ABSTRACT A large number of machine learning-based Major Histocompatibility Complex (MHC) binding affinity (BA) prediction tools have been developed and are widely used for both investigational and therapeutic applications, so it is important to explore differences in tool outputs. We examined predictions of four popular tools (netMHCpan, HLAthena, MHCflurry, and MHCnuggets) across a range of possible peptide sources (human, viral, and randomly generated) and MHC class I alleles. We uncovered inconsistencies in predictions of BA, allele promiscuity and the relationship between physical properties of peptides by source and BA predictions, as well as quality of training data. Our work raises fundamental questions about the fidelity of peptide-MHC binding prediction tools and their real-world implications.

Discordant results among MHC binding affinity prediction tools