{"id":"https://openalex.org/W2170876339","doi":"https://doi.org/10.1186/1758-2946-2-3","title":"Automatic vs. manual curation of a multi-source chemical dictionary: the impact on text mining","display_name":"Automatic vs. manual curation of a multi-source chemical dictionary: the impact on text mining","publication_year":2010,"publication_date":"2010-03-23","ids":{"openalex":"https://openalex.org/W2170876339","doi":"https://doi.org/10.1186/1758-2946-2-3","mag":"2170876339","pmid":"https://pubmed.ncbi.nlm.nih.gov/20331846"},"language":"en","primary_location":{"id":"doi:10.1186/1758-2946-2-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-2-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-2-3","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/counter/pdf/10.1186/1758-2946-2-3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029869005","display_name":"Kristina Hettne","orcid":"https://orcid.org/0000-0002-4182-7560"},"institutions":[{"id":"https://openalex.org/I2801952686","display_name":"Erasmus MC","ror":"https://ror.org/018906e22","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2801952686"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Kristina M Hettne","raw_affiliation_strings":["Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, The Netherlands. k.hettne@erasmusmc.nl","Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, The Netherlands. k.hettne@erasmusmc.nl","institution_ids":[]},{"raw_affiliation_string":"Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, The Netherlands","institution_ids":["https://openalex.org/I2801952686"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062051745","display_name":"Antony Williams","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antony J Williams","raw_affiliation_strings":["Royal Society of Chemistry, 904 Tamaras Circle, Wake Forest, NC, 27587, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Royal Society of Chemistry, 904 Tamaras Circle, Wake Forest, NC, 27587, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053857782","display_name":"Erik M. van Mulligen","orcid":"https://orcid.org/0000-0003-1377-9386"},"institutions":[{"id":"https://openalex.org/I2801952686","display_name":"Erasmus MC","ror":"https://ror.org/018906e22","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2801952686"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Erik M van Mulligen","raw_affiliation_strings":["Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, The Netherlands","institution_ids":["https://openalex.org/I2801952686"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111676146","display_name":"Jos Kleinjans","orcid":null},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jos Kleinjans","raw_affiliation_strings":["Department of Health Risk Analysis and Toxicology, Maastricht University, Maastricht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Health Risk Analysis and Toxicology, Maastricht University, Maastricht, The Netherlands","institution_ids":["https://openalex.org/I34352273"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112237087","display_name":"Valery Tkachenko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Valery Tkachenko","raw_affiliation_strings":["Royal Society of Chemistry, 904 Tamaras Circle, Wake Forest, NC, 27587, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Royal Society of Chemistry, 904 Tamaras Circle, Wake Forest, NC, 27587, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005077862","display_name":"Jan A. Kors","orcid":"https://orcid.org/0000-0002-4929-026X"},"institutions":[{"id":"https://openalex.org/I2801952686","display_name":"Erasmus MC","ror":"https://ror.org/018906e22","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2801952686"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jan A Kors","raw_affiliation_strings":["Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, The Netherlands","institution_ids":["https://openalex.org/I2801952686"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029869005"],"corresponding_institution_ids":["https://openalex.org/I2801952686"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":2.6848,"has_fulltext":true,"cited_by_count":56,"citation_normalized_percentile":{"value":0.90399767,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2","issue":"1","first_page":"3","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7178000211715698,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7178000211715698,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"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"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.23170000314712524,"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/T13297","display_name":"History and advancements in chemistry","score":0.007000000216066837,"subfield":{"id":"https://openalex.org/subfields/1606","display_name":"Physical and Theoretical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8089040517807007},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.6682443618774414},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.6326220035552979},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6047828197479248},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.5996781587600708},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5642923712730408},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.549789309501648},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5122038722038269},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4446978271007538},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.22500741481781006}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8089040517807007},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.6682443618774414},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.6326220035552979},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6047828197479248},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.5996781587600708},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5642923712730408},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.549789309501648},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5122038722038269},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4446978271007538},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.22500741481781006},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":12,"locations":[{"id":"doi:10.1186/1758-2946-2-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-2-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-2-3","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:20331846","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20331846","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:cris.maastrichtuniversity.nl:openaire/0da5191c-93dd-404f-8059-98d675f8468c","is_oa":true,"landing_page_url":"https://cris.maastrichtuniversity.nl/en/publications/0da5191c-93dd-404f-8059-98d675f8468c","pdf_url":null,"source":{"id":"https://openalex.org/S4306402616","display_name":"Research Publications (Maastricht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I34352273","host_organization_name":"Maastricht University","host_organization_lineage":["https://openalex.org/I34352273"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Hettne, K M, Williams, A J, van Mulligen, E M, Kleinjans, J C S, Tkachenko, V & Kors, J A 2010, 'Automatic vs. manual curation of a multi-source chemical dictionary: the impact on text mining', Journal of Cheminformatics, vol. 2, no. 1, 3. https://doi.org/10.1186/1758-2946-2-3","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:eur:oai:repub.eur.nl:33037","is_oa":true,"landing_page_url":"http://hdl.handle.net/1765/33037","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, 2(1)","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:f50865556b394cc88c32c3cd8076c5eb","is_oa":false,"landing_page_url":"https://doaj.org/article/f50865556b394cc88c32c3cd8076c5eb","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 2, Iss 1, p 3 (2010)","raw_type":"article"},{"id":"pmh:oai:figshare.com:article/653956","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Automatic_vs_manual_curation_of_a_multi_source_chemical_dictionary_the_impact_on_text_mining/653956","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"},{"id":"pmh:oai:openaccess.leidenuniv.nl:1887/78676","is_oa":false,"landing_page_url":"http://hdl.handle.net/1887/78676","pdf_url":null,"source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1186/1758-2946-2-3","raw_type":"Article / Letter to editor"},{"id":"pmh:oai:pubmedcentral.nih.gov:2848622","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2848622","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:pure.eur.nl:openaire_cris_publications/1920b3ae-a5bc-4081-8d6d-852f6aeace31","is_oa":true,"landing_page_url":"https://pure.eur.nl/en/publications/1920b3ae-a5bc-4081-8d6d-852f6aeace31","pdf_url":null,"source":{"id":"https://openalex.org/S4306401266","display_name":"EUR Research Repository (Erasmus University Rotterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I913958620","host_organization_name":"Erasmus University Rotterdam","host_organization_lineage":["https://openalex.org/I913958620"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hettne , K , Williams , AJ , van Mulligen , E , Kleinjans , J , Tkachenko , V &amp; Kors , J 2010 , ' Automatic vs. manual curation of a multi-source chemical dictionary: the impact on text mining ' , Journal of Cheminformatics , vol. 2 , no. 3 . https://doi.org/10.1186/1758-2946-2-4","raw_type":"article"},{"id":"pmh:oai:repub.eur.nl:33037","is_oa":true,"landing_page_url":"http://repub.eur.nl/pub/33037","pdf_url":null,"source":{"id":"https://openalex.org/S4377196287","display_name":"RePub (Erasmus University Rotterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I913958620","host_organization_name":"Erasmus University Rotterdam","host_organization_lineage":["https://openalex.org/I913958620"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics vol. 2 no. 1","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:scholarlypublications.universiteitleiden.nl:item_2973578","is_oa":false,"landing_page_url":"https://hdl.handle.net/1887/78676","pdf_url":null,"source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics","raw_type":"Article / Letter to editor"},{"id":"doi:10.6084/m9.figshare.653956.v1","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.653956.v1","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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"}],"best_oa_location":{"id":"doi:10.1186/1758-2946-2-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1758-2946-2-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/1758-2946-2-3","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":[],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320334893","display_name":"Stichting voor de Technische Wetenschappen","ror":"https://ror.org/057tq3593"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2170876339.pdf","grobid_xml":"https://content.openalex.org/works/W2170876339.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W77347155","https://openalex.org/W90362830","https://openalex.org/W103980920","https://openalex.org/W2009313526","https://openalex.org/W2023164253","https://openalex.org/W2032361183","https://openalex.org/W2033377040","https://openalex.org/W2053385401","https://openalex.org/W2070217628","https://openalex.org/W2087728643","https://openalex.org/W2095596879","https://openalex.org/W2096814387","https://openalex.org/W2113221321","https://openalex.org/W2121244856","https://openalex.org/W2122322270","https://openalex.org/W2127239015","https://openalex.org/W2138689719","https://openalex.org/W2140407633","https://openalex.org/W2152317795","https://openalex.org/W2159583324","https://openalex.org/W2165674132","https://openalex.org/W2522519459","https://openalex.org/W2977393556"],"related_works":["https://openalex.org/W2701062589","https://openalex.org/W4308914582","https://openalex.org/W4388126069","https://openalex.org/W2567393658","https://openalex.org/W3200944274","https://openalex.org/W4330338194","https://openalex.org/W2358294942","https://openalex.org/W4367460280","https://openalex.org/W4328049145","https://openalex.org/W2146486983"],"abstract_inverted_index":{"BACKGROUND:":[0],"Previously,":[1],"we":[2,41],"developed":[3],"a":[4,21,43,68,82,153,156,170,175,187,192,204,209,221,226,252,268,285],"combined":[5],"dictionary":[6,71,126,145,168,202,242,250,293],"dubbed":[7],"Chemlist":[8,141,161,201,249,292],"for":[9,139,271],"the":[10,101,125,135,140,158,180,214,237,244,248,256,273,277,291,308],"identification":[11,77],"of":[12,23,45,67,103,146,160,172,177,182,189,194,206,211,216,223,228],"small":[13],"molecules":[14],"and":[15,27,39,47,110,118,133,174,184,186,191,198,208,218,220,225,232,255,262,276,290],"drugs":[16],"in":[17,78,301],"text":[18],"based":[19],"on":[20,30,74,129,307],"number":[22,44],"publicly":[24],"available":[25,283,296],"databases":[26],"tested":[28,124],"it":[29,56],"an":[31,36,63,130,298],"annotated":[32,131],"corpus.":[33],"To":[34],"achieve":[35,267],"acceptable":[37],"recall":[38,176,193,210,227,254],"precision":[40,171,188,205,222,246,270],"used":[42],"automatic":[46],"semi-automatic":[48,115],"processing":[49],"steps":[50],"together":[51],"with":[52,137],"disambiguation":[53,119,185,219,263],"rules.":[54],"However,":[55],"remained":[57],"to":[58,155,266],"be":[59],"investigated":[60],"which":[61],"impact":[62],"extensive":[64,88],"manual":[65,89,116],"curation":[66,90],"multi-source":[69],"chemical":[70,75,83,95],"would":[72],"have":[73],"term":[76,113],"text.":[79],"ChemSpider":[80,104,128,144,167,241,281],"is":[81,264,282,294],"database":[84],"that":[85],"has":[86],"undergone":[87],"aimed":[91],"at":[92,162,288,310],"establishing":[93],"valid":[94],"name-to-structure":[96],"relationships.":[97],"RESULTS:":[98],"We":[99,123,235],"acquired":[100],"component":[102],"containing":[105],"only":[106,152],"manually":[107,278],"curated":[108,279],"names":[109,150],"synonyms.":[111],"Rule-based":[112,260],"filtering,":[114],"curation,":[117],"rules":[120],"were":[121],"applied.":[122],"from":[127],"corpus":[132],"compared":[134],"results":[136],"those":[138],"dictionary.":[142,280],"The":[143,166,200,240],"ca.":[147],"80":[148],"k":[149],"was":[151],"1/3":[154],"1/4":[157],"size":[159],"around":[163],"300":[164],"k.":[165],"had":[169,203,251],"0.43":[173],"0.19":[178,195],"before":[179,213],"application":[181,215],"filtering":[183,197,217,231,261],"0.87":[190],"after":[196,230],"disambiguation.":[199,233],"0.20":[207],"0.47":[212],"0.67":[224],"0.40":[229],"CONCLUSIONS:":[234],"conclude":[236],"following:":[238],"(1)":[239],"achieved":[243],"best":[245,257],"but":[247],"higher":[253],"F-score;":[258],"(2)":[259],"necessary":[265],"high":[269],"both":[272],"automatically":[274],"generated":[275],"as":[284,297],"web":[286,309],"service":[287],"http://www.chemspider.com/":[289],"freely":[295],"XML":[299],"file":[300],"Simple":[302],"Knowledge":[303],"Organization":[304],"System":[305],"format":[306],"http://www.biosemantics.org/chemlist.":[311]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
