{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T04:57:17Z","timestamp":1782881837778,"version":"3.54.5"},"reference-count":39,"publisher":"Oxford University Press (OUP)","issue":"Supplement_1","license":[{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"vor","delay-in-days":14,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["DBI2308699"],"award-info":[{"award-number":["DBI2308699"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R01GM093123"],"award-info":[{"award-number":["R01GM093123"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Support Services"},{"DOI":"10.13039\/100007165","name":"University of Missouri-Columbia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007165","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Powerful generative AI models of protein\u2013ligand structure have recently been proposed, but few of these methods support both flexible protein\u2013ligand docking and affinity estimation. Of those that do, none can directly model multiple binding ligands concurrently or have been rigorously benchmarked on pharmacologically relevant drug targets, hindering their widespread adoption in drug discovery efforts.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>In this work, we propose FlowDock, the first deep geometric generative model based on conditional flow matching (CFM) that learns to directly map unbound (apo) structures to their bound (holo) counterparts for an arbitrary number of binding ligands. Furthermore, FlowDock provides predicted structural confidence scores and binding affinity values with each of its generated protein\u2013ligand complex structures, enabling fast virtual screening of new (multi-ligand) drug targets. For the well-known PoseBusters Benchmark dataset, FlowDock outperforms single-sequence AlphaFold 3 (AF3) with a 51% blind docking success rate using unbound (apo) protein input structures and without any information derived from multiple sequence alignments, and for the challenging new DockGen-E dataset, FlowDock outperforms single-sequence AF3 and matches single-sequence Chai-1 for binding pocket generalization. Additionally, in the ligand category of the 16th community-wide Critical Assessment of Techniques for Structure Prediction, FlowDock ranked among the top-5 methods for pharmacological binding affinity estimation across 140 protein\u2013ligand complexes, demonstrating the efficacy of its learned representations in virtual screening.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Source code, data, and pre-trained models are available at https:\/\/github.com\/BioinfoMachineLearning\/FlowDock<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf187","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T13:02:14Z","timestamp":1752584534000},"page":"i198-i206","source":"Crossref","is-referenced-by-count":13,"title":["<scp>FlowDock<\/scp>: Geometric flow matching for generative protein\u2013ligand docking and affinity prediction"],"prefix":"10.1093","volume":"41","author":[{"given":"Alex","family":"Morehead","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering & Computer Science, NextGen Precision Health, University of Missouri-Columbia , Columbia, MO 65211,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianlin","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering & Computer Science, NextGen Precision Health, University of Missouri-Columbia , Columbia, MO 65211,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"2025071509020751400_btaf187-B1","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":"2025071509020751400_btaf187-B2","first-page":"10","article-title":"Protein data bank","volume":"233","author":"Bank","year":"1971","journal-title":"Nature New Biol"},{"key":"2025071509020751400_btaf187-B3","author":"Bose","year":"2024"},{"key":"2025071509020751400_btaf187-B4","doi-asserted-by":"crossref","first-page":"3130","DOI":"10.1039\/D3SC04185A","article-title":"Posebusters: AI-based docking methods fail to generate physically valid poses or generalise to novel sequences","volume":"15","author":"Buttenschoen","year":"2024","journal-title":"Chem Sci"},{"key":"2025071509020751400_btaf187-B5","author":"CASP16-Organizers","year":"2024"},{"key":"2025071509020751400_btaf187-B6","author":"Chen","year":"2024"},{"key":"2025071509020751400_btaf187-B7","volume-title":"Modeling Molecular Structures with Intrinsic Diffusion Models","author":"Corso","year":"2023"},{"key":"2025071509020751400_btaf187-B8","author":"Corso","year":"2023"},{"key":"2025071509020751400_btaf187-B9","author":"Corso","year":"2024"},{"key":"2025071509020751400_btaf187-B10","author":"Corso","year":"2024"},{"key":"2025071509020751400_btaf187-B11","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1126\/science.add2187","article-title":"Robust deep learning\u2013based protein sequence design using proteinmpnn","volume":"378","author":"Dauparas","year":"2022","journal-title":"Science"},{"key":"2025071509020751400_btaf187-B12","doi-asserted-by":"crossref","first-page":"bbab476","DOI":"10.1093\/bib\/bbab476","article-title":"Artificial intelligence in the prediction of protein\u2013ligand interactions: recent advances and future directions","volume":"23","author":"Dhakal","year":"2022","journal-title":"Brief Bioinform"},{"key":"2025071509020751400_btaf187-B13","first-page":"2024","article-title":"Chai-1: decoding the molecular interactions of life","author":"Discovery","year":"2024","journal-title":"bioRxiv"},{"key":"2025071509020751400_btaf187-B14","author":"Durairaj","year":"2024"},{"key":"2025071509020751400_btaf187-B15","doi-asserted-by":"crossref","first-page":"e1005659","DOI":"10.1371\/journal.pcbi.1005659","article-title":"Openmm 7: rapid development of high performance algorithms for molecular dynamics","volume":"13","author":"Eastman","year":"2017","journal-title":"PLoS Comput Biol"},{"key":"2025071509020751400_btaf187-B16","doi-asserted-by":"crossref","first-page":"3891","DOI":"10.1021\/acs.jcim.1c00203","article-title":"Autodock vina 1.2. 0: new docking methods, expanded force field, and python bindings","volume":"61","author":"Eberhardt","year":"2021","journal-title":"J Chem Inf Model"},{"key":"2025071509020751400_btaf187-B17","author":"Esser","year":"2024"},{"key":"2025071509020751400_btaf187-B18","doi-asserted-by":"crossref","first-page":"726","DOI":"10.1021\/jm061277y","article-title":"Diverse, high-quality test set for the validation of protein- ligand docking performance","volume":"50","author":"Hartshorn","year":"2007","journal-title":"J Med Chem"},{"key":"2025071509020751400_btaf187-B19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025071509020751400_btaf187-B20","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1002\/prot.20512","article-title":"Binding moad (mother of all databases)","volume":"60","author":"Hu","year":"2005","journal-title":"Proteins"},{"key":"2025071509020751400_btaf187-B21","author":"Jing","year":"2024"},{"key":"2025071509020751400_btaf187-B22","first-page":"15330","author":"Joshi","year":"2023"},{"key":"2025071509020751400_btaf187-B23","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":"2025071509020751400_btaf187-B24","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume":"35","author":"Karras","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025071509020751400_btaf187-B25","article-title":"Equivariant flow matching","author":"Klein","year":"2024","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025071509020751400_btaf187-B26","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":"Lin","year":"2023","journal-title":"Science"},{"key":"2025071509020751400_btaf187-B27","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1093\/bioinformatics\/btu626","article-title":"Pdb-wide collection of binding data: current status of the pdbbind database","volume":"31","author":"Liu","year":"2015","journal-title":"Bioinformatics"},{"key":"2025071509020751400_btaf187-B28","first-page":"7236","article-title":"Tankbind: trigonometry-aware neural networks for drug-protein binding structure prediction","volume":"35","author":"Lu","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025071509020751400_btaf187-B29","doi-asserted-by":"crossref","first-page":"1071","DOI":"10.1038\/s41467-024-45461-2","article-title":"Dynamicbind: predicting ligand-specific protein-ligand complex structure with a deep equivariant generative model","volume":"15","author":"Lu","year":"2024","journal-title":"Nat Commun"},{"key":"2025071509020751400_btaf187-B30","first-page":"2503","article-title":"Riemannian continuous normalizing flows","volume":"33","author":"Mathieu","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025071509020751400_btaf187-B31","article-title":"Deep learning for protein-ligand docking: are we there yet?","author":"Morehead","year":"2024"},{"key":"2025071509020751400_btaf187-B32","first-page":"1","article-title":"Normalizing flows for probabilistic modeling and inference","volume":"22","author":"Papamakarios","year":"2021","journal-title":"J Machine Learning Res. Norfolk, Massachusetts, USA."},{"key":"2025071509020751400_btaf187-B33","first-page":"28100","author":"Pooladian","year":"2023"},{"key":"2025071509020751400_btaf187-B34","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1038\/s42256-024-00792-z","article-title":"State-specific protein\u2013ligand complex structure prediction with a multiscale deep generative model","volume":"6","author":"Qiao","year":"2024","journal-title":"Nat Machine Intell"},{"key":"2025071509020751400_btaf187-B35","first-page":"20503","author":"St\u00e4rk","year":"2022"},{"key":"2025071509020751400_btaf187-B36","author":"St\u00e4rk","year":"2024"},{"key":"2025071509020751400_btaf187-B37","first-page":"2835","author":"Tong","year":"2024"},{"key":"2025071509020751400_btaf187-B38","article-title":"Boltz-1: Democratizing Biomolecular Interaction Modeling","volume":"11","author":"Wohlwend","year":"2024","journal-title":"bioRxiv"},{"key":"2025071509020751400_btaf187-B39","doi-asserted-by":"crossref","first-page":"702","DOI":"10.1002\/prot.20264","article-title":"Scoring function for automated assessment of protein structure template quality","volume":"57","author":"Zhang","year":"2004","journal-title":"Proteins"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/Supplement_1\/i198\/63745399\/btaf187.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/Supplement_1\/i198\/63745399\/btaf187.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T13:02:17Z","timestamp":1752584537000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/41\/Supplement_1\/i198\/8199366"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"references-count":39,"journal-issue":{"issue":"Supplement_1","published-print":{"date-parts":[[2025,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf187","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,7]]},"published":{"date-parts":[[2025,7,1]]}}}