{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:31:59Z","timestamp":1772137919809,"version":"3.50.1"},"reference-count":17,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2020,12,24]],"date-time":"2020-12-24T00:00:00Z","timestamp":1608768000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,12,24]],"date-time":"2020-12-24T00:00:00Z","timestamp":1608768000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"European Union\u2019s Horizon 2020 research and innovation program","award":["676434"],"award-info":[{"award-number":["676434"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2021,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Automated retrosynthetic planning algorithms are a research area of increasing importance. Automated reaction-template extraction from large datasets, in conjunction with neural-network-enhanced tree-search algorithms, can find plausible routes to target compounds in seconds. However, the current method for training neural networks to predict suitable templates for a given target product leads to many predictions that are not applicable\n                    <jats:italic>in silico<\/jats:italic>\n                    . Most templates in the top 50 suggested templates cannot be applied to the target molecule to perform the virtual reaction. Here, we describe how to generate data and train a neural network policy that predicts whether templates are applicable or not. First, we generate a massive training dataset by applying each retrosynthetic template to each product from our reaction database. Second, we train a neural network to perform near-perfect prediction of the applicability labels on a held-out test set. The trained network is then joined with a policy model trained to predict and prioritize templates using the labels from the original dataset. The combined model was found to outperform the policy model in a route-finding task using 1700 compounds from our internal drug-discovery projects.\n                  <\/jats:p>","DOI":"10.1088\/2632-2153\/abcf90","type":"journal-article","created":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T17:46:36Z","timestamp":1606844796000},"page":"017001","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Artificial applicability labels for improving policies in retrosynthesis prediction"],"prefix":"10.1088","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1614-7376","authenticated-orcid":false,"given":"Esben Jannik","family":"Bjerrum","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0403-4067","authenticated-orcid":false,"given":"Amol","family":"Thakkar","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":"266","published-online":{"date-parts":[[2020,12,24]]},"reference":[{"key":"mlstabcf90bib1","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1126\/science.166.3902.178","article-title":"Computer-assisted design of complex organic syntheses","volume":"166","author":"Corey","year":"1969","journal-title":"Science"},{"key":"mlstabcf90bib2","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/s10822-016-9975-3","article-title":"Computer-aided drug design at Boehringer Ingelheim","volume":"31","author":"Muegge","year":"2017","journal-title":"J. Comput. Aided. Mol. Des."},{"key":"mlstabcf90bib3","doi-asserted-by":"publisher","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."},{"key":"mlstabcf90bib4","doi-asserted-by":"publisher","DOI":"10.1002\/minf.201800041","article-title":"Cheminformatics in drug discovery, an industrial perspective","volume":"37","author":"Chen","year":"2018","journal-title":"Mol. Inform."},{"key":"mlstabcf90bib5","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1039\/C4GC01563K","article-title":"Overcoming barriers to green chemistry in the pharmaceutical industry\u2014the green aspiration levelTM concept","volume":"17","author":"Roschangar","year":"2015","journal-title":"Green Chem."},{"key":"mlstabcf90bib6","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/nature25978","article-title":"Planning chemical syntheses with deep neural networks and symbolic AI","volume":"555","author":"Segler","year":"2018","journal-title":"Nature"},{"key":"mlstabcf90bib7","doi-asserted-by":"publisher","first-page":"2529","DOI":"10.1021\/acs.jcim.9b00286","article-title":"RDChiral: an RDKit wrapper for handling stereochemistry in retrosynthetic template extraction and application","volume":"59","author":"Coley","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"mlstabcf90bib8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1039\/C9SC04944D","article-title":"Datasets and their influence on the development of computer assisted synthesis planning tools in the pharmaceutical domain","volume":"11","author":"Thakkar","year":"2019","journal-title":"Chem. Sci."},{"key":"mlstabcf90bib9","article-title":"RDKIT: open source cheminformatics","year":"2019"},{"key":"mlstabcf90bib10","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-connectivity fingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem. Inf. Model"},{"key":"mlstabcf90bib11","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1021\/c160017a018","article-title":"The generation of a unique machine description for chemical structures\u2014a technique developed at chemical abstracts service","volume":"5","author":"Morgan","year":"1965","journal-title":"J. Chem. Doc."},{"key":"mlstabcf90bib12","doi-asserted-by":"publisher","first-page":"8791","DOI":"10.1021\/acs.jmedchem.9b01919","article-title":"\u2018Ring Breaker\u2019: assessing synthetic accessibility of the ring system chemical space","volume":"63","author":"Thakkar","year":"2020"},{"key":"mlstabcf90bib13","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: fundamental algorithms for scientific computing in Python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"mlstabcf90bib14","author":"Chollet","year":"2015"},{"key":"mlstabcf90bib15","first-page":"265","article-title":"TensorFlow: a system for large-scale machine learning","author":"Abadi","year":"2016"},{"key":"mlstabcf90bib16","doi-asserted-by":"publisher","first-page":"3398","DOI":"10.1021\/acs.jcim.0c00403","article-title":"Data augmentation and pretraining for template-based retrosynthetic prediction in computer-aided synthesis planning","volume":"60","author":"Fortunato","year":"2020","journal-title":"J. Chem. Inf. Model."},{"key":"mlstabcf90bib17","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1016\/j.chempr.2018.02.002","article-title":"Efficient syntheses of diverse, medicinally relevant targets planned by computer and executed in the laboratory","volume":"4","author":"Klucznik","year":"2018","journal-title":"Chem"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcf90","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcf90\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcf90","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcf90\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcf90\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcf90","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcf90\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcf90\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcf90\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcf90\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcf90\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcf90","content-type":"text\/html","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T09:55:29Z","timestamp":1672998929000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcf90"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,24]]},"references-count":17,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2020,12,24]]},"published-print":{"date-parts":[[2021,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/abcf90","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv.12249458","asserted-by":"object"},{"id-type":"doi","id":"10.26434\/chemrxiv.12249458.v1","asserted-by":"object"}]},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,24]]},"assertion":[{"value":"Artificial applicability labels for improving policies in retrosynthesis prediction","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2020 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2020-07-27","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2020-12-01","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2020-12-24","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}