{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T22:34:44Z","timestamp":1781822084711,"version":"3.54.5"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"content-version":"vor","delay-in-days":18,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003006","name":"ETH Zurich","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,25]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Effective clustering of T-cell receptor (TCR) sequences could be used to predict their antigen-specificities. TCRs with highly dissimilar sequences can bind to the same antigen, thus making their clustering into a common antigen group a central challenge. Here, we develop TouCAN, a method that relies on contrastive learning and pretrained protein language models to perform TCR sequence clustering and antigen-specificity predictions. Following training, TouCAN demonstrates the ability to cluster highly dissimilar TCRs into common antigen groups. Additionally, TouCAN demonstrates TCR clustering performance and antigen-specificity predictions comparable to other leading methods in the field.<\/jats:p>","DOI":"10.1093\/bib\/bbae375","type":"journal-article","created":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T05:18:16Z","timestamp":1723439896000},"source":"Crossref","is-referenced-by-count":10,"title":["TCR clustering by contrastive learning on antigen specificity"],"prefix":"10.1093","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5561-784X","authenticated-orcid":false,"given":"Margarita","family":"Pertseva","sequence":"first","affiliation":[{"name":"Department of Biosystems Science and Engineering, ETH Zurich , Schanzenstrasse 44, 4056 Basel, Switzerland"},{"name":"Life Science Zurich Graduate School, ETH Zurich and University of Zurich , Winterthurerstrasse 190, 8057 Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2577-1808","authenticated-orcid":false,"given":"Oceane","family":"Follonier","sequence":"additional","affiliation":[{"name":"Department of Biosystems Science and Engineering, ETH Zurich , Schanzenstrasse 44, 4056 Basel, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniele","family":"Scarcella","sequence":"additional","affiliation":[{"name":"Department of Biosystems Science and Engineering, ETH Zurich , Schanzenstrasse 44, 4056 Basel, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sai T","family":"Reddy","sequence":"additional","affiliation":[{"name":"Department of Biosystems Science and Engineering, ETH Zurich , Schanzenstrasse 44, 4056 Basel, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,8,11]]},"reference":[{"key":"2024081205175764800_ref1","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1038\/s41392-023-01471-y","article-title":"T cells in health and disease","volume":"8","author":"Sun","year":"2023","journal-title":"Signal Transduct Target Ther"},{"key":"2024081205175764800_ref2","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1146\/annurev.immunol.23.021704.115658","article-title":"How TCRs bind MHCs, peptides, and coreceptors","volume":"24","author":"Rudolph","year":"2006","journal-title":"Annu Rev Immunol"},{"key":"2024081205175764800_ref3","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1016\/j.cell.2005.07.015","article-title":"How the T cell receptor sees antigen\u2014a structural view","volume":"122","author":"Christopher Garcia","year":"2005","journal-title":"Cell"},{"key":"2024081205175764800_ref4","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":"2024081205175764800_ref5","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":"2024081205175764800_ref6","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":"2024081205175764800_ref7","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":"2024081205175764800_ref8","doi-asserted-by":"crossref","first-page":"1461","DOI":"10.1093\/bioinformatics\/bty821","article-title":"On the viability of unsupervised T-cell receptor sequence clustering for epitope preference","volume":"35","author":"Meysman","year":"2019","journal-title":"Bioinformatics"},{"key":"2024081205175764800_ref9","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1038\/nri3279","article-title":"Why must T cells be cross-reactive?","volume":"12","author":"Sewell","year":"2012","journal-title":"Nat Rev Immunol"},{"key":"2024081205175764800_ref10","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1038\/s41577-023-00835-3","article-title":"Can we predict T cell specificity with digital biology and machine learning?","volume":"23","author":"Hudson","year":"2023","journal-title":"Nat Rev Immunol"},{"key":"2024081205175764800_ref11","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1038\/s41592-020-0867-z","article-title":"T cell antigen discovery","volume":"18","author":"Joglekar","year":"2021","journal-title":"Nat Methods"},{"key":"2024081205175764800_ref12","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1038\/s41592-021-01201-8","article-title":"High-throughput and single-cell T cell receptor sequencing technologies","volume":"18","author":"Pai","year":"2021","journal-title":"Nat Methods"},{"key":"2024081205175764800_ref13","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1126\/science.aam8999","article-title":"Single-cell profiling of the developing mouse brain and spinal cord with split-pool barcoding","volume":"360","author":"Rosenberg","year":"2018","journal-title":"Science"},{"key":"2024081205175764800_ref14","doi-asserted-by":"crossref","first-page":"1060","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":"2024081205175764800_ref15","doi-asserted-by":"crossref","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":"2024081205175764800_ref16","doi-asserted-by":"crossref","first-page":"1055151","DOI":"10.3389\/fimmu.2022.1055151","article-title":"NetTCR-2.1: lessons and guidance on how to develop models for TCR specificity predictions","volume":"13","author":"Montemurro","year":"2022","journal-title":"Front Immunol"},{"key":"2024081205175764800_ref17","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":"2024081205175764800_ref18","doi-asserted-by":"crossref","first-page":"2309","DOI":"10.1038\/s41467-021-22667-2","article-title":"Author correction: 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":"2024081205175764800_ref19","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2015.7298682","article-title":"FaceNet: a unified embedding for face recognition and clustering","volume-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Schroff","year":"2015"},{"key":"2024081205175764800_ref20","doi-asserted-by":"crossref","first-page":"858","DOI":"10.1038\/s41592-019-0511-y","article-title":"BindSpace decodes transcription factor binding signals by large-scale sequence embedding","volume":"16","author":"Yuan","year":"2019","journal-title":"Nat Methods"},{"key":"2024081205175764800_ref21","doi-asserted-by":"crossref","first-page":"1358","DOI":"10.1126\/science.adf2465","article-title":"Enzyme function prediction using contrastive learning","volume":"379","author":"Yu","year":"2023","journal-title":"Science"},{"key":"2024081205175764800_ref22","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac378","article-title":"Attention-aware contrastive learning for predicting T cell receptor\u2013antigen binding specificity","volume":"23","author":"Fang","year":"2022","journal-title":"Brief Bioinform"},{"key":"2024081205175764800_ref23","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2016239118","article-title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","volume":"118","author":"Rives","year":"2021","journal-title":"Proc Natl Acad Sci"},{"key":"2024081205175764800_ref24","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"key":"2024081205175764800_ref25","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":"2024081205175764800_ref26","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":"2024081205175764800_ref27","doi-asserted-by":"crossref","first-page":"lqab023","DOI":"10.1093\/nargab\/lqab023","article-title":"Platypus: an open-access software for integrating lymphocyte single-cell immune repertoires with transcriptomes","volume":"3","author":"Yermanos","year":"2021","journal-title":"NAR Genom Bioinform"},{"key":"2024081205175764800_ref28","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":"2024081205175764800_ref29","doi-asserted-by":"crossref","first-page":"D413","DOI":"10.1093\/nar\/gku1056","article-title":"IMGT\u00ae, the international ImMunoGeneTics information system\u00ae 25 years on","volume":"43","author":"Lefranc","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2024081205175764800_ref30","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"},{"key":"2024081205175764800_ref31","doi-asserted-by":"crossref","first-page":"1480","DOI":"10.4049\/jimmunol.1501721","article-title":"The length distribution of class I-restricted T cell epitopes is determined by both peptide supply and MHC allele-specific binding preference","volume":"196","author":"Trolle","year":"2016","journal-title":"J Immunol"},{"key":"2024081205175764800_ref32","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkac190","article-title":"Stitchr: stitching coding TCR nucleotide sequences from V\/J\/CDR3 information","volume":"50","author":"Heather","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2024081205175764800_ref33","doi-asserted-by":"crossref","first-page":"10915","DOI":"10.1073\/pnas.89.22.10915","article-title":"Amino acid substitution matrices from protein blocks","volume":"89","author":"Henikoff","year":"1992","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2024081205175764800_ref34","volume-title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems","author":"Abadi","year":"2016"},{"key":"2024081205175764800_ref35","volume-title":"Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD'96)","author":"Ester","year":"1996"},{"key":"2024081205175764800_ref36","first-page":"2825","article-title":"Scikit-learn: machine learning in python Fabian","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2024081205175764800_ref37","doi-asserted-by":"crossref","first-page":"1792","DOI":"10.1093\/nar\/gkh340","article-title":"MUSCLE: multiple sequence alignment with high accuracy and high throughput","volume":"32","author":"Edgar","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2024081205175764800_ref38","doi-asserted-by":"crossref","first-page":"1188","DOI":"10.1101\/gr.849004","article-title":"WebLogo: a sequence logo generator","volume":"14","author":"Crooks","year":"2004","journal-title":"Genome Res"},{"key":"2024081205175764800_ref39","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: fundamental algorithms for scientific computing in Python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat Methods"},{"key":"2024081205175764800_ref40","article-title":"A comparison of clustering models for inference of T cell receptor antigen specificity","volume":"13","author":"Hudson","year":"2023","journal-title":"bioRxiv"},{"key":"2024081205175764800_ref41","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":"2024081205175764800_ref42","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":"2024081205175764800_ref43","article-title":"TCR-BERT: learning the grammar of T-cell receptors for flexible antigen-xbinding analyses","volume":"240","author":"Wu","year":"2023","journal-title":"Proceedings of Machine Learning Research"},{"key":"2024081205175764800_ref44","doi-asserted-by":"crossref","first-page":"eadf3700","DOI":"10.1126\/sciadv.adf3700","article-title":"TCR-engineered T cell therapy in solid tumors: state of the art and perspectives","volume":"9","author":"Baulu","year":"2023","journal-title":"Sci Adv"},{"key":"2024081205175764800_ref45","doi-asserted-by":"crossref","first-page":"996","DOI":"10.1038\/s41573-023-00809-z","article-title":"T cell receptor therapeutics: immunological targeting of the intracellular cancer proteome","volume":"22","author":"Klebanoff","year":"2023","journal-title":"Nat Rev Drug Discov"},{"key":"2024081205175764800_ref46","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1038\/s41587-023-01763-2","article-title":"Efficient evolution of human antibodies from general protein language models","volume":"42","author":"Hie","year":"2024","journal-title":"Nat Biotechnol"},{"key":"2024081205175764800_ref47","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1038\/s41587-024-02123-4","article-title":"Designing proteins with language models","volume":"42","author":"Ruffolo","year":"2024","journal-title":"Nat Biotechnol"},{"key":"2024081205175764800_ref48","article-title":"STAPLER: efficient learning of TCR-peptide specificity prediction from full-length TCR-peptide data","author":"Kwee","year":"2023","journal-title":"bioRxiv"},{"key":"2024081205175764800_ref49","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":"2024081205175764800_ref50","article-title":"Unified cross-modality integration and analysis of T cell receptors and T cell transcriptomes by low-resource-aware representation learning","volume":"4","author":"Gao","year":"2024","journal-title":"Cell Genom"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/5\/bbae375\/58795421\/bbae375.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/5\/bbae375\/58795421\/bbae375.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T05:18:37Z","timestamp":1723439917000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbae375\/7731389"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,25]]},"references-count":50,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,7,25]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbae375","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,9]]},"published":{"date-parts":[[2024,7,25]]},"article-number":"bbae375"}}