{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T18:31:15Z","timestamp":1786991475785,"version":"build-2736575974"},"posted":{"date-parts":[[2026,8,13]]},"group-title":"Bioinformatics","reference-count":37,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["U19AI110495"],"award-info":[{"award-number":["U19AI110495"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002341","name":"Research Council of Finland","doi-asserted-by":"crossref","award":["359135"],"award-info":[{"award-number":["359135"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Cancer Foundation of Finland"},{"name":"Sigrid JusM-CM-)lius Foundation"},{"name":"Merkin Institute Fellows program at the Broad Institute"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,8,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  CD4\n                  <jats:sup>+<\/jats:sup>\n                  T cells recognize peptides presented by human leukocyte antigen (HLA) II, implementing a fundamental mediation mechanism of the adaptive immune system. Although post-translational modifications (PTMs) alter immune responses, PTM-peptide-HLA interaction prediction remains challenging due to data scarcity resulting from substoichiometric levels of PTMs. To overcome this, we developed PepChem, a deep learning model utilizing novel, molecular-level peptide representations that enable predictions for sidechain modifications. Using monoallelic datasets that we reanalyze for PTMs of interest, we show accurate predictions on PTMs that were unseen during training. Furthermore, we introduce a novel training protocol that improves PTM-peptide generalization compared to conventional methods. We predict and experimentally validate citrullination-induced binding increase of rheumatoid arthritis (RA)-linked peptides to HLA II risk allele DRB1*04:01. This framework bridges the critical gap in PTM-aware immune recognition prediction, with immediate applications in autoimmunity, cancer, and infectious disease.\n                <\/jats:p>","DOI":"10.64898\/2026.08.07.743493","type":"posted-content","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T02:10:28Z","timestamp":1786673428000},"source":"Crossref","is-referenced-by-count":0,"title":["Peptide-HLA II interaction prediction for post-translationally modified peptides"],"prefix":"10.64898","author":[{"given":"Alexandru","family":"Dumitrescu","sequence":"first","affiliation":[{"name":"Aalto University, Computer Science Department, Espoo, Finland"},{"name":"Broad Institute of MIT and Harvard, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dani","family":"Korpela","sequence":"additional","affiliation":[{"name":"Aalto University, Computer Science Department, Espoo, Finland"},{"name":"Broad Institute of MIT and Harvard, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adrian M.","family":"Bebenek","sequence":"additional","affiliation":[{"name":"Broad Institute of MIT and Harvard, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Ju","sequence":"additional","affiliation":[{"name":"Broad Institute of MIT and Harvard, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Griffin M.","family":"Lawrence","sequence":"additional","affiliation":[{"name":"Broad Institute of MIT and Harvard, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karl R.","family":"Clauser","sequence":"additional","affiliation":[{"name":"Broad Institute of MIT and Harvard, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jennifer G.","family":"Abelin","sequence":"additional","affiliation":[{"name":"Broad Institute of MIT and Harvard, Cambridge, MA, USA"},{"name":"Dana Farber Cancer Institute, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Stra\u017ear","sequence":"additional","affiliation":[{"name":"Broad Institute of MIT and Harvard, Cambridge, MA, USA"},{"name":"Department of Biotechnology and Systems Biology, National Institute of Biology, Ljubljana, Slovenia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harri","family":"L\u00e4hdesm\u00e4ki","sequence":"additional","affiliation":[{"name":"Aalto University, Computer Science Department, Espoo, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel B.","family":"Graham","sequence":"additional","affiliation":[{"name":"Broad Institute of MIT and Harvard, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramnik J.","family":"Xavier","sequence":"additional","affiliation":[{"name":"Broad Institute of MIT and Harvard, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026081711150895000_2026.08.07.743493v1.1","doi-asserted-by":"publisher","DOI":"10.1038\/S41586-024-07487-W"},{"key":"2026081711150895000_2026.08.07.743493v1.2","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.82813"},{"key":"2026081711150895000_2026.08.07.743493v1.3","doi-asserted-by":"crossref","unstructured":"Bento, A. P. et al. An open source chemical structure curation pipeline using RDKit. J Cheminform 12, 51 (2020).","DOI":"10.1186\/s13321-020-00456-1"},{"key":"2026081711150895000_2026.08.07.743493v1.4","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btab422"},{"key":"2026081711150895000_2026.08.07.743493v1.5","first-page":"D609","article-title":"UniProt: the universal protein knowledgebase in 2025","volume":"53","year":"2024","journal-title":"Nucleic Acids Research"},{"key":"2026081711150895000_2026.08.07.743493v1.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.coi.2011.12.003"},{"key":"2026081711150895000_2026.08.07.743493v1.7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3095381"},{"key":"2026081711150895000_2026.08.07.743493v1.8","doi-asserted-by":"crossref","first-page":"3168","DOI":"10.1038\/s41467-021-23303-9","article-title":"Structure-based protein function prediction using graph convolutional networks","volume":"12","year":"2021","journal-title":"Nature Communications"},{"key":"2026081711150895000_2026.08.07.743493v1.9","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0203-7"},{"key":"2026081711150895000_2026.08.07.743493v1.10","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.89.22.10915"},{"key":"2026081711150895000_2026.08.07.743493v1.11","doi-asserted-by":"publisher","DOI":"10.1038\/S41586-021-03819-2"},{"key":"2026081711150895000_2026.08.07.743493v1.12","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-022-01464-2"},{"key":"2026081711150895000_2026.08.07.743493v1.13","doi-asserted-by":"crossref","unstructured":"Kessler, A. L. et al. Increased EThcD efficiency on the hybrid Orbitrap Excedion Pro Mass Analyzer extends the depth in identification and sequence coverage of HLA class I immunopeptidomes. bioRxiv 2025\u201306 (2025).","DOI":"10.1101\/2025.06.01.657241"},{"key":"2026081711150895000_2026.08.07.743493v1.14","doi-asserted-by":"publisher","DOI":"10.1101\/2024.10.06.616783"},{"key":"2026081711150895000_2026.08.07.743493v1.15","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad743"},{"key":"2026081711150895000_2026.08.07.743493v1.16","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade2574"},{"key":"2026081711150895000_2026.08.07.743493v1.17","first-page":"1032","article-title":"HLA-DRB1*0401\/0404 genotype and rheumatoid arthritis: increased association in men, young age at onset, and disease severity","volume":"22","year":"1995","journal-title":"J Rheumatol"},{"key":"2026081711150895000_2026.08.07.743493v1.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.str.2023.11.011"},{"key":"2026081711150895000_2026.08.07.743493v1.19","doi-asserted-by":"crossref","unstructured":"Nielsen, M. et al. Lessons learned from the IMMREP23 TCR-epitope prediction challenge. ImmunoInformatics 16, 100045 (2024).","DOI":"10.1016\/j.immuno.2024.100045"},{"key":"2026081711150895000_2026.08.07.743493v1.20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000036"},{"key":"2026081711150895000_2026.08.07.743493v1.21","doi-asserted-by":"crossref","unstructured":"Nielsen, M. , Lundegaard, C. & Lund, O . Prediction of MHC class II binding affinity using SMM-align, a novel stabilization matrix alignment method. BMC Bioinformatics 8, 238 (2007).","DOI":"10.1186\/1471-2105-8-238"},{"key":"2026081711150895000_2026.08.07.743493v1.22","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adj6367"},{"key":"2026081711150895000_2026.08.07.743493v1.23","doi-asserted-by":"publisher","DOI":"10.1101\/2025.06.14.659707"},{"key":"2026081711150895000_2026.08.07.743493v1.24","doi-asserted-by":"crossref","first-page":"945","DOI":"10.1038\/s41592-025-02656-9","article-title":"PTM-Mamba: a PTM-aware protein language model with bidirectional gated Mamba blocks","volume":"22","year":"2025","journal-title":"Nature Methods"},{"key":"2026081711150895000_2026.08.07.743493v1.25","doi-asserted-by":"publisher","DOI":"10.1016\/j.immuni.2023.03.009"},{"key":"2026081711150895000_2026.08.07.743493v1.26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0177140"},{"key":"2026081711150895000_2026.08.07.743493v1.27","doi-asserted-by":"publisher","DOI":"10.1016\/j.immuni.2023.05.009"},{"key":"2026081711150895000_2026.08.07.743493v1.28","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btl071"},{"key":"2026081711150895000_2026.08.07.743493v1.29","doi-asserted-by":"publisher","DOI":"10.1021\/pr500030x"},{"key":"2026081711150895000_2026.08.07.743493v1.30","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae1092"},{"key":"2026081711150895000_2026.08.07.743493v1.31","doi-asserted-by":"publisher","DOI":"10.1007\/s10067-016-3247-4"},{"key":"2026081711150895000_2026.08.07.743493v1.32","doi-asserted-by":"crossref","first-page":"1857","DOI":"10.1038\/s41592-025-02797-x","article-title":"DeepMVP: deep learning models trained on high-quality data accurately predict PTM sites and variant-induced alterations","volume":"22","year":"2025","journal-title":"Nature Methods"},{"key":"2026081711150895000_2026.08.07.743493v1.33","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-117-10-801"},{"key":"2026081711150895000_2026.08.07.743493v1.34","doi-asserted-by":"crossref","unstructured":"He, K. , Zhang, X. , Ren, S. , and Sun, J . (2015). Delving deep into rectifiers: Surpass-ing human-level performance on imagenet classification. In Proceedings of the IEEE international conference on computer vision, pages 1026\u20131034.","DOI":"10.1109\/ICCV.2015.123"},{"issue":"8","key":"2026081711150895000_2026.08.07.743493v1.35","first-page":"597","article-title":"HLA class II and rheumatoid arthritis: the bumpy road of revelation","volume":"69","year":"2017","journal-title":"Immunogenetics"},{"key":"2026081711150895000_2026.08.07.743493v1.36","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkx276"},{"key":"2026081711150895000_2026.08.07.743493v1.37","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-12902-2"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.08.07.743493","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T18:15:24Z","timestamp":1786990524000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.08.07.743493"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":37,"URL":"https:\/\/doi.org\/10.64898\/2026.08.07.743493","relation":{},"subject":[],"published":{"date-parts":[[2026,8,13]]},"subtype":"preprint"}}