{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T17:13:32Z","timestamp":1774890812041,"version":"3.50.1"},"reference-count":59,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T00:00:00Z","timestamp":1756857600000},"content-version":"vor","delay-in-days":3,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001691","name":"KAKENHI","doi-asserted-by":"publisher","award":["22K12150"],"award-info":[{"award-number":["22K12150"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MEXT KAKENHI","award":["21H05027, 22H03645, 25H01144"],"award-info":[{"award-number":["21H05027, 22H03645, 25H01144"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,31]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Sparked by AlphaFold2\u2019s groundbreaking success in protein structure prediction, recent years have seen a surge of interest in developing deep learning (DL) models for molecular docking. Molecular docking is a computational approach for predicting how proteins interact with small molecules known as ligands. It has become an essential tool in drug discovery, enabling structure-based virtual screening (VS) methods to efficiently explore vast libraries of drug-like molecules and identify potential therapeutic candidates. However, traditional docking methods primarily rely on search-and-score algorithms, which are computationally demanding. To be viable for VS applications, these methods often sacrifice accuracy for speed by simplifying their search algorithms and scoring functions. Recent advancements in DL have transformed molecular docking, offering accuracy that rivals\u2014or even surpasses\u2014traditional approaches while significantly reducing computational costs. Despite these advancements, DL-based molecular docking still faces major challenges. DL models often struggle to generalize beyond their training data and frequently mispredict key molecular properties, such as stereochemistry, bond lengths, and steric interactions, leading to physically unrealistic predictions. To overcome these limitations, a new generation of models is using DL to incorporate protein flexibility into docking predictions, aiming to more accurately capture the dynamic nature of biomolecular interactions\u2014a long-standing challenge for traditional methods. This review explores how DL has reshaped molecular docking, examines its current shortcomings, and highlights emerging solutions. Finally, we discuss future opportunities to further bridge the gap between computational predictions and real-world molecular interactions.<\/jats:p>","DOI":"10.1093\/bib\/bbaf454","type":"journal-article","created":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T13:38:19Z","timestamp":1756906699000},"source":"Crossref","is-referenced-by-count":8,"title":["Beyond rigid docking: deep learning approaches for fully flexible protein\u2013ligand interactions"],"prefix":"10.1093","volume":"26","author":[{"given":"John","family":"Lee","sequence":"first","affiliation":[{"name":"Bioinformatics Center , Institute for Chemical Research, Kyoto University, Uji 611-0011,","place":["Japan"]}]},{"given":"Canh","family":"Hao Nguyen","sequence":"additional","affiliation":[{"name":"Bioinformatics Center , Institute for Chemical Research, Kyoto University, Uji 611-0011,","place":["Japan"]}]},{"given":"Hiroshi","family":"Mamitsuka","sequence":"additional","affiliation":[{"name":"Bioinformatics Center , Institute for Chemical Research, Kyoto University, Uji 611-0011,","place":["Japan"]}]}],"member":"286","published-online":{"date-parts":[[2025,9,3]]},"reference":[{"key":"2025090309381266000_ref1","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.1111\/j.1476-5381.2010.01127.x","article-title":"Principles of early drug discovery","volume":"162","author":"Hughes","year":"2011","journal-title":"Br J Pharmacol"},{"key":"2025090309381266000_ref2","doi-asserted-by":"publisher","first-page":"1375","DOI":"10.3390\/ijms20061375","article-title":"The light and dark sides of virtual screening: what is there to know?","volume":"20","author":"Gimeno","year":"2019","journal-title":"Int J Mol Sci"},{"key":"2025090309381266000_ref3","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1016\/bs.pmch.2021.01.004","article-title":"Use of molecular docking computational tools in drug discovery","volume":"60","author":"Stanzione","year":"2021","journal-title":"Prog Med Chem"},{"key":"2025090309381266000_ref4","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","article-title":"Highly accurate protein structure prediction with alphafold","volume":"630","author":"Abramson","year":"2024","journal-title":"Nature"},{"key":"2025090309381266000_ref5","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1016\/0022-2836(82)90153-X","article-title":"A geometric approach to macromolecule-ligand interactions","volume":"161","author":"Kuntz","year":"1982","journal-title":"J Mol Biol"},{"key":"2025090309381266000_ref6","doi-asserted-by":"publisher","first-page":"3016","DOI":"10.3390\/ijms11083016","article-title":"Advances and challenges in protein-ligand docking","volume":"11","author":"Huang","year":"2010","journal-title":"Int J Mol Sci"},{"key":"2025090309381266000_ref7","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1002\/jcc.21334","article-title":"Autodock vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading","volume":"31","author":"Trott","year":"2010","journal-title":"J Comput Chem"},{"key":"2025090309381266000_ref8","doi-asserted-by":"publisher","first-page":"1739","DOI":"10.1021\/jm0306430","article-title":"Glide: a new approach for rapid, accurate docking and scoring. 1. Method and assessment of docking accuracy","volume":"47","author":"Friesner","year":"2004","journal-title":"J Med Chem"},{"key":"2025090309381266000_ref9","volume-title":"And Tommi Jaakkola","author":"St\u00e4rk","year":"2022"},{"key":"2025090309381266000_ref10","article-title":"Tankbind: trigonometry-aware neural networks for drug-protein binding structure prediction","author":"Wei","year":"2022"},{"key":"2025090309381266000_ref11","article-title":"Do deep learning models really outperform traditional approaches in molecular docking?"},{"key":"2025090309381266000_ref12","article-title":"Docking (molecular)","author":"Wikipedia contributors"},{"key":"2025090309381266000_ref13","article-title":"Diffdock: Diffusion steps, twists, and turns for molecular docking"},{"key":"2025090309381266000_ref14","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.1c01830","article-title":"InteractionGraphNet: a novel and efficient deep graph representation learning framework for accurate protein\u2013ligand interaction predictions","volume":"64","author":"","journal-title":"J Med Chem"},{"key":"2025090309381266000_ref15","doi-asserted-by":"publisher","first-page":"2020","DOI":"10.1021\/acs.jpclett.2c03906","article-title":"Geometric interaction graph neural network for predicting protein\u2013ligand binding affinities from 3D structures (GIGN)","volume":"14","author":"Yang","year":"2023","journal-title":"J Phys Chem Lett"},{"key":"2025090309381266000_ref16","volume-title":"And Woo Youn Kim","author":"Moon","year":"2021"},{"key":"2025090309381266000_ref17","doi-asserted-by":"publisher","DOI":"10.3389\/fbinf.2022.885983","article-title":"Scoring functions for protein\u2013ligand binding affinity prediction using structure-based deep learning: a review","volume":"2","author":"","journal-title":"Front Bioinform"},{"key":"2025090309381266000_ref18","article-title":"Never use re-docking for estimation of docking accuracy","author":"Bjerrum"},{"key":"2025090309381266000_ref19","article-title":"DiffDock-pocket: diffusion for pocket-level docking with sidechain flexibility.","author":"Plainer","year":"2023"},{"key":"2025090309381266000_ref20","doi-asserted-by":"publisher","first-page":"8446","DOI":"10.1021\/acs.jctc.3c00273","article-title":"Equivariant flexible modeling of the protein\u2013ligand binding pose with geometric deep learning","volume":"19","author":"Dong","year":"2023","journal-title":"J Chem Theory Comput"},{"key":"2025090309381266000_ref21","article-title":"Aligned diffusion schr\u00f6dinger bridges","author":"Somnath","year":"2024"},{"key":"2025090309381266000_ref22","doi-asserted-by":"publisher","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":"","journal-title":"Nat Commun"},{"key":"2025090309381266000_ref23","doi-asserted-by":"publisher","first-page":"69","DOI":"10.3389\/fphar.2020.00069","article-title":"Predicting or pretending: Artificial intelligence for protein-ligand interactions lack of sufficiently large and unbiased datasets","volume":"11","author":"Yang","year":"2020","journal-title":"Front Pharmacol"},{"key":"2025090309381266000_ref24","article-title":"Diffdock: diffusion steps, twists, and turns for molecular docking","volume-title":"International Conference on Learning Representations (ICLR)","author":"Corso","year":"2023"},{"key":"2025090309381266000_ref25","doi-asserted-by":"publisher","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":"2025090309381266000_ref26","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1038\/s43588-023-00511-5","article-title":"Efficient and accurate large library ligand docking with karmadock","volume":"3","author":"Zhang","year":"2023","journal-title":"Nat Comput Sci"},{"key":"2025090309381266000_ref27","volume-title":"e3nn: Euclidean Neural Networks","author":"Geiger","year":"2022"},{"key":"2025090309381266000_ref28","article-title":"Swallowing the bitter pill: simplified scalable conformer generation"},{"key":"2025090309381266000_ref29","article-title":"Does equivariance matter at scale?"},{"key":"2025090309381266000_ref30","article-title":"Equivariance is not all you need: characterizing the utility of equivariant graph neural networks for particle physics tasks","author":""},{"key":"2025090309381266000_ref31","doi-asserted-by":"publisher","article-title":"Uni-Mol: a universal 3D molecular representation learning framework","DOI":"10.26434\/chemrxiv-2022-jjm0j-v4"},{"key":"2025090309381266000_ref32","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1093\/bib\/bbad462","article-title":"Gaabind: a geometry-aware attention-based network for accurate protein\u2013ligand binding pose and binding affinity prediction","volume":"25","author":"Tan","year":"2023","journal-title":"Brief Bioinform"},{"key":"2025090309381266000_ref33","doi-asserted-by":"publisher","first-page":"1449","DOI":"10.1039\/D3SC05552C","article-title":"Carsidock: a deep learning paradigm for accurate protein\u2013ligand docking and screening based on large-scale pre-training","volume":"15","author":"Cai","year":"2024","journal-title":"Chem Sci"},{"key":"2025090309381266000_ref34","doi-asserted-by":"publisher","first-page":"10223","DOI":"10.1038\/s41467-024-54440-6","article-title":"Interformer: an interaction-aware model for protein-ligand docking and affinity prediction","volume":"15","author":"Lai","year":"2024","journal-title":"Nat Commun"},{"key":"2025090309381266000_ref35","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1711","article-title":"Diffusion models in protein structure and docking","volume":"14","author":"Yim","year":"2024","journal-title":"WIREs Comput Mol Sci"},{"key":"2025090309381266000_ref36","doi-asserted-by":"publisher","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":"2025090309381266000_ref37","doi-asserted-by":"publisher","first-page":"e1004586","DOI":"10.1371\/journal.pcbi.1004586","article-title":"AutoDockFR: advances in protein-ligand docking with explicitly specified binding site flexibility","volume":"11","author":"Ravindranath","year":"2015","journal-title":"PLoS Comput Biol"},{"key":"2025090309381266000_ref38","doi-asserted-by":"publisher","first-page":"1104","DOI":"10.1110\/ps.041153605","article-title":"Side-chain flexibility in protein\u2013ligand binding: the minimal rotation hypothesis","volume":"14","author":"Zavodszky","year":"2005","journal-title":"Protein Sci"},{"key":"2025090309381266000_ref39","article-title":"Flexidock: compositional diffusion models for flexible molecular docking","author":"Wang","year":"2023"},{"key":"2025090309381266000_ref40","doi-asserted-by":"publisher","article-title":"ApoDock: ligand-conditioned sidechain packing for flexible molecular docking","DOI":"10.1101\/2024.11.22.624942"},{"key":"2025090309381266000_ref41","article-title":"FlexVDW: a machine learning approach to account for protein flexibility in ligand docking","author":""},{"key":"2025090309381266000_ref42","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1038\/s41592-024-02516-y","article-title":"Surfdock is a surface-informed diffusion generative model for reliable and accurate protein\u2013ligand complex prediction","volume":"22","author":"Cao","year":"2025","journal-title":"Nat Methods"},{"key":"2025090309381266000_ref43","doi-asserted-by":"publisher","first-page":"1695","DOI":"10.1021\/acs.jcim.2c01436","article-title":"Deep learning model for efficient protein-ligand docking with implicit side-chain flexibility","volume":"63","author":"Masters","year":"2023","journal-title":"J Chem Inf Model"},{"key":"2025090309381266000_ref44","article-title":"Quickbind: a light-weight and interpretable molecular docking model","author":"Treyde","year":"2024"},{"key":"2025090309381266000_ref45","article-title":"Flexible docking via unbalanced flow matching","volume-title":"ICML 2024 AI for Science Workshop"},{"key":"2025090309381266000_ref46","article-title":"Re-Dock: towards flexible and realistic molecular docking with diffusion bridge"},{"key":"2025090309381266000_ref47","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1021\/acs.jmedchem.4c02740","article-title":"Improving the reliability of language model-predicted structures as docking targets through geometric graph learning","volume":"68","author":"Shen","year":"2025","journal-title":"J Med Chem"},{"key":"2025090309381266000_ref48","doi-asserted-by":"publisher","first-page":"i198","DOI":"10.1093\/bioinformatics\/btaf187","volume-title":"Flowdock: geometric flow matching for generative protein-ligand docking and affinity prediction","author":"Morehead","year":"2025"},{"key":"2025090309381266000_ref49","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-48837-6","article-title":"Structure prediction of protein-ligand complexes from sequence information with Umol","volume":"15","author":"","journal-title":"Nat Commun"},{"key":"2025090309381266000_ref50","doi-asserted-by":"publisher","DOI":"10.1126\/science.adl2528","article-title":"Generalized biomolecular modeling and design with rosettafold all-atom","volume":"384","author":"Krishna","year":"2024","journal-title":"Science"},{"key":"2025090309381266000_ref51","doi-asserted-by":"publisher","article-title":"Chai-1: decoding the molecular interactions of life","DOI":"10.1101\/2024.10.10.615955"},{"key":"2025090309381266000_ref52","doi-asserted-by":"publisher","article-title":"Boltz-1: democratizing biomolecular interaction modeling","DOI":"10.1101\/2024.11.19.624167"},{"key":"2025090309381266000_ref53","article-title":"NeuralPLexer3: accurate biomolecular complex structure prediction with flow models"},{"key":"2025090309381266000_ref54","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0666-6","article-title":"Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning","volume":"17","author":"","journal-title":"Nature Methods"},{"key":"2025090309381266000_ref55","article-title":"Assessing the potential of deep learning for protein\u2013ligand docking"},{"key":"2025090309381266000_ref56","doi-asserted-by":"publisher","DOI":"10.1039\/D3SC06803J","article-title":"DiffBindFR: an SE(3) equivariant network for flexible protein\u2013ligand docking","volume-title":"Chem Sci","author":""},{"key":"2025090309381266000_ref57","doi-asserted-by":"publisher","article-title":"Have protein\u2013ligand co-folding methods moved beyond memorisation?","DOI":"10.1101\/2025.02.03.636309"},{"key":"2025090309381266000_ref58","doi-asserted-by":"publisher","article-title":"Do deep learning models for co-folding learn the physics of protein\u2013ligand interactions?","author":"","DOI":"10.1101\/2024.06.03.597219"},{"key":"2025090309381266000_ref59","article-title":"Generative modeling of molecular dynamics trajectories","volume-title":"Advances in Neural Information Processing Systems"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/5\/bbaf454\/64199316\/bbaf454.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/26\/5\/bbaf454\/64199316\/bbaf454.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T13:38:21Z","timestamp":1756906701000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbaf454\/8246683"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":59,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,8,31]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbaf454","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,9]]},"published":{"date-parts":[[2025,8,31]]},"article-number":"bbaf454"}}