Properties of CD8 T-cell-recognized neoantigens in different tumor types.

Background: Neoantigen-based immunotherapies rely on computational tools predicting peptide immunogenicity based on properties such as its expression level, binding affinity to human leukocyte antigen (HLA), likelihood of proteasomal cleavage and dissimilarity from wild-type peptide. However, current datasets are scarce and limited to highly mutated tumor types such as melanoma and lung cancer, leaving uncertainty about the value of these properties in other tumor types. Materials and methods: To investigate this, we retrospectively analyzed the properties of immunogenic neoantigens identified in CD8 T-cell recognition screens of predicted neoantigens in tumor-infiltrating lymphocytes (TILs) from 12 melanoma patients and peripheral blood mononuclear cells (PBMCs) from 14 patients with mesothelioma, triple-negative breast cancer or urothelial cancer. In both experimental settings, CD8 T-cell recognition was assessed using a combinatorial peptide-HLA (pHLA) multimer-based technology. Results: CD8 T-cell responses were detected against in total 34 of the 8103 predicted neoantigens (0.4%). In both PBMCs and TILs, the eluted ligand (EL) score-the predicted likelihood of a pHLA being presented on the cell surface-was the strongest predictor of immunogenicity, followed by predicted HLA binding affinity. Moreover, in the TILs, the frequency of neoantigen-specific CD8 T cells was strongly correlated with these properties across the 12 patients. Conclusions: These findings underscore the value of both EL score and HLA binding affinity as key predictors of neoantigen immunogenicity in different tumor types. Furthermore, we demonstrate for the first time an immunodominance hierarchy of neoantigen-specific CD8 T-cell responses across patients in