{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T11:32:10Z","timestamp":1787311930877,"version":"3.56.0"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,3,20]],"date-time":"2021-03-20T00:00:00Z","timestamp":1616198400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2021,3,20]],"date-time":"2021-03-20T00:00:00Z","timestamp":1616198400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    A main challenge in drug discovery is finding molecules with a desirable balance of multiple properties. Here, we focus on the task of molecular optimization, where the goal is to optimize a given starting molecule towards desirable properties. This task can be framed as a machine translation problem in natural language processing, where in our case, a molecule is translated into a molecule with optimized properties based on the SMILES representation. Typically, chemists would use their intuition to suggest chemical transformations for the starting molecule being optimized. A widely used strategy is the concept of matched molecular pairs where two molecules differ by a single transformation. We seek to capture the chemist\u2019s intuition from matched molecular pairs using machine translation models. Specifically, the sequence-to-sequence model with attention mechanism, and the Transformer model are employed to generate molecules with desirable properties. As a proof of concept, three ADMET properties are optimized simultaneously:\n                    <jats:italic>logD<\/jats:italic>\n                    ,\n                    <jats:italic>solubility<\/jats:italic>\n                    , and\n                    <jats:italic>clearance<\/jats:italic>\n                    , which are important properties of a drug. Since desirable properties often vary from project to project, the user-specified desirable property changes are incorporated into the input as an additional condition together with the starting molecules being optimized. Thus, the models can be guided to generate molecules satisfying the desirable properties. Additionally, we compare the two machine translation models based on the SMILES representation, with a graph-to-graph translation model HierG2G, which has shown the state-of-the-art performance in molecular optimization. Our results show that the Transformer can generate more molecules with desirable properties by making small modifications to the given starting molecules, which can be intuitive to chemists. A further enrichment of diverse molecules can be achieved by using an ensemble of models.\n                  <\/jats:p>","DOI":"10.1186\/s13321-021-00497-0","type":"journal-article","created":{"date-parts":[[2021,3,20]],"date-time":"2021-03-20T08:02:54Z","timestamp":1616227374000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":79,"title":["Molecular optimization by capturing chemist\u2019s intuition using deep neural networks"],"prefix":"10.1186","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5848-8318","authenticated-orcid":false,"given":"Jiazhen","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huifang","family":"You","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emil","family":"Sandstr\u00f6m","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eva","family":"Nittinger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Esben Jannik","family":"Bjerrum","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Tyrchan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Werngard","family":"Czechtizky","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ola","family":"Engkvist","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,3,20]]},"reference":[{"issue":"8","key":"497_CR1","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1007\/s10822-013-9672-4","volume":"27","author":"PG Polishchuk","year":"2013","unstructured":"Polishchuk PG, Madzhidov TI, Varnek A (2013) Estimation of the size of drug-like chemical space based on gdb-17 data. J Comput Aided Mol Design 27(8):675\u2013679","journal-title":"J Comput Aided Mol Design"},{"issue":"10","key":"497_CR2","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.1021\/jm00280a002","volume":"15","author":"JG Topliss","year":"1972","unstructured":"Topliss JG (1972) Utilization of operational schemes for analog synthesis in drug design. J Med Chem 15(10):1006\u20131011","journal-title":"J Med Chem"},{"key":"497_CR3","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1002\/3527603743.ch11","volume":"23","author":"PW Kenny","year":"2005","unstructured":"Kenny PW, Sadowski J (2005) Structure modification in chemical databases. Chemoinf Drug Discov 23:271\u2013285","journal-title":"Chemoinf Drug Discov"},{"key":"497_CR4","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1016\/j.csbj.2016.12.003","volume":"15","author":"C Tyrchan","year":"2017","unstructured":"Tyrchan C, Evertsson E (2017) Matched molecular pair analysis in short: algorithms, applications and limitations. Comput Struct Biotechnol J 15:86\u201390","journal-title":"Comput Struct Biotechnol J"},{"issue":"12","key":"497_CR5","doi-asserted-by":"publisher","first-page":"5203","DOI":"10.1021\/jm400223y","volume":"56","author":"J Weber","year":"2013","unstructured":"Weber J, Achenbach J, Moser D, Proschak E (2013) Vammpire: a matched molecular pairs database for structure-based drug design and optimization. J Med Chem 56(12):5203\u20135207","journal-title":"J Med Chem"},{"issue":"22","key":"497_CR6","doi-asserted-by":"publisher","first-page":"7739","DOI":"10.1021\/jm200452d","volume":"54","author":"E Griffen","year":"2011","unstructured":"Griffen E, Leach AG, Robb GR, Warner DJ (2011) Matched molecular pairs as a medicinal chemistry tool: miniperspective. J Med Chem 54(22):7739\u20137750","journal-title":"J Med Chem"},{"issue":"23","key":"497_CR7","doi-asserted-by":"publisher","first-page":"6672","DOI":"10.1021\/jm0605233","volume":"49","author":"AG Leach","year":"2006","unstructured":"Leach AG, Jones HD, Cosgrove DA, Kenny PW, Ruston L, MacFaul P, Wood JM, Colclough N, Law B (2006) Matched molecular pairs as a guide in the optimization of pharmaceutical properties; a study of aqueous solubility, plasma protein binding and oral exposure. J Med Chem 49(23):6672\u20136682","journal-title":"J Med Chem"},{"issue":"4824","key":"497_CR8","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1038\/194178b0","volume":"194","author":"C Hansch","year":"1962","unstructured":"Hansch C, Maloney PP, Fujita T, Muir RM (1962) Correlation of biological activity of phenoxyacetic acids with hammett substituent constants and partition coefficients. Nature 194(4824):178\u2013180","journal-title":"Nature"},{"issue":"8","key":"497_CR9","doi-asserted-by":"publisher","first-page":"1616","DOI":"10.1021\/ja01062a035","volume":"86","author":"C Hansch","year":"1964","unstructured":"Hansch C, Fujita T (1964) p-$$\\sigma$$-$$\\pi$$ analysis. a method for the correlation of biological activity and chemical structure. J Am Chem Soc 86(8):1616\u20131626","journal-title":"J Am Chem Soc"},{"issue":"4","key":"497_CR10","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1021\/jm00334a001","volume":"7","author":"SM Free","year":"1964","unstructured":"Free SM, Wilson JW (1964) A mathematical contribution to structure-activity studies. J Med Chem 7(4):395\u2013399","journal-title":"J Med Chem"},{"issue":"1","key":"497_CR11","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1021\/acscentsci.7b00512","volume":"4","author":"MH Segler","year":"2018","unstructured":"Segler MH, Kogej T, Tyrchan C, Waller MP (2018) Generating focused molecule libraries for drug discovery with recurrent neural networks. ACS Central Sci 4(1):120\u2013131","journal-title":"ACS Central Sci"},{"issue":"1\u20132","key":"497_CR12","doi-asserted-by":"publisher","first-page":"1700111","DOI":"10.1002\/minf.201700111","volume":"37","author":"A Gupta","year":"2018","unstructured":"Gupta A, M\u00fcller AT, Huisman BJ, Fuchs JA, Schneider P, Schneider G (2018) Generative recurrent networks for de novo drug design. Mol Inf 37(1\u20132):1700111","journal-title":"Mol Inf"},{"issue":"2","key":"497_CR13","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, Wei JN, Duvenaud D, Hern\u00e1ndez-Lobato JM, S\u00e1nchez-Lengeling B, Sheberla D, Aguilera-Iparraguirre J, Hirzel TD, Adams RP, Aspuru-Guzik A (2018) Automatic chemical design using a data-driven continuous representation of molecules. ACS Central Sci 4(2):268\u2013276","journal-title":"ACS Central Sci"},{"key":"497_CR14","unstructured":"Dai H, Tian Y, Dai B, Skiena S, Song L (2018) Syntax-directed variational autoencoder for molecule generation. In: Proceedings of the international conference on learning representations"},{"issue":"1","key":"497_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-017-0256-5","volume":"10","author":"J Lim","year":"2018","unstructured":"Lim J, Ryu S, Kim JW, Kim WY (2018) Molecular generative model based on conditional variational autoencoder for de novo molecular design. J Chem 10(1):1\u20139","journal-title":"J Chem"},{"key":"497_CR16","unstructured":"Jin W, Barzilay R, Jaakkola T (2018) Junction tree variational autoencoder for molecular graph generation. In: International conference on machine learning, pp. 2323\u20132332"},{"key":"497_CR17","unstructured":"Liu Q, Allamanis M, Brockschmidt M, Gaunt A (2018) Constrained graph variational autoencoders for molecule design. In: Advances in neural information processing systems, pp. 7795\u20137804"},{"key":"497_CR18","doi-asserted-by":"crossref","unstructured":"Simonovsky M, Komodakis N (2018) Graphvae: Towards generation of small graphs using variational autoencoders. In: International conference on artificial neural networks, pp. 412\u2013422. Springer","DOI":"10.1007\/978-3-030-01418-6_41"},{"key":"497_CR19","unstructured":"Guimaraes GL, Sanchez-Lengeling B, Outeiral C, Farias PLC, Aspuru-Guzik A (2017)Objective-reinforced generative adversarial networks (organ) for sequence generation models. arXiv preprint arXiv:1705.10843"},{"issue":"6","key":"497_CR20","doi-asserted-by":"publisher","first-page":"1194","DOI":"10.1021\/acs.jcim.7b00690","volume":"58","author":"E Putin","year":"2018","unstructured":"Putin E, Asadulaev A, Ivanenkov Y, Aladinskiy V, Sanchez-Lengeling B, Aspuru-Guzik A, Zhavoronkov A (2018) Reinforced adversarial neural computer for de novo molecular design. J Chem Inf Modeling 58(6):1194\u20131204","journal-title":"J Chem Inf Modeling"},{"issue":"10","key":"497_CR21","doi-asserted-by":"publisher","first-page":"4386","DOI":"10.1021\/acs.molpharmaceut.7b01137","volume":"15","author":"E Putin","year":"2018","unstructured":"Putin E, Asadulaev A, Vanhaelen Q, Ivanenkov Y, Aladinskaya AV, Aliper A, Zhavoronkov A (2018) Adversarial threshold neural computer for molecular de novo design. Mol Pharm 15(10):4386\u20134397","journal-title":"Mol Pharm"},{"key":"497_CR22","unstructured":"De Cao N, Kipf T (2018) Molgan: An implicit generative model for small molecular graphs. arXiv preprint arXiv:1805.11973"},{"issue":"1","key":"497_CR23","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 (2017) Molecular de-novo design through deep reinforcement learning. J Cheminf 9(1):48","journal-title":"J Cheminf"},{"key":"497_CR24","unstructured":"Jin W, Yang K, Barzilay R, Jaakkola T (2018) Learning multimodal graph-to-graph translation for molecular optimization. arXiv preprint arXiv:1812.01070"},{"issue":"9","key":"497_CR25","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 (2017) drugan: an advanced generative adversarial autoencoder model for de novo generation of new molecules with desired molecular properties in silico. Mol Pharm 14(9):3098\u20133104","journal-title":"Mol Pharm"},{"issue":"1\u20132","key":"497_CR26","doi-asserted-by":"publisher","first-page":"1700123","DOI":"10.1002\/minf.201700123","volume":"37","author":"T Blaschke","year":"2018","unstructured":"Blaschke T, Olivecrona M, Engkvist O, Bajorath J, Chen H (2018) Application of generative autoencoder in de novo molecular design. Mol Inf 37(1\u20132):1700123","journal-title":"Mol Inf"},{"issue":"34","key":"497_CR27","doi-asserted-by":"publisher","first-page":"8016","DOI":"10.1039\/C9SC01928F","volume":"10","author":"R Winter","year":"2019","unstructured":"Winter R, Montanari F, Steffen A, Briem H, No\u00e9 F, Clevert D-A (2019) Efficient multi-objective molecular optimization in a continuous latent space. Chem Sci 10(34):8016\u20138024","journal-title":"Chem Sci"},{"key":"497_CR28","unstructured":"Bradshaw J, Paige B, Kusner MJ, Segler, MH, Hern\u00e1ndez-Lobato JM (2020) Barking up the right tree: an approach to search over molecule synthesis dags. NeurIPS 2020 workshop on machine learning for molecules"},{"issue":"1","key":"497_CR29","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 (2018) Multi-objective de novo drug design with conditional graph generative model. J Cheminf 10(1):33","journal-title":"J Cheminf"},{"issue":"5","key":"497_CR30","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, Ar\u00fas-Pous J, Chen H, Engkvist O, Tyrchan C, Bjerrum EJ (2020) Direct steering of de novo molecular generation with descriptor conditional recurrent neural networks. Nat Mach Intellig 2(5):254\u2013265","journal-title":"Nat Mach Intellig"},{"key":"497_CR31","unstructured":"You J, Liu B, Ying Z, Pande V, Leskovec J (2018) Graph convolutional policy network for goal-directed molecular graph generation. In: Advances in neural information processing systems, pp. 6410\u20136421"},{"issue":"1","key":"497_CR32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-018-37186-2","volume":"9","author":"Z Zhou","year":"2019","unstructured":"Zhou Z, Kearnes S, Li L, Zare RN, Riley P (2019) Optimization of molecules via deep reinforcement learning. Sci Rep 9(1):1\u201310","journal-title":"Sci Rep"},{"key":"497_CR33","unstructured":"Bahdanau D, Cho K, Bengio Y (2015) Neural machine translation by jointly learning to align and translate. In: 3rd international conference on learning representations, ICLR 2015"},{"key":"497_CR34","unstructured":"Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Advances in neural information processing systems, pp. 3104\u20133112"},{"key":"497_CR35","unstructured":"Luong M-T, Pham H, Manning CD (2015) Effective approaches to attention-based neural machine translation. In: Proceedings of the 2015 conference on empirical methods in natural language processing, pp. 1412\u20131421"},{"key":"497_CR36","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp. 5998\u20136008"},{"issue":"9","key":"497_CR37","doi-asserted-by":"publisher","first-page":"1572","DOI":"10.1021\/acscentsci.9b00576","volume":"5","author":"P Schwaller","year":"2019","unstructured":"Schwaller P, Laino T, Gaudin T, Bolgar P, Hunter CA, Bekas C, Lee AA (2019) Molecular transformer: a model for uncertainty-calibrated chemical reaction prediction. ACS Central Sci 5(9):1572\u20131583","journal-title":"ACS Central Sci"},{"key":"497_CR38","unstructured":"Jin W, Barzilay R, Jaakkola T (2019) Hierarchical graph-to-graph translation for molecules. arXiv 1907"},{"key":"497_CR39","unstructured":"Jin W, Barzilay R, Jaakkola T (2020) Hierarchical generation of molecular graphs using structural motifs. arXiv preprint arXiv:2002.03230"},{"issue":"1","key":"497_CR40","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","volume":"28","author":"D Weininger","year":"1988","unstructured":"Weininger D (1988) Smiles, a chemical language and information system. 1. Introduction to methodology and encoding rules. J Chem Inf Comput Sci 28(1):31\u201336","journal-title":"J Chem Inf Comput Sci"},{"issue":"5","key":"497_CR41","doi-asserted-by":"publisher","first-page":"902","DOI":"10.1021\/acs.jcim.8b00173","volume":"58","author":"A Dalke","year":"2018","unstructured":"Dalke A, Hert J, Kramer C (2018) mmpdb: an open-source matched molecular pair platform for large multiproperty data sets. J Chem Inf Model 58(5):902\u2013910","journal-title":"J Chem Inf Model"},{"key":"497_CR42","unstructured":"Swain M (2018) MolVS: molecule validation and standardization"},{"issue":"12","key":"497_CR43","doi-asserted-by":"publisher","first-page":"948","DOI":"10.1038\/nrd4128","volume":"12","author":"JG Cumming","year":"2013","unstructured":"Cumming JG, Davis AM, Muresan S, Haeberlein M, Chen H (2013) Chemical predictive modelling to improve compound quality. Nat Rev Drug Dis 12(12):948\u2013962","journal-title":"Nat Rev Drug Dis"},{"issue":"8","key":"497_CR44","doi-asserted-by":"publisher","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","volume":"59","author":"K Yang","year":"2019","unstructured":"Yang K, Swanson K, Jin W, Coley C, Eiden P, Gao H, Guzman-Perez A, Hopper T, Kelley B, Mathea M et al (2019) Analyzing learned molecular representations for property prediction. J Chem Inf Model 59(8):3370\u20133388","journal-title":"J Chem Inf Model"},{"issue":"399","key":"497_CR45","first-page":"918","volume":"82","author":"FW Scholz","year":"1987","unstructured":"Scholz FW, Stephens MA (1987) K-sample Anderson\u2013Darling tests. J Am Stat Assoc 82(399):918\u2013924","journal-title":"J Am Stat Assoc"},{"key":"497_CR46","doi-asserted-by":"crossref","unstructured":"Polykovskiy D, Zhebrak A, Sanchez-Lengeling B, Golovanov S, Tatanov O, Belyaev S, Kurbanov R, Artamonov A, Aladinskiy V, Veselov M et al (2020) Molecular sets (moses): a benchmarking platform for molecular generation models. Front Pharmacol 11:58","DOI":"10.3389\/fphar.2020.565644"},{"issue":"3","key":"497_CR47","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 MH, Vaucher AC (2019) Guacamol: benchmarking models for de novo molecular design. J Chem Inf Model 59(3):1096\u20131108","journal-title":"J Chem Inf Model"},{"key":"497_CR48","unstructured":"Brubaker J, Dinsmore C, Hoffman DM, Jung J, Liu D, Peterson S, Siu T, Torres LE, Zhang H, Wei Z, et al (2015) Cycloalkylnitrile pyrazole carboxamides as janus kinase inhibitors. Google Patents. US Patent 8,962,608"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-021-00497-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13321-021-00497-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-021-00497-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T20:48:10Z","timestamp":1671655690000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-021-00497-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,20]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["497"],"URL":"https:\/\/doi.org\/10.1186\/s13321-021-00497-0","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-101137\/v1","asserted-by":"object"},{"id-type":"doi","id":"10.26434\/chemrxiv.12941744.v2","asserted-by":"object"},{"id-type":"doi","id":"10.26434\/chemrxiv.12941744.v1","asserted-by":"object"},{"id-type":"doi","id":"10.26434\/chemrxiv.12941744","asserted-by":"object"}]},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,20]]},"assertion":[{"value":"30 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 March 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"26"}}