{"id":"https://openalex.org/W4414751614","doi":"https://doi.org/10.1093/database/baaf063","title":"Characterization and automated classification of sentences in the biomedical literature: a case study for biocuration of gene expression and protein kinase activity","display_name":"Characterization and automated classification of sentences in the biomedical literature: a case study for biocuration of gene expression and protein kinase activity","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414751614","doi":"https://doi.org/10.1093/database/baaf063","pmid":"https://pubmed.ncbi.nlm.nih.gov/41026497"},"language":"en","primary_location":{"id":"doi:10.1093/database/baaf063","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baaf063","pdf_url":null,"source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/database/baaf063","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016040259","display_name":"Daniela Raciti","orcid":"https://orcid.org/0000-0002-4945-5837"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniela Raciti","raw_affiliation_strings":["Division of Biology and Biological Engineering, California Institute of Technology , 1200 E. California Boulevard, Pasadena, CA 91125 ,","Division of Biology and Biological Engineering, California Institute of Technology, 1200 E. California Boulevard, Pasadena, CA 91125, United States"],"raw_orcid":"https://orcid.org/0000-0002-4945-5837","affiliations":[{"raw_affiliation_string":"Division of Biology and Biological Engineering, California Institute of Technology , 1200 E. California Boulevard, Pasadena, CA 91125 ,","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"Division of Biology and Biological Engineering, California Institute of Technology, 1200 E. California Boulevard, Pasadena, CA 91125, United States","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034108611","display_name":"Kimberly Van Auken","orcid":"https://orcid.org/0000-0002-1706-4196"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kimberly M Van\u00a0Auken","raw_affiliation_strings":["Division of Biology and Biological Engineering, California Institute of Technology , 1200 E. California Boulevard, Pasadena, CA 91125 ,","Division of Biology and Biological Engineering, California Institute of Technology, 1200 E. California Boulevard, Pasadena, CA 91125, United States"],"raw_orcid":"https://orcid.org/0000-0002-1706-4196","affiliations":[{"raw_affiliation_string":"Division of Biology and Biological Engineering, California Institute of Technology , 1200 E. California Boulevard, Pasadena, CA 91125 ,","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"Division of Biology and Biological Engineering, California Institute of Technology, 1200 E. California Boulevard, Pasadena, CA 91125, United States","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004162519","display_name":"Valerio Arnaboldi","orcid":"https://orcid.org/0000-0002-2563-5374"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Valerio Arnaboldi","raw_affiliation_strings":["Division of Biology and Biological Engineering, California Institute of Technology , 1200 E. California Boulevard, Pasadena, CA 91125 ,","Division of Biology and Biological Engineering, California Institute of Technology, 1200 E. California Boulevard, Pasadena, CA 91125, United States"],"raw_orcid":"https://orcid.org/0000-0002-2563-5374","affiliations":[{"raw_affiliation_string":"Division of Biology and Biological Engineering, California Institute of Technology , 1200 E. California Boulevard, Pasadena, CA 91125 ,","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"Division of Biology and Biological Engineering, California Institute of Technology, 1200 E. California Boulevard, Pasadena, CA 91125, United States","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078040818","display_name":"Christopher J. Tabone","orcid":"https://orcid.org/0000-0001-8746-0680"},"institutions":[{"id":"https://openalex.org/I4210115256","display_name":"Jackson Laboratory","ror":"https://ror.org/021sy4w91","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210115256"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher J Tabone","raw_affiliation_strings":["The Jackson Laboratory , 600 Main Street, Bar Harbor, ME 04609 ,","The Jackson Laboratory, 600 Main Street, Bar Harbor, ME 04609, United States"],"raw_orcid":"https://orcid.org/0000-0001-8746-0680","affiliations":[{"raw_affiliation_string":"The Jackson Laboratory , 600 Main Street, Bar Harbor, ME 04609 ,","institution_ids":["https://openalex.org/I4210115256"]},{"raw_affiliation_string":"The Jackson Laboratory, 600 Main Street, Bar Harbor, ME 04609, United States","institution_ids":["https://openalex.org/I4210115256"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108594690","display_name":"Hans-Michael Muller","orcid":"https://orcid.org/0000-0003-1036-3051"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hans-Michael Muller","raw_affiliation_strings":["Division of Biology and Biological Engineering, California Institute of Technology , 1200 E. California Boulevard, Pasadena, CA 91125 ,","Division of Biology and Biological Engineering, California Institute of Technology, 1200 E. California Boulevard, Pasadena, CA 91125, United States"],"raw_orcid":"https://orcid.org/0000-0003-1036-3051","affiliations":[{"raw_affiliation_string":"Division of Biology and Biological Engineering, California Institute of Technology , 1200 E. California Boulevard, Pasadena, CA 91125 ,","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"Division of Biology and Biological Engineering, California Institute of Technology, 1200 E. California Boulevard, Pasadena, CA 91125, United States","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033624132","display_name":"Paul W. Sternberg","orcid":"https://orcid.org/0000-0002-7699-0173"},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul W Sternberg","raw_affiliation_strings":["Division of Biology and Biological Engineering, California Institute of Technology , 1200 E. California Boulevard, Pasadena, CA 91125 ,","Division of Biology and Biological Engineering, California Institute of Technology, 1200 E. California Boulevard, Pasadena, CA 91125, United States"],"raw_orcid":"https://orcid.org/0000-0002-7699-0173","affiliations":[{"raw_affiliation_string":"Division of Biology and Biological Engineering, California Institute of Technology , 1200 E. California Boulevard, Pasadena, CA 91125 ,","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"Division of Biology and Biological Engineering, California Institute of Technology, 1200 E. California Boulevard, Pasadena, CA 91125, United States","institution_ids":["https://openalex.org/I122411786"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1415,"currency":"GBP","value_usd":1735},"fwci":1.4604,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82909867,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"2025","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9871000051498413,"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":0.9871000051498413,"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/annotation","display_name":"Annotation","score":0.7360000014305115},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5936999917030334},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.48420000076293945},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.3767000138759613},{"id":"https://openalex.org/keywords/gene-annotation","display_name":"Gene Annotation","score":0.37209999561309814},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.3720000088214874},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.3573000133037567},{"id":"https://openalex.org/keywords/biological-database","display_name":"Biological database","score":0.3564000129699707}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7360000014305115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6621000170707703},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5936999917030334},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4555000066757202},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41280001401901245},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3995000123977661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3817000091075897},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.37209999561309814},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.3573000133037567},{"id":"https://openalex.org/C20901353","wikidata":"https://www.wikidata.org/wiki/Q4117139","display_name":"Biological database","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.33970001339912415},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3246999979019165},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C6856738","wikidata":"https://www.wikidata.org/wiki/Q331672","display_name":"Protein expression","level":3,"score":0.27459999918937683},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.26100000739097595},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.25699999928474426},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.25380000472068787}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000096104","descriptor_name":"Biocuration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000096104","descriptor_name":"Biocuration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000096104","descriptor_name":"Biocuration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000096104","descriptor_name":"Biocuration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000096104","descriptor_name":"Biocuration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000096104","descriptor_name":"Biocuration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000096104","descriptor_name":"Biocuration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000096104","descriptor_name":"Biocuration","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D015870","descriptor_name":"Gene Expression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015870","descriptor_name":"Gene Expression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015870","descriptor_name":"Gene Expression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015870","descriptor_name":"Gene Expression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015870","descriptor_name":"Gene Expression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015870","descriptor_name":"Gene Expression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015870","descriptor_name":"Gene Expression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015870","descriptor_name":"Gene Expression","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/database/baaf063","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baaf063","pdf_url":null,"source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},{"id":"pmid:41026497","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41026497","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":"Database : the journal of biological databases and curation","raw_type":null},{"id":"pmh:oai:europepmc.org:11293723","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12482909","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:12482909","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12482909/","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":"Database (Oxford)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/database/baaf063","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baaf063","pdf_url":null,"source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1276305942","display_name":null,"funder_award_id":"P41 HG002223","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G2006294599","display_name":null,"funder_award_id":"U24HG002223","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2463583488","display_name":null,"funder_award_id":"U41HG000739","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3236890151","display_name":null,"funder_award_id":"U41 HG000739","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G3450862538","display_name":null,"funder_award_id":"U24HG010859","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G3978529930","display_name":null,"funder_award_id":"U24 HG010859","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G5645381697","display_name":null,"funder_award_id":"R01 LM013871","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G620664340","display_name":null,"funder_award_id":"U24 HG002223","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W2041053370","https://openalex.org/W2071925258","https://openalex.org/W2102983252","https://openalex.org/W2104544690","https://openalex.org/W2107141268","https://openalex.org/W2107728961","https://openalex.org/W2112227057","https://openalex.org/W2115150863","https://openalex.org/W2120421225","https://openalex.org/W2137273296","https://openalex.org/W2146486983","https://openalex.org/W2148008364","https://openalex.org/W2204108528","https://openalex.org/W2295598076","https://openalex.org/W2302501749","https://openalex.org/W2470529639","https://openalex.org/W2509885322","https://openalex.org/W2810729566","https://openalex.org/W2884443195","https://openalex.org/W2889326414","https://openalex.org/W2896016608","https://openalex.org/W2906230340","https://openalex.org/W2906406865","https://openalex.org/W2911489562","https://openalex.org/W2916913049","https://openalex.org/W2937423263","https://openalex.org/W2944400536","https://openalex.org/W2963341956","https://openalex.org/W2973232653","https://openalex.org/W2996758863","https://openalex.org/W3012427063","https://openalex.org/W3023019135","https://openalex.org/W3023417367","https://openalex.org/W3105750359","https://openalex.org/W3128288937","https://openalex.org/W3179500067","https://openalex.org/W3203751410","https://openalex.org/W3208185324","https://openalex.org/W4200139355","https://openalex.org/W4206446428","https://openalex.org/W4223916509","https://openalex.org/W4244393794","https://openalex.org/W4327810158","https://openalex.org/W4393306739","https://openalex.org/W4393936594","https://openalex.org/W4393950665"],"related_works":[],"abstract_inverted_index":{"Biological":[0],"knowledgebases":[1],"are":[2,36],"essential":[3],"resources":[4],"for":[5,55,88],"biomedical":[6,229],"researchers,":[7],"providing":[8],"ready":[9],"access":[10],"to":[11,44,84,111,133,167,174,181],"gene":[12,57,61],"function":[13,58],"and":[14,25,63,80,98,114,118,144,214,224],"genomic":[15],"data.":[16],"Professional,":[17],"manual":[18],"curation":[19,218],"of":[20,52,72,155,165,171,190,211,227],"knowledgebases,":[21],"however,":[22],"is":[23],"labour-intensive":[24],"thus":[26],"high-performing":[27],"machine":[28],"learning":[29],"(ML)":[30],"methods":[31],"that":[32,116,149,159],"improve":[33],"biocuration":[34,183,202],"efficiency":[35],"needed.":[37],"Here,":[38],"we":[39],"report":[40],"on":[41,153],"sentence-level":[42],"classification":[43,154],"identify":[45],"biocuration-relevant":[46,192],"sentences":[47,73,90,158,193],"in":[48,76,126],"the":[49,77,121,137,188,209,215,228],"full":[50,195],"text":[51],"published":[53],"references":[54,75],"two":[56],"data":[59,176],"types:":[60],"expression":[62],"protein":[64],"kinase":[65],"activity.":[66],"We":[67,105],"performed":[68],"a":[69,161,178],"detailed":[70],"characterization":[71,83],"from":[74,131,194],"WormBase":[78],"bibliography":[79],"used":[81,207],"this":[82,172],"define":[85],"three":[86],"tasks":[87,113],"classifying":[89],"as":[91,205],"either":[92],"(i)":[93],"fully":[94,97],"curatable,":[95,100],"(ii)":[96],"partially":[99],"or":[101],"(iii)":[102],"all":[103],"language-related.":[104],"evaluated":[106],"various":[107],"ML":[108],"models":[109,199],"applied":[110],"these":[112,198],"found":[115],"GPT":[117],"BioBERT":[119],"achieve":[120],"highest":[122],"average":[123],"performance,":[124],"resulting":[125],"F1":[127],"performance":[128],"scores":[129],"ranging":[130],"0.89":[132],"0.99":[134],"depending":[135],"upon":[136],"task.":[138],"Moreover,":[139],"our":[140],"inter-annotator":[141],"agreement":[142],"analyses":[143],"curator":[145],"timing":[146],"exercises":[147],"demonstrated":[148],"curators":[150],"readily":[151],"converged":[152],"high-quality":[156],"training":[157],"take":[160],"relatively":[162],"short":[163],"period":[164],"time":[166],"collect,":[168],"making":[169],"expansion":[170],"approach":[173],"other":[175],"types":[177],"realistic":[179],"addition":[180],"existing":[182],"workflows.":[184],"Our":[185],"findings":[186],"demonstrate":[187],"feasibility":[189],"extracting":[191],"text.":[196],"Integrating":[197],"into":[200],"professional":[201],"workflows,":[203],"such":[204],"those":[206],"by":[208],"Alliance":[210],"Genome":[212],"Resources":[213],"ACKnowledge":[216],"community":[217],"platform,":[219],"might":[220],"well":[221],"facilitate":[222],"efficient":[223],"accurate":[225],"annotation":[226],"literature.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
