MHCflurry 2.0: Improved Pan-Allele Prediction of MHC Class I-Presented Peptides by Incorporating Antigen Processing

Computational prediction of the peptides presented on major histocompatibility complex (MHC) class I proteins is an important tool for studying T cell immunity. The data available to develop such predictors have expanded with the use of mass spectrometry to identify naturally presented MHC ligands. In addition to elucidating binding motifs, the identified ligands also reflect the antigen processing steps that occur prior to MHC binding. Here, we developed an integrated predictor of MHC class I presentation that combines new models for MHC class I binding and antigen processing. Considering only peptides first predicted by the binding model to bind strongly to MHC, the antigen processing model is trained to discriminate published mass spectrometry-identified MHC class I ligands from unobserved peptides. The integrated model outperformed the two individual components as well as NetMHCpan 4.0 and MixMHCpred 2.0.2 on held-out mass spectrometry experiments. Our predictors are implemented in the open source MHCflurry package, version 2.0 (github.com/openvax/mhcflurry). [Display omitted] •New pan-allele MHC class I binding predictor•Antigen processing predictor trained on mass spectrometry-identified MHC ligands•Combined model outperforms existing methods•Open source Python package with command line and library interfaces O’Donnell et al. developed improved models for predicting the antigens available for recognition by cytotoxic T cells. Separate predictors of MHC class I binding and antigen processing were trained using published datasets of peptides naturally presented on MHC. The software is open source and readily incorporated into workflows for neoantigen discovery and vaccine design.