{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T13:33:13Z","timestamp":1793021593322,"version":"4.5.0"},"reference-count":43,"publisher":"American Chemical Society (ACS)","issue":"20","license":[{"start":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T00:00:00Z","timestamp":1791417600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T00:00:00Z","timestamp":1791417600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T00:00:00Z","timestamp":1791417600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2022M3E5F3080873"],"award-info":[{"award-number":["NRF-2022M3E5F3080873"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00334098"],"award-info":[{"award-number":["RS-2024-00334098"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,26]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Efficient exploration of combinatorial chemical space under synthetic constraints remains a central challenge in computational molecular design. Here, we present FragDock, a molecular design framework that combines building-block (BB)-based virtual synthesis with tethered docking guided by a predefined core structure. FragDock defines a structured search space by assembling molecules from synthetically accessible BBs through known chemical reactions and evaluating candidates using tethered docking with a restrained core-binding pose. Within this framework, we introduce FragDockRL, a reinforcement-learning-based search method that uses rewards derived from rDock-based tethered docking followed by SMINA scoring and a modified Deep Q-Network (DQN) to guide stepwise molecular growth. We evaluated FragDockRL on three therapeutically important protein targets\u2500the receptor tyrosine kinases CSF1R and VEGFR2 and the coagulation protease FA10\u2500selected to represent distinct biological functions and target classes. We assessed its performance using training-cycle analysis and benchmark comparisons with One-Step Reaction, Random Search, Beam Search, and Monte Carlo Tree Search. FragDockRL progressively enriched molecules with favorable docking scores during learning and generated more cutoff-passing unique molecules than Random Search across all three targets, supporting the benefit of learning-guided prioritization. However, the best-performing search strategy was target-dependent: One-Step Reaction, FragDockRL, and Beam Search each showed advantages in different cases. Representative molecular case studies showed that selected compounds retained reference-like binding poses while introducing structural variation into peripheral regions. The reaction schemes used commercially available BBs and well-established medicinal chemistry transformations, which supported the synthetic plausibility of the selected compounds. Overall, FragDock provides a flexible framework for synthetically constrained, structure-guided molecular exploration, and FragDockRL offers a learning-guided search mode for productive candidate prioritization under limited-generation budgets.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c02851","type":"journal-article","created":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T12:02:10Z","timestamp":1791460930000},"page":"13339-13356","source":"Crossref","is-referenced-by-count":0,"title":["FragDockRL: A Reinforcement\nLearning Method for Fragment-Based\nLigand Design via Building-Block Assembly and Tethered Docking"],"prefix":"10.1021","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6124-4568","authenticated-orcid":true,"given":"Seung Hwan","family":"Hong","sequence":"first","affiliation":[{"name":"Novelism , ,","place":["Seoul, Republic of Korea, 06730"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyunsoo","family":"Kim","sequence":"additional","affiliation":[{"name":"Novelism , ,","place":["Seoul, Republic of Korea, 06730"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sejin","family":"Kim","sequence":"additional","affiliation":[{"name":"Ewha Womans University , , ,","place":["Seoul, Republic of Korea, 03760"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7016-2417","authenticated-orcid":true,"given":"Soosung","family":"Kang","sequence":"additional","affiliation":[{"name":"Ewha Womans University , , ,","place":["Seoul, Republic of Korea, 03760"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,10,8]]},"reference":[{"key":"2026102608110477600_cit1","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1111\/j.1365-2125.2004.02194.x","article-title":"The Use\nof Pharmacokinetic and Pharmacodynamic Data in the Assessment of Drug\nSafety in Early Drug Development","volume":"58","author":"Walker","year":"2004","journal-title":"Br. J. Clin.\nPharmacol."},{"key":"2026102608110477600_cit2","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1038\/d41573-018-00007-2","article-title":"Mapping\nBiologically Active Chemical Space to Accelerate Drug Discovery","volume":"18","author":"Sittampalam","year":"2019","journal-title":"Nat. Rev. Drug Discovery"},{"key":"2026102608110477600_cit3","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1007\/s12094-006-0048-2","article-title":"High Throughput\nScreening in Drug Discovery","volume":"8","author":"Carnero","year":"2006","journal-title":"Clin. Transl. Oncol."},{"issue":"7805","key":"2026102608110477600_cit4","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1038\/s41586-020-2117-z","article-title":"An Open-Source Drug\nDiscovery Platform Enables Ultra-Large Virtual Screens","volume":"580","author":"Gorgulla","year":"2020","journal-title":"Nature"},{"key":"2026102608110477600_cit5","doi-asserted-by":"publisher","first-page":"1132","DOI":"10.1002\/jcc.23905","article-title":"DOCK 6:\nImpact of New Features and Current Docking Performance","volume":"36","author":"Allen","year":"2015","journal-title":"J. Comput. Chem."},{"key":"2026102608110477600_cit6","doi-asserted-by":"publisher","first-page":"3891","DOI":"10.1021\/acs.jcim.1c00203","article-title":"AutoDock Vina 1.2.0:\nNew Docking Methods, Expanded Force Field, and Python Bindings","volume":"61","author":"Eberhardt","year":"2021","journal-title":"J. Chem. Inf. Model."},{"key":"2026102608110477600_cit7","doi-asserted-by":"publisher","first-page":"1893","DOI":"10.1021\/ci300604z","article-title":"Lessons Learned\nin Empirical Scoring\nwith smina from the CSAR 2011 Benchmarking Exercise","volume":"53","author":"Koes","year":"2013","journal-title":"J. Chem. Inf. Model."},{"key":"2026102608110477600_cit8","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1003571","article-title":"rDock: A Fast, Versatile and Open Source Program for\nDocking Ligands to Proteins and Nucleic Acids","volume":"10","author":"Ruiz-Carmona","year":"2014","journal-title":"PLoS Comput. Biol."},{"key":"2026102608110477600_cit9","doi-asserted-by":"publisher","first-page":"7866","DOI":"10.1039\/D0SC06805E","article-title":"Accelerating High-Throughput\nVirtual\nScreening through Molecular Pool-Based Active Learning","volume":"12","author":"Graff","year":"2021","journal-title":"Chem. Sci."},{"key":"2026102608110477600_cit10","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.1021\/acs.jcim.3c01790","article-title":"Thompson\nSampling\u2500An Efficient Method for Searching Ultralarge Synthesis\non Demand Databases","volume":"64","author":"Klarich","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"2026102608110477600_cit11","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1021\/acscentsci.0c00229","article-title":"Deep Docking:\nA Deep Learning Platform for Augmentation of Structure Based Drug\nDiscovery","volume":"6","author":"Gentile","year":"2020","journal-title":"ACS Cent. Sci."},{"key":"2026102608110477600_cit12","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1038\/s41596-021-00659-2","article-title":"Artificial\nIntelligence-Enabled Virtual Screening of Ultra-Large Chemical Libraries\nwith Deep Docking","volume":"17","author":"Gentile","year":"2022","journal-title":"Nat. Protoc."},{"key":"2026102608110477600_cit13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2405.01155","article-title":"SynFlowNet: Design\nof Diverse\nand Novel Molecules with Synthesis Constraints","author":"Cretu","year":"2025","journal-title":"arXiv"},{"key":"2026102608110477600_cit14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2401.09840","article-title":"FREED++: Improving\nRL Agents for Fragment-Based Molecule Generation by Thorough Reproduction","author":"Telepov","year":"2024","journal-title":"arXiv"},{"key":"2026102608110477600_cit15","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1038\/s41586-021-04220-9","article-title":"Synthon-Based Ligand\nDiscovery in Virtual Libraries of over 11 Billion Compounds","volume":"601","author":"Sadybekov","year":"2022","journal-title":"Nature"},{"key":"2026102608110477600_cit16","doi-asserted-by":"publisher","first-page":"4576","DOI":"10.1021\/acs.jcim.6c00397","article-title":"A Reinforcement\nLearning-Guided Genetic Algorithm Integrating\nMedicinal Chemistry-Inspired Molecular Transformations","volume":"66","author":"Alberga","year":"2026","journal-title":"J. Chem. Inf. Model."},{"key":"2026102608110477600_cit17","doi-asserted-by":"publisher","first-page":"3463","DOI":"10.1021\/jm040031v","article-title":"Fragment-Based\nDrug Discovery","volume":"47","author":"Erlanson","year":"2004","journal-title":"J. Med. Chem."},{"key":"2026102608110477600_cit18","doi-asserted-by":"publisher","first-page":"2239","DOI":"10.1016\/j.bmcl.2018.05.048","article-title":"\u201cTethering\u201d\nFragment-Based Drug Discovery to Identify Inhibitors of the Essential\nRespiratory Membrane Protein Type II NADH Dehydrogenase","volume":"28","author":"Heikal","year":"2018","journal-title":"Bioorg. Med. Chem. Lett."},{"key":"2026102608110477600_cit19","unstructured":"Enamine Building-Block Library.\n          \n          2026. https:\/\/enamine.net. (Accessed May\n11 2026)."},{"key":"2026102608110477600_cit20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.5602","article-title":"Playing Atari with\nDeep Reinforcement Learning","author":"Mnih","year":"2013","journal-title":"arXiv"},{"key":"2026102608110477600_cit21","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/978-3-540-75538-8_7","article-title":"Efficient Selectivity\nand Backup Operators in Monte-Carlo Tree Search","volume-title":"Computers And Games","author":"Coulom","year":"2007"},{"key":"2026102608110477600_cit22","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/11871842_29","article-title":"Bandit Based Monte-Carlo\nPlanning","volume-title":"Machine Learning: ECML 2006","author":"Kocsis","year":"2006"},{"key":"2026102608110477600_cit23","doi-asserted-by":"publisher","first-page":"3093","DOI":"10.1021\/ci200379p","article-title":"A Collection\nof Robust Organic Synthesis Reactions for in Silico Molecule Design","volume":"51","author":"Hartenfeller","year":"2011","journal-title":"J. Chem. Inf. Model."},{"key":"2026102608110477600_cit24","unstructured":"RDKit:\nOpen-Source Cheminformatics Software. 2026. https:\/\/www.rdkit.org.\n(Accessed May 11, 2026)."},{"issue":"1","key":"2026102608110477600_cit25","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1186\/s40425-017-0257-y","article-title":"Colony-Stimulating\nFactor 1 Receptor (CSF1R) Inhibitors\nin Cancer Therapy","volume":"5","author":"Cannarile","year":"2017","journal-title":"J. Immunother. Cancer"},{"key":"2026102608110477600_cit26","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/s11239-021-02458-8","article-title":"Roles of Factor\nXa beyond Coagulation","volume":"52","author":"Ruf","year":"2021","journal-title":"J. Thromb. Thrombolysis"},{"key":"2026102608110477600_cit27","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1038\/nm0603-669","article-title":"The Biology\nof VEGF and Its Receptors","volume":"9","author":"Ferrara","year":"2003","journal-title":"Nat. Med."},{"key":"2026102608110477600_cit28","doi-asserted-by":"publisher","first-page":"6582","DOI":"10.1021\/jm300687e","article-title":"Directory of Useful\nDecoys, Enhanced (DUD-E): Better Ligands and Decoys for Better Benchmarking","volume":"55","author":"Mysinger","year":"2012","journal-title":"J. Med. Chem."},{"key":"2026102608110477600_cit29","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1007\/978-1-4939-7000-1_26","article-title":"Protein Data Bank (PDB): The Single Global Macromolecular\nStructure Archive","volume":"1607","author":"Burley","year":"2017","journal-title":"Methods Mol. Biol."},{"key":"2026102608110477600_cit30","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1005659","article-title":"OpenMM 7: Rapid Development\nof High Performance Algorithms for Molecular Dynamics","volume":"13","author":"Eastman","year":"2017","journal-title":"PLoS Comput. Biol."},{"key":"2026102608110477600_cit31","doi-asserted-by":"publisher","first-page":"2302","DOI":"10.1093\/nar\/gki524","article-title":"TM-align: A Protein Structure Alignment\nAlgorithm Based\non the TM-score","volume":"33","author":"Zhang","year":"2005","journal-title":"Nucleic Acids Res."},{"key":"2026102608110477600_cit32","unstructured":"Schro\u0308dinger, LLC.\n          \n          The PyMOL Molecular\nGraphics System; Schro\u0308dinger, LLC2024."},{"issue":"D1","key":"2026102608110477600_cit33","doi-asserted-by":"publisher","first-page":"D1180","DOI":"10.1093\/nar\/gkad1004","article-title":"The\nChEMBL Database\nin 2023: A Drug Discovery Platform Spanning Multiple Bioactivity Data\nTypes and Time Periods","volume":"52","author":"Zdrazil","year":"2024","journal-title":"Nucleic Acids Res."},{"key":"2026102608110477600_cit34","doi-asserted-by":"publisher","first-page":"2785","DOI":"10.1002\/jcc.21256","article-title":"AutoDock4\nand AutoDockTools4: Automated\nDocking with Selective Receptor Flexibility","volume":"30","author":"Morris","year":"2009","journal-title":"J. Comput. Chem."},{"key":"2026102608110477600_cit35","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-Connectivity Fingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem.\nInf. Model."},{"key":"2026102608110477600_cit36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980","article-title":"Adam: A Method for Stochastic\nOptimization","author":"Kingma","year":"2017","journal-title":"arXiv"},{"key":"2026102608110477600_cit37","first-page":"249","article-title":"Understanding\nthe Difficulty of Training Deep Feedforward Neural Networks","volume-title":"Proceedings of the Thirteenth International Conference\non Artificial Intelligence and Statistics","author":"Glorot","year":"2010"},{"key":"2026102608110477600_cit38","doi-asserted-by":"publisher","first-page":"565644","DOI":"10.3389\/fphar.2020.565644","article-title":"Molecular Sets (MOSES):\nA Benchmarking Platform for Molecular Generation\nModels","volume":"11","author":"Polykovskiy","year":"2020","journal-title":"Front. Pharmacol."},{"key":"2026102608110477600_cit39","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.1021\/jm9602928","article-title":"The Properties of Known Drugs. 1","volume":"39","author":"Bemis","year":"1996","journal-title":"Molecular Frameworks. J. Med. Chem."},{"key":"2026102608110477600_cit40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1708.08227","article-title":"ChemGAN Challenge\nfor Drug Discovery: Can AI Reproduce Natural Chemical Diversity?","author":"Benhenda","year":"2017","journal-title":"arXiv"},{"key":"2026102608110477600_cit41","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0169-409X(00)00129-0","article-title":"Experimental and\ncomputational approaches to estimate solubility and permeability in\ndrug discovery and development settings","volume":"46","author":"Lipinski","year":"2001","journal-title":"Adv.\nDrug Delivery Rev."},{"key":"2026102608110477600_cit42","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/nchem.1243","article-title":"Quantifying\nthe Chemical Beauty of Drugs","volume":"4","author":"Bickerton","year":"2012","journal-title":"Nat. Chem."},{"key":"2026102608110477600_cit43","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/1758-2946-1-8","article-title":"Estimation\nof Synthetic Accessibility Score of Drug-Like\nMolecules Based on Molecular Complexity and Fragment Contributions","volume":"1","author":"Ertl","year":"2009","journal-title":"J. Cheminform."}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c02851","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/20\/13339\/68781961\/acs.jcim.6c02851.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/20\/13339\/68781961\/acs.jcim.6c02851.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T12:38:03Z","timestamp":1793018283000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/20\/13339\/5446760\/FragDockRL-A-Reinforcement-Learning-Method-for"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,8]]},"references-count":43,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2026,10,8]]},"published-print":{"date-parts":[[2026,10,26]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c02851","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,8]]}}}