{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:31:51Z","timestamp":1789432311229,"version":"build-2803163510"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Bioorganic & Medicinal Chemistry"],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1016\/j.bmc.2021.116308","type":"journal-article","created":{"date-parts":[[2021,7,9]],"date-time":"2021-07-09T12:06:43Z","timestamp":1625832403000},"page":"116308","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":29,"special_numbering":"C","title":["De novo design with deep generative models based on 3D similarity scoring"],"prefix":"10.1016","volume":"44","author":[{"given":"Kostas","family":"Papadopoulos","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kathryn A.","family":"Giblin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jon Paul","family":"Janet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atanas","family":"Patronov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ola","family":"Engkvist","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"5","key":"10.1016\/j.bmc.2021.116308_b0005","doi-asserted-by":"crossref","first-page":"593","DOI":"10.4155\/fmc.12.19","article-title":"Virtual compound screening in drug discovery","volume":"4","author":"Stumpfe","year":"2012","journal-title":"Future Med Chem"},{"issue":"7805","key":"10.1016\/j.bmc.2021.116308_b0010","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1038\/s41586-020-2117-z","article-title":"An open-source drug discovery platform enables ultra-large virtual screens","volume":"580","author":"Gorgulla","year":"2020","journal-title":"Nature"},{"issue":"8","key":"10.1016\/j.bmc.2021.116308_b0015","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1007\/s10822-013-9672-4","article-title":"Estimation of the size of drug-like chemical space based on GDB-17 data","volume":"27","author":"Polishchuk","year":"2013","journal-title":"J Comput Aided Mol Des"},{"issue":"7553","key":"10.1016\/j.bmc.2021.116308_b0020","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Lecun","year":"2015","journal-title":"Nature"},{"issue":"4","key":"10.1016\/j.bmc.2021.116308_b0025","doi-asserted-by":"crossref","first-page":"828","DOI":"10.1039\/C9ME00039A","article-title":"Deep learning for molecular design - A review of the state of the art","volume":"4","author":"Elton","year":"2019","journal-title":"Mol Syst Des Eng"},{"issue":"6","key":"10.1016\/j.bmc.2021.116308_b0030","doi-asserted-by":"crossref","first-page":"1241","DOI":"10.1016\/j.drudis.2018.01.039","article-title":"The rise of deep learning in drug discovery","volume":"23","author":"Chen","year":"2018","journal-title":"Drug Discov Today"},{"issue":"9","key":"10.1016\/j.bmc.2021.116308_b0035","doi-asserted-by":"crossref","first-page":"1038","DOI":"10.1038\/s41587-019-0224-x","article-title":"Deep learning enables rapid identification of potent DDR1 kinase inhibitors","volume":"37","author":"Zhavoronkov","year":"2019","journal-title":"Nat Biotechnol"},{"issue":"3","key":"10.1016\/j.bmc.2021.116308_b0040","doi-asserted-by":"crossref","first-page":"e427","DOI":"10.1016\/j.ddtec.2013.02.001","article-title":"Multi-objective optimization methods in drug design","volume":"10","author":"Nicolaou","year":"2013","journal-title":"Drug Discov Today: Technol"},{"issue":"7","key":"10.1016\/j.bmc.2021.116308_b0045","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1016\/j.drudis.2013.12.004","article-title":"Data-driven medicinal chemistry in the era of big data","volume":"19","author":"Lusher","year":"2014","journal-title":"Drug Discov Today"},{"key":"10.1016\/j.bmc.2021.116308_b0050","series-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"issue":"1","key":"10.1016\/j.bmc.2021.116308_b0055","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-020-78537-2","article-title":"Autonomous molecule generation using reinforcement learning and docking to develop potential novel inhibitors","volume":"10","author":"Jeon","year":"2020","journal-title":"Sci Rep"},{"issue":"1","key":"10.1016\/j.bmc.2021.116308_b0060","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1186\/s13321-017-0235-x","article-title":"Molecular de-novo design through deep reinforcement learning","volume":"9","author":"Olivecrona","year":"2017","journal-title":"J Cheminform"},{"issue":"7","key":"10.1016\/j.bmc.2021.116308_b0065","doi-asserted-by":"crossref","first-page":"eaap7885","DOI":"10.1126\/sciadv.aap7885","article-title":"Deep reinforcement learning for de novo drug design","volume":"4","author":"Popova","year":"2018","journal-title":"Sci Adv"},{"issue":"1","key":"10.1016\/j.bmc.2021.116308_b0070","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13321-019-0355-6","article-title":"An exploration strategy improves the diversity of de novo ligands using deep reinforcement learning: A case for the adenosine A2A receptor","volume":"11","author":"Liu","year":"2019","journal-title":"J Cheminform"},{"issue":"7083","key":"10.1016\/j.bmc.2021.116308_b0075","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1038\/nature04710","article-title":"hERG potassium channels and cardiac arrhythmia","volume":"440","author":"Sanguinetti","year":"2006","journal-title":"Nature"},{"issue":"2","key":"10.1016\/j.bmc.2021.116308_b0080","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1021\/acs.accounts.0c00699","article-title":"Applications of Deep Learning in Molecule Generation and Molecular Property Prediction","volume":"54","author":"Walters","year":"2021","journal-title":"Acc Chem Res"},{"issue":"6","key":"10.1016\/j.bmc.2021.116308_b0085","doi-asserted-by":"crossref","first-page":"1098","DOI":"10.1021\/acs.jcim.5b00110","article-title":"The Relative Importance of Domain Applicability Metrics for Estimating Prediction Errors in QSAR Varies with Training Set Diversity","volume":"55","author":"Sheridan","year":"2015","journal-title":"J Chem Inf Model"},{"key":"10.1016\/j.bmc.2021.116308_b0090","unstructured":"D\u2019Amour A, et al., Underspecification Presents Challenges for Credibility in Modern Machine Learning. arXiv Prepr. arXiv2011.03395; 2020."},{"key":"10.1016\/j.bmc.2021.116308_b0095","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.ddtec.2020.09.003","article-title":"On failure modes in molecule generation and optimization","volume":"32-33","author":"Renz","year":"2019","journal-title":"Drug Discov Today Technol"},{"issue":"11","key":"10.1016\/j.bmc.2021.116308_b0100","doi-asserted-by":"crossref","first-page":"14360","DOI":"10.1021\/acsomega.9b02221","article-title":"Evolving Concept of Activity Cliffs","volume":"4","author":"Stumpfe","year":"2019","journal-title":"ACS Omega"},{"issue":"3","key":"10.1016\/j.bmc.2021.116308_b0105","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1021\/ci500731a","article-title":"Classification of current scoring functions","volume":"55","author":"Liu","year":"2015","journal-title":"J Chem Inf Model"},{"issue":"1","key":"10.1016\/j.bmc.2021.116308_b0110","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1021\/jm0603365","article-title":"Comparison of shape-matching and docking as virtual screening tools","volume":"50","author":"Hawkins","year":"2007","journal-title":"J Med Chem"},{"issue":"1","key":"10.1016\/j.bmc.2021.116308_b0115","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13321-020-00473-0","article-title":"Memory-assisted reinforcement learning for diverse molecular de novo design","volume":"12","author":"Blaschke","year":"2020","journal-title":"J Cheminform"},{"issue":"5","key":"10.1016\/j.bmc.2021.116308_b0120","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1038\/s42256-020-0174-5","article-title":"Direct steering of de novo molecular generation with descriptor conditional recurrent neural networks","volume":"2","author":"Kotsias","year":"2020","journal-title":"Nat Mach Intell"},{"issue":"1","key":"10.1016\/j.bmc.2021.116308_b0125","doi-asserted-by":"crossref","DOI":"10.1186\/s13321-020-00441-8","article-title":"SMILES-based deep generative scaffold decorator for de-novo drug design","volume":"12","author":"Ar\u00fas-Pous","year":"2020","journal-title":"J Cheminform"},{"issue":"51","key":"10.1016\/j.bmc.2021.116308_b0130","doi-asserted-by":"crossref","first-page":"32984","DOI":"10.1021\/acsomega.0c04153","article-title":"Molecular Design in Synthetically Accessible Chemical Space via Deep Reinforcement Learning","volume":"5","author":"Horwood","year":"2020","journal-title":"ACS Omega"},{"issue":"1","key":"10.1016\/j.bmc.2021.116308_b0135","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1021\/acs.jcim.9b00727","article-title":"DeepScaffold: A Comprehensive Tool for Scaffold-Based de Novo Drug Discovery Using Deep Learning","volume":"60","author":"Li","year":"2020","journal-title":"J Chem Inf Model"},{"key":"10.1016\/j.bmc.2021.116308_b0140","unstructured":"Jin W, Yang K, Barzilay R, Jaakkola T. Learning Multimodal Graph-to-Graph Translation for Molecular Optimization. arXiv Prepr. arXiv1812.01070; Dec. 2018."},{"issue":"12","key":"10.1016\/j.bmc.2021.116308_b0145","doi-asserted-by":"crossref","first-page":"5918","DOI":"10.1021\/acs.jcim.0c00915","article-title":"REINVENT 2.0: An AI Tool for De Novo Drug Design","volume":"60","author":"Blaschke","year":"2020","journal-title":"J Chem Inf Model"},{"key":"10.1016\/j.bmc.2021.116308_b0150","unstructured":"\u201cMolecularAI\/Reinvent.\u201d Online. Available: https:\/\/github.com\/MolecularAI\/Reinvent. Accessed: 02-Mar-2021."},{"issue":"5","key":"10.1016\/j.bmc.2021.116308_b0155","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.1021\/ci300030u","article-title":"Performance evaluation of 2D fingerprint and 3D shape similarity methods in virtual screening","volume":"52","author":"Hu","year":"2012","journal-title":"J Chem Inf Model"},{"issue":"1","key":"10.1016\/j.bmc.2021.116308_b0160","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1002\/cmdc.200900314","article-title":"Comparison of structure- and ligand-based virtual screening protocols considering hit list complementarity and enrichment factors","volume":"5","author":"Kr\u00fcger","year":"2010","journal-title":"ChemMedChem"},{"issue":"8","key":"10.1016\/j.bmc.2021.116308_b0165","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1007\/s10822-019-00218-8","article-title":"Evaluation of different virtual screening strategies on the basis of compound sets with characteristic core distributions and dissimilarity relationships","volume":"33","author":"Miyao","year":"2019","journal-title":"J Comput Aided Mol Des"},{"issue":"16","key":"10.1016\/j.bmc.2021.116308_b0170","doi-asserted-by":"crossref","first-page":"8809","DOI":"10.1021\/acs.jmedchem.9b02044","article-title":"Automated de Novo Design in Medicinal Chemistry: Which Types of Chemistry Does a Generative Neural Network Learn?","volume":"63","author":"Grebner","year":"2020","journal-title":"J Med Chem"},{"issue":"3","key":"10.1016\/j.bmc.2021.116308_b0175","doi-asserted-by":"crossref","first-page":"1205","DOI":"10.1021\/acs.jcim.8b00706","article-title":"Shape-Based Generative Modeling for de Novo Drug Design","volume":"59","author":"Skalic","year":"2019","journal-title":"J Chem Inf Model"},{"issue":"D1","key":"10.1016\/j.bmc.2021.116308_b0180","doi-asserted-by":"crossref","first-page":"D945","DOI":"10.1093\/nar\/gkw1074","article-title":"The ChEMBL database in 2017","volume":"45","author":"Gaulton","year":"2017","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"10.1016\/j.bmc.2021.116308_b0185","doi-asserted-by":"crossref","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 Cheminform"},{"key":"10.1016\/j.bmc.2021.116308_b0190","unstructured":"Landrum G, et al. rdkit\/rdkit: 2019_09_1 (Q3 2019) Release; Oct. 2019."},{"key":"10.1016\/j.bmc.2021.116308_b0195","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"issue":"1","key":"10.1016\/j.bmc.2021.116308_b0200","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-020-14884-y","article-title":"Haloperidol bound D2 dopamine receptor structure inspired the discovery of subtype selective ligands","volume":"11","author":"Fan","year":"2020","journal-title":"Nat Commun"},{"key":"10.1016\/j.bmc.2021.116308_b0205","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.ejmech.2016.07.072","article-title":"Evaluation of selected 3D virtual screening tools for the prospective identification of peroxisome proliferator-activated receptor (PPAR) \u03b3 partial agonists","volume":"124","author":"Kaserer","year":"2016","journal-title":"Eur J Med Chem"},{"key":"10.1016\/j.bmc.2021.116308_b0210","unstructured":"\u201cOEToolkits 2019.Oct \u2014 Toolkits -- Python.\u201d Online. Available: https:\/\/docs.eyesopen.com\/toolkits\/python\/releasenotes\/releasenotes2019_Oct.html Accessed: 26-Feb-2021."},{"key":"10.1016\/j.bmc.2021.116308_b0215","unstructured":"\u201cDaylight Theory: SMARTS - A Language for Describing Molecular Patterns.\u201d Online. Available: https:\/\/www.daylight.com\/dayhtml\/doc\/theory\/theory.smarts.html Accessed: 15-Mar-2021."},{"issue":"3","key":"10.1016\/j.bmc.2021.116308_b0220","doi-asserted-by":"crossref","first-page":"1096","DOI":"10.1021\/acs.jcim.8b00839","article-title":"GuacaMol: Benchmarking Models for de Novo Molecular Design","volume":"59","author":"Brown","year":"2019","journal-title":"J Chem Inf Model"},{"key":"10.1016\/j.bmc.2021.116308_b0225","doi-asserted-by":"crossref","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"},{"issue":"12","key":"10.1016\/j.bmc.2021.116308_b0230","doi-asserted-by":"crossref","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":"10.1016\/j.bmc.2021.116308_b0235","doi-asserted-by":"crossref","first-page":"3339","DOI":"10.1039\/D0SC05401A","article-title":"Retrosynthetic accessibility score (RAscore)-rapid machine learned synthesizability classification from AI driven retrosynthetic planning","volume":"12","author":"Thakkar","year":"2021","journal-title":"Chem Sci"},{"issue":"1","key":"10.1016\/j.bmc.2021.116308_b0240","doi-asserted-by":"crossref","DOI":"10.1186\/s13321-019-0393-0","article-title":"Randomized SMILES strings improve the quality of molecular generative models","volume":"11","author":"Ar\u00fas-Pous","year":"2019","journal-title":"J Cheminform"},{"issue":"15","key":"10.1016\/j.bmc.2021.116308_b0245","doi-asserted-by":"crossref","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"},{"issue":"5","key":"10.1016\/j.bmc.2021.116308_b0250","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1002\/minf.201000019","article-title":"Bioisosteric Replacement and Scaffold Hopping in Lead Generation and Optimization","volume":"29","author":"Langdon","year":"2010","journal-title":"Mol Inform"},{"issue":"3","key":"10.1016\/j.bmc.2021.116308_b0255","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.ddtec.2004.10.009","article-title":"Scaffold hopping","volume":"1","author":"B\u00f6hm","year":"2004","journal-title":"Drug Discov Today: Technol"},{"key":"10.1016\/j.bmc.2021.116308_b0260","series-title":"Lead Generation","first-page":"183","article-title":"Competitive Intelligence\u2013based Lead Generation and Fast Follower Approaches","author":"Jiang","year":"2016"},{"issue":"21","key":"10.1016\/j.bmc.2021.116308_b0265","doi-asserted-by":"crossref","first-page":"9442","DOI":"10.1021\/acs.jmedchem.8b00675","article-title":"Where Do Recent Small Molecule Clinical Development Candidates Come From?","volume":"61","author":"Brown","year":"2018","journal-title":"J Med Chem"}],"updated-by":[{"DOI":"10.1016\/j.bmc.2021.116374","type":"erratum","label":"Erratum","source":"publisher","updated":{"date-parts":[[2021,9,15]],"date-time":"2021-09-15T00:00:00Z","timestamp":1631664000000}}],"container-title":["Bioorganic & Medicinal Chemistry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0968089621003163?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0968089621003163?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,3,24]],"date-time":"2023-03-24T18:35:30Z","timestamp":1679682930000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0968089621003163"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":53,"alternative-id":["S0968089621003163"],"URL":"https:\/\/doi.org\/10.1016\/j.bmc.2021.116308","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv.14572050.v1","asserted-by":"object"}]},"ISSN":["0968-0896"],"issn-type":[{"value":"0968-0896","type":"print"}],"subject":[],"published":{"date-parts":[[2021,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"De novo design with deep generative models based on 3D similarity scoring","name":"articletitle","label":"Article Title"},{"value":"Bioorganic & Medicinal Chemistry","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.bmc.2021.116308","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2021 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"116308"}}