{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T12:15:08Z","timestamp":1771935308874,"version":"3.50.1"},"reference-count":64,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T00:00:00Z","timestamp":1672012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>We present a multi-sequence generalization of Variational Information Bottleneck and call the resulting model Attentive Variational Information Bottleneck (AVIB). Our AVIB model leverages multi-head self-attention to implicitly approximate a posterior distribution over latent encodings conditioned on multiple input sequences. We apply AVIB to a fundamental immuno-oncology problem: predicting the interactions between T-cell receptors (TCRs) and peptides.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Experimental results on various datasets show that AVIB significantly outperforms state-of-the-art methods for TCR\u2013peptide interaction prediction. Additionally, we show that the latent posterior distribution learned by AVIB is particularly effective for the unsupervised detection of out-of-distribution amino acid sequences.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The code and the data used for this study are publicly available at: https:\/\/github.com\/nec-research\/vibtcr.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btac820","type":"journal-article","created":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T16:34:01Z","timestamp":1671813241000},"source":"Crossref","is-referenced-by-count":17,"title":["Attentive Variational Information Bottleneck for TCR\u2013peptide interaction prediction"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8888-133X","authenticated-orcid":false,"given":"Filippo","family":"Grazioli","sequence":"first","affiliation":[{"name":"Biomedical AI Group, NEC Laboratories Europe , Heidelberg 69115, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2646-3674","authenticated-orcid":false,"given":"Pierre","family":"Machart","sequence":"additional","affiliation":[{"name":"Biomedical AI Group, NEC Laboratories Europe , Heidelberg 69115, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6008-0220","authenticated-orcid":false,"given":"Anja","family":"M\u00f6sch","sequence":"additional","affiliation":[{"name":"Biomedical AI Group, NEC Laboratories Europe , Heidelberg 69115, Germany"}]},{"given":"Kai","family":"Li","sequence":"additional","affiliation":[{"name":"Machine Learning Department, NEC Laboratories America , Princeton, NJ 08540, USA"}]},{"given":"Leonardo V","family":"Castorina","sequence":"additional","affiliation":[{"name":"School of Informatics, University of Edinburgh , Edinburgh EH8 9AB, UK"}]},{"given":"Nico","family":"Pfeifer","sequence":"additional","affiliation":[{"name":"Methods in Medical Informatics, Department of Computer Science, University of T\u00fcbingen , T\u00fcbingen 72076, Germany"}]},{"given":"Martin Renqiang","family":"Min","sequence":"additional","affiliation":[{"name":"Machine Learning Department, NEC Laboratories America , Princeton, NJ 08540, USA"}]}],"member":"286","published-online":{"date-parts":[[2022,12,26]]},"reference":[{"key":"2023010723554753000_btac820-B1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-018-2448-z","article-title":"Learning protein binding affinity using privileged information","volume":"19","author":"Abbasi","year":"2018","journal-title":"BMC Bioinformatics"},{"key":"2023010723554753000_btac820-B2","author":"Alemi","year":"2016"},{"key":"2023010723554753000_btac820-B3","author":"Alemi","year":"2018"},{"key":"2023010723554753000_btac820-B4","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":"2023010723554753000_btac820-B5","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1007\/s12026-012-8348-9","article-title":"Improving T cell responses to modified peptides in tumor vaccines","volume":"55","author":"Buhrman","year":"2013","journal-title":"Immunol. Res"},{"key":"2023010723554753000_btac820-B6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2105-10-S4-S4","article-title":"Mixture of experts models to exploit global sequence similarity on biomolecular sequence labeling","volume":"10","author":"Caragea","year":"2009","journal-title":"BMC Bioinformatics"},{"key":"2023010723554753000_btac820-B7","doi-asserted-by":"crossref","first-page":"4172","DOI":"10.1093\/bioinformatics\/btab422","article-title":"BERTMHC: improved MHC\u2013peptide class II interaction prediction with transformer and multiple instance learning","volume":"37","author":"Cheng","year":"2021","journal-title":"Bioinformatics"},{"key":"2023010723554753000_btac820-B8","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":"2023010723554753000_btac820-B9","doi-asserted-by":"crossref","first-page":"5039","DOI":"10.4049\/jimmunol.1003650","article-title":"Strength of TCR\u2013peptide\/MHC interactions and in vivo T cell responses","volume":"186","author":"Corse","year":"2011","journal-title":"J. Immunol"},{"key":"2023010723554753000_btac820-B10","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":"2023010723554753000_btac820-B11","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1038\/334395a0","article-title":"T-cell antigen receptor genes and T-cell recognition","volume":"334","author":"Davis","year":"1988","journal-title":"Nature"},{"key":"2023010723554753000_btac820-B12","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1007\/s00251-017-1023-5","article-title":"On the feasibility of mining CD8+ T cell receptor patterns underlying immunogenic peptide recognition","volume":"70","author":"De Neuter","year":"2018","journal-title":"Immunogenetics"},{"key":"2023010723554753000_btac820-B13","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1038\/ni1502","article-title":"Structural evidence for a germline-encoded T cell receptor\u2013major histocompatibility complex interaction \u2018codon\u2019","volume":"8","author":"Feng","year":"2007","journal-title":"Nat. Immunol"},{"key":"2023010723554753000_btac820-B14","doi-asserted-by":"crossref","first-page":"e9416","DOI":"10.15252\/msb.20199416","article-title":"Predicting antigen specificity of single T cells based on TCR CDR 3 regions","volume":"16","author":"Fischer","year":"2020","journal-title":"Mol. Syst. Biol"},{"key":"2023010723554753000_btac820-B15","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":"2023010723554753000_btac820-B16","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":"2023010723554753000_btac820-B17","doi-asserted-by":"crossref","first-page":"e1010050","DOI":"10.1371\/journal.pcbi.1010050","article-title":"Microbiome-based disease prediction with multimodal variational information bottlenecks","volume":"18","author":"Grazioli","year":"2022","journal-title":"PLoS Comput. Biol"},{"key":"2023010723554753000_btac820-B18","doi-asserted-by":"crossref","first-page":"1014256","DOI":"10.3389\/fimmu.2022.1014256","article-title":"On TCR binding predictors failing to generalize to unseen peptides","volume":"13","author":"Grazioli","year":"2022","journal-title":"Front. Immunol"},{"key":"2023010723554753000_btac820-B19","author":"Hendrycks","year":"2016"},{"key":"2023010723554753000_btac820-B20","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. USA"},{"key":"2023010723554753000_btac820-B21","author":"Higgins","year":"2017"},{"key":"2023010723554753000_btac820-B22","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1162\/089976602760128018","article-title":"Training products of experts by minimizing contrastive divergence","volume":"14","author":"Hinton","year":"2002","journal-title":"Neural Comput"},{"key":"2023010723554753000_btac820-B23","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1158\/2326-6066.CIR-19-0401","article-title":"Pvactools: a computational toolkit to identify and visualize cancer neoantigens","volume":"8","author":"Hundal","year":"2020","journal-title":"Cancer Immunol. Res"},{"key":"2023010723554753000_btac820-B24","first-page":"542332","author":"Jokinen","year":"2019"},{"key":"2023010723554753000_btac820-B25","first-page":"433706","author":"Jurtz","year":"2018"},{"key":"2023010723554753000_btac820-B26","author":"Kingma","year":"2013"},{"key":"2023010723554753000_btac820-B27","doi-asserted-by":"crossref","first-page":"e0141561","DOI":"10.1371\/journal.pone.0141561","article-title":"Multiplex identification of antigen-specific t cell receptors using a combination of immune assays and immune receptor sequencing","volume":"10","author":"Klinger","year":"2015","journal-title":"PLoS One"},{"key":"2023010723554753000_btac820-B28","doi-asserted-by":"crossref","first-page":"e1009086","DOI":"10.1371\/journal.pcbi.1009086","article-title":"Mixture-of-experts variational autoencoder for clustering and generating from similarity-based representations on single cell data","volume":"17","author":"Kopf","year":"2021","journal-title":"PLoS Comput. Biol"},{"key":"2023010723554753000_btac820-B29","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1038\/ni1173","article-title":"How T cells\u2019 see\u2019 antigen","volume":"6","author":"Krogsgaard","year":"2005","journal-title":"Nat. Immunol"},{"key":"2023010723554753000_btac820-B30","author":"Kutuzova","year":"2021"},{"key":"2023010723554753000_btac820-B31","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1038\/s41577-018-0007-5","article-title":"Understanding the drivers of MHC restriction of t cell receptors","volume":"18","author":"La Gruta","year":"2018","journal-title":"Nat. Rev. Immunol"},{"key":"2023010723554753000_btac820-B32","doi-asserted-by":"crossref","first-page":"2080","DOI":"10.3389\/fimmu.2019.02080","article-title":"T-cell receptor cognate target prediction based on paired \u03b1 and \u03b2 chain sequence and structural CDR loop similarities","volume":"10","author":"Lanzarotti","year":"2019","journal-title":"Front. Immunol"},{"key":"2023010723554753000_btac820-B33","first-page":"1513","author":"Lee","year":"2021"},{"key":"2023010723554753000_btac820-B34","author":"Lee","year":"2018"},{"key":"2023010723554753000_btac820-B35","author":"Liang","year":"2017"},{"key":"2023010723554753000_btac820-B36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-020-78758-5","article-title":"Artificial intelligence predicts the immunogenic landscape of sars-cov-2 leading to universal blueprints for vaccine designs","volume":"10","author":"Malone","year":"2020","journal-title":"Sci. Rep"},{"key":"2023010723554753000_btac820-B37","first-page":"2543","article-title":"Relating TCR-peptide-MHC affinity to immunogenicity for the design of tumor vaccines","volume":"116","author":"McMahan","year":"2006","journal-title":"J. Clin. Invest"},{"key":"2023010723554753000_btac820-B38","doi-asserted-by":"crossref","first-page":"926","DOI":"10.1023\/A:1016497818471","article-title":"Rational design of peptide-based tumor vaccines","volume":"19","author":"Meng","year":"2002","journal-title":"Pharm. Res"},{"key":"2023010723554753000_btac820-B39","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":"2023010723554753000_btac820-B40","author":"Moris","year":"2021"},{"key":"2023010723554753000_btac820-B41","doi-asserted-by":"crossref","first-page":"3938","DOI":"10.1093\/bioinformatics\/btab573","article-title":"TCRpair: prediction of functional pairing between HLA-A*02:01-restricted T-cell receptor \u03b1 and \u03b2 chains","volume":"37","author":"M\u00f6sch","year":"2021","journal-title":"Bioinformatics"},{"key":"2023010723554753000_btac820-B42","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1110\/ps.0239403","article-title":"Reliable prediction of t-cell epitopes using neural networks with novel sequence representations","volume":"12","author":"Nielsen","year":"2003","journal-title":"Protein Sci"},{"key":"2023010723554753000_btac820-B43","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.cels.2018.05.014","article-title":"MHCFLURRY: open-source class I MHC binding affinity prediction","volume":"7","author":"O\u2019Donnell","year":"2018","journal-title":"Cell Syst"},{"key":"2023010723554753000_btac820-B44","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.cels.2020.06.010","article-title":"MHCflurry 2.0: improved pan-allele prediction of MHC class I-presented peptides by incorporating antigen processing","volume":"11","author":"O\u2019Donnell","year":"2020","journal-title":"Cell Syst"},{"key":"2023010723554753000_btac820-B45","first-page":"8024","author":"Paszke","year":"2019"},{"key":"2023010723554753000_btac820-B46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2105-8-S10-S6","article-title":"A mixture of feature experts approach for protein-protein interaction prediction","volume":"8","author":"Qi","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"2023010723554753000_btac820-B47","doi-asserted-by":"crossref","first-page":"W449","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":"Reynisson","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2023010723554753000_btac820-B48","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":"2023010723554753000_btac820-B49","doi-asserted-by":"crossref","first-page":"1755","DOI":"10.1126\/science.272.5269.1755","article-title":"The complete 685-kilobase DNA sequence of the human \u03b2 T cell receptor locus","volume":"272","author":"Rowen","year":"1996","journal-title":"Science"},{"key":"2023010723554753000_btac820-B51","author":"Shi","year":"2019"},{"key":"2023010723554753000_btac820-B52","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1016\/S1074-7613(00)00052-2","article-title":"Enhanced antigen-specific antitumor immunity with altered peptide ligands that stabilize the MHC-peptide-TCR complex","volume":"13","author":"Slansky","year":"2000","journal-title":"Immunity"},{"key":"2023010723554753000_btac820-B53","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":"2023010723554753000_btac820-B54","doi-asserted-by":"crossref","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":"2023010723554753000_btac820-B56","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":"2023010723554753000_btac820-B57","author":"Tishby","year":"2000"},{"key":"2023010723554753000_btac820-B58","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":"2023010723554753000_btac820-B59","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"2023010723554753000_btac820-B60","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":"2023010723554753000_btac820-B61","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":"2023010723554753000_btac820-B62","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1021\/ci00062a008","article-title":"Smiles. 2. Algorithm for generation of unique smiles notation","volume":"29","author":"Weininger","year":"1989","journal-title":"J. Chem. Inf. Comput. Sci"},{"key":"2023010723554753000_btac820-B63","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s42003-019-0442-2","article-title":"TRAV1-2 CD8 T-cells including oligoconal expansions of MAIT cells are enriched in the airways in human tuberculosis","volume":"2","author":"Wong","year":"2019","journal-title":"Commun. Biol"},{"key":"2023010723554753000_btac820-B64","first-page":"557","article-title":"Correlation and causation","volume":"20","author":"Wright","year":"1921","journal-title":"J. Agric. Res"},{"key":"2023010723554753000_btac820-B65","author":"Wu","year":"2018"},{"key":"2023010723554753000_btac820-B66","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.cels.2019.05.004","article-title":"Quantification of uncertainty in peptide-MHC binding prediction improves high-affinity peptide selection for therapeutic design","volume":"9","author":"Zeng","year":"2019","journal-title":"Cell Syst"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac820\/48416473\/btac820.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/1\/btac820\/48493569\/btac820.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/1\/btac820\/48493569\/btac820.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,7]],"date-time":"2023-01-07T23:57:12Z","timestamp":1673135832000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btac820\/6960920"}},"subtitle":[],"editor":[{"given":"Alfonso","family":"Valencia","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2022,12,26]]},"references-count":64,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac820","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,1,1]]},"published":{"date-parts":[[2022,12,26]]},"article-number":"btac820"}}