A Method For Predicting HLA-DRB10401 Binding Peptides

It plays an important role in the immune response that Human major histocompatibility complex (HLA) binds with antigen-binding peptides. Prediction of peptides binding with MHC classâ…¡allele HLA-DRB1* 0401 can effectively reduce the cost of experiments. The prevailing methods to predict HLA binding peptides are reviewed. Motif matching, matrix, support vector machine (SVM). The motif matching method appeared first and developed with the increased understanding of the characteristic structure of HLA-peptide complexes, that is, pockets aligned in the groove and corresponding residues fitting on them. This method is now becoming outdated due to the insufficiency and inaccuracy of information. The matrix method, the generalization of interaction between pockets of HLA and residues of bound peptide to all the positions in the groove, is the most prevalent one. Efficiency of calculation makes this method appropriate to scan for candidates of HLA binding peptides within whole expressed proteins in an organ or even in a body. A large amount of experimental binding data is necessary to determine a matrix.This paper describes support vector machine(SVM) based method developed for identifying HLA-DRB 10401 binding peptides in an antigenic sequence.SVM was trained and tested on large and clean dataset consisting of 567 binders and equal number of non-binders.The accuracy of the method was 79.54% and one of the non-binding peptide prediction accuracy was 89.74%. It proved that the new machine learning method can be effectively used to identify immune response antigen peptides.