{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:34:34Z","timestamp":1772138074086,"version":"3.50.1"},"reference-count":47,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T00:00:00Z","timestamp":1742947200000},"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":[[2025,3,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Predicting the structure of antibody-antigen complexes is a challenging task with significant implications for the design of better antibody therapeutics. However, the levels of success have remained dauntingly low, particularly when high standards for model quality are required, a necessity for efficient antibody design. Artificial intelligence (AI) has significantly impacted the landscape of structure prediction for antibodies, both alone and in complex with their antigens.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We utilized AI-guided antibody modeling tools to generate ensembles displaying diversity in the complementarity-determining region (CDR) and integrated those into our previously published AlphaFold2-rescored docking pipeline, a strategy called AI-augmented physics-based docking. In this study, we also compare docking performance with AlphaFold and Boltz-1, the new state-of-the-art. We distinguish between two types of success tailored to specific downstream applications: (i) criteria sufficient for epitope mapping, where gross quality is adequate and can complement experimental techniques, and (ii) criteria for producing higher-quality models suitable for engineering purposes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We highlight that the quality of the ensemble is crucial for docking performance, that including too many models can be detrimental, and that prioritization of models is essential for achieving good performance. In a scenario analogous to docking using a crystallized antigen, our results robustly demonstrate the advantages of AI-augmented docking over AlphaFold2, further accentuated when higher standards in quality are imposed. Docking also shows improvements over Boltz-1, but those are less pronounced. Docking performance is still noticeably lower than AlphaFold3 in both epitope mapping and antibody design use cases. We observe a strong dependence on CDR-H3 loop length for physics-based tools on their ability to successfully predict. This helps define an applicability range where physics-based docking can be competitive to the newer generation of AI tools.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The AF2 rescoring scripts are available at github.com\/gaudreaultfnrc\/AF2-Rescoring.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf129","type":"journal-article","created":{"date-parts":[[2025,3,23]],"date-time":"2025-03-23T08:47:11Z","timestamp":1742719631000},"source":"Crossref","is-referenced-by-count":5,"title":["AI-augmented physics-based docking for antibody-antigen complex prediction"],"prefix":"10.1093","volume":"41","author":[{"given":"Francis","family":"Gaudreault","sequence":"first","affiliation":[{"name":"Human Health Therapeutics Research Centre, National Research Council Canada , Montreal, Quebec H4P 2R2,","place":["Canada"]}]},{"given":"Traian","family":"Sulea","sequence":"additional","affiliation":[{"name":"Human Health Therapeutics Research Centre, National Research Council Canada , Montreal, Quebec H4P 2R2,","place":["Canada"]},{"name":"Institute of Parasitology, McGill University , Sainte-Anne-de-Bellevue, Quebec H9X 3V9,","place":["Canada"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7657-0286","authenticated-orcid":false,"given":"Christopher R","family":"Corbeil","sequence":"additional","affiliation":[{"name":"Human Health Therapeutics Research Centre, National Research Council Canada , Montreal, Quebec H4P 2R2,","place":["Canada"]},{"name":"Department of Biochemistry, McGill University , Montreal, Quebec H3A 1A3,","place":["Canada"]}]}],"member":"286","published-online":{"date-parts":[[2025,3,26]]},"reference":[{"key":"2025041602172014400_btaf129-B1","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1038\/s42003-023-04927-7","article-title":"ImmuneBuilder: deep-learning models for predicting the structures of immune proteins","volume":"6","author":"Abanades","year":"2023","journal-title":"Commun Biol"},{"key":"2025041602172014400_btaf129-B2","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":"Abramson","year":"2024","journal-title":"Nature"},{"key":"2025041602172014400_btaf129-B3","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1080\/19420862.2015.1099773","article-title":"Computational tool for the early screening of monoclonal antibodies for their viscosities","volume":"8","author":"Agrawal","year":"2016","journal-title":"MAbs"},{"key":"2025041602172014400_btaf129-B4","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1016\/j.jmb.2003.12.073","article-title":"A dissection of specific and non-specific protein\u2013protein interfaces","volume":"336","author":"Bahadur","year":"2004","journal-title":"J Mol Biol"},{"key":"2025041602172014400_btaf129-B5","doi-asserted-by":"crossref","first-page":"e0161879","DOI":"10.1371\/journal.pone.0161879","article-title":"DockQ: a quality measure for protein-protein docking models","volume":"11","author":"Basu","year":"2016","journal-title":"PLoS One"},{"key":"2025041602172014400_btaf129-B6","author":"Boitreaud","year":"2024"},{"key":"2025041602172014400_btaf129-B7","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1093\/bioinformatics\/btq007","article-title":"PyRosetta: a script-based interface for implementing molecular modeling algorithms using Rosetta","volume":"26","author":"Chaudhury","year":"2010","journal-title":"Bioinformatics"},{"key":"2025041602172014400_btaf129-B8","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1002\/prot.10389","article-title":"ZDOCK: an initial-stage protein-docking algorithm","volume":"52","author":"Chen","year":"2003","journal-title":"Proteins"},{"key":"2025041602172014400_btaf129-B9","doi-asserted-by":"crossref","first-page":"11937","DOI":"10.1073\/pnas.0904191106","article-title":"Design of therapeutic proteins with enhanced stability","volume":"106","author":"Chennamsetty","year":"2009","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2025041602172014400_btaf129-B10","doi-asserted-by":"crossref","first-page":"5179","DOI":"10.1021\/ja00124a002","article-title":"A second generation force field for the simulation of proteins, nucleic acids, and organic molecules","volume":"117","author":"Cornell","year":"1995","journal-title":"J Am Chem Soc"},{"key":"2025041602172014400_btaf129-B11","doi-asserted-by":"crossref","first-page":"1731","DOI":"10.1021\/ja026939x","article-title":"HADDOCK: a protein\u2212protein docking approach based on biochemical or biophysical information","volume":"125","author":"Dominguez","year":"2003","journal-title":"J Am Chem Soc"},{"key":"2025041602172014400_btaf129-B12","doi-asserted-by":"crossref","first-page":"D1140","DOI":"10.1093\/nar\/gkt1043","article-title":"SAbDab: the structural antibody database","volume":"42","author":"Dunbar","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2025041602172014400_btaf129-B13","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1021\/acs.jpcb.3c06662","article-title":"OpenMM 8: molecular dynamics simulation with machine learning potentials","volume":"128","author":"Eastman","year":"2024","journal-title":"J Phys Chem B"},{"key":"2025041602172014400_btaf129-B14","author":"Evans","year":"2022"},{"key":"2025041602172014400_btaf129-B15","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1080\/19420862.2019.1618676","article-title":"CDR-H3 loop ensemble in solution\u2013conformational selection upon antibody binding","volume":"11","author":"Fern\u00e1ndez-Quintero","year":"2019","journal-title":"MAbs"},{"key":"2025041602172014400_btaf129-B16","doi-asserted-by":"crossref","first-page":"182","DOI":"10.3389\/fmolb.2020.00182","article-title":"Local and global rigidification upon antibody affinity maturation","volume":"7","author":"Fern\u00e1ndez-Quintero","year":"2020","journal-title":"Front Mol Biosci"},{"key":"2025041602172014400_btaf129-B17","doi-asserted-by":"crossref","first-page":"3065","DOI":"10.3389\/fimmu.2018.03065","article-title":"Characterizing the diversity of the CDR-H3 loop conformational ensembles in relationship to antibody binding properties","volume":"9","author":"Fern\u00e1ndez-Quintero","year":"2019","journal-title":"Front Immunol"},{"key":"2025041602172014400_btaf129-B18","doi-asserted-by":"crossref","first-page":"1253689","DOI":"10.3389\/fmolb.2023.1253689","article-title":"Exploring rigid-backbone protein docking in biologics discovery: a test using the DARPin scaffold","volume":"10","author":"Gaudreault","year":"2023","journal-title":"Front Mol Biosci"},{"key":"2025041602172014400_btaf129-B19","doi-asserted-by":"crossref","first-page":"15107","DOI":"10.1038\/s41598-023-42090-5","article-title":"Enhanced antibody-antigen structure prediction from molecular docking using AlphaFold2","volume":"13","author":"Gaudreault","year":"2023","journal-title":"Sci Rep"},{"key":"2025041602172014400_btaf129-B20","author":"Ghani","year":"2022"},{"key":"2025041602172014400_btaf129-B21","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":"Hie","year":"2024","journal-title":"Nat Biotechnol"},{"key":"2025041602172014400_btaf129-B22","author":"Hitawala"},{"key":"2025041602172014400_btaf129-B23","doi-asserted-by":"crossref","first-page":"4938","DOI":"10.1021\/acs.jctc.8b00225","article-title":"ProPOSE: direct exhaustive Protein-Protein docking with side chain flexibility","volume":"14","author":"Hogues","year":"2018","journal-title":"J Chem Theory Comput"},{"key":"2025041602172014400_btaf129-B24","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.1016\/j.drudis.2014.02.005","article-title":"Search strategies and evaluation in protein-protein docking: principles, advances and challenges","volume":"19","author":"Huang","year":"2014","journal-title":"Drug Discov Today"},{"key":"2025041602172014400_btaf129-B25","doi-asserted-by":"crossref","first-page":"969","DOI":"10.1016\/j.drudis.2015.03.007","article-title":"Exploring the potential of global protein-protein docking: an overview and critical assessment of current programs for automatic ab initio docking","volume":"20","author":"Huang","year":"2015","journal-title":"Drug Discov Today"},{"key":"2025041602172014400_btaf129-B26","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2025041602172014400_btaf129-B27","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1002\/prot.22488","article-title":"Improved prediction of protein side-chain conformations with SCWRL4","volume":"77","author":"Krivov","year":"2009","journal-title":"Proteins"},{"key":"2025041602172014400_btaf129-B28","author":"Lee","year":"2023"},{"key":"2025041602172014400_btaf129-B29","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1016\/j.jmb.2010.09.028","article-title":"A simple definition of structural regions in proteins and its use in analyzing interface evolution","volume":"403","author":"Levy","year":"2010","journal-title":"J Mol Biol"},{"key":"2025041602172014400_btaf129-B30","doi-asserted-by":"crossref","first-page":"20461","DOI":"10.1073\/pnas.1209312109","article-title":"Cellular crowding imposes global constraints on the chemistry and evolution of proteomes","volume":"109","author":"Levy","year":"2012","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2025041602172014400_btaf129-B31","doi-asserted-by":"crossref","first-page":"2322533","DOI":"10.1080\/19420862.2024.2322533","article-title":"Do antibody CDR loops change conformation upon binding?","volume":"16","author":"Liu","year":"2024","journal-title":"MAbs"},{"key":"2025041602172014400_btaf129-B32","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1038\/s41592-022-01488-1","article-title":"ColabFold: making protein folding accessible to all","volume":"19","author":"Mirdita","year":"2022","journal-title":"Nat Methods"},{"key":"2025041602172014400_btaf129-B33","doi-asserted-by":"crossref","first-page":"1078","DOI":"10.1002\/prot.21373","article-title":"ZRANK: reranking protein docking predictions with an optimized energy function","volume":"67","author":"Pierce","year":"2007","journal-title":"Proteins"},{"key":"2025041602172014400_btaf129-B34","doi-asserted-by":"crossref","first-page":"238101","DOI":"10.1103\/PhysRevLett.129.238101","article-title":"State-of-the-art estimation of protein model accuracy using AlphaFold","volume":"129","author":"Roney","year":"2022","journal-title":"Phys Rev Lett"},{"key":"2025041602172014400_btaf129-B35","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1038\/nprot.2010.5","article-title":"I-TASSER: a unified platform for automated protein structure and function prediction","volume":"5","author":"Roy","year":"2010","journal-title":"Nat Protoc"},{"key":"2025041602172014400_btaf129-B36","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":"Ruffolo","year":"2023","journal-title":"Nat Commun"},{"key":"2025041602172014400_btaf129-B37","doi-asserted-by":"crossref","first-page":"979","DOI":"10.1016\/j.cels.2023.10.001","article-title":"IgLM: infilling language modeling for antibody sequence design","volume":"14","author":"Shuai","year":"2023","journal-title":"Cell Syst"},{"key":"2025041602172014400_btaf129-B38","doi-asserted-by":"crossref","first-page":"W474","DOI":"10.1093\/nar\/gkp387","article-title":"RosettaAntibody: antibody variable region homology modeling server","volume":"37","author":"Sircar","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"2025041602172014400_btaf129-B39","doi-asserted-by":"crossref","first-page":"4405","DOI":"10.1172\/JCI69377","article-title":"Human antibodies that neutralize respiratory droplet transmissible H5N1 influenza viruses","volume":"123","author":"Thornburg","year":"2013","journal-title":"J Clin Invest"},{"key":"2025041602172014400_btaf129-B40","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1016\/S1367-5931(00)00216-7","article-title":"Human antibodies as next generation therapeutics","volume":"5","author":"van Dijk","year":"2001","journal-title":"Curr Opin Chem Biol"},{"key":"2025041602172014400_btaf129-B41","doi-asserted-by":"crossref","first-page":"e0181490","DOI":"10.1371\/journal.pone.0181490","article-title":"Assisted design of antibody and protein therapeutics (ADAPT)","volume":"12","author":"Vivcharuk","year":"2017","journal-title":"PLoS One"},{"key":"2025041602172014400_btaf129-B42","doi-asserted-by":"crossref","first-page":"1050","DOI":"10.1002\/prot.25873","article-title":"Performance of ZDOCK and IRAD in CAPRI rounds 39-45","volume":"88","author":"Vreven","year":"2020","journal-title":"Proteins"},{"key":"2025041602172014400_btaf129-B43","doi-asserted-by":"crossref","first-page":"btad573","DOI":"10.1093\/bioinformatics\/btad573","article-title":"AFsample: improving multimer prediction with AlphaFold using massive sampling","volume":"39","author":"Wallner","year":"2023","journal-title":"Bioinformatics"},{"key":"2025041602172014400_btaf129-B44","doi-asserted-by":"crossref","first-page":"832","DOI":"10.1038\/s41586-023-06832-9","article-title":"Predicting multiple conformations via sequence clustering and AlphaFold2","volume":"625","author":"Wayment-Steele","year":"2024","journal-title":"Nature"},{"key":"2025041602172014400_btaf129-B45","author":"Wohlwend","year":"2024"},{"key":"2025041602172014400_btaf129-B46","doi-asserted-by":"crossref","first-page":"e4379","DOI":"10.1002\/pro.4379","article-title":"Benchmarking AlphaFold for protein complex modeling reveals accuracy determinants","volume":"31","author":"Yin","year":"2022","journal-title":"Protein Sci"},{"key":"2025041602172014400_btaf129-B47","doi-asserted-by":"crossref","first-page":"W306","DOI":"10.1093\/nar\/gkv359","article-title":"AGGRESCAN3D (A3D): server for prediction of aggregation properties of protein structures","volume":"43","author":"Zambrano","year":"2015","journal-title":"Nucleic Acids Res"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf129\/62728359\/btaf129.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/4\/btaf129\/62728359\/btaf129.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/4\/btaf129\/62728359\/btaf129.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T02:17:37Z","timestamp":1744769857000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf129\/8093612"}},"subtitle":[],"editor":[{"given":"Arne","family":"Elofsson","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,3,26]]},"references-count":47,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,3,29]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf129","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.11.06.622293","asserted-by":"object"}]},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,4]]},"published":{"date-parts":[[2025,3,26]]},"article-number":"btaf129"}}