Softwares
KISS (Kernel-based Inter-allele peptide binding prediction SyStem) is a server that predicts epitopes of MHC-I molecules for a variety of different alleles. It is based on a multitask support vector machine.
Reference
[1] L. Jacob and J.-P. Vert, Efficient peptide-MHC-I binding prediction for alleles with few known binders, Bioinformatics, vol.24, n.3, p.358-366, 2008.
DSIR (Design of siRNA) helps you design your siRNA by predicting their efficacy. It is based on a sparse linear model based on sequence features.
Reference
[1] J.-P. Vert, N. Foveau, C. Lajaunie and Y.Vandenbrouck, An accurate and interpretable model for siRNA efficacy prediction, BMC Bioinformatics 2006, 7:520.
ChemCpp is a C++ toolbox for chemoinformatics focusing on the computation of kernel functions between chemical compounds.
Reference
[1] P. Mahé, N. Ueda, T. Akutsu, J.-L. Perret and J.-P. Vert, Graph kernels for molecular structure-activity relationship analysis with support vector machines, Journal of Chemical Information and Modeling, vol. 45, n. 4, 939 -951, 2005.
[2] P. Mahé, L. Ralaivola, V. Stoven and J.-P. Vert, The pharmacophore kernel for virtual screening with support vector machines,Journal of Chemical Information and Modeling, vol. 46, n.5, p.2003-2014, 2006.
[3] P. MAhé, Kernels for molecules and applications in virtual screening with support vector machines, PhD thesis, Ecole des Mines de Paris, 2006.
SLP-local is a server for the prediction of protein subcellular localization from their amino-acid sequence with support vector machines
Reference
[1] S. Matsuda, J.-P. Vert, H. Saigo, N. Ueda, H. Toh, and T. Akutsu, A novel representation of protein sequences for prediction of subcellular location using support vector machines, Protein Science, vol.14, p.2804-2813, 2005.
Local alignment kernels
The local alignment kernel is a similarity score between biological sequences. Combined with support vector machines it leads to very good performance for remote homology detection, and might be useful for other applications as well. This C code should allow you to compute the local alignment kernel between protein sequences encoded in FASTA file.
Reference
[1] J.-P. Vert, H. Saigo, T. Akutsu, Local alignment kernels for biological sequences, in Kernel Methods in Computational Biology, B. Schölkopf, K. Tsuda and J.-P. Vert (Eds.), MIT Press, p.131-154, 2004.[pdf]
[2] H. Saigo, J.-P. Vert, T. Akutsu and N. Ueda, Protein homology detection using string alignment kernels, Bioinformatics, vol.20, p.1682-1689, 2004.
Vert Jean-Philippe
Last modified: Fri Mar 14 09:28:38 CET 2008