biostudies-literatureXu MThe 2024 STCSM 'Science and Technology Innovation Action Plan' Computational Biology Program in ShanghaiNational Natural Science Foundation of ChinaNational Center of Technology Innovation for Biopharmaceuticals in Chinabbaf716https://www.ebi.ac.uk/biostudies/studies/S-EPMC12790622biostudies-literatureUnknown27(1)The ability of T-cell receptors (TCRs) to recognize neoantigens is fundamental to the initiation and maintenance of adaptive immune responses. In TCR-based immunotherapies, elucidating the recognition patterns of TCRs for peptides and accurately identifying therapeutically relevant TCR-peptide pairs remain critical challenges. Here, we present a novel dual-pathway network model, ProTCR, which integrates the protein language model ProtT5 with deep learning methods. By incorporating both global and local feature extraction mechanisms, ProTCR enables efficient representation of amino acid sequences, thereby enhancing the model's generalizability across diverse data distributions and improving its biological interpretability. ProTCR demonstrates robust performance and broad applicability acrosBriefings in bioinformaticsProTCR: a protein language model-driven framework for decoding TCR-antigen recognition toward precision immunotherapies.PMC12790622NCTIB2022HS020073187082924JS2840300Lu MXu MChen LLiu PLiu QXie LLin YZhang SfalseProTCR: a protein language model-driven framework for decoding TCR-antigen recognition toward precision immunotherapies.The ability of T-cell receptors (TCRs) to recognize neoantigens is fundamental to the initiation and maintenance of adaptive immune responses. In TCR-based immunotherapies, elucidating the recognition patterns of TCRs for peptides and accurately identifying therapeutically relevant TCR-peptide pairs remain critical challenges. Here, we present a novel dual-pathway network model, ProTCR, which integrates the protein language model ProtT5 with deep learning methods. By incorporating both global and local feature extraction mechanisms, ProTCR enables efficient representation of amino acid sequences, thereby enhancing the model's generalizability across diverse data distributions and improving its biological interpretability. ProTCR demonstrates robust performance and broad applicability acros2026-01-01T00:00:00Z2026 Jan2026-06-06T11:30:26.721Z2026-05-29T03:12:42.559ZS-EPMC127906224152023010.1093/bib/bbaf716