Towards designing improved cancer immunotherapy targets with a peptide-MHC-I presentation model, HLApollo
William John Thrift, Nicolas Lounsbury, Quade Broadwell, Amy Heidersbach, Emily Freund, Yassan Abdolazimi, Qui Phung, Jieming Chen, Aude-Hélène Capietto, Ann-Jay Tong, Christopher M. Rose, Craig Blanchette, Jennie R. Lill, Benjamin Haley, Lélia Delamarre, Richard Bourgon, Kai Liu, Suchit Jhunjhunwala
Abstract
Based on the success of cancer immunotherapy, personalized cancer vaccines have emerged as a leading oncology treatment. Antigen presentation on MHC class I (MHC-I) is crucial for the adaptive immune response to cancer cells, necessitating highly predictive computational methods to model this phenomenon. Here, we introduce HLApollo, a transformer-based model for peptide-MHC-I (pMHC-I) presentation prediction, leveraging the language of peptides, MHC, and source proteins. HLApollo provides end-to-end treatment of MHC-I sequences and deconvolution of multi-allelic data, using a negative-set switching strategy to mitigate misassigned negatives in unlabelled ligandome data. HLApollo shows a 12.65% increase in average precision (AP) on ligandome data and a 4.1% AP increase on immunogenicity test data compared to next-best models. Incorporating protein features from protein language models yields further gains and reduces the need for gene expression measurements. Guided by clinical use, we demonstrate pan-allelic generalization which effectively captures rare alleles in underrepresented ancestries. Computational methods are used to predict which peptides or antigens are able to bind to MHC in order to activate T cell receptors in neoantigen-directed immunotherapies. Here the authors present an accurate transformer-based method to consider not only the peptide and MHC but also the source antigenic protein to predict peptides which bind to MHC molecules.