{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T05:36:13Z","timestamp":1774935373971,"version":"3.50.1"},"reference-count":56,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2019,1,30]],"date-time":"2019-01-30T00:00:00Z","timestamp":1548806400000},"content-version":"vor","delay-in-days":29,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"Elsevier B.V."}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,1,1]]},"DOI":"10.1093\/database\/baz001","type":"journal-article","created":{"date-parts":[[2019,1,4]],"date-time":"2019-01-04T20:10:07Z","timestamp":1546632607000},"source":"Crossref","is-referenced-by-count":29,"title":["Automatic identification of relevant chemical compounds from patents"],"prefix":"10.1093","volume":"2019","author":[{"given":"Saber A","family":"Akhondi","sequence":"first","affiliation":[{"name":"Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, CA, Netherlands"},{"name":"Elsevier B.V., Radarweg 29, Amsterdam NX, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hinnerk","family":"Rey","sequence":"additional","affiliation":[{"name":"Elsevier Information Systems GmbH, Theodor-Heuss-Allee 108, Frankfurt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Markus","family":"Schw\u00f6rer","sequence":"additional","affiliation":[{"name":"Elsevier Information Systems GmbH, Theodor-Heuss-Allee 108, Frankfurt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Maier","sequence":"additional","affiliation":[{"name":"Elsevier Information Systems GmbH, Theodor-Heuss-Allee 108, Frankfurt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Toomey","sequence":"additional","affiliation":[{"name":"Elsevier Limited, 125 London Wall, London, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heike","family":"Nau","sequence":"additional","affiliation":[{"name":"Elsevier Information Systems GmbH, Theodor-Heuss-Allee 108, Frankfurt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gabriele","family":"Ilchmann","sequence":"additional","affiliation":[{"name":"Elsevier Information Systems GmbH, Theodor-Heuss-Allee 108, Frankfurt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Sheehan","sequence":"additional","affiliation":[{"name":"Elsevier Information Systems GmbH, Theodor-Heuss-Allee 108, Frankfurt, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Irmer","sequence":"additional","affiliation":[{"name":"OntoChem IT Solutions GmbH, Bl\u00fccherstra\u00dfe 24, Halle (Saale), Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claudia","family":"Bobach","sequence":"additional","affiliation":[{"name":"OntoChem IT Solutions GmbH, Bl\u00fccherstra\u00dfe 24, Halle (Saale), Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marius","family":"Doornenbal","sequence":"additional","affiliation":[{"name":"Elsevier B.V., Radarweg 29, Amsterdam NX, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michelle","family":"Gregory","sequence":"additional","affiliation":[{"name":"Elsevier B.V., Radarweg 29, Amsterdam NX, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan A","family":"Kors","sequence":"additional","affiliation":[{"name":"Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, CA, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2019,1,30]]},"reference":[{"key":"key\n\t\t\t\t2019013001291920600_ref1","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.1016\/j.drudis.2011.10.005","article-title":"Making every SAR point count: the development of chemistry connect for the large-scale integration of structure and bioactivity data","volume":"16","author":"Muresan","year":"2011","journal-title":"Drug Discov. Today"},{"key":"key\n\t\t\t\t2019013001291920600_ref2","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1186\/1758-2946-3-14","article-title":"Analysis of in vitro bioactivity data extracted from drug discovery literature and patents: ranking 1654 human protein targets by assayed compounds and molecular scaffolds","volume":"3","author":"Southan","year":"2011","journal-title":"J. Cheminform."},{"key":"key\n\t\t\t\t2019013001291920600_ref3","doi-asserted-by":"crossref","first-page":"D1220","DOI":"10.1093\/nar\/gkv1253","article-title":"SureChEMBL: a large-scale, chemically annotated patent document database","volume":"44","author":"Papadatos","year":"2016","journal-title":"Nucleic Acids Res."},{"issue":"12","key":"key\n\t\t\t\t2019013001291920600_ref4","doi-asserted-by":"crossref","first-page":"7673","DOI":"10.1021\/acs.chemrev.6b00851","article-title":"Information retrieval and text mining technologies for chemistry","volume":"117","author":"Krallinger","year":"2017","journal-title":"Chem. Rev."},{"key":"key\n\t\t\t\t2019013001291920600_ref5","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1186\/s13321-015-0097-z","article-title":"Managing expectations: assessment of chemistry databases generated by automated extraction of chemical structures from patents","volume":"7","author":"Senger","year":"2015","journal-title":"J. Cheminform."},{"key":"key\n\t\t\t\t2019013001291920600_ref6","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1016\/j.wpi.2005.05.003","article-title":"Patents: a unique source for scientific technical information in chemistry related industry?","volume":"27","author":"Bregonje","year":"2015","journal-title":"World Pat. Inf."},{"key":"key\n\t\t\t\t2019013001291920600_ref7","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0107477","article-title":"Annotated chemical patent corpus: a gold standard for text mining","volume":"9","author":"Akhondi","year":"2014","journal-title":"PLoS One"},{"key":"key\n\t\t\t\t2019013001291920600_ref8","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.wpi.2016.11.004","article-title":"\u201c80% of technical information found only in patents\u201d\u2014is there proof of this?","volume":"48","author":"Asche","year":"2017","journal-title":"World Pat. Inf."},{"key":"key\n\t\t\t\t2019013001291920600_ref9","doi-asserted-by":"crossref","first-page":"1480","DOI":"10.1021\/ci3001293","article-title":"Exploiting structural information in patent specifications for key compound prediction","volume":"52","author":"Tyrchan","year":"2012","journal-title":"J. Chem. Inf. Model."},{"issue":"4","key":"key\n\t\t\t\t2019013001291920600_ref10","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0121635","article-title":"Quantitative determination of technological improvement from patent data","volume":"10","author":"Benson","year":"2015","journal-title":"PLoS One"},{"key":"key\n\t\t\t\t2019013001291920600_ref11","author":"European Patent Office"},{"key":"key\n\t\t\t\t2019013001291920600_ref12","author":"United States Patent and Trademark Office"},{"key":"key\n\t\t\t\t2019013001291920600_ref13","author":"World Intellectual Property Organization"},{"key":"key\n\t\t\t\t2019013001291920600_ref14","doi-asserted-by":"crossref","first-page":"785","DOI":"10.2174\/1568026054637692","article-title":"Information extraction in the life sciences: perspectives for medicinal chemistry, pharmacology and toxicology","volume":"5","author":"Zimmermann","year":"2005","journal-title":"Curr. Top. Med. Chem."},{"key":"key\n\t\t\t\t2019013001291920600_ref15","author":"Reaxys"},{"key":"key\n\t\t\t\t2019013001291920600_ref16","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1021\/bk-2014-1164.ch008","volume-title":"The Future of the History of Chemical Information","author":"Lawson","year":"2014"},{"key":"key\n\t\t\t\t2019013001291920600_ref17","author":"SciFinder"},{"key":"key\n\t\t\t\t2019013001291920600_ref18","author":"Thomson Reuters Pharma"},{"key":"key\n\t\t\t\t2019013001291920600_ref19","doi-asserted-by":"crossref","first-page":"D428","DOI":"10.1093\/nar\/gkr919","article-title":"SCRIPDB: a portal for easy access to syntheses, chemicals and reactions in patents","volume":"40","author":"Heifets","year":"2012","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019013001291920600_ref20","doi-asserted-by":"crossref","first-page":"D249","DOI":"10.1093\/nar\/gkp886","article-title":"Chemical entities of biological interest: an update","volume":"38","author":"Matos","year":"2010","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019013001291920600_ref21","article-title":"IBM contributes data to the National Institutes of Health to speed drug discovery and cancer research innovation","author":"IBM"},{"key":"key\n\t\t\t\t2019013001291920600_ref22","article-title":"Unleashing over a million reactions into the wild","author":"NextMove Software"},{"key":"key\n\t\t\t\t2019013001291920600_ref23","doi-asserted-by":"crossref","first-page":"D1202","DOI":"10.1093\/nar\/gkv951","article-title":"PubChem substance and compound databases","volume":"44","author":"Kim","year":"2016","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019013001291920600_ref24","author":"Japan Patent Office"},{"key":"key\n\t\t\t\t2019013001291920600_ref25","doi-asserted-by":"crossref","first-page":"780","DOI":"10.1021\/ci800449t","article-title":"CLiDE Pro: the latest generation of CLiDE, a tool for optical chemical structure recognition","volume":"49","author":"Valko","year":"2009","journal-title":"J. Chem. Inf. Model."},{"key":"key\n\t\t\t\t2019013001291920600_ref26","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1002\/minf.201100005","article-title":"Text mining for drugs and chemical compounds: methods, tools and applications","volume":"30","author":"Vazquez","year":"2011","journal-title":"Molecular Informatics"},{"key":"key\n\t\t\t\t2019013001291920600_ref27","doi-asserted-by":"crossref","first-page":"S10","DOI":"10.1186\/1758-2946-7-S1-S10","article-title":"Recognition of chemical entities: combining dictionary-based and grammar-based approaches","volume":"7","author":"Akhondi","year":"2015","journal-title":"J. Chem."},{"key":"key\n\t\t\t\t2019013001291920600_ref28","doi-asserted-by":"crossref","DOI":"10.1093\/database\/baw061","article-title":"Chemical entity recognition in patents by combining dictionary-based and statistical approaches","volume":"2016","author":"Akhondi","year":"2016","journal-title":"Database (Oxford)"},{"key":"key\n\t\t\t\t2019013001291920600_ref29","doi-asserted-by":"crossref","first-page":"1216","DOI":"10.1016\/j.ipm.2006.11.011","article-title":"Text mining techniques for patent analysis","volume":"43","author":"Tseng","year":"2007","journal-title":"Inf. Process. Manag."},{"key":"key\n\t\t\t\t2019013001291920600_ref30","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1021\/ci00007a012","article-title":"Description of several chemical structure file formats used by computer programs developed at molecular design limited","author":"Dalby","year":"1992","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"key\n\t\t\t\t2019013001291920600_ref31","first-page":"63","article-title":"Overview of the CHEMDNER patents task","author":"Krallinger","year":"2015"},{"key":"key\n\t\t\t\t2019013001291920600_ref32","doi-asserted-by":"crossref","first-page":"S1","DOI":"10.1186\/1758-2946-7-S1-S1","article-title":"CHEMDNER: the drugs and chemical names extraction challenge","volume":"7","author":"Krallinger","year":"2015","journal-title":"J. Chem."},{"key":"key\n\t\t\t\t2019013001291920600_ref33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1758-2946-6-17","article-title":"Chemical named entities recognition: a review on approaches and applications","volume":"6","author":"Eltyeb","year":"2014","journal-title":"J. Cheminform."},{"key":"key\n\t\t\t\t2019013001291920600_ref34","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1186\/1758-2946-4-35","article-title":"Consistency of systematic chemical identifiers within and between small-molecule databases","volume":"4","author":"Akhondi","year":"2012","journal-title":"J. Cheminform."},{"key":"key\n\t\t\t\t2019013001291920600_ref35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13321-015-0102-6","article-title":"Ambiguity of non-systematic chemical identifiers within and between small-molecule databases","volume":"7","author":"Akhondi","year":"2015","journal-title":"J. Cheminform."},{"issue":"suppl 1","key":"key\n\t\t\t\t2019013001291920600_ref36","doi-asserted-by":"crossref","first-page":"S2","DOI":"10.1186\/1758-2946-7-S1-S2","article-title":"The CHEMDNER corpus of chemicals and drugs and its annotation principles","volume":"7","author":"Krallinger","year":"2015","journal-title":"J. Cheminform."},{"key":"key\n\t\t\t\t2019013001291920600_ref37","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1186\/1758-2946-3-40","article-title":"Mining chemical information from open patents","volume":"3","author":"Jessop","year":"2011","journal-title":"J. Cheminform."},{"key":"key\n\t\t\t\t2019013001291920600_ref38","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.wpi.2015.12.003","article-title":"Indexing chemical structures: exemplified compound indexing in patents by the vendors Thomson Reuters, Chemical Abstracts and Elsevier\u2014a comparative study by the Patent Documentation Group (PDG)","volume":"44","author":"Ede","year":"2016","journal-title":"World Pat. Inf."},{"key":"key\n\t\t\t\t2019013001291920600_ref39","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1021\/ci7002686","article-title":"Predicting key example compounds in \u201ccompetitors\u201d patent applications using structural information alone","volume":"48","author":"Hattori","year":"2008","journal-title":"J. Chem. Inf. Model."},{"key":"key\n\t\t\t\t2019013001291920600_ref40","article-title":"Method and software for extracting chemical data","volume-title":"Unites States Patent Office (USPTO).","author":"Lawson","year":"2011"},{"key":"key\n\t\t\t\t2019013001291920600_ref41","first-page":"119","article-title":"OCMiner for patents. extracting chemical information from patent texts","volume-title":"Proceedings of the Fifth BioCreative Challenge Evaluation Workshop","author":"Irmer","year":"2015"},{"key":"key\n\t\t\t\t2019013001291920600_ref42","article-title":"Using Reaxys for searching chemistry in Patents","author":"Roller"},{"key":"key\n\t\t\t\t2019013001291920600_ref43","first-page":"51","article-title":"Chemical names: terminological resources and corpora annotation","volume-title":"Workshop on Building and Evaluating Resources for Biomedical Text Mining","author":"Kol\u00e1rik","year":"2008"},{"key":"key\n\t\t\t\t2019013001291920600_ref44","first-page":"61","article-title":"Integrated annotation for biomedical information extraction","author":"Kulick","year":"2004"},{"key":"key\n\t\t\t\t2019013001291920600_ref45","doi-asserted-by":"crossref","first-page":"i180","DOI":"10.1093\/bioinformatics\/btg1023","article-title":"GENIA corpus\u2014a semantically annotated corpus for bio-textmining","volume":"19","author":"Kim","year":"2003","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t2019013001291920600_ref46","doi-asserted-by":"crossref","first-page":"57","DOI":"10.3115\/1572392.1572403","article-title":"Annotation of chemical named entities","volume-title":"Proceedings of the Workshop on BioNLP 2007 Biological, Translational, and Clinical Language Processing\u2014BioNLP \u201c07\u201d","author":"Corbett","year":"2007"},{"key":"key\n\t\t\t\t2019013001291920600_ref47","author":"The Brat Contributors"},{"key":"key\n\t\t\t\t2019013001291920600_ref48","first-page":"102","article-title":"BRAT: a web-based tool for NLP-assisted text annotation","volume-title":"13th Conference of the European Chapter of the Association for Computational Linguistics, Avignon, France, April 23-27, 2012.","author":"Stenetorp","year":"2012"},{"key":"key\n\t\t\t\t2019013001291920600_ref49","doi-asserted-by":"crossref","first-page":"D1091","DOI":"10.1093\/nar\/gkt1068","article-title":"DrugBank 4.0: shedding new light on drug metabolism","volume":"42","author":"Law","year":"2014","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019013001291920600_ref50","doi-asserted-by":"crossref","first-page":"D1083","DOI":"10.1093\/nar\/gkt1031","article-title":"The ChEMBL bioactivity database: an update","volume":"42","author":"Bento","year":"2014","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019013001291920600_ref51","article-title":"Extraction of chemical structures and reactions from the literature","author":"Lowe","year":"2012"},{"key":"key\n\t\t\t\t2019013001291920600_ref52","doi-asserted-by":"crossref","DOI":"10.1093\/database\/baw120","article-title":"The Markyt visualisation, prediction and benchmark platform for chemical and gene entity recognition at at BioCreative\/CHEMDNER challenge","volume":"2016","author":"P\u00e9rez-P\u00e9rez","year":"2016","journal-title":"Database (Oxford)"},{"key":"key\n\t\t\t\t2019013001291920600_ref53","doi-asserted-by":"crossref","first-page":"2429","DOI":"10.1021\/ci9001102","article-title":"Finding key members in compound libraries by analyzing networks of molecules assembled by structural similarity","volume":"49","author":"Lepp","year":"2009","journal-title":"J. Chem. Inf. Model."},{"key":"key\n\t\t\t\t2019013001291920600_ref54","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1039\/c0md00148a","article-title":"Data-mining patent literature for novel chemical reagents for use in medicinal chemistry design","volume":"1","author":"Kettle","year":"2010","journal-title":"Med. Chem. Commun."},{"key":"key\n\t\t\t\t2019013001291920600_ref55","article-title":"BioCreative Virtual Issue","author":"Oxford Academic"},{"key":"key\n\t\t\t\t2019013001291920600_ref56","article-title":"Automatic identification of relevant chemical compounds from patents. The training corpus","author":"Akhondi","year":"2018","journal-title":"Mendeley Data"}],"container-title":["Database"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/database\/article-pdf\/doi\/10.1093\/database\/baz001\/27636778\/baz001.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,13]],"date-time":"2019-11-13T15:50:26Z","timestamp":1573660226000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/database\/article\/doi\/10.1093\/database\/baz001\/5301319"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1,1]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1093\/database\/baz001","relation":{},"ISSN":["1758-0463"],"issn-type":[{"value":"1758-0463","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019]]},"published":{"date-parts":[[2019,1,1]]}}}