{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T18:46:15Z","timestamp":1782413175199,"version":"3.54.5"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1014396","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000}}],"reference-count":53,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225109, 62450112"],"award-info":[{"award-number":["62225109, 62450112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"King Abdullah University of Science and Technology (KAUST) Office of Research Administration","award":["REI\/1\/5234-01-01, REI\/1\/5414-01-01, REI\/1\/5289-01-01, REI\/1\/5404-01-01, REI\/1\/5992-01-01, URF\/1\/4663-01-01"],"award-info":[{"award-number":["REI\/1\/5234-01-01, REI\/1\/5414-01-01, REI\/1\/5289-01-01, REI\/1\/5404-01-01, REI\/1\/5992-01-01, URF\/1\/4663-01-01"]}]},{"name":"Center of Excellence for Smart Health","award":["5932"],"award-info":[{"award-number":["5932"]}]},{"name":"Center of Excellence on Generative AI","award":["5940"],"award-info":[{"award-number":["5940"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"\n Deciphering how human T cells recognise peptide-HLA (pHLA) complexes underpins next-generation vaccines and personalised immunotherapies, yet extreme sequence diversity and paired-chains interdependence still hamper reliable\n in silico<\/jats:italic>\n prediction of T-cell receptor (TCR) specificity. To overcome these hurdles, we built TCRBinder, a paired-chain-aware deep model with a multi-branch encoder that routes each molecular component through dedicated transformer-based modules to capture contextual signals in both HLA pseudo-sequences and antigenic peptides while simultaneously processing the TCR\n \n \n \n \n \n \u03b1<\/mml:mi>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n and\n \n \n \n \n \n \u03b2<\/mml:mi>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n chains. This design captures the synergistic interaction between paired chains to emulate peptide-HLA-TCR (PHT) interactions and expose residue-level contact motifs. Across PHT and peptide-TCR (pTCR) benchmarks, the model delivered state-of-the-art performance (AUC-ROC\u2009=\u20090.911, AUPR\u2009=\u20090.791 for the PHT task) and remained superior on multiple independent datasets. We tracked the dynamics of clonal expansion and, in a large SARS-CoV-2 repertoire containing completely unseen peptides, improved the AUC-ROC by up to 16.3% over the leading alternatives. Moreover, TCRBinder provided mechanistic insights by pinpointing contact hotspots and quantifying residue contributions to binding probability. These capabilities position TCRBinder as a versatile tool for rational antigen discovery, immunotherapy stratification, and neoantigen vaccine design.\n <\/jats:p>","DOI":"10.1371\/journal.pcbi.1014396","type":"journal-article","created":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T17:48:08Z","timestamp":1782150488000},"page":"e1014396","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["TCRBinder: Unified pre-trained language model with paired-chain synergy for predicting T-cell receptor binding specificity"],"prefix":"10.1371","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8022-9793","authenticated-orcid":true,"given":"Weihe","family":"Dong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6645-6890","authenticated-orcid":true,"given":"Xiaokun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1347-3491","authenticated-orcid":true,"given":"Kuanquan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suyu","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gongning","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiansong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guohua","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"issue":"6382","key":"pcbi.1014396.ref001","doi-asserted-by":"crossref","first-page":"1350","DOI":"10.1126\/science.aar4060","article-title":"Cancer immunotherapy using checkpoint blockade","volume":"359","author":"A Ribas","year":"2018","journal-title":"Science"},{"issue":"11","key":"pcbi.1014396.ref002","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1038\/s41577-020-0306-5","article-title":"A guide to cancer immunotherapy: from T cell basic science to clinical practice","volume":"20","author":"AD Waldman","year":"2020","journal-title":"Nat Rev Immunol"},{"issue":"2","key":"pcbi.1014396.ref003","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1038\/s41577-020-0275-8","article-title":"Dissecting the mechanisms of immune checkpoint therapy","volume":"20","author":"P Sharma","year":"2020","journal-title":"Nat Rev Immunol"},{"issue":"7637","key":"pcbi.1014396.ref004","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1038\/nature21349","article-title":"Elements of cancer immunity and the cancer-immune set point","volume":"541","author":"DS Chen","year":"2017","journal-title":"Nature"},{"issue":"1","key":"pcbi.1014396.ref005","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.immuni.2019.12.011","article-title":"Top 10 Challenges in Cancer Immunotherapy","volume":"52","author":"PS Hegde","year":"2020","journal-title":"Immunity"},{"issue":"4","key":"pcbi.1014396.ref006","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1016\/j.ccell.2020.07.013","article-title":"Identifying and Targeting Human Tumor Antigens for T Cell-Based Immunotherapy of Solid Tumors","volume":"38","author":"V Leko","year":"2020","journal-title":"Cancer Cell"},{"issue":"7662","key":"pcbi.1014396.ref007","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1038\/nature22991","article-title":"An immunogenic personal neoantigen vaccine for patients with melanoma","volume":"547","author":"PA Ott","year":"2017","journal-title":"Nature"},{"issue":"7662","key":"pcbi.1014396.ref008","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1038\/nature23003","article-title":"Personalized RNA mutanome vaccines mobilize poly-specific therapeutic immunity against cancer","volume":"547","author":"U Sahin","year":"2017","journal-title":"Nature"},{"issue":"6583","key":"pcbi.1014396.ref009","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1126\/science.abl5447","article-title":"Molecular signatures of antitumor neoantigen-reactive T cells from metastatic human cancers","volume":"375","author":"FJ Lowery","year":"2022","journal-title":"Science"},{"issue":"1","key":"pcbi.1014396.ref010","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.immuni.2013.07.012","article-title":"Oncology meets immunology: the cancer-immunity cycle","volume":"39","author":"DS Chen","year":"2013","journal-title":"Immunity"},{"issue":"7","key":"pcbi.1014396.ref011","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.adf3700","article-title":"TCR-engineered T cell therapy in solid tumors: State of the art and perspectives","volume":"9","author":"E Baulu","year":"2023","journal-title":"Sci Adv"},{"issue":"7870","key":"pcbi.1014396.ref012","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1038\/s41586-021-03752-4","article-title":"Transcriptional programs of neoantigen-specific TIL in anti-PD-1-treated lung cancers","volume":"596","author":"JX Caushi","year":"2021","journal-title":"Nature"},{"issue":"7870","key":"pcbi.1014396.ref013","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1038\/s41586-021-03704-y","article-title":"Phenotype, specificity and avidity of antitumour CD8+ T cells in melanoma","volume":"596","author":"G Oliveira","year":"2021","journal-title":"Nature"},{"issue":"7953","key":"pcbi.1014396.ref014","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1038\/s41586-022-05531-1","article-title":"Non-viral precision T\u2009cell receptor replacement for personalized cell therapy","volume":"615","author":"SP Foy","year":"2023","journal-title":"Nature"},{"issue":"5","key":"pcbi.1014396.ref015","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1016\/j.coi.2013.09.017","article-title":"Immunosequencing: applications of immune repertoire deep sequencing","volume":"25","author":"H Robins","year":"2013","journal-title":"Curr Opin Immunol"},{"key":"pcbi.1014396.ref016","doi-asserted-by":"crossref","first-page":"1516","DOI":"10.3389\/fimmu.2019.01516","article-title":"Single T Cell Sequencing Demonstrates the Functional Role of \u03b1\u03b2 TCR Pairing in Cell Lineage and Antigen Specificity","volume":"10","author":"JA Carter","year":"2019","journal-title":"Front Immunol"},{"issue":"3","key":"pcbi.1014396.ref017","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1038\/s41590-022-01129-x","article-title":"Repertoire analyses reveal T cell antigen receptor sequence features that influence T cell fate","volume":"23","author":"KA Lagattuta","year":"2022","journal-title":"Nat Immunol"},{"issue":"17","key":"pcbi.1014396.ref018","doi-asserted-by":"crossref","DOI":"10.1002\/cam4.70164","article-title":"Human TCR repertoire in cancer","volume":"13","author":"L Chen","year":"2024","journal-title":"Cancer Med"},{"issue":"12","key":"pcbi.1014396.ref019","doi-asserted-by":"crossref","first-page":"1274","DOI":"10.1038\/ni.3873","article-title":"Adaptive Immune Receptor Repertoire Community recommendations for sharing immune-repertoire sequencing data","volume":"18","author":"F Rubelt","year":"2017","journal-title":"Nat Immunol"},{"issue":"1","key":"pcbi.1014396.ref020","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1038\/s41591-022-02110-9","article-title":"T cell receptor repertoires associated with control and disease progression following Mycobacterium tuberculosis infection","volume":"29","author":"M Musvosvi","year":"2023","journal-title":"Nat Med"},{"issue":"10","key":"pcbi.1014396.ref021","doi-asserted-by":"crossref","first-page":"864","DOI":"10.1038\/s42256-021-00383-2","article-title":"Deep learning-based prediction of the T cell receptor-antigen binding specificity","volume":"3","author":"T Lu","year":"2021","journal-title":"Nat Mach Intell"},{"issue":"4","key":"pcbi.1014396.ref022","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbae302","article-title":"HLAIImaster: a deep learning method with adaptive domain knowledge predicts HLA II neoepitope immunogenic responses","volume":"25","author":"Q Yang","year":"2024","journal-title":"Brief Bioinform"},{"issue":"1","key":"pcbi.1014396.ref023","article-title":"Meta learning for mutant HLA class I epitope immunogenicity prediction to accelerate cancer clinical immunotherapy","volume":"26","author":"L Xu","year":"2024","journal-title":"Brief Bioinform"},{"key":"pcbi.1014396.ref024","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkaa379","article-title":"NetMHCpan-4.1 and NetMHCIIpan-4.0: improved predictions of MHC antigen presentation by concurrent motif deconvolution and integration of MS MHC eluted ligand data","volume":"48","author":"B Reynisson","year":"2020","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"pcbi.1014396.ref025","article-title":"MHCflurry 2.0: Improved Pan-Allele Prediction of MHC Class I-Presented Peptides by Incorporating Antigen Processing","volume":"11","author":"TJ O\u2019Donnell","year":"2020","journal-title":"Cell Syst"},{"issue":"4","key":"pcbi.1014396.ref026","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbaa318","article-title":"Current challenges for unseen-epitope TCR interaction prediction and a new perspective derived from image classification","volume":"22","author":"P Moris","year":"2021","journal-title":"Brief Bioinform"},{"key":"pcbi.1014396.ref027","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1038\/s42256-023-00634-4","article-title":"Characterizing the interaction conformation between T-cell receptors and epitopes with deep learning","volume":"5","author":"X Peng","year":"2023","journal-title":"Nat Mach Intell"},{"issue":"20","key":"pcbi.1014396.ref028","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.abf5835","article-title":"A framework for highly multiplexed dextramer mapping and prediction of T cell receptor sequences to antigen specificity","volume":"7","author":"W Zhang","year":"2021","journal-title":"Sci Adv"},{"issue":"9","key":"pcbi.1014396.ref029","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1013050","article-title":"THLANet: A deep learning framework for predicting TCR-pHLA binding in immunotherapy applications","volume":"21","author":"X Long","year":"2025","journal-title":"PLoS Comput Biol"},{"issue":"9","key":"pcbi.1014396.ref030","doi-asserted-by":"crossref","first-page":"1017","DOI":"10.1038\/s41592-022-01578-0","article-title":"VDJdb in the pandemic era: a compendium of T cell receptors specific for SARS-CoV-2","volume":"19","author":"M Goncharov","year":"2022","journal-title":"Nat Methods"},{"key":"pcbi.1014396.ref031","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gky1006","article-title":"The Immune Epitope Database (IEDB): 2018 update","volume":"47","author":"R Vita","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1014396.ref032","doi-asserted-by":"crossref","first-page":"3333","DOI":"10.1016\/j.cell.2023.06.020","article-title":"Targeting of multiple tumor-associated antigens by individual T cell receptors during successful cancer immunotherapy","volume":"186","author":"G Dolton","year":"2023","journal-title":"Cell"},{"issue":"1","key":"pcbi.1014396.ref033","doi-asserted-by":"crossref","first-page":"2401","DOI":"10.1038\/s41467-023-37532-7","article-title":"Structural analysis of cancer-relevant TCR-CD3 and peptide-MHC complexes by cryoEM","volume":"14","author":"K Saotome","year":"2023","journal-title":"Nat Commun"},{"issue":"1","key":"pcbi.1014396.ref034","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1038\/s42003-024-06209-2","article-title":"Identification and affinity enhancement of T-cell receptor targeting a KRASG12V cancer neoantigen","volume":"7","author":"M Zhang","year":"2024","journal-title":"Commun Biol"},{"issue":"4","key":"pcbi.1014396.ref035","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.adr8638","article-title":"De novo design of peptide binders to conformationally diverse targets with contrastive language modeling","volume":"11","author":"S Bhat","year":"2025","journal-title":"Sci Adv"},{"key":"pcbi.1014396.ref036","article-title":"STAPLER: efficient learning of TCR-peptide specificity prediction from full-length TCR-peptide data","author":"BPY Kwee","year":"2023","journal-title":"bioRxiv"},{"key":"pcbi.1014396.ref037","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.93934","article-title":"Enhancing TCR specificity predictions by combined pan- and peptide-specific training, loss-scaling, and sequence similarity integration","volume":"12","author":"MF Jensen","year":"2024","journal-title":"Elife"},{"issue":"1","key":"pcbi.1014396.ref038","doi-asserted-by":"crossref","first-page":"3211","DOI":"10.1038\/s41467-024-47461-8","article-title":"Deep learning predictions of TCR-epitope interactions reveal epitope-specific chains in dual alpha T cells","volume":"15","author":"G Croce","year":"2024","journal-title":"Nat Commun"},{"issue":"11","key":"pcbi.1014396.ref039","doi-asserted-by":"crossref","first-page":"1344","DOI":"10.1038\/s42256-024-00913-8","article-title":"Epitope-anchored contrastive transfer learning for paired CD8 T cell receptor\u2013antigen recognition","volume":"6","author":"Y Zhang","year":"2024","journal-title":"Nat Mach Intell"},{"key":"pcbi.1014396.ref040","doi-asserted-by":"crossref","first-page":"100045","DOI":"10.1016\/j.immuno.2024.100045","article-title":"Lessons learned from the IMMREP23 TCR-epitope prediction challenge","volume":"16","author":"M Nielsen","year":"2024","journal-title":"ImmunoInformatics"},{"key":"pcbi.1014396.ref041","unstructured":"Noceda MG, et al. ImmSET: Sequence-Based Predictor of TCR-pMHC Specificity at Scale. Machine Learning for Health 2025. 2025."},{"issue":"42","key":"pcbi.1014396.ref042","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2504783122","article-title":"T cell receptor specificity landscape revealed through de novo peptide design","volume":"122","author":"GM Visani","year":"2025","journal-title":"Proc Natl Acad Sci U S A"},{"key":"pcbi.1014396.ref043","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.82813","article-title":"Structure-based prediction of T cell receptor:peptide-MHC interactions","volume":"12","author":"P Bradley","year":"2023","journal-title":"Elife"},{"key":"pcbi.1014396.ref044","article-title":"TCRmodel2: high-resolution modeling of T cell receptor recognition using deep learning","volume":"51","author":"R Yin","year":"2023","journal-title":"Nucleic Acids Res"},{"issue":"5","key":"pcbi.1014396.ref045","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1038\/s41590-022-01184-4","article-title":"SARS-CoV-2 antigen exposure history shapes phenotypes and specificity of memory CD8+ T cells","volume":"23","author":"AA Minervina","year":"2022","journal-title":"Nat Immunol"},{"issue":"11","key":"pcbi.1014396.ref046","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btae618","article-title":"Addressing the antibody germline bias and its effect on language models for improved antibody design","volume":"40","author":"TH Olsen","year":"2024","journal-title":"Bioinformatics"},{"key":"pcbi.1014396.ref047","volume-title":"A new way of exploring immunity - linking highly multiplexed antigen recognition to immune repertoire and phenotype","author":"10x Genomics, et al","year":"2022"},{"issue":"3","key":"pcbi.1014396.ref048","article-title":"TRAIT: A Comprehensive Database for T-cell Receptor-antigen Interactions","volume":"23","author":"M Wei","year":"2025","journal-title":"Genomics Proteomics Bioinformatics"},{"issue":"42","key":"pcbi.1014396.ref049","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2408696121","article-title":"Limits on inferring T cell specificity from partial information","volume":"121","author":"J Henderson","year":"2024","journal-title":"Proc Natl Acad Sci U S A"},{"key":"pcbi.1014396.ref050","doi-asserted-by":"crossref","first-page":"114704","DOI":"10.1016\/j.celrep.2024.114704","article-title":"The observed T cell receptor space database enables paired-chain repertoire mining, coherence analysis, and language modeling","volume":"43","author":"MIJ Raybould","year":"2024","journal-title":"Cell Rep"},{"issue":"18","key":"pcbi.1014396.ref051","doi-asserted-by":"crossref","first-page":"2924","DOI":"10.1093\/bioinformatics\/btx286","article-title":"McPAS-TCR: a manually curated catalogue of pathology-associated T cell receptor sequences","volume":"33","author":"N Tickotsky","year":"2017","journal-title":"Bioinformatics"},{"key":"pcbi.1014396.ref052","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.81810","article-title":"Improved T cell receptor antigen pairing through data-driven filtering of sequencing information from single cells","volume":"12","author":"HR Povlsen","year":"2023","journal-title":"Elife"},{"issue":"8","key":"pcbi.1014396.ref053","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0000796","article-title":"NetMHCpan, a method for quantitative predictions of peptide binding to any HLA-A and -B locus protein of known sequence","volume":"2","author":"M Nielsen","year":"2007","journal-title":"PLoS One"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1014396","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T17:48:20Z","timestamp":1782409700000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014396"}},"subtitle":[],"editor":[{"given":"Piero","family":"Fariselli","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":53,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6,22]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1014396","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,22]]}}}