{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T19:04:15Z","timestamp":1792263855595,"version":"4.4.0"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1012618","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000}}],"reference-count":39,"publisher":"Public Library of Science (PLoS)","issue":"11","license":[{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000865","name":"Bill and Melinda Gates Foundation","doi-asserted-by":"publisher","award":["OPP1084362 and OPP1175094"],"award-info":[{"award-number":["OPP1084362 and OPP1175094"]}],"id":[{"id":"10.13039\/100000865","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>\n                    The ability to predict HIV-1 resistance to broadly neutralizing antibodies (bnAbs) will increase bnAb therapeutic benefits. Machine learning is a powerful approach for such prediction. One challenge is that some HIV-1 subtypes in currently available training datasets are underrepresented, which likely affects models\u2019 generalizability across subtypes. A second challenge is that combinations of bnAbs are required to avoid the inevitable resistance to a single bnAb, and computationally determining optimal combinations of bnAbs is an unsolved problem. Recently, machine learning models trained using resistance outcomes for multiple antibodies at once, a strategy called multi-task learning (MTL), have been shown to improve predictions. We develop a new model and show that, beyond the boost in performance, MTL also helps address the previous two challenges. Specifically, we demonstrate empirically that MTL can mitigate bias from underrepresented subtypes, and that MTL allows the model to learn patterns of co-resistance to combinations of antibodies, thus providing tools to predict antibodies\u2019 epitopes and to potentially select optimal bnAb combinations. Our analyses, publicly available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/iaime\/LBUM\" xlink:type=\"simple\">https:\/\/github.com\/iaime\/LBUM<\/jats:ext-link>\n                    , can be adapted to other infectious diseases that are treated with antibody therapy.\n                  <\/jats:p>","DOI":"10.1371\/journal.pcbi.1012618","type":"journal-article","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T13:39:09Z","timestamp":1732109949000},"page":"e1012618","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":11,"title":["Learning patterns of HIV-1 resistance to broadly neutralizing antibodies with reduced subtype bias using multi-task learning"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2850-637X","authenticated-orcid":true,"given":"Aime Bienfait","family":"Igiraneza","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3645-662X","authenticated-orcid":true,"given":"Panagiota","family":"Zacharopoulou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3169-698X","authenticated-orcid":true,"given":"Robert","family":"Hinch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9847-8226","authenticated-orcid":true,"given":"Chris","family":"Wymant","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3662-4192","authenticated-orcid":true,"given":"Lucie","family":"Abeler-D\u00f6rner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7163-7277","authenticated-orcid":true,"given":"John","family":"Frater","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2399-9657","authenticated-orcid":true,"given":"Christophe","family":"Fraser","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,11,20]]},"reference":[{"issue":"6151","key":"pcbi.1012618.ref001","doi-asserted-by":"crossref","first-page":"1199","DOI":"10.1126\/science.1241144","article-title":"Antibodies in HIV-1 Vaccine Development and Therapy","volume":"341","author":"F Klein","year":"2013","journal-title":"Science"},{"issue":"7724","key":"pcbi.1012618.ref002","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1038\/s41586-018-0531-2","article-title":"Combination therapy with anti-HIV-1 antibodies maintains viral suppression","volume":"561","author":"P Mendoza","year":"2018","journal-title":"Nature"},{"issue":"7913","key":"pcbi.1012618.ref003","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1038\/s41586-022-04597-1","article-title":"Prolonged viral suppression with anti-HIV-1 antibody therapy","volume":"606","author":"C Gaebler","year":"2022","journal-title":"Nature"},{"key":"pcbi.1012618.ref004","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1007\/978-1-59745-170-3_26","article-title":"Measuring HIV neutralization in a luciferase reporter gene assay","volume":"485","author":"DC Montefiori","year":"2009","journal-title":"Methods Mol Biol Clifton NJ"},{"key":"pcbi.1012618.ref005","doi-asserted-by":"crossref","first-page":"14696","DOI":"10.1038\/s41598-019-50635-w","article-title":"Accurate Prediction for Antibody Resistance of Clinical HIV-1 Isolates","volume":"9","author":"R Rawi","year":"2019","journal-title":"Sci Rep"},{"issue":"10","key":"pcbi.1012618.ref006","doi-asserted-by":"crossref","first-page":"e1005789","DOI":"10.1371\/journal.pcbi.1005789","article-title":"Prediction of HIV-1 sensitivity to broadly neutralizing antibodies shows a trend towards resistance over time","volume":"13","author":"A Hake","year":"2017","journal-title":"PLoS Comput Biol"},{"issue":"22","key":"pcbi.1012618.ref007","doi-asserted-by":"crossref","first-page":"4187","DOI":"10.1093\/bioinformatics\/btab398","article-title":"Super LeArner Prediction of NAb Panels (SLAPNAP): a containerized tool for predicting combination monoclonal broadly neutralizing antibody sensitivity","volume":"37","author":"BD Williamson","year":"2021","journal-title":"Bioinformatics"},{"issue":"4","key":"pcbi.1012618.ref008","doi-asserted-by":"crossref","first-page":"e1006952","DOI":"10.1371\/journal.pcbi.1006952","article-title":"Prediction of VRC01 neutralization sensitivity by HIV-1 gp160 sequence features","volume":"15","author":"CA Magaret","year":"2019","journal-title":"PLoS Comput Biol"},{"issue":"4","key":"pcbi.1012618.ref009","doi-asserted-by":"crossref","first-page":"e1006954","DOI":"10.1371\/journal.pcbi.1006954","article-title":"Estimation of the breadth of CD4bs targeting HIV antibodies by molecular modeling and machine learning","volume":"15","author":"S Conti","year":"2019","journal-title":"PLOS Comput Biol"},{"issue":"10","key":"pcbi.1012618.ref010","doi-asserted-by":"crossref","first-page":"1710","DOI":"10.3390\/ijms17101710","article-title":"Learning the Relationship between the Primary Structure of HIV Envelope Glycoproteins and Neutralization Activity of Particular Antibodies by Using Artificial Neural Networks","volume":"17","author":"C Buiu","year":"2016","journal-title":"Int J Mol Sci"},{"issue":"9","key":"pcbi.1012618.ref011","doi-asserted-by":"crossref","first-page":"e1003842","DOI":"10.1371\/journal.pcbi.1003842","article-title":"IDEPI: Rapid Prediction of HIV-1 Antibody Epitopes and Other Phenotypic Features from Sequence Data Using a Flexible Machine Learning Platform","volume":"10","author":"NL Hepler","year":"2014","journal-title":"PLOS Comput Biol"},{"issue":"18","key":"pcbi.1012618.ref012","doi-asserted-by":"crossref","first-page":"4278","DOI":"10.1093\/bioinformatics\/btac530","article-title":"Prediction of HIV sensitivity to monoclonal antibodies using aminoacid sequences and deep learning","volume":"38","author":"VR D\u0103n\u0103il\u0103","year":"2022","journal-title":"Bioinformatics"},{"issue":"W1","key":"pcbi.1012618.ref013","doi-asserted-by":"crossref","first-page":"W213","DOI":"10.1093\/nar\/gkv404","article-title":"CATNAP: a tool to compile, analyze and tally neutralizing antibody panels","volume":"43","author":"H Yoon","year":"2015","journal-title":"Nucleic Acids Res"},{"issue":"3","key":"pcbi.1012618.ref014","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1097\/COH.0000000000000534","article-title":"HIV subtype diversity worldwide","volume":"14","author":"N Bbosa","year":"2019","journal-title":"Curr Opin HIV AIDS"},{"key":"pcbi.1012618.ref015","unstructured":"HIV and AIDS [Internet]. [cited 2023 May 24]. Available from: https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/hiv-aids."},{"issue":"1","key":"pcbi.1012618.ref016","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.chom.2018.12.001","article-title":"HIV-1 Neutralizing Antibody Signatures and Application to Epitope-Targeted Vaccine Design","volume":"25","author":"CA Bricault","year":"2019","journal-title":"Cell Host Microbe"},{"issue":"1","key":"pcbi.1012618.ref017","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask Learning","volume":"28","author":"R. Caruana","year":"1997","journal-title":"Mach Learn"},{"key":"pcbi.1012618.ref018","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-94-009-8467-7_1","volume-title":"Papers on Syntax","author":"ZS Harris","year":"1981"},{"key":"pcbi.1012618.ref019","article-title":"Learning the language of viral evolution and escape","author":"B Hie","year":"2021","journal-title":"Science"},{"key":"pcbi.1012618.ref020","doi-asserted-by":"crossref","unstructured":"Yang Z, Yang D, Dyer C, He X, Smola A, Hovy E. Hierarchical Attention Networks for Document Classification. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies [Internet]. San Diego, California: Association for Computational Linguistics; 2016 [cited 2022 Aug 4]. p. 1480\u20139. Available from: https:\/\/aclanthology.org\/N16-1174","DOI":"10.18653\/v1\/N16-1174"},{"key":"pcbi.1012618.ref021","article-title":"Neural Machine Translation by Jointly Learning to Align and Translate","author":"D Bahdanau","year":"2016","journal-title":"arXiv"},{"key":"pcbi.1012618.ref022","article-title":"Feed-Forward Networks with Attention Can Solve Some Long-Term Memory Problems","author":"C Raffel","year":"2016","journal-title":"arXiv"},{"key":"pcbi.1012618.ref023","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1146\/annurev-immunol-041015-055515","article-title":"Broadly Neutralizing Antibodies to HIV and Their Role in Vaccine Design","volume":"34","author":"DR Burton","year":"2016","journal-title":"Annu Rev Immunol"},{"issue":"7525","key":"pcbi.1012618.ref024","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1038\/nature13601","article-title":"Broad and potent HIV-1 neutralization by a human antibody that binds the gp41-gp120 interface","volume":"515","author":"J Huang","year":"2014","journal-title":"Nature"},{"issue":"6287","key":"pcbi.1012618.ref025","doi-asserted-by":"crossref","first-page":"828","DOI":"10.1126\/science.aae0474","article-title":"Fusion peptide of HIV-1 as a site of vulnerability to neutralizing antibody","volume":"352","author":"R Kong","year":"2016","journal-title":"Science"},{"issue":"6","key":"pcbi.1012618.ref026","doi-asserted-by":"crossref","first-page":"1379","DOI":"10.1016\/j.cell.2015.08.035","article-title":"Broadly Neutralizing Antibody 8ANC195 Recognizes Closed and Open States of HIV-1","volume":"162","author":"L Scharf","year":"2015","journal-title":"Env. Cell"},{"issue":"5","key":"pcbi.1012618.ref027","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1016\/j.immuni.2014.04.009","article-title":"Broadly neutralizing HIV antibodies define a glycan-dependent epitope on the pre-fusion conformation of the gp41 protein on cleaved Envelope trimers","volume":"40","author":"E Falkowska","year":"2014","journal-title":"Immunity"},{"key":"pcbi.1012618.ref028","doi-asserted-by":"crossref","first-page":"102429","DOI":"10.1016\/j.artmed.2022.102429","article-title":"The applications of machine learning in HIV neutralizing antibodies research\u2014A systematic review","volume":"134","author":"VR D\u0103n\u0103il\u0103","year":"2022","journal-title":"Artif Intell Med"},{"issue":"1","key":"pcbi.1012618.ref029","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"L. Breiman","year":"2001","journal-title":"Mach Learn"},{"issue":"5","key":"pcbi.1012618.ref030","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"JH Friedman","year":"2001","journal-title":"Ann Stat"},{"issue":"1","key":"pcbi.1012618.ref031","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1128\/JVI.01791-15","article-title":"New Member of the V1V2-Directed CAP256-VRC26 Lineage That Shows Increased Breadth and Exceptional Potency","volume":"90","author":"NA Doria-Rose","year":"2015","journal-title":"J Virol"},{"issue":"11","key":"pcbi.1012618.ref032","doi-asserted-by":"crossref","first-page":"1003","DOI":"10.1056\/NEJMoa2031738","article-title":"Two Randomized Trials of Neutralizing Antibodies to Prevent HIV-1 Acquisition","volume":"384","author":"L Corey","year":"2021","journal-title":"N Engl J Med"},{"key":"pcbi.1012618.ref033","doi-asserted-by":"crossref","unstructured":"Ono M, Miwa M, Sasaki Y. Word Embedding-based Antonym Detection using Thesauri and Distributional Information. In: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies [Internet]. Denver, Colorado: Association for Computational Linguistics; 2015 [cited 2023 Aug 29]. p. 984\u20139. Available from: https:\/\/aclanthology.org\/N15-1100.","DOI":"10.3115\/v1\/N15-1100"},{"issue":"11","key":"pcbi.1012618.ref034","doi-asserted-by":"crossref","first-page":"1617","DOI":"10.1038\/s41587-022-01432-w","article-title":"Single-sequence protein structure prediction using a language model and deep learning","volume":"40","author":"R Chowdhury","year":"2022","journal-title":"Nat Biotechnol"},{"key":"pcbi.1012618.ref035","first-page":"29287","volume-title":"Advances in Neural Information Processing Systems","author":"J Meier","year":"2021"},{"issue":"8","key":"pcbi.1012618.ref036","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"S Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"pcbi.1012618.ref037","article-title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","author":"L McInnes","year":"2020","journal-title":"arXiv"},{"issue":"85","key":"pcbi.1012618.ref038","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"pcbi.1012618.ref039","unstructured":"O\u2019Malley T, Bursztein E, Long J, Chollet F, Jin H, Invernizzi L, et al. KerasTuner [Internet]. 2019. Available from: https:\/\/github.com\/keras-team\/keras-tuner."}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1012618","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012618","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T13:45:47Z","timestamp":1733319947000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1012618"}},"subtitle":[],"editor":[{"given":"Roland R.","family":"Regoes","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,11,20]]},"references-count":39,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2024,11,20]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1012618","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.09.28.559724","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,20]]}}}