{"id":"https://openalex.org/W2146486983","doi":"https://doi.org/10.1186/1471-2105-10-228","title":"Semi-automated curation of protein subcellular localization: a text mining-based approach to Gene Ontology (GO) Cellular Component curation","display_name":"Semi-automated curation of protein subcellular localization: a text mining-based approach to Gene Ontology (GO) Cellular Component curation","publication_year":2009,"publication_date":"2009-07-21","ids":{"openalex":"https://openalex.org/W2146486983","doi":"https://doi.org/10.1186/1471-2105-10-228","mag":"2146486983","pmid":"https://pubmed.ncbi.nlm.nih.gov/19622167"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-10-228","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-228","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-228","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-228","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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 Van Auken","raw_affiliation_strings":["Division of Biology, California Institute of Technology, Pasadena, CA 91125, USA. vanauken@caltech.edu","Division of Biology, California Institute of Technology, Pasadena, CA, 91125, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Biology, California Institute of Technology, Pasadena, CA 91125, USA. vanauken@caltech.edu","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"Division of Biology, California Institute of Technology, Pasadena, CA, 91125, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091357283","display_name":"Joshua Jaffery","orcid":null},"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"]},{"id":"https://openalex.org/I1328614147","display_name":"California Department of Transportation","ror":"https://ror.org/04d46jp54","country_code":"US","type":"government","lineage":["https://openalex.org/I1328614147","https://openalex.org/I4389425283"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua Jaffery","raw_affiliation_strings":["California Department of Transportation, San Bernardino, California, 92401, USA","Division of Biology, California Institute of Technology, Pasadena, CA, 91125, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Department of Transportation, San Bernardino, California, 92401, USA","institution_ids":["https://openalex.org/I1328614147"]},{"raw_affiliation_string":"Division of Biology, California Institute of Technology, Pasadena, CA, 91125, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111902938","display_name":"Juancarlos Chan","orcid":"https://orcid.org/0000-0002-7259-8107"},"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":"Juancarlos Chan","raw_affiliation_strings":["Division of Biology, California Institute of Technology, Pasadena, CA, 91125, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Biology, California Institute of Technology, Pasadena, CA, 91125, USA","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063280401","display_name":"Hans\u2010Michael M\u00fcller","orcid":"https://orcid.org/0000-0002-2384-7285"},"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 M\u00fcller","raw_affiliation_strings":["Division of Biology, California Institute of Technology, Pasadena, CA, 91125, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Biology, California Institute of Technology, Pasadena, CA, 91125, USA","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"]},{"id":"https://openalex.org/I1344073410","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90","country_code":"US","type":"facility","lineage":["https://openalex.org/I1344073410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Paul W Sternberg","raw_affiliation_strings":["Division of Biology, California Institute of Technology, Pasadena, CA, 91125, USA","Howard Hughes Medical Institute and Division of Biology, California Institute of Technology, Pasadena, CA, 91125, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Biology, California Institute of Technology, Pasadena, CA, 91125, USA","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"Howard Hughes Medical Institute and Division of Biology, California Institute of Technology, Pasadena, CA, 91125, USA","institution_ids":["https://openalex.org/I122411786","https://openalex.org/I1344073410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033624132"],"corresponding_institution_ids":["https://openalex.org/I122411786","https://openalex.org/I1344073410"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":3.1479,"has_fulltext":true,"cited_by_count":61,"citation_normalized_percentile":{"value":0.92444538,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"10","issue":"1","first_page":"228","last_page":"228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9447000026702881,"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":0.9447000026702881,"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":0.019899999722838402,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.005799999926239252,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/data-curation","display_name":"Data curation","score":0.8227007985115051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7337355017662048},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.6634066104888916},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6524503231048584},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.626343846321106},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.5815395712852478},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5407242178916931},{"id":"https://openalex.org/keywords/gene-ontology","display_name":"Gene ontology","score":0.5156970620155334},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4587022066116333},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4554339349269867},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"Biomedical text mining","score":0.4516793489456177},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4418475031852722},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.41014543175697327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34258463978767395},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3288657069206238},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2594897747039795},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.20127025246620178},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.17866477370262146}],"concepts":[{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.8227007985115051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7337355017662048},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.6634066104888916},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6524503231048584},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.626343846321106},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.5815395712852478},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5407242178916931},{"id":"https://openalex.org/C2987395477","wikidata":"https://www.wikidata.org/wiki/Q135085","display_name":"Gene ontology","level":4,"score":0.5156970620155334},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4587022066116333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4554339349269867},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.4516793489456177},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4418475031852722},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.41014543175697327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34258463978767395},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3288657069206238},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2594897747039795},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.20127025246620178},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.17866477370262146},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/1471-2105-10-228","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-228","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-228","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:19622167","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19622167","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:authors.library.caltech.edu:15819","is_oa":true,"landing_page_url":"https://authors.library.caltech.edu/15819/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402161","display_name":"CaltechAUTHORS (California Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122411786","host_organization_name":"California Institute of Technology","host_organization_lineage":["https://openalex.org/I122411786"],"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":"Article"},{"id":"pmh:oai:doaj.org/article:9902acce6fb24775b2bf43bf878fe3f0","is_oa":false,"landing_page_url":"https://doaj.org/article/9902acce6fb24775b2bf43bf878fe3f0","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":"BMC Bioinformatics, Vol 10, Iss 1, p 228 (2009)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2719631","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2719631","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":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-10-228","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-228","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-228","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"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/G41881309","display_name":null,"funder_award_id":"P41-HG02223","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G5170952278","display_name":null,"funder_award_id":"P41 HG002273","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G5985279535","display_name":null,"funder_award_id":"R01 HG004090","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G6289400939","display_name":null,"funder_award_id":"R01-HG004090","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G895186580","display_name":null,"funder_award_id":"P41-HG02273","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320306082","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90"},{"id":"https://openalex.org/F4320309292","display_name":"Princeton University","ror":"https://ror.org/00hx57361"},{"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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2146486983.pdf","grobid_xml":"https://content.openalex.org/works/W2146486983.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W626692","https://openalex.org/W1574901103","https://openalex.org/W1818881584","https://openalex.org/W1981348283","https://openalex.org/W1985904552","https://openalex.org/W2012950009","https://openalex.org/W2039235696","https://openalex.org/W2042500831","https://openalex.org/W2053673723","https://openalex.org/W2056119436","https://openalex.org/W2061193761","https://openalex.org/W2065589669","https://openalex.org/W2103017472","https://openalex.org/W2103907281","https://openalex.org/W2106093878","https://openalex.org/W2109711517","https://openalex.org/W2117663476","https://openalex.org/W2142562562","https://openalex.org/W2145258036","https://openalex.org/W2148130205","https://openalex.org/W2148331745","https://openalex.org/W2151296343","https://openalex.org/W2158789585","https://openalex.org/W2167289895","https://openalex.org/W2170526618","https://openalex.org/W2276605232","https://openalex.org/W4231056502","https://openalex.org/W6824033132"],"related_works":["https://openalex.org/W3185751515","https://openalex.org/W1479703980","https://openalex.org/W2146486983","https://openalex.org/W2539274330","https://openalex.org/W1553529581","https://openalex.org/W4206039273","https://openalex.org/W2749535755","https://openalex.org/W4232119327","https://openalex.org/W2911489562","https://openalex.org/W2134429551"],"abstract_inverted_index":{"BACKGROUND:":[0],"Manual":[1],"curation":[2,26,54,114,141,252,262,300,312,328],"of":[3,98,103,130,139,144,152,160,168,188,194,213,218,229,242,248,290,313,322,327],"experimental":[4],"data":[5,28,315],"from":[6,43,158,309],"the":[7,44,59,77,88,107,137,149,161,166,245,258,288],"biomedical":[8],"literature":[9,45],"is":[10,282],"an":[11,283,334],"expensive":[12],"and":[13,30,64,121,125,175,185,190,210,215,268],"time-consuming":[14],"endeavor.":[15],"Nevertheless,":[16],"most":[17],"biological":[18],"knowledge":[19],"bases":[20],"still":[21],"rely":[22,341],"heavily":[23,342],"on":[24,343],"manual":[25,53,140,199,251,311,344],"for":[27,154,286,337],"extraction":[29,65],"entry.":[31],"Text":[32],"mining":[33],"software":[34],"that":[35,100,143,147,177,255,340],"can":[36],"semi-":[37],"or":[38],"fully":[39],"automate":[40],"information":[41,62],"retrieval":[42,63],"would":[46],"thus":[47],"provide":[48,333],"a":[49,95,169,296,318],"significant":[50],"boost":[51],"to":[52,71,87,142,198,226,260,307,317],"efforts.":[55],"RESULTS:":[56],"We":[57,135],"employ":[58],"Textpresso":[60,74,145,178,204,256,281,330],"category-based":[61],"system":[66],"(http://www.textpresso.org),":[67],"developed":[68],"by":[69,264],"WormBase":[70,303],"explore":[72],"how":[73],"might":[75],"improve":[76],"efficiency":[78,263,289],"with":[79,128,183,208,238],"which":[80],"we":[81,110,253],"manually":[82],"curate":[83],"C.":[84,172],"elegans":[85,173],"proteins":[86],"Gene":[89],"Ontology's":[90],"Cellular":[91,235,298],"Component":[92,236,299],"Ontology.":[93],"Using":[94],"training":[96],"set":[97],"sentences":[99,155,207],"describe":[101],"results":[102,138],"localization":[104],"experiments":[105],"in":[106,276],"published":[108],"literature,":[109],"generated":[111],"three":[112,162],"new":[113,163],"task-specific":[115,329],"categories":[116,164,331],"(Cellular":[117],"Components,":[118],"Assay":[119],"Terms,":[120],"Verbs)":[122],"containing":[123,156],"words":[124],"phrases":[126],"associated":[127],"reports":[129],"experimentally":[131,232,292],"determined":[132],"subcellular":[133],"localization.":[134],"compared":[136,197],"queries":[146],"searched":[148],"full":[150],"text":[151],"articles":[153],"terms":[157],"each":[159],"plus":[165],"name":[167],"previously":[170],"uncurated":[171],"protein,":[174],"found":[176],"searches":[179],"identified":[180,205],"curatable":[181],"papers":[182],"recall":[184,209],"precision":[186,211,240],"rates":[187,212],"79.1%":[189],"61.8%,":[191],"respectively":[192],"(F-score":[193,217,241],"69.5%),":[195],"when":[196],"curation.":[200,294,345],"Within":[201],"those":[202],"documents,":[203],"relevant":[206],"30.3%":[214],"80.1%":[216],"44.0%).":[219],"From":[220],"returned":[221],"sentences,":[222],"curators":[223],"were":[224],"able":[225],"make":[227],"66.2%":[228],"all":[230],"possible":[231],"supported":[233],"GO":[234],"annotations":[237],"97.3%":[239],"78.8%).":[243],"Measuring":[244],"relative":[246],"efficiencies":[247],"Textpresso-based":[249,297],"versus":[250],"find":[254],"has":[257,304],"potential":[259],"increase":[261],"at":[265,302],"least":[266],"8-fold,":[267],"perhaps":[269],"as":[270,272],"much":[271],"15-fold,":[273],"given":[274],"differences":[275],"individual":[277],"curatorial":[278],"speed.":[279],"CONCLUSION:":[280],"effective":[284],"tool":[285],"improving":[287],"manual,":[291],"based":[293],"Incorporating":[295],"pipeline":[301,321],"allowed":[305],"us":[306],"transition":[308],"strictly":[310],"this":[314],"type":[316],"more":[319],"efficient":[320],"computer-assisted":[323],"validation.":[324],"Continued":[325],"development":[326],"will":[332],"invaluable":[335],"resource":[336],"genomics":[338],"databases":[339]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":15}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
