Pan-Specific Prediction of Peptide-MHC Class I Complex Stability, a Correlate of T Cell Immunogenicity.

Binding of peptides to MHC class I (MHC-I) molecules is the most selective event in the processing and presentation of Ags to CTL, and insights into the mechanisms that govern peptide–MHC-I binding should facilitate our understanding of CTL biology. Peptide–MHC-I interactions have traditionally been quantified by the strength of the interaction, that is, the binding affinity, yet it has been shown that the stability of the peptide–MHC-I complex is a better correlate of immunogenicity compared with binding affinity. In this study, we have experimentally analyzed peptide–MHC-I complex stability of a large panel of human MHC-I allotypes and generated a body of data sufficient to develop a neural network–based pan-specific predictor of peptide–MHC-I complex stability. Integrating the neural network predictors of peptide–MHC-I complex stability with state-of-the-art predictors of peptide–MHC-I binding is shown to significantly improve the prediction of CTL epitopes. The method is publicly available at http://www.cbs.dtu.dk/services/NetMHCstabpan.