{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T16:35:49Z","timestamp":1773938149040,"version":"3.50.1"},"publisher-location":"Cham","reference-count":7,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030304928","type":"print"},{"value":"9783030304935","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>A Recurrent Neural Network (RNN) trained with a set of molecules represented as SMILES strings can generate millions of different valid and meaningful chemical structures. In most of the reported architectures the models have been trained using a canonical (unique for each molecule) representation of SMILES. Instead, this research shows that when using randomized SMILES as a data amplification technique, a model can generate more molecules and those are going to accurately represent the training set properties. To show that, an extensive benchmark study has been conducted using research from a recently published article which shows that models trained with molecules from the GDB-13 database (975 million molecules) achieve better overall chemical space coverage when the posterior probability distribution is as uniform as possible. Specifically, we created models that generate nearly all the GDB-13 chemical space using only 1 million molecules as training set. Lastly, models were also trained with smaller training set sizes and show substantial improvement when using randomized SMILES compared to canonical.<\/jats:p>","DOI":"10.1007\/978-3-030-30493-5_68","type":"book-chapter","created":{"date-parts":[[2019,9,10]],"date-time":"2019-09-10T20:03:41Z","timestamp":1568145821000},"page":"747-751","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Improving Deep Generative Models with Randomized SMILES"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9860-2944","authenticated-orcid":false,"given":"Josep","family":"Ar\u00fas-Pous","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9139-6378","authenticated-orcid":false,"given":"Simon","family":"Johansson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9694-1192","authenticated-orcid":false,"given":"Oleksii","family":"Prykhodko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1614-7376","authenticated-orcid":false,"given":"Esben Jannik","family":"Bjerrum","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6470-984X","authenticated-orcid":false,"given":"Christian","family":"Tyrchan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2724-2942","authenticated-orcid":false,"given":"Jean-Louis","family":"Reymond","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4470-876X","authenticated-orcid":false,"given":"Hongming","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4970-6461","authenticated-orcid":false,"given":"Ola","family":"Engkvist","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,9,9]]},"reference":[{"issue":"1","key":"68_CR1","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., Blaschke, T., Ulander, S., Reymond, J.L., Chen, H., Engkvist, O.: Exploring the GDB-13 chemical space using deep generative models. J. Cheminform. 11(1), 20 (2019). https:\/\/doi.org\/10.1186\/s13321-019-0341-z","journal-title":"J. Cheminform."},{"key":"68_CR2","doi-asserted-by":"publisher","unstructured":"Awale, M., Sirockin, F., Stiefl, N., Reymond, J.l.: Drug analogs from fragment based long short-term memory generative neural networks (2018). https:\/\/doi.org\/10.26434\/chemrxiv.7277354.v1, https:\/\/chemrxiv.org\/articles\/Drug_Analogs_from_Fragment_Based_Long_Short-Term_Memory_Generative_Neural_Networks\/7277354","DOI":"10.26434\/chemrxiv.7277354.v1"},{"key":"68_CR3","unstructured":"Bjerrum, E.J.: SMILES Enumeration as Data Augmentation for Neural Network Modeling of Molecules. arXiv March 2017. http:\/\/arxiv.org\/abs\/1703.07076"},{"issue":"25","key":"68_CR4","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(25), 8732\u20138733 (2009). https:\/\/doi.org\/10.1021\/ja902302h","journal-title":"J. Am. Chem. Soc."},{"key":"68_CR5","doi-asserted-by":"publisher","unstructured":"Olivecrona, M., Blaschke, T., Engkvist, O., Chen, H.: Molecular de novo design through deep reinforcement learning. J. Cheminform. 9(1) (2017). https:\/\/doi.org\/10.1186\/s13321-017-0235-x, http:\/\/arxiv.org\/abs\/1704.07555","DOI":"10.1186\/s13321-017-0235-x"},{"issue":"1","key":"68_CR6","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1021\/acscentsci.7b00512","volume":"4","author":"Marwin H. S. Segler","year":"2017","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(1), 1\u201317 (2018). https:\/\/doi.org\/10.1021\/acscentsci.7b00512, http:\/\/arxiv.org\/abs\/1701.01329","journal-title":"ACS Central Science"},{"issue":"1","key":"68_CR7","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(1), 31\u201336 (1988). https:\/\/doi.org\/10.1021\/ci00057a005","journal-title":"J. Chem. Inf. Comput. Sci."}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2019: Workshop and Special Sessions"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-30493-5_68","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T16:55:09Z","timestamp":1710348909000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-30493-5_68"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030304928","9783030304935"],"references-count":7,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-30493-5_68","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"9 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}