{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T03:56:51Z","timestamp":1776225411097,"version":"3.50.1"},"reference-count":39,"publisher":"Oxford University Press (OUP)","issue":"12","license":[{"start":{"date-parts":[[2023,12,9]],"date-time":"2023-12-09T00:00:00Z","timestamp":1702080000000},"content-version":"vor","delay-in-days":8,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sigrid Juselius Foundation"},{"DOI":"10.13039\/501100010711","name":"Cancer Foundation Finland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>T cells play an essential role in adaptive immune system to fight pathogens and cancer but may also give rise to autoimmune diseases. The recognition of a peptide\u2013MHC (pMHC) complex by a T cell receptor (TCR) is required to elicit an immune response. Many machine learning models have been developed to predict the binding, but generalizing predictions to pMHCs outside the training data remains challenging.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We have developed a new machine learning model that utilizes information about the TCR from both \u03b1 and \u03b2 chains, epitope sequence, and MHC. Our method uses ProtBERT embeddings for the amino acid sequences of both chains and the epitope, as well as convolution and multi-head attention architectures. We show the importance of each input feature as well as the benefit of including epitopes with only a few TCRs to the training data. We evaluate our model on existing databases and show that it compares favorably against other state-of-the-art models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>https:\/\/github.com\/DaniTheOrange\/EPIC-TRACE.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad743","type":"journal-article","created":{"date-parts":[[2023,12,7]],"date-time":"2023-12-07T21:41:21Z","timestamp":1701985281000},"source":"Crossref","is-referenced-by-count":27,"title":["EPIC-TRACE: predicting TCR binding to unseen epitopes using attention and contextualized embeddings"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2845-8836","authenticated-orcid":false,"given":"Dani","family":"Korpela","sequence":"first","affiliation":[{"name":"Department of Computer Science, Aalto University , 02150 Espoo, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0060-6868","authenticated-orcid":false,"given":"Emmi","family":"Jokinen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Aalto University , 02150 Espoo, Finland"},{"name":"Translational Immunology Research Program, Department of Clinical Chemistry and Hematology, University of Helsinki , 00290 Helsinki, Finland"},{"name":"Hematology Research Unit Helsinki, Helsinki University Hospital Comprehensive Cancer Center , 00290 Helsinki, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0909-9484","authenticated-orcid":false,"given":"Alexandru","family":"Dumitrescu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Aalto University , 02150 Espoo, Finland"}]},{"given":"Jani","family":"Huuhtanen","sequence":"additional","affiliation":[{"name":"Translational Immunology Research Program, Department of Clinical Chemistry and Hematology, University of Helsinki , 00290 Helsinki, Finland"},{"name":"Hematology Research Unit Helsinki, Helsinki University Hospital Comprehensive Cancer Center , 00290 Helsinki, Finland"}]},{"given":"Satu","family":"Mustjoki","sequence":"additional","affiliation":[{"name":"Translational Immunology Research Program, Department of Clinical Chemistry and Hematology, University of Helsinki , 00290 Helsinki, Finland"},{"name":"Hematology Research Unit Helsinki, Helsinki University Hospital Comprehensive Cancer Center , 00290 Helsinki, Finland"},{"name":"iCAN Digital Precision Cancer Medicine Flagship , Helsinki, Finland"}]},{"given":"Harri","family":"L\u00e4hdesm\u00e4ki","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Aalto University , 02150 Espoo, Finland"}]}],"member":"286","published-online":{"date-parts":[[2023,12,9]]},"reference":[{"key":"2023122020204336800_btad743-B1","article-title":"A new way of exploring immunity-linking highly multiplexed antigen recognition to immune repertoire and phenotype","author":"10x Genomics","year":"2020","journal-title":"Technol Network"},{"key":"2023122020204336800_btad743-B2","doi-asserted-by":"crossref","first-page":"D1057","DOI":"10.1093\/nar\/gkz874","article-title":"VDJdb in 2019: database extension, new analysis infrastructure and a T-cell receptor motif compendium","volume":"48","author":"Bagaev","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2023122020204336800_btad743-B3","doi-asserted-by":"crossref","first-page":"640725","DOI":"10.3389\/fimmu.2021.640725","article-title":"TCRMatch: predicting T-cell receptor specificity based on sequence similarity to previously characterized receptors","volume":"12","author":"Chronister","year":"2021","journal-title":"Front Immunol"},{"key":"2023122020204336800_btad743-B4","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1038\/nature22383","article-title":"Quantifiable predictive features define epitope-specific T cell receptor repertoires","volume":"547","author":"Dash","year":"2017","journal-title":"Nature"},{"key":"2023122020204336800_btad743-B5","first-page":"44:7012\u201327","article-title":"ProtTrans: towards cracking the language of lifes code through self-supervised deep learning and high performance computing","author":"Elnaggar","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2023122020204336800_btad743-B6","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1159\/000019130","article-title":"The human T cell receptor beta diversity (TRBD) and beta joining (TRBJ) genes","volume":"17","author":"Folch","year":"2000","journal-title":"Exp Clin Immunogenet"},{"key":"2023122020204336800_btad743-B7","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1159\/000019123","article-title":"The human T cell receptor beta variable (TRBV) genes","volume":"17","author":"Folch","year":"2000","journal-title":"Exp Clin Immunogenet"},{"key":"2023122020204336800_btad743-B8","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1038\/s42256-023-00619-3","article-title":"Pan-peptide meta learning for T-cell receptor\u2013antigen binding recognition","volume":"5","author":"Gao","year":"2023","journal-title":"Nat Mach Intell"},{"key":"2023122020204336800_btad743-B9","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":"2023122020204336800_btad743-B10","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":"2023122020204336800_btad743-B11","doi-asserted-by":"crossref","first-page":"1194","DOI":"10.1038\/s41587-020-0505-4","article-title":"Analyzing the Mycobacterium tuberculosis immune response by T-cell receptor clustering with GLIPH2 and genome-wide antigen screening","volume":"38","author":"Huang","year":"2020","journal-title":"Nat Biotechnol"},{"key":"2023122020204336800_btad743-B12","author":"Izmailov","year":"2018"},{"key":"2023122020204336800_btad743-B13","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":"2023122020204336800_btad743-B14","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":"2023122020204336800_btad743-B15","doi-asserted-by":"crossref","first-page":"btac788","DOI":"10.1093\/bioinformatics\/btac788","article-title":"TCRconv: predicting recognition between T cell receptors and epitopes using contextualized motifs","volume":"39","author":"Jokinen","year":"2023","journal-title":"Bioinformatics"},{"key":"2023122020204336800_btad743-B16","article-title":"NetTCR: sequence-based prediction of TCR binding to peptide-MHC complexes using convolutional neural networks","author":"Jurtz","journal-title":"bioRxiv"},{"key":"2023122020204336800_btad743-B17","doi-asserted-by":"crossref","first-page":"20140291","DOI":"10.1098\/rstb.2014.0291","article-title":"Estimating T-cell repertoire diversity: limitations of classical estimators and a new approach","volume":"370","author":"Laydon","year":"2015","journal-title":"Phil Trans R Soc B"},{"key":"2023122020204336800_btad743-B18","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/S0145-305X(02)00039-3","article-title":"IMGT unique numbering for immunoglobulin and T cell receptor variable domains and Ig superfamily V-like domains","volume":"27","author":"Lefranc","year":"2003","journal-title":"Dev Comp Immunol"},{"key":"2023122020204336800_btad743-B19","doi-asserted-by":"crossref","first-page":"2688","DOI":"10.3389\/fimmu.2018.02688","article-title":"Epitope specific antibodies and T cell receptors in the immune epitope database","volume":"9","author":"Mahajan","year":"2018","journal-title":"Front Immunol"},{"key":"2023122020204336800_btad743-B20","doi-asserted-by":"crossref","first-page":"100024","DOI":"10.1016\/j.immuno.2023.100024","article-title":"Benchmarking solutions to the T-cell receptor epitope prediction problem: IMMREP22 workshop report","volume":"9","author":"Meysman","year":"2023","journal-title":"ImmunoInformatics"},{"key":"2023122020204336800_btad743-B21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s42003-021-02610-3","article-title":"NetTCR-2.0 enables accurate prediction of TCR-peptide binding by using paired TCR\u03b1 and \u03b2 sequence data","volume":"4","author":"Montemurro","year":"2021","journal-title":"Commun Biol"},{"key":"2023122020204336800_btad743-B22","doi-asserted-by":"crossref","first-page":"bbaa318","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":"Moris","year":"2021","journal-title":"Brief Bioinform"},{"key":"2023122020204336800_btad743-B23","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":"2023122020204336800_btad743-B24","doi-asserted-by":"crossref","first-page":"btad284","DOI":"10.1093\/bioinformatics\/btad284","article-title":"epiTCR: a highly sensitive predictor for TCR\u2013peptide binding","volume":"39","author":"Pham","year":"2023","journal-title":"Bioinformatics"},{"key":"2023122020204336800_btad743-B25","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1016\/j.it.2016.08.010","article-title":"Present yourself! by MHC class I and MHC class II molecules","volume":"37","author":"Rock","year":"2016","journal-title":"Trends Immunol"},{"key":"2023122020204336800_btad743-B26","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/S0952-7915(01)00298-9","article-title":"The specificity of TCR\/pMHC interaction","volume":"14","author":"Rudolph","year":"2002","journal-title":"Curr Opin Immunol"},{"key":"2023122020204336800_btad743-B27","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1159\/000019129","article-title":"The human T cell receptor alpha joining (TRAJ) genes","volume":"17","author":"Scaviner","year":"2000","journal-title":"Exp Clin Immunogenet"},{"key":"2023122020204336800_btad743-B28","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1159\/000019128","article-title":"The human T cell receptor alpha variable (TRAV) genes","volume":"17","author":"Scaviner","year":"2000","journal-title":"Exp Clin Immunogenet"},{"key":"2023122020204336800_btad743-B29","doi-asserted-by":"crossref","first-page":"1605","DOI":"10.1038\/s41467-021-21879-w","article-title":"DeepTCR is a deep learning framework for revealing sequence concepts within T-cell repertoires","volume":"12","author":"Sidhom","year":"2021","journal-title":"Nat Commun"},{"key":"2023122020204336800_btad743-B30","doi-asserted-by":"crossref","first-page":"1803","DOI":"10.3389\/fimmu.2020.01803","article-title":"Prediction of specific TCR-peptide binding from large dictionaries of TCR-peptide pairs","volume":"11","author":"Springer","year":"2020","journal-title":"Front Immunol"},{"key":"2023122020204336800_btad743-B31","doi-asserted-by":"crossref","first-page":"664514","DOI":"10.3389\/fimmu.2021.664514","article-title":"Contribution of T cell receptor alpha and beta CDR3, MHC typing, V and J genes to peptide binding prediction","volume":"12","author":"Springer","year":"2021","journal-title":"Front Immunol"},{"key":"2023122020204336800_btad743-B32","doi-asserted-by":"crossref","first-page":"107281","DOI":"10.1016\/j.compbiolchem.2020.107281","article-title":"SETE: sequence-based ensemble learning approach for TCR epitope binding prediction","volume":"87","author":"Tong","year":"2020","journal-title":"Comput Biol Chem"},{"key":"2023122020204336800_btad743-B33","doi-asserted-by":"crossref","first-page":"100009","DOI":"10.1016\/j.immuno.2022.100009","article-title":"Recent advances in T-cell receptor repertoire analysis: bridging the gap with multimodal single-cell RNA sequencing","volume":"5","author":"Valkiers","year":"2022","journal-title":"ImmunoInformatics"},{"key":"2023122020204336800_btad743-B34","author":"Vig","year":"2021"},{"key":"2023122020204336800_btad743-B35","doi-asserted-by":"crossref","first-page":"i237","DOI":"10.1093\/bioinformatics\/btab294","article-title":"TITAN: T-cell receptor specificity prediction with bimodal attention networks","volume":"37","author":"Weber","year":"2021","journal-title":"Bioinformatics"},{"key":"2023122020204336800_btad743-B36","doi-asserted-by":"crossref","first-page":"1168","DOI":"10.1074\/jbc.M111.289488","article-title":"A single autoimmune T cell receptor recognizes more than a million different peptides","volume":"287","author":"Wooldridge","year":"2012","journal-title":"J Biol Chem"},{"key":"2023122020204336800_btad743-B37","author":"Wu","year":"2021"},{"key":"2023122020204336800_btad743-B38","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1038\/s41586-022-05501-7","article-title":"Autoimmunity-associated T cell receptors recognize HLA-B 27-bound peptides","volume":"612","author":"Yang","year":"2022","journal-title":"Nature"},{"key":"2023122020204336800_btad743-B39","doi-asserted-by":"crossref","first-page":"eabf5835","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":"Zhang","year":"2021","journal-title":"Sci Adv"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad743\/54182400\/btad743.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/12\/btad743\/54680253\/btad743.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/12\/btad743\/54680253\/btad743.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T15:21:18Z","timestamp":1703085678000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad743\/7467056"}},"subtitle":[],"editor":[{"given":"Lenore","family":"Cowen","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2023,12,1]]},"references-count":39,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,12,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad743","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.06.26.546489","asserted-by":"object"}]},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,12,1]]},"published":{"date-parts":[[2023,12,1]]},"article-number":"btad743"}}