{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T12:26:09Z","timestamp":1775478369082,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1012153","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000}}],"reference-count":39,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NIH","award":["R01AI104739"],"award-info":[{"award-number":["R01AI104739"]}]},{"name":"NIH","award":["R01GM131642"],"award-info":[{"award-number":["R01GM131642"]}]},{"name":"NIH","award":["P50CA121974"],"award-info":[{"award-number":["P50CA121974"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Antibodies play a crucial role in the adaptive immune response, with their specificity to antigens being a fundamental determinant of immune function. Accurate prediction of antibody-antigen specificity is vital for understanding immune responses, guiding vaccine design, and developing antibody-based therapeutics. In this study, we present a method of supervised fine-tuning for antibody language models, which improves on pre-trained antibody language model embeddings in binding specificity prediction to SARS-CoV-2 spike protein and influenza hemagglutinin. We perform supervised fine-tuning on four pre-trained antibody language models to predict specificity to these antigens and demonstrate that fine-tuned language model classifiers exhibit enhanced predictive accuracy compared to classifiers trained on pre-trained model embeddings. Additionally, we investigate the change of model attention activations after supervised fine-tuning to gain insights into the molecular basis of antigen recognition by antibodies. Furthermore, we apply the supervised fine-tuned models to BCR repertoire data related to influenza and SARS-CoV-2 vaccination, demonstrating their ability to capture changes in repertoire following vaccination. Overall, our study highlights the effect of supervised fine-tuning on pre-trained antibody language models as valuable tools to improve antigen specificity prediction.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1012153","type":"journal-article","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T16:35:17Z","timestamp":1743438917000},"page":"e1012153","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":14,"title":["Supervised fine-tuning of pre-trained antibody language models improves antigen specificity prediction"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3453-7805","authenticated-orcid":true,"given":"Meng","family":"Wang","sequence":"first","affiliation":[]},{"given":"Jonathan","family":"Patsenker","sequence":"additional","affiliation":[]},{"given":"Henry","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yuval","family":"Kluger","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4957-1544","authenticated-orcid":true,"given":"Steven H.","family":"Kleinstein","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2025,3,31]]},"reference":[{"issue":"4","key":"pcbi.1012153.ref001","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1039\/C8ME00080H","article-title":"Role of antibody heavy and light chain interface residues in affinity maturation of binding to HIV envelope glycoprotein","volume":"4","author":"A Cisneros","year":"2019","journal-title":"Mol Syst Des Eng"},{"issue":"11","key":"pcbi.1012153.ref002","doi-asserted-by":"crossref","first-page":"935","DOI":"10.1038\/nrd1549","article-title":"Docking and scoring in virtual screening for drug discovery: methods and applications","volume":"3","author":"DB Kitchen","year":"2004","journal-title":"Nat Rev Drug Discov"},{"issue":"1","key":"pcbi.1012153.ref003","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab476","article-title":"Artificial intelligence in the prediction of protein-ligand interactions: recent advances and future directions","volume":"23","author":"A Dhakal","year":"2022","journal-title":"Brief Bioinform"},{"issue":"8016","key":"pcbi.1012153.ref004","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","article-title":"Accurate structure prediction of biomolecular interactions with AlphaFold 3","volume":"630","author":"J Abramson","year":"2024","journal-title":"Nature"},{"issue":"7","key":"pcbi.1012153.ref005","doi-asserted-by":"crossref","first-page":"e1012253","DOI":"10.1371\/journal.pcbi.1012253","article-title":"Improved protein complex prediction with AlphaFold-multimer by denoising the MSA profile","volume":"20","author":"P Bryant","year":"2024","journal-title":"PLoS Comput Biol"},{"key":"pcbi.1012153.ref006","article-title":"Multistate and functional protein design using RoseTTAFold sequence space diffusion","author":"SL Lisanza","year":"2024","journal-title":"Nat Biotechnol"},{"issue":"1","key":"pcbi.1012153.ref007","doi-asserted-by":"crossref","first-page":"2389","DOI":"10.1038\/s41467-023-38063-x","article-title":"Fast, accurate antibody structure prediction from deep learning on massive set of natural antibodies","volume":"14","author":"JA Ruffolo","year":"2023","journal-title":"Nat Commun"},{"key":"pcbi.1012153.ref008","article-title":"AntiFold: Improved antibody structure-based design using inverse folding","volume":"2405","author":"M H\u00f8ie","year":"2024","journal-title":"arXiv"},{"key":"pcbi.1012153.ref009","article-title":"Deciphering antibody affinity maturation with language models and weakly supervised learning","author":"JA Ruffolo","year":"2021","journal-title":"arXiv"},{"issue":"7","key":"pcbi.1012153.ref010","doi-asserted-by":"crossref","first-page":"100513","DOI":"10.1016\/j.patter.2022.100513","article-title":"Deciphering the language of antibodies using self-supervised learning","volume":"3","author":"J Leem","year":"2022","journal-title":"Patterns (N Y)"},{"key":"pcbi.1012153.ref011","doi-asserted-by":"crossref","DOI":"10.1101\/2023.12.12.569610","article-title":"Enhancing Antibody Language Models with Structural Information","author":"J Barton","year":"2024"},{"issue":"11","key":"pcbi.1012153.ref012","first-page":"979-989.e4","article-title":"IgLM: Infilling language modeling for antibody sequence design","volume":"14","author":"RW Shuai","year":"2023","journal-title":"Cell Syst"},{"key":"pcbi.1012153.ref013","article-title":"Addressing the antibody germline bias and its effect on language models for improved antibody design","author":"TH Olsen","year":"2024","journal-title":"arXiv"},{"issue":"1","key":"pcbi.1012153.ref014","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1002\/pro.4205","article-title":"Observed antibody space: a diverse database of cleaned, annotated, and translated unpaired and paired antibody sequences","volume":"31","author":"TH Olsen","year":"2022","journal-title":"Protein Sci"},{"key":"pcbi.1012153.ref015","article-title":"Disease diagnostics using machine learning of immune receptors","author":"ME Zaslavsky","year":"2024","journal-title":"bioRxiv"},{"issue":"5","key":"pcbi.1012153.ref016","doi-asserted-by":"crossref","first-page":"100967","DOI":"10.1016\/j.patter.2024.100967","article-title":"Improving antibody language models with native pairing","volume":"5","author":"SM Burbach","year":"2024","journal-title":"Patterns (N Y)"},{"key":"pcbi.1012153.ref017","article-title":"Attention is all you need","volume":"30","author":"A Vaswani","year":"2017","journal-title":"Adv Neural Inform Process Syst"},{"key":"pcbi.1012153.ref018","article-title":"Neural machine translation by jointly learning to align and translate","author":"D Bahdanau","year":"2016","journal-title":"arXiv"},{"issue":"6637","key":"pcbi.1012153.ref019","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":"Z Lin","year":"2023","journal-title":"Science"},{"key":"pcbi.1012153.ref020","doi-asserted-by":"crossref","DOI":"10.1101\/2020.12.15.422761","article-title":"Transformer protein language models are unsupervised structure learners","author":"R Rao","year":"2020"},{"key":"pcbi.1012153.ref021","article-title":"Large scale paired antibody language models","author":"H Kenlay","year":"2024","journal-title":"arXiv"},{"issue":"2","key":"pcbi.1012153.ref022","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":"BL Hie","year":"2024","journal-title":"Nat Biotechnol"},{"issue":"1","key":"pcbi.1012153.ref023","doi-asserted-by":"crossref","DOI":"10.1080\/19420862.2022.2163584","article-title":"Toward generalizable prediction of antibody thermostability using machine learning on sequence and structure features","volume":"15","author":"A Harmalkar","year":"2023","journal-title":"mAbs"},{"key":"pcbi.1012153.ref024","first-page":"04805","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1810","author":"J Devlin","year":"2018","journal-title":"arXiv"},{"key":"pcbi.1012153.ref025","article-title":"Universal language model fine-tuning for text classification","author":"J Howard","year":"2018","journal-title":"arXiv"},{"issue":"D1","key":"pcbi.1012153.ref026","doi-asserted-by":"crossref","first-page":"D339","DOI":"10.1093\/nar\/gky1006","article-title":"The Immune Epitope Database (IEDB): 2018 update","volume":"47","author":"R Vita","year":"2019","journal-title":"Nucleic Acids Res"},{"issue":"7827","key":"pcbi.1012153.ref027","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1038\/s41586-020-2711-0","article-title":"Human germinal centres engage memory and naive B cells after influenza vaccination","volume":"586","author":"JS Turner","year":"2020","journal-title":"Nature"},{"issue":"8","key":"pcbi.1012153.ref028","doi-asserted-by":"crossref","first-page":"e20240668","DOI":"10.1084\/jem.20240668","article-title":"Maturation of germinal center B cells after influenza virus vaccination in humans","volume":"221","author":"KM McIntire","year":"2024","journal-title":"Journal of Experimental Medicine"},{"key":"pcbi.1012153.ref029","article-title":"An explainable language model for antibody specificity prediction using curated influenza hemagglutinin antibodies","author":"Y Wang","year":"2023","journal-title":"bioRxiv"},{"issue":"18","key":"pcbi.1012153.ref030","doi-asserted-by":"crossref","first-page":"9250","DOI":"10.18632\/aging.204778","article-title":"High-throughput single-cell profiling of B cell responses following inactivated influenza vaccination in young and older adults","volume":"15","author":"M Wang","year":"2023","journal-title":"Aging (Albany NY)"},{"issue":"2","key":"pcbi.1012153.ref031","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1093\/nar\/gkad1128","article-title":"Language model-based B cell receptor sequence embeddings can effectively encode receptor specificity","volume":"52","author":"M Wang","year":"2024","journal-title":"Nucleic Acids Res"},{"issue":"7904","key":"pcbi.1012153.ref032","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1038\/s41586-022-04527-1","article-title":"Germinal centre-driven maturation of B cell response to mRNA vaccination","volume":"604","author":"W Kim","year":"2022","journal-title":"Nature"},{"issue":"1","key":"pcbi.1012153.ref033","doi-asserted-by":"crossref","first-page":"2020203","DOI":"10.1080\/19420862.2021.2020203","article-title":"BioPhi: a platform for antibody design, humanization, and humanness evaluation based on natural antibody repertoires and deep learning","volume":"14","author":"D Prihoda","year":"2022","journal-title":"MAbs"},{"key":"pcbi.1012153.ref034","first-page":"13296","article-title":"The ultimate guide to fine-tuning LLMs from basics to breakthroughs: an exhaustive review of technologies, research, best practices, applied research challenges and opportunities","volume":"2408","author":"V Parthasarathy","year":"2024","journal-title":"arXiv"},{"key":"pcbi.1012153.ref035","article-title":"LoRA: low-rank adaptation of large language models","author":"E Hu","year":"2021","journal-title":"arXiv"},{"issue":"10","key":"pcbi.1012153.ref036","doi-asserted-by":"crossref","first-page":"1060","DOI":"10.1038\/s42256-023-00727-0","article-title":"The pitfalls of negative data bias for the T-cell epitope specificity challenge","volume":"5","author":"C Dens","year":"2023","journal-title":"Nat Mach Intell"},{"key":"pcbi.1012153.ref037","doi-asserted-by":"crossref","DOI":"10.1101\/2024.06.17.599333","article-title":"Training data composition determines machine learning generalization and biological rule discovery","author":"E Ursu","year":"2024"},{"issue":"5","key":"pcbi.1012153.ref038","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1038\/s42256-023-00637-1","article-title":"Linguistically inspired roadmap for building biologically reliable protein language models","volume":"5","author":"MH Vu","year":"2023","journal-title":"Nat Mach Intell"},{"issue":"6","key":"pcbi.1012153.ref039","doi-asserted-by":"crossref","first-page":"2489","DOI":"10.4049\/jimmunol.1601850","article-title":"Hierarchical clustering can identify b cell clones with high confidence in ig repertoire sequencing data","volume":"198","author":"NT Gupta","year":"2017","journal-title":"J Immunol"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1012153","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T13:40:32Z","timestamp":1745329232000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012153"}},"subtitle":[],"editor":[{"given":"Rob J","family":"De Boer","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":39,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,3,31]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1012153","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.05.13.593807","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,31]]}}}