{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T05:21:55Z","timestamp":1794547315214,"version":"4.9.1"},"reference-count":53,"publisher":"American Chemical Society (ACS)","issue":"19","license":[{"start":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:00:00Z","timestamp":1790121600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:00:00Z","timestamp":1790121600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:00:00Z","timestamp":1790121600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202498"],"award-info":[{"award-number":["62202498"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572487"],"award-info":[{"award-number":["62572487"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2025MS1026"],"award-info":[{"award-number":["ZR2025MS1026"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016697","name":"Youth Innovation Technology Project of Higher School in Shandong Province","doi-asserted-by":"publisher","award":["2023KJ070"],"award-info":[{"award-number":["2023KJ070"]}],"id":[{"id":"10.13039\/100016697","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Young Talent of Lifting engineering for Science and Technology in Shandong","award":["SDAST2025QTA018"],"award-info":[{"award-number":["SDAST2025QTA018"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Ensuring synthetic accessibility remains a major challenge in de novo drug design, as generative models can produce high-scoring molecules that are difficult to synthesize. To address this issue, we propose CRAFT, a reaction-aware molecular optimization framework that integrates Monte Carlo Tree Search (MCTS) with a multimodal strategy network. Unlike sequence-only baselines, CRAFT explicitly encodes two-dimensional molecular topology and atom-level reaction roles, enabling chemically feasible transformations during multi-step optimization. Comprehensive evaluations on DRD2, AKT1, and CXCR4 demonstrate that CRAFT consistently outperforms state-of-the-art methods, generating more high-scoring candidates while improving reaction-constrained synthetic accessibility and molecular diversity. CRAFT also rediscovers scaffolds homologous to known active ligands and identifies novel chemical entities beyond the training distribution, as supported by molecular docking simulations. Moreover, the model provides transparent forward-synthesis pathways for generated candidates, helping bridge in silico molecular design and practical synthesis.<\/jats:p>","DOI":"10.1021\/acs.jmedchem.6c00920","type":"journal-article","created":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T16:03:13Z","timestamp":1790179393000},"page":"21919-21936","source":"Crossref","is-referenced-by-count":0,"title":["CRAFT: A Chemical Reaction-Aware Transformer for Synthesizable Molecular Optimization via Multimodal Learning"],"prefix":"10.1021","volume":"69","author":[{"given":"Runfu","family":"Yu","sequence":"first","affiliation":[{"name":"China University of Petroleum , , ,","place":["Qingdao, China, 266580"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7485-8558","authenticated-orcid":true,"given":"Tongmao","family":"Ma","sequence":"additional","affiliation":[{"name":"China University of Petroleum , , ,","place":["Qingdao, China, 266580"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zian","family":"Song","sequence":"additional","affiliation":[{"name":"China University of Petroleum , , ,","place":["Qingdao, China, 266580"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiyao","family":"Yin","sequence":"additional","affiliation":[{"name":"China University of Petroleum , , ,","place":["Qingdao, China, 266580"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0335-7914","authenticated-orcid":true,"given":"Shuang","family":"Wang","sequence":"additional","affiliation":[{"name":"China University of Petroleum , , ,","place":["Qingdao, China, 266580"]},{"name":"Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software , ,","place":["Qingdao, China, 266580"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,23]]},"reference":[{"key":"2026100811110582500_cit1","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1001\/jama.2020.1166","article-title":"Estimated research and development investment needed to bring a new medicine to market, 2009\u22122018","volume":"323","author":"Wouters","year":"2020","journal-title":"JAMA"},{"key":"2026100811110582500_cit2","doi-asserted-by":"crossref","DOI":"10.26434\/chemrxiv.14554803.v1","volume-title":"Report on an NIH Workshop on Ultralarge Chemistry Databases","author":"Warr","year":"2021"},{"key":"2026100811110582500_cit3","doi-asserted-by":"publisher","first-page":"31357","DOI":"10.1021\/jacs.4c11686","article-title":"Deep lead optimization: leveraging generative AI for structural modification","volume":"146","author":"Zhang","year":"2024","journal-title":"J. Am. Chem. Soc."},{"key":"2026100811110582500_cit4","doi-asserted-by":"publisher","first-page":"131109","DOI":"10.1016\/j.eswa.2026.131109","article-title":"DualBind: Dual-Module Protein-ligand Binding Affinity Prediction with Adaptive GNN and Structure-Aware Transformer","volume":"309","author":"Lin","year":"2026","journal-title":"Expert Systems with Applications"},{"key":"2026100811110582500_cit5","doi-asserted-by":"publisher","first-page":"bbad235","DOI":"10.1093\/bib\/bbad235","article-title":"Comprehensive evaluation of deep and graph learning on drug\u2212drug interactions prediction","volume":"24","author":"Lin","year":"2023","journal-title":"Briefings Bioinf."},{"key":"2026100811110582500_cit6","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1597","article-title":"Deep learning for drug repurposing: Methods, databases, and applications","volume":"12","author":"Pan","year":"2022","journal-title":"Wiley Interdiscip. Rev.:Comput. Mol. Sci."},{"key":"2026100811110582500_cit7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tkde.2022.3188154","article-title":"Kg-mtl: knowledge graph enhanced multi-task learning for molecular interaction","volume":"35","author":"Ma","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"2026100811110582500_cit8","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","article-title":"Automatic chemical design using a data-driven continuous representation of molecules","volume":"4","author":"Go\u0301mez-Bombarelli","year":"2018","journal-title":"ACS Cent. Sci."},{"key":"2026100811110582500_cit9","doi-asserted-by":"publisher","first-page":"3408","DOI":"10.1038\/s41467-024-47613-w","article-title":"Prospective de novo drug design with deep interactome learning","volume":"15","author":"Atz","year":"2024","journal-title":"Nat. Commun."},{"key":"2026100811110582500_cit10","doi-asserted-by":"publisher","first-page":"18","DOI":"10.3390\/molecules30010018","article-title":"Generation of rational drug-like molecular structures through a multiple-objective reinforcement learning framework","volume":"30","author":"Zhang","year":"2024","journal-title":"Molecules"},{"key":"2026100811110582500_cit11","doi-asserted-by":"publisher","first-page":"43963","DOI":"10.1021\/acsomega.4c08027","article-title":"Enhancing de novo drug design across multiple therapeutic targets with CVAE generative models","volume":"9","author":"Romanelli","year":"2024","journal-title":"ACS Omega"},{"key":"2026100811110582500_cit12","doi-asserted-by":"publisher","first-page":"3867","DOI":"10.1016\/j.bpj.2025.01.022","article-title":"Transformer graph variational autoencoder for generative molecular design","volume":"124","author":"Nguyen","year":"2025","journal-title":"Biophys. J."},{"key":"2026100811110582500_cit13","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1038\/s42004-025-01635-7","article-title":"Optimizing drug design by merging generative AI with a physics-based active learning framework","volume":"8","author":"Filella-Merce","year":"2025","journal-title":"Commun. Chem."},{"key":"2026100811110582500_cit14","doi-asserted-by":"publisher","first-page":"113131","DOI":"10.1016\/j.knosys.2025.113131","article-title":"AdaMGT: Molecular representation learning via adaptive mixture of GCN-Transformer","volume":"311","author":"Ding","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"2026100811110582500_cit15","doi-asserted-by":"publisher","first-page":"1212","DOI":"10.1038\/s41598-023-50834-6","article-title":"MedGAN: optimized generative adversarial network with graph convolutional networks for novel molecule design","volume":"14","author":"Macedo","year":"2024","journal-title":"Sci. Rep."},{"key":"2026100811110582500_cit16","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1012229","article-title":"MTMol-GPT: De novo multi-target molecular generation with transformer-based generative adversarial imitation learning","volume":"20","author":"Ai","year":"2024","journal-title":"PLoS Comput. Biol."},{"key":"2026100811110582500_cit17","doi-asserted-by":"publisher","first-page":"arXiv.2502.16446","DOI":"10.48550\/arXiv.2502.16446","article-title":"Auxiliary Discrminator Sequence Generative Adversarial Networks (ADSeqGAN) for Few Sample Molecule Generation","author":"Tang","year":"2025","journal-title":"arXiv"},{"key":"2026100811110582500_cit18","doi-asserted-by":"publisher","first-page":"arXiv.2303.03543","DOI":"10.48550\/arXiv.2303.03543","article-title":"3D Equivariant Diffusion for target-aware Molecule Generation and Affinity Prediction","author":"Guan","year":"2023","journal-title":"arXiv"},{"key":"2026100811110582500_cit19","unstructured":"Huang, Z.; Yang, L.; Zhou, X.; Protein-ligand interaction prior for binding-aware 3D molecule diffusion models. In Proceedings of the International Conference on Learning Representations; ICLR, 2024."},{"key":"2026100811110582500_cit20","doi-asserted-by":"publisher","first-page":"arXiv.2403.13829","DOI":"10.48550\/arXiv.2403.13829","article-title":"Decompopt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization","author":"Zhou","year":"2024","journal-title":"arXiv"},{"key":"2026100811110582500_cit21","doi-asserted-by":"publisher","first-page":"7928","DOI":"10.1038\/s41467-025-63245-0","article-title":"Target-aware 3D molecular generation based on guided equivariant diffusion","volume":"16","author":"Hu","year":"2025","journal-title":"Nat. Commun."},{"key":"2026100811110582500_cit22","doi-asserted-by":"publisher","first-page":"115605","DOI":"10.1016\/j.knosys.2026.115605","article-title":"Unifying affinity prediction and target-aware molecule generation with a multi-task diffusion model","volume":"340","author":"Li","year":"2026","journal-title":"Knowledge-Based Systems"},{"key":"2026100811110582500_cit23","doi-asserted-by":"publisher","first-page":"5714","DOI":"10.1021\/acs.jcim.0c00174","article-title":"The synthesizability of molecules proposed by generative models","volume":"60","author":"Gao","year":"2020","journal-title":"J. Chem. Inf. Model."},{"key":"2026100811110582500_cit24","unstructured":"Cretu, M.; Harris, C.; Roy, J.; SynFlowNet: Towards molecule design with guaranteed synthesis pathways. In ICLR 2024 Workshop on Generative and Experimental Perspectives for Biomolecular Design, 2024."},{"key":"2026100811110582500_cit25","doi-asserted-by":"publisher","first-page":"46908","DOI":"10.52202\/079017-1488","article-title":"RGFN: Synthesizable molecular generation using GFlowNets","volume":"37","author":"Koziarski","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2026100811110582500_cit26","doi-asserted-by":"publisher","first-page":"arXiv.2410.04542","DOI":"10.48550\/arXiv.2410.04542","article-title":"Generative flows on synthetic pathway for drug design","author":"Seo","year":"2024","journal-title":"arXiv"},{"key":"2026100811110582500_cit27","doi-asserted-by":"publisher","first-page":"10127","DOI":"10.1038\/s41467-024-54456-y","article-title":"ClickGen: Directed exploration of synthesizable chemical space via modular reactions and reinforcement learning","volume":"15","author":"Wang","year":"2024","journal-title":"Nat. Commun."},{"key":"2026100811110582500_cit28","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1038\/s42004-025-01437-x","article-title":"Molecular optimization using a conditional transformer for reaction-aware compound exploration with reinforcement learning","volume":"8","author":"Nakamura","year":"2025","journal-title":"Commun. Chem."},{"key":"2026100811110582500_cit29","doi-asserted-by":"crossref","unstructured":"Li, C.; Yamanaka, C.; Kaitoh, K.; Transformer-based Objective-reinforced Generative Adversarial Network to Generate Desired Molecules. In Proceedings of the International Joint Conference on Artificial Intelligence, 2022; pp 3884\u22123890.","DOI":"10.24963\/ijcai.2022\/539"},{"key":"2026100811110582500_cit30","doi-asserted-by":"publisher","first-page":"arXiv.2105.14491","DOI":"10.48550\/arXiv.2105.14491","article-title":"How attentive are graph attention networks?","author":"Brody","year":"2021","journal-title":"arXiv"},{"key":"2026100811110582500_cit31","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1038\/s42256-024-00809-7","article-title":"Generative AI for designing and validating easily synthesizable and structurally novel antibiotics","volume":"6","author":"Swanson","year":"2024","journal-title":"Nat. Mach. Intell."},{"key":"2026100811110582500_cit32","first-page":"6852","article-title":"Barking up the right tree: an approach to search over molecule synthesis DAGs","volume":"33","author":"Bradshaw","year":"2020","journal-title":"In Adv. Neural Inf. Process. Syst."},{"key":"2026100811110582500_cit33","doi-asserted-by":"publisher","first-page":"044117","DOI":"10.1063\/5.0076749","article-title":"Generating reaction trees with cascaded variational autoencoders","volume":"156","author":"Nguyen","year":"2022","journal-title":"J. Chem. Phys."},{"key":"2026100811110582500_cit34","article-title":"A model to search for synthesizable molecules","volume":"32","author":"Bradshaw","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2026100811110582500_cit35","doi-asserted-by":"publisher","first-page":"1197","DOI":"10.1038\/s41467-024-45102-8","article-title":"Difficulty in chirality recognition for transformer architectures learning chemical structures from string representations","volume":"15","author":"Yoshikai","year":"2024","journal-title":"Nat. Commun."},{"key":"2026100811110582500_cit36","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.1021\/jm9602928","article-title":"The properties of known drugs. 1. Molecular frameworks","volume":"39","author":"Bemis","year":"1996","journal-title":"J. Med. Chem."},{"key":"2026100811110582500_cit37","doi-asserted-by":"publisher","first-page":"565644","DOI":"10.3389\/fphar.2020.565644","article-title":"Molecular sets (MOSES): a benchmarking platform for molecular generation models","volume":"11","author":"Polykovskiy","year":"2020","journal-title":"Front. Pharmacol."},{"key":"2026100811110582500_cit38","doi-asserted-by":"publisher","first-page":"1736","DOI":"10.1021\/acs.jcim.8b00234","article-title":"Fre\u0301chet ChemNet distance: a metric for generative models for molecules in drug discovery","volume":"58","author":"Preuer","year":"2018","journal-title":"J. Chem. Inf. Model."},{"key":"2026100811110582500_cit39","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/1758-2946-1-8","article-title":"Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions","volume":"1","author":"Ertl","year":"2009","journal-title":"J. Cheminf."},{"key":"2026100811110582500_cit40","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":"2026100811110582500_cit41","unstructured":"Lowe, D.\n          \n          Chemical Reactions from U.S. Patents (1976\u2212Sep2016); Figshare dataset. Available online, 2017."},{"key":"2026100811110582500_cit42","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1038\/s42256-020-00284-w","article-title":"Mapping the space of chemical reactions using attention-based neural networks","volume":"3","author":"Schwaller","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"2026100811110582500_cit43","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abe4166","article-title":"Extraction of organic chemistry grammar from unsupervised learning of chemical reactions","volume":"7","author":"Schwaller","year":"2021","journal-title":"Sci. Adv."},{"key":"2026100811110582500_cit44","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1039\/c9sc04944d","article-title":"Datasets and their influence on the development of computer assisted synthesis planning tools in the pharmaceutical domain","volume":"11","author":"Thakkar","year":"2020","journal-title":"Chem. Sci."},{"key":"2026100811110582500_cit45","unstructured":"Daylight Chemical Information Systems\n          \n          SMARTS Theory Manual, Website (Accessed 30 Sep, 2020)."},{"key":"2026100811110582500_cit46","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1186\/s13321-017-0203-5","article-title":"ExCAPE-DB: an integrated large scale dataset facilitating big data analysis in chemogenomics","volume":"9","author":"Sun","year":"2017","journal-title":"J. Cheminf."},{"key":"2026100811110582500_cit47","doi-asserted-by":"publisher","first-page":"D1180","DOI":"10.1093\/nar\/gkad1004","article-title":"The ChEMBL database in 2023: a drug discovery platform spanning multiple bioac-tivity data types and time periods","volume":"52","author":"Zdrazil","year":"2024","journal-title":"Nucleic Acids Res."},{"key":"2026100811110582500_cit48","doi-asserted-by":"publisher","first-page":"6582","DOI":"10.1021\/jm300687e","article-title":"Directory of useful decoys, enhanced (DUD-E): better ligands and decoys for better benchmarking","volume":"55","author":"Mysinger","year":"2012","journal-title":"J. Med. Chem."},{"key":"2026100811110582500_cit49","doi-asserted-by":"publisher","first-page":"4111","DOI":"10.1021\/jm048957q","article-title":"The PDBbind database: methodologies and updates","volume":"48","author":"Wang","year":"2005","journal-title":"J. Med. Chem."},{"key":"2026100811110582500_cit50","unstructured":"Fpocket Fpocket Website; GitHub repository, Accessed Jan. 10, 2024, 2024."},{"key":"2026100811110582500_cit51","doi-asserted-by":"crossref","unstructured":"Kocsis, L.; Szepesva\u0301ri, C.\n          Bandit based monte-carlo planning. In Proceedings of the European Conference on Machine Learning, 2006; pp 282\u2212293.","DOI":"10.1007\/11871842_29"},{"key":"2026100811110582500_cit52","unstructured":"Landrum, G.; Team, R.\n          RDKit: Open-source cheminformatics; Software2024."},{"key":"2026100811110582500_cit53","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Journal of Medicinal Chemistry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jmedchem.6c00920","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jmcmar\/article-pdf\/69\/19\/21919\/68625020\/jm6c00920.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jmcmar\/article-pdf\/69\/19\/21919\/68625020\/jm6c00920.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T04:21:16Z","timestamp":1794543676000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jmcmar\/article\/69\/19\/21919\/5436860\/CRAFT-A-Chemical-Reaction-Aware-Transformer-for"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,23]]},"references-count":53,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,9,23]]},"published-print":{"date-parts":[[2026,10,8]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jmedchem.6c00920","relation":{"has-part":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1021\/acs.jmedchem.6c00920.s005","asserted-by":"subject"}]},"ISSN":["0022-2623","1520-4804"],"issn-type":[{"value":"0022-2623","type":"print"},{"value":"1520-4804","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,23]]}}}