Prediction of MHC class I binding peptides, using SVMHC

BMC Bioinformatics

Pierre Dönnes²  Arne Elofsson¹ 

[1] Stockholm Bioinformatics Center, SCFAB, Stockholm University, SE-106 91 Stockholm, Sweden

[2] Center for Bioinformatics Saar, Saarland University, D-660 41 Saarbrücken, Germany

关键词: Support Vector Machines;    Machine Learning;    Peptide prediction;    MHC class I;   

Others  :  1171927
DOI  :  10.1186/1471-2105-3-25

 received in 2002-03-22, accepted in 2002-09-11,  发布年份 2002

【 摘 要 】

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/ webcite.

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.

【 授权许可】

   
2002 Dönnes and Elofsson; licensee BioMed Central Ltd. This is an Open Access article: verbatim copying and redistribution of this article are permitted in all media for any purpose, provided this notice is preserved along with the article's original URL.

【 图 表 】

Figure 1.

Figure 2.

Figure 3.

【 参考文献 】

• [1]Sette A, Chesnut R, Fikes J: HLA expression in cancer: implications for T cell-based immunotherapy. Immunogenetics 2001, 53:255-263.
• [2]Yewdell J, Bennink J: Immunodominance in major histocompatibility complex class I-restricted T lymphocyte responses. Annu Rev Immunol 1999, 17:51-81.
• [3]Rotzschke O, Falk K, Stevanovic S, Jung G, Rammensee H: Peptide motifs of closely related HLA class I molecules encompass substantial differences. European Journal of Immunology 1992, 22:2453-2456.
• [4]Rammensee H-G, Friede T, Stevanovic S: MHC ligands and peptide motifs: first listing. Immunogenetics 1995, 41:962-965.
• [5]Gribskov M, McLachlan AD, Eisenberg D: Profile analysis: detection of distantly related proteins. Proc Natl Acad Sci U S A 1987, 84:4355-4358.
• [6]Rammensee H-G, Bachman J, Philipp N, Emmerich N, Bachor OA, Stevanovic S: SYFPEITHI: a database for MHC ligands and peptide motifs. Immunogenetics 1999, 50:213-219.
• [7]Parker KC, Bednarek MA, Coligan JE: Scheme for ranking potential HLA-A2 binding peptides based on independent binding of individual peptide side-chains. J Immunol 1994, 152:163-175.
• [8]Gulukota K, Sidney J, Sette A, DeLisi C: Two complementary methods for predicting peptides binding major histocompatibility complex molecules. J Mol Biol 1997, 267:1258-1267.
• [9]Baldi P, Brunak S: Bioinformatics, the machine learning approach. MIT Press Cambridge Massachusetts, London England 1998.
• [10]Honeyman M, Brusic V, Stone N, Harrison L: Neural network-based prediction of candidate t-cell epitopes. Nature Biotechnology 1998, 16:966-969.
• [11]Mamitsuka H: MHC molecules using supervised learning of hidden Markov models. Proteins: Structure, Function and Genetics 1998, 33:460-474.
• [12]Brusic V, Harrison L: Prediction of MHC binding peptides using artificial neural networks, Complex Systems:. In In Complex Systems: Mechanism of Adaptation. Edited by Stonier RJ, Yu XS. IOS Press, Amsterdam, The Netherlands/OHMSHA Tokyo; 1994:253-260.
• [13]Schueler-Furman O, Altuvia Y, Sette A: Structure-based prediction of binding peptides to MHC class I molecules: application to a broad range of MHC alleles. Protein Science 2000, 9:1838-1846.
• [14]Brown M, Grundy WN, Lin D, Cristianini N, Sugnet CW, S T, Ares M Jr, Haussler D: Genetics knowledge-based analysis of microarray gene expression data by using support vector machines. Proc Natl Acad Sci USA 2000, 97:262-267.
• [15]Cristianini N, Shawe-Taylor J: Support vector machines and other kernel-based learning methods. Cambridge University Press, Cambridge England The Edinburgh Building, Cambridge, CB2 2RU, UK 2000.
• [16]Ding C, Dubchak I: Multi-class protein fold recognition using support vector machines and neural networks. Bioinformatics 2001, 17:349-358.
• [17]Joachims T: Making large-Scale SVM Learning Practical. In Advances in kernel methods – support vector learning. Edited by B Schölkopf and C Burges and A Smola. MIT Press, Cambridge Massachusetts, London England; 1999.
• [18]Vapnik VN: The Nature of Statistical Learning Theory. Wiley New York 1998.
• [19]Rost B, Sander C: Prediction of protein secondary structure structure at better than 70% accuracy. J Mol Biol 1993, 232:584-599.
• [20]Matthews B: Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochim Biophys Acta 1975, 405:442-451.
• [21]Brusic V, Rudy G, Harrsison LC: MHCPEP, a database of MHC-binding peptides: update 1997. Nucleic Acids Research 1998, 26:368-171.
• [22]Hubbard T, Barker D, Birney E, Cameron G, Chen Y, Clark L, Cox T, Cuff J, Curwen V, Down T, Durbin R, Eyras E, Gilbert J, Hammond M, Huminiecki L, Kasprzyk A, Lehvaslaiho H, Lijnzaad P, Melsopp C, Mongin E, Pettett R, Pocock M, Potter S, Rust A, Schmidt E, Searle S, Slater G, Smith J, Spooner W, Stabenau A, Stalker J, Stupka E, Ureta-Vidal A, Vastrik I, Clamp M: The Ensembl genome database project. Nucleic Acids Research 2002, 30:38-41.
• [23]Lindahl E, Elofsson A: Identification of related proteins on family, superfamily and fold level. J Mol Biol 2000, 295:613-625.