{"id":"https://openalex.org/W2915895751","doi":"https://doi.org/10.1093/bioinformatics/btz070","title":"PMC text mining subset in BioC: about three million full-text articles and growing","display_name":"PMC text mining subset in BioC: about three million full-text articles and growing","publication_year":2019,"publication_date":"2019-01-29","ids":{"openalex":"https://openalex.org/W2915895751","doi":"https://doi.org/10.1093/bioinformatics/btz070","mag":"2915895751","pmid":"https://pubmed.ncbi.nlm.nih.gov/30715220"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btz070","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz070","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/18/3533/48975610/bioinformatics_35_18_3533.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/35/18/3533/48975610/bioinformatics_35_18_3533.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031842571","display_name":"Donald C. Comeau","orcid":"https://orcid.org/0000-0002-9373-530X"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donald C Comeau","raw_affiliation_strings":["National Center for Biotechnology Information (NCBI), U.S. Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information (NCBI), U.S. Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058918482","display_name":"Chih-Hsuan Wei","orcid":"https://orcid.org/0000-0001-5094-7321"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chih-Hsuan Wei","raw_affiliation_strings":["National Center for Biotechnology Information (NCBI), U.S. Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information (NCBI), U.S. Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008126200","display_name":"Rezarta Islamaj","orcid":"https://orcid.org/0000-0001-5651-1860"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rezarta Islamaj Do\u011fan","raw_affiliation_strings":["National Center for Biotechnology Information (NCBI), U.S. Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information (NCBI), U.S. Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083081872","display_name":"Zhiyong Lu","orcid":"https://orcid.org/0000-0001-9998-916X"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhiyong Lu","raw_affiliation_strings":["National Center for Biotechnology Information (NCBI), U.S. Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information (NCBI), U.S. Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083081872"],"corresponding_institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":3.5799,"has_fulltext":true,"cited_by_count":86,"citation_normalized_percentile":{"value":0.93865392,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"35","issue":"18","first_page":"3533","last_page":"3535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9990000128746033,"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":0.9990000128746033,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9726999998092651,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9682000279426575,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6152594089508057},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.46206340193748474},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46197688579559326},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.45064103603363037},{"id":"https://openalex.org/keywords/text-messaging","display_name":"Text messaging","score":0.44773098826408386},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.42225033044815063},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34368154406547546},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.30669939517974854},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13343021273612976}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6152594089508057},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.46206340193748474},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46197688579559326},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.45064103603363037},{"id":"https://openalex.org/C3018949938","wikidata":"https://www.wikidata.org/wiki/Q17166101","display_name":"Text messaging","level":2,"score":0.44773098826408386},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.42225033044815063},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34368154406547546},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30669939517974854},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13343021273612976},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035843","descriptor_name":"Biomedical Research","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035843","descriptor_name":"Biomedical Research","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035843","descriptor_name":"Biomedical Research","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btz070","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz070","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/18/3533/48975610/bioinformatics_35_18_3533.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:30715220","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30715220","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:6748740","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6748740","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btz070","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz070","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/18/3533/48975610/bioinformatics_35_18_3533.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2915895751.pdf","grobid_xml":"https://content.openalex.org/works/W2915895751.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1874869336","https://openalex.org/W2031966872","https://openalex.org/W2040298461","https://openalex.org/W2071925258","https://openalex.org/W2098068971","https://openalex.org/W2104148262","https://openalex.org/W2115150863","https://openalex.org/W2117123654","https://openalex.org/W2121157913","https://openalex.org/W2127546476","https://openalex.org/W2155690268","https://openalex.org/W2252278859","https://openalex.org/W2573117738","https://openalex.org/W2786693834","https://openalex.org/W2952465807","https://openalex.org/W2952755768","https://openalex.org/W6691644754"],"related_works":["https://openalex.org/W2336574202","https://openalex.org/W1647149388","https://openalex.org/W2796209226","https://openalex.org/W1797055419","https://openalex.org/W3029039898","https://openalex.org/W3109393126","https://openalex.org/W345154246","https://openalex.org/W2606713739","https://openalex.org/W2980254430","https://openalex.org/W2288055910"],"abstract_inverted_index":{"https://www.ncbi.nlm.nih.gov/research/bionlp/APIs/BioC-PMC/.":[0]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
