{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T18:16:25Z","timestamp":1787940985502,"version":"build-2784847793"},"reference-count":25,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62372158"],"award-info":[{"award-number":["62372158"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62572178"],"award-info":[{"award-number":["62572178"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62402533"],"award-info":[{"award-number":["62402533"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004761","name":"The Natural Science Foundation of Hunan Province","doi-asserted-by":"crossref","award":["2025JJ60400"],"award-info":[{"award-number":["2025JJ60400"]}],"id":[{"id":"10.13039\/501100004761","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the Educational Commission of Hunan Province","award":["23B0237"],"award-info":[{"award-number":["23B0237"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>T-cell receptors (TCRs) recognize antigenic peptides presented by major histocompatibility complex (MHC) molecules and are central to adaptive immunity. Computational prediction of TCR\u2013epitope binding (TEB) can accelerate immunotherapy development, yet remains hampered by limited labeled data, false-negative noise in unobserved pairs, and over-smoothing in graph-based models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We present DynaTCR, a dynamic graph ensemble learning framework for TEB prediction. DynaTCR encodes TCR and epitope sequences with protein language model embeddings and organizes them into a bipartite interaction graph. A graph regularization-variance-preserving aggregation (GR-VPA) encoder stabilizes message propagation and alleviates over-smoothing, while a global attention layer captures long-range dependencies. Multiple base learners are trained with iteratively updated hard-negative samples to reduce false-negative predictions. Under the StrictTCR evaluation protocol on four public datasets, DynaTCR achieves AUC improvements of 4.0\u20138.2 percentage points over the strongest existing method and up to 15.8 percentage points in AUPR. On the most stringently curated dataset, DynaTCR attains an AUC of 95.1%. Furthermore, on an independent structure-derived test set, DynaTCR achieves the highest AUC (72.6%) among all compared methods, demonstrating its robustness and effectiveness for TEB prediction and candidate prioritization.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability<\/jats:title>\n                    <jats:p>Source code and data can be downloaded from: https:\/\/github.com\/2014402680\/TEB\/.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag544","type":"journal-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T11:34:52Z","timestamp":1784633692000},"source":"Crossref","is-referenced-by-count":0,"title":["DynaTCR: dynamic hard-negative ensemble graph learning improves TCR-epitope binding prediction"],"prefix":"10.1093","volume":"42","author":[{"given":"Xiangzheng","family":"Fu","sequence":"first","affiliation":[{"name":"Faculty of Computer Science and Artificial Intelligence, Shenzhen University of Advanced Technology , Shenzhen 518107,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Data Science and Artificial Intelligence, Wenzhou University of Technology , Wenzhou 325000,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linlin","family":"Zhuo","sequence":"additional","affiliation":[{"name":"School of Data Science and Artificial Intelligence, Wenzhou University of Technology , Wenzhou 325000,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer and Mathematics, Central South University of Forestry and Technology , Changsha, Hunan 410004,","place":["China"]},{"name":"School of Information Engineering, Changsha Medical University , Changsha 410219,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongsheng","family":"Cao","sequence":"additional","affiliation":[{"name":"Xiangya School of Pharmaceutical Sciences, Central South University , Changsha 410003,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6406-1142","authenticated-orcid":false,"given":"Quan","family":"Zou","sequence":"additional","affiliation":[{"name":"Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China , Chengdu 610054,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"key":"2026082813193920600_btag544-B1","doi-asserted-by":"crossref","first-page":"D488","DOI":"10.1093\/nar\/gkac1077","article-title":"RCSB Protein Data Bank (RCSB. org): delivery of experimentally-determined PDB structures alongside one million computed structure models of proteins from artificial intelligence\/machine learning","volume":"51","author":"Burley","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2026082813193920600_btag544-B2","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1111\/imr.12772","article-title":"T cell receptor-based cancer immunotherapy: emerging efficacy and pathways of resistance","volume":"290","author":"Chandran","year":"2019","journal-title":"Immunol Rev"},{"key":"2026082813193920600_btag544-B3","doi-asserted-by":"crossref","first-page":"100027","DOI":"10.1016\/j.immuno.2023.100027","article-title":"Interpretable deep learning to uncover the molecular binding patterns determining TCR\u2013epitope interaction predictions","volume":"11","author":"Dens","year":"2023","journal-title":"ImmunoInformatics"},{"key":"2026082813193920600_btag544-B4","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1146\/annurev.immunol.22.012703.104803","article-title":"The three Es of cancer immunoediting","volume":"22","author":"Dunn","year":"2004","journal-title":"Annu Rev Immunol"},{"key":"2026082813193920600_btag544-B5","doi-asserted-by":"crossref","first-page":"bbaf522","DOI":"10.1093\/bib\/bbaf522","article-title":"GRAPE: graph-regularized protein language modeling unlocks TCR-epitope binding specificity","volume":"26","author":"Fu","year":"2025","journal-title":"Brief Bioinform"},{"key":"2026082813193920600_btag544-B6","doi-asserted-by":"crossref","first-page":"1093","DOI":"10.1038\/s41467-023-36736-1","article-title":"Hierarchical graph learning for protein\u2013protein interaction","volume":"14","author":"Gao","year":"2023","journal-title":"Nat Commun"},{"key":"2026082813193920600_btag544-B7","doi-asserted-by":"crossref","first-page":"2820","DOI":"10.3389\/fimmu.2019.02820","article-title":"Detection of enriched T cell epitope specificity in full T cell receptor sequence repertoires","volume":"10","author":"Gielis","year":"2019","journal-title":"Front Immunol"},{"key":"2026082813193920600_btag544-B8","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1038\/nature22976","article-title":"Identifying specificity groups in the T cell receptor repertoire","volume":"547","author":"Glanville","year":"2017","journal-title":"Nature"},{"key":"2026082813193920600_btag544-B9","doi-asserted-by":"crossref","first-page":"bbae343","DOI":"10.1093\/bib\/bbae343","article-title":"GTE: a graph learning framework for prediction of T-cell receptors and epitopes binding specificity","volume":"25","author":"Jiang","year":"2024","journal-title":"Brief Bioinform"},{"key":"2026082813193920600_btag544-B10","doi-asserted-by":"crossref","first-page":"bbad086","DOI":"10.1093\/bib\/bbad086","article-title":"TEINet: a deep learning framework for prediction of TCR\u2013epitope binding specificity","volume":"24","author":"Jiang","year":"2023","journal-title":"Brief Bioinform"},{"key":"2026082813193920600_btag544-B11","doi-asserted-by":"publisher","DOI":"10.1101\/542332"},{"key":"2026082813193920600_btag544-B12","doi-asserted-by":"crossref","first-page":"e1008814","DOI":"10.1371\/journal.pcbi.1008814","article-title":"Predicting recognition between T cell receptors and epitopes with TCRGP","volume":"17","author":"Jokinen","year":"2021","journal-title":"PLoS Comput Biol"},{"key":"2026082813193920600_btag544-B13","doi-asserted-by":"publisher","author":"Jurtz VI, Jessen LE, Bentzen AK","DOI":"10.1101\/433706"},{"key":"2026082813193920600_btag544-B14","doi-asserted-by":"crossref","first-page":"1016","DOI":"10.1016\/j.cell.2019.07.009","article-title":"T-Scan: a genome-wide method for the systematic discovery of T cell epitopes","volume":"178","author":"Kula","year":"2019","journal-title":"Cell"},{"key":"2026082813193920600_btag544-B15","doi-asserted-by":"publisher","DOI":"10.1101\/2022.07.20.500902"},{"key":"2026082813193920600_btag544-B16","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\u2013antigen binding specificity","volume":"3","author":"Lu","year":"2021","journal-title":"Nat Mach Intell"},{"key":"2026082813193920600_btag544-B17","doi-asserted-by":"crossref","first-page":"910","DOI":"10.1126\/science.1065103","article-title":"Specificity and stability in topology of protein networks","volume":"296","author":"Maslov","year":"2002","journal-title":"Science"},{"key":"2026082813193920600_btag544-B18","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":"Peng","year":"2023","journal-title":"Nat Mach Intell"},{"key":"2026082813193920600_btag544-B19","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1146\/annurev-immunol-032414-112334","article-title":"T cell antigen receptor recognition of antigen-presenting molecules","volume":"33","author":"Rossjohn","year":"2015","journal-title":"Annu Rev Immunol"},{"key":"2026082813193920600_btag544-B20"},{"key":"2026082813193920600_btag544-B21","doi-asserted-by":"crossref","first-page":"D419","DOI":"10.1093\/nar\/gkx760","article-title":"VDJdb: a curated database of T-cell receptor sequences with known antigen specificity","volume":"46","author":"Shugay","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2026082813193920600_btag544-B22","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":"Tickotsky","year":"2017","journal-title":"Bioinformatics"},{"key":"2026082813193920600_btag544-B23","doi-asserted-by":"crossref","first-page":"D339","DOI":"10.1093\/nar\/gky1006","article-title":"The immune epitope database (IEDB): 2018 update","volume":"47","author":"Vita","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2026082813193920600_btag544-B24","first-page":"3040"},{"key":"2026082813193920600_btag544-B25","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1016\/j.cell.2017.07.002","article-title":"Identification of phosphorylation codes for arrestin recruitment by G protein-coupled receptors","volume":"170","author":"Zhou","year":"2017","journal-title":"Cell"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag544\/69749203\/btag544.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/8\/btag544\/69749203\/btag544.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/8\/btag544\/69749203\/btag544.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T17:19:45Z","timestamp":1787937585000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag544\/8739518"}},"subtitle":[],"editor":[{"given":"Daisuke","family":"Kihara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,21]]},"references-count":25,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag544","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,8]]},"published":{"date-parts":[[2026,7,21]]},"article-number":"btag544"}}