{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T11:25:51Z","timestamp":1787570751377,"version":"build-2736575974"},"reference-count":12,"publisher":"Oxford University Press (OUP)","issue":"Supplement_2","license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"vor","delay-in-days":23,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002341","name":"Research Council of Finland","doi-asserted-by":"publisher","award":["359135"],"award-info":[{"award-number":["359135"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Cancer Foundation of Finland"},{"DOI":"10.13039\/501100006306","name":"Sigrid Jus\u00e9lius Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006306","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Juhani Aho Medical Foundation"},{"name":"Swedish Academy of Engineering Sciences in Finland"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Peptide-MHC II binding drives adaptive immunity, yet discovery of novel binder peptides remains challenging due to open binding grooves of MHC-II that accommodate variable-length peptides. While discriminative models perform well, they are unfeasible for generation via enumeration due to vast peptide space (2013\u22488\u00d71016 for peptides of length 13 amino acids). Generative AI approaches could accelerate binder design to enable vaccines targeted to particular MHC-II alleles or optimize other peptide chemical properties.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We introduce PepGen, the first protein language model for MHC II peptide generation building on Generalized Language Modeling. PepGen conditions on alleles, arbitrary partial peptides including putative TCR-interacting motifs, and continuous binding affinity. Across multiple benchmarks including infilling and de novo generation, PepGen outperformed frequency sampling, Gibbs clustering, and autoregressive baselines. Adjusted log-probabilities enable good classification performance. Experimental validation confirmed that the SARS-CoV-2 peptide TEGALNTPKDHIGTR binding the HLA-DQA101:03-DQB106:03 allele can be redesigned to bind the HLA-DQA101:02-DQB105:02 allele. PepGen generated three putative TCR-motif-preserving binders gaining up to 70% of original MFI. Overall, PepGen provides scalable, motif-constrained MHC II peptide redesign and de novo generation, validated through thorough benchmarks and functional assays.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Code and Data are available at https:\/\/github.com\/DaniTheOrange\/PepGen.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag464","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T11:35:55Z","timestamp":1783424155000},"source":"Crossref","is-referenced-by-count":0,"title":["PepGen: conditional generation of peptides for MHC binding"],"prefix":"10.1093","volume":"42","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 , Espoo, 02150,","place":["Finland"]},{"name":"Broad Institute of MIT and Harvard , Cambridge, MA, 02142,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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 , Espoo, 02150,","place":["Finland"]},{"name":"Broad Institute of MIT and Harvard , Cambridge, MA, 02142,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3064-1055","authenticated-orcid":false,"given":"Martin","family":"Stra\u017ear","sequence":"additional","affiliation":[{"name":"Broad Institute of MIT and Harvard , Cambridge, MA, 02142,","place":["United States"]},{"name":"Department of Biotechnology and Systems Biology, National Institute of Biology , Ljubljana, 1000,","place":["Slovenia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4803-5339","authenticated-orcid":false,"given":"Rui","family":"Li","sequence":"additional","affiliation":[{"name":"Broad Institute of MIT and Harvard , Cambridge, MA, 02142,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5630-5167","authenticated-orcid":false,"given":"Ramnik J","family":"Xavier","sequence":"additional","affiliation":[{"name":"Broad Institute of MIT and Harvard , Cambridge, MA, 02142,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8403-8115","authenticated-orcid":false,"given":"Daniel B","family":"Graham","sequence":"additional","affiliation":[{"name":"Broad Institute of MIT and Harvard , Cambridge, MA, 02142,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harri","family":"L\u00e4hdesm\u00e4ki","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Aalto University , Espoo, 02150,","place":["Finland"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,8,21]]},"reference":[{"key":"2026082407034138700_btag464-B1","doi-asserted-by":"crossref","first-page":"W458","DOI":"10.1093\/nar\/gkx248","article-title":"GibbsCluster: unsupervised clustering and alignment of peptide sequences","volume":"45","author":"Andreatta","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2026082407034138700_btag464-B2","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btad055","article-title":"Binding peptide generation for MHC class I proteins with deep reinforcement learning","volume":"39","author":"Chen","year":"2023","journal-title":"Bioinformatics"},{"key":"2026082407034138700_btag464-B3","doi-asserted-by":"crossref","first-page":"3160","DOI":"10.1093\/bioinformatics\/btab131","article-title":"Machine learning optimization of peptides for presentation by class II MHCs","volume":"37","author":"Dai","year":"2021","journal-title":"Bioinformatics"},{"key":"2026082407034138700_btag464-B4","year":"2022"},{"key":"2026082407034138700_btag464-B5","author":"Holtzman A, Buys J, Du L","year":"2020"},{"key":"2026082407034138700_btag464-B6","doi-asserted-by":"crossref","first-page":"eadg9845","DOI":"10.1126\/sciadv.adg9845","article-title":"Multi-tiered approach to detect autoimmune cross-reactivity of therapeutic T cell receptors","volume":"9","author":"Ishii","year":"2023","journal-title":"Sci Adv"},{"key":"2026082407034138700_btag464-B7","doi-asserted-by":"crossref","first-page":"eadj6367","DOI":"10.1126\/sciadv.adj6367","article-title":"Accurate prediction of HLA class II antigen presentation across all loci using tailored data acquisition and refined machine learning","volume":"9","author":"Nilsson","year":"2023","journal-title":"Sci Adv"},{"key":"2026082407034138700_btag464-B8","doi-asserted-by":"crossref","first-page":"1487","DOI":"10.1038\/s42256-024-00928-1","article-title":"Reshaping the discovery of self-assembling peptides with generative AI guided by hybrid deep learning","volume":"6","author":"Njirjak","year":"2024","journal-title":"Nat Mach Intell"},{"key":"2026082407034138700_btag464-B9","author":"Sanchez G, Spangher A, Fan H","year":"2024"},{"key":"2026082407034138700_btag464-B10","doi-asserted-by":"crossref","first-page":"1681","DOI":"10.1016\/j.immuni.2023.05.009","article-title":"HLA-II immunopeptidome profiling and deep learning reveal features of antigenicity to inform antigen discovery","volume":"56","author":"Stra\u017ear","year":"2023","journal-title":"Immunity"},{"key":"2026082407034138700_btag464-B11","doi-asserted-by":"crossref","first-page":"14840","DOI":"10.1073\/pnas.1416864111","article-title":"Autoreactive T cells specific for insulin B: 11-23 recognize a low-affinity peptide register in human subjects with autoimmune diabetes","volume":"111","author":"Yang J, Chow IT, Sosinowski T","year":"2014","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026082407034138700_btag464-B12","article-title":"DeepMHCII: a novel binding core-aware deep interaction model for accurate MHC-II peptide binding affinity prediction","volume":"38","author":"You R, Qu W, Mamitsuka H","year":"2022","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/Supplement_2\/btag464\/70726171\/btag464.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/Supplement_2\/btag464\/70726171\/btag464.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T11:03:52Z","timestamp":1787569432000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag464\/8767311"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,1]]},"references-count":12,"journal-issue":{"issue":"Supplement_2","published-print":{"date-parts":[[2026,8,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag464","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":[[2026,8,1]]},"article-number":"btag464"}}