HLA binding is currently the most well-established criteria for ranking neoantigen candidates. Recent advances in training data generated from mass spectrometry, provide a larger dataset of peptide binders and non-binders for individual HLA alleles. This new binding data takes two important additional components into consideration: cleavage and transportation, which are critically important for presentation assessment. We leverage this advancement, developing a brand new MHC binding prediction algorithm which outperforms both NetMHC predictors across the range of prediction score cut-offs (Figure 5).

Figure 5