{"id":"https://openalex.org/W3082081167","doi":"https://doi.org/10.1186/s13321-020-00456-1","title":"An open source chemical structure curation pipeline using RDKit","display_name":"An open source chemical structure curation pipeline using RDKit","publication_year":2020,"publication_date":"2020-08-31","ids":{"openalex":"https://openalex.org/W3082081167","doi":"https://doi.org/10.1186/s13321-020-00456-1","mag":"3082081167","pmid":"https://pubmed.ncbi.nlm.nih.gov/33431044"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-020-00456-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-020-00456-1","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-020-00456-1","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-020-00456-1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076510996","display_name":"A. Patr\u00edcia Bento","orcid":"https://orcid.org/0000-0003-1424-480X"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"A. Patr\u00edcia Bento","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK"],"raw_orcid":"https://orcid.org/0000-0003-1424-480X","affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003544163","display_name":"Anne Hersey","orcid":"https://orcid.org/0000-0003-4679-6211"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anne Hersey","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023616305","display_name":"Eloy F\u00e9lix","orcid":"https://orcid.org/0000-0002-5512-6810"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eloy F\u00e9lix","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056808182","display_name":"Gregory A. Landrum","orcid":"https://orcid.org/0000-0001-6279-4481"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Greg Landrum","raw_affiliation_strings":["T5 Informatics GmbH, Basel, 4055, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"T5 Informatics GmbH, Basel, 4055, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050930900","display_name":"Anna Gaulton","orcid":"https://orcid.org/0000-0003-2634-7400"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anna Gaulton","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007659406","display_name":"Francis Atkinson","orcid":"https://orcid.org/0000-0003-4688-959X"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I4210098980","display_name":"Cambridge Crystallographic Data Centre","ror":"https://ror.org/00zbfm828","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210098980"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Francis Atkinson","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK","The Cambridge Crystallographic Data Centre, 12 Union Road, Cambridge, CB2 1EZ, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK","institution_ids":["https://openalex.org/I1303153112"]},{"raw_affiliation_string":"The Cambridge Crystallographic Data Centre, 12 Union Road, Cambridge, CB2 1EZ, UK","institution_ids":["https://openalex.org/I4210098980"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021944314","display_name":"Louisa J. Bellis","orcid":"https://orcid.org/0000-0001-9581-870X"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Louisa J. Bellis","raw_affiliation_strings":["Department of Oncology, University of Cambridge, Cambridge, UK","European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Oncology, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073856092","display_name":"Marleen De Veij","orcid":"https://orcid.org/0000-0003-2587-8752"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marleen De Veij","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036729806","display_name":"Andrew R. Leach","orcid":"https://orcid.org/0000-0001-8178-0253"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew R. Leach","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK. arl@ebi.ac.uk","European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK. arl@ebi.ac.uk","institution_ids":["https://openalex.org/I1303153112"]},{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, CB10 1SD, Cambridgeshire, UK","institution_ids":["https://openalex.org/I1303153112"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5076510996"],"corresponding_institution_ids":["https://openalex.org/I1303153112"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":27.3814,"has_fulltext":true,"cited_by_count":672,"citation_normalized_percentile":{"value":0.99719645,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"12","issue":"1","first_page":"51","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.6486999988555908,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.6486999988555908,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10252","display_name":"Microbial Natural Products and Biosynthesis","score":0.07639999687671661,"subfield":{"id":"https://openalex.org/subfields/2736","display_name":"Pharmacology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13971","display_name":"Synthesis and Biological Activity","score":0.014600000344216824,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6979510188102722},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6773931384086609},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.5912817120552063},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5454384684562683},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5019471645355225},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.40346449613571167},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3873664140701294},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.20771726965904236},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1352849304676056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6979510188102722},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6773931384086609},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.5912817120552063},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5454384684562683},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5019471645355225},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.40346449613571167},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3873664140701294},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.20771726965904236},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1352849304676056}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1186/s13321-020-00456-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-020-00456-1","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-020-00456-1","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:33431044","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33431044","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of cheminformatics","raw_type":null},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/327433","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/327433","pdf_url":"https://www.repository.cam.ac.uk/handle/1810/327433","source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:bbbf7ee22f154d9a97199854b9ea5039","is_oa":true,"landing_page_url":"https://doaj.org/article/bbbf7ee22f154d9a97199854b9ea5039","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 12, Iss 1, Pp 1-16 (2020)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:7458899","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7458899","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/309800","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/309800","pdf_url":null,"source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.17863/cam.56899","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.56899","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.17863/cam.74885","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.74885","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1186/s13321-020-00456-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-020-00456-1","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-020-00456-1","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1211227482","display_name":null,"funder_award_id":"WT104104/Z/14/Z","funder_id":"https://openalex.org/F4320307874","funder_display_name":"Wellcome"},{"id":"https://openalex.org/G2083160379","display_name":null,"funder_award_id":"WT086151/Z/08/Z","funder_id":"https://openalex.org/F4320307874","funder_display_name":"Wellcome"},{"id":"https://openalex.org/G5814704786","display_name":null,"funder_award_id":"WT104104/Z/14/Z","funder_id":"https://openalex.org/F4320314023","funder_display_name":"European Molecular Biology Laboratory"},{"id":"https://openalex.org/G7498243579","display_name":null,"funder_award_id":"WT086151/Z/08/Z","funder_id":"https://openalex.org/F4320314023","funder_display_name":"European Molecular Biology Laboratory"}],"funders":[{"id":"https://openalex.org/F4320307874","display_name":"Wellcome","ror":"https://ror.org/029chgv08"},{"id":"https://openalex.org/F4320311904","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08"},{"id":"https://openalex.org/F4320314023","display_name":"European Molecular Biology Laboratory","ror":"https://ror.org/050589e39"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3082081167.pdf","grobid_xml":"https://content.openalex.org/works/W3082081167.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W959778778","https://openalex.org/W1508604947","https://openalex.org/W1546956326","https://openalex.org/W1975147762","https://openalex.org/W2016455326","https://openalex.org/W2051810242","https://openalex.org/W2087563523","https://openalex.org/W2116238734","https://openalex.org/W2132289924","https://openalex.org/W2169678694","https://openalex.org/W2204695023","https://openalex.org/W2761529199","https://openalex.org/W2769853272","https://openalex.org/W2789003308","https://openalex.org/W2802412060","https://openalex.org/W2807636208","https://openalex.org/W2844076759","https://openalex.org/W2887459817","https://openalex.org/W2899070097","https://openalex.org/W2900090807","https://openalex.org/W2955167367"],"related_works":["https://openalex.org/W2701062589","https://openalex.org/W4308914582","https://openalex.org/W4388126069","https://openalex.org/W2567393658","https://openalex.org/W2995122411","https://openalex.org/W2736466919","https://openalex.org/W4306317641","https://openalex.org/W1488337274","https://openalex.org/W4287611188","https://openalex.org/W2216178707"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,193],"ChEMBL":[2,143,209,226],"database":[3,43,67,144,166,227],"is":[4,59,195],"one":[5],"of":[6,9,40,96,141,157,173],"a":[7,90,104,116,198],"number":[8],"public":[10],"databases":[11],"that":[12,119,245],"contain":[13],"bioactivity":[14],"data":[15,50],"on":[16,51],"small":[17],"molecule":[18],"compounds":[19,25,108,223,238],"curated":[20],"from":[21,55,125,150],"diverse":[22],"sources.":[23],"Incoming":[24],"are":[26],"typically":[27],"not":[28],"standardised":[29],"according":[30,109],"to":[31,36,45,68,92,110,128,137,153,161,185,217,236],"consistent":[32],"rules.":[33],"In":[34],"order":[35],"maintain":[37],"the":[38,41,52,62,66,81,94,126,138,142,155,158,171,174,208,219,225,229,240],"quality":[39],"final":[42],"and":[44,48,99,113,115,123,160,187,201,228],"easily":[46],"compare":[47],"integrate":[49],"same":[53],"compound":[54,127,230],"different":[56],"sources":[57,152],"it":[58,202],"necessary":[60],"for":[61,182,189,250],"chemical":[63,74,97],"structures":[64,98],"in":[65,165,197,224],"be":[69,205,248],"appropriately":[70],"standardised.":[71],"RESULTS:":[72],"A":[73],"curation":[75],"pipeline":[76,133,176],"has":[77,134,213,233],"been":[78,135,178,214,234],"developed":[79],"using":[80],"open":[82],"source":[83],"toolkit":[84],"RDKit.":[85],"It":[86,212],"comprises":[87],"three":[88],"components:":[89],"Checker":[91],"test":[93,154],"validity":[95,231],"flag":[100],"any":[101,121],"serious":[102,242],"errors;":[103],"Standardizer":[105],"which":[106],"formats":[107],"defined":[111],"rules":[112],"conventions":[114],"GetParent":[117],"component":[118],"removes":[120],"salts":[122],"solvents":[124],"create":[129],"its":[130],"parent.":[131],"This":[132],"applied":[136],"latest":[139],"version":[140],"as":[145,147],"well":[146],"uncurated":[148],"datasets":[149],"other":[151,183],"robustness":[156],"process":[159],"identify":[162,237],"common":[163],"issues":[164,243],"molecular":[167],"structures.":[168],"CONCLUSION:":[169],"All":[170],"components":[172],"structure":[175],"have":[177],"made":[179],"freely":[180],"available":[181,196],"researchers":[184],"use":[186],"adapt":[188],"their":[190],"own":[191],"use.":[192],"code":[194],"GitHub":[199],"repository":[200],"can":[203,247],"also":[204],"accessed":[206],"via":[207],"Beaker":[210],"webservices.":[211],"used":[215,235],"successfully":[216],"standardise":[218],"nearly":[220],"2":[221],"million":[222],"checker":[232],"with":[239],"most":[241],"so":[244],"they":[246],"prioritised":[249],"manual":[251],"curation.":[252]},"counts_by_year":[{"year":2026,"cited_by_count":87},{"year":2025,"cited_by_count":238},{"year":2024,"cited_by_count":159},{"year":2023,"cited_by_count":97},{"year":2022,"cited_by_count":41},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":12}],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2025-10-10T00:00:00"}
