{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T17:56:08Z","timestamp":1787680568339,"version":"build-2784847793"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T00:00:00Z","timestamp":1680480000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T00:00:00Z","timestamp":1680480000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000266","name":"RCUK | Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/S024093\/1"],"award-info":[{"award-number":["EP\/S024093\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"RCUK | Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/S024093\/1"],"award-info":[{"award-number":["EP\/S024093\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"RCUK | Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/S024093\/1"],"award-info":[{"award-number":["EP\/S024093\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"DOI":"10.1038\/s42256-023-00636-2","type":"journal-article","created":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T12:04:55Z","timestamp":1680523495000},"page":"386-394","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["Testing the limits of SMILES-based de novo molecular generation with curriculum and deep reinforcement learning"],"prefix":"10.1038","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9440-584X","authenticated-orcid":false,"given":"Maranga","family":"Mokaya","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fergus","family":"Imrie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5325-4261","authenticated-orcid":false,"given":"Willem P.","family":"van Hoorn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aleksandra","family":"Kalisz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anthony R.","family":"Bradley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1388-2252","authenticated-orcid":false,"given":"Charlotte M.","family":"Deane","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,4,3]]},"reference":[{"key":"636_CR1","doi-asserted-by":"publisher","first-page":"4077","DOI":"10.1021\/acs.jmedchem.5b01849","volume":"59","author":"P Schneider","year":"2016","unstructured":"Schneider, P. & Schneider, G. De novo design at the edge of chaos. J. Med. Chem. 59, 4077\u20134086 (2016).","journal-title":"J. Med. Chem."},{"key":"636_CR2","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1038\/nrd4609","volume":"14","author":"MJ Waring","year":"2015","unstructured":"Waring, M. J. et al. An analysis of the attrition of drug candidates from four major pharmaceutical companies. Nat. Rev. Drug Discov. 14, 475\u2013486 (2015).","journal-title":"Nat. Rev. Drug Discov."},{"key":"636_CR3","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1038\/nbt.2786","volume":"32","author":"M Hay","year":"2014","unstructured":"Hay, M., Thomas, D. W., Craighead, J. L., Economides, C. & Rosenthal, J. Clinical development success rates for investigational drugs. Nat. Biotechnol. 32, 40\u201351 (2014).","journal-title":"Nat. Biotechnol."},{"key":"636_CR4","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1038\/nchembio.581","volume":"7","author":"ME Bunnage","year":"2011","unstructured":"Bunnage, M. E. Getting pharmaceutical R&D back on target. Nat. Chem. Biol. 7, 335\u2013339 (2011).","journal-title":"Nat. Chem. Biol."},{"key":"636_CR5","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.1111\/j.1476-5381.2010.01127.x","volume":"162","author":"J Hughes","year":"2011","unstructured":"Hughes, J., Rees, S., Kalindjian, S. & Philpott, K. Principles of early drug discovery: principles of early drug discovery. Br. J. Pharmacol. 162, 1239\u20131249 (2011).","journal-title":"Br. J. Pharmacol."},{"key":"636_CR6","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":"636_CR7","doi-asserted-by":"publisher","first-page":"D1202","DOI":"10.1093\/nar\/gkv951","volume":"44","author":"S Kim","year":"2016","unstructured":"Kim, S. et al. PubChem substance and compound databases. Nucleic Acids Res. 44, D1202\u2013D1213 (2016).","journal-title":"Nucleic Acids Res."},{"key":"636_CR8","doi-asserted-by":"publisher","first-page":"368","DOI":"10.3389\/fgene.2019.00368","volume":"10","author":"JD Romano","year":"2019","unstructured":"Romano, J. D. & Tatonetti, N. P. Informatics and computational methods in natural product drug discovery: a review and perspectives. Front. Genet. 10, 368 (2019).","journal-title":"Front. Genet."},{"key":"636_CR9","doi-asserted-by":"publisher","first-page":"1375","DOI":"10.3390\/molecules25061375","volume":"25","author":"X Lin","year":"2020","unstructured":"Lin, X., Li, X. & Lin, X. A review on applications of computational methods in drug screening and design. Molecules 25, 1375 (2020).","journal-title":"Molecules"},{"key":"636_CR10","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1038\/nature11691","volume":"492","author":"J Besnard","year":"2012","unstructured":"Besnard, J. et al. Automated design of ligands to polypharmacological profiles. Nature 492, 215\u2013220 (2012).","journal-title":"Nature"},{"key":"636_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":"636_CR12","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1002\/wcms.23","volume":"1","author":"D Stumpfe","year":"2011","unstructured":"Stumpfe, D. & Bajorath, J. Similarity searching. WIREs Comput. Mol. Sci. 1, 260\u2013282 (2011).","journal-title":"WIREs Comput. Mol. Sci."},{"key":"636_CR13","doi-asserted-by":"publisher","first-page":"2412","DOI":"10.1021\/jm9603781","volume":"40","author":"D Horvath","year":"1997","unstructured":"Horvath, D. A virtual screening approach applied to the search for trypanothione reductase inhibitors. J. Med. Chem. 40, 2412\u20132423 (1997).","journal-title":"J. Med. Chem."},{"key":"636_CR14","doi-asserted-by":"publisher","first-page":"504","DOI":"10.22270\/jddt.v8i5.1894","volume":"8","author":"S Surabhi","year":"2018","unstructured":"Surabhi, S. & Singh, B. K. Computer-aided drug design: an overview. J. Drug Deliv. Ther. 8, 504\u2013509 (2018).","journal-title":"J. Drug Deliv. Ther."},{"key":"636_CR15","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":"636_CR16","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1021\/ci6003652","volume":"47","author":"H Mauser","year":"2007","unstructured":"Mauser, H. & Stahl, M. Chemical fragment spaces for de novo design. J. Chem. Inf. Model. 47, 318\u2013324 (2007).","journal-title":"J. Chem. Inf. Model."},{"key":"636_CR17","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1111\/j.1747-0285.2008.00672.x","volume":"72","author":"M Hartenfeller","year":"2008","unstructured":"Hartenfeller, M., Proschak, E., Sch\u00fcller, A. & Schneider, G. Concept of combinatorial de novo design of drug-like molecules by particle swarm optimization. Chem. Biol. Drug Des. 72, 16\u201326 (2008).","journal-title":"Chem. Biol. Drug Des."},{"key":"636_CR18","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1021\/ci700424b","volume":"48","author":"F Dey","year":"2008","unstructured":"Dey, F. & Caflisch, A. Fragment-based de novo ligand design by multiobjective evolutionary optimization. J. Chem. Inf. Model. 48, 679\u2013690 (2008).","journal-title":"J. Chem. Inf. Model."},{"key":"636_CR19","doi-asserted-by":"crossref","unstructured":"Elton, D. C., Boukouvalas, Z., Fuge, M. D. & Chung, P. W. Deep learning for molecular design\u2014a review of the state of the art. Mol. Syst. Des. Eng. 4, 828\u2013849 (2019).","DOI":"10.1039\/C9ME00039A"},{"key":"636_CR20","unstructured":"Baldi, P. Autoencoders, unsupervised learning, and deep architectures. In Proc. ICML Workshop on Unsupervised and Transfer Learning (eds. Guyon, I. et al.) Vol. 27, 37\u201349 (PMLR, 2012)."},{"key":"636_CR21","doi-asserted-by":"publisher","unstructured":"Jin, W., Barzilay, R. & Jaakkola, T. Junction tree variational autoencoder for molecular graph generation. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.1802.04364 (2018).","DOI":"10.48550\/arXiv.1802.04364"},{"key":"636_CR22","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. Comput. Sci. 28, 31\u201336 (1988).","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"636_CR23","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-018-0286-7","volume":"10","author":"J Lim","year":"2018","unstructured":"Lim, J., Ryu, S., Kim, J. W. & Kim, W. Y. Molecular generative model based on conditional variational autoencoder for de novo molecular design. J. Cheminform. 10, 31 (2018).","journal-title":"J. Cheminform."},{"key":"636_CR24","doi-asserted-by":"publisher","unstructured":"Goodfellow, I. J. et al. Generative adversarial networks. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.1406.266 (2014).","DOI":"10.48550\/arXiv.1406.266"},{"key":"636_CR25","doi-asserted-by":"publisher","first-page":"1194","DOI":"10.1021\/acs.jcim.7b00690","volume":"58","author":"E Putin","year":"2018","unstructured":"Putin, E. et al. Reinforced adversarial neural computer for de novo molecular design. J. Chem. Inf. Model. 58, 1194\u20131204 (2018).","journal-title":"J. Chem. Inf. Model."},{"key":"636_CR26","doi-asserted-by":"publisher","unstructured":"Guimaraes, G. L., Sanchez-Lengeling, B., Outeiral, C., Farias, P. L. C. & Aspuru-Guzik, A. Objective-reinforced generative adversarial networks (ORGAN) for sequence generation models. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.1705.10843 (2017).","DOI":"10.48550\/arXiv.1705.10843"},{"key":"636_CR27","doi-asserted-by":"publisher","unstructured":"Vaswani, A. et al. Attention Is all you need. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.1706.03762 (2017).","DOI":"10.48550\/arXiv.1706.03762"},{"key":"636_CR28","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-79682-4","volume":"11","author":"D Grechishnikova","year":"2021","unstructured":"Grechishnikova, D. Transformer neural network for protein-specific de novo drug generation as a machine translation problem. Sci. Rep. 11, 321 (2021).","journal-title":"Sci. Rep."},{"key":"636_CR29","doi-asserted-by":"publisher","first-page":"2064","DOI":"10.1021\/acs.jcim.1c00600","volume":"62","author":"V Bagal","year":"2022","unstructured":"Bagal, V., Aggarwal, R., Vinod, P. K. & Priyakumar, U. D. MolGPT: molecular generation using a transformer-decoder model. J. Chem. Inf. Model. 62, 2064\u20132076 (2022).","journal-title":"J. Chem. Inf. Model."},{"key":"636_CR30","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-021-00565-5","volume":"13","author":"S Zheng","year":"2021","unstructured":"Zheng, S. et al. Deep scaffold hopping with multimodal transformer neural networks. J. Cheminform. 13, 87 (2021).","journal-title":"J. Cheminform."},{"key":"636_CR31","doi-asserted-by":"publisher","unstructured":"He, J. et al. Transformer neural network for structure constrained molecular optimization. Preprint at ChemRxiv https:\/\/doi.org\/10.26434\/chemrxiv.14416133.v1 (2021).","DOI":"10.26434\/chemrxiv.14416133.v1"},{"key":"636_CR32","doi-asserted-by":"crossref","unstructured":"Goldberg, Y. A Primer on neural network models for natural language Processing. J. Artif. Intell. Res. 57, 345\u2013420 (2016).","DOI":"10.1613\/jair.4992"},{"key":"636_CR33","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":"636_CR34","unstructured":"Bjerrum, E. J. & Threlfall, R. Molecular generation with recurrent neural networks (RNNs). Preprint at https:\/\/arxiv.org\/abs\/1705.04612 (2017)."},{"key":"636_CR35","doi-asserted-by":"publisher","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":"636_CR36","doi-asserted-by":"publisher","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":"636_CR37","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R. J. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992).","journal-title":"Mach. Learn."},{"key":"636_CR38","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":"636_CR39","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s42256-022-00494-4","volume":"4","author":"J Guo","year":"2022","unstructured":"Guo, J. et al. Improving de novo molecular design with curriculum learning. Nat. Mach. Intell. 4, 555\u2013563 (2022).","journal-title":"Nat. Mach. Intell."},{"key":"636_CR40","doi-asserted-by":"publisher","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":"636_CR41","doi-asserted-by":"publisher","unstructured":"Soviany, P., Ionescu, R. T., Rota, P. & Sebe, N. Curriculum learning: a survey. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2101.10382 (2021).","DOI":"10.48550\/arXiv.2101.10382"},{"key":"636_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":"636_CR43","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 ChemRxiv https:\/\/doi.org\/10.26434\/chemrxiv.7097960.v1 (2018)","DOI":"10.26434\/chemrxiv.7097960.v1"},{"key":"636_CR44","doi-asserted-by":"publisher","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","volume":"40","author":"A Gaulton","year":"2012","unstructured":"Gaulton, A. et al. ChEMBL: a large-scale bioactivity database for drug discovery. Nucleic Acids Res. 40, D1100\u2013D1107 (2012).","journal-title":"Nucleic Acids Res."},{"key":"636_CR45","unstructured":"Landrum, G. RDKit: Open-Source Cheminformatics (RDKit, 2006)."},{"key":"636_CR46","doi-asserted-by":"publisher","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":"636_CR47","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":"636_CR48","doi-asserted-by":"crossref","unstructured":"Polykovskiy, D. et al. Molecular Sets (MOSES): a benchmarking platform for molecular generation models. Front. Pharmacol. 11, 565644 (2020).","DOI":"10.3389\/fphar.2020.565644"},{"key":"636_CR49","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/0010-0277(93)90058-4","volume":"48","author":"JL Elman","year":"1993","unstructured":"Elman, J. L. Learning and development in neural networks: the importance of starting small. Cognition 48, 71\u201399 (1993).","journal-title":"Cognition"},{"key":"636_CR50","doi-asserted-by":"publisher","first-page":"5918","DOI":"10.1021\/acs.jcim.0c00915","volume":"60","author":"T Blaschke","year":"2020","unstructured":"Blaschke, T. et al. REINVENT 2.0: an AI tool for de novo drug design. J. Chem. Inf. Model. 60, 5918\u20135922 (2020).","journal-title":"J. Chem. Inf. Model."}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00636-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00636-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00636-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,23]],"date-time":"2023-04-23T19:04:39Z","timestamp":1682276679000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00636-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,3]]},"references-count":50,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,4]]}},"alternative-id":["636"],"URL":"https:\/\/doi.org\/10.1038\/s42256-023-00636-2","relation":{},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,3]]},"assertion":[{"value":"15 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2023","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"}}]}}