{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T17:20:14Z","timestamp":1785345614913,"version":"3.55.0"},"reference-count":81,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2021,7,19]],"date-time":"2021-07-19T00:00:00Z","timestamp":1626652800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,7,19]],"date-time":"2021-07-19T00:00:00Z","timestamp":1626652800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100008762","name":"Genome Canada","doi-asserted-by":"publisher","award":["284MBO"],"award-info":[{"award-number":["284MBO"]}],"id":[{"id":"10.13039\/100008762","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008762","name":"Genome Canada","doi-asserted-by":"publisher","award":["264PRO"],"award-info":[{"award-number":["264PRO"]}],"id":[{"id":"10.13039\/100008762","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008762","name":"Genome Canada","doi-asserted-by":"publisher","award":["284MBO"],"award-info":[{"award-number":["284MBO"]}],"id":[{"id":"10.13039\/100008762","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008762","name":"Genome Canada","doi-asserted-by":"publisher","award":["284MBO"],"award-info":[{"award-number":["284MBO"]}],"id":[{"id":"10.13039\/100008762","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008762","name":"Genome Canada","doi-asserted-by":"publisher","award":["284MBO"],"award-info":[{"award-number":["284MBO"]}],"id":[{"id":"10.13039\/100008762","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008762","name":"Genome Canada","doi-asserted-by":"publisher","award":["264PRO"],"award-info":[{"award-number":["264PRO"]}],"id":[{"id":"10.13039\/100008762","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"DOI":"10.1038\/s42256-021-00368-1","type":"journal-article","created":{"date-parts":[[2021,7,19]],"date-time":"2021-07-19T12:03:39Z","timestamp":1626696219000},"page":"759-770","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":135,"title":["Chemical language models enable navigation in sparsely populated chemical space"],"prefix":"10.1038","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2168-1621","authenticated-orcid":false,"given":"Michael A.","family":"Skinnider","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R. Greg","family":"Stacey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David S.","family":"Wishart","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leonard J.","family":"Foster","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,7,19]]},"reference":[{"key":"368_CR1","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1002\/(SICI)1098-1128(199601)16:1<3::AID-MED1>3.0.CO;2-6","volume":"16","author":"RS Bohacek","year":"1996","unstructured":"Bohacek, R. S., McMartin, C. & Guida, W. C. The art and practice of structure-based drug design: a molecular modeling perspective. Med. Res. Rev. 16, 3\u201350 (1996).","journal-title":"Med. Res. Rev."},{"key":"368_CR2","doi-asserted-by":"publisher","first-page":"7296","DOI":"10.1021\/ja401184g","volume":"135","author":"AM Virshup","year":"2013","unstructured":"Virshup, A. M., Contreras-Garc\u00eda, J., Wipf, P., Yang, W. & Beratan, D. N. Stochastic voyages into uncharted chemical space produce a representative library of all possible drug-like compounds. J. Am. Chem. Soc. 135, 7296\u20137303 (2013).","journal-title":"J. Am. Chem. Soc."},{"key":"368_CR3","doi-asserted-by":"publisher","first-page":"636","DOI":"10.1002\/cmdc.200700021","volume":"2","author":"R van Deursen","year":"2007","unstructured":"van Deursen, R. & Reymond, J.-L. Chemical space travel. ChemMedChem 2, 636\u2013640 (2007).","journal-title":"ChemMedChem"},{"key":"368_CR4","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1021\/ci050369d","volume":"46","author":"E-W Lameijer","year":"2006","unstructured":"Lameijer, E.-W., Kok, J. N., B\u00e4ck, T. & Ijzerman, A. P. The molecule evoluator. An interactive evolutionary algorithm for the design of drug-like molecules. J. Chem. Inf. Model. 46, 545\u2013552 (2006).","journal-title":"J. Chem. Inf. Model."},{"key":"368_CR5","doi-asserted-by":"publisher","first-page":"1304","DOI":"10.1021\/ci7003412","volume":"48","author":"SN Pollock","year":"2008","unstructured":"Pollock, S. N., Coutsias, E. A., Wester, M. J. & Oprea, T. I. Scaffold topologies. 1. Exhaustive enumeration up to eight rings. J. Chem. Inf. Model. 48, 1304\u20131310 (2008).","journal-title":"J. Chem. Inf. Model."},{"key":"368_CR6","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1021\/ci600423u","volume":"47","author":"T Fink","year":"2007","unstructured":"Fink, T. & Reymond, J.-L. Virtual exploration of the chemical universe up to 11 atoms of C, N, O, F: assembly of 26.4 million structures (110.9 million stereoisomers) and analysis for new ring systems, stereochemistry, physicochemical properties, compound classes and drug discovery. J. Chem. Inf. Model. 47, 342\u2013353 (2007).","journal-title":"J. Chem. Inf. Model."},{"key":"368_CR7","doi-asserted-by":"publisher","first-page":"8732","DOI":"10.1021\/ja902302h","volume":"131","author":"LC Blum","year":"2009","unstructured":"Blum, L. C. & Reymond, J.-L. 970 million druglike small molecules for virtual screening in the chemical universe database GDB-13. J. Am. Chem. Soc. 131, 8732\u20138733 (2009).","journal-title":"J. Am. Chem. Soc."},{"key":"368_CR8","doi-asserted-by":"publisher","first-page":"2864","DOI":"10.1021\/ci300415d","volume":"52","author":"L Ruddigkeit","year":"2012","unstructured":"Ruddigkeit, L., van Deursen, R., Blum, L. C. & Reymond, J.-L. Enumeration of 166 billion organic small molecules in the chemical universe database GDB-17. J. Chem. Inf. Model. 52, 2864\u20132875 (2012).","journal-title":"J. Chem. Inf. Model."},{"key":"368_CR9","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1039\/C9ME00039A","volume":"4","author":"DC Elton","year":"2019","unstructured":"Elton, D. C., Boukouvalas, Z., Fuge, M. D. & Chung, P. W. Deep learning for molecular design-a review of the state of the art. Mol. Syst. Des. Eng 4, 828\u2013849 (2019).","journal-title":"Mol. Syst. Des. Eng"},{"key":"368_CR10","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","volume":"28","author":"D Weininger","year":"1988","unstructured":"Weininger, D. SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. J. Chem. Inf. Model. 28, 31\u201336 (1988).","journal-title":"J. Chem. Inf. Model."},{"key":"368_CR11","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","volume":"4","author":"R G\u00f3mez-Bombarelli","year":"2018","unstructured":"G\u00f3mez-Bombarelli, R. et al. Automatic chemical design using a data-driven continuous representation of molecules. ACS Cent. Sci. 4, 268\u2013276 (2018).","journal-title":"ACS Cent. Sci."},{"key":"368_CR12","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1021\/acscentsci.7b00512","volume":"4","author":"MHS Segler","year":"2018","unstructured":"Segler, M. H. S., Kogej, T., Tyrchan, C. & Waller, M. P. Generating focused molecule libraries for drug discovery with recurrent neural networks. ACS Cent. Sci. 4, 120\u2013131 (2018).","journal-title":"ACS Cent. Sci."},{"key":"368_CR13","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1186\/s13321-017-0235-x","volume":"9","author":"M Olivecrona","year":"2017","unstructured":"Olivecrona, M., Blaschke, T., Engkvist, O. & Chen, H. Molecular de-novo design through deep reinforcement learning. J. Cheminform. 9, 48 (2017).","journal-title":"J. Cheminform."},{"key":"368_CR14","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s13321-019-0341-z","volume":"11","author":"J Ar\u00fas-Pous","year":"2019","unstructured":"Ar\u00fas-Pous, J. et al. Exploring the GDB-13 chemical space using deep generative models. J. Cheminform. 11, 20 (2019).","journal-title":"J. Cheminform."},{"key":"368_CR15","doi-asserted-by":"publisher","first-page":"1700153","DOI":"10.1002\/minf.201700153","volume":"37","author":"D Merk","year":"2018","unstructured":"Merk, D., Friedrich, L., Grisoni, F. & Schneider, G. De novo design of bioactive small molecules by artificial intelligence. Mol. Inform. 37, 1700153 (2018).","journal-title":"Mol. Inform."},{"key":"368_CR16","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1038\/s42256-020-0160-y","volume":"2","author":"M Moret","year":"2020","unstructured":"Moret, M., Friedrich, L., Grisoni, F., Merk, D. & Schneider, G. Generative molecular design in low data regimes. Nat. Mach. Intell. 2, 171\u2013180 (2020).","journal-title":"Nat. Mach. Intell."},{"key":"368_CR17","doi-asserted-by":"publisher","first-page":"eaap7885","DOI":"10.1126\/sciadv.aap7885","volume":"4","author":"M Popova","year":"2018","unstructured":"Popova, M., Isayev, O. & Tropsha, A. Deep reinforcement learning for de novo drug design. Sci. Adv. 4, eaap7885 (2018).","journal-title":"Sci. Adv."},{"key":"368_CR18","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1038\/s42256-020-0174-5","volume":"2","author":"P-C Kotsias","year":"2020","unstructured":"Kotsias, P.-C. et al. Direct steering of de novo molecular generation with descriptor conditional recurrent neural networks. Nat. Mach. Intell. 2, 254\u2013265 (2020).","journal-title":"Nat. Mach. Intell."},{"key":"368_CR19","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/s13321-018-0287-6","volume":"10","author":"Y Li","year":"2018","unstructured":"Li, Y., Zhang, L. & Liu, Z. Multi-objective de novo drug design with conditional graph generative model. J. Cheminform. 10, 33 (2018).","journal-title":"J. Cheminform."},{"key":"368_CR20","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-47148-x","volume":"9","author":"Z Zhou","year":"2019","unstructured":"Zhou, Z., Kearnes, S., Li, L., Zare, R. N. & Riley, P. Optimization of molecules via deep reinforcement learning. Sci. Rep. 9, 10752 (2019).","journal-title":"Sci. Rep."},{"key":"368_CR21","unstructured":"Jin, W., Barzilay, R. & Jaakkola, T. Junction tree variational autoencoder for molecular graph generation. In Proc. 35th International Conference on Machine Learning Vol. 80 (eds Dy, J. & Krause, A.) 2323\u20132332 (PMLR, 2018)."},{"key":"368_CR22","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1021\/acs.jcim.8b00839","volume":"59","author":"N Brown","year":"2019","unstructured":"Brown, N., Fiscato, M., Segler, M. H. S. & Vaucher, A. C. Guacamol: benchmarking models for de novo molecular design. J. Chem. Inf. Model. 59, 1096\u20131108 (2019).","journal-title":"J. Chem. Inf. Model."},{"key":"368_CR23","doi-asserted-by":"publisher","first-page":"565644","DOI":"10.3389\/fphar.2020.565644","volume":"11","author":"D Polykovskiy","year":"2020","unstructured":"Polykovskiy, D. et al. Molecular sets (MOSES): a benchmarking platform for molecular generation models. Front. Pharmacol. 11, 565644 (2020).","journal-title":"Front. Pharmacol."},{"key":"368_CR24","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1126\/science.aat2663","volume":"361","author":"B Sanchez-Lengeling","year":"2018","unstructured":"Sanchez-Lengeling, B. & Aspuru-Guzik, A. Inverse molecular design using machine learning: generative models for matter engineering. Science 361, 360\u2013365 (2018).","journal-title":"Science"},{"key":"368_CR25","doi-asserted-by":"publisher","first-page":"3166","DOI":"10.1021\/acs.jcim.9b00325","volume":"59","author":"N St\u00e5hl","year":"2019","unstructured":"St\u00e5hl, N., Falkman, G., Karlsson, A., Mathiason, G. & Bostr\u00f6m, J. Deep reinforcement learning for multiparameter optimization in de novo drug design. J. Chem. Inf. Model. 59, 3166\u20133176 (2019).","journal-title":"J. Chem. Inf. Model."},{"key":"368_CR26","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1186\/s13321-019-0355-6","volume":"11","author":"X Liu","year":"2019","unstructured":"Liu, X., Ye, K., van Vlijmen, H. W. T., IJzerman, A. P. & van Westen, G. J. P. An exploration strategy improves the diversity of de novo ligands using deep reinforcement learning: a case for the adenosine A2A receptor. J. Cheminform. 11, 35 (2019).","journal-title":"J. Cheminform."},{"key":"368_CR27","unstructured":"Neil, D. et al. Exploring deep recurrent models with reinforcement learning for molecule design. In Proc. 6th International Conference on Learning Representations (ICLR, 2018)."},{"key":"368_CR28","doi-asserted-by":"publisher","first-page":"5699","DOI":"10.1021\/acs.jcim.0c00343","volume":"60","author":"S Amabilino","year":"2020","unstructured":"Amabilino, S., Pog\u00e1ny, P., Pickett, S. D. & Green, D. V. S. Guidelines for recurrent neural network transfer learning-based molecular generation of focused libraries. J. Chem. Inf. Model. 60, 5699\u20135713 (2020).","journal-title":"J. Chem. Inf. Model."},{"key":"368_CR29","doi-asserted-by":"publisher","first-page":"1700111","DOI":"10.1002\/minf.201700111","volume":"37","author":"A Gupta","year":"2018","unstructured":"Gupta, A. et al. Generative recurrent networks for de novo drug design. Mol. Inform. 37, 1700111 (2018).","journal-title":"Mol. Inform."},{"key":"368_CR30","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1021\/acs.jcim.8b00902","volume":"59","author":"M Awale","year":"2019","unstructured":"Awale, M., Sirockin, F., Stiefl, N. & Reymond, J.-L. Drug analogs from fragment-based long short-term memory generative neural networks. J. Chem. Inf. Model. 59, 1347\u20131356 (2019).","journal-title":"J. Chem. Inf. Model."},{"key":"368_CR31","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1038\/s42004-018-0068-1","volume":"1","author":"D Merk","year":"2018","unstructured":"Merk, D., Grisoni, F., Friedrich, L. & Schneider, G. Tuning artificial intelligence on the de novo design of natural-product-inspired retinoid X receptor modulators. Commun. Chem. 1, 68 (2018).","journal-title":"Commun. Chem."},{"key":"368_CR32","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.ddtec.2020.09.003","volume":"32\u201333","author":"P Renz","year":"2019","unstructured":"Renz, P., Van Rompaey, D., Wegner, J. K., Hochreiter, S. & Klambauer, G. On failure modes in molecule generation and optimization. Drug Discov. Today Technol. 32\u201333, 55\u201363 (2019).","journal-title":"Drug Discov. Today Technol."},{"key":"368_CR33","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1186\/s13321-019-0393-0","volume":"11","author":"J Ar\u00fas-Pous","year":"2019","unstructured":"Ar\u00fas-Pous, J. et al. Randomized SMILES strings improve the quality of molecular generative models. J. Cheminform. 11, 71 (2019).","journal-title":"J. Cheminform."},{"key":"368_CR34","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1021\/ci049714+","volume":"45","author":"JJ Irwin","year":"2005","unstructured":"Irwin, J. J. & Shoichet, B. K. ZINC\u2014a free database of commercially available compounds for virtual screening. J. Chem. Inf. Model. 45, 177\u2013182 (2005).","journal-title":"J. Chem. Inf. Model."},{"key":"368_CR35","doi-asserted-by":"publisher","unstructured":"Benhenda, M. Can AI reproduce observed chemical diversity? Preprint at bioRxiv https:\/\/doi.org\/10.1101\/292177 (2018).","DOI":"10.1101\/292177"},{"key":"368_CR36","doi-asserted-by":"publisher","first-page":"1736","DOI":"10.1021\/acs.jcim.8b00234","volume":"58","author":"K Preuer","year":"2018","unstructured":"Preuer, K., Renz, P., Unterthiner, T., Hochreiter, S. & Klambauer, G. Fr\u00e9chet ChemNet distance: a metric for generative models for molecules in drug discovery. J. Chem. Inf. Model. 58, 1736\u20131741 (2018).","journal-title":"J. Chem. Inf. Model."},{"key":"368_CR37","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1186\/s13321-020-00425-8","volume":"12","author":"R van Deursen","year":"2020","unstructured":"van Deursen, R., Ertl, P., Tetko, I. V. & Godin, G. GEN: highly efficient SMILES explorer using autodidactic generative examination networks. J. Cheminform. 12, 22 (2020).","journal-title":"J. Cheminform."},{"key":"368_CR38","doi-asserted-by":"publisher","first-page":"D930","DOI":"10.1093\/nar\/gky1075","volume":"47","author":"D Mendez","year":"2019","unstructured":"Mendez, D. et al. ChEMBL: towards direct deposition of bioassay data. Nucleic Acids Res. 47, D930\u2013D940 (2019).","journal-title":"Nucleic Acids Res."},{"key":"368_CR39","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s13321-020-00424-9","volume":"12","author":"M Sorokina","year":"2020","unstructured":"Sorokina, M. & Steinbeck, C. Review on natural products databases: where to find data in 2020. J. Cheminform. 12, 20 (2020).","journal-title":"J. Cheminform."},{"key":"368_CR40","doi-asserted-by":"publisher","unstructured":"Sanchez-Lengeling, B., Outeiral, C., Guimaraes, G. L. & Aspuru-Guzik, A. Optimizing distributions over molecular space. An Objective-Reinforced Generative Adversarial Network for Inverse-design Chemistry (ORGANIC). Preprint at https:\/\/doi.org\/10.26434\/chemrxiv.5309668.v3 (2017).","DOI":"10.26434\/chemrxiv.5309668.v3"},{"key":"368_CR41","doi-asserted-by":"publisher","unstructured":"O\u2019Boyle, N. & Dalke, A. DeepSMILES: an adaptation of SMILES for use in machine-learning of chemical structures. Preprint at https:\/\/doi.org\/10.26434\/chemrxiv.7097960 (2018).","DOI":"10.26434\/chemrxiv.7097960"},{"key":"368_CR42","doi-asserted-by":"publisher","first-page":"045024","DOI":"10.1088\/2632-2153\/aba947","volume":"1","author":"M Krenn","year":"2020","unstructured":"Krenn, M., H\u00e4se, F., Nigam, A., Friederich, P. & Aspuru-Guzik, A. Self-referencing embedded strings (SELFIES): a 100% robust molecular string representation. Mach. Learn. Sci. Technol. 1, 045024 (2020).","journal-title":"Mach. Learn. Sci. Technol."},{"key":"368_CR43","unstructured":"Kusner, M. J., Paige, B. & Hernandez-Lobato, J. M. Grammar variational autoencoder. Preprint at https:\/\/arxiv.org\/pdf\/1703.01925.pdf (2017)."},{"key":"368_CR44","unstructured":"Dai, H., Tian, Y., Dai, B., Skiena, S. & Song, L. Syntax-directed variational autoencoder for structured data. Preprint at https:\/\/arxiv.org\/pdf\/1802.08786.pdf (2018)."},{"key":"368_CR45","unstructured":"Bjerrum, E. J. SMILES enumeration as data augmentation for neural network modeling of molecules. Preprint at https:\/\/arxiv.org\/pdf\/1703.07076.pdf (2017)."},{"key":"368_CR46","doi-asserted-by":"publisher","first-page":"131","DOI":"10.3390\/biom8040131","volume":"8","author":"EJ Bjerrum","year":"2018","unstructured":"Bjerrum, E. J. & Sattarov, B. Improving chemical autoencoder latent space and molecular de novo generation diversity with heteroencoders. Biomolecules 8, 131 (2018).","journal-title":"Biomolecules"},{"key":"368_CR47","doi-asserted-by":"publisher","first-page":"1692","DOI":"10.1039\/C8SC04175J","volume":"10","author":"R Winter","year":"2019","unstructured":"Winter, R., Montanari, F., No\u00e9, F. & Clevert, D.-A. Learning continuous and data-driven molecular descriptors by translating equivalent chemical representations. Chem. Sci. 10, 1692\u20131701 (2019).","journal-title":"Chem. Sci."},{"key":"368_CR48","doi-asserted-by":"publisher","first-page":"12031","DOI":"10.1073\/pnas.1406418111","volume":"111","author":"Q Zhang","year":"2014","unstructured":"Zhang, Q. et al. Structural investigation of ribosomally synthesized natural products by hypothetical structure enumeration and evaluation using tandem MS. Proc. Natl Acad. Sci. USA 111, 12031\u201312036 (2014).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"368_CR49","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms9421","volume":"6","author":"CW Johnston","year":"2015","unstructured":"Johnston, C. W. et al. An automated genomes-to-natural products platform (GNP) for the discovery of modular natural products. Nat. Commun. 6, 8421 (2015).","journal-title":"Nat. Commun."},{"key":"368_CR50","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1186\/s13321-019-0328-9","volume":"11","author":"S Zheng","year":"2019","unstructured":"Zheng, S. et al. QBMG: quasi-biogenic molecule generator with deep recurrent neural network. J. Cheminform. 11, 5 (2019).","journal-title":"J. Cheminform."},{"key":"368_CR51","doi-asserted-by":"publisher","first-page":"12549","DOI":"10.1073\/pnas.1516878112","volume":"112","author":"RR da Silva","year":"2015","unstructured":"da Silva, R. R., Dorrestein, P. C. & Quinn, R. A. Illuminating the dark matter in metabolomics. Proc. Natl Acad. Sci. USA 112, 12549\u201312550 (2015).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"368_CR52","doi-asserted-by":"publisher","first-page":"1496","DOI":"10.1021\/acsmedchemlett.0c00088","volume":"11","author":"Q Vanhaelen","year":"2020","unstructured":"Vanhaelen, Q., Lin, Y.-C. & Zhavoronkov, A. The advent of generative chemistry. ACS Med. Chem. Lett. 11, 1496\u20131505 (2020).","journal-title":"ACS Med. Chem. Lett."},{"key":"368_CR53","doi-asserted-by":"publisher","first-page":"23414","DOI":"10.1002\/anie.201909989","volume":"59","author":"CW Coley","year":"2020","unstructured":"Coley, C. W., Eyke, N. S. & Jensen, K. F. Autonomous discovery in the chemical sciences part II: outlook. Angew. Chem. Int. Ed. 59, 23414\u201323436 (2020).","journal-title":"Angew. Chem. Int. Ed."},{"key":"368_CR54","doi-asserted-by":"publisher","first-page":"1572","DOI":"10.1021\/acscentsci.9b00576","volume":"5","author":"P Schwaller","year":"2019","unstructured":"Schwaller, P. et al. Molecular transformer: a model for uncertainty-calibrated chemical reaction prediction. ACS Cent. Sci. 5, 1572\u20131583 (2019).","journal-title":"ACS Cent. Sci."},{"key":"368_CR55","doi-asserted-by":"publisher","first-page":"3098","DOI":"10.1021\/acs.molpharmaceut.7b00346","volume":"14","author":"A Kadurin","year":"2017","unstructured":"Kadurin, A., Nikolenko, S., Khrabrov, K., Aliper, A. & Zhavoronkov, A. druGAN: an advanced generative adversarial autoencoder model for de novo generation of new molecules with desired molecular properties in silico. Mol. Pharm. 14, 3098\u20133104 (2017).","journal-title":"Mol. Pharm."},{"key":"368_CR56","first-page":"1","volume":"21","author":"B Samanta","year":"2020","unstructured":"Samanta, B. et al. NEVAE: a deep generative model for molecular graphs. J. Mach. Learn. Res. 21, 1\u201333 (2020).","journal-title":"J. Mach. Learn. Res."},{"key":"368_CR57","doi-asserted-by":"publisher","unstructured":"Mercado, R. et al. Practical notes on building molecular graph generative models. Appl. AI Lett. https:\/\/doi.org\/10.1002\/ail2.18 (2020).","DOI":"10.1002\/ail2.18"},{"key":"368_CR58","unstructured":"De Cao, N. & Kipf, T. MolGAN: an implicit generative model for small molecular graphs. Preprint at https:\/\/arxiv.org\/pdf\/1805.11973.pdf (2018)."},{"key":"368_CR59","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1021\/acs.jcim.7b00616","volume":"58","author":"S Jaeger","year":"2018","unstructured":"Jaeger, S., Fulle, S. & Turk, S. Mol2vec: unsupervised machine learning approach with chemical intuition. J. Chem. Inf. Model. 58, 27\u201335 (2018).","journal-title":"J. Chem. Inf. Model."},{"key":"368_CR60","doi-asserted-by":"publisher","unstructured":"O\u2019Boyle, N. & Dalke, A. DeepSMILES: an adaptation of SMILES for use in machine-learning of chemical structures. Preprint at https:\/\/doi.org\/10.26434\/chemrxiv.7097960.v1 (2018).","DOI":"10.26434\/chemrxiv.7097960.v1"},{"key":"368_CR61","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","volume":"50","author":"D Rogers","year":"2010","unstructured":"Rogers, D. & Hahn, M. Extended-connectivity fingerprints. J. Chem. Inf. Model. 50, 742\u2013754 (2010).","journal-title":"J. Chem. Inf. Model."},{"key":"368_CR62","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1186\/s13321-016-0148-0","volume":"8","author":"NM O\u2019Boyle","year":"2016","unstructured":"O\u2019Boyle, N. M. & Sayle, R. A. Comparing structural fingerprints using a literature-based similarity benchmark. J. Cheminform. 8, 36 (2016).","journal-title":"J. Cheminform."},{"key":"368_CR63","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1186\/s13321-017-0234-y","volume":"9","author":"MA Skinnider","year":"2017","unstructured":"Skinnider, M. A., Dejong, C. A., Franczak, B. C., McNicholas, P. D. & Magarvey, N. A. Comparative analysis of chemical similarity methods for modular natural products with a hypothetical structure enumeration algorithm. J. Cheminform. 9, 46 (2017).","journal-title":"J. Cheminform."},{"key":"368_CR64","unstructured":"Smith, S. L., Kindermans, P.-J. & Le, Q. V. Don\u2019t decay the learning rate, increase the batch size. Preprint at https:\/\/arxiv.org\/pdf\/1711.00489.pdf (2017)."},{"key":"368_CR65","doi-asserted-by":"publisher","first-page":"3599","DOI":"10.1021\/ja00402a071","volume":"103","author":"SH Bertz","year":"1981","unstructured":"Bertz, S. H. The first general index of molecular complexity. J. Am. Chem. Soc. 103, 3599\u20133601 (1981).","journal-title":"J. Am. Chem. Soc."},{"key":"368_CR66","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1021\/ci990307l","volume":"39","author":"SA Wildman","year":"1999","unstructured":"Wildman, S. A. & Crippen, G. M. Prediction of physicochemical parameters by atomic contributions. J. Chem. Inf. Comput. Sci. 39, 868\u2013873 (1999).","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"368_CR67","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.1021\/jm9602928","volume":"39","author":"GW Bemis","year":"1996","unstructured":"Bemis, G. W. & Murcko, M. A. The properties of known drugs. 1. Molecular frameworks. J. Med. Chem. 39, 2887\u20132893 (1996).","journal-title":"J. Med. Chem."},{"key":"368_CR68","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1021\/ci700286x","volume":"48","author":"P Ertl","year":"2008","unstructured":"Ertl, P., Roggo, S. & Schuffenhauer, A. Natural product-likeness score and its application for prioritization of compound libraries. J. Chem. Inf. Model. 48, 68\u201374 (2008).","journal-title":"J. Chem. Inf. Model."},{"key":"368_CR69","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/nchem.1243","volume":"4","author":"GR Bickerton","year":"2012","unstructured":"Bickerton, G. R., Paolini, G. V., Besnard, J., Muresan, S. & Hopkins, A. L. Quantifying the chemical beauty of drugs. Nat. Chem. 4, 90\u201398 (2012).","journal-title":"Nat. Chem."},{"key":"368_CR70","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/1758-2946-1-8","volume":"1","author":"P Ertl","year":"2009","unstructured":"Ertl, P. & Schuffenhauer, A. Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions. J. Cheminform. 1, 8 (2009).","journal-title":"J. Cheminform."},{"key":"368_CR71","doi-asserted-by":"publisher","first-page":"3714","DOI":"10.1021\/jm000942e","volume":"43","author":"P Ertl","year":"2000","unstructured":"Ertl, P., Rohde, B. & Selzer, P. Fast calculation of molecular polar surface area as a sum of fragment-based contributions and its application to the prediction of drug transport properties. J. Med. Chem. 43, 3714\u20133717 (2000).","journal-title":"J. Med. Chem."},{"key":"368_CR72","doi-asserted-by":"publisher","first-page":"D495","DOI":"10.1093\/nar\/gkv1060","volume":"44","author":"T Sajed","year":"2016","unstructured":"Sajed, T. et al. ECMDB 2.0: a richer resource for understanding the biochemistry of E. coli. Nucleic Acids Res. 44, D495\u2013D501 (2016).","journal-title":"Nucleic Acids Res."},{"key":"368_CR73","doi-asserted-by":"publisher","first-page":"D575","DOI":"10.1093\/nar\/gkx1061","volume":"46","author":"W Huang","year":"2018","unstructured":"Huang, W. et al. PAMDB: a comprehensive Pseudomonas aeruginosa metabolome database. Nucleic Acids Res. 46, D575\u2013D580 (2018).","journal-title":"Nucleic Acids Res."},{"key":"368_CR74","doi-asserted-by":"publisher","first-page":"D600","DOI":"10.1093\/nar\/gkaa868","volume":"49","author":"AFA Moumbock","year":"2020","unstructured":"Moumbock, A. F. A. et al. StreptomeDB 3.0: an updated compendium of streptomycetes natural products. Nucleic Acids Res 49, D600\u2013D604 (2020).","journal-title":"Nucleic Acids Res"},{"key":"368_CR75","doi-asserted-by":"publisher","first-page":"D1217","DOI":"10.1093\/nar\/gkx1026","volume":"46","author":"X Zeng","year":"2018","unstructured":"Zeng, X. et al. NPASS: natural product activity and species source database for natural product research, discovery and tool development. Nucleic Acids Res. 46, D1217\u2013D1222 (2018).","journal-title":"Nucleic Acids Res."},{"key":"368_CR76","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1093\/bib\/bbx085","volume":"20","author":"PD Karp","year":"2019","unstructured":"Karp, P. D. et al. The BioCyc collection of microbial genomes and metabolic pathways. Brief. Bioinform. 20, 1085\u20131093 (2019).","journal-title":"Brief. Bioinform."},{"key":"368_CR77","doi-asserted-by":"publisher","first-page":"bap024","DOI":"10.1093\/database\/bap024","volume":"2010","author":"V Neveu","year":"2010","unstructured":"Neveu, V. et al. Phenol-Explorer: an online comprehensive database on polyphenol contents in foods. Database (Oxford) 2010, bap024 (2010).","journal-title":"Database"},{"key":"368_CR78","doi-asserted-by":"publisher","first-page":"D440","DOI":"10.1093\/nar\/gkw1058","volume":"45","author":"M Ramirez-Gaona","year":"2017","unstructured":"Ramirez-Gaona, M. et al. YMDB 2.0: a significantly expanded version of the yeast metabolome database. Nucleic Acids Res. 45, D440\u2013D445 (2017).","journal-title":"Nucleic Acids Res."},{"key":"368_CR79","doi-asserted-by":"crossref","unstructured":"McInnes, L., Healy, J. & Melville, J. UMAP: Uniform Manifold Approximation and Projection for dimension reduction. Preprint at https:\/\/arxiv.org\/pdf\/1802.03426.pdf (2018).","DOI":"10.21105\/joss.00861"},{"key":"368_CR80","doi-asserted-by":"publisher","unstructured":"Molecules used to train generative models (Zenodo, 2021); https:\/\/doi.org\/10.5281\/zenodo.4641960","DOI":"10.5281\/zenodo.4641960"},{"key":"368_CR81","doi-asserted-by":"publisher","unstructured":"Python source code used to train and evaluate generative models of molecules (Zenodo, 2021); https:\/\/doi.org\/10.5281\/zenodo.4642099","DOI":"10.5281\/zenodo.4642099"}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-021-00368-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-021-00368-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-021-00368-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T15:36:47Z","timestamp":1670081807000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-021-00368-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,19]]},"references-count":81,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,9]]}},"alternative-id":["368"],"URL":"https:\/\/doi.org\/10.1038\/s42256-021-00368-1","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv.13638347.v1","asserted-by":"object"}]},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,19]]},"assertion":[{"value":"19 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 July 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}