A structure-informed deep learning framework for modeling TCR-peptide-HLA interactions

Interactions between T cell receptors (TCRs), peptides, and human leukocyte antigens (HLAs) underlie antigen-specific T cell immunity. Despite substantial advances in prediction methods, accurate modeling of coupled TCR–peptide–HLA recognition remains underdeveloped, limiting applications such as TCR and neoepitope prioritization in cancer and antigen identification in autoimmunity. Here we present StriMap, a unified framework for predicting TCR–peptide–HLA interactions by integrating physicochemical, sequence-context, and structural features at recognition interfaces. StriMap achieves state-of-the-art performance with improved generalizability and enables applications in cancer and autoimmunity. As a case study, we screened 13 million peptides from 43,241 bacterial proteins and identified candidate molecular mimics that were experimentally validated to activate T cells expressing an ankylosing spondylitis (AS)-associated TCR. A top validated peptide was enriched in patients with inflammatory bowel disease (IBD), suggesting potential shared microbial triggers. Overall, StriMap provides a framework for rational immunotherapy design and dissecting antigenic drivers of autoimmunity. Bioinformatics tools can be used for modelling T cell receptor (TCR)-peptide-Human Leukocyte antigen (HLA) interactions since these are important in the initiation of immune responses. Here the authors present StriMap a framework for predicting TCR-peptide-HLA interactions by integrating physicochemical, sequence-context and structural features and show application in an ankylosing spondylitis (AS) case study and experimentally validate predicted peptides.