Performance Evaluation of MULTIEPD1 on Prediction of MHC Class I Binders

Identification of T-cell epitopes (parts of antigenic proteins to which the T-cells receptor respond) is important in the development of vaccines and immunotherapeutics. We developed MULTIPRED1 (http://antigen.i2r.a-star.edu.sg/multipred1/), a Web-based computational system for prediction of peptides (protein fragments) that bind multiple related human leukocyte antigen (HLA) molecules (the human major histocompatibility complex - MHC molecules). In this paper, the performance of MULTIPRED1 in predicting individual 9-mer binders to HLA-A2 and A3 molecules was compared with five other publicly available prediction tools, SFYPEITHI, BIMAS, SMM, RANKPEP and SVMHC. The results show that MULTIPRED1 is both sensitive and specific for prediction of binders to individual HLA alleles and demonstrates comparable accuracy as those of other prediction tools. Majority voting was applied to combine the strength of the three prediction models of MULTIPRED1 and results indicate that better prediction performance can be achieved. MULTIPRED1 is useful in the selection of key antigenic regions to minimize the number of experiments required for mapping of promiscuous T-cell epitopes.