Abstract
One Sentence Summary Accurate epitope prediction was achieved via machine learning by incorporating TCR-peptide contact profiles.
Abstract Computational methodologies to predict epitopes for cytotoxic T lymphocytes (CTLs) will galvanize vaccine research and pave the way toward targeted immunotherapy of infections and cancer. However, the classification of immunogenic epitopes and non-immunogenic major histocompatibility complex (MHC) class I ligands in silico has yet to attain sufficient accuracy. Here, we demonstrated highly accurate epitope prediction by a machine learning-based classifier incorporating T cell receptor (TCR)-peptide contact profiles, with an accuracy of 0.77 and an area under the curve of 0.84 in hold-out validation. Predictive accuracy was retained for five major human leucocyte antigen supertypes. Successful prediction using independent datasets of viral epitopes and tumor neoepitopes was demonstrated. Collectively, this is the first study demonstrating accurate and generalizable CTL immunogenicity prediction from the TCR-peptide axis. The R package Repitope was implemented to maximize code reusability. Prospective validation in vaccination and/or cancer immunotherapy cohorts is warranted.
Footnotes
Conflict of Interest (COI): The authors declare no conflicts of interest.