{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T12:49:17Z","timestamp":1791809357522,"version":"4.3.4"},"reference-count":32,"publisher":"American Chemical Society (ACS)","issue":"19","license":[{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"publisher","award":["R35GM153437"],"award-info":[{"award-number":["R35GM153437"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Generalizability of molecular docking predictions across novel protein targets and distinct small-molecule chemotypes is key to the successful application of deep learning co-folding approaches in drug discovery, as highlighted by recent benchmarks, including Runs-n-Poses [S\u030ckrinjar, P.; et al.Nat. Struct. Mol. Biol.2026, 33, 782\u2013794.]. To compare generalizability across physics-based, hybrid rescoring models, and co-folding approaches, we systematically benchmarked several molecular docking tools representing these paradigms. Our results support previous observations that co-folding approaches show superior performance on targets resembling their training datasets. However, they deteriorate sharply to unacceptably low 20\u201340% success rates on novel dissimilar systems, consistent with memorization. In contrast, physics-based and hybrid methods exhibit greater out-of-distribution robustness, maintaining more than 60% success rates for docking protein\u2013ligand complexes with minimal similarity to previously known complexes. Our results highlight the complementarity of AI-based approaches and methods based on physical sampling in all-atom models, in terms of their applicability range, and argue for the benefits of tighter integration.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c01293","type":"journal-article","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T14:03:26Z","timestamp":1789999406000},"page":"12948-12954","source":"Crossref","is-referenced-by-count":0,"title":["Multiparadigm Benchmark\nof Molecular Docking: From\nPhysics to Co-Folding and Hybrid Models"],"prefix":"10.1021","volume":"66","author":[{"given":"Ao","family":"Xu","sequence":"first","affiliation":[{"name":"University of Southern California , , , ,","place":["Los Angeles, California, United States, 90089"]},{"name":"University of Southern California , , , ,","place":["Los Angeles, California, United States, 90089"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jordy Homing","family":"Lam","sequence":"additional","affiliation":[{"name":"University of Southern California , , , ,","place":["Los Angeles, California, United States, 90089"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3228-3896","authenticated-orcid":true,"given":"Aiichiro","family":"Nakano","sequence":"additional","affiliation":[{"name":"University of Southern California , , , ,","place":["Los Angeles, California, United States, 90089"]},{"name":"University of Southern California , , , ,","place":["Los Angeles, California, United States, 90089"]},{"name":"University of Southern California , , , ,","place":["Los Angeles, California, United States, 90089"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3883-4505","authenticated-orcid":true,"given":"Vsevolod","family":"Katritch","sequence":"additional","affiliation":[{"name":"University of Southern California , , , ,","place":["Los Angeles, California, United States, 90089"]},{"name":"University of Southern California , , , ,","place":["Los Angeles, California, United States, 90089"]},{"name":"University of Southern California , , , ,","place":["Los Angeles, California, United States, 90089"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,21]]},"reference":[{"key":"2026101208072074400_cit1","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1038\/s41594-026-01797-5","article-title":"Evaluating generalization in protein-ligand\ncofolding methods","volume":"33","author":"S\u030ckrinjar","year":"2026","journal-title":"Nat. Struct. Mol. Biol."},{"key":"2026101208072074400_cit2","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1002\/prot.21082","article-title":"Protein-ligand docking: current status\nand future challenges","volume":"65","author":"Sousa","year":"2006","journal-title":"Proteins"},{"key":"2026101208072074400_cit3","doi-asserted-by":"publisher","first-page":"13384","DOI":"10.3390\/molecules200713384","article-title":"Molecular\ndocking and structure-based drug design strategies","volume":"20","author":"Ferreira","year":"2015","journal-title":"Molecules"},{"key":"2026101208072074400_cit4","doi-asserted-by":"publisher","first-page":"545","DOI":"10.3390\/md18110545","article-title":"Recent advances in\nmolecular docking\nfor the research and discovery of potential marine drugs","volume":"18","author":"Chen","year":"2020","journal-title":"Mar. Drugs"},{"key":"2026101208072074400_cit5","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-40160-2","article-title":"Molecular docking as\na tool for the discovery of molecular targets of nutraceuticals in\ndiseases management","volume":"13","author":"Agu","year":"2023","journal-title":"Sci. Rep."},{"key":"2026101208072074400_cit6","doi-asserted-by":"publisher","first-page":"7569","DOI":"10.1021\/acs.jcim.5c00222","article-title":"Synthon-Based Strategies Exploiting\nMolecular Similarity\nand Protein-Ligand Interactions for Efficient Screening of Ultra-Large\nChemical Libraries","volume":"65","author":"Medel-Lacruz","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"2026101208072074400_cit7","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1038\/s41586-023-05905-z","article-title":"Computational approaches\nstreamlining drug discovery","volume":"616","author":"Sadybekov","year":"2023","journal-title":"Nature"},{"key":"2026101208072074400_cit8","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1002\/jcc.21334","article-title":"AutoDock Vina: improving\nthe speed and accuracy of\ndocking with a new scoring function, efficient optimization, and multithreading","volume":"31","author":"Trott","year":"2010","journal-title":"J. Comput. Chem."},{"key":"2026101208072074400_cit9","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1002\/jcc.540150503","article-title":"ICM\u2500A new method for protein\nmodeling and design: Applications to docking and structure prediction\nfrom the distorted native conformation","volume":"15","author":"Abagyan","year":"1994","journal-title":"J. Comput.\nChem."},{"key":"2026101208072074400_cit10","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1006\/jmbi.1994.1430","article-title":"Decomposition of the free energy of a system in terms\nof specific interactions: implications for theoretical and experimental\nstudies","volume":"240","author":"Mark","year":"1994","journal-title":"J. Mol. Biol."},{"key":"2026101208072074400_cit11","doi-asserted-by":"publisher","first-page":"13735","DOI":"10.1021\/j100102a046","article-title":"When are\nfree energy components meaningful?","volume":"98","author":"Smith","year":"1994","journal-title":"J. Phys.\nChem. A"},{"key":"2026101208072074400_cit12","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-021-00522-2","article-title":"GNINA 1.0: molecular\ndocking with deep learning","volume":"13","author":"McNutt","year":"2021","journal-title":"J. Cheminf."},{"key":"2026101208072074400_cit13","unstructured":"Ho, J.; Jain, A.; Abbeel, P. In  Denoising Diffusion\nProbabilistic\nModels, Advances in Neural Information Processing Systems\n33,; NeurIPS, 2020;\npp 6840\u20136851."},{"key":"2026101208072074400_cit14","unstructured":"Corso, G.; Sta\u0308rk, H.; Jing, B.; Barzilay, R.; Jaakkola, T.\n          DiffDock: Diffusion Steps,\nTwists, and Turns for Molecular Docking, International\nConference on Learning Representations (ICLR). 2023,\narXiv:2210.01776. arXiv.org e-Print archive. https:\/\/arxiv.org\/abs\/2210.01776."},{"key":"2026101208072074400_cit15","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1038\/s41592-024-02516-y","article-title":"SurfDock is a surface-informed\ndiffusion generative model for reliable\nand accurate protein-ligand complex prediction","volume":"22","author":"Cao","year":"2025","journal-title":"Nat. Methods"},{"key":"2026101208072074400_cit16","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-45461-2","article-title":"DynamicBind: predicting\nligand-specific protein-ligand complex structure\nwith a deep equivariant generative model","volume":"15","author":"Lu","year":"2024","journal-title":"Nat.\nCommun."},{"key":"2026101208072074400_cit17","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction\nwith AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2026101208072074400_cit18","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-024-07487-w","article-title":"Accurate\nstructure prediction of biomolecular\ninteractions with AlphaFold 3","volume":"630","author":"Abramson","year":"2024","journal-title":"Nature"},{"key":"2026101208072074400_cit19","unstructured":"Boitreaud, J.; Dent, J.; McPartlon, M.; Meier, J.; Reis, V.; Rogozhonikov, A.; Wu, K.; Chai Discovery Team.. Chai-1: Decoding\nthe molecular interactions of lifebioRxiv20242024.10.10.61595510.1101\/2024.10.10.615955."},{"key":"2026101208072074400_cit20","doi-asserted-by":"crossref","unstructured":"Passaro, S.; Corso, G.; Wohlwend, J.; Reveiz, M.; Thaler, S.; Somnath, V. R.; Getz, N.; Portnoi, T.; Roy, J.; Stark, H.; et al.\n          Boltz-2: Towards accurate and efficient\nbinding affinity prediction\n          bioRxiv\n          2025\n          10.1101\/2025.06.14.659707.","DOI":"10.1101\/2025.06.14.659707"},{"key":"2026101208072074400_cit21","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/s42256-024-00792-z","article-title":"State-specific\nprotein-ligand complex structure prediction with a multiscale deep\ngenerative model","volume":"6","author":"Qiao","year":"2024","journal-title":"Nat. Mach. Intell."},{"key":"2026101208072074400_cit22","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-67127-3","article-title":"Benchmarking\nall-atom\nbiomolecular structure prediction with FoldBench","volume":"17","author":"Xu","year":"2026","journal-title":"Nat. Commun."},{"key":"2026101208072074400_cit23","doi-asserted-by":"publisher","first-page":"8848","DOI":"10.1021\/acs.jcim.4c00905","article-title":"Benchmarking Cross-Docking\nStrategies in Kinase Drug Discovery","volume":"64","author":"Schaller","year":"2024","journal-title":"J. Chem.\nInf. Model."},{"key":"2026101208072074400_cit24","unstructured":"Huang, Y.; Zhang, O.; Wu, L.; Tan, C.; Lin, H.; Gao, Z.; Li, S.; Li, S. Z. In  Re-Dock: Towards\nFlexible and Realistic Molecular Docking with Diffusion Bridge, Proceedings of the 41st International Conference on Machine Learning\n(ICML); ICML, 2024;\npp 20474\u201320489."},{"key":"2026101208072074400_cit25","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1038\/s42256-025-01160-1","article-title":"Assessing\nthe potential of deep learning for protein-ligand docking","volume":"8","author":"Morehead","year":"2026","journal-title":"Nat. Mach. Intell."},{"key":"2026101208072074400_cit26","doi-asserted-by":"crossref","unstructured":"Leung, S.; Bodkin, M.; Von Delft, F.; Brennan, P.; Morris, G.\n          SuCOS is better\nthan RMSD for evaluating fragment elaboration and docking poses\n          ChemRxiv\n          2019\n          10.26434\/chemrxiv.8100203.v1.","DOI":"10.26434\/chemrxiv.8100203.v1"},{"key":"2026101208072074400_cit27","doi-asserted-by":"publisher","first-page":"3336","DOI":"10.1021\/acs.jctc.2c01145","article-title":"Uni-dock:\nGpu-accelerated docking enables ultralarge virtual screening","volume":"19","author":"Yu","year":"2023","journal-title":"J. Chem. Theory Comput."},{"key":"2026101208072074400_cit28","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1007\/s10822-012-9547-0","article-title":"Docking and scoring\nwith ICM: the\nbenchmarking results and strategies for improvement","volume":"26","author":"Neves","year":"2012","journal-title":"J. Comput.-Aided Mol. Des."},{"key":"2026101208072074400_cit29","doi-asserted-by":"crossref","unstructured":"Wohlwend, J.; Corso, G.; Passaro, S.; Getz, N.; Reveiz, M.; Leidal, K.; Swiderski, W.; Atkinson, L.; Portnoi, T.; Chinn, I.; et al.\n          Boltz-1 democratizing biomolecular interaction\nmodeling\n          bioRxiv\n          2025\n          10.1101\/2024.11.19.624167.","DOI":"10.1101\/2024.11.19.624167"},{"key":"2026101208072074400_cit30","unstructured":"Chen, X.; Zhang, Y.; Lu, C.; Ma, W.; Guan, J.; Gong, C.; Yang, J.; Zhang, H.; Zhang, K.; ByteDance AML AI4Science Team; et al.. Protenix-advancing structure prediction\nthrough a comprehensive AlphaFold3 reproductionbioRxiv202510.1101\/2025.01.08.631967."},{"key":"2026101208072074400_cit31","doi-asserted-by":"publisher","first-page":"3130","DOI":"10.1039\/D3SC04185A","article-title":"PoseBusters:\nAI-based docking methods\nfail to generate physically valid poses or generalise to novel sequences","volume":"15","author":"Buttenschoen","year":"2024","journal-title":"Chem. Sci."},{"key":"2026101208072074400_cit32","doi-asserted-by":"publisher","first-page":"2722","DOI":"10.1093\/bioinformatics\/btt473","article-title":"lDDT: a local superposition-free\nscore for comparing protein structures and models using distance difference\ntests","volume":"29","author":"Mariani","year":"2013","journal-title":"Bioinformatics"}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c01293","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/19\/12948\/68582407\/acs.jcim.6c01293.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/19\/12948\/68582407\/acs.jcim.6c01293.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T12:27:32Z","timestamp":1791808052000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/19\/12948\/5434364\/Multiparadigm-Benchmark-of-Molecular-Docking-From"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,21]]},"references-count":32,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,9,21]]},"published-print":{"date-parts":[[2026,10,12]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c01293","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,21]]}}}