Efficient peptideMHC-I binding prediction for alleles with few known binders

被引:80
作者
Jacob, Laurent [1 ]
Vert, Jean-Philippe [1 ]
机构
[1] Ecole Mines Paris, Ctr Computat Biol, F-77305 Fontainebleau, France
关键词
D O I
10.1093/bioinformatics/btm611
中图分类号
Q5 [生物化学];
学科分类号
071010 ; 081704 ;
摘要
Motivation: In silico methods for the prediction of antigenic peptides binding to MHC class I molecules play an increasingly important role in the identification of T-cell epitopes. Statistical and machine learning methods in particular are widely used to score candidate binders based on their similarity with known binders and non-binders. The genes coding for the MHC molecules, however, are highly polymorphic, and statistical methods have difficulties building models for alleles with few known binders. In this context, recent work has demonstrated the utility of leveraging information across alleles to improve the performance of the prediction. Results: We design a support vector machine algorithm that is able to learn peptideMHC-I binding models for many alleles simultaneously, by sharing binding information across alleles. The sharing of information is controlled by a user-defined measure of similarity between alleles. We show that this similarity can be defined in terms of supertypes, or more directly by comparing key residues known to play a role in the peptideMHC binding. We illustrate the potential of this approach on various benchmark experiments where it outperforms other state-of-the-art methods.
引用
收藏
页码:358 / 366
页数:9
相关论文
共 41 条
[1]  
[Anonymous], 2004, KERNEL METHODS PATTE
[2]   DynaPred: A structure and sequence based method for the prediction of MHC class I binding peptide sequences and conformations [J].
Antes, Iris ;
Siu, Shirley W. I. ;
Lengauer, Thomas .
BIOINFORMATICS, 2006, 22 (14) :E16-E24
[3]   THEORY OF REPRODUCING KERNELS [J].
ARONSZAJN, N .
TRANSACTIONS OF THE AMERICAN MATHEMATICAL SOCIETY, 1950, 68 (MAY) :337-404
[4]   MHCBN: a comprehensive database of MHC binding and non-binding peptides [J].
Bhasin, M ;
Singh, H ;
Raghava, GPS .
BIOINFORMATICS, 2003, 19 (05) :665-666
[5]   Prediction of CTL epitopes using QM, SVM and ANN techniques [J].
Bhasin, M ;
Raghava, GPS .
VACCINE, 2004, 22 (23-24) :3195-3204
[6]  
Bottou L., 2007, LARGE SCALE KERNEL M
[7]   Structural prediction of peptides binding to MHC class I molecules [J].
Bui, HH ;
Schiewe, AJ ;
von Grafenstein, H ;
Haworth, IS .
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS, 2006, 63 (01) :43-52
[8]   Automated generation and evaluation of specific MHC binding predictive tools:: ARB matrix applications [J].
Bui, HH ;
Sidney, J ;
Peters, B ;
Sathiamurthy, M ;
Sinichi, A ;
Purton, KA ;
Mothé, BR ;
Chisari, FV ;
Watkins, DI ;
Sette, A .
IMMUNOGENETICS, 2005, 57 (05) :304-314
[9]   Harnessing bioinformatics to discover new vaccines [J].
Davies, Matthew N. ;
Flower, Darren R. .
DRUG DISCOVERY TODAY, 2007, 12 (9-10) :389-395
[10]   Prediction of MHC class I binding peptides, using SVMHC -: art. no. 25 [J].
Dönnes, P ;
Elofsson, A .
BMC BIOINFORMATICS, 2002, 3 (1)