {Artificial Intelligence; Computing Methodologies; HLA-A2 Antigen;
Neural Networks (Computer); Oligopeptides; Protein Binding; Reproducibility
of Results},
owner = {laurent},
pii = {S0022-2836(97)90937-2},
pmid = {9150410},
timestamp = {2007.01.27},
url = {http://dx.doi.org/10.1006/jmbi.1997.0937}
}
@article{Gygi1999Quantitative,
author = {S. P. Gygi and B. Rist and S. A. Gerber and F. Turecek and M. H.
Gelb and R. Aebersold},
title = {Quantitative analysis of complex protein mixtures using isotope-coded
affinity tags.},
journal = {Nat Biotechnol},
year = {1999},
volume = {17},
pages = {994--999},
number = {10},
month = {Oct},
abstract = {We describe an approach for the accurate quantification and concurrent
sequence identification of the individual proteins within complex
mixtures. The method is based on a class of new chemical reagents
termed isotope-coded affinity tags (ICATs) and tandem mass spectrometry.
Using this strategy, we compared protein expression in the yeast
Saccharomyces cerevisiae, using either ethanol or galactose as a
carbon source. The measured differences in protein expression correlated
with known yeast metabolic function under glucose-repressed conditions.
The method is redundant if multiple cysteinyl residues are present,
and the relative quantification is highly accurate because it is
based on stable isotope dilution techniques. The ICAT approach should
provide a widely applicable means to compare quantitatively global
protein expression in cells and tissues.},
doi = {10.1038/13690},
institution = {Department of Molecular Biotechnology, University of Washington,
Box 357730, Seattle WA 98195-7730, USA.},
keywords = {Affinity Labels; Amino Acid Sequence; Chromatography, Liquid; Isotope
Labeling; Mass Spectrometry; Proteins},
owner = {phupe},
pmid = {10504701},
timestamp = {2010.08.19},
url = {http://dx.doi.org/10.1038/13690}
}
@article{Haasdonk2005Feature,
author = {Bernard Haasdonk},
title = {Feature space interpretation of {SVM}s with indefinite kernels.},
journal = {I{EEE} {T}rans {P}attern {A}nal {M}ach {I}ntell},
year = {2005},
volume = {27},
pages = {482-92},
number = {4},
month = {Apr},
abstract = {Kernel methods are becoming increasingly popular for various kinds
of machine learning tasks, the most famous being the support vector
machine ({SVM}) for classification. {T}he {SVM} is well understood
when using conditionally positive definite (cpd) kernel functions.
{H}owever, in practice, non-cpd kernels arise and demand application
in {SVM}s. {T}he procedure of "plugging" these indefinite kernels
in {SVM}s often yields good empirical classification results. {H}owever,
they are hard to interpret due to missing geometrical and theoretical
understanding. {I}n this paper, we provide a step toward the comprehension
of {SVM} classifiers in these situations. {W}e give a geometric interpretation
of {SVM}s with indefinite kernel functions. {W}e show that such {SVM}s
are optimal hyperplane classifiers not by margin maximization, but
by minimization of distances between convex hulls in pseudo-{E}uclidean
spaces. {B}y this, we obtain a sound framework and motivation for
indefinite {SVM}s. {T}his interpretation is the basis for further
theoretical analysis, e.g., investigating uniqueness, and for the
derivation of practical guidelines like characterizing the suitability
of indefinite {SVM}s.},
doi = {10.1109/TPAMI.2005.78},
pdf = {../local/Haasdonk2005Feature.pdf},
file = {Haasdonk2005Feature.pdf:local/Haasdonk2005Feature.pdf:PDF},
keywords = {Algorithms, Animals, Antibiotics, Antineoplastic, Artificial Intelligence,
Automated, Automatic Data Processing, Butadienes, Chloroplasts, Cluster
Analysis, Comparative Study, Computer Simulation, Computer-Assisted,
Computing Methodologies, Database Management Systems, Databases,
Diagnosis, Disinfectants, Dose-Response Relationship, Drug, Drug
Toxicity, Electrodes, Electroencephalography, Ethylamines, Expert
Systems, Factual, Feedback, Fungicides, Gene Expression Profiling,
Genes, Genetic Markers, Humans, Image Enhancement, Image Interpretation,
Implanted, Industrial, Information Storage and Retrieval, Kidney,
Kidney Tubules, MEDLINE, Male, Mercuric Chloride, Microarray Analysis,
Molecular Biology, Motor Cortex, Movement, Natural Language Processing,
Neural Networks (Computer), Non-P.H.S., Non-U.S. Gov't, Numerical
Analysis, Pattern Recognition, Plant Proteins, Predictive Value of
Tests, Proteins, Proteome, Proximal, Puromycin Aminonucleoside, Rats,
Reproducibility of Results, Research Support, Sensitivity and Specificity,
Signal Processing, Sprague-Dawley, Subcellular Fractions, Terminology,
Therapy, Time Factors, Toxicogenetics, U.S. Gov't, User-Computer
Interface, 15794155},
url = {http://dx.doi.org/10.1109/TPAMI.2005.78}
}
@article{Harborth2003Sequence,
author = {Harborth, J. and Elbashir, S. M. and Vandenburgh, K. and Manninga,
H. and Scaringe, S. A. and Weber, K. and Tuschl, T.},
title = {Sequence, chemical, and structural variation of small interfering
{RNA}s and short hairpin {RNA}s and the effect on mammalian gene
silencing.},
journal = {Antisense {N}ucleic {A}cid. {D}rug. {D}ev.},
year = {2003},
volume = {13},
pages = {83-105},
number = {2},
month = {Apr},
abstract = {Small interfering {RNA}s (si{RNA}s) induce sequence-specific gene
silencing in mammalian cells and guide m{RNA} degradation in the
process of {RNA} interference ({RNA}i). {B}y targeting endogenous
lamin {A}/{C} m{RNA} in human {H}e{L}a or mouse {SW}3{T}3 cells,
we investigated the positional variation of si{RNA}-mediated gene
silencing. {W}e find cell-type-dependent global effects and cell-type-independent
positional effects. {H}e{L}a cells were about 2-fold more responsive
to si{RNA}s than {SW}3{T}3 cells but displayed a very similar pattern
of positional variation of lamin {A}/{C} silencing. {I}n {H}e{L}a
cells, 26 of 44 tested standard 21-nucleotide (nt) si{RNA} duplexes
reduced the protein expression by at least 90\%, and only 2 duplexes
reduced the lamin {A}/{C} proteins to <50\%. {F}luorescent chromophores
did not perturb gene silencing when conjugated to the 5'-end or 3'-end
of the sense si{RNA} strand and the 5'-end of the antisense si{RNA}
strand, but conjugation to the 3'-end of the antisense si{RNA} abolished
gene silencing. {RN}ase-protecting phosphorothioate and 2'-fluoropyrimidine
{RNA} backbone modifications of si{RNA}s did not significantly affect
silencing efficiency, although cytotoxic effects were observed when
every second phosphate of an si{RNA} duplex was replaced by phosphorothioate.
{S}ynthetic {RNA} hairpin loops were subsequently evaluated for lamin
{A}/{C} silencing as a function of stem length and loop composition.
{A}s long as the 5'-end of the guide strand coincided with the 5'-end
of the hairpin {RNA}, 19-29 base pair (bp) hairpins effectively silenced
lamin {A}/{C}, but when the hairpin started with the 5'-end of the
sense strand, only 21-29 bp hairpins were highly active.},
doi = {10.1089/108729003321629638},
keywords = {Adaptor Protein Complex alpha Subunits, Animal, Animals, Antisense,
Apolipoproteins B, Base Sequence, Biological Transport, Blotting,
Catalytic, Cell Line, Cell Membrane, Cell Survival, Chemical, Cholesterol,
Clathrin, Clathrin Heavy Chains, Disease Models, Endocytosis, Epidermal
Growth Factor, Fluorescence, Gene Expression Profiling, Gene Silencing,
Gene Therapy, Hela Cells, Humans, Injections, Intravenous, Jejunum,
Kinetics, Lamin Type A, Liver, Messenger, Metabolic Syndrome X, Mice,
Microscopy, Models, Molecular Sequence Data, NIH 3T3 Cells, Non-U.S.
Gov't, Nucleic Acid, Oligonucleotides, Open Reading Frames, Post-Transcriptional,
Protein Isoforms, Pyrimidines, RNA, RNA Interference, RNA Processing,
RNA Stability, Research Support, Reverse Transcriptase Polymerase
Chain Reaction, Sensitivity and Specificity, Sequence Homology, Small
Interfering, Subcellular Fractions, Swiss 3T3 Cells, Thionucleotides,
Time Factors, Transfection, Transferrin, Transgenic, Tumor, Western,
12804036},
url = {http://dx.doi.org/10.1089/108729003321629638}
}
@article{Henikoff1992Amino,
author = {Henikoff, S. and Henikoff, J. G.},
title = {Amino acid substitution matrices from protein blocks.},
journal = {Proc. Natl. Acad. Sci. USA},
year = {1992},
volume = {89},
pages = {10915--10919},
number = {22},
month = {Nov},
abstract = {Methods for alignment of protein sequences typically measure similarity
by using a substitution matrix with scores for all possible exchanges
of one amino acid with another. The most widely used matrices are
based on the Dayhoff model of evolutionary rates. Using a different
approach, we have derived substitution matrices from about 2000 blocks
of aligned sequence segments characterizing more than 500 groups
of related proteins. This led to marked improvements in alignments
and in searches using queries from each of the groups.},
keywords = {Algorithms; Amino Acid Sequence; Animals; Caenorhabditis elegans;
Drosophila; Lod Score; Mathematics; Molecular Sequence Data; Probability;
Proteins; Sequence Homology, Amino Acid; Software},
owner = {laurent},
pmid = {1438297},
timestamp = {2008.01.15}
}
@article{Hizukuri2004Extraction,
author = {Yoshiyuki Hizukuri and Yoshihiro Yamanishi and Kosuke Hashimoto and
Minoru Kanehisa},
title = {Extraction of species-specific glycan substructures.},
journal = {Genome {I}nform {S}er {W}orkshop {G}enome {I}nform},
year = {2004},
volume = {15},
pages = {69-81},
number = {1},
abstract = {Glycans, which are carbohydrate sugar chains attached to some lipids
or proteins, have a huge variety of structures and play a key role
in cell communication, protein interaction and immunity. {T}he availability
of a number of glycan structures stored in the {KEGG}/{GLYCAN} database
makes it possible for us to conduct a large-scale comparative research
of glycans. {I}n this paper, we present a novel approach to compare
glycan structures and extract characteristic glycan substructures
of certain organisms. {I}n the algorithm we developed a new similarity
measure of glycan structures taking into account of several biological
aspects of glycan synthesis and glycosyltransferases, and we confirmed
the validity of our similarity measure by conducting experiments
on its ability to classify glycans between organisms in the framework
of a support vector machine. {F}inally, our method successfully extracted
a set of candidates of substructrues which are characteristic to
human, rat, mouse, bovine, pig, chicken, yeast, wheat and sycamore,
respectively. {W}e confirmed that the characteristic substructures
extracted by our method correspond to the substructures which are
known as the species-specific sugar chain of gamma-glutamyltranspeptidases
in the kidney.},
pdf = {../local/Hizukuri2004Extraction.pdf},
file = {Hizukuri2004Extraction.pdf:local/Hizukuri2004Extraction.pdf:PDF},
keywords = {Amino Acid Sequence, Animals, Carbohydrate Conformation, Carbohydrate
Sequence, Cattle, Computer Simulation, Databases, Genes, Histocompatibility
Antigens Class I, Humans, Least-Squares Analysis, MHC Class I, Major
Histocompatibility Complex, Mice, Monosaccharides, Non-U.S. Gov't,
Peptides, Phylogeny, Plants, Polysaccharides, Protein, Rats, Research
Support, Saccharomyces cerevisiae, Species Specificity, 15712111},
url = {http://www.jsbi.org/journal/IBSB04/IBSB04F018.html}
}
@article{Ho2002Systematic,
author = {Yuen Ho and Albrecht Gruhler and Adrian Heilbut and Gary D Bader
and Lynda Moore and Sally-Lin Adams and Anna Millar and Paul Taylor
and Keiryn Bennett and Kelly Boutilier and Lingyun Yang and Cheryl
Wolting and Ian Donaldson and Søren Schandorff and Juanita Shewnarane
and Mai Vo and Joanne Taggart and Marilyn Goudreault and Brenda Muskat
and Cris Alfarano and Danielle Dewar and Zhen Lin and Katerina Michalickova
and Andrew R Willems and Holly Sassi and Peter A Nielsen and Karina
J Rasmussen and Jens R Andersen and Lene E Johansen and Lykke H Hansen
and Hans Jespersen and Alexandre Podtelejnikov and Eva Nielsen and
Janne Crawford and Vibeke Poulsen and Birgitte D Sørensen and Jesper
Matthiesen and Ronald C Hendrickson and Frank Gleeson and Tony Pawson
and Michael F Moran and Daniel Durocher and Matthias Mann and Christopher
W V Hogue and Daniel Figeys and Mike Tyers},
title = {Systematic identification of protein complexes in {S}accharomyces
cerevisiae by mass spectrometry.},
journal = {Nature},
year = {2002},
volume = {415},
pages = {180-3},
number = {6868},
month = {Jan},
abstract = {The recent abundance of genome sequence data has brought an urgent
need for systematic proteomics to decipher the encoded protein networks
that dictate cellular function. {T}o date, generation of large-scale
protein-protein interaction maps has relied on the yeast two-hybrid
system, which detects binary interactions through activation of reporter
gene expression. {W}ith the advent of ultrasensitive mass spectrometric
protein identification methods, it is feasible to identify directly
protein complexes on a proteome-wide scale. {H}ere we report, using
the budding yeast {S}accharomyces cerevisiae as a test case, an example
of this approach, which we term high-throughput mass spectrometric
protein complex identification ({HMS}-{PCI}). {B}eginning with 10\%
of predicted yeast proteins as baits, we detected 3,617 associated
proteins covering 25\% of the yeast proteome. {N}umerous protein
complexes were identified, including many new interactions in various
signalling pathways and in the {DNA} damage response. {C}omparison
of the {HMS}-{PCI} data set with interactions reported in the literature
revealed an average threefold higher success rate in detection of
known complexes compared with large-scale two-hybrid studies. {G}iven
the high degree of connectivity observed in this study, even partial
{HMS}-{PCI} coverage of complex proteomes, including that of humans,
should allow comprehensive identification of cellular networks.},
doi = {10.1038/415180a},
pdf = {../local/ho02.pdf},
file = {ho02.pdf:local/ho02.pdf:PDF},
keywords = {Affinity Labels, Amino Acid Sequence, Animals, Cell Cycle Proteins,
Cloning, Comparative Study, DNA, DNA Damage, DNA Repair, Electrospray
Ionization, Fungal, Genetic, Humans, Macromolecular Substances, Mass,
Mitosis, Molecular, Molecular Sequence Data, Non-P.H.S., Non-U.S.
Gov't, P.H.S., Phosphoric Monoester Hydrolases, Protein Binding,
Protein Interaction Mapping, Protein Kinases, Proteome, Proteomics,
Research Support, Ribonucleoproteins, Ribosomes, Saccharomyces cerevisiae,
Saccharomyces cerevisiae Proteins, Sequence Alignment, Signal Transduction,
Spectrometry, Spectrum Analysis, Transcription, U.S. Gov't, 11805813},
owner = {vert},
pii = {415180a},
url = {http://dx.doi.org/10.1038/415180a}
}
@article{Huang2006Ligsite,
author = {Bingding Huang and Michael Schroeder},
title = {LIGSITEcsc: predicting ligand binding sites using the Connolly surface
and degree of conservation.},
journal = {BMC Struct Biol},
year = {2006},
volume = {6},
pages = {19},
abstract = {BACKGROUND: Identifying pockets on protein surfaces is of great importance
for many structure-based drug design applications and protein-ligand
docking algorithms. Over the last ten years, many geometric methods
for the prediction of ligand-binding sites have been developed. RESULTS:
We present LIGSITEcsc, an extension and implementation of the LIGSITE
algorithm. LIGSITEcsc is based on the notion of surface-solvent-surface
events and the degree of conservation of the involved surface residues.
We compare our algorithm to four other approaches, LIGSITE, CAST,
PASS, and SURFNET, and evaluate all on a dataset of 48 unbound/bound
structures and 210 bound-structures. LIGSITEcsc performs slightly
better than the other tools and achieves a success rate of 71\% and
75\%, respectively. CONCLUSION: The use of the Connolly surface leads
to slight improvements, the prediction re-ranking by conservation
to significant improvements of the binding site predictions. A web
server for LIGSITEcsc and its source code is available at scoppi.biotec.tu-dresden.de/pocket},
doi = {10.1186/1472-6807-6-19},
institution = {atics Group, Biotechnological Center, Technical University Dresden,
Germany. bingding.huang@biotec.tu-dresden.de},
keywords = {Algorithms; Binding Sites; Databases, Protein; Ligands; Models, Molecular;
Proteins, chemistry},
owner = {bricehoffmann},
pii = {1472-6807-6-19},
pmid = {16995956},
timestamp = {2009.02.13},
url = {http://dx.doi.org/10.1186/1472-6807-6-19}
}
@article{Bild2003,
author = {Huang, E. and Ishida, S. and Pittman, J. and Dressman, H. and Bild,
A. and Kloos, M. and D'Amico, M. and Pestell, R. G. and West, M.
and Nevins, J. R.},
title = {Gene expression phenotypic models that predict the activity of oncogenic
pathways},
journal = {Nat {G}enet},
year = {2003},
volume = {34},
pages = {226-30},
number = {2},
abstract = {High-density {DNA} microarrays measure expression of large numbers
of genes in one assay. {T}he ability to find underlying structure
in complex gene expression data sets and rigorously test association
of that structure with biological conditions is essential to developing
multi-faceted views of the gene activity that defines cellular phenotype.
{W}e sought to connect features of gene expression data with biological
hypotheses by integrating 'metagene' patterns from {DNA} microarray
experiments in the characterization and prediction of oncogenic phenotypes.
{W}e applied these techniques to the analysis of regulatory pathways
controlled by the genes {HRAS} ({H}arvey rat sarcoma viral oncogene
homolog), {MYC} (myelocytomatosis viral oncogene homolog) and {E}2{F}1,
{E}2{F}2 and {E}2{F}3 (encoding {E}2{F} transcription factors 1,
2 and 3, respectively). {T}he phenotypic models accurately predict
the activity of these pathways in the context of normal cell proliferation.
{M}oreover, the metagene models trained with gene expression patterns
evoked by ectopic production of {M}yc or {R}as proteins in primary
tissue culture cells properly predict the activity of in vivo tumor
models that result from deregulation of the {MYC} or {HRAS} pathways.
{W}e conclude that these gene expression phenotypes have the potential
to characterize the complex genetic alterations that typify the neoplastic
state, whether in vitro or in vivo, in a way that truly reflects
the complexity of the regulatory pathways that are affected.},
keywords = {Animals *Cell Cycle Proteins *DNA-Binding Proteins E2F Transcription
Factors E2F1 Transcription Factor E2F2 Transcription Factor E2F3
Transcription Factor Female *Gene Expression Gene Expression Profiling
Gene Expression Regulation, Neoplastic Genes, myc Genes, ras Mammary
Neoplasms, Experimental/genetics Mice Mice, Transgenic *Models, Genetic
Oligonucleotide Array Sequence Analysis *Oncogenes Phenotype Transcription
Factors/genetics}
}
@article{Huebert2006Genome-wide,
author = {Dana J Huebert and Michael Kamal and Aisling O'Donovan and Bradley
E Bernstein},
title = {Genome-wide analysis of histone modifications by ChIP-on-chip.},
journal = {Methods},
year = {2006},
volume = {40},
pages = {365--369},
number = {4},
month = {Dec},
abstract = {Post-translational modifications to histone proteins regulate the
packaging of genomic DNA into chromatin, gene activity and other
functions of the genome. They are understood to play key roles in
embryonic development and disease pathogenesis. Recent advances in
technology have made it possible to analyze chromatin structure genome-wide
in mammalian cells. Global patterns of histone modifications can
be observed using a technique called ChIP-on-chip, which combines
the specificity of chromatin immunoprecipitation with the unbiased,
high-throughput capabilities of microarrays. The resulting maps provide
insight into the functions of, and relationships between, different
modifications. Here, we provide validated ChIP-on-chip methods for
analyzing histone modification patterns at genome-scale in mammalian
cells.},
doi = {10.1016/j.ymeth.2006.07.032},
institution = {Molecular Pathology Unit and Center for Cancer Research, Massachusetts
General Hospital, Charlestown, MA 02129, USA.},
keywords = {Animals; Chromatin Immunoprecipitation; Chromosomes, Mammalian; Genomics;
Histone Code; Histones; Oligonucleotide Array Sequence Analysis;
Protein Processing, Post-Translational},
owner = {phupe},
pii = {S1046-2023(06)00227-1},
pmid = {17101450},
timestamp = {2010.08.09},
url = {http://dx.doi.org/10.1016/j.ymeth.2006.07.032}
}
@article{Ikeda2005asymptotic,
author = {Kazushi Ikeda and Tsutomu Aoishi},
title = {An asymptotic statistical analysis of support vector machines with
soft margins.},
journal = {Neural {N}etw},
year = {2005},
volume = {18},
pages = {251-9},
number = {3},
month = {Apr},
abstract = {The generalization properties of support vector machines ({SVM}s)
are examined. {F}rom a geometrical point of view, the estimated parameter
of an {SVM} is the one nearest the origin in the convex hull formed
with given examples. {S}ince introducing soft margins is equivalent
to reducing the convex hull of the examples, an {SVM} with soft margins
has a different learning curve from the original. {I}n this paper
we derive the asymptotic average generalization error of {SVM}s with
soft margins in simple cases, that is, only when the dimension of
inputs is one, and quantitatively show that soft margins increase
the generalization error.},
doi = {10.1016/j.neunet.2004.11.008},
pdf = {../local/Ikeda2005asymptotic.pdf},
file = {Ikeda2005asymptotic.pdf:local/Ikeda2005asymptotic.pdf:PDF},
keywords = {Apoptosis, Gene Expression Profiling, Humans, Neoplasms, Non-U.S.
Gov't, Oligonucleotide Array Sequence Analysis, Polymerase Chain
Reaction, Proteins, Research Support, Subcellular Fractions, Unknown
Primary, 15896573},
pii = {S0893-6080(05)00021-3},
url = {http://dx.doi.org/10.1016/j.neunet.2004.11.008}
}
@article{Jambon2003New,
author = {Martin Jambon and Anne Imberty and Gilbert Deléage and Christophe
Geourjon},
title = {A new bioinformatic approach to detect common 3D sites in protein
structures.},
journal = {Proteins},
year = {2003},
volume = {52},
pages = {137--145},
number = {2},
month = {Aug},
abstract = {An innovative bioinformatic method has been designed and implemented
to detect similar three-dimensional (3D) sites in proteins. This
approach allows the comparison of protein structures or substructures
and detects local spatial similarities: this method is completely
independent from the amino acid sequence and from the backbone structure.
In contrast to already existing tools, the basis for this method
is a representation of the protein structure by a set of stereochemical
groups that are defined independently from the notion of amino acid.
An efficient heuristic for finding similarities that uses graphs
of triangles of chemical groups to represent the protein structures
has been developed. The implementation of this heuristic constitutes
a software named SuMo (Surfing the Molecules), which allows the dynamic
definition of chemical groups, the selection of sites in the proteins,
and the management and screening of databases. To show the relevance
of this approach, we focused on two extreme examples illustrating
convergent and divergent evolution. In two unrelated serine proteases,
SuMo detects one common site, which corresponds to the catalytic
triad. In the legume lectins family composed of >100 structures that
share similar sequences and folds but may have lost their ability
to bind a carbohydrate molecule, SuMo discriminates between functional
and non-functional lectins with a selectivity of 96\%. The time needed
for searching a given site in a protein structure is typically 0.1
s on a PIII 800MHz/Linux computer; thus, in further studies, SuMo
will be used to screen the PDB.},
doi = {10.1002/prot.10339},
institution = {Institut de Biologie et Chimie des Protéines (IBCP), Lyon, France.},
keywords = {Algorithms; Catalytic Domain; Chymotrypsin, chemistry/genetics; Computational
Biology, methods; Evolution, Molecular; Fabaceae, chemistry; Models,
Molecular; Plant Lectins, chemistry/genetics; Protein Conformation;
Proteins, chemistry; Reproducibility of Results; Subtilisin, chemistry/genetics},
owner = {bricehoffmann},
pmid = {12833538},
timestamp = {2009.02.13},
url = {http://dx.doi.org/10.1002/prot.10339}
}
@article{Jensen2009STRING,
author = {Jensen, L.J. and Kuhn, M. and Stark, M. and Chaffron, S. and Creevey,
C. and Muller, J. and Doerks, T. and Julien, P. and Roth, A. and
Simonovic, M. and Bork, P. and von Mering, C.},
title = {STRING 8--a global view on proteins and their functional interactions
in 630 organisms.},
journal = {Nucleic Acids Res},
year = {2009},
volume = {37},
pages = {D412--D416},
number = {Database issue},
month = {Jan},
abstract = {Functional partnerships between proteins are at the core of complex
cellular phenotypes, and the networks formed by interacting proteins
provide researchers with crucial scaffolds for modeling, data reduction
and annotation. STRING is a database and web resource dedicated to
protein-protein interactions, including both physical and functional
interactions. It weights and integrates information from numerous
sources, including experimental repositories, computational prediction
methods and public text collections, thus acting as a meta-database
that maps all interaction evidence onto a common set of genomes and
proteins. The most important new developments in STRING 8 over previous
releases include a URL-based programming interface, which can be
used to query STRING from other resources, improved interaction prediction
via genomic neighborhood in prokaryotes, and the inclusion of protein
structures. Version 8.0 of STRING covers about 2.5 million proteins
from 630 organisms, providing the most comprehensive view on protein-protein
interactions currently available. STRING can be reached at http://string-db.org/.},
doi = {10.1093/nar/gkn760},
institution = {European Molecular Biology Laboratory, Heidelberg, Germany.},
keywords = {Databases, Protein; Genomics; Multiprotein Complexes; Protein Interaction
Mapping; Proteins; User-Computer Interface},
owner = {fantine},
pii = {gkn760},
pmid = {18940858},
timestamp = {2010.10.21},
url = {http://dx.doi.org/10.1093/nar/gkn760}
}
@article{Jeong2001,
author = {H. Jeong and S. P. Mason and A. L. Barabási and Z. N. Oltvai},
title = {Lethality and centrality in protein networks.},
journal = {Nature},
year = {2001},
volume = {411},
pages = {41--42},
number = {6833},
month = {May},
doi = {10.1038/35075138},
institution = {Department of Physics, University of Notre Dame, Notre Dame, Indiana
46556, USA.},
keywords = {Fungal Proteins, genetics/physiology; Gene Deletion; Protein Binding;
Proteome; Saccharomyces cerevisiae, genetics/physiology; Signal Transduction},
language = {eng},
medline-pst = {ppublish},
owner = {Andrei Zinovyev},
pii = {35075138},
pmid = {11333967},
timestamp = {2011.04.07},
url = {http://dx.doi.org/10.1038/35075138}
}
@article{Jin2007yeast,
author = {Fulai Jin and Larisa Avramova and Jing Huang and Tony Hazbun},
title = {A yeast two-hybrid smart-pool-array system for protein-interaction
mapping.},
journal = {Nat Methods},
year = {2007},
volume = {4},
pages = {405--407},
number = {5},
month = {May},
abstract = {We present here a new two-hybrid smart pool array (SPA) system in
which, instead of individual activation domain strains, well-designed
activation domain pools are screened in an array format that allows
built-in replication and prey-bait deconvolution. Using this method,
a Saccharomyces cerevisiae genome SPA increases yeast two-hybrid
screening efficiency by an order of magnitude.},
doi = {10.1038/nmeth1042},
institution = {Department of Molecular and Medical Pharmacology, David Geffen School
of Medicine, and the Molecular Biology Institute, University of California,
Los Angeles, California 90095, USA.},
keywords = {Genome, Fungal; Protein Interaction Mapping; Saccharomyces cerevisiae;
Saccharomyces cerevisiae Proteins; Two-Hybrid System Techniques},
owner = {phupe},
pii = {nmeth1042},
pmid = {17450148},
timestamp = {2010.09.01},
url = {http://dx.doi.org/10.1038/nmeth1042}
}
@article{Jones1997Development,
author = {G. Jones and P. Willett and R. C. Glen and A. R. Leach and R. Taylor},
title = {{D}evelopment and validation of a genetic algorithm for flexible
docking.},
journal = {J. Mol. Biol.},
year = {1997},
volume = {267},
pages = {727--748},
number = {3},
month = {Apr},
abstract = {Prediction of small molecule binding modes to macromolecules of known
three-dimensional structure is a problem of paramount importance
in rational drug design (the "docking" problem). We report the development
and validation of the program GOLD (Genetic Optimisation for Ligand
Docking). GOLD is an automated ligand docking program that uses a
genetic algorithm to explore the full range of ligand conformational
flexibility with partial flexibility of the protein, and satisfies
the fundamental requirement that the ligand must displace loosely
bound water on binding. Numerous enhancements and modifications have
been applied to the original technique resulting in a substantial
increase in the reliability and the applicability of the algorithm.
The advanced algorithm has been tested on a dataset of 100 complexes
extracted from the Brookhaven Protein DataBank. When used to dock
the ligand back into the binding site, GOLD achieved a 71\% success
rate in identifying the experimental binding mode.},
doi = {10.1006/jmbi.1996.0897},
keywords = {Algorithms, Binding Sites, Computer Simulation, Crystallography, Genetic,
Humans, Ligands, Models, Molecular, NADP, Protein Binding, Protein
Conformation, Proteins, Tetrahydrofolate Dehydrogenase, X-Ray, 9126849},
owner = {mahe},
pii = {97-9},
pmid = {9126849},
timestamp = {2006.09.05},
url = {http://dx.doi.org/10.1006/jmbi.1996.0897}
}
@article{Kahraman2007Shape,
author = {A. Kahraman and R. J. Morris and R. A. Laskowski and J. M. Thornton},
title = {Shape variation in protein binding pockets and their ligands.},
journal = {J. Mol. Biol.},
year = {2007},
volume = {368},
pages = {283--301},
number = {1},
month = {Apr},
abstract = {A common assumption about the shape of protein binding pockets is
that they are related to the shape of the small ligand molecules
that can bind there. But to what extent is that assumption true?
Here we use a recently developed shape matching method to compare
the shapes of protein binding pockets to the shapes of their ligands.
We find that pockets binding the same ligand show greater variation
in their shapes than can be accounted for by the conformational variability
of the ligand. This suggests that geometrical complementarity in
general is not sufficient to drive molecular recognition. Nevertheless,
we show when considering only shape and size that a significant proportion
of the recognition power of a binding pocket for its ligand resides
in its shape. Additionally, we observe a "buffer zone" or a region
of free space between the ligand and protein, which results in binding
pockets being on average three times larger than the ligand that
they bind.},
doi = {10.1016/j.jmb.2007.01.086},
keywords = {Binding Sites; Computer Simulation; Ligands; Models, Molecular; Models,
Statistical; Protein Binding; Protein Conformation; Protein Folding},
owner = {laurent},
pii = {S0022-2836(07)00164-7},
pmid = {17337005},
timestamp = {2008.07.08},
url = {http://dx.doi.org/10.1016/j.jmb.2007.01.086}
}
@article{Kaper2004BCI,
author = {Matthias Kaper and Peter Meinicke and Ulf Grossekathoefer and Thomas
Lingner and Helge Ritter},
title = {B{CI} {C}ompetition 2003--{D}ata set {II}b: support vector machines
for the {P}300 speller paradigm.},
journal = {I{EEE} {T}rans {B}iomed {E}ng},
year = {2004},
volume = {51},
pages = {1073-6},
number = {6},
month = {Jun},
abstract = {We propose an approach to analyze data from the {P}300 speller paradigm
using the machine-learning technique support vector machines. {I}n
a conservative classification scheme, we found the correct solution
after five repetitions. {W}hile the classification within the competition
is designed for offline analysis, our approach is also well-suited
for a real-world online solution: {I}t is fast, requires only 10
electrode positions and demands only a small amount of preprocessing.},
keywords = {Algorithms, Animals, Antisense, Artificial Intelligence, Automated,
Autonomic Nervous System, Brain, Cell Line, Child, Cluster Analysis,
Cognition, Comparative Study, Computational Biology, Computer Simulation,
Computer-Assisted, DNA Fingerprinting, Databases, Drug Evaluation,
Electroencephalography, Emotions, Event-Related Potentials, Factual,
Fluorescence, Fuzzy Logic, Gene Silencing, Gene Targeting, Genetic,
Hela Cells, Humans, Imaging, Intracellular Space, Microscopy, Models,
Monitoring, Neoplasms, Neural Networks (Computer), Non-U.S. Gov't,
Oligonucleotides, P.H.S., P300, Pattern Recognition, Peptides, Physiologic,
Preclinical, Predictive Value of Tests, Preschool, Prognosis, Protein
Interaction Mapping, Protein Structure, Proteins, Proteomics, Quantitative
Structure-Activity Relationship, Quaternary, RNA, RNA Interference,
Recognition (Psychology), Reproducibility of Results, Research Support,
Sensitivity and Specificity, Signal Processing, Small Interfering,
Software, Thionucleotides, Three-Dimensional, Tumor, U.S. Gov't,
User-Computer Interface, Word Processing, 15188881}
}
@article{Kharchenko2004Filling,
author = {Kharchenko, P. and Vitkup, D. and Church, G. M.},
title = {{F}illing gaps in a metabolic network using expression information.},
journal = {Bioinformatics},
year = {2004},
volume = {20 Suppl 1},
pages = {I178--I185},
month = {Aug},
abstract = {MOTIVATION: The metabolic models of both newly sequenced and well-studied
organisms contain reactions for which the enzymes have not been identified
yet. We present a computational approach for identifying genes encoding
such missing metabolic enzymes in a partially reconstructed metabolic
network. RESULTS: The metabolic expression placement (MEP) method
relies on the coexpression properties of the metabolic network and
is complementary to the sequence homology and genome context methods
that are currently being used to identify missing metabolic genes.
The MEP algorithm predicts over 20\% of all known Saccharomyces cerevisiae
metabolic enzyme-encoding genes within the top 50 out of 5594 candidates
for their enzymatic function, and 70\% of metabolic genes whose expression
level has been significantly perturbed across the conditions of the
expression dataset used. AVAILABILITY: Freely available (in Supplementary
information). SUPPLEMENTARY INFORMATION: Available at the following
URL http://arep.med.harvard.edu/kharchenko/mep/supplements.html},
doi = {10.1093/bioinformatics/bth930},
keywords = {Bacterial, Binding Sites, Biological, Comparative Study, DNA, Energy
Metabolism, Enzyme Induction, Enzymes, Escherichia coli Proteins,
Fungal, Gene Expression Regulation, Genes, Genetic, Genome, Models,
Non-P.H.S., Non-U.S. Gov't, Phylogeny, Promoter Regions (Genetics),
Protein, Research Support, Saccharomyces cerevisiae, Saccharomyces
cerevisiae Proteins, Sequence Analysis, Systems Biology, Transcription
Factors, U.S. Gov't, 15262797},
pii = {20/suppl_1/i178},
pmid = {15262797},
timestamp = {2006.11.21},
url = {http://dx.doi.org/10.1093/bioinformatics/bth930}
}
@unpublished{Kim2001Evolving,
author = {J. Kim and P.L. Krapivsky and B. Kahng and S. Redner},
title = {Evolving protein interaction networks},
note = {E-print cond-mat/0203167},
year = {2001},
pdf = {../local/kim02.pdf},
file = {kim02.pdf:local/kim02.pdf:PDF},
subject = {bionetprot},
url = {http://xxx.lanl.gov/abs/cond-mat/0203167}
}
@article{Kim2004Emotion,
author = {K. H. Kim and S. W. Bang and S. R. Kim},
title = {Emotion recognition system using short-term monitoring of physiological
signals.},
journal = {Med {B}iol {E}ng {C}omput},
year = {2004},
volume = {42},
pages = {419-27},
number = {3},
month = {May},
abstract = {A physiological signal-based emotion recognition system is reported.
{T}he system was developed to operate as a user-independent system,
based on physiological signal databases obtained from multiple subjects.
{T}he input signals were electrocardiogram, skin temperature variation
and electrodermal activity, all of which were acquired without much
discomfort from the body surface, and can reflect the influence of
emotion on the autonomic nervous system. {T}he system consisted of
preprocessing, feature extraction and pattern classification stages.
{P}reprocessing and feature extraction methods were devised so that
emotion-specific characteristics could be extracted from short-segment
signals. {A}lthough the features were carefully extracted, their
distribution formed a classification problem, with large overlap
among clusters and large variance within clusters. {A} support vector
machine was adopted as a pattern classifier to resolve this difficulty.
{C}orrect-classification ratios for 50 subjects were 78.4\% and 61.8\%,
for the recognition of three and four categories, respectively.},
keywords = {Algorithms, Animals, Antisense, Artificial Intelligence, Autonomic
Nervous System, Cell Line, Child, Cluster Analysis, Comparative Study,
Computational Biology, Computer Simulation, Computer-Assisted, DNA
Fingerprinting, Drug Evaluation, Emotions, Fluorescence, Fuzzy Logic,
Gene Silencing, Gene Targeting, Genetic, Hela Cells, Humans, Imaging,
Intracellular Space, Microscopy, Models, Monitoring, Neoplasms, Neural
Networks (Computer), Non-U.S. Gov't, Oligonucleotides, P.H.S., Physiologic,
Preclinical, Preschool, Prognosis, Proteomics, Quantitative Structure-Activity
Relationship, RNA, RNA Interference, Recognition (Psychology), Research
Support, Sensitivity and Specificity, Signal Processing, Small Interfering,
Thionucleotides, Three-Dimensional, Tumor, U.S. Gov't, User-Computer
Interface, 15191089}
}
@article{Klebe2000Recent,
author = {G. Klebe},
title = {{R}ecent developments in structure-based drug design.},
journal = {J Mol Med},
year = {2000},
volume = {78},
pages = {269--281},
number = {5},
abstract = {Structure-based design has emerged as a new tool in medicinal chemistry.
A prerequisite for this new approach is an understanding of the principles
of molecular recognition in protein-ligand complexes. If the three-dimensional
structure of a given protein is known, this information can be directly
exploited for the retrieval and design of new ligands. Structure-based
ligand design is an iterative approach. First of all, it requires
the crystal structure or a model derived from the crystal structure
of a closely related homolog of the target protein, preferentially
complexed with a ligand. This complex unravels the binding mode and
conformation of a ligand under investigation and indicates the essential
aspects determining its binding affinity. It is then used to generate
new ideas about ways of improving an existing ligand or of developing
new alternative bonding skeletons. Computational methods supplemented
by molecular graphics are applied to assist this step of hypothesis
generation. The features of the protein binding pocket can be translated
into queries used for virtual computer screening of large compound
libraries or to design novel ligands de novo. These initial proposals
must be confirmed experimentally. Subsequently they are optimized
toward higher affinity and better selectivity. The latter aspect
is of utmost importance in defining and controlling the pharmacological
profile of a ligand. A prerequisite to tailoring selectivity by rational
design is a detailed understanding of molecular parameters determining
selectivity. Taking examples from current drug development programs
(HIV proteinase, t-RNA transglycosylase, thymidylate synthase, thrombin
and, related serine proteinases), we describe recent advances in
lead discovery via computer screening, iterative design, and understanding
of selectivity discrimination.},
keywords = {Animals, Chemistry, Computer Simulation, Cross-Over Studies, Crystallography,
Deglutition, Deglutition Disorders, Drug Design, Endoscopy, Enzyme
Inhibitors, Female, Fluoroscopy, Glossopharyngeal Nerve, HIV Protease
Inhibitors, Horse Diseases, Horses, Male, Models, Molecular, Nerve
Block, Non-U.S. Gov't, P.H.S., Pharmaceutical, Proteins, Quantitative
Structure-Activity Relationship, Random Allocation, Research Support,
Thrombin, Thymidylate Synthase, U.S. Gov't, X-Ray, 10954196},
owner = {mahe},
pmid = {10954196},
timestamp = {2006.09.05}
}
@article{Kononen1998Tissue,
author = {J. Kononen and L. Bubendorf and A. Kallioniemi and M. Bärlund and
P. Schraml and S. Leighton and J. Torhorst and M. J. Mihatsch and
G. Sauter and O. P. Kallioniemi},
title = {Tissue microarrays for high-throughput molecular profiling of tumor
specimens.},
journal = {Nat Med},
year = {1998},
volume = {4},
pages = {844--847},
number = {7},
month = {Jul},
abstract = {Many genes and signalling pathways controlling cell proliferation,
death and differentiation, as well as genomic integrity, are involved
in cancer development. New techniques, such as serial analysis of
gene expression and cDNA microarrays, have enabled measurement of
the expression of thousands of genes in a single experiment, revealing
many new, potentially important cancer genes. These genome screening
tools can comprehensively survey one tumor at a time; however, analysis
of hundreds of specimens from patients in different stages of disease
is needed to establish the diagnostic, prognostic and therapeutic
importance of each of the emerging cancer gene candidates. Here we
have developed an array-based high-throughput technique that facilitates
gene expression and copy number surveys of very large numbers of
tumors. As many as 1000 cylindrical tissue biopsies from individual
tumors can be distributed in a single tumor tissue microarray. Sections
of the microarray provide targets for parallel in situ detection
of DNA, RNA and protein targets in each specimen on the array, and
consecutive sections allow the rapid analysis of hundreds of molecular
markers in the same set of specimens. Our detection of six gene amplifications
as well as p53 and estrogen receptor expression in breast cancer
demonstrates the power of this technique for defining new subgroups
of tumors.},
institution = {Laboratory of Cancer Genetics, National Human Genome Research Institute,
National Institutes of Health, Bethesda, MD 20892-4470, USA.},
keywords = {Animals; Breast Neoplasms, genetics/metabolism/pathology; Cyclin D1,
genetics/metabolism; Female; Genetic Techniques; Humans; Immunoenzyme
Techniques; In Situ Hybridization, Fluorescence; Mice; Oncogene Proteins
v-myb; Proto-Oncogene Proteins c-myc, genetics/metabolism; Rabbits;
Receptor, erbB-2, genetics/metabolism; Receptors, Estrogen, genetics/metabolism;
Retroviridae Proteins, Oncogenic, genetics/metabolism; Tumor Markers,
Biological, genetics/metabolism; Tumor Suppressor Protein p53, genetics/metabolism},
language = {eng},
medline-pst = {ppublish},
owner = {philippe},
pmid = {9662379},
timestamp = {2010.08.08}
}
@article{Kristiansen1996database,
author = {K. Kristiansen and S. G. Dahl and O. Edvardsen},
title = {A database of mutants and effects of site-directed mutagenesis experiments
on {G} protein-coupled receptors.},
journal = {Proteins},
year = {1996},
volume = {26},
pages = {81--94},
number = {1},
month = {Sep},
abstract = {A database system and computer programs for storage and retrieval
of information about guanine nucleotide-binding protein (G protein)
-coupled receptor mutants and associated biological effects have
been developed. Mutation data on the receptors were collected from
the literature and a database of mutants and effects of mutations
was developed. The G protein-coupled receptor, family A, point mutation
database (GRAP) provides detailed information on ligand-binding and
signal transduction properties of more than 2130 receptor mutants.
The amino acid sequences of receptors for which mutation experiments
have been reported were aligned, and from this alignment mutation
data may be retrieved. Alternatively, a search form allowing detailed
specification of which mutants to retrieve may be used, for example,
to search for specific amino acid substitutions, substitutions in
specific protein domains or reported biological effects. Furthermore,
ligand and bibliographic oriented queries may be performed. GRAP
is available on the Internet (URL: http://www-grap.fagmed.uit.no/GRAP/+
+homepage.html) using the World-Wide Web system.},
doi = {3.0.CO;2-J},
keywords = {Amino Acid Sequence; Computer Communication Networks; Computers; GTP-Binding
Proteins; Information Systems; Molecular Sequence Data; Mutagenesis,
Site-Directed; Mutation; Receptors, Cell Surface; Sequence Alignment},
owner = {laurent},
pii = {3.0.CO;2-J},
pmid = {8880932},
timestamp = {2008.01.16},
url = {http://dx.doi.org/3.0.CO;2-J}
}
@article{Kroemer2007Structure,
author = {Romano T Kroemer},
title = {Structure-based drug design: docking and scoring.},
journal = {Curr. Protein Pept. Sci.},
year = {2007},
volume = {8},
pages = {312--328},
number = {4},
month = {Aug},
abstract = {This review gives an introduction into ligand - receptor docking and
illustrates the basic underlying concepts. An overview of different
approaches and algorithms is provided. Although the application of
docking and scoring has led to some remarkable successes, there are
still some major challenges ahead, which are outlined here as well.
Approaches to address some of these challenges and the latest developments
in the area are presented. Some aspects of the assessment of docking
program performance are discussed. A number of successful applications
of structure-based virtual screening are described.},
institution = {ciences, Department of Chemistry, Nerviano Medical Sciences, Viale
Pasteur 10, 20014 Nerviano (MI), Italy. romano.kroemer@sanofi-aventis.com},
keywords = {Algorithms; Artificial Intelligence; Computational Biology; Computer
Simulation; Computer-Aided Design; Drug Design; Imaging, Three-Dimensional;
Ligands; Models, Molecular; Protein Binding; Protein Conformation;
Software; Structure-Activity Relationship},
owner = {bricehoffmann},
pmid = {17696866},
timestamp = {2009.02.13}
}
@article{Kubinyi2006Chemogenomics,
author = {H. Kubinyi},
title = {Chemogenomics in drug discovery.},
journal = {Ernst Schering Res Found Workshop},
year = {2006},
volume = {58},
pages = {1--19},
abstract = {Chemogenomics is a new strategy in drug discovery which, in principle,
searches for all molecules that are capable of interacting with any
biological target. Because of the almost infinite number of drug-like
organic molecules, this is an impossible task. Therefore chemogenomics
has been defined as the investigation of classes of compounds (libraries)
against families of functionally related proteins. In this definition,
chemogenomics deals with the systematic analysis of chemical-biological
interactions. Congeneric series of chemical analogs are probes to
investigate their action on specific target classes, e.g., GPCRs,
kinases, phosphodiesterases, ion channels, serine proteases, and
others. Whereas such a strategy developed in pharmaceutical industry
almost 20 years ago, it is now more systematically applied in the
search for target- and subtype-specific ligands. The term "privileged
structures" has been defined for scaffolds, such as the benzodiazepines,
which very often produce biologically active analogs in a target
family, in this case in the class of G-protein-coupled receptors.
The SOSA approach is a strategy to modify the selectivity of biologically
active compounds, generating new drug candidates from the side activities
of therapeutically used drugs.},
keywords = {Animals; Chemistry, Pharmaceutical; Combinatorial Chemistry Techniques;
Drug Design; Drug Industry; Genomics; Humans; Models, Chemical; Molecular
Structure; Mutation; Pharmacogenetics; Protein Binding},
owner = {laurent},
pmid = {16708995},
timestamp = {2007.09.22}
}
@article{Kurata2006PlosCompBio,
author = {Hiroyuki Kurata and Hana El-Samad and Rei Iwasaki and Hisao Ohtake
and John C Doyle and Irina Grigorova and Carol A Gross and Mustafa
Khammash},
title = {Module-based analysis of robustness tradeoffs in the heat shock response
system.},
journal = {PLoS Comput Biol},
year = {2006},
volume = {2},
pages = {e59},
number = {7},
month = {Jul},
abstract = {Biological systems have evolved complex regulatory mechanisms, even
in situations where much simpler designs seem to be sufficient for
generating nominal functionality. Using module-based analysis coupled
with rigorous mathematical comparisons, we propose that in analogy
to control engineering architectures, the complexity of cellular
systems and the presence of hierarchical modular structures can be
attributed to the necessity of achieving robustness. We employ the
Escherichia coli heat shock response system, a strongly conserved
cellular mechanism, as an example to explore the design principles
of such modular architectures. In the heat shock response system,
the sigma-factor sigma32 is a central regulator that integrates multiple
feedforward and feedback modules. Each of these modules provides
a different type of robustness with its inherent tradeoffs in terms
of transient response and efficiency. We demonstrate how the overall
architecture of the system balances such tradeoffs. An extensive
mathematical exploration nevertheless points to the existence of
an array of alternative strategies for the existing heat shock response
that could exhibit similar behavior. We therefore deduce that the
evolutionary constraints facing the system might have steered its
architecture toward one of many robustly functional solutions.},
doi = {10.1371/journal.pcbi.0020059},
institution = {Department of Bioscience and Bioinformatics, Kyushu Institute of
Technology, Iizuka, Fukuoka, Japan. kurata@bio.kyutech.ac.jp},
keywords = {Computer Simulation; Escherichia coli Proteins, metabolism; Escherichia
coli, metabolism; Feedback, physiology; Gene Expression Regulation,
Bacterial, physiology; Heat-Shock Proteins, metabolism; Heat-Shock
Response, physiology; Models, Biological; Oxidative Stress, physiology;
Signal Transduction, physiology; Systems Biology, methods},
language = {eng},
medline-pst = {ppublish},
owner = {Andrei Zinovyev},
pii = {05-PLCB-RA-0264R4},
pmid = {16863396},
timestamp = {2011.04.08},
url = {http://dx.doi.org/10.1371/journal.pcbi.0020059}
}
@article{Kohler2008Walking,
author = {K{\"o}hler, S. and Bauer, S. and Horn, D. and Robinson, P.N.},
title = {Walking the interactome for prioritization of candidate disease genes.},
journal = {Am. J. Hum. Genet.},
year = {2008},
volume = {82},
pages = {949--958},
number = {4},
month = {Apr},
abstract = {The identification of genes associated with hereditary disorders has
contributed to improving medical care and to a better understanding
of gene functions, interactions, and pathways. However, there are
well over 1500 Mendelian disorders whose molecular basis remains
unknown. At present, methods such as linkage analysis can identify
the chromosomal region in which unknown disease genes are located,
but the regions could contain up to hundreds of candidate genes.
In this work, we present a method for prioritization of candidate
genes by use of a global network distance measure, random walk analysis,
for definition of similarities in protein-protein interaction networks.
We tested our method on 110 disease-gene families with a total of
783 genes and achieved an area under the ROC curve of up to 98\%
on simulated linkage intervals of 100 genes surrounding the disease
gene, significantly outperforming previous methods based on local
distance measures. Our results not only provide an improved tool
for positional-cloning projects but also add weight to the assumption
that phenotypically similar diseases are associated with disturbances
of subnetworks within the larger protein interactome that extend
beyond the disease proteins themselves.},
doi = {10.1016/j.ajhg.2008.02.013},
institution = {Institute for Medical Genetics, Charité Universitätsmedizin Berlin,
Augustenburger Platz 1, 13353 Berlin, Germany.},
keywords = {Animals; Chromosome Mapping; Computational Biology; Databases, Genetic;
Genetic Diseases, Inborn; Genetic Predisposition to Disease; Humans;
Internet; Linkage (Genetics); Mice; Pedigree; Protein Interaction
Mapping; Software},
owner = {mordelet},
pii = {S0002-9297(08)00172-9},
pmid = {18371930},
timestamp = {2010.09.28},
url = {http://dx.doi.org/10.1016/j.ajhg.2008.02.013}
}
@article{LeCao2009Sparse,
author = {{L\^e Cao}, K.-A. and Martin, P. G. P. and Robert-Grani\'e, C. and
Besse, P.},
title = {Sparse canonical methods for biological data integration: application
to a cross-platform study.},
journal = {BMC Bioinformatics},
year = {2009},
volume = {10},
pages = {34},
abstract = {In the context of systems biology, few sparse approaches have been
proposed so far to integrate several data sets. It is however an
important and fundamental issue that will be widely encountered in
post genomic studies, when simultaneously analyzing transcriptomics,
proteomics and metabolomics data using different platforms, so as
to understand the mutual interactions between the different data
sets. In this high dimensional setting, variable selection is crucial
to give interpretable results. We focus on a sparse Partial Least
Squares approach (sPLS) to handle two-block data sets, where the
relationship between the two types of variables is known to be symmetric.
Sparse PLS has been developed either for a regression or a canonical
correlation framework and includes a built-in procedure to select
variables while integrating data. To illustrate the canonical mode
approach, we analyzed the NCI60 data sets, where two different platforms
(cDNA and Affymetrix chips) were used to study the transcriptome
of sixty cancer cell lines.We compare the results obtained with two
other sparse or related canonical correlation approaches: CCA with
Elastic Net penalization (CCA-EN) and Co-Inertia Analysis (CIA).
The latter does not include a built-in procedure for variable selection
and requires a two-step analysis. We stress the lack of statistical
criteria to evaluate canonical correlation methods, which makes biological
interpretation absolutely necessary to compare the different gene
selections. We also propose comprehensive graphical representations
of both samples and variables to facilitate the interpretation of
the results.sPLS and CCA-EN selected highly relevant genes and complementary
findings from the two data sets, which enabled a detailed understanding
of the molecular characteristics of several groups of cell lines.
These two approaches were found to bring similar results, although
they highlighted the same phenomenons with a different priority.
They outperformed CIA that tended to select redundant information.},
doi = {10.1186/1471-2105-10-34},
institution = {Station d'Amélioration Génétique des Animaux UR 631, Institut National
de Recherche Agronomique, F-31326 Castanet, France. k.lecao@imb.uq.edu.au},
keywords = {Computational Biology, methods; Genomics; Metabolomics; Proteomics;
Systems Biology, methods},
language = {eng},
medline-pst = {epublish},
owner = {jp},
pii = {1471-2105-10-34},
pmid = {19171069},
timestamp = {2012.02.29},
url = {http://dx.doi.org/10.1186/1471-2105-10-34}
}
@article{LaBaer2005Protein,
author = {Joshua LaBaer and Niroshan Ramachandran},
title = {Protein microarrays as tools for functional proteomics.},
journal = {Curr Opin Chem Biol},
year = {2005},
volume = {9},
pages = {14--19},
number = {1},
month = {Feb},
abstract = {Protein microarrays present an innovative and versatile approach to
study protein abundance and function at an unprecedented scale. Given
the chemical and structural complexity of the proteome, the development
of protein microarrays has been challenging. Despite these challenges
there has been a marked increase in the use of protein microarrays
to map interactions of proteins with various other molecules, and
to identify potential disease biomarkers, especially in the area
of cancer biology. In this review, we discuss some of the promising
advances made in the development and use of protein microarrays.},
doi = {10.1016/j.cbpa.2004.12.006},
institution = {Harvard Institute of Proteomics, Department of Biological Chemistry
and Molecular Pharmacology, Harvard Medical School, 320 Charles Street,
Cambridge, Massachusetts 02141, USA. joshua_labaer@hms.harvard.edu},
keywords = {Protein Array Analysis; Proteins; Proteomics; Surface Properties},
owner = {phupe},
pii = {S1367-5931(04)00165-6},
pmid = {15701447},
timestamp = {2010.08.12},
url = {http://dx.doi.org/10.1016/j.cbpa.2004.12.006}
}
@article{Lal2004Support,
author = {Thomas Navin Lal and Michael Schröder and Thilo Hinterberger and
Jason Weston and Martin Bogdan and Niels Birbaumer and Bernhard Schölkopf},
title = {Support vector channel selection in {BCI}.},
journal = {I{EEE} {T}rans {B}iomed {E}ng},
year = {2004},
volume = {51},
pages = {1003-10},
number = {6},
month = {Jun},
abstract = {Designing a brain computer interface ({BCI}) system one can choose
from a variety of features that may be useful for classifying brain
activity during a mental task. {F}or the special case of classifying
electroencephalogram ({EEG}) signals we propose the usage of the
state of the art feature selection algorithms {R}ecursive {F}eature
{E}limination and {Z}ero-{N}orm {O}ptimization which are based on
the training of support vector machines ({SVM}). {T}hese algorithms
can provide more accurate solutions than standard filter methods
for feature selection. {W}e adapt the methods for the purpose of
selecting {EEG} channels. {F}or a motor imagery paradigm we show
that the number of used channels can be reduced significantly without
increasing the classification error. {T}he resulting best channels
agree well with the expected underlying cortical activity patterns
during the mental tasks. {F}urthermore we show how time dependent
task specific information can be visualized.},
keywords = {Algorithms, Animals, Antisense, Artificial Intelligence, Automated,
Autonomic Nervous System, Brain, Cell Line, Cerebral Cortex, Child,
Cluster Analysis, Cognition, Comparative Study, Computational Biology,
Computer Simulation, Computer-Assisted, DNA Fingerprinting, Databases,
Drug Evaluation, Electroencephalography, Emotions, Event-Related
Potentials, Evoked Potentials, Factual, Fluorescence, Fuzzy Logic,
Gene Silencing, Gene Targeting, Genetic, Hand, Hela Cells, Humans,
Imaging, Intracellular Space, Male, Microscopy, Models, Monitoring,
Motor, Neoplasms, Neural Networks (Computer), Non-U.S. Gov't, Oligonucleotides,
P.H.S., P300, Pattern Recognition, Peptides, Physiologic, Preclinical,
Predictive Value of Tests, Preschool, Prognosis, Protein Interaction
Mapping, Protein Structure, Proteins, Proteomics, Quantitative Structure-Activity
Relationship, Quaternary, RNA, RNA Interference, Recognition (Psychology),
Reproducibility of Results, Research Support, Sensitivity and Specificity,
Signal Processing, Small Interfering, Software, Thionucleotides,
Three-Dimensional, Tumor, U.S. Gov't, User-Computer Interface, Word
Processing, 15188871}
}
@article{Larsen2005integrative,
author = {Mette Voldby Larsen and Claus Lundegaard and Kasper Lamberth and
S\o ren Buus and S\o ren Brunak and Ole Lund and Morten Nielsen},
title = {An integrative approach to {CTL} epitope prediction: a combined algorithm
integrating {MHC} class {I} binding, {TAP} transport efficiency,
and proteasomal cleavage predictions.},
journal = {Eur. J. Immunol.},
year = {2005},
volume = {35},
pages = {2295--2303},
number = {8},
month = {Aug},
abstract = {Reverse immunogenetic approaches attempt to optimize the selection
of candidate epitopes, and thus minimize the experimental effort
needed to identify new epitopes. When predicting cytotoxic T cell
epitopes, the main focus has been on the highly specific MHC class
I binding event. Methods have also been developed for predicting
the antigen-processing steps preceding MHC class I binding, including
proteasomal cleavage and transporter associated with antigen processing
(TAP) transport efficiency. Here, we use a dataset obtained from
the SYFPEITHI database to show that a method integrating predictions
of MHC class I binding affinity, TAP transport efficiency, and C-terminal
proteasomal cleavage outperforms any of the individual methods. Using
an independent evaluation dataset of HIV epitopes from the Los Alamos
database, the validity of the integrated method is confirmed. The
performance of the integrated method is found to be significantly
higher than that of the two publicly available prediction methods
BIMAS and SYFPEITHI. To identify 85\% of the epitopes in the HIV
dataset, 9\% and 10\% of all possible nonamers in the HIV proteins
must be tested when using the BIMAS and SYFPEITHI methods, respectively,
for the selection of candidate epitopes. This number is reduced to
7\% when using the integrated method. In practical terms, this means
that the experimental effort needed to identify an epitope in a hypothetical
protein with 85\% probability is reduced by 20-30\% when using the
integrated method.The method is available at http://www.cbs.dtu.dk/services/NetCTL.
Supplementary material is available at http://www.cbs.dtu.dk/suppl/immunology/CTL.php.},
doi = {10.1002/eji.200425811},
keywords = {Algorithms; Data Interpretation, Statistical; Epitopes, T-Lymphocyte;
Histocompatibility Antigens Class I; Humans; Hydrolysis; Predictive
Value of Tests; Proteasome Endopeptidase Complex; Protein Binding;
Research Support, N.I.H., Extramural; Research Support, Non-U.S.
Gov't; Research Support, U.S. Gov't, P.H.S.; T-Lymphocytes, Cytotoxic},
owner = {jacob},
pmid = {15997466},
timestamp = {2006.08.30},
url = {http://dx.doi.org/10.1002/eji.200425811}
}
@article{Lasso2005Vessel,
author = {András Lassó and Emanuele Trucco},
title = {Vessel enhancement in digital {X}-ray angiographic sequences by temporal
statistical learning.},
journal = {Comput {M}ed {I}maging {G}raph},
year = {2005},
volume = {29},
pages = {343-55},
number = {5},
month = {Jul},
doi = {10.1016/j.compmedimag.2005.02.002},
keywords = {Apoptosis, Gene Expression Profiling, Humans, Neoplasms, Non-U.S.
Gov't, Oligonucleotide Array Sequence Analysis, Polymerase Chain
Reaction, Proteins, Research Support, Subcellular Fractions, Unknown
Primary, 15893453},
pii = {S0895-6111(05)00032-7},
url = {http://dx.doi.org/10.1016/j.compmedimag.2005.02.002}
}
@article{Launay2008Homology,
author = {G. Launay and T. Simonson},
title = {Homology modelling of protein-protein complexes: a simple method
and its possibilities and limitations.},
journal = {BMC Bioinformatics},
year = {2008},
volume = {9},
pages = {427},
abstract = {BACKGROUND: Structure-based computational methods are needed to help
identify and characterize protein-protein complexes and their function.
For individual proteins, the most successful technique is homology
modelling. We investigate a simple extension of this technique to
protein-protein complexes. We consider a large set of complexes of
known structures, involving pairs of single-domain proteins. The
complexes are compared with each other to establish their sequence
and structural similarities and the relation between the two. Compared
to earlier studies, a simpler dataset, a simpler structural alignment
procedure, and an additional energy criterion are used. Next, we
compare the Xray structures to models obtained by threading the native
sequence onto other, homologous complexes. An elementary requirement
for a successful energy function is to rank the native structure
above any threaded structure. We use the DFIREbeta energy function,
whose quality and complexity are typical of the models used today.
Finally, we compare near-native models to distinctly non-native models.
RESULTS: If weakly stable complexes are excluded (defined by a binding
energy cutoff), as well as a few unusual complexes, a simple homology
principle holds: complexes that share more than 35\% sequence identity
share similar structures and interaction modes; this principle was
less clearcut in earlier studies. The energy function was then tested
for its ability to identify experimental structures among sets of
decoys, produced by a simple threading procedure. On average, the
experimental structure is ranked above 92\% of the alternate structures.
Thus, discrimination of the native structure is good but not perfect.
The discrimination of near-native structures is fair. Typically,
a single, alternate, non-native binding mode exists that has a native-like
energy. Some of the associated failures may correspond to genuine,
alternate binding modes and/or native complexes that are artefacts
of the crystal environment. In other cases, additional model filtering
with more sophisticated tools is needed. CONCLUSION: The results
suggest that the simple modelling procedure applied here could help
identify and characterize protein-protein complexes. The next step
is to apply it on a genomic scale.},
doi = {10.1186/1471-2105-9-427},
institution = {Laboratoire de Biochimie (UMR CNRS 7654), Department of Biology,
Ecole Polytechnique, 91128, Palaiseau, France. guillaume.launay@irisa.fr},
keywords = {Algorithms; Protein Binding; Protein Conformation; Protein Interaction
Domains and Motifs; Proteins, chemistry/metabolism; Structural Homology,
Protein},
owner = {bricehoffmann},
pii = {1471-2105-9-427},
pmid = {18844985},
timestamp = {2009.02.13},
url = {http://dx.doi.org/10.1186/1471-2105-9-427}
}
@article{Lazo2000Combinatorial,
author = {J. S. Lazo and P. Wipf},
title = {{C}ombinatorial chemistry and contemporary pharmacology.},
journal = {J. Pharmacol. Exp. Ther.},
year = {2000},
volume = {293},
pages = {705--709},
number = {3},
month = {Jun},
abstract = {Both solid- and liquid-phase combinatorial chemistry have emerged
as powerful tools for identifying pharmacologically active compounds
and optimizing the biological activity of a lead compound. Complementary
high-throughput in vitro assays are essential for compound evaluation.
Cell-based assays that use optical endpoints permit investigation
of a wide variety of functional properties of these compounds including
specific intracellular biochemical pathways, protein-protein interactions,
and the subcellular localization of targets. Integration of combinatorial
chemistry with contemporary pharmacology now represents an important
factor in drug discovery and development.},
keywords = {Alzheimer Disease, Animals, Antineoplastic Agents, Biological, Bleomycin,
Cell Cycle, Cell Cycle Proteins, Cell Death, Cell Line, Cell Nucleus,
Cell Shape, Cell Transformation, Combinatorial Chemistry Techniques,
Cultured, Drug Delivery Systems, Drug Design, Drug Evaluation, Enzyme
Inhibitors, Formazans, Gene Expression, Humans, Inhibitory Concentration
50, Kinetics, Magnetic Resonance Spectroscopy, Mass, Mitochondria,
Models, Molecular, Neoplasms, Neoplastic, Non-P.H.S., Non-U.S. Gov't,
P.H.S., Paclitaxel, Peptide Library, Pharmaceutical Preparations,
Pharmacology, Phosphoprotein Phosphatase, Preclinical, Protease Inhibitors,
Protein-Tyrosine-Phosphatase, Research Support, Sensitivity and Specificity,
Signal Transduction, Spectrum Analysis, Stereoisomerism, Structure-Activity
Relationship, Sulfonic Acids, Tetrazolium Salts, Thiazoles, Toxicity
Tests, Tumor, Tumor Cells, U.S. Gov't, cdc25 Phosphatase, 10869367},
owner = {mahe},
pmid = {10869367},
timestamp = {2006.08.22}
}
@article{Leach2006Prediction,
author = {A. R. Leach and B. K. Shoichet and C. E. Peishoff},
title = {Prediction of protein-ligand interactions. Docking and scoring: successes
and gaps.},
journal = {J. Med. Chem.},
year = {2006},
volume = {49},
pages = {5851--5855},
number = {20},
month = {Oct},
doi = {10.1021/jm060999m},
institution = {GlaxoSmithKline Pharmaceuticals, 1250 South Collegeville Road, Collegeville,
Pennsylvania 19426, USA.},
keywords = {Binding Sites; Drug Design; Ligands; Models, Molecular; Protein Binding;
Proteins, chemistry; Quantitative Structure-Activity Relationship},
owner = {bricehoffmann},
pmid = {17004700},
timestamp = {2009.02.13},
url = {http://dx.doi.org/10.1021/jm060999m}
}
@article{Li2002Involvement,
author = {Jiwen Li and Qiushi Lin and Ho-Geun Yoon and Zhi-Qing Huang and Brian
D Strahl and C. David Allis and Jiemin Wong},
title = {Involvement of histone methylation and phosphorylation in regulation
of transcription by thyroid hormone receptor.},
journal = {Mol Cell Biol},
year = {2002},
volume = {22},
pages = {5688--5697},
number = {16},
month = {Aug},
abstract = {Previous studies have established an important role of histone acetylation
in transcriptional control by nuclear hormone receptors. With chromatin
immunoprecipitation assays, we have now investigated whether histone
methylation and phosphorylation are also involved in transcriptional
regulation by thyroid hormone receptor (TR). We found that repression
by unliganded TR is associated with a substantial increase in methylation
of H3 lysine 9 (H3-K9) and a decrease in methylation of H3 lysine
4 (H3-K4), methylation of H3 arginine 17 (H3-R17), and a dual modification
of phosphorylation of H3 serine 10 and acetylation of lysine 14 (pS10/acK14).
On the other hand, transcriptional activation by liganded TR is coupled
with a substantial decrease in both H3-K4 and H3-K9 methylation and
a robust increase in H3-R17 methylation and the dual modification
of pS10/acK14. Trichostatin A treatment results in not only histone
hyperacetylation but also an increase in methylation of H3-K4, increase
in dual modification of pS10/acK14, and reduction in methylation
of H3-K9, revealing an extensive interplay between histone acetylation,
methylation, and phosphorylation. In an effort to understand the
underlying mechanism for an increase in H3-K9 methylation during
repression by unliganded TR, we demonstrated that TR interacts in
vitro with an H3-K9-specific histone methyltransferase (HMT), SUV39H1.
Functional analysis indicates that SUV39H1 can facilitate repression
by unliganded TR and in so doing requires its HMT activity. Together,
our data uncover a novel role of H3-K9 methylation in repression
by unliganded TR and provide strong evidence for the involvement
of multiple distinct histone covalent modifications (acetylation,
methylation, and phosphorylation) in transcriptional control by nuclear
hormone receptors.},
institution = {Department of Molecular and Cellular Biology, Baylor College of Medicine,
Houston, Texas 77030, USA.},
keywords = {Animals; Cell Fractionation; Gene Expression Regulation, drug effects;
Genes, Reporter; Histone-Lysine N-Methyltransferase; Histones, chemistry/genetics/metabolism;
Humans; Hydroxamic Acids, pharmacology; Methylation; Methyltransferases,
metabolism; Oocytes, physiology; Phosphorylation; Protein Methyltransferases;
Protein Synthesis Inhibitors, pharmacology; Receptors, Thyroid Hormone,
metabolism; Transcription, Genetic; Xenopus laevis, physiology},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pmid = {12138181},
timestamp = {2010.11.23}
}
@article{Li2004Fusing,
author = {Shutao Li and James Tin-Yau Kwok and Ivor Wai-Hung Tsang and Yaonan
Wang},
title = {Fusing images with different focuses using support vector machines.},
journal = {I{EEE} {T}rans {N}eural {N}etw},
year = {2004},
volume = {15},
pages = {1555-61},
number = {6},
month = {Nov},
abstract = {Many vision-related processing tasks, such as edge detection, image
segmentation and stereo matching, can be performed more easily when
all objects in the scene are in good focus. {H}owever, in practice,
this may not be always feasible as optical lenses, especially those
with long focal lengths, only have a limited depth of field. {O}ne
common approach to recover an everywhere-in-focus image is to use
wavelet-based image fusion. {F}irst, several source images with different
focuses of the same scene are taken and processed with the discrete
wavelet transform ({DWT}). {A}mong these wavelet decompositions,
the wavelet coefficient with the largest magnitude is selected at
each pixel location. {F}inally, the fused image can be recovered
by performing the inverse {DWT}. {I}n this paper, we improve this
fusion procedure by applying the discrete wavelet frame transform
({DWFT}) and the support vector machines ({SVM}). {U}nlike {DWT},
{DWFT} yields a translation-invariant signal representation. {U}sing
features extracted from the {DWFT} coefficients, a {SVM} is trained
to select the source image that has the best focus at each pixel
location, and the corresponding {DWFT} coefficients are then incorporated
into the composite wavelet representation. {E}xperimental results
show that the proposed method outperforms the traditional approach
both visually and quantitatively.},
keywords = {Algorithms, Amino Acid, Amino Acids, Artificial Intelligence, Ascomycota,
Automated, Base Sequence, Chromosome Mapping, Codon, Colonic Neoplasms,
Comparative Study, Computer Simulation, Computer-Assisted, Computing
Methodologies, Crystallography, DNA, DNA Primers, Databases, Diagnostic
Imaging, Enzymes, Fixation, Gene Expression Profiling, Genetic, Hordeum,
Host-Parasite Relations, Humans, Image Enhancement, Image Interpretation,
Informatics, Information Storage and Retrieval, Kinetics, Magnetic
Resonance Spectroscopy, Models, Nanotechnology, Neural Networks (Computer),
Non-P.H.S., Non-U.S. Gov't, Ocular, Oligonucleotide Array Sequence
Analysis, P.H.S., Pattern Recognition, Plant, Plants, Predictive
Value of Tests, Protein, Protein Conformation, Research Support,
Sample Size, Selection (Genetics), Sequence Alignment, Sequence Analysis,
Sequence Homology, Signal Processing, Skin, Software, Statistical,
Subtraction Technique, Theoretical, Thermodynamics, U.S. Gov't, Viral
Proteins, X-Ray, 15565781}
}
@article{Liang2001Detection,
author = {H. Liang and Z. Lin},
title = {Detection of delayed gastric emptying from electrogastrograms with
support vector machine.},
journal = {I{EEE} {T}rans {B}iomed {E}ng},
year = {2001},
volume = {48},
pages = {601-4},
number = {5},
month = {May},
abstract = {A recent study reported a conventional neural network ({NN}) approach
for the noninvasive diagnosis of delayed gastric emptying from the
cutaneous electrogastrograms. {U}sing support vector machine, we
show that this relatively new technique can be used for detection
of delayed gastric emptying and is in fact able to outdo the conventional
{NN}.},
keywords = {Algorithms, Amino Acid Sequence, Artificial Intelligence, Biological,
Cell Compartmentation, Comparative Study, Computer Simulation, Computer-Assisted,
Decision Trees, Diagnosis, Discriminant Analysis, Electrophysiology,
Gastric Emptying, Humans, Logistic Models, Melanoma, Models, Neural
Networks (Computer), Nevus, Non-U.S. Gov't, Organelles, P.H.S., Pigmented,
Predictive Value of Tests, Proteins, Reproducibility of Results,
Research Support, Skin Diseases, Skin Neoplasms, Skin Pigmentation,
Stomach Diseases, U.S. Gov't, 11341535}
}
@article{Lievens2009Mammalian,
author = {Sam Lievens and Irma Lemmens and Jan Tavernier},
title = {Mammalian two-hybrids come of age.},
journal = {Trends Biochem Sci},
year = {2009},
volume = {34},
pages = {579--588},
number = {11},
month = {Nov},
abstract = {A diverse series of mammalian two-hybrid technologies for the detection
of protein-protein interactions have emerged in the past few years,
complementing the established yeast two-hybrid approach. Given the
mammalian background in which they operate, these assays open new
avenues to study the dynamics of mammalian protein interaction networks,
i.e. the temporal, spatial and functional modulation of protein-protein
associations. In addition, novel assay formats are available that
enable high-throughput mammalian two-hybrid applications, facilitating
their use in large-scale interactome mapping projects. Finally, as
they can be applied in drug discovery and development programs, these
techniques also offer exciting new opportunities for biomedical research.},
doi = {10.1016/j.tibs.2009.06.009},
institution = {Department of Medical Protein Research, VIB, A. Baertsoenkaai 3,
9000 Ghent, Belgium},
keywords = {Animals; Genes, Reporter; Humans; Models, Biological; Protein Binding;
Protein Interaction Mapping; Proteins; Recombinant Fusion Proteins;
Transfection; Two-Hybrid System Techniques},
owner = {phupe},
pii = {S0968-0004(09)00158-3},
pmid = {19786350},
timestamp = {2010.08.31},
url = {http://dx.doi.org/10.1016/j.tibs.2009.06.009}
}
@article{Luo2004gene-silencing,
author = {Luo, K. Q. and Chang, D. C.},
title = {The gene-silencing efficiency of si{RNA} is strongly dependent on
the local structure of m{RNA} at the targeted region.},
journal = {Biochem. {B}iophys. {R}es. {C}ommun.},
year = {2004},
volume = {318},
pages = {303-10},
number = {1},
month = {May},
abstract = {The gene-silencing effect of short interfering {RNA} (si{RNA}) is
known to vary strongly with the targeted position of the m{RNA}.
{A} number of hypotheses have been suggested to explain this phenomenon.
{W}e would like to test if this positional effect is mainly due to
the secondary structure of the m{RNA} at the target site. {W}e proposed
that this structural factor can be characterized by a single parameter
called "the hydrogen bond ({H}-b) index," which represents the average
number of hydrogen bonds formed between nucleotides in the target
region and the rest of the m{RNA}. {T}his index can be determined
using a computational approach. {W}e tested the correlation between
the {H}-b index and the gene-silencing effects on three genes ({B}cl-2,
h{TF}, and cyclin {B}1) using a variety of si{RNA}s. {W}e found that
the gene-silencing effect is inversely dependent on the {H}-b index,
indicating that the local m{RNA} structure at the targeted site is
the main cause of the positional effect. {B}ased on this finding,
we suggest that the {H}-b index can be a useful guideline for future
si{RNA} design.},
doi = {10.1016/j.bbrc.2004.04.027},
keywords = {Animals, Apoptosis, Base Composition, Base Pairing, Base Sequence,
Binding Sites, Cell Cycle, Cell Proliferation, Comparative Study,
Cultured, Cyclin B, Cyclin D1, DNA-Binding Proteins, Down-Regulation,
Extramural, Fluorescence, Gene Silencing, Gene Targeting, Genetic
Vectors, Green Fluorescent Proteins, Hela Cells, Humans, Hydrogen
Bonding, Luminescent Proteins, Male, Messenger, Mice, Microscopy,
Models, Molecular, Molecular Sequence Data, N.I.H., Non-U.S. Gov't,
Nucleic Acid Conformation, Nude, P.H.S., Prostatic Neoplasms, Proto-Oncogene
Proteins c-bcl-2, Proto-Oncogene Proteins c-myc, RNA, Regression
Analysis, Research Support, STAT3 Transcription Factor, Small Interfering,
Thromboplastin, Trans-Activators, Tumor Cells, U.S. Gov't, 15110788},
pii = {S0006291X04007284},
url = {http://dx.doi.org/10.1016/j.bbrc.2004.04.027}
}
@article{Luo1997Mammalian,
author = {Y. Luo and A. Batalao and H. Zhou and L. Zhu},
title = {Mammalian two-hybrid system: a complementary approach to the yeast
two-hybrid system.},
journal = {Biotechniques},
year = {1997},
volume = {22},
pages = {350--352},
number = {2},
month = {Feb},
abstract = {Here we demonstrate the use of a mammalian two-hybrid system to study
protein-protein interactions. Like the yeast two-hybrid system, this
is a genetic, in vivo assay based on the reconstitution of the function
of a transcriptional activator. In this system, one protein of interest
is expressed as a fusion to the Gal4 DNA-binding domain and another
protein is expressed as a fusion to the activation domain of the
VP16 protein of the herpes simplex virus. The vectors that express
these fusion proteins are cotransfected with a reporter chloramphenicol
acetyltransferase (CAT) vector into a mammalian cell line. The reporter
plasmid contains a cat gene under the control of five consensus Gal4
binding sites. If the two fusion proteins interact, there will be
a significant increase in expression of the cat reporter gene. Previously,
it was reported that mouse p53 antitumor protein and simian virus
40 large T antigen interact in a yeast two-hybrid system. Using a
mammalian two-hybrid system, we were able to independently confirm
this interaction. The mammalian two-hybrid system can be used as
a complementary approach to verify protein-protein interactions detected
by a yeast two-hybrid system screening. In addition, the mammalian
two-hybrid system has two main advantages: (i) Assay results can
be obtained within 48 h of transfection, and (ii) protein interactions
in mammalian cells may better mimic actual in vivo interactions.},
institution = {CLONTECH Laboratories, Palo Alto, CA, USA. yluo@clontech.com},
keywords = {Antigens, Polyomavirus Transforming; Binding Sites; Chloramphenicol
O-Acetyltransferase; DNA; DNA-Binding Proteins; Fungal Proteins;
Genes, Reporter; Genetic Vectors; Hela Cells; Herpes Simplex Virus
Protein Vmw65; Humans; Promoter Regions, Genetic; Recombinant Fusion
Proteins; Saccharomyces cerevisiae Proteins; Simian virus 40; Transcription
Factors; Transfection; Tumor Suppressor Protein p53},
owner = {phupe},
pmid = {9043710},
timestamp = {2010.08.31}
}
@article{Ma2001Hormone-dependent,
author = {H. Ma and C. T. Baumann and H. Li and B. D. Strahl and R. Rice and
M. A. Jelinek and D. W. Aswad and C. D. Allis and G. L. Hager and
M. R. Stallcup},
title = {Hormone-dependent, CARM1-directed, arginine-specific methylation
of histone H3 on a steroid-regulated promoter.},
journal = {Curr Biol},
year = {2001},
volume = {11},
pages = {1981--1985},
number = {24},
month = {Dec},
abstract = {Activation of gene transcription involves chromatin remodeling by
coactivator proteins that are recruited by DNA-bound transcription
factors. Local modification of chromatin structure at specific gene
promoters by ATP-dependent processes and by posttranslational modifications
of histone N-terminal tails provides access to RNA polymerase II
and its accompanying transcription initiation complex. While the
roles of lysine acetylation, serine phosphorylation, and lysine methylation
of histones in chromatin remodeling are beginning to emerge, low
levels of arginine methylation of histones have only recently been
documented, and its physiological role is unknown. The coactivator
CARM1 methylates histone H3 at Arg17 and Arg26 in vitro and cooperates
synergistically with p160-type coactivators (e.g., GRIP1, SRC-1,
ACTR) and coactivators with histone acetyltransferase activity (e.g.,
p300, CBP) to enhance gene activation by steroid and nuclear hormone
receptors (NR) in transient transfection assays. In the current study,
CARM1 cooperated with GRIP1 to enhance steroid hormone-dependent
activation of stably integrated mouse mammary tumor virus (MMTV)
promoters, and this coactivator function required the methyltransferase
activity of CARM1. Chromatin immunoprecipitation assays and immunofluorescence
studies indicated that CARM1 and the CARM1-methylated form of histone
H3 specifically associated with a large tandem array of MMTV promoters
in a hormone-dependent manner. Thus, arginine-specific histone methylation
by CARM1 is an important part of the transcriptional activation process.},
institution = {Department of Pathology, HMR 301, University of Southern California,
2011 Zonal Avenue, Los Angeles, CA 90089, USA.},
keywords = {Acetylation; Arginine, metabolism; Fluorescent Antibody Technique;
Histones, chemistry/metabolism; Hormones, physiology; Lysine, metabolism;
Mammary Tumor Virus, Mouse, genetics; Methylation; Phosphorylation;
Precipitin Tests; Promoter Regions, Genetic; Protein-Arginine N-Methyltransferases,
physiology; Serine, metabolism; Steroids, physiology},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {S0960-9822(01)00600-5},
pmid = {11747826},
timestamp = {2010.11.23}
}
@article{Ma2006MSB,
author = {Wenzhe Ma and Luhua Lai and Qi Ouyang and Chao Tang},
title = {Robustness and modular design of the Drosophila segment polarity
network.},
journal = {Mol Syst Biol},
year = {2006},
volume = {2},
pages = {70},
abstract = {Biomolecular networks have to perform their functions robustly. A
robust function may have preferences in the topological structures
of the underlying network. We carried out an exhaustive computational
analysis on network topologies in relation to a patterning function
in Drosophila embryogenesis. We found that whereas the vast majority
of topologies can either not perform the required function or only
do so very fragilely, a small fraction of topologies emerges as particularly
robust for the function. The topology adopted by Drosophila, that
of the segment polarity network, is a top ranking one among all topologies
with no direct autoregulation. Furthermore, we found that all robust
topologies are modular-each being a combination of three kinds of
modules. These modules can be traced back to three subfunctions of
the patterning function, and their combinations provide a combinatorial
variability for the robust topologies. Our results suggest that the
requirement of functional robustness drastically reduces the choices
of viable topology to a limited set of modular combinations among
which nature optimizes its choice under evolutionary and other biological
constraints.},
doi = {10.1038/msb4100111},
institution = {Center for Theoretical Biology, Peking University, Beijing, China.},
keywords = {Animals; Biological Evolution; Body Patterning; Computer Simulation;
Drosophila Proteins, physiology; Drosophila melanogaster, anatomy
/&/ histology/physiology; Feedback, Physiological; Gene Expression
Regulation, Developmental; Genes, Insect; Models, Biological; Signal
Transduction; Systems Biology, methods; Transcription Factors},
language = {eng},
medline-pst = {ppublish},
owner = {Andrei Zinovyev},
pii = {msb4100111},
pmid = {17170765},
timestamp = {2011.04.08},
url = {http://dx.doi.org/10.1038/msb4100111}
}
@article{MacBeath2002Protein,
author = {Gavin MacBeath},
title = {Protein microarrays and proteomics.},
journal = {Nat Genet},
year = {2002},
volume = {32 Suppl},
pages = {526--532},
month = {Dec},
abstract = {The system-wide study of proteins presents an exciting challenge in
this information-rich age of whole-genome biology. Although traditional
investigations have yielded abundant information about individual
proteins, they have been less successful at providing us with an
integrated understanding of biological systems. The promise of proteomics
is that, by studying many components simultaneously, we will learn
how proteins interact with each other, as well as with non-proteinaceous
molecules, to control complex processes in cells, tissues and even
whole organisms. Here, I discuss the role of microarray technology
in this burgeoning area.},
doi = {10.1038/ng1037},
institution = {Department of Chemistry and Chemical Biology, and Bauer Center for
Genomics Research, Harvard University, 12 Oxford Street, Cambridge,
Massachusetts 02138, USA. macbeath@chemistry.harvard.edu},
keywords = {Forecasting; Humans; Immunoassay, methods; Protein Array Analysis,
methods; Proteomics, methods},
language = {eng},
medline-pst = {ppublish},
owner = {philippe},
pii = {ng1037},
pmid = {12454649},
timestamp = {2010.07.28},
url = {http://dx.doi.org/10.1038/ng1037}
}
@article{Marsland2002self-organising,
author = {Stephen Marsland and Jonathan Shapiro and Ulrich Nehmzow},
title = {A self-organising network that grows when required.},
journal = {Neural {N}etw},
year = {2002},
volume = {15},
pages = {1041-58},
number = {8-9},
abstract = {The ability to grow extra nodes is a potentially useful facility for
a self-organising neural network. {A} network that can add nodes
into its map space can approximate the input space more accurately,
and often more parsimoniously, than a network with predefined structure
and size, such as the {S}elf-{O}rganising {M}ap. {I}n addition, a
growing network can deal with dynamic input distributions. {M}ost
of the growing networks that have been proposed in the literature
add new nodes to support the node that has accumulated the highest
error during previous iterations or to support topological structures.
{T}his usually means that new nodes are added only when the number
of iterations is an integer multiple of some pre-defined constant,
{A}. {T}his paper suggests a way in which the learning algorithm
can add nodes whenever the network in its current state does not
sufficiently match the input. {I}n this way the network grows very
quickly when new data is presented, but stops growing once the network
has matched the data. {T}his is particularly important when we consider
dynamic data sets, where the distribution of inputs can change to
a new regime after some time. {W}e also demonstrate the preservation
of neighbourhood relations in the data by the network. {T}he new
network is compared to an existing growing network, the {G}rowing
{N}eural {G}as ({GNG}), on a artificial dataset, showing how the
network deals with a change in input distribution after some time.
{F}inally, the new network is applied to several novelty detection
tasks and is compared with both the {GNG} and an unsupervised form
of the {R}educed {C}oulomb {E}nergy network on a robotic inspection
task and with a {S}upport {V}ector {M}achine on two benchmark novelty
detection tasks.},
keywords = {Acute, Algorithms, Animals, Anion Exchange Resins, Artificial Intelligence,
Automated, Base Pair Mismatch, Base Pairing, Base Sequence, Biological,
Biosensing Techniques, Carcinoma, Chemical, Chromatography, Citric
Acid Cycle, Classification, Cluster Analysis, Comparative Study,
Computational Biology, Computer-Assisted, Cystadenoma, DNA, Databases,
Decision Making, Diagnosis, Differential, Drug, Drug Design, Electrostatics,
Eukaryotic Cells, Factual, Feasibility Studies, Female, Gene Expression,
Gene Expression Profiling, Gene Expression Regulation, Genes, Genetic,
Genetic Heterogeneity, Genetic Markers, Hemolysins, Humans, Internet,
Ion Exchange, Leukemia, Ligands, Likelihood Functions, Logistic Models,
Lung Neoplasms, Lymphocytic, Lymphoma, Markov Chains, Mathematics,
Messenger, Models, Molecular, Molecular Probe Techniques, Molecular
Sequence Data, Nanotechnology, Neoplasm, Neoplasms, Neoplastic, Neural
Networks (Computer), Non-P.H.S., Non-Small-Cell Lung, Non-U.S. Gov't,
Nucleic Acid Conformation, Nucleic Acid Hybridization, Observer Variation,
Oligonucleotide Array Sequence Analysis, Ovarian Neoplasms, P.H.S.,
Pattern Recognition, Probability, Probability Learning, Protein Binding,
Protein Conformation, Proteins, Quality Control, Quantum Theory,
RNA, RNA Splicing, Receptors, Reference Values, Regression Analysis,
Reproducibility of Results, Research Support, Robotics, Saccharomyces
cerevisiae Proteins, Sensitivity and Specificity, Sequence Analysis,
Signal Processing, Software, Statistical, Stomach Neoplasms, Structural,
Structure-Activity Relationship, Thermodynamics, Transcription, Tumor
Markers, U.S. Gov't, 12416693}
}
@article{Mateos2002Systematic,
author = {Alvaro Mateos and JoaquÃn Dopazo and Ronald Jansen and Yuhai Tu
and Mark Gerstein and Gustavo Stolovitzky},
title = {Systematic learning of gene functional classes from {DNA} array expression
data by using multilayer perceptrons.},
journal = {Genome {R}es.},
year = {2002},
volume = {12},
pages = {1703-15},
number = {11},
month = {Nov},
abstract = {Recent advances in microarray technology have opened new ways for
functional annotation of previously uncharacterised genes on a genomic
scale. {T}his has been demonstrated by unsupervised clustering of
co-expressed genes and, more importantly, by supervised learning
algorithms. {U}sing prior knowledge, these algorithms can assign
functional annotations based on more complex expression signatures
found in existing functional classes. {P}reviously, support vector
machines ({SVM}s) and other machine-learning methods have been applied
to a limited number of functional classes for this purpose. {H}ere
we present, for the first time, the comprehensive application of
supervised neural networks ({SNN}s) for functional annotation. {O}ur
study is novel in that we report systematic results for ~100 classes
in the {M}unich {I}nformation {C}enter for {P}rotein {S}equences
({MIPS}) functional catalog. {W}e found that only ~10\% of these
are learnable (based on the rate of false negatives). {A} closer
analysis reveals that false positives (and negatives) in a machine-learning
context are not necessarily "false" in a biological sense. {W}e show
that the high degree of interconnections among functional classes
confounds the signatures that ought to be learned for a unique class.
{W}e term this the "{B}orges effect" and introduce two new numerical
indices for its quantification. {O}ur analysis indicates that classification
systems with a lower {B}orges effect are better suitable for machine
learning. {F}urthermore, we introduce a learning procedure for combining
false positives with the original class. {W}e show that in a few
iterations this process converges to a gene set that is learnable
with considerably low rates of false positives and negatives and
contains genes that are biologically related to the original class,
allowing for a coarse reconstruction of the interactions between
associated biological pathways. {W}e exemplify this methodology using
the well-studied tricarboxylic acid cycle.},
doi = {10.1101/gr.192502},
pdf = {../local/Mateos2002Systematic.pdf},
file = {Mateos2002Systematic.pdf:local/Mateos2002Systematic.pdf:PDF},
keywords = {Acute, Algorithms, Animals, Anion Exchange Resins, Artificial Intelligence,
Automated, Base Pair Mismatch, Base Pairing, Base Sequence, Biological,
Biosensing Techniques, Carcinoma, Chemical, Chromatography, Citric
Acid Cycle, Classification, Cluster Analysis, Comparative Study,
Computational Biology, Computer-Assisted, Cystadenoma, DNA, Databases,
Decision Making, Diagnosis, Differential, Drug, Drug Design, Electrostatics,
Eukaryotic Cells, Factual, Feasibility Studies, Female, Gene Expression,
Gene Expression Profiling, Gene Expression Regulation, Genes, Genetic,
Genetic Heterogeneity, Genetic Markers, Hemolysins, Humans, Internet,
Ion Exchange, Leukemia, Ligands, Likelihood Functions, Logistic Models,
Lung Neoplasms, Lymphocytic, Lymphoma, Markov Chains, Mathematics,
Messenger, Models, Molecular, Molecular Probe Techniques, Molecular
Sequence Data, Nanotechnology, Neoplasm, Neoplasms, Neoplastic, Neural
Networks (Computer), Non-P.H.S., Non-Small-Cell Lung, Non-U.S. Gov't,
Nucleic Acid Conformation, Nucleic Acid Hybridization, Observer Variation,
Oligonucleotide Array Sequence Analysis, Ovarian Neoplasms, P.H.S.,
Pattern Recognition, Probability, Protein Binding, Protein Conformation,
Proteins, Quality Control, Quantum Theory, RNA, RNA Splicing, Receptors,
Reference Values, Regression Analysis, Reproducibility of Results,
Research Support, Saccharomyces cerevisiae Proteins, Sensitivity
and Specificity, Sequence Analysis, Signal Processing, Software,
Statistical, Stomach Neoplasms, Structural, Structure-Activity Relationship,
Thermodynamics, Transcription, Tumor Markers, U.S. Gov't, 12421757},
url = {http://dx.doi.org/10.1101/gr.192502}
}
@article{Mathews1999Expandeda,
author = {D. H. Mathews and J. Sabina and M. Zuker and D. H. Turner},
title = {{E}xpanded sequence dependence of thermodynamic parameters improves
prediction of {RNA} secondary structure.},
journal = {J. Mol. Biol.},
year = {1999},
volume = {288},
pages = {911--940},
number = {5},
month = {May},
abstract = {An improved dynamic programming algorithm is reported for RNA secondary
structure prediction by free energy minimization. Thermodynamic parameters
for the stabilities of secondary structure motifs are revised to
include expanded sequence dependence as revealed by recent experiments.
Additional algorithmic improvements include reduced search time and
storage for multibranch loop free energies and improved imposition
of folding constraints. An extended database of 151,503 nt in 955
structures? determined by comparative sequence analysis was assembled
to allow optimization of parameters not based on experiments and
to test the accuracy of the algorithm. On average, the predicted
lowest free energy structure contains 73 \% of known base-pairs when
domains of fewer than 700 nt are folded; this compares with 64 \%
accuracy for previous versions of the algorithm and parameters. For
a given sequence, a set of 750 generated structures contains one
structure that, on average, has 86 \% of known base-pairs. Experimental
constraints, derived from enzymatic and flavin mononucleotide cleavage,
improve the accuracy of structure predictions.},
doi = {10.1006/jmbi.1999.2700},
keywords = {16S, 23S, 5S, Affinity, Algorithms, Aluminum Silicates, Amino Acid,
Amino Acid Sequence, Amyloidosis, Archaeal, Bacillus, Bacterial,
Bacterial Proteins, Bacteriophage T4, Base Sequence, Chloroplast,
Chromatography, Circular Dichroism, Comparative Study, Computational
Biology, Databases, Electrophoresis, Entropy, Enzyme Stability, Escherichia
coli, Factual, Fibroblast Growth Factor 2, Flavin Mononucleotide,
Fluorescence, Genetic, Guanidine, Humans, Huntington Disease, Kinetics,
Light, Models, Molecular Sequence Data, Non-P.H.S., Non-U.S. Gov't,
Nucleic Acid Conformation, P.H.S., Peptides, Phylogeny, Polyacrylamide
Gel, Predictive Value of Tests, Protein Binding, Protein Denaturation,
Protein Folding, Protein Structure, RNA, Radiation, Recombinant Proteins,
Research Support, Ribosomal, Scattering, Secondary, Sequence Homology,
Solutions, Spectrometry, Statistical, Temperature, Thermodynamics,
Time Factors, Trinucleotide Repeat Expansion, U.S. Gov't, alpha-Amylase,
10329189},
owner = {vert},
pii = {S0022-2836(99)92700-6},
pmid = {10329189},
timestamp = {2006.04.27},
url = {http://dx.doi.org/10.1006/jmbi.1999.2700}
}
@article{Mavroforakis2005Significance,
author = {Michael Mavroforakis and Harris Georgiou and Nikos Dimitropoulos
and Dionisis Cavouras and Sergios Theodoridis},
title = {Significance analysis of qualitative mammographic features, using
linear classifiers, neural networks and support vector machines.},
journal = {Eur {J} {R}adiol},
year = {2005},
volume = {54},
pages = {80-9},
number = {1},
month = {Apr},
abstract = {Advances in modern technologies and computers have enabled digital
image processing to become a vital tool in conventional clinical
practice, including mammography. {H}owever, the core problem of the
clinical evaluation of mammographic tumors remains a highly demanding
cognitive task. {I}n order for these automated diagnostic systems
to perform in levels of sensitivity and specificity similar to that
of human experts, it is essential that a robust framework on problem-specific
design parameters is formulated. {T}his study is focused on identifying
a robust set of clinical features that can be used as the base for
designing the input of any computer-aided diagnosis system for automatic
mammographic tumor evaluation. {A} thorough list of clinical features
was constructed and the diagnostic value of each feature was verified
against current clinical practices by an expert physician. {T}hese
features were directly or indirectly related to the overall morphological
properties of the mammographic tumor or the texture of the fine-scale
tissue structures as they appear in the digitized image, while others
contained external clinical data of outmost importance, like the
patient's age. {T}he entire feature set was used as an annotation
list for describing the clinical properties of mammographic tumor
cases in a quantitative way, such that subsequent objective analyses
were possible. {F}or the purposes of this study, a mammographic image
database was created, with complete clinical evaluation descriptions
and positive histological verification for each case. {A}ll tumors
contained in the database were characterized according to the identified
clinical features' set and the resulting dataset was used as input
for discrimination and diagnostic value analysis for each one of
these features. {S}pecifically, several standard methodologies of
statistical significance analysis were employed to create feature
rankings according to their discriminating power. {M}oreover, three
different classification models, namely linear classifiers, neural
networks and support vector machines, were employed to investigate
the true efficiency of each one of them, as well as the overall complexity
of the diagnostic task of mammographic tumor characterization. {B}oth
the statistical and the classification results have proven the explicit
correlation of all the selected features with the final diagnosis,
qualifying them as an adequate input base for any type of similar
automated diagnosis system. {T}he underlying complexity of the diagnostic
task has justified the high value of sophisticated pattern recognition
architectures.},
doi = {10.1016/j.ejrad.2004.12.015},
pdf = {../local/Mavroforakis2005Significance.pdf},
file = {Mavroforakis2005Significance.pdf:local/Mavroforakis2005Significance.pdf:PDF},
keywords = {Algorithms, Animals, Antibiotics, Antineoplastic, Artificial Intelligence,
Butadienes, Chloroplasts, Comparative Study, Computer Simulation,
Computer-Assisted, Diagnosis, Disinfectants, Dose-Response Relationship,
Drug, Drug Toxicity, Electrodes, Electroencephalography, Ethylamines,
Expert Systems, Feedback, Fungicides, Gene Expression Profiling,
Genes, Genetic Markers, Humans, Implanted, Industrial, Information
Storage and Retrieval, Kidney, Kidney Tubules, MEDLINE, Male, Mercuric
Chloride, Microarray Analysis, Molecular Biology, Motor Cortex, Movement,
Natural Language Processing, Neural Networks (Computer), Non-P.H.S.,
Non-U.S. Gov't, Plant Proteins, Predictive Value of Tests, Proteins,
Proteome, Proximal, Puromycin Aminonucleoside, Rats, Reproducibility
of Results, Research Support, Sprague-Dawley, Subcellular Fractions,
Terminology, Therapy, Time Factors, Toxicogenetics, U.S. Gov't, User-Computer
Interface, 15797296},
pii = {S0720-048X(05)00023-9},
url = {http://dx.doi.org/10.1016/j.ejrad.2004.12.015}
}
@article{Mestres2004Computational,
author = {Jordi Mestres},
title = {Computational chemogenomics approaches to systematic knowledge-based
drug discovery.},
journal = {Curr Opin Drug Discov Devel},
year = {2004},
volume = {7},
pages = {304--313},
number = {3},
month = {May},
abstract = {Chemogenomics, the identification of all possible drugs for all possible
targets, has recently emerged as a new paradigm in drug discovery
in which efficiency in the compound design and optimization process
is achieved through the gain and reuse of targeted knowledge. As
targeted knowledge resides at the interface between chemistry and
biology, computational tools aimed at integrating the chemical and
biological spaces play a central role in chemogenomics. This review
covers the recent progress made in integrative computational approaches
to data annotation and knowledge generation for the systematic knowledge-based
design and screening of chemical libraries.},
keywords = {Chemistry, Pharmaceutical; Combinatorial Chemistry Techniques; Computational
Biology; Drug Design; Genomics; Ligands; Proteins; Receptors, G-Protein-Coupled},
owner = {vert},
pmid = {15216933},
timestamp = {2007.08.02}
}
@article{Micchelli2005On,
author = {Charles A Micchelli and Massimiliano Pontil},
title = {On learning vector-valued functions.},
journal = {Neural {C}omput},
year = {2005},
volume = {17},
pages = {177-204},
number = {1},
month = {Jan},
abstract = {In this letter, we provide a study of learning in a {H}ilbert space
of vectorvalued functions. {W}e motivate the need for extending learning
theory of scalar-valued functions by practical considerations and
establish some basic results for learning vector-valued functions
that should prove useful in applications. {S}pecifically, we allow
an output space {Y} to be a {H}ilbert space, and we consider a reproducing
kernel {H}ilbert space of functions whose values lie in {Y}. {I}n
this setting, we derive the form of the minimal norm interpolant
to a finite set of data and apply it to study some regularization
functionals that are important in learning theory. {W}e consider
specific examples of such functionals corresponding to multiple-output
regularization networks and support vector machines, for both regression
and classification. {F}inally, we provide classes of operator-valued
kernels of the dot product and translation-invariant type.},
doi = {10.1162/0899766052530802},
keywords = {Algorithms, Amino Acid, Amino Acids, Artificial Intelligence, Ascomycota,
Automated, Base Sequence, Chromosome Mapping, Codon, Colonic Neoplasms,
Comparative Study, Computer Simulation, Computer-Assisted, Computing
Methodologies, Crystallography, DNA, DNA Primers, Databases, Decision
Support Techniques, Diagnostic Imaging, Enzymes, Feedback, Fixation,
Gene Expression Profiling, Genetic, Hordeum, Host-Parasite Relations,
Humans, Image Enhancement, Image Interpretation, Informatics, Information
Storage and Retrieval, Kinetics, Logistic Models, Magnetic Resonance
Spectroscopy, Mathematical Computing, Models, Nanotechnology, Neural
Networks (Computer), Non-P.H.S., Non-U.S. Gov't, Nonlinear Dynamics,
Ocular, Oligonucleotide Array Sequence Analysis, P.H.S., Pattern
Recognition, Plant, Plants, Predictive Value of Tests, Protein, Protein
Conformation, Regression Analysis, Research Support, Sample Size,
Selection (Genetics), Sequence Alignment, Sequence Analysis, Sequence
Homology, Signal Processing, Skin, Software, Statistical, Subtraction
Technique, Theoretical, Thermodynamics, U.S. Gov't, Viral Proteins,
X-Ray, 15563752},
url = {http://dx.doi.org/10.1162/0899766052530802}
}
@article{Mishra2006Human,
author = {Mishra, G.R. and Suresh, M. and Kumaran, K. and Kannabiran, N. and
Suresh, S. and Bala, P. and Shivakumar, K. and Anuradha, N. and Reddy,
R. and Raghavan, T.M. and Menon, S. and Hanumanthu, G. and Gupta,
M. and Upendran, S. and Gupta, S. and Mahesh, M. and Jacob, B. and
Mathew, P. and Chatterjee, P. and Arun, K.S. and Sharma, S. and Chandrika,
K.N. and Deshpande, N. and Palvankar, K. and Raghavnath, R. and Krishnakanth,
R. and Karathia, H. and Rekha, B. and Nayak, R. and Vishnupriya,
G. and Kumar, H.G.M. and Nagini, M. and Kumar, G.S.S. and Jose, R.
and Deepthi, P. and Mohan, S.S. and GandhiT.K.B. and Harsha, H.C.
and Deshpande, K.S. and Sarker, M. and Prasad, T.S.K. and Pandey,
A.},
title = {Human protein reference database--2006 update.},
journal = {Nucleic Acids Res},
year = {2006},
volume = {34},
pages = {D411--D414},
number = {Database issue},
month = {Jan},
abstract = {Human Protein Reference Database (HPRD) (http://www.hprd.org) was
developed to serve as a comprehensive collection of protein features,
post-translational modifications (PTMs) and protein-protein interactions.
Since the original report, this database has increased to >20 000
proteins entries and has become the largest database for literature-derived
protein-protein interactions (>30 000) and PTMs (>8000) for human
proteins. We have also introduced several new features in HPRD including:
(i) protein isoforms, (ii) enhanced search options, (iii) linking
of pathway annotations and (iv) integration of a novel browser, GenProt
Viewer (http://www.genprot.org), developed by us that allows integration
of genomic and proteomic information. With the continued support
and active participation by the biomedical community, we expect HPRD
to become a unique source of curated information for the human proteome
and spur biomedical discoveries based on integration of genomic,
transcriptomic and proteomic data.},
doi = {10.1093/nar/gkj141},
institution = {Institute of Bioinformatics, International Tech Park, Bangalore 560
066, India.},
keywords = {Databases, Protein; Genomics; Humans; Internet; Protein Interaction
Mapping; Protein Isoforms; Protein Processing, Post-Translational;
Proteins; Proteome; Proteomics; Signal Transduction; Systems Integration;
User-Computer Interface},
owner = {fantine},
pii = {34/suppl_1/D411},
pmid = {16381900},
timestamp = {2010.10.21},
url = {http://dx.doi.org/10.1093/nar/gkj141}
}
@article{Miteva2005Fast,
author = {M. A. Miteva and W. H. Lee and M. O. Montes and B. O. Villoutreix},
title = {{F}ast structure-based virtual ligand screening combining {FRED},
{DOCK}, and {S}urflex.},
journal = {J. Med. Chem.},
year = {2005},
volume = {48},
pages = {6012--6022},
number = {19},
month = {Sep},
abstract = {A protocol was devised in which FRED, DOCK, and Surflex were combined
in a multistep virtual ligand screening (VLS) procedure to screen
the pocket of four different proteins. One goal was to evaluate the
impact of chaining "freely available packages to academic users"
on docking/scoring accuracy and CPU time consumption. A bank of 65
660 compounds including 49 known actives was generated. Our procedure
is successful because docking/scoring parameters are tuned according
to the nature of the binding pocket and because a shape-based filtering
tool is applied prior to flexible docking. The obtained enrichment
factors are in line with those reported in recent studies. We suggest
that consensus docking/scoring could be valuable to some drug discovery
projects. The present protocol could process the entire bank for
one receptor in less than a week on one processor, suggesting that
VLS experiments could be performed even without large computer resources.},
doi = {10.1021/jm050262h},
keywords = {Binding Sites, Databases, Estrogen, Factor VIIa, Factual, Ligands,
Molecular Structure, Neuraminidase, Non-U.S. Gov't, Protein Binding,
Quantitative Structure-Activity Relationship, Receptors, Research
Support, Thymidine Kinase, 16162004},
owner = {mahe},
pmid = {16162004},
timestamp = {2006.09.07},
url = {http://dx.doi.org/10.1021/jm050262h}
}
@article{Miwakeichi2001comparison,
author = {F. Miwakeichi and R. Ramirez-Padron and P. A. Valdes-Sosa and T.
Ozaki},
title = {A comparison of non-linear non-parametric models for epilepsy data.},
journal = {Comput. {B}iol. {M}ed.},
year = {2001},
volume = {31},
pages = {41-57},
number = {1},
month = {Jan},
abstract = {E{EG} spike and wave ({SW}) activity has been described through a
non-parametric stochastic model estimated by the {N}adaraya-{W}atson
({NW}) method. {I}n this paper the performance of the {NW}, the local
linear polynomial regression and support vector machines ({SVM})
methods were compared. {T}he noise-free realizations obtained by
the {NW} and {SVM} methods reproduced {SW} better than as reported
in previous works. {T}he tuning parameters had to be estimated manually.
{A}dding dynamical noise, only the {NW} method was capable of generating
{SW} similar to training data. {T}he standard deviation of the dynamical
noise was estimated by means of the correlation dimension.},
keywords = {Acute, Acute Disease, Adenocarcinoma, Algorithms, Amino Acid Sequence,
Animals, Artificial Intelligence, Automated, B-Lymphocytes, Bacterial
Proteins, Base Pair Mismatch, Base Sequence, Bayes Theorem, Binding
Sites, Biological, Bone Marrow Cells, Brachyura, Cell Compartmentation,
Chemistry, Child, Chromosome Aberrations, Classification, Codon,
Colonic Neoplasms, Comparative Study, Computational Biology, Computer
Simulation, Computer-Assisted, DNA, Data Interpretation, Databases,
Decision Trees, Diabetes Mellitus, Diagnosis, Discriminant Analysis,
Discrimination Learning, Electric Conductivity, Electroencephalography,
Electrophysiology, Epilepsy, Escherichia coli Proteins, Factual,
Feedback, Female, Fungal, Gastric Emptying, Gene Expression Profiling,
Gene Expression Regulation, Genes, Genetic, Genetic Markers, Genetic
Predisposition to Disease, Genomics, Hemolysins, Humans, Indians,
Information Storage and Retrieval, Initiator, Ion Channels, Kinetics,
Leukemia, Likelihood Functions, Linear Models, Lipid Bilayers, Logistic
Models, Lymphocytic, MEDLINE, Male, Markov Chains, Melanoma, Models,
Molecular, Myeloid, Neoplasm, Neoplasms, Neoplastic, Neural Networks
(Computer), Neurological, Nevus, Non-P.H.S., Non-U.S. Gov't, Nonlinear
Dynamics, Normal Distribution, North American, Nucleic Acid Conformation,
Oligonucleotide Array Sequence Analysis, Organ Specificity, Organelles,
Ovarian Neoplasms, Ovary, P.H.S., Pattern Recognition, Physical,
Pigmented, Predictive Value of Tests, Promoter Regions (Genetics),
Protein Biosynthesis, Protein Folding, Protein Structure, Proteins,
Proteome, RNA, Reproducibility of Results, Research Support, Saccharomyces
cerevisiae, Secondary, Sensitivity and Specificity, Sequence Alignment,
Sequence Analysis, Sex Characteristics, Skin Diseases, Skin Neoplasms,
Skin Pigmentation, Software, Sound Spectrography, Statistical, Stochastic
Processes, Stomach Diseases, T-Lymphocytes, Thermodynamics, Transcription,
Transcription Factors, Tumor Markers, Type 2, U.S. Gov't, Vertebrates,
11058693},
pii = {S0010482500000214}
}
@article{Moitessier2008Towards,
author = {N. Moitessier and P. Englebienne and D. Lee and J. Lawandi and C.
R. Corbeil},
title = {Towards the development of universal, fast and highly accurate docking/scoring
methods: a long way to go.},
journal = {Br. J. Pharmacol.},
year = {2008},
volume = {153 Suppl 1},
pages = {S7--26},
month = {Mar},
abstract = {Accelerating the drug discovery process requires predictive computational
protocols capable of reducing or simplifying the synthetic and/or
combinatorial challenge. Docking-based virtual screening methods
have been developed and successfully applied to a number of pharmaceutical
targets. In this review, we first present the current status of docking
and scoring methods, with exhaustive lists of these. We next discuss
reported comparative studies, outlining criteria for their interpretation.
In the final section, we describe some of the remaining developments
that would potentially lead to a universally applicable docking/scoring
method.},
doi = {10.1038/sj.bjp.0707515},
institution = {Department of Chemistry, McGill University, Montréal, Québec, Canada.
nicolas.moitessier@mcgill.ca},
keywords = {Algorithms; Animals; Artificial Intelligence; Computer Simulation;
Drug Evaluation, Preclinical, methods; Humans; Metals, chemistry;
Models, Molecular; Molecular Conformation; Nucleic Acids, chemistry/drug
effects; Proteins, chemistry/drug effects; Reproducibility of Results;
Stochastic Processes},
owner = {bricehoffmann},
pii = {0707515},
pmid = {18037925},
timestamp = {2009.02.13},
url = {http://dx.doi.org/10.1038/sj.bjp.0707515}
}
@article{Morris2007Identification,
author = {Stephanie A Morris and Bhargavi Rao and Benjamin A Garcia and Sandra
B Hake and Robert L Diaz and Jeffrey Shabanowitz and Donald F Hunt
and C. David Allis and Jason D Lieb and Brian D Strahl},
title = {Identification of histone H3 lysine 36 acetylation as a highly conserved
histone modification.},
journal = {J Biol Chem},
year = {2007},
volume = {282},
pages = {7632--7640},
number = {10},
month = {Mar},
abstract = {Histone lysine acetylation is a major mechanism by which cells regulate
the structure and function of chromatin, and new sites of acetylation
continue to be discovered. Here we identify and characterize histone
H3K36 acetylation (H3K36ac). By mass spectrometric analyses of H3
purified from Tetrahymena thermophila and Saccharomyces cerevisiae
(yeast), we find that H3K36 can be acetylated or methylated. Using
an antibody specific to H3K36ac, we show that this modification is
conserved in mammals. In yeast, genome-wide ChIP-chip experiments
show that H3K36ac is localized predominantly to the promoters of
RNA polymerase II-transcribed genes, a pattern inversely related
to that of H3K36 methylation. The pattern of H3K36ac localization
is similar to that of other sites of H3 acetylation, including H3K9ac
and H3K14ac. Using histone acetyltransferase complexes purified from
yeast, we show that the Gcn5-containing SAGA complex that regulates
transcription specifically acetylates H3K36 in vitro. Deletion of
GCN5 completely abolishes H3K36ac in vivo. These data expand our
knowledge of the genomic targets of Gcn5, show H3K36ac is highly
conserved, and raise the intriguing possibility that the transition
between H3K36ac and H3K36me acts as an "acetyl/methyl switch" governing
chromatin function along transcription units.},
doi = {10.1074/jbc.M607909200},
institution = {Department of Biochemistry and Biophysics, University of North Carolina
School of Medicine, Chapel Hill, North Carolina 27599, USA.},
keywords = {Acetylation; Amino Acid Sequence; Animals; Chromatin Immunoprecipitation;
Conserved Sequence; Histone Acetyltransferases, physiology; Histones,
chemistry; Humans; Lysine; Methylation; Mice; Molecular Sequence
Data; Promoter Regions, Genetic; Saccharomyces cerevisiae Proteins,
physiology; Saccharomyces cerevisiae, chemistry; Tetrahymena, chemistry},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {M607909200},
pmid = {17189264},
timestamp = {2010.11.23},
url = {http://dx.doi.org/10.1074/jbc.M607909200}
}
@article{Mustafi2009Topology,
author = {Debarshi Mustafi and Krzysztof Palczewski},
title = {Topology of class A G protein-coupled receptors: insights gained
from crystal structures of rhodopsins, adrenergic and adenosine receptors.},
journal = {Mol Pharmacol},
year = {2009},
volume = {75},
pages = {1--12},
number = {1},
month = {Jan},
abstract = {Biological membranes are densely packed with membrane proteins that
occupy approximately half of their volume. In almost all cases, membrane
proteins in the native state lack the higher-order symmetry required
for their direct study by diffraction methods. Despite many technical
difficulties, numerous crystal structures of detergent solubilized
membrane proteins have been determined that illustrate their internal
organization. Among such proteins, class A G protein-coupled receptors
have become amenable to crystallization and high resolution X-ray
diffraction analyses. The derived structures of native and engineered
receptors not only provide insights into their molecular arrangements
but also furnish a framework for designing and testing potential
models of transformation from inactive to active receptor signaling
states and for initiating rational drug design.},
doi = {10.1124/mol.108.051938},
institution = {Department of Pharmacology, School of Medicine, Case Western Reserve
University, Cleveland, Ohio 44106-4965, USA.},
keywords = {Animals; Crystallography, X-Ray; Humans; Models, Molecular; Protein
Structure, Secondary; Receptors, Adrenergic; Receptors, G-Protein-Coupled;
Receptors, Purinergic P1; Rhodopsin},
owner = {ljacob},
pii = {mol.108.051938},
pmid = {18945819},
timestamp = {2009.11.09},
url = {http://dx.doi.org/10.1124/mol.108.051938}
}
@article{Nabieva2005Whole-proteome,
author = {Elena Nabieva and Kam Jim and Amit Agarwal and Bernard Chazelle and
Mona Singh},
title = {Whole-proteome prediction of protein function via graph-theoretic
analysis of interaction maps.},
journal = {Bioinformatics},
year = {2005},
volume = {21 Suppl 1},
pages = {i302--i310},
month = {Jun},
abstract = {MOTIVATION: Determining protein function is one of the most important
problems in the post-genomic era. For the typical proteome, there
are no functional annotations for one-third or more of its proteins.
Recent high-throughput experiments have determined proteome-scale
protein physical interaction maps for several organisms. These physical
interactions are complemented by an abundance of data about other
types of functional relationships between proteins, including genetic
interactions, knowledge about co-expression and shared evolutionary
history. Taken together, these pairwise linkages can be used to build
whole-proteome protein interaction maps. RESULTS: We develop a network-flow
based algorithm, FunctionalFlow, that exploits the underlying structure
of protein interaction maps in order to predict protein function.
In cross-validation testing on the yeast proteome, we show that FunctionalFlow
has improved performance over previous methods in predicting the
function of proteins with few (or no) annotated protein neighbors.
By comparing several methods that use protein interaction maps to
predict protein function, we demonstrate that FunctionalFlow performs
well because it takes advantage of both network topology and some
measure of locality. Finally, we show that performance can be improved
substantially as we consider multiple data sources and use them to
create weighted interaction networks. AVAILABILITY: http://compbio.cs.princeton.edu/function},
doi = {10.1093/bioinformatics/bti1054},
institution = {Computer Science Department, Princeton University Princeton, NJ 08544,
USA.},
keywords = {Algorithms; Computational Biology, methods; Evolution, Molecular;
Fungal Proteins, chemistry; Genomics; Models, Statistical; Models,
Theoretical; Protein Interaction Mapping, methods; Proteins, chemistry;
Proteomics, methods},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {21/suppl_1/i302},
pmid = {15961472},
timestamp = {2010.04.03},
url = {http://dx.doi.org/10.1093/bioinformatics/bti1054}
}
@article{Nakayama2001Role,
author = {J. Nakayama and J. C. Rice and B. D. Strahl and C. D. Allis and S.
I. Grewal},
title = {Role of histone H3 lysine 9 methylation in epigenetic control of
heterochromatin assembly.},
journal = {Science},
year = {2001},
volume = {292},
pages = {110--113},
number = {5514},
month = {Apr},
abstract = {The assembly of higher order chromatin structures has been linked
to the covalent modifications of histone tails. We provide in vivo
evidence that lysine 9 of histone H3 (H3 Lys9) is preferentially
methylated by the Clr4 protein at heterochromatin-associated regions
in fission yeast. Both the conserved chromo- and SET domains of Clr4
are required for H3 Lys9 methylation in vivo. Localization of Swi6,
a homolog of Drosophila HP1, to heterochomatic regions is dependent
on H3 Lys9 methylation. Moreover, an H3-specific deacetylase Clr3
and a beta-propeller domain protein Rik1 are required for H3 Lys9
methylation by Clr4 and Swi6 localization. These data define a conserved
pathway wherein sequential histone modifications establish a "histone
code" essential for the epigenetic inheritance of heterochromatin
assembly.},
doi = {10.1126/science.1060118},
institution = {Cold Spring Harbor Laboratory, Post Office Box 100, Cold Spring Harbor,
NY 11724, USA.},
keywords = {Acetylation; Cell Cycle Proteins, chemistry/genetics/metabolism; Centromere,
metabolism; Chromosomes, Fungal, metabolism; Fungal Proteins, genetics/metabolism;
Gene Silencing; Genes, Fungal; Heterochromatin, metabolism; Histone
Deacetylases, genetics/metabolism; Histone-Lysine N-Methyltransferase;
Histones, chemistry/metabolism; Lysine, metabolism; Methylation;
Methyltransferases, chemistry/genetics/metabolism; Mutation; Protein
Methyltransferases; Protein Structure, Tertiary; Recombinant Proteins,
chemistry/metabolism; Saccharomyces cerevisiae Proteins; Schizosaccharomyces
pombe Proteins; Schizosaccharomyces, genetics/metabolism; Transcription
Factors, metabolism},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {1060118},
pmid = {11283354},
timestamp = {2010.11.23},
url = {http://dx.doi.org/10.1126/science.1060118}
}
@article{Nielsen1997Identification,
author = {Nielsen, H. and Engelbrecht, J. and Brunak, S. and von Heijne, G.},
title = {Identification of prokaryotic and eukaryotic signal peptides and
prediction of their cleavage sites},
journal = {Protein {E}ng.},
year = {1997},
volume = {10},
pages = {1--6},
number = {1},
pdf = {../local/niel97.pdf},
file = {niel97.pdf:local/niel97.pdf:PDF},
subject = {bioprot},
url = {http://protein.oupjournals.org/cgi/content/abstract/10/1/1}
}
@article{Ong2002Stable,
author = {Shao-En Ong and Blagoy Blagoev and Irina Kratchmarova and Dan Bach
Kristensen and Hanno Steen and Akhilesh Pandey and Matthias Mann},
title = {Stable isotope labeling by amino acids in cell culture, SILAC, as
a simple and accurate approach to expression proteomics.},
journal = {Mol Cell Proteomics},
year = {2002},
volume = {1},
pages = {376--386},
number = {5},
month = {May},
abstract = {Quantitative proteomics has traditionally been performed by two-dimensional
gel electrophoresis, but recently, mass spectrometric methods based
on stable isotope quantitation have shown great promise for the simultaneous
and automated identification and quantitation of complex protein
mixtures. Here we describe a method, termed SILAC, for stable isotope
labeling by amino acids in cell culture, for the in vivo incorporation
of specific amino acids into all mammalian proteins. Mammalian cell
lines are grown in media lacking a standard essential amino acid
but supplemented with a non-radioactive, isotopically labeled form
of that amino acid, in this case deuterated leucine (Leu-d3). We
find that growth of cells maintained in these media is no different
from growth in normal media as evidenced by cell morphology, doubling
time, and ability to differentiate. Complete incorporation of Leu-d3
occurred after five doublings in the cell lines and proteins studied.
Protein populations from experimental and control samples are mixed
directly after harvesting, and mass spectrometric identification
is straightforward as every leucine-containing peptide incorporates
either all normal leucine or all Leu-d3. We have applied this technique
to the relative quantitation of changes in protein expression during
the process of muscle cell differentiation. Proteins that were found
to be up-regulated during this process include glyceraldehyde-3-phosphate
dehydrogenase, fibronectin, and pyruvate kinase M2. SILAC is a simple,
inexpensive, and accurate procedure that can be used as a quantitative
proteomic approach in any cell culture system.},
institution = {Protein Interaction Laboratory, University of Southern Denmark, Odense,
Denmark.},
keywords = {3T3 Cells; Amino Acids; Animals; Cell Culture Techniques; Cell Differentiation;
Cell Line; Deuterium; Genetic Techniques; Hydrogen-Ion Concentration;
Leucine; Mice; Muscles; Peptides; Proteomics; Time Factors; Up-Regulation},
owner = {phupe},
pmid = {12118079},
timestamp = {2010.08.19}
}
@article{Opper2001Universal,
author = {M. Opper and R. Urbanczik},
title = {Universal learning curves of support vector machines.},
journal = {Phys {R}ev {L}ett},
year = {2001},
volume = {86},
pages = {4410-3},
number = {19},
month = {May},
abstract = {Using methods of statistical physics, we investigate the role of model
complexity in learning with support vector machines ({SVM}s), which
are an important alternative to neural networks. {W}e show the advantages
of using {SVM}s with kernels of infinite complexity on noisy target
rules, which, in contrast to common theoretical beliefs, are found
to achieve optimal generalization error although the training error
does not converge to the generalization error. {M}oreover, we find
a universal asymptotics of the learning curves which depend only
on the target rule but not on the {SVM} kernel.},
keywords = {Algorithms, Amino Acid Sequence, Artificial Intelligence, Biological,
Cell Compartmentation, Chemistry, Comparative Study, Computational
Biology, Computer Simulation, Computer-Assisted, Databases, Decision
Trees, Diagnosis, Discriminant Analysis, Electrophysiology, Factual,
Gastric Emptying, Humans, Logistic Models, Melanoma, Models, Neural
Networks (Computer), Nevus, Non-U.S. Gov't, Organelles, P.H.S., Physical,
Pigmented, Predictive Value of Tests, Proteins, Proteome, Reproducibility
of Results, Research Support, Skin Diseases, Skin Neoplasms, Skin
Pigmentation, Software, Stomach Diseases, U.S. Gov't, 11328187}
}
@article{Opper2000Gaussian,
author = {M. Opper and O. Winther},
title = {Gaussian processes for classification: mean-field algorithms.},
journal = {Neural {C}omput},
year = {2000},
volume = {12},
pages = {2655-84},
number = {11},
month = {Nov},
abstract = {We derive a mean-field algorithm for binary classification with gaussian
processes that is based on the {TAP} approach originally proposed
in statistical physics of disordered systems. {T}he theory also yields
an approximate leave-one-out estimator for the generalization error,
which is computed with no extra computational cost. {W}e show that
from the {TAP} approach, it is possible to derive both a simpler
"naive" mean-field theory and support vector machines ({SVM}s) as
limiting cases. {F}or both mean-field algorithms and support vector
machines, simulation results for three small benchmark data sets
are presented. {T}hey show that one may get state-of-the-art performance
by using the leave-one-out estimator for model selection and the
built-in leave-one-out estimators are extremely precise when compared
to the exact leave-one-out estimate. {T}he second result is taken
as strong support for the internal consistency of the mean-field
approach.},
keywords = {Acute, Acute Disease, Adenocarcinoma, Algorithms, Amino Acid Sequence,
Animals, Artificial Intelligence, Automated, B-Lymphocytes, Bacterial
Proteins, Base Pair Mismatch, Base Sequence, Bayes Theorem, Binding
Sites, Biological, Bone Marrow Cells, Brachyura, Cell Compartmentation,
Chemistry, Child, Chromosome Aberrations, Classification, Colonic
Neoplasms, Comparative Study, Computational Biology, Computer Simulation,
Computer-Assisted, DNA, Data Interpretation, Databases, Decision
Trees, Diabetes Mellitus, Diagnosis, Discriminant Analysis, Discrimination
Learning, Electric Conductivity, Electrophysiology, Escherichia coli
Proteins, Factual, Feedback, Female, Fungal, Gastric Emptying, Gene
Expression Profiling, Gene Expression Regulation, Genes, Genetic,
Genetic Markers, Genetic Predisposition to Disease, Hemolysins, Humans,
Indians, Ion Channels, Kinetics, Leukemia, Likelihood Functions,
Lipid Bilayers, Logistic Models, Lymphocytic, Male, Markov Chains,
Melanoma, Models, Molecular, Myeloid, Neoplasm, Neoplasms, Neoplastic,
Neural Networks (Computer), Neurological, Nevus, Non-P.H.S., Non-U.S.
Gov't, Nonlinear Dynamics, Normal Distribution, North American, Nucleic
Acid Conformation, Oligonucleotide Array Sequence Analysis, Organ
Specificity, Organelles, Ovarian Neoplasms, Ovary, P.H.S., Pattern
Recognition, Physical, Pigmented, Predictive Value of Tests, Promoter
Regions (Genetics), Protein Folding, Protein Structure, Proteins,
Proteome, RNA, Reproducibility of Results, Research Support, Saccharomyces
cerevisiae, Secondary, Sensitivity and Specificity, Sequence Alignment,
Sex Characteristics, Skin Diseases, Skin Neoplasms, Skin Pigmentation,
Software, Sound Spectrography, Statistical, Stomach Diseases, T-Lymphocytes,
Thermodynamics, Transcription, Transcription Factors, Tumor Markers,
Type 2, U.S. Gov't, 11110131}
}
@article{Oti2006Predicting,
author = {M. Oti and B. Snel and M. A. Huynen and H. G. Brunner},
title = {Predicting disease genes using protein-protein interactions.},
journal = {J Med Genet},
year = {2006},
volume = {43},
pages = {691--698},
number = {8},
month = {Aug},
abstract = {BACKGROUND: The responsible genes have not yet been identified for
many genetically mapped disease loci. Physically interacting proteins
tend to be involved in the same cellular process, and mutations in
their genes may lead to similar disease phenotypes. OBJECTIVE: To
investigate whether protein-protein interactions can predict genes
for genetically heterogeneous diseases. METHODS: 72,940 protein-protein
interactions between 10,894 human proteins were used to search 432
loci for candidate disease genes representing 383 genetically heterogeneous
hereditary diseases. For each disease, the protein interaction partners
of its known causative genes were compared with the disease associated
loci lacking identified causative genes. Interaction partners located
within such loci were considered candidate disease gene predictions.
Prediction accuracy was tested using a benchmark set of known disease
genes. RESULTS: Almost 300 candidate disease gene predictions were
made. Some of these have since been confirmed. On average, 10\% or
more are expected to be genuine disease genes, representing a 10-fold
enrichment compared with positional information only. Examples of
interesting candidates are AKAP6 for arrythmogenic right ventricular
dysplasia 3 and SYN3 for familial partial epilepsy with variable
foci. CONCLUSIONS: Exploiting protein-protein interactions can greatly
increase the likelihood of finding positional candidate disease genes.
When applied on a large scale they can lead to novel candidate gene
predictions.},
doi = {10.1136/jmg.2006.041376},
keywords = {Animals; Benchmarking; Databases, Protein; Disease; Genetic Predisposition
to Disease; Humans; Protein Binding; Proteins},
owner = {mordelet},
pii = {jmg.2006.041376},
pmid = {16611749},
timestamp = {2010.09.28},
url = {http://dx.doi.org/10.1136/jmg.2006.041376}
}
@article{Paik2006Gene,
author = {Paik, Soonmyung and Tang, Gong and Shak, Steven and Kim, Chungyeul
and Baker, Joffre and Kim, Wanseop and Cronin, Maureen and Baehner,
Frederick L. and Watson, Drew and Bryant, John and Costantino, Joseph
P. and Geyer, Jr, Charles E and Wickerham, D Lawrence and Wolmark,
Norman},
title = {Gene expression and benefit of chemotherapy in women with node-negative,
estrogen receptor-positive breast cancer.},
journal = {J Clin Oncol},
year = {2006},
volume = {24},
pages = {3726--3734},
number = {23},
month = {Aug},
abstract = {The 21-gene recurrence score (RS) assay quantifies the likelihood
of distant recurrence in women with estrogen receptor-positive, lymph
node-negative breast cancer treated with adjuvant tamoxifen. The
relationship between the RS and chemotherapy benefit is not known.The
RS was measured in tumors from the tamoxifen-treated and tamoxifen
plus chemotherapy-treated patients in the National Surgical Adjuvant
Breast and Bowel Project (NSABP) B20 trial. Cox proportional hazards
models were utilized to test for interaction between chemotherapy
treatment and the RS.A total of 651 patients were assessable (227
randomly assigned to tamoxifen and 424 randomly assigned to tamoxifen
plus chemotherapy). The test for interaction between chemotherapy
treatment and RS was statistically significant (P = .038). Patients
with high-RS (> or = 31) tumors (ie, high risk of recurrence) had
a large benefit from chemotherapy (relative risk, 0.26; 95\% CI,
0.13 to 0.53; absolute decrease in 10-year distant recurrence rate:
mean, 27.6\%; SE, 8.0\%). Patients with low-RS (< 18) tumors derived
minimal, if any, benefit from chemotherapy treatment (relative risk,
1.31; 95\% CI, 0.46 to 3.78; absolute decrease in distant recurrence
rate at 10 years: mean, -1.1\%; SE, 2.2\%). Patients with intermediate-RS
tumors did not appear to have a large benefit, but the uncertainty
in the estimate can not exclude a clinically important benefit.The
RS assay not only quantifies the likelihood of breast cancer recurrence
in women with node-negative, estrogen receptor-positive breast cancer,
but also predicts the magnitude of chemotherapy benefit.},
doi = {10.1200/JCO.2005.04.7985},
institution = {Division of Pathology, Operations Center, and Biostatistical Center,
National Surgical Adjuvant Breast and Bowel Project, Pittsburgh,
PA 15212, USA. soon.paik@nsabp.org},
keywords = {Adult; Aged; Antineoplastic Combined Chemotherapy Protocols, administration
/&/ dosage/therapeutic use; Breast Neoplasms, drug therapy/metabolism/pathology/prevention
/&/ control; Cisplatin, administration /&/ dosage; Female; Fluorouracil,
administration /&/ dosage; Gene Expression Regulation, Neoplastic;
Humans; Linear Models; Lymphatic Metastasis; Methotrexate, administration
/&/ dosage; Middle Aged; Mitomycins, administration /&/ dosage; Neoplasm
Proteins, metabolism; Neoplasm Recurrence, Local, metabolism/prevention
/&/ control; Odds Ratio; Predictive Value of Tests; Prognosis; Proportional
Hazards Models; Randomized Controlled Trials as Topic; Receptors,
Estrogen, metabolism; Recurrence, prevention /&/ control; Reverse
Transcriptase Polymerase Chain Reaction; Risk Assessment; Risk Factors;
Tamoxifen, administration /&/ dosage; Tumor Markers, Biological,
metabolism},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {JCO.2005.04.7985},
pmid = {16720680},
timestamp = {2012.03.09},
url = {http://dx.doi.org/10.1200/JCO.2005.04.7985}
}
@article{Pandey2000Proteomics,
author = {Pandey, A. and Mann, M.},
title = {Proteomics to study genes and genomes},
journal = {Nature},
year = {2000},
volume = {405},
pages = {837--846},
pdf = {../local/pand00.pdf},
file = {pand00.pdf:local/pand00.pdf:PDF},
subject = {bioprot},
url = {http://www.nature.com/cgi-taf/DynaPage.taf?file=/nature/journal/v405/n6788/full/405837a0_fs.html&content_filetype=pdf}
}
@article{Papadopoulos2005Characterization,
author = {A. Papadopoulos and D. I. Fotiadis and A. Likas},
title = {Characterization of clustered microcalcifications in digitized mammograms
using neural networks and support vector machines.},
journal = {Artif. {I}ntell. {M}ed.},
year = {2005},
volume = {34},
pages = {141-50},
number = {2},
month = {Jun},
abstract = {O{BJECTIVE}: {D}etection and characterization of microcalcification
clusters in mammograms is vital in daily clinical practice. {T}he
scope of this work is to present a novel computer-based automated
method for the characterization of microcalcification clusters in
digitized mammograms. {METHODS} {AND} {MATERIAL}: {T}he proposed
method has been implemented in three stages: (a) the cluster detection
stage to identify clusters of microcalcifications, (b) the feature
extraction stage to compute the important features of each cluster
and (c) the classification stage, which provides with the final characterization.
{I}n the classification stage, a rule-based system, an artificial
neural network ({ANN}) and a support vector machine ({SVM}) have
been implemented and evaluated using receiver operating characteristic
({ROC}) analysis. {T}he proposed method was evaluated using the {N}ijmegen
and {M}ammographic {I}mage {A}nalysis {S}ociety ({MIAS}) mammographic
databases. {T}he original feature set was enhanced by the addition
of four rule-based features. {RESULTS} {AND} {CONCLUSIONS}: {I}n
the case of {N}ijmegen dataset, the performance of the {SVM} was
{A}z=0.79 and 0.77 for the original and enhanced feature set, respectively,
while for the {MIAS} dataset the corresponding characterization scores
were {A}z=0.81 and 0.80. {U}tilizing neural network classification
methodology, the corresponding performance for the {N}ijmegen dataset
was {A}z=0.70 and 0.76 while for the {MIAS} dataset it was {A}z=0.73
and 0.78. {A}lthough the obtained high classification performance
can be successfully applied to microcalcification clusters characterization,
further studies must be carried out for the clinical evaluation of
the system using larger datasets. {T}he use of additional features
originating either from the image itself (such as cluster location
and orientation) or from the patient data may further improve the
diagnostic value of the system.},
doi = {10.1016/j.artmed.2004.10.001},
pdf = {../local/Papadopoulos2005Characterization.pdf},
file = {Papadopoulos2005Characterization.pdf:local/Papadopoulos2005Characterization.pdf:PDF},
keywords = {Apoptosis, Gene Expression Profiling, Humans, Neoplasms, Non-U.S.
Gov't, Oligonucleotide Array Sequence Analysis, Polymerase Chain
Reaction, Proteins, Research Support, Subcellular Fractions, Unknown
Primary, 15894178},
pii = {S0933-3657(04)00154-X},
url = {http://dx.doi.org/10.1016/j.artmed.2004.10.001}
}
@article{Park2009ChIP,
author = {Peter J Park},
title = {ChIP-seq: advantages and challenges of a maturing technology.},
journal = {Nat Rev Genet},
year = {2009},
volume = {10},
pages = {669--680},
number = {10},
month = {Oct},
abstract = {Chromatin immunoprecipitation followed by sequencing (ChIP-seq) is
a technique for genome-wide profiling of DNA-binding proteins, histone
modifications or nucleosomes. Owing to the tremendous progress in
next-generation sequencing technology, ChIP-seq offers higher resolution,
less noise and greater coverage than its array-based predecessor
ChIP-chip. With the decreasing cost of sequencing, ChIP-seq has become
an indispensable tool for studying gene regulation and epigenetic
mechanisms. In this Review, I describe the benefits and challenges
in harnessing this technique with an emphasis on issues related to
experimental design and data analysis. ChIP-seq experiments generate
large quantities of data, and effective computational analysis will
be crucial for uncovering biological mechanisms.},
doi = {10.1038/nrg2641},
institution = {Harvard Medical School, 10 Shattuck Street, Boston, MA 02115, USA.
peter_park@harvard.edu},
keywords = {Animals; Chromatin Immunoprecipitation, methods; Computational Biology;
DNA-Binding Proteins, genetics; Epigenesis, Genetic; Humans; Nucleosomes,
genetics; Sequence Analysis, DNA, methods},
language = {eng},
medline-pst = {ppublish},
owner = {philippe},
pii = {nrg2641},
pmid = {19736561},
timestamp = {2010.08.05},
url = {http://dx.doi.org/10.1038/nrg2641}
}
@techreport{Pastor-Satorras2002Evolving,
author = {Pastor-Satorras, R. and Smith, E. D. and Sol{\'e}, R. V.},
title = {Evolving protein interaction networks through gene duplication},
institution = {Santa Fe Institute},
year = {2002},
note = {Working paper 02-02-008},
pdf = {../local/past02.pdf},
file = {past02.pdf:local/past02.pdf:PDF},
subject = {bionetprot},
url = {http://www.santafe.edu/sfi/publications/Abstracts/02-02-008abs.html}
}
@article{Patterson2003Proteomics,
author = {Scott D Patterson and Ruedi H Aebersold},
title = {Proteomics: the first decade and beyond.},
journal = {Nat Genet},
year = {2003},
volume = {33 Suppl},
pages = {311--323},
month = {Mar},
abstract = {Proteomics is the systematic study of the many and diverse properties
of proteins in a parallel manner with the aim of providing detailed
descriptions of the structure, function and control of biological
systems in health and disease. Advances in methods and technologies
have catalyzed an expansion of the scope of biological studies from
the reductionist biochemical analysis of single proteins to proteome-wide
measurements. Proteomics and other complementary analysis methods
are essential components of the emerging 'systems biology' approach
that seeks to comprehensively describe biological systems through
integration of diverse types of data and, in the future, to ultimately
allow computational simulations of complex biological systems.},
doi = {10.1038/ng1106},
institution = {Celera Genomics Corporation, 45 West Gude Drive, Rockville, Maryland
20850, USA. scottp@farmalbiomed.com},
keywords = {Amino Acid Sequence; Base Sequence; Chromatography, Liquid; Computational
Biology; DNA; Genetic Techniques; History, 20th Century; History,
21st Century; Mass Spectrometry; Oligonucleotide Array Sequence Analysis;
Proteins; Proteomics},
owner = {phupe},
pii = {ng1106},
pmid = {12610541},
timestamp = {2010.08.13},
url = {http://dx.doi.org/10.1038/ng1106}
}
@article{Pavlidis2004Support,
author = {Paul Pavlidis and Ilan Wapinski and William Stafford Noble},
title = {Support vector machine classification on the web.},
journal = {Bioinformatics},
year = {2004},
volume = {20},
pages = {586-7},
number = {4},
month = {Mar},
abstract = {The support vector machine ({SVM}) learning algorithm has been widely
applied in bioinformatics. {W}e have developed a simple web interface
to our implementation of the {SVM} algorithm, called {G}ist. {T}his
interface allows novice or occasional users to apply a sophisticated
machine learning algorithm easily to their data. {M}ore advanced
users can download the software and source code for local installation.
{T}he availability of these tools will permit more widespread application
of this powerful learning algorithm in bioinformatics.},
doi = {10.1093/bioinformatics/btg461},
pdf = {../local/Pavlidis2004Support.pdf},
file = {Pavlidis2004Support.pdf:local/Pavlidis2004Support.pdf:PDF},
keywords = {Adaptation, Algorithms, Ambergris, Amino Acid Sequence, Animals, Artifacts,
Artificial Intelligence, Automated, Cadmium, Candida, Candida albicans,
Capillary, Clinical, Cluster Analysis, Combinatorial Chemistry Techniques,
Comparative Study, Computational Biology, Computer Simulation, Computer-Assisted,
Computing Methodologies, Databases, Decision Support Systems, Electrophoresis,
Enzymes, Europe, Eye Enucleation, Humans, Image Interpretation, Image
Processing, Information Storage and Retrieval, Internet, Magnetic
Resonance Imaging, Magnetic Resonance Spectroscopy, Markov Chains,
Melanoma, Models, Molecular, Molecular Conformation, Molecular Sequence
Data, Molecular Structure, Neural Networks (Computer), Non-P.H.S.,
Non-U.S. Gov't, Nonlinear Dynamics, Odors, P.H.S., Pattern Recognition,
Perfume, Physiological, Predictive Value of Tests, Prognosis, Prospective
Studies, Protein, Protein Structure, Proteins, Proteomics, Quantitative
Structure-Activity Relationship, Rats, Reproducibility of Results,
Research Support, Saccharomyces cerevisiae, Saccharomyces cerevisiae
Proteins, Secondary, Sensitivity and Specificity, Signal Processing,
Single-Blind Method, Soft Tissue Neoplasms, Software, Statistical,
U.S. Gov't, Uveal Neoplasms, Visual, 14990457},
pii = {btg461},
url = {http://dx.doi.org/10.1093/bioinformatics/btg461}
}
@article{Pepperrell1991Techniques,
author = {C. A. Pepperrell and P. Willett},
title = {{T}echniques for the calculation of three-dimensional structural
similarity using inter-atomic distances.},
journal = {J Comput Aided Mol Des},
year = {1991},
volume = {5},
pages = {455--474},
number = {5},
month = {Oct},
abstract = {This paper reports a comparison of several methods for measuring the
degree of similarity between pairs of 3-D chemical structures that
are represented by inter-atomic distance matrices. The methods that
have been tested use the distance information in very different ways
and have very different computational requirements. Experiments with
10 small datasets, for which both structural and biological activity
data are available, suggest that the most cost-effective technique
is based on a mapping procedure that tries to match pairs of atoms,
one from each of the molecules that are being compared, that have
neighbouring atoms at approximately the same distances.},
keywords = {Algorithms, Binding Sites, Chemical, Chemistry, Comparative Study,
Computer Simulation, Databases, Factual, Macromolecular Substances,
Models, Molecular Conformation, Molecular Structure, Non-U.S. Gov't,
Physical, Protein Conformation, Protein Structure, Proteins, Research
Support, Structure-Activity Relationship, Tertiary, 1770381},
owner = {mahe},
pmid = {1770381},
timestamp = {2006.08.22}
}
@article{Perola2004Conformational,
author = {Emanuele Perola and Paul S Charifson},
title = {Conformational analysis of drug-like molecules bound to proteins:
an extensive study of ligand reorganization upon binding.},
journal = {J. Med. Chem.},
year = {2004},
volume = {47},
pages = {2499--2510},
number = {10},
month = {May},
abstract = {This paper describes a large-scale study on the nature and the energetics
of the conformational changes drug-like molecules experience upon
binding. Ligand strain energies and conformational reorganization
were analyzed with different computational methods on 150 crystal
structures of pharmaceutically relevant protein-ligand complexes.
The common knowledge that ligands rarely bind in their lowest calculated
energy conformation was confirmed. Additionally, we found that over
60\% of the ligands do not bind in a local minimum conformation.
While approximately 60\% of the ligands were calculated to bind with
strain energies lower than 5 kcal/mol, strain energies over 9 kcal/mol
were calculated in at least 10\% of the cases regardless of the method
used. A clear correlation was found between acceptable strain energy
and ligand flexibility, while there was no correlation between strain
energy and binding affinity, thus indicating that expensive conformational
rearrangements can be tolerated in some cases without overly penalizing
the tightness of binding. On the basis of the trends observed, thresholds
for the acceptable strain energies of bioactive conformations were
defined with consideration of the impact of ligand flexibility. An
analysis of the degree of folding of the bound ligands confirmed
the general tendency of small molecules to bind in an extended conformation.
The results suggest that the unfolding of hydrophobic ligands during
binding, which exposes hydrophobic surfaces to contact with protein
residues, could be one of the factors accounting for high reorganization
energies. Finally, different methods for conformational analysis
were evaluated, and guidelines were defined to maximize the prevalence
of bioactive conformations in computationally generated ensembles.},
doi = {10.1021/jm030563w},
keywords = {Drug Design; Endopeptidases; Ligands; Molecular Conformation; Pharmaceutical
Preparations; Phosphotransferases; Protein Binding; Protein Folding;
Proteins; Thermodynamics},
owner = {laurent},
pmid = {15115393},
timestamp = {2008.01.16},
url = {http://dx.doi.org/10.1021/jm030563w}
}
@article{Peters2005Generating,
author = {Bjoern Peters and Alessandro Sette},
title = {Generating quantitative models describing the sequence specificity
of biological processes with the stabilized matrix method.},
journal = {BMC Bioinformatics},
year = {2005},
volume = {6},
pages = {132},
abstract = {BACKGROUND: Many processes in molecular biology involve the recognition
of short sequences of nucleic-or amino acids, such as the binding
of immunogenic peptides to major histocompatibility complex (MHC)
molecules. From experimental data, a model of the sequence specificity
of these processes can be constructed, such as a sequence motif,
a scoring matrix or an artificial neural network. The purpose of
these models is two-fold. First, they can provide a summary of experimental
results, allowing for a deeper understanding of the mechanisms involved
in sequence recognition. Second, such models can be used to predict
the experimental outcome for yet untested sequences. In the past
we reported the development of a method to generate such models called
the Stabilized Matrix Method (SMM). This method has been successfully
applied to predicting peptide binding to MHC molecules, peptide transport
by the transporter associated with antigen presentation (TAP) and
proteasomal cleavage of protein sequences. RESULTS: Herein we report
the implementation of the SMM algorithm as a publicly available software
package. Specific features determining the type of problems the method
is most appropriate for are discussed. Advantageous features of the
package are: (1) the output generated is easy to interpret, (2) input
and output are both quantitative, (3) specific computational strategies
to handle experimental noise are built in, (4) the algorithm is designed
to effectively handle bounded experimental data, (5) experimental
data from randomized peptide libraries and conventional peptides
can easily be combined, and (6) it is possible to incorporate pair
interactions between positions of a sequence. CONCLUSION: Making
the SMM method publicly available enables bioinformaticians and experimental
biologists to easily access it, to compare its performance to other
prediction methods, and to extend it to other applications.},
doi = {10.1186/1471-2105-6-132},
keywords = {Algorithms; Amino Acid Sequence; Biology; Computational Biology; Computer
Simulation; Data Interpretation, Statistical; Databases, Protein;
Models, Biological; Models, Statistical; Neural Networks (Computer);
Peptide Library; Peptides; Programming Languages; Prote; Sensitivity
and Specificity; Software; in Binding},
owner = {laurent},
pii = {1471-2105-6-132},
pmid = {15927070},
timestamp = {2007.07.12},
url = {http://dx.doi.org/10.1186/1471-2105-6-132}
}
@article{Poggio1998Sparse,
author = {Poggio and Girosi},
title = {A {S}parse {R}epresentation for {F}unction {A}pproximation.},
journal = {Neural {C}omput},
year = {1998},
volume = {10},
pages = {1445-54},
number = {6},
month = {Jul},
abstract = {We derive a new general representation for a function as a linear
combination of local correlation kernels at optimal sparse locations
(and scales) and characterize its relation to principal component
analysis, regularization, sparsity principles, and support vector
machines.},
keywords = {Algorithms, Automated, Biometry, Computers, DNA, Databases, Factual,
Fungal, Fungal Proteins, GTP-Binding Proteins, Gene Expression, Genes,
Learning, Markov Chains, Models, Neural Networks (Computer), Neurological,
Non-P.H.S., Non-U.S. Gov't, Nucleic Acid Hybridization, Open Reading
Frames, P.H.S., Pattern Recognition, Protein, Protein Structure,
Proteins, Reproducibility of Results, Research Support, Saccharomyces
cerevisiae, Sequence Alignment, Sequence Analysis, Software, Statistical,
Tertiary, U.S. Gov't, 9698352}
}
@article{Pontil1998Properties,
author = {M. Pontil and A. Verri},
title = {Properties of support vector machines.},
journal = {Neural {C}omput},
year = {1998},
volume = {10},
pages = {955-74},
number = {4},
month = {May},
abstract = {Support vector machines ({SVM}s) perform pattern recognition between
two point classes by finding a decision surface determined by certain
points of the training set, termed support vectors ({SV}). {T}his
surface, which in some feature space of possibly infinite dimension
can be regarded as a hyperplane, is obtained from the solution of
a problem of quadratic programming that depends on a regularization
parameter. {I}n this article, we study some mathematical properties
of support vectors and show that the decision surface can be written
as the sum of two orthogonal terms, the first depending on only the
margin vectors (which are {SV}s lying on the margin), the second
proportional to the regularization parameter. {F}or almost all values
of the parameter, this enables us to predict how the decision surface
varies for small parameter changes. {I}n the special but important
case of feature space of finite dimension m, we also show that m
+ 1 {SV}s are usually sufficient to determine the decision surface
fully. {F}or relatively small m, this latter result leads to a consistent
reduction of the {SV} number.},
keywords = {Algorithms, Artificial Intelligence, Automated, Biometry, Computers,
DNA, Databases, Factual, Fungal, Fungal Proteins, GTP-Binding Proteins,
Gene Expression, Genes, Learning, Linear Models, Markov Chains, Mathematics,
Models, Neural Networks (Computer), Neurological, Non-P.H.S., Non-U.S.
Gov't, Nonlinear Dynamics, Nucleic Acid Hybridization, Open Reading
Frames, P.H.S., Pattern Recognition, Protein, Protein Structure,
Proteins, Reproducibility of Results, Research Support, Saccharomyces
cerevisiae, Sequence Alignment, Sequence Analysis, Software, Statistical,
Tertiary, U.S. Gov't, 9573414}
}
@article{Prados2004Mining,
author = {Prados, J. and Kalousis, A. and Sanchez, J.C. and Allard, L. and
Carrette, O. and Hilario, M.},
title = {Mining mass spectra for diagnosis and biomarker discovery of cerebral
accidents.},
journal = {Proteomics},
year = {2004},
volume = {4},
pages = {2320-2332},
number = {8},
abstract = {In this paper we try to identify potential biomarkers for early stroke
diagnosis using surface-enhanced laser desorption/ionization mass
spectrometry coupled with analysis tools from machine learning and
data mining. {D}ata consist of 42 specimen samples, i.e., mass spectra
divided in two big categories, stroke and control specimens. {A}mong
the stroke specimens two further categories exist that correspond
to ischemic and hemorrhagic stroke; in this paper we limit our data
analysis to discriminating between control and stroke specimens.
{W}e performed two suites of experiments. {I}n the first one we simply
applied a number of different machine learning algorithms; in the
second one we have chosen the best performing algorithm as it was
determined from the first phase and coupled it with a number of different
feature selection methods. {T}he reason for this was 2-fold, first
to establish whether feature selection can indeed improve performance,
which in our case it did not seem to confirm, but more importantly
to acquire a small list of potentially interesting biomarkers. {O}f
the different methods explored the most promising one was support
vector machines which gave us high levels of sensitivity and specificity.
{F}inally, by analyzing the models constructed by support vector
machines we produced a small set of 13 features that could be used
as potential biomarkers, and which exhibited good performance both
in terms of sensitivity, specificity and model stability.},
doi = {10.1002/pmic.200400857},
pdf = {../local/Prados2004Mining.pdf},
file = {Prados2004Mining.pdf:local/Prados2004Mining.pdf:PDF},
keywords = {biosvm proteomics},
owner = {jeanphilippevert},
url = {http://dx.doi.org/10.1002/pmic.200400857}
}
@article{Puig2001tandem,
author = {O. Puig and F. Caspary and G. Rigaut and B. Rutz and E. Bouveret
and E. Bragado-Nilsson and M. Wilm and B. Séraphin},
title = {The tandem affinity purification (TAP) method: a general procedure
of protein complex purification.},
journal = {Methods},
year = {2001},
volume = {24},
pages = {218--229},
number = {3},
month = {Jul},
abstract = {Identification of components present in biological complexes requires
their purification to near homogeneity. Methods of purification vary
from protein to protein, making it impossible to design a general
purification strategy valid for all cases. We have developed the
tandem affinity purification (TAP) method as a tool that allows rapid
purification under native conditions of complexes, even when expressed
at their natural level. Prior knowledge of complex composition or
function is not required. The TAP method requires fusion of the TAP
tag, either N- or C-terminally, to the target protein of interest.
Starting from a relatively small number of cells, active macromolecular
complexes can be isolated and used for multiple applications. Variations
of the method to specifically purify complexes containing two given
components or to subtract undesired complexes can easily be implemented.
The TAP method was initially developed in yeast but can be successfully
adapted to various organisms. Its simplicity, high yield, and wide
applicability make the TAP method a very useful procedure for protein
purification and proteome exploration.},
doi = {10.1006/meth.2001.1183},
institution = {European Molecular Biology Laboratory Meyerhofstrasse 1, Heidelberg,
D-69117, Germany.},
keywords = {Bacterial Proteins; Blotting, Western; DNA, Bacterial; Fungal Proteins;
Genetic Vectors; Methods; Mutation; Polymerase Chain Reaction; Proteins;
Proteome; Ribonucleases; Ribonucleoproteins; Saccharomyces cerevisiae;
Saccharomyces cerevisiae Proteins; Staphylococcus aureus},
owner = {phupe},
pii = {S1046-2023(01)91183-1},
pmid = {11403571},
timestamp = {2010.08.31},
url = {http://dx.doi.org/10.1006/meth.2001.1183}
}
@article{Perez-Cruz2005Convergence,
author = {Fernando Pérez-Cruz and Carlos Bousoño-Calzón and Antonio Artés-RodrÃguez},
title = {Convergence of the {IRWLS} {P}rocedure to the {S}upport {V}ector
{M}achine {S}olution.},
journal = {Neural {C}omput},
year = {2005},
volume = {17},
pages = {7-18},
number = {1},
month = {Jan},
abstract = {An iterative reweighted least squares ({IRWLS}) procedure recently
proposed is shown to converge to the support vector machine solution.
{T}he convergence to a stationary point is ensured by modifying the
original {IRWLS} procedure.},
keywords = {80 and over, Aged, Algorithms, Amino Acids, Animals, Area Under Curve,
Automated, Brain Chemistry, Brain Neoplasms, Comparative Study, Computer-Assisted,
Cross-Sectional Studies, Decision Trees, Diagnosis, Diagnostic Imaging,
Diagnostic Techniques, Discriminant Analysis, Evolution, Face, Genetic,
Glaucoma, Humans, Lasers, Least-Squares Analysis, Magnetic Resonance
Imaging, Magnetic Resonance Spectroscopy, Middle Aged, Models, Molecular,
Nerve Fibers, Non-U.S. Gov't, Numerical Analysis, Ophthalmological,
Optic Nerve Diseases, P.H.S., Pattern Recognition, Photic Stimulation,
Protein, ROC Curve, Regression Analysis, Research Support, Retinal
Ganglion Cells, Sensitivity and Specificity, Sequence Analysis, Statistics,
U.S. Gov't, beta-Lactamases, 15779160}
}
@article{Qin2004[Automated,
author = {Dong-mei Qin and Zhan-yi Hu and Yong-heng Zhao},
title = {Automated classification of celestial spectra based on support vector
machines},
journal = {Guang {P}u {X}ue {Y}u {G}uang {P}u {F}en {X}i},
year = {2004},
volume = {24},
pages = {507-11},
number = {4},
month = {Apr},
abstract = {The main objective of an automatic recognition system of celestial
objects via their spectra is to classify celestial spectra and estimate
physical parameters automatically. {T}his paper proposes a new automatic
classification method based on support vector machines to separate
non-active objects from active objects via their spectra. {W}ith
low {SNR} and unknown red-shift value, it is difficult to extract
true spectral lines, and as a result, active objects can not be determined
by finding strong spectral lines and the spectral classification
between non-active and active objects becomes difficult. {T}he proposed
method in this paper combines the principal component analysis with
support vector machines, and can automatically recognize the spectra
of active objects with unknown red-shift values from non-active objects.
{I}t finds its applicability in the automatic processing of voluminous
observed data from large sky surveys in astronomy.},
keywords = {80 and over, Adult, Aged, Algorithms, Amino Acids, Animals, Area Under
Curve, Artifacts, Automated, Birefringence, Brain Chemistry, Brain
Neoplasms, Comparative Study, Computer-Assisted, Cornea, Cross-Sectional
Studies, Decision Trees, Diagnosis, Diagnostic Imaging, Diagnostic
Techniques, Discriminant Analysis, Evolution, Face, Female, Genetic,
Glaucoma, Humans, Intraocular Pressure, Lasers, Least-Squares Analysis,
Magnetic Resonance Imaging, Magnetic Resonance Spectroscopy, Male,
Middle Aged, Models, Molecular, Nerve Fibers, Non-U.S. Gov't, Numerical
Analysis, Ophthalmological, Optic Nerve Diseases, Optical Coherence,
P.H.S., Pattern Recognition, Photic Stimulation, Prospective Studies,
Protein, ROC Curve, Regression Analysis, Research Support, Retinal
Ganglion Cells, Sensitivity and Specificity, Sequence Analysis, Statistics,
Tomography, U.S. Gov't, Visual Fields, beta-Lactamases, 15766170}
}
@article{Qiu2007structural,
author = {Qiu, J. and Hue, J. and Ben-Hur, A. and Vert, J.-P. and Noble, W.
S.},
title = {A structural alignment kernel for protein structures.},
journal = {Bioinformatics},
year = {2007},
volume = {23},
pages = {1090--1098},
number = {9},
month = {May},
abstract = {MOTIVATION: This work aims to develop computational methods to annotate
protein structures in an automated fashion. We employ a support vector
machine (SVM) classifier to map from a given class of structures
to their corresponding structural (SCOP) or functional (Gene Ontology)
annotation. In particular, we build upon recent work describing various
kernels for protein structures, where a kernel is a similarity function
that the classifier uses to compare pairs of structures. RESULTS:
We describe a kernel that is derived in a straightforward fashion
from an existing structural alignment program, MAMMOTH. We find in
our benchmark experiments that this kernel significantly out-performs
a variety of other kernels, including several previously described
kernels. Furthermore, in both benchmarks, classifying structures
using MAMMOTH alone does not work as well as using an SVM with the
MAMMOTH kernel. AVAILABILITY: http://noble.gs.washington.edu/proj/3dkernel},
doi = {10.1093/bioinformatics/btl642},
keywords = {Algorithms; Amino Acid Sequence; Artificial Intelligence; Molecular
Sequence Data; Pattern Recognition, Automated; Proteins; Sequence
Alignment; Sequence Analysis, Protein; Sequence Homology, Amino Acid},
owner = {laurent},
pii = {btl642},
pmid = {17234638},
timestamp = {2007.07.27},
url = {http://dx.doi.org/10.1093/bioinformatics/btl642}
}
@article{Rain2001protein-protein,
author = {Rain, J.-C. and Selig, L. and De Reuse, H. and Battaglia, V. and
Reverdy, C. and Simon, S. and Lenzen, G. and Petel, F. and Wojcik,
J. and Sch{\"a}chter, V. and Chemama, Y. and Labigne, A. and Legrain,
P.},
title = {The protein-protein interaction map of {H}elicobacter pylori},
journal = {Nature},
year = {2001},
volume = {409},
pages = {211--215},
pdf = {../local/rain01.pdf},
file = {rain01.pdf:local/rain01.pdf:PDF},
subject = {bionetprot},
url = {http://www.nature.com/cgi-taf/DynaPage.taf?file=/nature/journal/v409/n6817/full/409211a0_fs.html&content_filetype=pdf}
}
@article{Rarey1996fast,
author = {M. Rarey and B. Kramer and T. Lengauer and G. Klebe},
title = {{A} fast flexible docking method using an incremental construction
algorithm.},
journal = {J. Mol. Biol.},
year = {1996},
volume = {261},
pages = {470--489},
number = {3},
month = {Aug},
abstract = {We present an automatic method for docking organic ligands into protein
binding sites. The method can be used in the design process of specific
protein ligands. It combines an appropriate model of the physico-chemical
properties of the docked molecules with efficient methods for sampling
the conformational space of the ligand. If the ligand is flexible,
it can adopt a large variety of different conformations. Each such
minimum in conformational space presents a potential candidate for
the conformation of the ligand in the complexed state. Our docking
method samples the conformation space of the ligand on the basis
of a discrete model and uses a tree-search technique for placing
the ligand incrementally into the active site. For placing the first
fragment of the ligand into the protein, we use hashing techniques
adapted from computer vision. The incremental construction algorithm
is based on a greedy strategy combined with efficient methods for
overlap detection and for the search of new interactions. We present
results on 19 complexes of which the binding geometry has been crystallographically
determined. All considered ligands are docked in at most three minutes
on a current workstation. The experimentally observed binding mode
of the ligand is reproduced with 0.5 to 1.2 A rms deviation. It is
almost always found among the highest-ranking conformations computed.},
doi = {10.1006/jmbi.1996.0477},
keywords = {Aldehyde Reductase, Algorithms, Amiloride, Aminoimidazole Carboxamide,
Animals, Arabinose, Automation, Binding Sites, Carbonic Anhydrases,
Computational Biology, Computer Simulation, Concanavalin A, Crystallography,
Databases, Drug Design, Drug Evaluation, Enzyme Inhibitors, Factual,
Folic Acid, Folic Acid Antagonists, Fructose-Bisphosphatase, Humans,
Internet, Ligands, Methotrexate, Models, Molecular, Non-U.S. Gov't,
Pancreatic Elastase, Pentamidine, Pliability, Point Mutation, Preclinical,
Protein Binding, Protein Conformation, Proteins, Reproducibility
of Results, Research Support, Ribonucleosides, Software, Tetrahydrofolate
Dehydrogenase, Thermolysin, Time Factors, Trypsin, X-Ray, 8780787},
owner = {mahe},
pii = {S0022-2836(96)90477-5},
pmid = {8780787},
timestamp = {2006.09.05},
url = {http://dx.doi.org/10.1006/jmbi.1996.0477}
}
@article{Rarey1996Placement,
author = {M. Rarey and S. Wefing and T. Lengauer},
title = {Placement of medium-sized molecular fragments into active sites of
proteins.},
journal = {J Comput Aided Mol Des},
year = {1996},
volume = {10},
pages = {41--54},
number = {1},
month = {Feb},
abstract = {We present an algorithm for placing molecular fragments into the active
site of a receptor. A molecular fragment is defined as a connected
part of a molecule containing only complete ring systems. The algorithm
is part of a docking tool, called FLEXX, which is currently under
development at GMD. The overall goal is to provide means of automatically
computing low-energy conformations of the ligand within the active
site, with an accuracy approaching the limitations of experimental
methods for resolving molecular structures and within a run time
that allows for docking large sets of ligands. The methods by which
we plan to achieve this goal are the explicit exploitation of molecular
flexibility of the ligand and the incorporation of physicochemical
properties of the molecules. The algorithm for fragment placement,
which is the topic of this paper, is based on pattern recognition
techniques and is able to predict a small set of possible positions
of a molecular fragment with low flexibility within seconds on a
workstation. In most cases, a placement with rms deviation below
1.0 A with respect to the X-ray structure is found among the 10 highest
ranking solutions, assuming that the receptor is given in the bound
conformation.},
institution = {German National Research Center for Information Technology (GMD),
Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin,
Germany.},
keywords = {Algorithms; Binding Sites; Databases, Factual; Ligands; Models, Chemical;
Peptide Fragments, chemistry; Proteins, chemistry; Software},
owner = {bricehoffmann},
pmid = {8786414},
timestamp = {2009.02.13}
}
@article{Rea2000Regulation,
author = {S. Rea and F. Eisenhaber and D. O'Carroll and B. D. Strahl and Z.
W. Sun and M. Schmid and S. Opravil and K. Mechtler and C. P. Ponting
and C. D. Allis and T. Jenuwein},
title = {Regulation of chromatin structure by site-specific histone H3 methyltransferases.},
journal = {Nature},
year = {2000},
volume = {406},
pages = {593--599},
number = {6796},
month = {Aug},
abstract = {The organization of chromatin into higher-order structures influences
chromosome function and epigenetic gene regulation. Higher-order
chromatin has been proposed to be nucleated by the covalent modification
of histone tails and the subsequent establishment of chromosomal
subdomains by non-histone modifier factors. Here we show that human
SUV39H1 and murine Suv39h1--mammalian homologues of Drosophila Su(var)3-9
and of Schizosaccharomyces pombe clr4--encode histone H3-specific
methyltransferases that selectively methylate lysine 9 of the amino
terminus of histone H3 in vitro. We mapped the catalytic motif to
the evolutionarily conserved SET domain, which requires adjacent
cysteine-rich regions to confer histone methyltransferase activity.
Methylation of lysine 9 interferes with phosphorylation of serine
10, but is also influenced by pre-existing modifications in the amino
terminus of H3. In vivo, deregulated SUV39H1 or disrupted Suv39h
activity modulate H3 serine 10 phosphorylation in native chromatin
and induce aberrant mitotic divisions. Our data reveal a functional
interdependence of site-specific H3 tail modifications and suggest
a dynamic mechanism for the regulation of higher-order chromatin.},
doi = {10.1038/35020506},
institution = {Research Institute of Molecular Pathology, The Vienna Biocenter,
Austria.},
keywords = {Amino Acid Sequence; Animals; Catalytic Domain; Chromatin, chemistry/metabolism;
Drosophila; Hela Cells; Histone-Lysine N-Methyltransferase; Humans;
Lysine, metabolism; Methylation; Methyltransferases, genetics/metabolism;
Mice; Molecular Sequence Data; Phosphorylation; Protein Conformation;
Protein Methyltransferases; Protein Structure, Tertiary; Recombinant
Proteins, metabolism; Repressor Proteins, genetics/metabolism; Sequence
Homology, Amino Acid; Serine, metabolism; Substrate Specificity},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pmid = {10949293},
timestamp = {2010.11.23},
url = {http://dx.doi.org/10.1038/35020506}
}
@article{Rhodes2007Oncomine,
author = {Rhodes, Daniel R. and Kalyana-Sundaram, Shanker and Mahavisno, Vasudeva
and Varambally, Radhika and Yu, Jianjun and Briggs, Benjamin B. and
Barrette, Terrence R. and Anstet, Matthew J. and Kincead-Beal, Colleen
and Kulkarni, Prakash and Varambally, Sooryanaryana and Ghosh, Debashis
and Chinnaiyan, Arul M.},
title = {Oncomine 3.0: genes, pathways, and networks in a collection of 18,000
cancer gene expression profiles.},
journal = {Neoplasia},
year = {2007},
volume = {9},
pages = {166--180},
number = {2},
month = {Feb},
abstract = {DNA microarrays have been widely applied to cancer transcriptome analysis;
however, the majority of such data are not easily accessible or comparable.
Furthermore, several important analytic approaches have been applied
to microarray analysis; however, their application is often limited.
To overcome these limitations, we have developed Oncomine, a bioinformatics
initiative aimed at collecting, standardizing, analyzing, and delivering
cancer transcriptome data to the biomedical research community. Our
analysis has identified the genes, pathways, and networks deregulated
across 18,000 cancer gene expression microarrays, spanning the majority
of cancer types and subtypes. Here, we provide an update on the initiative,
describe the database and analysis modules, and highlight several
notable observations. Results from this comprehensive analysis are
available at http://www.oncomine.org.},
institution = {Department of Pathology, University of Michigan Medical School, Ann
Arbor, MI 48109-0940, USA.},
keywords = {Antineoplastic Agents, pharmacology; Automatic Data Processing; Chromosome
Mapping; Chromosomes, Human, genetics; Computational Biology, organization
/&/ administration; Data Collection; Data Display; Data Interpretation,
Statistical; Databases, Genetic; Drug Design; Gene Expression Profiling,
statistics /&/ numerical data; Gene Expression Regulation, Neoplastic;
Genes, Neoplasm; Humans; Internet; Models, Biological; Neoplasm Proteins,
biosynthesis/chemistry/genetics; Neoplasms, classification/genetics/metabolism;
Oligonucleotide Array Sequence Analysis; Subtraction Technique; Transcription,
Genetic},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pmid = {17356713},
timestamp = {2012.03.10}
}
@article{Rice2005Reconstructing,
author = {Rice, J.J. and Tu, Y. and Stolovitzky, G.},
title = {Reconstructing biological networks using conditional correlation
analysis.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {765--773},
number = {6},
month = {Mar},
abstract = {MOTIVATION: One of the present challenges in biological research is
the organization of the data originating from high-throughput technologies.
One way in which this information can be organized is in the form
of networks of influences, physical or statistical, between cellular
components. We propose an experimental method for probing biological
networks, analyzing the resulting data and reconstructing the network
architecture. METHODS: We use networks of known topology consisting
of nodes (genes), directed edges (gene-gene interactions) and a dynamics
for the genes' mRNA concentrations in terms of the gene-gene interactions.
We proposed a network reconstruction algorithm based on the conditional
correlation of the mRNA equilibrium concentration between two genes
given that one of them was knocked down. Using simulated gene expression
data on networks of known connectivity, we investigated how the reconstruction
error is affected by noise, network topology, size, sparseness and
dynamic parameters. RESULTS: Errors arise from correlation between
nodes connected through intermediate nodes (false positives) and
when the correlation between two directly connected nodes is obscured
by noise, non-linearity or multiple inputs to the target node (false
negatives). Two critical components of the method are as follows:
(1) the choice of an optimal correlation threshold for predicting
connections and (2) the reduction of errors arising from indirect
connections (for which a novel algorithm is proposed). With these
improvements, we can reconstruct networks with the topology of the
transcriptional regulatory network in Escherichia coli with a reasonably
low error rate.},
doi = {10.1093/bioinformatics/bti064},
institution = {Computational Biology Center, IBM T.J. Watson Research Center, PO
Box 218, Yorktown Heights, NY 10598, USA.},
keywords = {Algorithms; Computer Simulation; Gene Expression Profiling; Gene Expression
Regulation; Models, Biological; Models, Statistical; Oligonucleotide
Array Sequence Analysis; Protein Interaction Mapping; Signal Transduction;
Statistics as Topic; Transcription Factors},
owner = {fantine},
pii = {bti064},
pmid = {15486043},
timestamp = {2010.10.21},
url = {http://dx.doi.org/10.1093/bioinformatics/bti064}
}
@article{Rigaut1999generic,
author = {G. Rigaut and A. Shevchenko and B. Rutz and M. Wilm and M. Mann and
B. Séraphin},
title = {A generic protein purification method for protein complex characterization
and proteome exploration.},
journal = {Nat Biotechnol},
year = {1999},
volume = {17},
pages = {1030--1032},
number = {10},
month = {Oct},
abstract = {We have developed a generic procedure to purify proteins expressed
at their natural level under native conditions using a novel tandem
affinity purification (TAP) tag. The TAP tag allows the rapid purification
of complexes from a relatively small number of cells without prior
knowledge of the complex composition, activity, or function. Combined
with mass spectrometry, the TAP strategy allows for the identification
of proteins interacting with a given target protein. The TAP method
has been tested in yeast but should be applicable to other cells
or organisms.},
doi = {10.1038/13732},
institution = {European Molecular Biology Laboratory, Meyerhofstrasse 1, D-69117
Heidelberg, Germany.},
keywords = {Affinity Labels; Amino Acid Sequence; Electrophoresis, Polyacrylamide
Gel; Methods; Molecular Sequence Data; Proteins; Proteome},
owner = {phupe},
pmid = {10504710},
timestamp = {2010.09.01},
url = {http://dx.doi.org/10.1038/13732}
}
@article{Risau-Gusman2000Generalization,
author = {Risau-Gusman and Gordon},
title = {Generalization properties of finite-size polynomial support vector
machines},
journal = {Phys {R}ev {E} {S}tat {P}hys {P}lasmas {F}luids {R}elat {I}nterdiscip
{T}opics},
year = {2000},
volume = {62},
pages = {7092-9},
number = {5 Pt B},
month = {Nov},
abstract = {The learning properties of finite-size polynomial support vector machines
are analyzed in the case of realizable classification tasks. {T}he
normalization of the high-order features acts as a squeezing factor,
introducing a strong anisotropy in the patterns distribution in feature
space. {A}s a function of the training set size, the corresponding
generalization error presents a crossover, more or less abrupt depending
on the distribution's anisotropy and on the task to be learned, between
a fast-decreasing and a slowly decreasing regime. {T}his behavior
corresponds to the stepwise decrease found by {D}ietrich et al. [{P}hys.
{R}ev. {L}ett. 82, 2975 (1999)] in the thermodynamic limit. {T}he
theoretical results are in excellent agreement with the numerical
simulations.},
keywords = {Acute, Acute Disease, Adenocarcinoma, Algorithms, Amino Acid Sequence,
Animals, Artificial Intelligence, Automated, B-Lymphocytes, Bacterial
Proteins, Base Pair Mismatch, Base Sequence, Bayes Theorem, Binding
Sites, Biological, Bone Marrow Cells, Brachyura, Cell Compartmentation,
Chemistry, Child, Chromosome Aberrations, Classification, Codon,
Colonic Neoplasms, Comparative Study, Computational Biology, Computer
Simulation, Computer-Assisted, DNA, Data Interpretation, Databases,
Decision Trees, Diabetes Mellitus, Diagnosis, Discriminant Analysis,
Discrimination Learning, Electric Conductivity, Electrophysiology,
Escherichia coli Proteins, Factual, Feedback, Female, Fungal, Gastric
Emptying, Gene Expression Profiling, Gene Expression Regulation,
Genes, Genetic, Genetic Markers, Genetic Predisposition to Disease,
Genomics, Hemolysins, Humans, Indians, Initiator, Ion Channels, Kinetics,
Leukemia, Likelihood Functions, Lipid Bilayers, Logistic Models,
Lymphocytic, Male, Markov Chains, Melanoma, Models, Molecular, Myeloid,
Neoplasm, Neoplasms, Neoplastic, Neural Networks (Computer), Neurological,
Nevus, Non-P.H.S., Non-U.S. Gov't, Nonlinear Dynamics, Normal Distribution,
North American, Nucleic Acid Conformation, Oligonucleotide Array
Sequence Analysis, Organ Specificity, Organelles, Ovarian Neoplasms,
Ovary, P.H.S., Pattern Recognition, Physical, Pigmented, Predictive
Value of Tests, Promoter Regions (Genetics), Protein Biosynthesis,
Protein Folding, Protein Structure, Proteins, Proteome, RNA, Reproducibility
of Results, Research Support, Saccharomyces cerevisiae, Secondary,
Sensitivity and Specificity, Sequence Alignment, Sequence Analysis,
Sex Characteristics, Skin Diseases, Skin Neoplasms, Skin Pigmentation,
Software, Sound Spectrography, Statistical, Stomach Diseases, T-Lymphocytes,
Thermodynamics, Transcription, Transcription Factors, Tumor Markers,
Type 2, U.S. Gov't, Vertebrates, 0011102066}
}
@article{Roschke2003Karyotypic,
author = {Anna V Roschke and Giovanni Tonon and Kristen S Gehlhaus and Nicolas
McTyre and Kimberly J Bussey and Samir Lababidi and Dominic A Scudiero
and John N Weinstein and Ilan R Kirsch},
title = {Karyotypic complexity of the NCI-60 drug-screening panel.},
journal = {Cancer Res},
year = {2003},
volume = {63},
pages = {8634--8647},
number = {24},
month = {Dec},
abstract = {We used spectral karyotyping to provide a detailed analysis of karyotypic
aberrations in the diverse group of cancer cell lines established
by the National Cancer Institute for the purpose of anticancer drug
discovery. Along with the karyotypic description of these cell lines
we defined and studied karyotypic complexity and heterogeneity (metaphase-to-metaphase
variations) based on three separate components of genomic anatomy:
(a) ploidy; (b) numerical changes; and (c) structural rearrangements.
A wide variation in these parameters was evident in these cell lines,
and different association patterns between them were revealed. Analysis
of the breakpoints and other specific features of chromosomal changes
across the entire set of cell lines or within particular lineages
pointed to a striking lability of centromeric regions that distinguishes
the epithelial tumor cell lines. We have also found that balanced
translocations are as frequent in absolute number within the cell
lines derived from solid as from hematopoietic tumors. Important
similarities were noticed between karyotypic changes in cancer cell
lines and that seen in primary tumors. This dataset offers insights
into the causes and consequences of the destabilizing events and
chromosomal instability that may occur during tumor development and
progression. It also provides a foundation for investigating associations
between structural genome anatomy and cancer molecular markers and
targets, gene expression, gene dosage, and resistance or sensitivity
to tens of thousands of molecular compounds.},
institution = {Genetics Branch, Center for Cancer Research, National Cancer Institute,
Bethesda, Maryland 20889-5105, USA.},
keywords = {Cell Line, Tumor; Chromosome Aberrations; DNA Repair, genetics; Drug
Screening Assays, Antitumor; Humans; Neoplasms, genetics/pathology;
Ploidies; Retinoblastoma Protein, genetics; Spectral Karyotyping;
Translocation, Genetic; Tumor Suppressor Protein p53, genetics},
language = {eng},
medline-pst = {ppublish},
owner = {philippe},
pmid = {14695175},
timestamp = {2010.08.05}
}
@article{Ross2004Multiplexed,
author = {Philip L Ross and Yulin N Huang and Jason N Marchese and Brian Williamson
and Kenneth Parker and Stephen Hattan and Nikita Khainovski and Sasi
Pillai and Subhakar Dey and Scott Daniels and Subhasish Purkayastha
and Peter Juhasz and Stephen Martin and Michael Bartlet-Jones and
Feng He and Allan Jacobson and Darryl J Pappin},
title = {Multiplexed protein quantitation in Saccharomyces cerevisiae using
amine-reactive isobaric tagging reagents.},
journal = {Mol Cell Proteomics},
year = {2004},
volume = {3},
pages = {1154--1169},
number = {12},
month = {Dec},
abstract = {We describe here a multiplexed protein quantitation strategy that
provides relative and absolute measurements of proteins in complex
mixtures. At the core of this methodology is a multiplexed set of
isobaric reagents that yield amine-derivatized peptides. The derivatized
peptides are indistinguishable in MS, but exhibit intense low-mass
MS/MS signature ions that support quantitation. In this study, we
have examined the global protein expression of a wild-type yeast
strain and the isogenic upf1Delta and xrn1Delta mutant strains that
are defective in the nonsense-mediated mRNA decay and the general
5' to 3' decay pathways, respectively. We also demonstrate the use
of 4-fold multiplexing to enable relative protein measurements simultaneously
with determination of absolute levels of a target protein using synthetic
isobaric peptide standards. We find that inactivation of Upf1p and
Xrn1p causes common as well as unique effects on protein expression.},
doi = {10.1074/mcp.M400129-MCP200},
institution = {Applied Biosystems, Framingham, MA 01701, USA.},
keywords = {Cations; Chromatography, Ion Exchange; Chromatography, Liquid; Down-Regulation;
Exoribonucleases; Fungal Proteins; Indicators and Reagents; Ions;
Mass Spectrometry; Models, Chemical; Peptides; Phenotype; Proteomics;
RNA Helicases; RNA, Messenger; Saccharomyces cerevisiae; Saccharomyces
cerevisiae Proteins; Succinimides},
owner = {phupe},
pii = {M400129-MCP200},
pmid = {15385600},
timestamp = {2010.08.19},
url = {http://dx.doi.org/10.1074/mcp.M400129-MCP200}
}
@article{Rual2005Towards,
author = {Jean-François Rual and Kavitha Venkatesan and Tong Hao and Tomoko
Hirozane-Kishikawa and Amélie Dricot and Ning Li and Gabriel F Berriz
and Francis D Gibbons and Matija Dreze and Nono Ayivi-Guedehoussou
and Niels Klitgord and Christophe Simon and Mike Boxem and Stuart
Milstein and Jennifer Rosenberg and Debra S Goldberg and Lan V Zhang
and Sharyl L Wong and Giovanni Franklin and Siming Li and Joanna
S Albala and Janghoo Lim and Carlene Fraughton and Estelle Llamosas
and Sebiha Cevik and Camille Bex and Philippe Lamesch and Robert
S Sikorski and Jean Vandenhaute and Huda Y Zoghbi and Alex Smolyar
and Stephanie Bosak and Reynaldo Sequerra and Lynn Doucette-Stamm
and Michael E Cusick and David E Hill and Frederick P Roth and Marc
Vidal},
title = {Towards a proteome-scale map of the human protein-protein interaction
network.},
journal = {Nature},
year = {2005},
volume = {437},
pages = {1173--1178},
number = {7062},
month = {Oct},
abstract = {Systematic mapping of protein-protein interactions, or 'interactome'
mapping, was initiated in model organisms, starting with defined
biological processes and then expanding to the scale of the proteome.
Although far from complete, such maps have revealed global topological
and dynamic features of interactome networks that relate to known
biological properties, suggesting that a human interactome map will
provide insight into development and disease mechanisms at a systems
level. Here we describe an initial version of a proteome-scale map
of human binary protein-protein interactions. Using a stringent,
high-throughput yeast two-hybrid system, we tested pairwise interactions
among the products of approximately 8,100 currently available Gateway-cloned
open reading frames and detected approximately 2,800 interactions.
This data set, called CCSB-HI1, has a verification rate of approximately
78\% as revealed by an independent co-affinity purification assay,
and correlates significantly with other biological attributes. The
CCSB-HI1 data set increases by approximately 70\% the set of available
binary interactions within the tested space and reveals more than
300 new connections to over 100 disease-associated proteins. This
work represents an important step towards a systematic and comprehensive
human interactome project.},
doi = {10.1038/nature04209},
institution = {Center for Cancer Systems Biology and Department of Cancer Biology,
Dana-Farber Cancer Institute, Harvard Medical School, 44 Binney Street,
Boston, Massachusetts 02115, USA.},
keywords = {Cloning, Molecular; Humans; Open Reading Frames; Protein Binding;
Proteome; RNA; Saccharomyces cerevisiae; Two-Hybrid System Techniques},
owner = {phupe},
pii = {nature04209},
pmid = {16189514},
timestamp = {2010.09.01},
url = {http://dx.doi.org/10.1038/nature04209}
}
@article{Russell1992Multiple,
author = {R. B. Russell and G. J. Barton},
title = {Multiple protein sequence alignment from tertiary structure comparison:
assignment of global and residue confidence levels.},
journal = {Proteins},
year = {1992},
volume = {14},
pages = {309--323},
number = {2},
month = {Oct},
abstract = {An algorithm is presented for the accurate and rapid generation of
multiple protein sequence alignments from tertiary structure comparisons.
A preliminary multiple sequence alignment is performed using sequence
information, which then determines an initial superposition of the
structures. A structure comparison algorithm is applied to all pairs
of proteins in the superimposed set and a similarity tree calculated.
Multiple sequence alignments are then generated by following the
tree from the branches to the root. At each branchpoint of the tree,
a structure-based sequence alignment and coordinate transformations
are output, with the multiple alignment of all structures output
at the root. The algorithm encoded in STAMP (STructural Alignment
of Multiple Proteins) is shown to give alignments in good agreement
with published structural accounts within the dehydrogenase fold
domains, globins, and serine proteinases. In order to reduce the
need for visual verification, two similarity indices are introduced
to determine the quality of each generated structural alignment.
Sc quantifies the global structural similarity between pairs or groups
of proteins, whereas Pij' provides a normalized measure of the confidence
in the alignment of each residue. STAMP alignments have the quality
of each alignment characterized by Sc and Pij' values and thus provide
a reproducible resource for studies of residue conservation within
structural motifs.},
doi = {10.1002/prot.340140216},
keywords = {Algorithms; Amino Acid Sequence; Animals; Confidence Intervals; Globins;
Humans; Molecular Sequence Data; Protein Structure, Tertiary; Sequence
Alignment; Sequence Homology, Amino Acid; Serine Endopeptidases;
Software},
owner = {laurent},
pmid = {1409577},
timestamp = {2008.01.15},
url = {http://dx.doi.org/10.1002/prot.340140216}
}
@article{Salim2003Combination,
author = {N. Salim and J. Holliday and P. Willett},
title = {{C}ombination of fingerprint-based similarity coefficients using
data fusion.},
journal = {J Chem Inf Comput Sci},
year = {2003},
volume = {43},
pages = {435--442},
number = {2},
abstract = {Many different types of similarity coefficients have been described
in the literature. Since different coefficients take into account
different characteristics when assessing the degree of similarity
between molecules, it is reasonable to combine them to further optimize
the measures of similarity between molecules. This paper describes
experiments in which data fusion is used to combine several binary
similarity coefficients to get an overall estimate of similarity
for searching databases of bioactive molecules. The results show
that search performances can be improved by combining coefficients
with little extra computational cost. However, there is no single
combination which gives a consistently high performance for all search
types.},
doi = {10.1021/ci025596j},
keywords = {80 and over, Acid-Base Imbalance, Acute, Acute Disease, Adolescent,
Adult, African Americans, Aged, Anemia, Animals, Anti-HIV Agents,
Anti-Infective Agents, Antibiotics, Antibodies, Antineoplastic, Antineoplastic
Agents, Antineoplastic Combined Chemotherapy Protocols, Antitubercular
Agents, Aorta, Asparaginase, Autoimmune, B-Cell, Bangladesh, Bicarbonates,
Biological Markers, Blood Glucose, California, Camptothecin, Cellulitis,
Chorionic Gonadotropin, Chronic Disease, Ciprofloxacin, Clinical
Protocols, Colorectal Neoplasms, Combination, Comparative Study,
Daunorubicin, Decision Trees, Dexamethasone, Diabetes Mellitus, Dideoxynucleosides,
Directly Observed Therapy, Disease Transmission, Drug Administration
Schedule, Drug Resistance, Drug Therapy, English Abstract, Female,
Fluorouracil, Follow-Up Studies, Glucose Tolerance Test, Glucosephosphate
Dehydrogenase, Glyburide, HIV Infections, HIV-1, Health Planning,
Health Resources, Helminth, Hemolysis, Hemolytic, Hormonal, Hospital
Mortality, Human, Humans, Hypoglycemic Agents, Immunoglobulin M,
In Vitro, Incidence, Indinavir, Insulin, Intensive Care Units, Interstitial,
Lactates, Leucovorin, Leukemia, Male, Maternal Age, Middle Aged,
Motor Activity, Multidrug-Resistant, Mutation, Nephritis, Non-U.S.
Gov't, Organoplatinum Compounds, Pennsylvania, Phytotherapy, Plant
Extracts, Plant Leaves, Population Dynamics, Potassium Channels,
Prednisone, Pregnancy, Pregnancy Outcome, Prenatal, Prenatal Care,
Progesterone, Prognosis, Prospective Studies, Pulmonary, Rabbits,
Randomized Controlled Trials, Rats, Research Support, Retrospective
Studies, Risk Assessment, Scalp Dermatoses, Schistosomiasis japonica,
Severity of Illness Index, Spondylarthropathies, Streptozocin, Survival
Rate, Trauma Centers, Trauma Severity Indices, Tubal, Tuberculosis,
Type 2, Ultrasonography, Vertical, Vincristine, Viral, Viral Load,
Wistar, Wounds and Injuries, Ziziphus, beta Subunit, 12653506},
owner = {mahe},
pmid = {12653506},
timestamp = {2006.09.01},
url = {http://dx.doi.org/10.1021/ci025596j}
}
@article{Salomon2006Predicting,
author = {Salomon, J. and Flower, D. R.},
title = {{P}redicting {C}lass {II} {MHC}-{P}eptide binding: a kernel based
approach using similarity scores.},
journal = {BMC Bioinformatics},
year = {2006},
volume = {7},
pages = {501},
abstract = {BACKGROUND: Modelling the interaction between potentially antigenic
peptides and Major Histocompatibility Complex (MHC) molecules is
a key step in identifying potential T-cell epitopes. For Class II
MHC alleles, the binding groove is open at both ends, causing ambiguity
in the positional alignment between the groove and peptide, as well
as creating uncertainty as to what parts of the peptide interact
with the MHC. Moreover, the antigenic peptides have variable lengths,
making naive modelling methods difficult to apply. This paper introduces
a kernel method that can handle variable length peptides effectively
by quantifying similarities between peptide sequences and integrating
these into the kernel. RESULTS: The kernel approach presented here
shows increased prediction accuracy with a significantly higher number
of true positives and negatives on multiple MHC class II alleles,
when testing data sets from MHCPEP 1, MCHBN 2, and MHCBench 3. Evaluation
by cross validation, when segregating binders and non-binders, produced
an average of 0.824 AROC for the MHCBench data sets (up from 0.756),
and an average of 0.96 AROC for multiple alleles of the MHCPEP database.
CONCLUSION: The method improves performance over existing state-of-the-art
methods of MHC class II peptide binding predictions by using a custom,
knowledge-based representation of peptides. Similarity scores, in
contrast to a fixed-length, pocket-specific representation of amino
acids, provide a flexible and powerful way of modelling MHC binding,
and can easily be applied to other dynamic sequence problems.},
doi = {10.1186/1471-2105-7-501},
keywords = {Amino Acid, Binding Sites, Computational Biology, Databases, Epitope
Mapping, Genetic, HLA-A Antigens, HLA-DR Antigens, Histocompatibility
Antigens Class II, Humans, Peptides, Protein, Protein Binding, Protein
Conformation, ROC Curve, Reproducibility of Results, Sequence Alignment,
Sequence Analysis, Sequence Homology, 17105666},
pii = {1471-2105-7-501},
pmid = {17105666},
timestamp = {2007.01.25},
url = {http://dx.doi.org/10.1186/1471-2105-7-501}
}
@article{Sassi2005automated,
author = {Alexander P Sassi and Frank Andel and Hans-Marcus L Bitter and Michael
P S Brown and Robert G Chapman and Jeraldine Espiritu and Alfred
C Greenquist and Isabelle Guyon and Mariana Horchi-Alegre and Kathy
L Stults and Ann Wainright and Jonathan C Heller and John T Stults},
title = {An automated, sheathless capillary electrophoresis-mass spectrometry
platform for discovery of biomarkers in human serum.},
journal = {Electrophoresis},
year = {2005},
volume = {26},
pages = {1500-12},
number = {7-8},
month = {Apr},
abstract = {A capillary electrophoresis-mass spectrometry ({CE}-{MS}) method has
been developed to perform routine, automated analysis of low-molecular-weight
peptides in human serum. {T}he method incorporates transient isotachophoresis
for in-line preconcentration and a sheathless electrospray interface.
{T}o evaluate the performance of the method and demonstrate the utility
of the approach, an experiment was designed in which peptides were
added to sera from individuals at each of two different concentrations,
artificially creating two groups of samples. {T}he {CE}-{MS} data
from the serum samples were divided into separate training and test
sets. {A} pattern-recognition/feature-selection algorithm based on
support vector machines was used to select the mass-to-charge (m/z)
values from the training set data that distinguished the two groups
of samples from each other. {T}he added peptides were identified
correctly as the distinguishing features, and pattern recognition
based on these peptides was used to assign each sample in the independent
test set to its respective group. {A} twofold difference in peptide
concentration could be detected with statistical significance (p-value
< 0.0001). {T}he accuracy of the assignment was 95\%, demonstrating
the utility of this technique for the discovery of patterns of biomarkers
in serum.},
doi = {10.1002/elps.200410127},
pdf = {../local/Sassi2005automated.pdf},
file = {Sassi2005automated.pdf:local/Sassi2005automated.pdf:PDF},
keywords = {80 and over, Adult, Aged, Algorithms, Amino Acids, Animals, Area Under
Curve, Artifacts, Automated, Birefringence, Brain Chemistry, Brain
Neoplasms, Comparative Study, Computer-Assisted, Cornea, Cross-Sectional
Studies, Decision Trees, Diagnosis, Diagnostic Imaging, Diagnostic
Techniques, Discriminant Analysis, Evolution, Face, Female, Genetic,
Glaucoma, Humans, Intraocular Pressure, Lasers, Least-Squares Analysis,
Magnetic Resonance Imaging, Magnetic Resonance Spectroscopy, Male,
Middle Aged, Models, Molecular, Nerve Fibers, Non-U.S. Gov't, Numerical
Analysis, Ophthalmological, Optic Nerve Diseases, Optical Coherence,
P.H.S., Pattern Recognition, Photic Stimulation, Prospective Studies,
Protein, ROC Curve, Regression Analysis, Research Support, Retinal
Ganglion Cells, Sensitivity and Specificity, Sequence Analysis, Statistics,
Tomography, U.S. Gov't, Visual Fields, beta-Lactamases, 15765480},
url = {http://dx.doi.org/10.1002/elps.200410127}
}
@article{Schalon2008Simple,
author = {C. Schalon and J-S. Surgand and E. Kellenberger and D. Rognan},
title = {A simple and fuzzy method to align and compare druggable ligand-binding
sites.},
journal = {Proteins},
year = {2008},
volume = {71},
pages = {1755--1778},
number = {4},
month = {Jun},
abstract = {A novel method to measure distances between druggable protein cavities
is presented. Starting from user-defined ligand binding sites, eight
topological and physicochemical properties are projected from cavity-lining
protein residues to an 80 triangle-discretised sphere placed at the
centre of the binding site, thus defining a cavity fingerprint. Representing
binding site properties onto a discretised sphere presents many advantages:
(i) a normalised distance between binding sites of different sizes
may be easily derived by summing up the normalised differences between
the 8 computed descriptors; (ii) a structural alignment of two proteins
is simply done by systematically rotating/translating one mobile
sphere around one immobile reference; (iii) a certain degree of fuzziness
in the comparison is reached by projecting global amino acid properties
(e.g., charge, size, functional groups count, distance to the site
centre) independently of local rotameric/tautomeric states of cavity-lining
residues. The method was implemented in a new program (SiteAlign)
and tested in a number of various scenarios: measuring the distance
between 376 related active site pairs, computing the cross-similarity
of members of a protein family, predicting the targets of ligands
with various promiscuity levels. The proposed method is robust enough
to detect local similarity among active sites of different sizes,
to discriminate between protein subfamilies and to recover the known
targets of promiscuous ligands by virtual screening.},
doi = {10.1002/prot.21858},
institution = {Bioinformatics of the Drug, Institut Gilbert Laustriat, CNRS UMR
7175-LC1, 74 route du Rhin, F-67400 Illkirch.},
keywords = {Algorithms; Amino Acid Sequence; Binding Sites, drug effects; Drug
Design; Hydrogen Bonding; Ligands; Protein Binding; Sequence Alignment;
Structure-Activity Relationship},
owner = {bricehoffmann},
pmid = {18175308},
timestamp = {2009.02.13},
url = {http://dx.doi.org/10.1002/prot.21858}
}
@article{Schmitt2002New,
author = {Stefan Schmitt and Daniel Kuhn and Gerhard Klebe},
title = {A new method to detect related function among proteins independent
of sequence and fold homology.},
journal = {J. Mol. Biol.},
year = {2002},
volume = {323},
pages = {387--406},
number = {2},
month = {Oct},
abstract = {A new method has been developed to detect functional relationships
among proteins independent of a given sequence or fold homology.
It is based on the idea that protein function is intimately related
to the recognition and subsequent response to the binding of a substrate
or an endogenous ligand in a well-characterized binding pocket. Thus,
recognition of similar ligands, supposedly linked to similar function,
requires conserved recognition features exposed in terms of common
physicochemical interaction properties via the functional groups
of the residues flanking a particular binding cavity. Following a
technique commonly used in the comparison of small molecule ligands,
generic pseudocenters coding for possible interaction properties
were assigned for a large sample set of cavities extracted from the
entire PDB and stored in the database Cavbase. Using a particular
query cavity a series of related cavities of decreasing similarity
is detected based on a clique detection algorithm. The detected similarity
is ranked according to property-based surface patches shared in common
by the different clique solutions. The approach either retrieves
protein cavities accommodating the same (e.g. co-factors) or closely
related ligands or it extracts proteins exhibiting similar function
in terms of a related catalytic mechanism. Finally the new method
has strong potential to suggest alternative molecular skeletons in
de novo design. The retrieval of molecular building blocks accommodated
in a particular sub-pocket that shares similarity with the pocket
in a protein studied by drug design can inspire the discovery of
novel ligands.},
institution = {Inst. of Pharmaceutical Chemistry, Univ. of Marburg, Marbacher Weg
6, D-35032, Marburg, Germany.},
keywords = {Algorithms; Binding Sites; Databases, Protein; Models, Molecular;
Molecular Structure; Protein Binding; Protein Folding; Protein Structure,
Tertiary; Proteins, chemistry/metabolism; Reproducibility of Results},
owner = {bricehoffmann},
pii = {S0022283602008112},
pmid = {12381328},
timestamp = {2009.02.13}
}
@article{Schneider1998Artificial,
author = {G. Schneider and P. Wrede},
title = {{A}rtificial neural networks for computer-based molecular design.},
journal = {Prog Biophys Mol Biol},
year = {1998},
volume = {70},
pages = {175--222},
number = {3},
abstract = {The theory of artificial neural networks is briefly reviewed focusing
on supervised and unsupervised techniques which have great impact
on current chemical applications. An introduction to molecular descriptors
and representation schemes is given. In addition, worked examples
of recent advances in this field are highlighted and pioneering publications
are discussed. Applications of several types of artificial neural
networks to compound classification, modelling of structure-activity
relationships, biological target identification, and feature extraction
from biopolymers are presented and compared to other techniques.
Advantages and limitations of neural networks for computer-aided
molecular design and sequence analysis are discussed.},
keywords = {Algorithms, Amino Acid Sequence, Amino Acids, Animals, Artificial
Intelligence, Automated, Bacterial, Bacterial Proteins, Bicuculline,
Binding Sites, Biological, Biological Availability, Blood Proteins,
Blood-Brain Barrier, Cation Transport Proteins, Cats, Cell Membrane
Permeability, Chemical, Chemistry, Cluster Analysis, Combinatorial
Chemistry Techniques, Comparative Study, Computational Biology, Computer
Simulation, Computer Systems, Computer-Aided Design, Computer-Assisted,
Computing Methodologies, DNA-Binding Proteins, Databases, Dogs, Drug
Design, Electric Stimulation, Electromyography, Enzyme Inhibitors,
Ether-A-Go-Go Potassium Channels, Excitatory Amino Acid Antagonists,
Factual, False Positive Reactions, Forecasting, Forelimb, GABA Antagonists,
Gene Expression Profiling, Genome, Glutamic Acid, Humans, Hydrogen
Bonding, Image Enhancement, Image Interpretation, Image Processing,
Information Storage and Retrieval, Iontophoresis, Kynurenic Acid,
Least-Squares Analysis, Linear Models, Liver, Markov Chains, Metabolic
Clearance Rate, Metalloendopeptidases, Microelectrodes, Models, Molecular,
Molecular Conformation, Molecular Sequence Data, Molecular Structure,
Motor Cortex, Movement, Multivariate Analysis, Nerve Net, Neural
Networks (Computer), Neuropeptides, Non-U.S. Gov't, Nonlinear Dynamics,
Pattern Recognition, Pharmaceutical, Pharmaceutical Preparations,
Pharmacokinetics, Phylogeny, Potassium Channels, Predictive Value
of Tests, Protein Interaction Mapping, Protein Sorting Signals, Protein
Structure, Proteins, Rats, Reproducibility of Results, Research Support,
Sensitivity and Specificity, Sequence Alignment, Sequence Analysis,
Shoulder, Signal Processing, Software, Statistical, Stereotaxic Techniques,
Structure-Activity Relationship, Terminology, Tertiary, Trans-Activators,
Voltage-Gated, Zinc, 9830312},
owner = {mahe},
pii = {S0079610798000261},
pmid = {9830312},
timestamp = {2006.09.06}
}
@article{Seeger2004Gaussian,
author = {Matthias Seeger},
title = {Gaussian processes for machine learning.},
journal = {Int {J} {N}eural {S}yst},
year = {2004},
volume = {14},
pages = {69-106},
number = {2},
month = {Apr},
abstract = {Gaussian processes ({GP}s) are natural generalisations of multivariate
{G}aussian random variables to infinite (countably or continuous)
index sets. {GP}s have been applied in a large number of fields to
a diverse range of ends, and very many deep theoretical analyses
of various properties are available. {T}his paper gives an introduction
to {G}aussian processes on a fairly elementary level with special
emphasis on characteristics relevant in machine learning. {I}t draws
explicit connections to branches such as spline smoothing models
and support vector machines in which similar ideas have been investigated.
{G}aussian process models are routinely used to solve hard machine
learning problems. {T}hey are attractive because of their flexible
non-parametric nature and computational simplicity. {T}reated within
a {B}ayesian framework, very powerful statistical methods can be
implemented which offer valid estimates of uncertainties in our predictions
and generic model selection procedures cast as nonlinear optimization
problems. {T}heir main drawback of heavy computational scaling has
recently been alleviated by the introduction of generic sparse approximations.13,78,31
{T}he mathematical literature on {GP}s is large and often uses deep
concepts which are not required to fully understand most machine
learning applications. {I}n this tutorial paper, we aim to present
characteristics of {GP}s relevant to machine learning and to show
up precise connections to other "kernel machines" popular in the
community. {O}ur focus is on a simple presentation, but references
to more detailed sources are provided.},
keywords = {Algorithms, Amino Acids, Antibodies, Artificial Intelligence, Astrocytoma,
Automated, Bayes Theorem, Biological, Biopsy, Brain, Brain Mapping,
Brain Neoplasms, Calibration, Comparative Study, Computational Biology,
Computer-Assisted, Computing Methodologies, Cysteine, Cystine, Dysplastic
Nevus Syndrome, Electrodes, Electroencephalography, Entropy, Eosine
Yellowish-(YS), Evoked Potentials, Female, Gene Expression Profiling,
Hematoxylin, Horseradish Peroxidase, Humans, Image Interpretation,
Image Processing, Imagery (Psychotherapy), Imagination, Laterality,
Linear Models, Male, Melanoma, Models, Monoclonal, Movement, Neoplasms,
Neural Networks (Computer), Neuropeptides, Non-P.H.S., Non-U.S. Gov't,
Nonparametric, Normal Distribution, P.H.S., Pattern Recognition,
Perception, Principal Component Analysis, Protein, Protein Array
Analysis, Protein Interaction Mapping, Proteins, Regression Analysis,
Research Support, Sensitivity and Specificity, Sequence Alignment,
Sequence Ana, Sequence Analysis, Skin Neoplasms, Software, Statistical,
Statistics, Tumor Markers, U.S. Gov't, User-Computer Interface, World
Health Organization, lysis, 15112367},
pii = {S0129065704001899}
}
@article{Seike2005Proteomic,
author = {Seike, M. and Kondo, T. and Fujii, K. and Okano, T. and Yamada, T.
and Matsuno, Y. and Gemma, A. and Kudoh, S. and Hirohashi, S.},
title = {Proteomic signatures for histological types of lung cancer.},
journal = {Proteomics},
year = {2005},
month = {Jul},
abstract = {We performed proteomic studies on lung cancer cells to elucidate the
mechanisms that determine histological phenotype. {T}hirty lung cancer
cell lines with three different histological backgrounds (squamous
cell carcinoma, small cell lung carcinoma and adenocarcinoma) were
subjected to two-dimensional difference gel electrophoresis (2-{D}
{DIGE}) and grouped by multivariate analyses on the basis of their
protein expression profiles. 2-{D} {DIGE} achieves more accurate
quantification of protein expression by using highly sensitive fluorescence
dyes to label the cysteine residues of proteins prior to two-dimensional
polyacrylamide gel electrophoresis. {W}e found that hierarchical
clustering analysis and principal component analysis divided the
cell lines according to their original histology. {S}pot ranking
analysis using a support vector machine algorithm and unsupervised
classification methods identified 32 protein spots essential for
the classification. {T}he proteins corresponding to the spots were
identified by mass spectrometry. {N}ext, lung cancer cells isolated
from tumor tissue by laser microdissection were classified on the
basis of the expression pattern of these 32 protein spots. {B}ased
on the expression profile of the 32 spots, the isolated cancer cells
were categorized into three histological groups: the squamous cell
carcinoma group, the adenocarcinoma group, and a group of carcinomas
with other histological types. {I}n conclusion, our results demonstrate
the utility of quantitative proteomic analysis for molecular diagnosis
and classification of lung cancer cells.},
doi = {10.1002/pmic.200401166},
pdf = {../local/Seike2005Proteomic.pdf},
file = {Seike2005Proteomic.pdf:local/Seike2005Proteomic.pdf:PDF},
keywords = {biosvm proteomics},
url = {http://dx.doi.org/10.1002/pmic.200401166}
}
@article{Seol2001Skp1,
author = {J. H. Seol and A. Shevchenko and A. Shevchenko and R. J. Deshaies},
title = {Skp1 forms multiple protein complexes, including {RAVE}, a regulator
of {V}-{ATP}ase assembly.},
journal = {Nat {C}ell {B}iol},
year = {2001},
volume = {3},
pages = {384-91},
number = {4},
month = {Apr},
abstract = {S{CF} ubiquitin ligases are composed of {S}kp1, {C}dc53, {H}rt1 and
one member of a large family of substrate receptors known as {F}-box
proteins ({FBP}s). {H}ere we report the identification, using sequential
rounds of epitope tagging, affinity purification and mass spectrometry,
of 16 {S}kp1 and {C}dc53-associated proteins in budding yeast, including
all components of {SCF}, 9 {FBP}s, {Y}jr033 ({R}av1) and {Y}dr202
({R}av2). {R}av1, {R}av2 and {S}kp1 form a complex that we have named
'regulator of the ({H}+)-{ATP}ase of the vacuolar and endosomal membranes'
({RAVE}), which associates with the {V}1 domain of the vacuolar membrane
({H}+)-{ATP}ase ({V}-{ATP}ase). {V}-{ATP}ases are conserved throughout
eukaryotes, and have been implicated in tumour metastasis and multidrug
resistance, and here we show that {RAVE} promotes glucose-triggered
assembly of the {V}-{ATP}ase holoenzyme. {P}revious systematic genome-wide
two-hybrid screens yielded 17 proteins that interact with {S}kp1
and {C}dc53, only 3 of which overlap with those reported here. {T}hus,
our results provide a distinct view of the interactions that link
proteins into a comprehensive cellular network.},
doi = {10.1038/35070067},
pdf = {../local/Seol2001Skp1.pdf},
file = {Seol2001Skp1.pdf:local/Seol2001Skp1.pdf:PDF},
keywords = {Affinity, Affinity Labels, Amino Acid Sequence, Animals, Cell Cycle
Proteins, Cells, Chromatography, Cloning, Comparative Study, Cullin
Proteins, Cultured, Cytoplasm, DNA, DNA Damage, DNA Repair, Electrospray
Ionization, Fungal, Fungal Proteins, Gene Targeting, Genetic, Glucose,
Holoenzymes, Humans, Macromolecular Substances, Mass, Matrix-Assisted
Laser Desorption-Ionization, Mitosis, Molecular, Molecular Sequence
Data, Non-P.H.S., Non-U.S. Gov't, P.H.S., Phosphoric Monoester Hydrolases,
Protein Binding, Protein Interaction Mapping, Protein Kinases, Proteome,
Proteomics, Proton-Translocating ATPases, Recombinant Fusion Proteins,
Research Support, Ribonucleoproteins, Ribosomes, S-Phase Kinase-Associated
Proteins, Saccharomyces cerevisiae, Saccharomyces cerevisiae Proteins,
Sensitivity and Specificity, Sequence Alignment, Signal Transduction,
Species Specificity, Spectrometry, Spectrum Analysis, Transcription,
U.S. Gov't, Vacuolar Proton-Translocating ATPases, 11283612},
owner = {vert},
pii = {35070067},
url = {http://dx.doi.org/10.1038/35070067}
}
@article{Sette1994relationship,
author = {A. Sette and A. Vitiello and B. Reherman and P. Fowler and R. Nayersina
and W. M. Kast and C. J. Melief and C. Oseroff and L. Yuan and J.
Ruppert and J. Sidney and M. F. del Guercio and S. Southwood and
R. T. Kubo and R. W. Chesnut and H. M. Grey and F. V. Chisari},
title = {The relationship between class I binding affinity and immunogenicity
of potential cytotoxic T cell epitopes.},
journal = {J. Immunol.},
year = {1994},
volume = {153},
pages = {5586--5592},
number = {12},
month = {Dec},
abstract = {The relationship between binding affinity for HLA class I molecules
and immunogenicity of discrete peptide epitopes has been analyzed
in two different experimental approaches. In the first approach,
the immunogenicity of potential epitopes ranging in MHC binding affinity
over a 10,000-fold range was analyzed in HLA-A*0201 transgenic mice.
In the second approach, the antigenicity of approximately 100 different
hepatitis B virus (HBV)-derived potential epitopes, all carrying
A*0201 binding motifs, was assessed by using PBL of acute hepatitis
patients. In both cases, it was found that an affinity threshold
of approximately 500 nM (preferably 50 nM or less) apparently determines
the capacity of a peptide epitope to elicit a CTL response. These
data correlate well with class I binding affinity measurements of
either naturally processed peptides or previously described T cell
epitopes. Taken together, these data have important implications
for the selection of epitopes for peptide-based vaccines, and also
formally demonstrate the crucial role of determinant selection in
the shaping of T cell responses. Because in most (but not all) cases,
high affinity peptides seem to be immunogenic, our data also suggest
that holes in the functional T cell repertoire, if they exist, may
be relatively rare.},
keywords = {Amino Acid Sequence; Animals; Cell Line; Cytotoxicity Tests, Immunologic;
Epitopes; HLA-A Antigens; Hepatitis B; Hepatitis B Antigens; Humans;
Mice; Mice, Transgenic; Molecular Sequence Data; Peptides; Protein
Binding; T-Lymphocytes, Cytotoxic},
owner = {laurent},
pmid = {7527444},
timestamp = {2007.07.12}
}
@article{Shadforth2005Protein,
author = {Ian Shadforth and Daniel Crowther and Conrad Bessant},
title = {Protein and peptide identification algorithms using MS for use in
high-throughput, automated pipelines.},
journal = {Proteomics},
year = {2005},
volume = {5},
pages = {4082--4095},
number = {16},
month = {Nov},
abstract = {Current proteomics experiments can generate vast quantities of data
very quickly, but this has not been matched by data analysis capabilities.
Although there have been a number of recent reviews covering various
aspects of peptide and protein identification methods using MS, comparisons
of which methods are either the most appropriate for, or the most
effective at, their proposed tasks are not readily available. As
the need for high-throughput, automated peptide and protein identification
systems increases, the creators of such pipelines need to be able
to choose algorithms that are going to perform well both in terms
of accuracy and computational efficiency. This article therefore
provides a review of the currently available core algorithms for
PMF, database searching using MS/MS, sequence tag searches and de
novo sequencing. We also assess the relative performances of a number
of these algorithms. As there is limited reporting of such information
in the literature, we conclude that there is a need for the adoption
of a system of standardised reporting on the performance of new peptide
and protein identification algorithms, based upon freely available
datasets. We go on to present our initial suggestions for the format
and content of these datasets.},
doi = {10.1002/pmic.200402091},
institution = {Cranfield Centre for Bioinformatics and IT, Cranfield University,
Silsoe, UK.},
keywords = {Algorithms; Alternative Splicing; Databases, Protein; Peptides; Polymorphism,
Genetic; Proteins; Proteomics; Sequence Analysis; Software; Spectrometry,
Mass, Matrix-Assisted Laser Desorption-Ionization},
owner = {phupe},
pmid = {16196103},
timestamp = {2010.08.19},
url = {http://dx.doi.org/10.1002/pmic.200402091}
}
@article{Sheinerman2003Sequence,
author = {Felix B Sheinerman and Bissan Al-Lazikani and Barry Honig},
title = {Sequence, structure and energetic determinants of phosphopeptide
selectivity of {SH2} domains.},
journal = {J. Mol. Biol.},
year = {2003},
volume = {334},
pages = {823--841},
number = {4},
month = {Dec},
abstract = {Here, we present an approach for the prediction of binding preferences
of members of a large protein family for which structural information
for a number of family members bound to a substrate is available.
The approach involves a number of steps. First, an accurate multiple
alignment of sequences of all members of a protein family is constructed
on the basis of a multiple structural superposition of family members
with known structure. Second, the methods of continuum electrostatics
are used to characterize the energetic contribution of each residue
in a protein to the binding of its substrate. Residues that make
a significant contribution are mapped onto the protein sequence and
are used to define a "binding site signature" for the complex being
considered. Third, sequences whose structures have not been determined
are checked to see if they have binding-site signatures similar to
one of the known complexes. Predictions of binding affinity to a
given substrate are based on similarities in binding-site signature.
An important component of the approach is the introduction of a context-specific
substitution matrix suitable for comparison of binding-site residues.The
methods are applied to the prediction of phosphopeptide selectivity
of SH2 domains. To this end, the energetic roles of all protein residues
in 17 different complexes of SH2 domains with their cognate targets
are analyzed. The total number of residues that make significant
contributions to binding is found to vary from nine to 19 in different
complexes. These energetically important residues are found to contribute
to binding through a variety of mechanisms, involving both electrostatic
and hydrophobic interactions. Binding-site signatures are found to
involve residues in different positions in SH2 sequences, some of
them as far as 9A away from a bound peptide. Surprisingly, similarities
in the signatures of different domains do not correlate with whole-domain
sequence identities unless the latter is greater than 50\%.An extensive
comparison with the optimal binding motifs determined by peptide
library experiments, as well as other experimental data indicate
that the similarity in binding preferences of different SH2 domains
can be deduced on the basis of their binding-site signatures. The
analysis provides a rationale for the empirically derived classification
of SH2 domains described by Songyang & Cantley, in that proteins
in the same group are found to have similar residues at positions
important for binding. Confident predictions of binding preference
can be made for about 85\% of SH2 domain sequences found in SWISSPROT.
The approach described in this work is quite general and can, in
principle, be used to analyze binding preferences of members of large
protein families for which structural information for a number of
family members is available. It also offers a strategy for predicting
cross-reactivity of compounds designed to bind to a particular target,
for example in structure-based drug design.},
keywords = {Amino Acid Sequence; Binding Sites; Molecular Sequence Data; Peptide
Library; Phosphopeptides; Protein Binding; Sequence Alignment; Substrate
Specificity; src Homology Domains},
owner = {laurent},
pii = {S0022283603012373},
pmid = {14636606},
timestamp = {2007.01.03}
}
@article{Sheinerman2005High,
author = {Felix B Sheinerman and Elie Giraud and Abdelazize Laoui},
title = {High affinity targets of protein kinase inhibitors have similar residues
at the positions energetically important for binding.},
journal = {J. Mol. Biol.},
year = {2005},
volume = {352},
pages = {1134--1156},
number = {5},
month = {Oct},
abstract = {Inhibition of protein kinase activity is a focus of intense drug discovery
efforts in several therapeutic areas. Major challenges facing the
field include understanding of the factors determining the selectivity
of kinase inhibitors and the development of compounds with the desired
selectivity profile. Here, we report the analysis of sequence variability
among high and low affinity targets of eight different small molecule
kinase inhibitors (BIRB796, Tarceva, NU6102, Gleevec, SB203580, balanol,
H89, PP1). It is observed that all high affinity targets of each
inhibitor are found among a relatively small number of kinases, which
have similar residues at the specific positions important for binding.
The findings are highly statistically significant, and allow one
to exclude the majority of kinases in a genome from a list of likely
targets for an inhibitor. The findings have implications for the
design of novel inhibitors with a desired selectivity profile (e.g.
targeted at multiple kinases), the discovery of new targets for kinase
inhibitor drugs, comparative analysis of different in vivo models,
and the design of "a-la-carte" chemical libraries tailored for individual
kinases.},
doi = {10.1016/j.jmb.2005.07.074},
keywords = {Amino Acid Sequence; Amino Acids; Binding Sites; Electrostatics; Humans;
Ligands; Molecular Sequence Data; Piperazines; Protein Binding; Protein
Kinase Inhibitors; Protein Kinases; Pyrazoles; Pyrimidines; Sequence
Alignment; Thermodynamics},
owner = {laurent},
pii = {S0022-2836(05)00900-9},
pmid = {16139843},
timestamp = {2007.01.03},
url = {http://dx.doi.org/10.1016/j.jmb.2005.07.074}
}
@article{Shen2005[Detection,
author = {Li Shen and Jie Yang and Yue Zhou},
title = {Detection of {PVC}s with support vector machine},
journal = {Sheng {W}u {Y}i {X}ue {G}ong {C}heng {X}ue {Z}a {Z}hi},
year = {2005},
volume = {22},
pages = {78-81},
number = {1},
month = {Feb},
abstract = {The classifiction of heart beats is the foundation for automated arrhythmia
monitoring devices. {S}upport vector machnies ({SVM}s) have meant
a great advance in solving classification or pattern recognition.
{T}his study describes {SVM} for the identification of premature
ventricular contractions ({PVC}s) in surface {ECG}s. {F}eatures for
the classification task are extracted by analyzing the heart rate,
morphology and wavelet energy of the heart beats from a single lead.
{T}he performance of different {SVM}s is evaluated on the {MIT}-{BIH}
arrhythmia database following the association for the advancement
of medical instrumentation ({AAMI}) recommendations.},
keywords = {80 and over, Adult, Aged, Algorithms, Amino Acids, Animals, Area Under
Curve, Artifacts, Automated, Birefringence, Brain Chemistry, Brain
Neoplasms, Comparative Study, Computer-Assisted, Cornea, Cross-Sectional
Studies, Decision Trees, Diagnosis, Diagnostic Imaging, Diagnostic
Techniques, Discriminant Analysis, Evolution, Face, Female, Genetic,
Glaucoma, Humans, Intraocular Pressure, Lasers, Least-Squares Analysis,
Magnetic Resonance Imaging, Magnetic Resonance Spectroscopy, Male,
Middle Aged, Models, Molecular, Nerve Fibers, Non-U.S. Gov't, Numerical
Analysis, Ophthalmological, Optic Nerve Diseases, Optical Coherence,
P.H.S., Pattern Recognition, Photic Stimulation, Prospective Studies,
Protein, ROC Curve, Regression Analysis, Research Support, Retinal
Ganglion Cells, Sensitivity and Specificity, Sequence Analysis, Statistics,
Tomography, U.S. Gov't, Visual Fields, beta-Lactamases, 15762121}
}
@article{Shoeb2004Patient-specific,
author = {Ali Shoeb and Herman Edwards and Jack Connolly and Blaise Bourgeois
and S. Ted Treves and John Guttag},
title = {Patient-specific seizure onset detection.},
journal = {Epilepsy {B}ehav},
year = {2004},
volume = {5},
pages = {483-98},
number = {4},
month = {Aug},
abstract = {This article presents an automated, patient-specific method for the
detection of epileptic seizure onset from noninvasive electroencephalography.
{W}e adopt a patient-specific approach to exploit the consistency
of an individual patient's seizure and nonseizure electroencephalograms.
{O}ur method uses a wavelet decomposition to construct a feature
vector that captures the morphology and spatial distribution of an
electroencephalographic epoch, and then determines whether that vector
is representative of a patient's seizure or nonseizure electroencephalogram
using the support vector machine classification algorithm. {O}ur
completely automated method was tested on noninvasive electroencephalograms
from 36 pediatric subjects suffering from a variety of seizure types.
{I}t detected 131 of 139 seizure events within 8.0+/-3.2 seconds
of electrographic onset, and declared 15 false detections in 60 hours
of clinical electroencephalography. {O}ur patient-specific method
can be used to initiate delay-sensitive clinical procedures following
seizure onset, for example, the injection of a functional imaging
radiotracer.},
doi = {10.1016/j.yebeh.2004.05.005},
pdf = {../local/Shoeb2004Patient-specific.pdf},
file = {Shoeb2004Patient-specific.pdf:local/Shoeb2004Patient-specific.pdf:PDF},
keywords = {Algorithms, Comparative Study, Computational Biology, Computer-Assisted,
Databases, Diagnosis, Drug Resistance, Electroencephalography, Epilepsy,
Forecasting, Genetic, Genotype, HIV Protease Inhibitors, HIV-1, Humans,
Information Management, Information Storage and Retrieval, Kinetics,
Linear Models, Microbial Sensitivity Tests, Models, Monitoring, Non-U.S.
Gov't, P.H.S., Periodicals, Physiologic, Point Mutation, Pyrimidinones,
Reaction Time, Research Support, Reverse Transcriptase Inhibitors,
Signal Processing, Theoretical, Time Factors, U.S. Gov't, Viral,
15256184},
pii = {S1525505004001593},
url = {http://dx.doi.org/10.1016/j.yebeh.2004.05.005}
}
@article{Shulman-Peleg2005SiteEngines,
author = {Alexandra Shulman-Peleg and Ruth Nussinov and Haim J Wolfson},
title = {SiteEngines: recognition and comparison of binding sites and protein-protein
interfaces.},
journal = {Nucleic Acids Res},
year = {2005},
volume = {33},
pages = {W337--W341},
number = {Web Server issue},
month = {Jul},
abstract = {Protein surface regions with similar physicochemical properties and
shapes may perform similar functions and bind similar binding partners.
Here we present two web servers and software packages for recognition
of the similarity of binding sites and interfaces. Both methods recognize
local geometrical and physicochemical similarity, which can be present
even in the absence of overall sequence or fold similarity. The first
method, SiteEngine (http:/bioinfo3d.cs.tau.ac.il/SiteEngine), receives
as an input two protein structures and searches the complete surface
of one protein for regions similar to the binding site of the other.
The second, Interface-to-Interface (I2I)-SiteEngine (http:/bioinfo3d.cs.tau.ac.il/I2I-SiteEngine),
compares protein-protein interfaces, which are regions of interaction
between two protein molecules. It receives as an input two structures
of protein-protein complexes, extracts the interfaces and finds the
three-dimensional transformation that maximizes the similarity between
two pairs of interacting binding sites. The output of both servers
consists of a superimposition in PDB file format and a list of physicochemical
properties shared by the compared entities. The methods are highly
efficient and the freely available software packages are suitable
for large-scale database searches of the entire PDB.},
doi = {10.1093/nar/gki482},
institution = {School of Computer Science, Raymond and Beverly Sackler Faculty of
Exact Sciences, Tel Aviv University, Tel Aviv 69978, Israel. shulmana@tau.ac.il},
keywords = {Amino Acids, chemistry; Binding Sites; Internet; Multiprotein Complexes,
chemistry/metabolism; Protein Conformation; Protein Interaction Mapping,
methods; Software; User-Computer Interface},
language = {eng},
medline-pst = {ppublish},
owner = {bricehoffmann},
pii = {33/suppl_2/W337},
pmid = {15980484},
timestamp = {2009.11.12},
url = {http://dx.doi.org/10.1093/nar/gki482}
}
@article{Shulman-Peleg2004Recognition,
author = {Alexandra Shulman-Peleg and Ruth Nussinov and Haim J Wolfson},
title = {Recognition of functional sites in protein structures.},
journal = {J Mol Biol},
year = {2004},
volume = {339},
pages = {607--633},
number = {3},
month = {Jun},
abstract = {Recognition of regions on the surface of one protein, that are similar
to a binding site of another is crucial for the prediction of molecular
interactions and for functional classifications. We first describe
a novel method, SiteEngine, that assumes no sequence or fold similarities
and is able to recognize proteins that have similar binding sites
and may perform similar functions. We achieve high efficiency and
speed by introducing a low-resolution surface representation via
chemically important surface points, by hashing triangles of physico-chemical
properties and by application of hierarchical scoring schemes for
a thorough exploration of global and local similarities. We proceed
to rigorously apply this method to functional site recognition in
three possible ways: first, we search a given functional site on
a large set of complete protein structures. Second, a potential functional
site on a protein of interest is compared with known binding sites,
to recognize similar features. Third, a complete protein structure
is searched for the presence of an a priori unknown functional site,
similar to known sites. Our method is robust and efficient enough
to allow computationally demanding applications such as the first
and the third. From the biological standpoint, the first application
may identify secondary binding sites of drugs that may lead to side-effects.
The third application finds new potential sites on the protein that
may provide targets for drug design. Each of the three applications
may aid in assigning a function and in classification of binding
patterns. We highlight the advantages and disadvantages of each type
of search, provide examples of large-scale searches of the entire
Protein Data Base and make functional predictions.},
doi = {10.1016/j.jmb.2004.04.012},
institution = {School of Computer Science, Tel Aviv University, Tel Aviv 69978,
Israel.},
keywords = {Algorithms; Catalytic Domain; Hydrogen Bonding; Models, Molecular;
Protein Conformation; Proteins, chemistry},
language = {eng},
medline-pst = {ppublish},
owner = {bricehoffmann},
pii = {S0022283604004139},
pmid = {15147845},
timestamp = {2009.11.12},
url = {http://dx.doi.org/10.1016/j.jmb.2004.04.012}
}
@article{Sidney1996Definition,
author = {J. Sidney and H. M. Grey and S. Southwood and E. Celis and P. A.
Wentworth and M. F. del Guercio and R. T. Kubo and R. W. Chesnut
and A. Sette},
title = {Definition of an {HLA-A3}-like supermotif demonstrates the overlapping
peptide-binding repertoires of common {HLA} molecules.},
journal = {Hum Immunol},
year = {1996},
volume = {45},
pages = {79--93},
number = {2},
month = {Feb},
abstract = {An HLA-A3-like supertype (minimally comprised of products from the
HLA class I alleles A3, A11, A31, A*3301, and A*6801) has been defined
on the basis of (a) structural similarities in the antigen-binding
groove, (b) shared main anchor peptide-binding motifs, (c) the identification
of peptides cross-reacting with most or all of these molecules, and
(d) the definition of an A3-like supermotif that efficiently predicts
highly cross-reactive peptides. Detailed secondary anchor maps for
A3, A11, A31, A*3301, and A*6801 are also described. The biologic
relevance of the A3-like supertype is indicated by the fact that
high frequencies of the A3-like supertype alleles are conserved in
all major ethnic groups. Because A3-like supertype alleles are found
in most major HLA evolutionary lineages, possibly a reflection of
common ancestry, the A3-like supermotif might in fact represent a
primeval human HLA class I peptide-binding specificity. It is also
possible that these phenomena might be related to optimal exploitation
of the peptide specificity by human TAP molecules. The grouping of
HLA alleles into supertypes on the basis of their overlapping peptide-binding
repertoires represents an alternative to serologic or phylogenetic
classification.},
keywords = {Alleles; Amino Acid Sequence; Cell Line, Transformed; Cross Reactions;
HLA Antigens; HLA-A3 Antigen; HLA-B Antigens; Haplotypes; Humans;
Molecular Sequence Data; Peptide Fragments; Protein Binding; Structure-Activity
Relationship},
owner = {laurent},
pii = {0198-8859(95)00173-5},
pmid = {8882405},
timestamp = {2007.01.05}
}
@article{Sidney1995Several,
author = {J. Sidney and M. F. del Guercio and S. Southwood and V. H. Engelhard
and E. Appella and H. G. Rammensee and K. Falk and O. R\"otzschke
and M. Takiguchi and R. T. Kubo},
title = {Several {HLA} alleles share overlapping peptide specificities.},
journal = {J. Immunol.},
year = {1995},
volume = {154},
pages = {247--259},
number = {1},
month = {Jan},
abstract = {Herein we describe the establishment of assays to measure peptide
binding to purified HLA-B*0701, -B*0801, -B*2705, -B*3501-03, -B*5401,
-Cw*0401, -Cw*0602, and -Cw*0702 molecules. The binding of known
peptide epitopes or naturally processed peptides correlates well
with HLA restriction or origin, underscoring the immunologic relevance
of these assays. Analysis of the sequences of various HLA class I
alleles suggested that alleles with peptide motifs characterized
by proline in position 2 and aromatic or hydrophobic residues at
their C-terminus shared key consensus residues at positions 9, 63,
66, 67, and 70 (B pocket) and residue 116 (F pocket). Prediction
of the peptide-binding specificity of HLA-B*5401, on the basis of
this consensus B and F pocket structure, verified this hypothesis
and suggested that a relatively large family of HLA-B alleles (which
we have defined as the HLA-B7-like supertype) may significantly overlap
in peptide binding specificity. Availability of quantitative binding
assays allowed verification that, indeed, many (25\%) of the peptide
ligands carrying proline in position 2 and hydrophobic/aromatic residues
at the C-terminus (the B7-like supermotif) were capable of binding
at least three of five HLA-B7-like supertype alleles. Identification
of epitopes carrying the B7-like supermotif and binding to a family
of alleles represented in over 40\% of individuals from all major
ethnic groups may be of considerable use in the design of peptide
vaccines.},
keywords = {Alleles; Amino Acid Sequence; Cell Line, Transformed; Consensus Sequence;
Epitopes; Genes, MHC Class I; HLA-B Antigens; HLA-C Antigens; Humans;
Molecular Sequence Data; Peptide Fragments; Protein Binding; Protein
Structure, Tertiary; Structure-Activity Relationship; Substrate Specificity},
owner = {laurent},
pmid = {7527812},
timestamp = {2007.01.05}
}
@article{Smith2004Towards,
author = {P. A. Smith and M. J. Sorich and L. S C Low and R. A. McKinnon and
J. O. Miners},
title = {Towards integrated {ADME} prediction: past, present and future directions
for modelling metabolism by {UDP}-glucuronosyltransferases.},
journal = {J {M}ol {G}raph {M}odel},
year = {2004},
volume = {22},
pages = {507-17},
number = {6},
month = {Jul},
abstract = {Undesirable absorption, distribution, metabolism, excretion ({ADME})
properties are the cause of many drug development failures and this
has led to the need to identify such problems earlier in the development
process. {T}his review highlights computational (in silico) approaches
that have been used to identify the characteristics of ligands influencing
molecular recognition and/or metabolism by the drug-metabolising
enzyme {UDP}-gucuronosyltransferase ({UGT}). {C}urrent studies applying
pharmacophore elucidation, 2{D}-quantitative structure metabolism
relationships (2{D}-{QSMR}), 3{D}-quantitative structure metabolism
relationships (3{D}-{QSMR}), and non-linear pattern recognition techniques
such as artificial neural networks and support vector machines for
modelling metabolism by {UGT} are reported. {A}n assessment of the
utility of in silico approaches for the qualitative and quantitative
prediction of drug glucuronidation parameters highlights the benefit
of using multiple pharmacophores and also non-linear techniques for
classification. {S}ome of the challenges facing the development of
generalisable models for predicting metabolism by {UGT}, including
the need for screening of more diverse structures, are also outlined.},
doi = {10.1016/j.jmgm.2004.03.011},
pdf = {../local/Smith2004Towards.pdf},
file = {Smith2004Towards.pdf:local/Smith2004Towards.pdf:PDF},
keywords = {Algorithms, Animals, Antisense, Artificial Intelligence, Astrocytoma,
Automated, Autonomic Nervous System, Brain, Brain Neoplasms, Cell
Line, Cerebral Cortex, Child, Cluster Analysis, Cognition, Comparative
Study, Computational Biology, Computer Simulation, Computer-Assisted,
DNA Fingerprinting, Databases, Diagnosis, Discriminant Analysis,
Drug Design, Drug Evaluation, Electroencephalography, Emotions, Event-Related
Potentials, Evoked Potentials, Factual, Fluorescence, Fuzzy Logic,
Gene Silencing, Gene Targeting, Genetic, Glucuronosyltransferase,
Hand, Hela Cells, Humans, Imaging, Intracellular Space, Magnetic
Resonance Spectroscopy, Male, Meningeal Neoplasms, Meningioma, Microscopy,
Models, Molecular Structure, Monitoring, Motor, Neoplasm Metastasis,
Neoplasms, Neural Networks (Computer), Non-U.S. Gov't, Oligonucleotides,
P.H.S., P300, Pattern Recognition, Peptides, Pharmaceutical Preparations,
Physiologic, Preclinical, Predictive Value of Tests, Preschool, Prognosis,
Protein Interaction Mapping, Protein Structure, Proteins, Proteomics,
Quantitative Structure-Activity Relationship, Quaternary, RNA, RNA
Interference, Recognition (Psychology), Reproducibility of Results,
Research Support, Sensitivity and Specificity, Signal Processing,
Small Interfering, Software, Thionucleotides, Three-Dimensional,
Tumor, U.S. Gov't, User-Computer Interface, Word Processing, 15182810},
pii = {S1093326304000269},
url = {http://dx.doi.org/10.1016/j.jmgm.2004.03.011}
}
@techreport{Sole2001Model,
author = {Sol{\'e}, R. V. and Pastor-Satorras, R. and Smith, E. D. and Kepler,
T.},
title = {A {M}odel of {L}arge-{S}cale {P}roteome {E}volution},
institution = {Santa Fe Institute},
year = {2001},
note = {Working paper 01-08-041},
pdf = {../local/sole01.pdf},
file = {sole01.pdf:local/sole01.pdf:PDF},
subject = {bionetprot},
url = {http://www.santafe.edu/sfi/publications/Abstracts/01-08-041abs.html}
}
@article{Song2002Prediction,
author = {Minghu Song and Curt M Breneman and Jinbo Bi and N. Sukumar and Kristin
P Bennett and Steven Cramer and Nihal Tugcu},
title = {Prediction of protein retention times in anion-exchange chromatography
systems using support vector regression.},
journal = {J {C}hem {I}nf {C}omput {S}ci},
year = {2002},
volume = {42},
pages = {1347-57},
number = {6},
abstract = {Quantitative {S}tructure-{R}etention {R}elationship ({QSRR}) models
are developed for the prediction of protein retention times in anion-exchange
chromatography systems. {T}opological, subdivided surface area, and
{TAE} ({T}ransferable {A}tom {E}quivalent) electron-density-based
descriptors are computed directly for a set of proteins using molecular
connectivity patterns and crystal structure geometries. {A} novel
algorithm based on {S}upport {V}ector {M}achine ({SVM}) regression
has been employed to obtain predictive {QSRR} models using a two-step
computational strategy. {I}n the first step, a sparse linear {SVM}
was utilized as a feature selection procedure to remove irrelevant
or redundant information. {S}ubsequently, the selected features were
used to produce an ensemble of nonlinear {SVM} regression models
that were combined using bootstrap aggregation (bagging) techniques,
where various combinations of training and validation data sets were
selected from the pool of available data. {A} visualization scheme
(star plots) was used to display the relative importance of each
selected descriptor in the final set of "bagged" models. {O}nce these
predictive models have been validated, they can be used as an automated
prediction tool for virtual high-throughput screening ({VHTS}).},
keywords = {Acute, Algorithms, Animals, Anion Exchange Resins, Artificial Intelligence,
Automated, Base Pair Mismatch, Base Pairing, Base Sequence, Biological,
Biosensing Techniques, Carcinoma, Chemical, Chromatography, Classification,
Cluster Analysis, Comparative Study, Computational Biology, Computer-Assisted,
Cystadenoma, DNA, Decision Making, Diagnosis, Differential, Drug,
Drug Design, Electrostatics, Eukaryotic Cells, Feasibility Studies,
Female, Gene Expression, Gene Expression Profiling, Gene Expression
Regulation, Genes, Genetic, Genetic Markers, Hemolysins, Humans,
Internet, Ion Exchange, Leukemia, Ligands, Likelihood Functions,
Logistic Models, Lung Neoplasms, Lymphocytic, Lymphoma, Markov Chains,
Mathematics, Messenger, Models, Molecular, Molecular Probe Techniques,
Molecular Sequence Data, Nanotechnology, Neoplasm, Neoplasms, Neoplastic,
Neural Networks (Computer), Non-P.H.S., Non-Small-Cell Lung, Non-U.S.
Gov't, Nucleic Acid Conformation, Nucleic Acid Hybridization, Observer
Variation, Oligonucleotide Array Sequence Analysis, Ovarian Neoplasms,
P.H.S., Pattern Recognition, Probability, Protein Binding, Protein
Conformation, Proteins, Quality Control, Quantum Theory, RNA, RNA
Splicing, Receptors, Reference Values, Regression Analysis, Reproducibility
of Results, Research Support, Sensitivity and Specificity, Sequence
Analysis, Signal Processing, Software, Statistical, Stomach Neoplasms,
Thermodynamics, Transcription, Tumor Markers, U.S. Gov't, 12444731},
pii = {ci025580t}
}
@article{Song2004Comparison,
author = {Xiaowei Song and Arnold Mitnitski and Jafna Cox and Kenneth Rockwood},
title = {Comparison of machine learning techniques with classical statistical
models in predicting health outcomes.},
journal = {Medinfo},
year = {2004},
volume = {11},
pages = {736-40},
number = {Pt 1},
abstract = {Several machine learning techniques (multilayer and single layer perceptron,
logistic regression, least square linear separation and support vector
machines) are applied to calculate the risk of death from two biomedical
data sets, one from patient care records, and another from a population
survey. {E}ach dataset contained multiple sources of information:
history of related symptoms and other illnesses, physical examination
findings, laboratory tests, medications (patient records dataset),
health attitudes, and disabilities in activities of daily living
(survey dataset). {E}ach technique showed very good mortality prediction
in the acute patients data sample ({AUC} up to 0.89) and fair prediction
accuracy for six year mortality ({AUC} from 0.70 to 0.76) in individuals
from epidemiological database surveys. {T}he results suggest that
the nature of data is of primary importance rather than the learning
technique. {H}owever, the consistently superior performance of the
artificial neural network (multi-layer perceptron) indicates that
nonlinear relationships (which cannot be discerned by linear separation
techniques) can provide additional improvement in correctly predicting
health outcomes.},
keywords = {Aged, Air, Algorithms, Amino Acids, Animals, Area Under Curve, Artifacts,
Artificial Intelligence, Atrial, Automated, Canada, Carotid Stenosis,
Cerebrovascular Accident, Cerebrovascular Circulation, Comparative
Study, Computer-Assisted, Cysteine, Decision Trees, Dementia, Diagnosis,
Disulfides, Doppler, Embolism, Expert Systems, Extramural, Factor
Analysis, Female, Gene Expression, Gene Expression Profiling, Health
Status, Heart Septal Defects, Humans, Intracranial Embolism, Male,
Models, Molecular, Myocardial Infarction, N.I.H., Neoplasms, Neural
Networks (Computer), Non-U.S. Gov't, Oligonucleotide Array Sequence
Analysis, Oxidation-Reduction, P.H.S., Pattern Recognition, Prognosis,
Protein Binding, Protein Folding, Proteins, ROC Curve, Research Support,
Sensitivity and Specificity, Software, Statistical, Transcranial,
Treatment Outcome, U.S. Gov't, Ultrasonography, 15360910},
pii = {D040004933}
}
@article{Stahura2004Virtual,
author = {Florence L Stahura and Jürgen Bajorath},
title = {Virtual screening methods that complement {HTS}.},
journal = {Comb {C}hem {H}igh {T}hroughput {S}creen},
year = {2004},
volume = {7},
pages = {259-69},
number = {4},
month = {Jun},
abstract = {In this review, we discuss a number of computational methods that
have been developed or adapted for molecule classification and virtual
screening ({VS}) of compound databases. {I}n particular, we focus
on approaches that are complementary to high-throughput screening
({HTS}). {T}he discussion is limited to {VS} methods that operate
at the small molecular level, which is often called ligand-based
{VS} ({LBVS}), and does not take into account docking algorithms
or other structure-based screening tools. {W}e describe areas that
greatly benefit from combining virtual and biological screening and
discuss computational methods that are most suitable to contribute
to the integration of screening technologies. {R}elevant approaches
range from established methods such as clustering or similarity searching
to techniques that have only recently been introduced for {LBVS}
applications such as statistical methods or support vector machines.
{F}inally, we discuss a number of representative applications at
the interface between {VS} and {HTS}.},
keywords = {Algorithms, Animals, Antisense, Artificial Intelligence, Cell Line,
Cluster Analysis, Comparative Study, Computational Biology, Computer
Simulation, DNA Fingerprinting, Drug Evaluation, Fluorescence, Fuzzy
Logic, Gene Silencing, Gene Targeting, Genetic, Hela Cells, Humans,
Imaging, Intracellular Space, Microscopy, Models, Neoplasms, Neural
Networks (Computer), Non-U.S. Gov't, Oligonucleotides, P.H.S., Preclinical,
Prognosis, Proteomics, Quantitative Structure-Activity Relationship,
RNA, RNA Interference, Research Support, Sensitivity and Specificity,
Small Interfering, Thionucleotides, Three-Dimensional, Tumor, U.S.
Gov't, 15200375}
}
@article{Stelzl2005human,
author = {Ulrich Stelzl and Uwe Worm and Maciej Lalowski and Christian Haenig
and Felix H Brembeck and Heike Goehler and Martin Stroedicke and
Martina Zenkner and Anke Schoenherr and Susanne Koeppen and Jan Timm
and Sascha Mintzlaff and Claudia Abraham and Nicole Bock and Silvia
Kietzmann and Astrid Goedde and Engin Toksöz and Anja Droege and
Sylvia Krobitsch and Bernhard Korn and Walter Birchmeier and Hans
Lehrach and Erich E Wanker},
title = {A human protein-protein interaction network: a resource for annotating
the proteome.},
journal = {Cell},
year = {2005},
volume = {122},
pages = {957--968},
number = {6},
month = {Sep},
abstract = {Protein-protein interaction maps provide a valuable framework for
a better understanding of the functional organization of the proteome.
To detect interacting pairs of human proteins systematically, a protein
matrix of 4456 baits and 5632 preys was screened by automated yeast
two-hybrid (Y2H) interaction mating. We identified 3186 mostly novel
interactions among 1705 proteins, resulting in a large, highly connected
network. Independent pull-down and co-immunoprecipitation assays
validated the overall quality of the Y2H interactions. Using topological
and GO criteria, a scoring system was developed to define 911 high-confidence
interactions among 401 proteins. Furthermore, the network was searched
for interactions linking uncharacterized gene products and human
disease proteins to regulatory cellular pathways. Two novel Axin-1
interactions were validated experimentally, characterizing ANP32A
and CRMP1 as modulators of Wnt signaling. Systematic human protein
interaction screens can lead to a more comprehensive understanding
of protein function and cellular processes.},
doi = {10.1016/j.cell.2005.08.029},
institution = {Max Delbrueck Center for Molecular Medicine, 13092 Berlin-Buch, Germany.},
keywords = {Databases as Topic; Humans; Intracellular Signaling Peptides and Proteins;
Models, Molecular; Nerve Tissue Proteins; Protein Binding; Proteins;
Proteomics; Repressor Proteins; Two-Hybrid System Techniques},
owner = {phupe},
pii = {S0092-8674(05)00866-4},
pmid = {16169070},
timestamp = {2010.09.01},
url = {http://dx.doi.org/10.1016/j.cell.2005.08.029}
}
@article{Stoddart2010Nucleobase,
author = {David Stoddart and Andrew J Heron and Jochen Klingelhoefer and Ellina
Mikhailova and Giovanni Maglia and Hagan Bayley},
title = {Nucleobase recognition in ssDNA at the central constriction of the
alpha-hemolysin pore.},
journal = {Nano Lett},
year = {2010},
volume = {10},
pages = {3633--3637},
number = {9},
month = {Sep},
abstract = {Nanopores are under investigation for single-molecule DNA sequencing.
The alpha-hemolysin (alphaHL) protein nanopore contains three recognition
points capable of nucleobase discrimination in individual immobilized
ssDNA molecules. We have modified the recognition point R(1) by extensive
mutagenesis of residue 113. Amino acids that provide an energy barrier
to ion flow (e.g., bulky or hydrophobic residues) strengthen base
identification, while amino acids that lower the barrier weaken it.
Amino acids with related side chains produce similar patterns of
nucleobase recognition providing a rationale for the redesign of
recognition points.},
doi = {10.1021/nl101955a},
institution = {Department of Chemistry, University of Oxford, Oxford OX1 3TA, United
Kingdom.},
keywords = {Amino Acid Substitution; Base Sequence; DNA, Single-Stranded, chemistry;
Hemolysin Proteins, chemistry; Models, Molecular; Mutagenesis},
language = {eng},
medline-pst = {ppublish},
owner = {phupe},
pmid = {20704324},
timestamp = {2011.06.01},
url = {http://dx.doi.org/10.1021/nl101955a}
}
@article{Strahl2000language,
author = {Strahl, B. D. and Allis, C. D.},
title = {The language of covalent histone modifications},
journal = {Nature},
year = {2000},
volume = {403},
pages = {41--45},
number = {6765},
month = {Jan},
abstract = {Histone proteins and the nucleosomes they form with DNA are the fundamental
building blocks of eukaryotic chromatin. A diverse array of post-translational
modifications that often occur on tail domains of these proteins
has been well documented. Although the function of these highly conserved
modifications has remained elusive, converging biochemical and genetic
evidence suggests functions in several chromatin-based processes.
We propose that distinct histone modifications, on one or more tails,
act sequentially or in combination to form a 'histone code' that
is, read by other proteins to bring about distinct downstream events.},
doi = {10.1038/47412},
institution = {Department of Biochemistry and Molecular Genetics, University of
Virginia Health Science Center, Charlottesville 22908, USA.},
keywords = {Acetylation; Amino Acid Sequence; Animals; Chromatin, physiology;
Histones, chemistry/metabolism/physiology; Humans; Lysine, physiology;
Microtubules, physiology; Models, Biological; Molecular Sequence
Data; Phosphorylation; Protein Processing, Post-Translational; Serine,
metabolism},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pmid = {10638745},
timestamp = {2010.11.23},
url = {http://dx.doi.org/10.1038/47412}
}
@article{Strahl2001Methylation,
author = {B. D. Strahl and S. D. Briggs and C. J. Brame and J. A. Caldwell
and S. S. Koh and H. Ma and R. G. Cook and J. Shabanowitz and D.
F. Hunt and M. R. Stallcup and C. D. Allis},
title = {Methylation of histone H4 at arginine 3 occurs in vivo and is mediated
by the nuclear receptor coactivator PRMT1.},
journal = {Curr Biol},
year = {2001},
volume = {11},
pages = {996--1000},
number = {12},
month = {Jun},
abstract = {Posttranslational modifications of histone amino termini play an important
role in modulating chromatin structure and function. Lysine methylation
of histones has been well documented, and recently this modification
has been linked to cellular processes involving gene transcription
and heterochromatin assembly. However, the existence of arginine
methylation on histones has remained unclear. Recent discoveries
of protein arginine methyltransferases, CARM1 and PRMT1, as transcriptional
coactivators for nuclear receptors suggest that histones may be physiological
targets of these enzymes as part of a poorly defined transcriptional
activation pathway. Here we show by using mass spectrometry that
histone H4, isolated from asynchronously growing human 293T cells,
is methylated at arginine 3 (Arg-3) in vivo. In support, a novel
antibody directed against histone H4 methylated at Arg-3 independently
demonstrates the in vivo occurrence of this modification and reveals
that H4 Arg-3 methylation is highly conserved throughout eukaryotes.
Finally, we show that PRMT1 is the major, if not exclusive, H4 Arg-3
methyltransfase in human 293T cells. These findings suggest a role
for arginine methylation of histones in the transcription process.},
institution = {Department of Biochemistry and Molecular Genetics, University of
Virginia Health Science Center, Charlottesville, VA 22908, USA.},
keywords = {Amino Acid Motifs; Animals; Arginine, metabolism; Cell Line; Genes,
Reporter; Histones, metabolism; Humans; Immunoblotting; Methylation;
Protein-Arginine N-Methyltransferases, metabolism; Recombinant Fusion
Proteins, genetics/metabolism},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {S0960-9822(01)00294-9},
pmid = {11448779},
timestamp = {2010.11.23}
}
@article{Strahl2002Set2,
author = {Brian D Strahl and Patrick A Grant and Scott D Briggs and Zu-Wen
Sun and James R Bone and Jennifer A Caldwell and Sahana Mollah and
Richard G Cook and Jeffrey Shabanowitz and Donald F Hunt and C. David
Allis},
title = {Set2 is a nucleosomal histone H3-selective methyltransferase that
mediates transcriptional repression.},
journal = {Mol Cell Biol},
year = {2002},
volume = {22},
pages = {1298--1306},
number = {5},
month = {Mar},
abstract = {Recent studies of histone methylation have yielded fundamental new
insights pertaining to the role of this modification in gene activation
as well as in gene silencing. While a number of methylation sites
are known to occur on histones, only limited information exists regarding
the relevant enzymes that mediate these methylation events. We thus
sought to identify native histone methyltransferase (HMT) activities
from Saccharomyces cerevisiae. Here, we describe the biochemical
purification and characterization of Set2, a novel HMT that is site-specific
for lysine 36 (Lys36) of the H3 tail. Using an antiserum directed
against Lys36 methylation in H3, we show that Set2, via its SET domain,
is responsible for methylation at this site in vivo. Tethering of
Set2 to a heterologous promoter reveals that Set2 represses transcription,
and part of this repression is mediated through the HMT activity
of the SET domain. These results suggest that Set2 and methylation
at H3 Lys36 play a role in the repression of gene transcription.},
institution = {Department of Biochemistry and Molecular Genetics,University of Virginia
Health System, University of Virginia, Charlottesville, Virginia
22908, USA.},
keywords = {Amino Acid Sequence; Gene Expression Regulation, Fungal; Histones,
metabolism; Methyltransferases, metabolism; Molecular Sequence Data;
Nucleosomes, enzymology; Saccharomyces cerevisiae Proteins, metabolism;
Saccharomyces cerevisiae, enzymology/genetics; Substrate Specificity;
Transcription, Genetic; Transcriptional Activation},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pmid = {11839797},
timestamp = {2010.11.23}
}
@article{Strahl1999Methylation,
author = {B. D. Strahl and R. Ohba and R. G. Cook and C. D. Allis},
title = {Methylation of histone H3 at lysine 4 is highly conserved and correlates
with transcriptionally active nuclei in Tetrahymena.},
journal = {Proc Natl Acad Sci U S A},
year = {1999},
volume = {96},
pages = {14967--14972},
number = {26},
month = {Dec},
abstract = {Studies into posttranslational modifications of histones, notably
acetylation, have yielded important insights into the dynamic nature
of chromatin structure and its fundamental role in gene expression.
The roles of other covalent histone modifications remain poorly understood.
To gain further insight into histone methylation, we investigated
its occurrence and pattern of site utilization in Tetrahymena, yeast,
and human HeLa cells. In Tetrahymena, transcriptionally active macronuclei,
but not transcriptionally inert micronuclei, contain a robust histone
methyltransferase activity that is highly selective for H3. Microsequence
analyses of H3 from Tetrahymena, yeast, and HeLa cells indicate that
lysine 4 is a highly conserved site of methylation, which to date,
is the major site detected in Tetrahymena and yeast. These data document
a nonrandom pattern of H3 methylation that does not overlap with
known acetylation sites in this histone. In as much as H3 methylation
at lysine 4 appears to be specific to macronuclei in Tetrahymena,
we suggest that this modification pattern plays a facilitatory role
in the transcription process in a manner that remains to be determined.
Consistent with this possibility, H3 methylation in yeast occurs
preferentially in a subpopulation of H3 that is preferentially acetylated.},
institution = {Department of Biochemistry, University of Virginia Health Science
Center, Charlottesville, VA 22908, USA.},
keywords = {Acetyltransferases, metabolism; Amino Acid Sequence; Animals; Cell
Nucleus, metabolism; Hela Cells; Histone Acetyltransferases; Histone-Lysine
N-Methyltransferase; Histones, metabolism; Humans; Lysine, analogs
/&/ derivatives/metabolism; Methylation; Methyltransferases, metabolism;
Molecular Sequence Data; Protein Methyltransferases; Protein Processing,
Post-Translational; Saccharomyces cerevisiae Proteins; Species Specificity;
Tetrahymena thermophila; Transcription, Genetic; Yeasts},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pmid = {10611321},
timestamp = {2010.11.23}
}
@article{Sturn2002Genesis:,
author = {Alexander Sturn and John Quackenbush and Zlatko Trajanoski},
title = {Genesis: cluster analysis of microarray data.},
journal = {Bioinformatics},
year = {2002},
volume = {18},
pages = {207-8},
number = {1},
month = {Jan},
abstract = {A versatile, platform independent and easy to use {J}ava suite for
large-scale gene expression analysis was developed. {G}enesis integrates
various tools for microarray data analysis such as filters, normalization
and visualization tools, distance measures as well as common clustering
algorithms including hierarchical clustering, self-organizing maps,
k-means, principal component analysis, and support vector machines.
{T}he results of the clustering are transparent across all implemented
methods and enable the analysis of the outcome of different algorithms
and parameters. {A}dditionally, mapping of gene expression data onto
chromosomal sequences was implemented to enhance promoter analysis
and investigation of transcriptional control mechanisms.},
keywords = {Algorithms, Artificial Intelligence, Cluster Analysis, Comparative
Study, Computational Biology, Databases, Gene Expression Profiling,
Genetic, Models, Molecular Structure, Neural Networks (Computer),
Non-U.S. Gov't, Oligonucleotide Array Sequence Analysis, Principal
Component Analysis, Programming Languages, Promoter Regions (Genetics),
Protein, Proteins, Research Support, Software, Statistical, Transcription,
11836235}
}
@article{Sun2004protein,
author = {Zhenghong Sun and Xiaoli Fu and Lu Zhang and Xiaoli Yang and Feizhou
Liu and Gengxi Hu},
title = {A protein chip system for parallel analysis of multi-tumor markers
and its application in cancer detection.},
journal = {Anticancer {R}es},
year = {2004},
volume = {24},
pages = {1159-65},
number = {2C},
abstract = {B{ACKGROUND}: {T}umor markers are routinely measured in clinical oncology.
{H}owever, their value in cancer detection has been controversial
largely because no single tumor marker is sensitive and specific
enough to meet strict diagnostic criteria. {O}ne strategy to overcome
the shortcomings of single tumor markers is to measure a combination
of tumor markers to increase sensitivity and look for distinct patterns
to increase specificity. {T}his study aimed to develop a system for
parallel detection of tumor markers as a tool for tumor detection
in both cancer patients and asymptomatic populations at high risk.
{MATERIALS} {AND} {METHODS}: {A} protein chip was fabricated with
twelve monoclonal antibodies against the following tumor markers
respectively: {CA}125, {CA}15-3, {CA}19-9, {CA}242, {CEA}, {AFP},
{PSA}, free-{PSA}, {HGH}, beta-{HCG}, {NSE} and ferritin. {T}umor
markers were captured after the protein chip was incubated with serum
samples. {A} secondary antibody conjugated with {HRP} was used to
detect the captured tumor markers using chemiluminescence technique.
{Q}uantification of the tumor markers was obtained after calibration
with standard curves. {RESULTS}: {T}he chip system showed an overall
sensitivity of 68.18\% after testing 1147 cancer patients, with high
sensitivities for liver, pancreas and ovarian tumors and low sensitivities
for gastrointestinal tumors, and a specificity of 97.1\% after testing
793 healthy individuals. {A}pplication of the chip system in physical
checkups of 15,867 individuals resulted in 16 cases that were subsequently
confirmed as having cancers. {A}nalysis of the detection results
with a {S}upport {V}ector {M}achine algorithm considerably increased
the specificity of the system as reflected in healthy individuals
and hepatitis/cirrhosis patients, but only modestly decreased the
sensitivity for cancer patients. {CONCLUSION}: {T}his protein chip
system is a potential tool for assisting cancer diagnosis and for
screening cancer in high-risk populations.},
keywords = {Antibodies, Artificial Intelligence, Biological, Calibration, Female,
Horseradish Peroxidase, Humans, Male, Monoclonal, Neoplasms, Protein
Array Analysis, Sensitivity and Specificity, Tumor Markers, 15154641}
}
@article{Surgand2006chemogenomic,
author = {Jean-Sebastien Surgand and Jordi Rodrigo and Esther Kellenberger
and Didier Rognan},
title = {A chemogenomic analysis of the transmembrane binding cavity of human
G-protein-coupled receptors.},
journal = {Proteins},
year = {2006},
volume = {62},
pages = {509--538},
number = {2},
month = {Feb},
abstract = {The amino acid sequences of 369 human nonolfactory G-protein-coupled
receptors (GPCRs) have been aligned at the seven transmembrane domain
(TM) and used to extract the nature of 30 critical residues supposed--from
the X-ray structure of bovine rhodopsin bound to retinal--to line
the TM binding cavity of ground-state receptors. Interestingly, the
clustering of human GPCRs from these 30 residues mirrors the recently
described phylogenetic tree of full-sequence human GPCRs (Fredriksson
et al., Mol Pharmacol 2003;63:1256-1272) with few exceptions. A TM
cavity could be found for all investigated GPCRs with physicochemical
properties matching that of their cognate ligands. The current approach
allows a very fast comparison of most human GPCRs from the focused
perspective of the predicted TM cavity and permits to easily detect
key residues that drive ligand selectivity or promiscuity.},
doi = {10.1002/prot.20768},
keywords = {Amino Acid Sequence; Binding Sites; Genomics; Humans; Ligands; Models,
Molecular; Phylogeny; Receptors, G-Protein-Coupled},
owner = {laurent},
pmid = {16294340},
timestamp = {2008.03.27},
url = {http://dx.doi.org/10.1002/prot.20768}
}
@article{Suter2008Two-hybrid,
author = {Bernhard Suter and Saranya Kittanakom and Igor Stagljar},
title = {Two-hybrid technologies in proteomics research.},
journal = {Curr Opin Biotechnol},
year = {2008},
volume = {19},
pages = {316--323},
number = {4},
month = {Aug},
abstract = {Given that protein-protein interactions (PPIs) regulate nearly every
living process; the exploration of global and pathway-specific protein
interaction networks is expected to have major implications in the
understanding of diseases and for drug discovery. Consequently, the
development and application of methodologies that address physical
associations among proteins is of major importance in today's proteomics
research. The most widely and successfully used methodology to assess
PPIs is the yeast two-hybrid system (YTH). Here we present an overview
on the current applications of YTH and variant technologies in yeast
and mammalian systems. Two-hybrid-based methods will not only continue
to have a dominant role in the assessment of protein interactomes
but will also become important in the development of novel compounds
that target protein interaction interfaces for therapeutic intervention.},
doi = {10.1016/j.copbio.2008.06.005},
institution = {Department of Biochemistry and Department of Molecular Genetics,
Terrence Donnelly Centre for Cellular and Biomolecular Research (DCCBR),
University of Toronto, 160 College Street, Toronto, ON M5S 3E1, Canada.},
keywords = {Animals; Drug Design; Mammals; Proteomics; Two-Hybrid System Techniques},
owner = {phupe},
pii = {S0958-1669(08)00075-X},
pmid = {18619540},
timestamp = {2010.08.31},
url = {http://dx.doi.org/10.1016/j.copbio.2008.06.005}
}
@article{Suykens2001Optimal,
author = {J. A. Suykens and J. Vandewalle and B. De Moor},
title = {Optimal control by least squares support vector machines.},
journal = {Neural {N}etw},
year = {2001},
volume = {14},
pages = {23-35},
number = {1},
month = {Jan},
abstract = {Support vector machines have been very successful in pattern recognition
and function estimation problems. {I}n this paper we introduce the
use of least squares support vector machines ({LS}-{SVM}'s) for the
optimal control of nonlinear systems. {L}inear and neural full static
state feedback controllers are considered. {T}he problem is formulated
in such a way that it incorporates the {N}-stage optimal control
problem as well as a least squares support vector machine approach
for mapping the state space into the action space. {T}he solution
is characterized by a set of nonlinear equations. {A}n alternative
formulation as a constrained nonlinear optimization problem in less
unknowns is given, together with a method for imposing local stability
in the {LS}-{SVM} control scheme. {T}he results are discussed for
support vector machines with radial basis function kernel. {A}dvantages
of {LS}-{SVM} control are that no number of hidden units has to be
determined for the controller and that no centers have to be specified
for the {G}aussian kernels when applying {M}ercer's condition. {T}he
curse of dimensionality is avoided in comparison with defining a
regular grid for the centers in classical radial basis function networks.
{T}his is at the expense of taking the trajectory of state variables
as additional unknowns in the optimization problem, while classical
neural network approaches typically lead to parametric optimization
problems. {I}n the {SVM} methodology the number of unknowns equals
the number of training data, while in the primal space the number
of unknowns can be infinite dimensional. {T}he method is illustrated
both on stabilization and tracking problems including examples on
swinging up an inverted pendulum with local stabilization at the
endpoint and a tracking problem for a ball and beam system.},
keywords = {Acute, Acute Disease, Adenocarcinoma, Algorithms, Amino Acid Sequence,
Artificial Intelligence, Automated, B-Lymphocytes, Bacterial Proteins,
Base Pair Mismatch, Base Sequence, Bayes Theorem, Binding Sites,
Biological, Bone Marrow Cells, Cell Compartmentation, Chemistry,
Child, Chromosome Aberrations, Comparative Study, Computational Biology,
Computer Simulation, Computer-Assisted, DNA, Data Interpretation,
Databases, Decision Trees, Diagnosis, Discriminant Analysis, Electric
Conductivity, Electrophysiology, Escherichia coli Proteins, Factual,
Feedback, Female, Fungal, Gastric Emptying, Gene Expression Profiling,
Gene Expression Regulation, Genes, Genetic, Genetic Markers, Hemolysins,
Humans, Ion Channels, Kinetics, Leukemia, Lipid Bilayers, Logistic
Models, Lymphocytic, Male, Markov Chains, Melanoma, Models, Molecular,
Myeloid, Neoplasm, Neoplastic, Neural Networks (Computer), Nevus,
Non-P.H.S., Non-U.S. Gov't, Nonlinear Dynamics, Normal Distribution,
Nucleic Acid Conformation, Organ Specificity, Organelles, P.H.S.,
Pattern Recognition, Physical, Pigmented, Predictive Value of Tests,
Promoter Regions (Genetics), Protein Folding, Protein Structure,
Proteins, Proteome, RNA, Reproducibility of Results, Research Support,
Saccharomyces cerevisiae, Secondary, Sensitivity and Specificity,
Sequence Alignment, Sex Characteristics, Skin Diseases, Skin Neoplasms,
Skin Pigmentation, Software, Statistical, Stomach Diseases, T-Lymphocytes,
Thermodynamics, Transcription, Transcription Factors, Tumor Markers,
U.S. Gov't, 11213211},
pii = {S0893608000000770}
}
@article{Takahashi2003Proteomic,
author = {Nobuhiro Takahashi and Mitsuaki Yanagida and Sally Fujiyama and Toshiya
Hayano and Toshiaki Isobe},
title = {Proteomic snapshot analyses of preribosomal ribonucleoprotein complexes
formed at various stages of ribosome biogenesis in yeast and mammalian
cells.},
journal = {Mass {S}pectrom {R}ev},
year = {2003},
volume = {22},
pages = {287-317},
number = {5},
abstract = {Proteomic technologies powered by advancements in mass spectrometry
and bioinformatics and coupled with accumulated genome sequence data
allow a comprehensive study of cell function through large-scale
and systematic protein identifications of protein constituents of
the cell and tissues, as well as of multi-protein complexes that
carry out many cellular function in a higher-order network in the
cell. {O}ne of the most extensively analyzed cellular functions by
proteomics is the production of ribosome, the protein-synthesis machinery,
in the nucle(ol)us--the main site of ribosome biogenesis. {T}he use
of tagged proteins as affinity bait, coupled with mass spectrometric
identification, enabled us to isolate synthetic intermediates of
ribosomes that might represent snapshots of nascent ribosomes at
particular stages of ribosome biogenesis and to identify their constituents--some
of which showed dynamic changes for association with the intermediates
at various stages of ribosome biogenesis. {I}n this review, in conjunction
with the results from yeast cells, our proteomic approach to analyze
ribosome biogenesis in mammalian cells is described.},
doi = {10.1002/mas.10057},
pdf = {../local/Takahashi2003Proteomic.pdf},
file = {Takahashi2003Proteomic.pdf:local/Takahashi2003Proteomic.pdf:PDF},
keywords = {Affinity Labels, Animals, Comparative Study, Electrospray Ionization,
Genetic, Macromolecular Substances, Mass, Mitosis, Non-P.H.S., Non-U.S.
Gov't, P.H.S., Protein Interaction Mapping, Proteome, Proteomics,
Research Support, Ribonucleoproteins, Ribosomes, Saccharomyces cerevisiae,
Saccharomyces cerevisiae Proteins, Signal Transduction, Spectrometry,
Transcription, U.S. Gov't, 12949916},
owner = {vert},
url = {http://dx.doi.org/10.1002/mas.10057}
}
@article{Taylor2008Guidelines,
author = {Chris F Taylor and Pierre-Alain Binz and Ruedi Aebersold and Michel
Affolter and Robert Barkovich and Eric W Deutsch and David M Horn
and Andreas Hühmer and Martin Kussmann and Kathryn Lilley and Marcus
Macht and Matthias Mann and Dieter Müller and Thomas A Neubert and
Janice Nickson and Scott D Patterson and Roberto Raso and Kathryn
Resing and Sean L Seymour and Akira Tsugita and Ioannis Xenarios
and Rong Zeng and Randall K Julian},
title = {Guidelines for reporting the use of mass spectrometry in proteomics.},
journal = {Nat Biotechnol},
year = {2008},
volume = {26},
pages = {860--861},
number = {8},
month = {Aug},
doi = {10.1038/nbt0808-860},
keywords = {Databases, Protein; Guidelines as Topic; Mass Spectrometry; Proteomics},
owner = {phupe},
pii = {nbt0808-860},
pmid = {18688232},
timestamp = {2010.08.13},
url = {http://dx.doi.org/10.1038/nbt0808-860}
}
@article{Taylor2007minimum,
author = {Chris F Taylor and Norman W Paton and Kathryn S Lilley and Pierre-Alain
Binz and Randall K Julian and Andrew R Jones and Weimin Zhu and Rolf
Apweiler and Ruedi Aebersold and Eric W Deutsch and Michael J Dunn
and Albert J R Heck and Alexander Leitner and Marcus Macht and Matthias
Mann and Lennart Martens and Thomas A Neubert and Scott D Patterson
and Peipei Ping and Sean L Seymour and Puneet Souda and Akira Tsugita
and Joel Vandekerckhove and Thomas M Vondriska and Julian P Whitelegge
and Marc R Wilkins and Ioannnis Xenarios and John R Yates and Henning
Hermjakob},
title = {The minimum information about a proteomics experiment (MIAPE).},
journal = {Nat Biotechnol},
year = {2007},
volume = {25},
pages = {887--893},
number = {8},
month = {Aug},
abstract = {Both the generation and the analysis of proteomics data are now widespread,
and high-throughput approaches are commonplace. Protocols continue
to increase in complexity as methods and technologies evolve and
diversify. To encourage the standardized collection, integration,
storage and dissemination of proteomics data, the Human Proteome
Organization's Proteomics Standards Initiative develops guidance
modules for reporting the use of techniques such as gel electrophoresis
and mass spectrometry. This paper describes the processes and principles
underpinning the development of these modules; discusses the ramifications
for various interest groups such as experimentalists, funders, publishers
and the private sector; addresses the issue of overlap with other
reporting guidelines; and highlights the criticality of appropriate
tools and resources in enabling 'MIAPE-compliant' reporting.},
doi = {10.1038/nbt1329},
institution = {The HUPO Proteomics Standards Initiative, Wellcome Trust Genome Campus,
Hinxton, Cambridgeshire CB10 1SD, UK. chris.taylor@ebi.ac.uk},
keywords = {Databases, Protein; Gene Expression Profiling; Genome, Human; Guidelines
as Topic; Humans; Information Storage and Retrieval; Internationality;
Proteomics; Research},
owner = {phupe},
pii = {nbt1329},
pmid = {17687369},
timestamp = {2010.08.13},
url = {http://dx.doi.org/10.1038/nbt1329}
}
@article{Terentiev2009Dynamic,
author = {A. A. Terentiev and N. T. Moldogazieva and K. V. Shaitan},
title = {Dynamic proteomics in modeling of the living cell. Protein-protein
interactions.},
journal = {Biochemistry (Mosc)},
year = {2009},
volume = {74},
pages = {1586--1607},
number = {13},
month = {Dec},
abstract = {This review is devoted to describing, summarizing, and analyzing of
dynamic proteomics data obtained over the last few years and concerning
the role of protein-protein interactions in modeling of the living
cell. Principles of modern high-throughput experimental methods for
investigation of protein-protein interactions are described. Systems
biology approaches based on integrative view on cellular processes
are used to analyze organization of protein interaction networks.
It is proposed that finding of some proteins in different protein
complexes can be explained by their multi-modular and polyfunctional
properties; the different protein modules can be located in the nodes
of protein interaction networks. Mathematical and computational approaches
to modeling of the living cell with emphasis on molecular dynamics
simulation are provided. The role of the network analysis in fundamental
medicine is also briefly reviewed.},
institution = {Russian State Medical University, ul. Ostrovityanova 1, Moscow, Russia.
aaterent@mtu-net.ru},
keywords = {Animals; Humans; Mass Spectrometry; Models, Theoretical; Molecular
Dynamics Simulation; Multiprotein Complexes; Protein Conformation;
Protein Interaction Mapping; Proteins; Proteomics; Systems Biology;
Two-Hybrid System Techniques},
owner = {phupe},
pii = {BCM74131586},
pmid = {20210711},
timestamp = {2010.08.31}
}
@article{Thukral2005Prediction,
author = {Sushil K Thukral and Paul J Nordone and Rong Hu and Leah Sullivan
and Eric Galambos and Vincent D Fitzpatrick and Laura Healy and Michael
B Bass and Mary E Cosenza and Cynthia A Afshari},
title = {Prediction of nephrotoxicant action and identification of candidate
toxicity-related biomarkers.},
journal = {Toxicol {P}athol},
year = {2005},
volume = {33},
pages = {343-55},
number = {3},
abstract = {A vast majority of pharmacological compounds and their metabolites
are excreted via the urine, and within the complex structure of the
kidney,the proximal tubules are a main target site of nephrotoxic
compounds. {W}e used the model nephrotoxicants mercuric chloride,
2-bromoethylamine hydrobromide, hexachlorobutadiene, mitomycin, amphotericin,
and puromycin to elucidate time- and dose-dependent global gene expression
changes associated with proximal tubular toxicity. {M}ale {S}prague-{D}awley
rats were dosed via intraperitoneal injection once daily for mercuric
chloride and amphotericin (up to 7 doses), while a single dose was
given for all other compounds. {A}nimals were exposed to 2 different
doses of these compounds and kidney tissues were collected on day
1, 3, and 7 postdosing. {G}ene expression profiles were generated
from kidney {RNA} using 17{K} rat c{DNA} dual dye microarray and
analyzed in conjunction with histopathology. {A}nalysis of gene expression
profiles showed that the profiles clustered based on similarities
in the severity and type of pathology of individual animals. {F}urther,
the expression changes were indicative of tubular toxicity showing
hallmarks of tubular degeneration/regeneration and necrosis. {U}se
of gene expression data in predicting the type of nephrotoxicity
was then tested with a support vector machine ({SVM})-based approach.
{A} {SVM} prediction module was trained using 120 profiles of total
profiles divided into four classes based on the severity of pathology
and clustering. {A}lthough mitomycin {C} and amphotericin {B} treatments
did not cause toxicity, their expression profiles were included in
the {SVM} prediction module to increase the sample size. {U}sing
this classifier, the {SVM} predicted the type of pathology of 28
test profiles with 100\% selectivity and 82\% sensitivity. {T}hese
data indicate that valid predictions could be made based on gene
expression changes from a small set of expression profiles. {A} set
of potential biomarkers showing a time- and dose-response with respect
to the progression of proximal tubular toxicity were identified.
{T}hese include several transporters ({S}lc21a2, {S}lc15, {S}lc34a2),
{K}im 1, {IGF}bp-1, osteopontin, alpha-fibrinogen, and {G}stalpha.},
doi = {10.1080/01926230590927230},
keywords = {Algorithms, Animals, Antibiotics, Antineoplastic, Artificial Intelligence,
Butadienes, Chloroplasts, Comparative Study, Computer Simulation,
Computer-Assisted, Diagnosis, Disinfectants, Dose-Response Relationship,
Drug, Drug Toxicity, Electrodes, Electroencephalography, Ethylamines,
Expert Systems, Feedback, Fungicides, Gene Expression Profiling,
Genes, Genetic Markers, Humans, Implanted, Industrial, Information
Storage and Retrieval, Kidney, Kidney Tubules, MEDLINE, Male, Mercuric
Chloride, Microarray Analysis, Molecular Biology, Motor Cortex, Movement,
Natural Language Processing, Neural Networks (Computer), Non-P.H.S.,
Non-U.S. Gov't, Plant Proteins, Predictive Value of Tests, Proteins,
Proteome, Proximal, Puromycin Aminonucleoside, Rats, Reproducibility
of Results, Research Support, Sprague-Dawley, Subcellular Fractions,
Terminology, Therapy, Time Factors, Toxicogenetics, U.S. Gov't, User-Computer
Interface, 15805072},
pii = {X3U2206L2747H31G},
url = {http://dx.doi.org/10.1080/01926230590927230}
}
@article{Tomizaki2010Protein,
author = {{Kin-ya} Tomizaki and Kenji Usui and Hisakazu Mihara},
title = {Protein-protein interactions and selection: array-based techniques
for screening disease-associated biomarkers in predictive/early diagnosis.},
journal = {FEBS J},
year = {2010},
volume = {277},
pages = {1996--2005},
number = {9},
month = {May},
abstract = {There has been considerable interest in recent years in the development
of miniaturized and parallelized array technology for protein-protein
interaction analysis and protein profiling, namely 'protein-detecting
microarrays'. Protein-detecting microarrays utilize a wide variety
of capture agents (antibodies, fusion proteins, DNA/RNA aptamers,
synthetic peptides, carbohydrates, and small molecules) immobilized
at high spatial density on a solid surface. Each capture agent binds
selectively to its target protein in a complex mixture, such as serum
or cell lysate samples. Captured proteins are subsequently detected
and quantified in a high-throughput fashion, with minimal sample
consumption. Protein-detecting microarrays were first described by
MacBeath and Schreiber in 2000, and the number of publications involving
this technology is rapidly increasing. Furthermore, the first multiplex
immunoassay systems have been cleared by the US Food and Drug Administration,
signaling recognition of the usefulness of miniaturized and parallelized
array technology for protein detection in predictive/early diagnosis.
Although genetic tests still predominate, with further development
protein-based diagnosis will become common in clinical use within
a few years.},
doi = {10.1111/j.1742-4658.2010.07626.x},
institution = {Innovative Materials and Processing Research Center and Department
of Materials Chemistry, Ryukoku University, Otsu, Japan.},
keywords = {Animals; Biological Markers, analysis/metabolism; Early Diagnosis;
Humans; Mass Screening, methods; Protein Array Analysis, methods;
Proteins, analysis/metabolism; Risk Factors},
language = {eng},
medline-pst = {ppublish},
owner = {philippe},
pii = {EJB7626},
pmid = {20412053},
timestamp = {2010.07.28},
url = {http://dx.doi.org/10.1111/j.1742-4658.2010.07626.x}
}
@article{Topiol2009X-ray,
author = {Sid Topiol and Michael Sabio},
title = {X-ray structure breakthroughs in the {GPCR} transmembrane region.},
journal = {Biochem Pharmacol},
year = {2009},
volume = {78},
pages = {11--20},
number = {1},
month = {Jul},
abstract = {G-protein-coupled receptor (GPCR) proteins [Lundstrom KH, Chiu ML,
editors. G protein-coupled receptors in drug discovery. CRC Press;
2006] are the single largest drug target, representing 25-50\% of
marketed drugs [Overington JP, Al-Lazikani B, Hopkins AL. How many
drug targets are there? Nat Rev Drug Discov 2006;5(12):993-6; Parrill
AL. Crystal structures of a second G protein-coupled receptor: triumphs
and implications. ChemMedChem 2008;3:1021-3]. While there are six
subclasses of GPCR proteins, the hallmark of all GPCR proteins is
the transmembrane-spanning region. The general architecture of this
transmembrane (TM) region has been known for some time to contain
seven alpha-helices. From a drug discovery and design perspective,
structural information of the GPCRs has been sought as a tool for
structure-based drug design. The advances in the past decade of technologies
for structure-based design have proven to be useful in a number of
areas. Invoking these approaches for GPCR targets has remained challenging.
Until recently, the most closely related structures available for
GPCR modeling have been those of bovine rhodopsin. While a representative
of class A GPCRs, bovine rhodopsin is not a ligand-activated GPCR
and is fairly distant in sequence homology to other class A GPCRs.
Thus, there is a variable degree of uncertainty in the use of the
rhodopsin X-ray structure as a template for homology modeling of
other GPCR targets. Recent publications of X-ray structures of class
A GPCRs now offer the opportunity to better understand the molecular
mechanism of action at the atomic level, to deploy X-ray structures
directly for their use in structure-based design, and to provide
more promising templates for many other ligand-mediated GPCRs. We
summarize herein some of the recent findings in this area and provide
an initial perspective of the emerging opportunities, possible limitations,
and remaining questions. Other aspects of the recent X-ray structures
are described by Weis and Kobilka [Weis WI, Kobilka BK. Structural
insights into G-protein-coupled receptor activation. Curr Opin Struct
Biol 2008;18:734-40] and Mustafi and Palczewski [Mustafi D, Palczewski
K. Topology of class A G protein-coupled receptors: insights gained
from crystal structures of rhodopsins, adrenergic and adenosine receptors.
Mol Pharmacol 2009;75:1-12].},
doi = {10.1016/j.bcp.2009.02.012},
institution = {Department of Computational Chemistry, Lundbeck Research USA, Inc.,
215 College Road, Paramus, NJ 07652, USA.},
keywords = {Animals; Cell Membrane; Humans; Models, Molecular; Molecular Conformation;
Pindolol; Propanolamines; Protein Conformation; Receptor, Adenosine
A2A; Receptors, Adrenergic, beta-2; Receptors, G-Protein-Coupled;
Retinaldehyde; Rhodopsin; X-Ray Diffraction},
owner = {ljacob},
pii = {S0006-2952(09)00113-0},
pmid = {19447219},
timestamp = {2009.11.09},
url = {http://dx.doi.org/10.1016/j.bcp.2009.02.012}
}
@article{Tucker2002Gene,
author = {Tucker, D. L. and Tucker, N. and Conway, T.},
title = {Gene expression profiling of the pH response in Escherichia coli.},
journal = {J Bacteriol.},
year = {2002},
volume = {184},
pages = {6551--6558},
number = {23},
month = {Dec},
abstract = {Escherichia coli MG1655 acid-inducible genes were identified by whole-genome
expression profiling. Cultures were grown to the mid-logarithmic
phase on acidified glucose minimal medium, conditions that induce
glutamate-dependent acid resistance (AR), while the other AR systems
are either repressed or not induced. A total of 28 genes were induced
in at least two of three experiments in which the gene expression
profiles of cells grown in acid (pH 5.5 or 4.5) were compared to
those of cells grown at pH 7.4. As expected, the genes encoding glutamate
decarboxylase, gadA and gadB, were significantly induced. Interestingly,
two acid-inducible genes code for small basic proteins with pIs of
>10.5, and six code for small acidic proteins with pIs ranging from
5.7 to 4.0; the roles of these small basic and acidic proteins in
acid resistance are unknown. The acid-induced genes represented only
five functional grouping categories, including eight genes involved
in metabolism, nine associated with cell envelope structures or modifications,
two encoding chaperones, six regulatory genes, and six unknown genes.
It is unlikely that all of these genes are involved in the glutamate-dependent
AR. However, nine acid-inducible genes are clustered in the gadA
region, including hdeA, which encodes a putative periplasmic chaperone,
and four putative regulatory genes. One of these putative regulators,
yhiE, was shown to significantly increase acid resistance when overexpressed
in cells that had not been preinduced by growth at pH 5.5, and mutation
of yhiE decreased acid resistance; yhiE could therefore encode an
activator of AR genes. Thus, the acid-inducible genes clustered in
the gadA region appear to be involved in glutatmate-dependent acid
resistance, although their specific roles remain to be elucidated.},
institution = {Advanced Center for Genome Technology, The University of Oklahoma,
Norman, Oklahoma 73069-0245, USA.},
keywords = {Culture Media; Escherichia coli; Escherichia coli Proteins; Gene Expression
Profiling; Gene Expression Regulation, Bacterial; Heat-Shock Response;
Hydrogen-Ion Concentration; Morpholines; Oligonucleotide Array Sequence
Analysis},
owner = {fantine},
pmid = {12426343},
timestamp = {2008.02.11}
}
@article{Tung2007POPI:,
author = {Chun-Wei Tung and Shinn-Ying Ho},
title = {POPI: predicting immunogenicity of MHC class I binding peptides by
mining informative physicochemical properties.},
journal = {Bioinformatics},
year = {2007},
volume = {23},
pages = {942--949},
number = {8},
month = {Apr},
abstract = {MOTIVATION: Both modeling of antigen-processing pathway including
major histocompatibility complex (MHC) binding and immunogenicity
prediction of those MHC-binding peptides are essential to develop
a computer-aided system of peptide-based vaccine design that is one
goal of immunoinformatics. Numerous studies have dealt with modeling
the immunogenic pathway but not the intractable problem of immunogenicity
prediction due to complex effects of many intrinsic and extrinsic
factors. Moderate affinity of the MHC-peptide complex is essential
to induce immune responses, but the relationship between the affinity
and peptide immunogenicity is too weak to use for predicting immunogenicity.
This study focuses on mining informative physicochemical properties
from known experimental immunogenicity data to understand immune
responses and predict immunogenicity of MHC-binding peptides accurately.
RESULTS: This study proposes a computational method to mine a feature
set of informative physicochemical properties from MHC class I binding
peptides to design a support vector machine (SVM) based system (named
POPI) for the prediction of peptide immunogenicity. High performance
of POPI arises mainly from an inheritable bi-objective genetic algorithm,
which aims to automatically determine the best number m out of 531
physicochemical properties, identify these m properties and tune
SVM parameters simultaneously. The dataset consisting of 428 human
MHC class I binding peptides belonging to four classes of immunogenicity
was established from MHCPEP, a database of MHC-binding peptides (Brusic
et al., 1998). POPI, utilizing the m = 23 selected properties, performs
well with the accuracy of 64.72\% using leave-one-out cross-validation,
compared with two sequence alignment-based prediction methods ALIGN
(54.91\%) and PSI-BLAST (53.23\%). POPI is the first computational
system for prediction of peptide immunogenicity based on physicochemical
properties. AVAILABILITY: A web server for prediction of peptide
immunogenicity (POPI) and the used dataset of MHC class I binding
peptides (PEPMHCI) are available at http://iclab.life.nctu.edu.tw/POPI},
doi = {10.1093/bioinformatics/btm061},
keywords = {Algorithms; Artificial Intelligence; Binding Sites; Epitope Mapping;
Histocompatibility Antigens Class I; Oligopeptides; Pattern Recognition,
Automated; Protein Binding; Software; Structure-Activity Relationship},
owner = {laurent},
pii = {btm061},
pmid = {17384427},
timestamp = {2007.07.12},
url = {http://dx.doi.org/10.1093/bioinformatics/btm061}
}
@article{Tzeng2004Predicting,
author = {Huey-Ming Tzeng and Jer-Guang Hsieh and Yih-Lon Lin},
title = {Predicting nurses' intention to quit with a support vector machine:
a new approach to set up an early warning mechanism in human resource
management.},
journal = {Comput {I}nform {N}urs},
year = {2004},
volume = {22},
pages = {232-42},
number = {4},
abstract = {This project developed a {S}upport {V}ector {M}achine for predicting
nurses' intention to quit, using working motivation, job satisfaction,
and stress levels as predictors. {T}his study was conducted in three
hospitals located in southern {T}aiwan. {T}he target population was
all nurses (389 valid cases). {F}or cross-validation, we randomly
split cases into four groups of approximately equal sizes, and performed
four training runs. {A}fter the training, the average percentage
of misclassification on the training data was 0.86, while that on
the testing data was 10.8, resulting in predictions with 89.2\% accuracy.
{T}his {S}upport {V}ector {M}achine can predict nurses' intention
to quit, without asking these nurses whether they have an intention
to quit.},
keywords = {Adolescent, Adult, Algorithms, Amino Acid Sequence, Amino Acids, Anatomic,
Attitude of Health Personnel, Bacterial Proteins, Bias (Epidemiology),
Brain, Brain Mapping, Burnout, Comparative Study, Computer Simulation,
Computer-Assisted, Data Interpretation, Diffusion Magnetic Resonance
Imaging, Facial Asymmetry, Facial Expression, Facial Paralysis, Female,
Gene Expression Profiling, Gram-Negative Bacteria, Gram-Positive
Bacteria, Hospital, Humans, Image Interpretation, Intention, Job
Satisfaction, Logistic Models, Magnetoencephalography, Male, Middle
Aged, Models, Motion, Neural Networks (Computer), Neural Pathways,
Non-U.S. Gov't, Nonlinear Dynamics, Nursing Administration Research,
Nursing Staff, Personnel Management, Personnel Turnover, Photography,
Predictive Value of Tests, Professional, Protein, Proteins, Proteome,
Psychological, Questionnaires, Regression Analysis, Reproducibility
of Results, Research Support, Retina, Risk Factors, Sequence Alignment,
Sequence Analysis, Severity of Illness Index, Software, Statistical,
Subcellular Fractions, Taiwan, Theoretical, Workplace, 15494654},
pii = {00024665-200407000-00012}
}
@article{Valentini2007Mosclust:,
author = {Giorgio Valentini},
title = {Mosclust: a software library for discovering significant structures
in bio-molecular data.},
journal = {Bioinformatics},
year = {2007},
volume = {23},
pages = {387--389},
number = {3},
month = {Feb},
abstract = {The R package mosclust (model order selection for clustering problems)
implements algorithms based on the concept of stability for discovering
significant structures in bio-molecular data. The software library
provides stability indices obtained through different data perturbations
methods (resampling, random projections, noise injection), as well
as statistical tests to assess the significance of multi-level structures
singled out from the data. Availability: http://homes.dsi.unimi.it/~valenti/SW/mosclust/download/mosclust_1.0.tar.gz.
Supplementary information: http://homes.dsi.unimi.it/~valenti/SW/mosclust.},
doi = {10.1093/bioinformatics/btl600},
institution = {DSI, Dipartimento di Scienze dell'Informazione, Università degli
Studi di Milano, Via Comelico 39, Italy. valentini@dsi.unimi.it},
keywords = {Algorithms; Artificial Intelligence; Cluster Analysis; Gene Expression
Profiling, methods; Oligonucleotide Array Sequence Analysis, methods;
Pattern Recognition, Automated, methods; Programming Languages; Proteome,
metabolism; Signal Transduction, physiology; Software},
language = {eng},
medline-pst = {ppublish},
owner = {philippe},
pii = {btl600},
pmid = {17127677},
timestamp = {2011.05.14},
url = {http://dx.doi.org/10.1093/bioinformatics/btl600}
}
@article{Vallabhaneni2004Motor,
author = {Anirudh Vallabhaneni and Bin He},
title = {Motor imagery task classification for brain computer interface applications
using spatiotemporal principle component analysis.},
journal = {Neurol {R}es},
year = {2004},
volume = {26},
pages = {282-7},
number = {3},
month = {Apr},
abstract = {Classification of single-trial imagined left- and right-hand movements
recorded through scalp {EEG} are explored in this study. {C}lassical
event-related desynchronization/synchronization ({ERD}/{ERS}) calculation
approach was utilized to extract {ERD} features from the raw scalp
{EEG} signal. {P}rinciple {C}omponent {A}nalysis ({PCA}) was used
for feature extraction and applied on spatial, as well as temporal
dimensions in two consecutive steps. {A} {S}upport {V}ector {M}achine
({SVM}) classifier using a linear decision function was used to classify
each trial as either left or right. {T}he present approach has yielded
good classification results and promises to have potential for further
refinement for increased accuracy as well as application in online
brain computer interface ({BCI}).},
doi = {10.1179/016164104225013950},
keywords = {Amino Acids, Antibodies, Artificial Intelligence, Biological, Brain,
Brain Mapping, Calibration, Comparative Study, Computational Biology,
Cysteine, Cystine, Electrodes, Electroencephalography, Evoked Potentials,
Female, Horseradish Peroxidase, Humans, Imagery (Psychotherapy),
Imagination, Laterality, Male, Monoclonal, Movement, Neoplasms, Non-P.H.S.,
Non-U.S. Gov't, P.H.S., Perception, Principal Component Analysis,
Protein, Protein Array Analysis, Proteins, Research Support, Sensitivity
and Specificity, Sequence Analysis, Tumor Markers, U.S. Gov't, User-Computer
Interface, 15142321},
url = {http://dx.doi.org/10.1179/016164104225013950}
}
@article{Vanunu2010Associating,
author = {Vanunu, O. and Magger, O. and Ruppin, E. and Shlomi, T. and Sharan,
R.},
title = {Associating genes and protein complexes with disease via network
propagation.},
journal = {PLoS Comput. Biol.},
year = {2010},
volume = {6},
pages = {e1000641},
number = {1},
month = {Jan},
abstract = {A fundamental challenge in human health is the identification of disease-causing
genes. Recently, several studies have tackled this challenge via
a network-based approach, motivated by the observation that genes
causing the same or similar diseases tend to lie close to one another
in a network of protein-protein or functional interactions. However,
most of these approaches use only local network information in the
inference process and are restricted to inferring single gene associations.
Here, we provide a global, network-based method for prioritizing
disease genes and inferring protein complex associations, which we
call PRINCE. The method is based on formulating constraints on the
prioritization function that relate to its smoothness over the network
and usage of prior information. We exploit this function to predict
not only genes but also protein complex associations with a disease
of interest. We test our method on gene-disease association data,
evaluating both the prioritization achieved and the protein complexes
inferred. We show that our method outperforms extant approaches in
both tasks. Using data on 1,369 diseases from the OMIM knowledgebase,
our method is able (in a cross validation setting) to rank the true
causal gene first for 34\% of the diseases, and infer 139 disease-related
complexes that are highly coherent in terms of the function, expression
and conservation of their member proteins. Importantly, we apply
our method to study three multi-factorial diseases for which some
causal genes have been found already: prostate cancer, alzheimer
and type 2 diabetes mellitus. PRINCE's predictions for these diseases
highly match the known literature, suggesting several novel causal
genes and protein complexes for further investigation.},
doi = {10.1371/journal.pcbi.1000641},
institution = {School of Computer Science, Tel-Aviv University, Tel-Aviv, Israel.},
keywords = {Algorithms; Alzheimer Disease; Databases, Genetic; Diabetes Mellitus;
Disease; Genes; Humans; Male; Multiprotein Complexes; Prostatic Neoplasms;
Protein Interaction Mapping; Proteins; Reproducibility of Results},
owner = {mordelet},
pmid = {20090828},
timestamp = {2010.09.27},
url = {http://dx.doi.org/10.1371/journal.pcbi.1000641}
}
@unpublished{Vazquez2001Modeling,
author = {Vazquez, A. and Flammini, A. and Maritan, A. and Vespignani, A.},
title = {Modeling of protein interaction networks},
note = {E-print cond-mat/0108043},
month = {Aug},
year = {2001},
pdf = {../local/vazq01.pdf},
file = {vazq01.pdf:local/vazq01.pdf:PDF},
subject = {bionetprot},
url = {http://xxx.lanl.gov/abs/cond-mat/0108043}
}
@article{Vercoutere2001Rapid,
author = {W. Vercoutere and S. Winters-Hilt and H. Olsen and D. Deamer and
D. Haussler and M. Akeson},
title = {Rapid discrimination among individual {DNA} hairpin molecules at
single-nucleotide resolution using an ion channel.},
journal = {Nat {B}iotechnol},
year = {2001},
volume = {19},
pages = {248-52},
number = {3},
month = {Mar},
abstract = {R{NA} and {DNA} strands produce ionic current signatures when driven
through an alpha-hemolysin channel by an applied voltage. {H}ere
we combine this nanopore detector with a support vector machine ({SVM})
to analyze {DNA} hairpin molecules on the millisecond time scale.
{M}easurable properties include duplex stem length, base pair mismatches,
and loop length. {T}his nanopore instrument can discriminate between
individual {DNA} hairpins that differ by one base pair or by one
nucleotide.},
doi = {10.1038/85696},
pdf = {../local/Vercoutere2001Rapid.pdf},
file = {Vercoutere2001Rapid.pdf:local/Vercoutere2001Rapid.pdf:PDF},
keywords = {Acute, Acute Disease, Adenocarcinoma, Algorithms, Amino Acid Sequence,
Artificial Intelligence, Automated, B-Lymphocytes, Bacterial Proteins,
Base Pair Mismatch, Base Sequence, Bayes Theorem, Binding Sites,
Biological, Bone Marrow Cells, Cell Compartmentation, Chemistry,
Child, Chromosome Aberrations, Comparative Study, Computational Biology,
Computer Simulation, Computer-Assisted, DNA, Data Interpretation,
Databases, Decision Trees, Diagnosis, Discriminant Analysis, Electric
Conductivity, Electrophysiology, Escherichia coli Proteins, Factual,
Female, Fungal, Gastric Emptying, Gene Expression Profiling, Gene
Expression Regulation, Genes, Genetic, Genetic Markers, Hemolysins,
Humans, Ion Channels, Kinetics, Leukemia, Lipid Bilayers, Logistic
Models, Lymphocytic, Male, Markov Chains, Melanoma, Models, Molecular,
Myeloid, Neoplasm, Neoplastic, Neural Networks (Computer), Nevus,
Non-P.H.S., Non-U.S. Gov't, Nucleic Acid Conformation, Organ Specificity,
Organelles, P.H.S., Pattern Recognition, Physical, Pigmented, Predictive
Value of Tests, Promoter Regions (Genetics), Protein Folding, Protein
Structure, Proteins, Proteome, RNA, Reproducibility of Results, Research
Support, Saccharomyces cerevisiae, Secondary, Sensitivity and Specificity,
Sequence Alignment, Sex Characteristics, Skin Diseases, Skin Neoplasms,
Skin Pigmentation, Software, Statistical, Stomach Diseases, T-Lymphocytes,
Thermodynamics, Transcription, Transcription Factors, Tumor Markers,
U.S. Gov't, 11231558},
pii = {85696},
url = {http://dx.doi.org/10.1038/85696}
}
@article{Vickers2003Efficient,
author = {Vickers, T. A. and Koo, S. and Bennett, C. F. and Crooke, S. T. and
Dean, N. M. and Baker, B. F.},
title = {Efficient reduction of target {RNA}s by small interfering {RNA} and
{RN}ase {H}-dependent antisense agents. {A} comparative analysis.},
journal = {J. {B}iol. {C}hem.},
year = {2003},
volume = {278},
pages = {7108-18},
number = {9},
month = {Feb},
abstract = {R{NA} interference can be considered as an antisense mechanism of
action that utilizes a double-stranded {RN}ase to promote hydrolysis
of the target {RNA}. {W}e have performed a comparative study of optimized
antisense oligonucleotides designed to work by an {RNA} interference
mechanism to oligonucleotides designed to work by an {RN}ase {H}-dependent
mechanism in human cells. {T}he potency, maximal effectiveness, duration
of action, and sequence specificity of optimized {RN}ase {H}-dependent
oligonucleotides and small interfering {RNA} (si{RNA}) oligonucleotide
duplexes were evaluated and found to be comparable. {E}ffects of
base mismatches on activity were determined to be position-dependent
for both si{RNA} oligonucleotides and {RN}ase {H}-dependent oligonucleotides.
{I}n addition, we determined that the activity of both si{RNA} oligonucleotides
and {RN}ase {H}-dependent oligonucleotides is affected by the secondary
structure of the target m{RNA}. {T}o determine whether positions
on target {RNA} identified as being susceptible for {RN}ase {H}-mediated
degradation would be coincident with si{RNA} target sites, we evaluated
the effectiveness of si{RNA}s designed to bind the same position
on the target m{RNA} as {RN}ase {H}-dependent oligonucleotides. {E}xamination
of 80 si{RNA} oligonucleotide duplexes designed to bind to {RNA}
from four distinct human genes revealed that, in general, activity
correlated with the activity to {RN}ase {H}-dependent oligonucleotides
designed to the same site, although some exceptions were noted. {T}he
one major difference between the two strategies is that {RN}ase {H}-dependent
oligonucleotides were determined to be active when directed against
targets in the pre-m{RNA}, whereas si{RNA}s were not. {T}hese results
demonstrate that si{RNA} oligonucleotide- and {RN}ase {H}-dependent
antisense strategies are both valid strategies for evaluating function
of genes in cell-based assays.},
doi = {10.1074/jbc.M210326200},
keywords = {Animals, Antisense, Base Sequence, COS Cells, Calf Thymus, Cultured,
Dose-Response Relationship, Drug, Flow Cytometry, Humans, Intercellular
Adhesion Molecule-1, Introns, Luciferases, Messenger, Molecular Sequence
Data, Nucleic Acid Conformation, Oligonucleotides, PTEN Phosphohydrolase,
Phosphoric Monoester Hydrolases, Protein Structure, RNA, Ribonuclease
H, Small Interfering, Tertiary, Time Factors, Tumor Cells, Tumor
Suppressor Proteins, 12500975},
pii = {M210326200},
url = {http://dx.doi.org/10.1074/jbc.M210326200}
}
@article{Wahba2002Soft,
author = {Grace Wahba},
title = {Soft and hard classification by reproducing kernel {H}ilbert space
methods.},
journal = {Proc {N}atl {A}cad {S}ci {U} {S} {A}},
year = {2002},
volume = {99},
pages = {16524-30},
number = {26},
month = {Dec},
abstract = {Reproducing kernel {H}ilbert space ({RKHS}) methods provide a unified
context for solving a wide variety of statistical modelling and function
estimation problems. {W}e consider two such problems: {W}e are given
a training set [yi, ti, i = 1, em leader, n], where yi is the response
for the ith subject, and ti is a vector of attributes for this subject.
{T}he value of y(i) is a label that indicates which category it came
from. {F}or the first problem, we wish to build a model from the
training set that assigns to each t in an attribute domain of interest
an estimate of the probability pj(t) that a (future) subject with
attribute vector t is in category j. {T}he second problem is in some
sense less ambitious; it is to build a model that assigns to each
t a label, which classifies a future subject with that t into one
of the categories or possibly "none of the above." {T}he approach
to the first of these two problems discussed here is a special case
of what is known as penalized likelihood estimation. {T}he approach
to the second problem is known as the support vector machine. {W}e
also note some alternate but closely related approaches to the second
problem. {T}hese approaches are all obtained as solutions to optimization
problems in {RKHS}. {M}any other problems, in particular the solution
of ill-posed inverse problems, can be obtained as solutions to optimization
problems in {RKHS} and are mentioned in passing. {W}e caution the
reader that although a large literature exists in all of these topics,
in this inaugural article we are selectively highlighting work of
the author, former students, and other collaborators.},
doi = {10.1073/pnas.242574899},
pdf = {../local/Wahba2002Soft.pdf},
file = {Wahba2002Soft.pdf:local/Wahba2002Soft.pdf:PDF},
keywords = {Acute, Algorithms, Animals, Automated, Base Pair Mismatch, Base Pairing,
Base Sequence, Biological, Biosensing Techniques, Classification,
Cluster Analysis, Comparative Study, Computational Biology, Computer-Assisted,
Cystadenoma, DNA, Drug, Drug Design, Eukaryotic Cells, Female, Gene
Expression, Gene Expression Profiling, Gene Expression Regulation,
Genes, Genetic, Genetic Markers, Hemolysins, Humans, Leukemia, Ligands,
Likelihood Functions, Lymphocytic, Markov Chains, Mathematics, Messenger,
Models, Molecular, Molecular Probe Techniques, Molecular Sequence
Data, Nanotechnology, Neoplasm, Neoplastic, Neural Networks (Computer),
Non-P.H.S., Non-U.S. Gov't, Nucleic Acid Conformation, Observer Variation,
Oligonucleotide Array Sequence Analysis, Ovarian Neoplasms, P.H.S.,
Pattern Recognition, Probability, Protein Binding, Proteins, Quality
Control, RNA, RNA Splicing, Receptors, Reference Values, Reproducibility
of Results, Research Support, Sensitivity and Specificity, Sequence
Analysis, Signal Processing, Statistical, Stomach Neoplasms, Thermodynamics,
Transcription, Tumor Markers, U.S. Gov't, 12477931},
pii = {242574899},
url = {http://dx.doi.org/10.1073/pnas.242574899}
}
@article{Wallace2010Identification,
author = {Emma V B Wallace and David Stoddart and Andrew J Heron and Ellina
Mikhailova and Giovanni Maglia and Timothy J Donohoe and Hagan Bayley},
title = {Identification of epigenetic DNA modifications with a protein nanopore.},
journal = {Chem Commun (Camb)},
year = {2010},
volume = {46},
pages = {8195--8197},
number = {43},
month = {Nov},
abstract = {Two DNA bases, 5-methylcytosine (5mC) and 5-hydroxymethylcytosine
(hmC), marks of epigenetic modification, are recognized in immobilized
DNA strands and distinguished from G, A, T and C by nanopore current
recording. Therefore, if further aspects of nanopore sequencing can
be addressed, the approach will provide a means to locate epigenetic
modifications in unamplified genomic DNA.},
doi = {10.1039/c0cc02864a},
institution = {Department of Chemistry, University of Oxford, Chemistry Research
Laboratory, Mansfield Road, Oxford, UK OX1 3TA.},
keywords = {5-Methylcytosine, chemistry; Cyclodextrins, chemistry; Cytosine, analogs
/&/ derivatives/chemistry; DNA, chemistry; Epigenesis, Genetic; Hemolysin
Proteins, chemistry; Nanopores},
language = {eng},
medline-pst = {ppublish},
owner = {phupe},
pmid = {20927439},
timestamp = {2011.06.01},
url = {http://dx.doi.org/10.1039/c0cc02864a}
}
@article{Wang2001Methylation,
author = {H. Wang and Z. Q. Huang and L. Xia and Q. Feng and H. Erdjument-Bromage
and B. D. Strahl and S. D. Briggs and C. D. Allis and J. Wong and
P. Tempst and Y. Zhang},
title = {Methylation of histone H4 at arginine 3 facilitating transcriptional
activation by nuclear hormone receptor.},
journal = {Science},
year = {2001},
volume = {293},
pages = {853--857},
number = {5531},
month = {Aug},
abstract = {Acetylation of core histone tails plays a fundamental role in transcription
regulation. In addition to acetylation, other posttranslational modifications,
such as phosphorylation and methylation, occur in core histone tails.
Here, we report the purification, molecular identification, and functional
characterization of a histone H4-specific methyltransferase PRMT1,
a protein arginine methyltransferase. PRMT1 specifically methylates
arginine 3 (Arg 3) of H4 in vitro and in vivo. Methylation of Arg
3 by PRMT1 facilitates subsequent acetylation of H4 tails by p300.
However, acetylation of H4 inhibits its methylation by PRMT1. Most
important, a mutation in the S-adenosyl-l-methionine-binding site
of PRMT1 substantially crippled its nuclear receptor coactivator
activity. Our finding reveals Arg 3 of H4 as a novel methylation
site by PRMT1 and indicates that Arg 3 methylation plays an important
role in transcriptional regulation.},
doi = {10.1126/science.1060781},
institution = {Department of Biochemistry and Biophysics, Lineberger Comprehensive
Cancer Center, University of North Carolina at Chapel Hill, Chapel
Hill, NC 27599-7295, USA.},
keywords = {Acetylation; Amino Acid Sequence; Animals; Arginine, metabolism; Binding
Sites; Cell Nucleus, metabolism; Hela Cells; Histones, chemistry/metabolism;
Humans; Hydroxamic Acids, pharmacology; Lysine, metabolism; Methylation;
Methyltransferases, chemistry/genetics/isolation /&/ purification/metabolism;
Molecular Sequence Data; Mutation; Oocytes; Receptors, Androgen,
metabolism; Recombinant Proteins, metabolism; S-Adenosylmethionine,
metabolism; Transcriptional Activation; Xenopus},
language = {eng},
medline-pst = {ppublish},
owner = {jp},
pii = {1060781},
pmid = {11387442},
timestamp = {2010.11.23},
url = {http://dx.doi.org/10.1126/science.1060781}
}
@article{Wang2004Simple,
author = {Kai Wang and Ekachai Jenwitheesuk and Ram Samudrala and John E Mittler},
title = {Simple linear model provides highly accurate genotypic predictions
of {HIV}-1 drug resistance.},
journal = {Antivir {T}her},
year = {2004},
volume = {9},
pages = {343-52},
number = {3},
month = {Jun},
abstract = {Drug resistance is a major obstacle to the successful treatment of
{HIV}-1 infection. {G}enotypic assays are used widely to provide
indirect evidence of drug resistance, but the performance of these
assays has been mixed. {W}e used standard stepwise linear regression
to construct drug resistance models for seven protease inhibitors
and 10 reverse transcriptase inhibitors using data obtained from
the {S}tanford {HIV} drug resistance database. {W}e evaluated these
models by hold-one-out experiments and by tests on an independent
dataset. {O}ur linear model outperformed other publicly available
genotypic interpretation algorithms, including decision tree, support
vector machine and four rules-based algorithms ({HIV}db, {VGI}, {ANRS}
and {R}ega) under both tests. {I}nterestingly, our model did well
despite the absence of any terms for interactions between different
residues in protease or reverse transcriptase. {T}he resulting linear
models are easy to understand and can potentially assist in choosing
combination therapy regimens.},
keywords = {Algorithms, Computational Biology, Databases, Drug Resistance, Forecasting,
Genetic, Genotype, HIV Protease Inhibitors, HIV-1, Humans, Information
Management, Information Storage and Retrieval, Kinetics, Linear Models,
Microbial Sensitivity Tests, Models, Non-U.S. Gov't, P.H.S., Periodicals,
Point Mutation, Pyrimidinones, Research Support, Reverse Transcriptase
Inhibitors, Theoretical, U.S. Gov't, Viral, 15259897}
}
@article{Waterman2003Transcriptional,
author = {Waterman, S.R. and Small, P.L.C.},
title = {Transcriptional expression of Escherichia coli glutamate-dependent
acid resistance genes gadA and gadBC in an hns rpoS mutant.},
journal = {J. Bacteriol.},
year = {2003},
volume = {185},
pages = {4644--4647},
number = {15},
month = {Aug},
abstract = {Resistance to being killed by acidic environments with pH values lower
than 3 is an important feature of both pathogenic and nonpathogenic
Escherichia coli. The most potent E. coli acid resistance system
utilizes two isoforms of glutamate decarboxylase encoded by gadA
and gadB and a putative glutamate:gamma-aminobutyric acid antiporter
encoded by gadC. The gad system is controlled by two repressors (H-NS
and CRP), one activator (GadX), one repressor-activator (GadW), and
two sigma factors (sigma(S) and sigma(70)). In contrast to results
of previous reports, we demonstrate that gad transcription can be
detected in an hns rpoS mutant strain of E. coli K-12, indicating
that gad promoters can be initiated by sigma(70) in the absence of
H-NS.},
institution = {Division of Human Immunology, Hanson Institute, Institute of Medical
and Veterinary Science, Adelaide, South Australia, 5000, Australia.
scott.waterman@imvs.sa.gov.au},
keywords = {Bacterial Proteins; DNA-Binding Proteins; Drug Resistance, Bacterial;
Escherichia coli; Escherichia coli Proteins; Gene Expression Regulation,
Bacterial; Glutamate Decarboxylase; Glutamates; Hydrogen-Ion Concentration;
Membrane Proteins; Mutation; Sigma Factor; Transcription, Genetic},
owner = {fantine},
pmid = {12867478},
timestamp = {2008.02.11}
}
@article{Weber2002Building,
author = {Griffin Weber and Staal Vinterbo and Lucila Ohno-Machado},
title = {Building an asynchronous web-based tool for machine learning classification.},
journal = {Proc {AMIA} {S}ymp},
year = {2002},
pages = {869-73},
abstract = {Various unsupervised and supervised learning methods including support
vector machines, classification trees, linear discriminant analysis
and nearest neighbor classifiers have been used to classify high-throughput
gene expression data. {S}impler and more widely accepted statistical
tools have not yet been used for this purpose, hence proper comparisons
between classification methods have not been conducted. {W}e developed
free software that implements logistic regression with stepwise variable
selection as a quick and simple method for initial exploration of
important genetic markers in disease classification. {T}o implement
the algorithm and allow our collaborators in remote locations to
evaluate and compare its results against those of other methods,
we developed a user-friendly asynchronous web-based application with
a minimal amount of programming using free, downloadable software
tools. {W}ith this program, we show that classification using logistic
regression can perform as well as other more sophisticated algorithms,
and it has the advantages of being easy to interpret and reproduce.
{B}y making the tool freely and easily available, we hope to promote
the comparison of classification methods. {I}n addition, we believe
our web application can be used as a model for other bioinformatics
laboratories that need to develop web-based analysis tools in a short
amount of time and on a limited budget.},
keywords = {Acute, Algorithms, Animals, Artificial Intelligence, Automated, Base
Pair Mismatch, Base Pairing, Base Sequence, Biological, Biosensing
Techniques, Classification, Cluster Analysis, Comparative Study,
Computational Biology, Computer-Assisted, Cystadenoma, DNA, Drug,
Drug Design, Eukaryotic Cells, Female, Gene Expression, Gene Expression
Profiling, Gene Expression Regulation, Genes, Genetic, Genetic Markers,
Hemolysins, Humans, Internet, Leukemia, Ligands, Likelihood Functions,
Logistic Models, Lymphocytic, Markov Chains, Mathematics, Messenger,
Models, Molecular, Molecular Probe Techniques, Molecular Sequence
Data, Nanotechnology, Neoplasm, Neoplasms, Neoplastic, Neural Networks
(Computer), Non-P.H.S., Non-U.S. Gov't, Nucleic Acid Conformation,
Observer Variation, Oligonucleotide Array Sequence Analysis, Ovarian
Neoplasms, P.H.S., Pattern Recognition, Probability, Protein Binding,
Proteins, Quality Control, RNA, RNA Splicing, Receptors, Reference
Values, Reproducibility of Results, Research Support, Sensitivity
and Specificity, Sequence Analysis, Signal Processing, Software,
Statistical, Stomach Neoplasms, Thermodynamics, Transcription, Tumor
Markers, U.S. Gov't, 12463949},
pii = {D020001919}
}
@article{Weis2008Structural,
author = {William I Weis and Brian K Kobilka},
title = {Structural insights into {G}-protein-coupled receptor activation.},
journal = {Curr Opin Struct Biol},
year = {2008},
volume = {18},
pages = {734--740},
number = {6},
month = {Dec},
abstract = {G-protein-coupled receptors (GPCRs) are the largest family of eukaryotic
plasma membrane receptors, and are responsible for the majority of
cellular responses to external signals. GPCRs share a common architecture
comprising seven transmembrane (TM) helices. Binding of an activating
ligand enables the receptor to catalyze the exchange of GTP for GDP
in a heterotrimeric G protein. GPCRs are in a conformational equilibrium
between inactive and activating states. Crystallographic and spectroscopic
studies of the visual pigment rhodopsin and two beta-adrenergic receptors
have defined some of the conformational changes associated with activation.},
doi = {10.1016/j.sbi.2008.09.010},
institution = { Cellular Physiology, Stanford University School of Medicine, USA.
bill.weis@stanford.edu},
keywords = {Animals; Crystallography; Humans; Membrane Proteins; Models, Molecular;
Receptors, Adrenergic, beta; Receptors, G-Protein-Coupled; Rhodopsin},
owner = {ljacob},
pii = {S0959-440X(08)00147-4},
pmid = {18957321},
timestamp = {2009.11.09},
url = {http://dx.doi.org/10.1016/j.sbi.2008.09.010}
}
@article{Wilbur2000Boosting,
author = {W. J. Wilbur},
title = {Boosting naive {B}ayesian learning on a large subset of {MEDLINE}.},
journal = {Proc {AMIA} {S}ymp},
year = {2000},
pages = {918-22},
abstract = {We are concerned with the rating of new documents that appear in a
large database ({MEDLINE}) and are candidates for inclusion in a
small specialty database ({REBASE}). {T}he requirement is to rank
the new documents as nearly in order of decreasing potential to be
added to the smaller database as possible, so as to improve the coverage
of the smaller database without increasing the effort of those who
manage this specialty database. {T}o perform this ranking task we
have considered several machine learning approaches based on the
naï ve {B}ayesian algorithm. {W}e find that adaptive boosting outperforms
naï ve {B}ayes, but that a new form of boosting which we term staged
{B}ayesian retrieval outperforms adaptive boosting. {S}taged {B}ayesian
retrieval involves two stages of {B}ayesian retrieval and we further
find that if the second stage is replaced by a support vector machine
we again obtain a significant improvement over the strictly {B}ayesian
approach.},
keywords = {Acute, Acute Disease, Adenocarcinoma, Algorithms, Amino Acid Sequence,
Animals, Artificial Intelligence, Automated, B-Lymphocytes, Bacterial
Proteins, Base Pair Mismatch, Base Sequence, Bayes Theorem, Binding
Sites, Biological, Bone Marrow Cells, Brachyura, Cell Compartmentation,
Chemistry, Child, Chromosome Aberrations, Classification, Codon,
Colonic Neoplasms, Comparative Study, Computational Biology, Computer
Simulation, Computer-Assisted, DNA, Data Interpretation, Databases,
Decision Trees, Diabetes Mellitus, Diagnosis, Discriminant Analysis,
Discrimination Learning, Electric Conductivity, Electrophysiology,
Escherichia coli Proteins, Factual, Feedback, Female, Fungal, Gastric
Emptying, Gene Expression Profiling, Gene Expression Regulation,
Genes, Genetic, Genetic Markers, Genetic Predisposition to Disease,
Genomics, Hemolysins, Humans, Indians, Information Storage and Retrieval,
Initiator, Ion Channels, Kinetics, Leukemia, Likelihood Functions,
Lipid Bilayers, Logistic Models, Lymphocytic, MEDLINE, Male, Markov
Chains, Melanoma, Models, Molecular, Myeloid, Neoplasm, Neoplasms,
Neoplastic, Neural Networks (Computer), Neurological, Nevus, Non-P.H.S.,
Non-U.S. Gov't, Nonlinear Dynamics, Normal Distribution, North American,
Nucleic Acid Conformation, Oligonucleotide Array Sequence Analysis,
Organ Specificity, Organelles, Ovarian Neoplasms, Ovary, P.H.S.,
Pattern Recognition, Physical, Pigmented, Predictive Value of Tests,
Promoter Regions (Genetics), Protein Biosynthesis, Protein Folding,
Protein Structure, Proteins, Proteome, RNA, Reproducibility of Results,
Research Support, Saccharomyces cerevisiae, Secondary, Sensitivity
and Specificity, Sequence Alignment, Sequence Analysis, Sex Characteristics,
Skin Diseases, Skin Neoplasms, Skin Pigmentation, Software, Sound
Spectrography, Statistical, Stomach Diseases, T-Lymphocytes, Thermodynamics,
Transcription, Transcription Factors, Tumor Markers, Type 2, U.S.
Gov't, Vertebrates, 11080018},
pii = {D200250}
}
@article{Wilkins1996From,
author = {M. R. Wilkins and C. Pasquali and R. D. Appel and K. Ou and O. Golaz
and J. C. Sanchez and J. X. Yan and A. A. Gooley and G. Hughes and
I. Humphery-Smith and K. L. Williams and D. F. Hochstrasser},
title = {From proteins to proteomes: large scale protein identification by
two-dimensional electrophoresis and amino acid analysis.},
journal = {Biotechnology (N Y)},
year = {1996},
volume = {14},
pages = {61--65},
number = {1},
month = {Jan},
abstract = {Separation and identification of proteins by two-dimensional (2-D)
electrophoresis can be used for protein-based gene expression analysis.
In this report single protein spots, from polyvinylidene difluoride
blots of micropreparative E. coli 2-D gels, were rapidly and economically
identified by matching their amino acid composition, estimated pI
and molecular weight against all E. coli entries in the SWISS-PROT
database. Thirty proteins from an E. coli 2-D map were analyzed and
identities assigned. Three of the proteins were unknown. By protein
sequencing analysis, 20 of the 27 proteins were correctly identified.
Importantly, correct identifications showed unambiguous "correct"
score patterns. While incorrect protein identifications also showed
distinctive score patterns, indicating that protein must be identified
by other means. These techniques allow large-scale screening of the
protein complement of simple organisms, or tissues in normal and
disease states. The computer program described here is accessible
via the World Wide Web at URL address (http:@expasy.hcuge.ch/).},
institution = {Macquarie University Centre for Analytical Biotechnology, Macquarie
University, Sydney, NSW, Australia.},
keywords = {Amino Acids; Bacterial Proteins; Blood Proteins; Databases, Factual;
Electrophoresis, Gel, Two-Dimensional; Escherichia coli; Humans;
Microchemistry; Molecular Weight; Multienzyme Complexes; Proteins;
Reproducibility of Results; Software; Time Factors},
owner = {ljacob},
pmid = {9636313},
timestamp = {2009.09.14}
}
@article{Wu2008Network-based,
author = {Wu, X. and Jiang, R. and Zhang, M.Q. and Li, S.},
title = {Network-based global inference of human disease genes.},
journal = {Mol. Syst. Biol.},
year = {2008},
volume = {4},
pages = {189},
abstract = {Deciphering the genetic basis of human diseases is an important goal
of biomedical research. On the basis of the assumption that phenotypically
similar diseases are caused by functionally related genes, we propose
a computational framework that integrates human protein-protein interactions,
disease phenotype similarities, and known gene-phenotype associations
to capture the complex relationships between phenotypes and genotypes.
We develop a tool named CIPHER to predict and prioritize disease
genes, and we show that the global concordance between the human
protein network and the phenotype network reliably predicts disease
genes. Our method is applicable to genetically uncharacterized phenotypes,
effective in the genome-wide scan of disease genes, and also extendable
to explore gene cooperativity in complex diseases. The predicted
genetic landscape of over 1000 human phenotypes, which reveals the
global modular organization of phenotype-genotype relationships.
The genome-wide prioritization of candidate genes for over 5000 human
phenotypes, including those with under-characterized disease loci
or even those lacking known association, is publicly released to
facilitate future discovery of disease genes.},
doi = {10.1038/msb.2008.27},
institution = {MOE Key Laboratory of Bioinformatics and Bioinformatics Division,
TNLIST/Department of Automation, Tsinghua University, Beijing, China.},
keywords = {BRCA1 Protein; Bias (Epidemiology); Breast Neoplasms; Disease; Female;
Gene Regulatory Networks; Genes; Genome, Human; Genotype; Humans;
Linkage (Genetics); Phenotype; Software},
owner = {mordelet},
pii = {msb200827},
pmid = {18463613},
timestamp = {2010.09.27},
url = {http://dx.doi.org/10.1038/msb.2008.27}
}
@article{Xia2004RNAi,
author = {Xia, H. and Mao, Q. and Eliason, S. L. and Harper, S. Q. and Martins,
I. H. and Orr, H. T. and Paulson, H. L. and Yang, L. and Kotin, R.
M. and Davidson, B. L.},
title = {{RNA}i suppresses polyglutamine-induced neurodegeneration in a model
of spinocerebellar ataxia.},
journal = {Nat. Med.},
year = {2004},
volume = {10},
pages = {816--820},
number = {8},
month = {Aug},
abstract = {The dominant polyglutamine expansion diseases, which include spinocerebellar
ataxia type 1 (SCA1) and Huntington disease, are progressive, untreatable,
neurodegenerative disorders. In inducible mouse models of SCA1 and
Huntington disease, repression of mutant allele expression improves
disease phenotypes. Thus, therapies designed to inhibit expression
of the mutant gene would be beneficial. Here we evaluate the ability
of RNA interference (RNAi) to inhibit polyglutamine-induced neurodegeneration
caused by mutant ataxin-1 in a mouse model of SCA1. Upon intracerebellar
injection, recombinant adeno-associated virus (AAV) vectors expressing
short hairpin RNAs profoundly improved motor coordination, restored
cerebellar morphology and resolved characteristic ataxin-1 inclusions
in Purkinje cells of SCA1 mice. Our data demonstrate in vivo the
potential use of RNAi as therapy for dominant neurodegenerative disease.},
doi = {10.1038/nm1076},
keywords = {Adenoviridae, Animal, Animals, Blotting, Brain, Cells, Comparative
Study, Cultured, Disease Models, Gene Expression, Genetic, Glutamine,
Immunohistochemistry, Messenger, Mice, Nerve Degeneration, Nerve
Tissue Proteins, Non-U.S. Gov't, Northern, Nuclear Proteins, P.H.S.,
Plasmids, Psychomotor Performance, Purkinje Cells, RNA, RNA Interference,
Research Support, Reverse Transcriptase Polymerase Chain Reaction,
Small Interfering, Spinocerebellar Ataxias, Transduction, Transgenic,
U.S. Gov't, 15286770},
owner = {vert},
pii = {nm1076},
pmid = {15286770},
timestamp = {2006.03.28},
url = {http://dx.doi.org/10.1038/nm1076}
}
@article{Xie2009Unified,
author = {Lei Xie and Li Xie and Philip E Bourne},
title = {A unified statistical model to support local sequence order independent
similarity searching for ligand-binding sites and its application
to genome-based drug discovery.},
journal = {Bioinformatics},
year = {2009},
volume = {25},
pages = {i305--i312},
number = {12},
month = {Jun},
abstract = {Functional relationships between proteins that do not share global
structure similarity can be established by detecting their ligand-binding-site
similarity. For a large-scale comparison, it is critical to accurately
and efficiently assess the statistical significance of this similarity.
Here, we report an efficient statistical model that supports local
sequence order independent ligand-binding-site similarity searching.
Most existing statistical models only take into account the matching
vertices between two sites that are defined by a fixed number of
points. In reality, the boundary of the binding site is not known
or is dependent on the bound ligand making these approaches limited.
To address these shortcomings and to perform binding-site mapping
on a genome-wide scale, we developed a sequence-order independent
profile-profile alignment (SOIPPA) algorithm that is able to detect
local similarity between unknown binding sites a priori. The SOIPPA
scoring integrates geometric, evolutionary and physical information
into a unified framework. However, this imposes a significant challenge
in assessing the statistical significance of the similarity because
the conventional probability model that is based on fixed-point matching
cannot be applied. Here we find that scores for binding-site matching
by SOIPPA follow an extreme value distribution (EVD). Benchmark studies
show that the EVD model performs at least two-orders faster and is
more accurate than the non-parametric statistical method in the previous
SOIPPA version. Efficient statistical analysis makes it possible
to apply SOIPPA to genome-based drug discovery. Consequently, we
have applied the approach to the structural genome of Mycobacterium
tuberculosis to construct a protein-ligand interaction network. The
network reveals highly connected proteins, which represent suitable
targets for promiscuous drugs.},
doi = {10.1093/bioinformatics/btp220},
institution = {San Diego Supercomputer Center, University of California, San Diego,
La Jolla, CA 92093, USA. lxie@sdsc.edu},
keywords = {Binding Sites; Computational Biology, methods; Drug Discovery, methods;
Genome; Ligands; Models, Statistical; Mycobacterium tuberculosis,
genetics/metabolism; Proteins, chemistry},
language = {eng},
medline-pst = {ppublish},
owner = {bricehoffmann},
pii = {btp220},
pmid = {19478004},
timestamp = {2009.07.27},
url = {http://dx.doi.org/10.1093/bioinformatics/btp220}
}
@article{Xue2001Mini-fingerprints,
author = {L. Xue and F. L. Stahura and J. W. Godden and J. Bajorath},
title = {{M}ini-fingerprints detect similar activity of receptor ligands previously
recognized only by three-dimensional pharmacophore-based methods.},
journal = {J Chem Inf Comput Sci},
year = {2001},
volume = {41},
pages = {394--401},
number = {2},
abstract = {Mini-fingerprints (MFPs) are short binary bit string representations
of molecular structure and properties, composed of few selected two-dimensional
(2D) descriptors and a number of structural keys. MFPs were specifically
designed to recognize compounds with similar activity. Here we report
that MFPs are capable of detecting similar activities of some druglike
molecules, including endothelin A antagonists and alpha(1)-adrenergic
receptor ligands, the recognition of which was previously thought
to depend on the use of multiple point three-dimensional (3D) pharmacophore
methods. Thus, in these cases, MFPs and pharmacophore fingerprints
produce similar results, although they define, in terms of their
complexity, opposite ends of the spectrum of methods currently used
to study molecular similarity or diversity. For each of the studied
compound classes, comparison of MFP bit settings identified a consensus
or signature pattern. Scaling factors can be applied to these bits
in order to increase the probability of finding compounds with similar
activity by virtual screening.},
keywords = {Adrenergic, Angiotensin II, Cell Surface, Combinatorial Chemistry
Techniques, Databases, Drug Evaluation, Endothelins, Environmental
Pollutants, Factual, Information Management, Ligands, Molecular Structure,
Pharmaceutical Preparations, Platelet Glycoprotein GPIIb-IIIa Complex,
Preclinical, Receptors, Serine Proteinase Inhibitors, Structure-Activity
Relationship, User-Computer Interface, alpha-1, 11277728},
owner = {mahe},
pii = {ci000305x},
pmid = {11277728},
timestamp = {2006.08.22}
}
@article{Yu2005Ovarian,
author = {J. S. Yu and S. Ongarello and R. Fiedler and X. W. Chen and G. Toffolo
and C. Cobelli and Z. Trajanoski},
title = {Ovarian cancer identification based on dimensionality reduction for
high-throughput mass spectrometry data.},
journal = {Bioinformatics},
year = {2005},
volume = {21},
pages = {2200-9},
number = {10},
month = {May},
abstract = {M{OTIVATION}: {H}igh-throughput and high-resolution mass spectrometry
instruments are increasingly used for disease classification and
therapeutic guidance. {H}owever, the analysis of immense amount of
data poses considerable challenges. {W}e have therefore developed
a novel method for dimensionality reduction and tested on a published
ovarian high-resolution {SELDI}-{TOF} dataset. {RESULTS}: {W}e have
developed a four-step strategy for data preprocessing based on: (1)
binning, (2) {K}olmogorov-{S}mirnov test, (3) restriction of coefficient
of variation and (4) wavelet analysis. {S}ubsequently, support vector
machines were used for classification. {T}he developed method achieves
an average sensitivity of 97.38\% (sd = 0.0125) and an average specificity
of 93.30\% (sd = 0.0174) in 1000 independent k-fold cross-validations,
where k = 2, ..., 10. {AVAILABILITY}: {T}he software is available
for academic and non-commercial institutions.},
doi = {10.1093/bioinformatics/bti370},
pdf = {../local/Yu2005Ovarian.pdf},
file = {Yu2005Ovarian.pdf:local/Yu2005Ovarian.pdf:PDF},
keywords = {biosvm proteomics},
pii = {bti370},
url = {http://dx.doi.org/10.1093/bioinformatics/bti370}
}
@article{Yu2002Methods,
author = {Kun Yu and Nikolai Petrovsky and Christian Schönbach and Judice
Y L Koh and Vladimir Brusic},
title = {Methods for prediction of peptide binding to {MHC} molecules: a comparative
study.},
journal = {Mol Med},
year = {2002},
volume = {8},
pages = {137--148},
number = {3},
month = {Mar},
abstract = {BACKGROUND: A variety of methods for prediction of peptide binding
to major histocompatibility complex (MHC) have been proposed. These
methods are based on binding motifs, binding matrices, hidden Markov
models (HMM), or artificial neural networks (ANN). There has been
little prior work on the comparative analysis of these methods. MATERIALS
AND METHODS: We performed a comparison of the performance of six
methods applied to the prediction of two human MHC class I molecules,
including binding matrices and motifs, ANNs, and HMMs. RESULTS: The
selection of the optimal prediction method depends on the amount
of available data (the number of peptides of known binding affinity
to the MHC molecule of interest), the biases in the data set and
the intended purpose of the prediction (screening of a single protein
versus mass screening). When little or no peptide data are available,
binding motifs are the most useful alternative to random guessing
or use of a complete overlapping set of peptides for selection of
candidate binders. As the number of known peptide binders increases,
binding matrices and HMM become more useful predictors. ANN and HMM
are the predictive methods of choice for MHC alleles with more than
100 known binding peptides. CONCLUSION: The ability of bioinformatic
methods to reliably predict MHC binding peptides, and thereby potential
T-cell epitopes, has major implications for clinical immunology,
particularly in the area of vaccine design.},
keywords = {Amino Acid Motifs; Computational Biology; Histocompatibility Antigens
Class I; Humans; Models, Molecular; Peptides; Protein Binding},
owner = {laurent},
pii = {S152836580230137X},
pmid = {12142545},
timestamp = {2007.01.27}
}
@article{Zhang2005MULTIPRED,
author = {Zhang, G. L. and Khan, A. M. and Srinivasan, K. N. and August, J.
T. and Brusic, V.},
title = {{MULTIPRED}: a computational system for prediction of promiscuous
{HLA} binding peptides.},
journal = {Nucleic Acids Res/},
year = {2005},
volume = {33},
pages = {W172--W179},
number = {Web Server issue},
month = {Jul},
abstract = {MULTIPRED is a web-based computational system for the prediction of
peptide binding to multiple molecules (proteins) belonging to human
leukocyte antigens (HLA) class I A2, A3 and class II DR supertypes.
It uses hidden Markov models and artificial neural network methods
as predictive engines. A novel data representation method enables
MULTIPRED to predict peptides that promiscuously bind multiple HLA
alleles within one HLA supertype. Extensive testing was performed
for validation of the prediction models. Testing results show that
MULTIPRED is both sensitive and specific and it has good predictive
ability (area under the receiver operating characteristic curve A(ROC)
> 0.80). MULTIPRED can be used for the mapping of promiscuous T-cell
epitopes as well as the regions of high concentration of these targets--termed
T-cell epitope hotspots. MULTIPRED is available at http://antigen.i2r.a-star.edu.sg/multipred/.},
doi = {10.1093/nar/gki452},
keywords = {Algorithms, Amino Acid Sequence, Antigen-Antibody Complex, Automated,
Binding Sites, Computational Biology, Drug Delivery Systems, Drug
Design, Epitopes, HLA Antigens, HLA-A Antigens, HLA-DR Antigens,
Humans, Internet, Markov Chains, Molecular Sequence Data, Neural
Networks (Computer), Pattern Recognition, Peptides, Protein, Protein
Binding, Protein Interaction Mapping, Sequence Analysis, Software,
T-Lymphocyte, User-Computer Interface, Viral Vaccines, 15980449},
pii = {33/suppl_2/W172},
pmid = {15980449},
timestamp = {2007.01.25},
url = {http://dx.doi.org/10.1093/nar/gki452}
}
@article{Zhao2003Applicationa,
author = {Zhao, Y. and Pinilla, C. and Valmori, D. and Martin, R. and Simon,
R.},
title = {{A}pplication of support vector machines for {T}-cell epitopes prediction.},
journal = {Bioinformatics},
year = {2003},
volume = {19},
pages = {1978--1984},
number = {15},
month = {Oct},
abstract = {MOTIVATION: The T-cell receptor, a major histocompatibility complex
(MHC) molecule, and a bound antigenic peptide, play major roles in
the process of antigen-specific T-cell activation. T-cell recognition
was long considered exquisitely specific. Recent data also indicate
that it is highly flexible, and one receptor may recognize thousands
of different peptides. Deciphering the patterns of peptides that
elicit a MHC restricted T-cell response is critical for vaccine development.
RESULTS: For the first time we develop a support vector machine (SVM)
for T-cell epitope prediction with an MHC type I restricted T-cell
clone. Using cross-validation, we demonstrate that SVMs can be trained
on relatively small data sets to provide prediction more accurate
than those based on previously published methods or on MHC binding.
SUPPLEMENTARY INFORMATION: Data for 203 synthesized peptides is available
at http://linus.nci.nih.gov/Data/LAU203_Peptide.pdf},
keywords = {Algorithms, Amino Acid Sequence, Antigen, Antigen Presentation, Antigen-Antibody
Complex, Artificial Intelligence, Autoimmune Diseases, Autoimmunity,
Bacterial Proteins, CD4-Positive T-Lymphocytes, Cell Proliferation,
Cells, Clone Cells, Cluster Analysis, Conserved Sequence, Cross Reactions,
Cultured, Cytokines, Databases, Epitope Mapping, Epitopes, Gene Products,
Genetic, HIV-1, HLA-DQ Antigens, HLA-DR2 Antigen, Haplotypes, Helper-Inducer,
Hemagglutination, Histocompatibility Antigens Class I, Humans, K562
Cells, Molecular Mimicry, Molecular Sequence Data, Multiple Sclerosis,
Myelin Proteins, Neural Networks (Computer), Orthomyxoviridae, Peptide
Library, Peptides, Protein, Protein Binding, Protein Interaction
Mapping, ROC Curve, Receptors, Relapsing-Remitting, Reproducibility
of Results, Reverse Transcriptase Polymerase Chain Reaction, Sensitivity
and Specificity, Sequence Analysis, Structure-Activity Relationship,
T-Cell, T-Lymphocyte, T-Lymphocytes, Torque teno virus, Viral, Viral
Proteins, gag, 14555632},
pmid = {14555632},
timestamp = {2007.01.25}
}
@article{Zhu2001Global,
author = {H. Zhu and M. Bilgin and R. Bangham and D. Hall and A. Casamayor
and P. Bertone and N. Lan and R. Jansen and S. Bidlingmaier and T.
Houfek and T. Mitchell and P. Miller and R. A. Dean and M. Gerstein
and M. Snyder},
title = {Global analysis of protein activities using proteome chips.},
journal = {Science},
year = {2001},
volume = {293},
pages = {2101-5},
number = {5537},
month = {Sep},
abstract = {To facilitate studies of the yeast proteome, we cloned 5800 open reading
frames and overexpressed and purified their corresponding proteins.
{T}he proteins were printed onto slides at high spatial density to
form a yeast proteome microarray and screened for their ability to
interact with proteins and phospholipids. {W}e identified many new
calmodulin- and phospholipid-interacting proteins; a common potential
binding motif was identified for many of the calmodulin-binding proteins.
{T}hus, microarrays of an entire eukaryotic proteome can be prepared
and screened for diverse biochemical activities. {T}he microarrays
can also be used to screen protein-drug interactions and to detect
posttranslational modifications.},
doi = {10.1126/science.1062191},
pdf = {../local/zhu01.pdf},
file = {zhu01.pdf:local/zhu01.pdf:PDF},
keywords = {Amino Acid Motifs, Amino Acid Sequence, Calmodulin, Calmodulin-Binding
Proteins, Cell Membrane, Cloning, Fungal Proteins, Glucose, Liposomes,
Membrane Proteins, Molecular, Molecular Sequence Data, Non-U.S. Gov't,
Open Reading Frames, P.H.S., Peptide Library, Phosphatidylcholines,
Phosphatidylinositols, Phospholipids, Protein Binding, Proteome,
Recombinant Fusion Proteins, Research Support, Saccharomyces cerevisiae,
Signal Transduction, Streptavidin, U.S. Gov't, 11474067},
pii = {1062191},
url = {http://dx.doi.org/10.1126/science.1062191}
}
@article{Zhu2003Introduction,
author = {Lingyun Zhu and Baoming Wu and Changxiu Cao},
title = {Introduction to medical data mining},
journal = {Sheng {W}u {Y}i {X}ue {G}ong {C}heng {X}ue {Z}a {Z}hi},
year = {2003},
volume = {20},
pages = {559-62},
number = {3},
month = {Sep},
abstract = {Modern medicine generates a great deal of information stored in the
medical database. {E}xtracting useful knowledge and providing scientific
decision-making for the diagnosis and treatment of disease from the
database increasingly becomes necessary. {D}ata mining in medicine
can deal with this problem. {I}t can also improve the management
level of hospital information and promote the development of telemedicine
and community medicine. {B}ecause the medical information is characteristic
of redundancy, multi-attribution, incompletion and closely related
with time, medical data mining differs from other one. {I}n this
paper we have discussed the key techniques of medical data mining
involving pretreatment of medical data, fusion of different pattern
and resource, fast and robust mining algorithms and reliability of
mining results. {T}he methods and applications of medical data mining
based on computation intelligence such as artificial neural network,
fuzzy system, evolutionary algorithms, rough set, and support vector
machine have been introduced. {T}he features and problems in data
mining are summarized in the last section.},
keywords = {Algorithms, Anion Exchange Resins, Automatic Data Processing, Chemical,
Chromatography, Computational Biology, Computer-Assisted, Data Interpretation,
Databases, Decision Making, Decision Trees, English Abstract, Factual,
Fuzzy Logic, Humans, Indicators and Reagents, Information Storage
and Retrieval, Ion Exchange, Models, Neural Networks (Computer),
Non-P.H.S., Non-U.S. Gov't, Nucleic Acid Conformation, P.H.S., Proteins,
Quantitative Structure-Activity Relationship, RNA, ROC Curve, Research
Support, Sequence Analysis, Statistical, Transfer, U.S. Gov't, 14565039}
}
@comment{{jabref-meta: selector_author:}}
@comment{{jabref-meta: selector_journal:Adv. Drug Deliv. Rev.;Am. J. Hu
m. Genet.;Am. J. Pathol.;Ann. Appl. Stat.;Ann. Math. Statist.;Ann. N.
Y. Acad. Sci.;Ann. Probab.;Ann. Stat.;Artif. Intell. Med.;Bernoulli;Bi
ochim. Biophys. Acta;Bioinformatics;Biometrika;BMC Bioinformatics;Br.
J. Pharmacol.;Breast Cancer Res.;Cell;Cell. Signal.;Chem. Res. Toxicol
.;Clin. Cancer Res.;Combinator. Probab. Comput.;Comm. Pure Appl. Math.
;Comput. Chem.;Comput. Comm. Rev.;Comput. Stat. Data An.;Curr. Genom.;
Curr. Opin. Chem. Biol.;Curr. Opin. Drug Discov. Devel.;Data Min. Know
l. Discov.;Electron. J. Statist.;Eur. J. Hum. Genet.;FEBS Lett.;Found.
Comput. Math.;Genome Biol.;IEEE T. Neural Networ.;IEEE T. Pattern. An
al.;IEEE T. Signal. Proces.;IEEE Trans. Inform. Theory;IEEE Trans. Kno
wl. Data Eng.;IEEE/ACM Trans. Comput. Biol. Bioinf.;Int. J. Comput. Vi
sion;Int. J. Data Min. Bioinform.;Int. J. Qantum Chem.;J Biol Syst;J.
ACM;J. Am. Soc. Inf. Sci. Technol.;J. Am. Stat. Assoc.;J. Bioinform. C
omput. Biol.;J. Biol. Chem.;J. Biomed. Inform.;J. Cell. Biochem.;J. Ch
em. Inf. Comput. Sci.;J. Chem. Inf. Model.;J. Clin. Oncol.;J. Comput.
Biol.;J. Comput. Graph. Stat.;J. Eur. Math. Soc.;J. Intell. Inform. Sy
st.;J. Mach. Learn. Res.;J. Med. Chem.;J. Mol. BIol.;J. R. Stat. Soc.
Ser. B;Journal of Statistical Planning and Inference;Mach. Learn.;Math
. Program.;Meth. Enzymol.;Mol. Biol. Cell;Mol. Biol. Evol.;Mol. Cell.
Biol.;Mol. Syst. Biol.;N. Engl. J. Med.;Nat. Biotechnol.;Nat. Genet.;N
at. Med.;Nat. Methods;Nat. Rev. Cancer;Nat. Rev. Drug Discov.;Nat. Rev
. Genet.;Nature;Neural Comput.;Neural Network.;Neurocomputing;Nucleic
Acids Res.;Pattern Anal. Appl.;Pattern Recognit.;Phys. Rev. E;Phys. Re
v. Lett.;PLoS Biology;PLoS Comput. Biol.;Probab. Theory Relat. Fields;
Proc. IEEE;Proc. Natl. Acad. Sci. USA;Protein Eng.;Protein Eng. Des. S
el.;Protein Sci.;Protein. Struct. Funct. Genet.;Random Struct. Algorit
hm.;Rev. Mod. Phys.;Science;Stat. Probab. Lett.;Statistica Sinica;Theo
r. Comput. Sci.;Trans. Am. Math. Soc.;Trends Genet.;}}
@comment{{jabref-meta: selector_keywords:biogm;biosvm;breastcancer;cgh;
chemogenomics;chemoinformatics;csbcbook;csbcbook-ch1;csbcbook-ch2;csbc
book-ch3;csbcbook-ch4;csbcbook-ch5;csbcbook-ch6;csbcbook-ch7;csbcbook-
ch8;csbcbook-ch9;csbcbook-mustread;dimred;featureselection;glycans;her
g;hic;highcontentscreening;image;immunoinformatics;kernel-theory;kerne
lbook;lasso;microarray;ngs;nlp;plasmodium;proteomics;PUlearning;rnaseq
;segmentation;sirna;}}
@comment{{jabref-meta: selector_booktitle:Adv. Neural. Inform. Process
Syst.;}}
This file was generated by bibtex2html 1.97.