{"id":"https://openalex.org/W4402919780","doi":"https://doi.org/10.1093/database/baae093","title":"Automated annotation of scientific texts for ML-based keyphrase extraction and validation","display_name":"Automated annotation of scientific texts for ML-based keyphrase extraction and validation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402919780","doi":"https://doi.org/10.1093/database/baae093","pmid":"https://pubmed.ncbi.nlm.nih.gov/39331731"},"language":"en","primary_location":{"id":"doi:10.1093/database/baae093","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baae093","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baae093/59376480/baae093.pdf","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://academic.oup.com/database/article-pdf/doi/10.1093/database/baae093/59376480/baae093.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047606322","display_name":"Oluwamayowa Amusat","orcid":"https://orcid.org/0000-0002-4569-5729"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Oluwamayowa O Amusat","raw_affiliation_strings":["Scientific Data Division, Lawrence Berkeley National Laboratory , 1 Cyclotron road, Berkeley, CA 94720,"],"raw_orcid":"https://orcid.org/0000-0002-4569-5729","affiliations":[{"raw_affiliation_string":"Scientific Data Division, Lawrence Berkeley National Laboratory , 1 Cyclotron road, Berkeley, CA 94720,","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057750338","display_name":"Harshad Hegde","orcid":"https://orcid.org/0000-0002-2411-565X"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harshad Hegde","raw_affiliation_strings":["Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory , 1 Cyclotron road, Berkeley, CA 94720,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory , 1 Cyclotron road, Berkeley, CA 94720,","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002223413","display_name":"Chris Mungall","orcid":"https://orcid.org/0000-0002-6601-2165"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher J Mungall","raw_affiliation_strings":["Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory , 1 Cyclotron road, Berkeley, CA 94720,"],"raw_orcid":"https://orcid.org/0000-0002-6601-2165","affiliations":[{"raw_affiliation_string":"Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory , 1 Cyclotron road, Berkeley, CA 94720,","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038063370","display_name":"Anna Giannakou","orcid":"https://orcid.org/0000-0003-2666-3497"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anna Giannakou","raw_affiliation_strings":["Scientific Data Division, Lawrence Berkeley National Laboratory , 1 Cyclotron road, Berkeley, CA 94720,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scientific Data Division, Lawrence Berkeley National Laboratory , 1 Cyclotron road, Berkeley, CA 94720,","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068328096","display_name":"Neil Byers","orcid":"https://orcid.org/0000-0001-5332-2255"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neil P Byers","raw_affiliation_strings":["DOE Joint Genome Institute, Lawrence Berkeley National Laboratory , 1 Cyclotron road, Berkeley, CA 94720,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DOE Joint Genome Institute, Lawrence Berkeley National Laboratory , 1 Cyclotron road, Berkeley, CA 94720,","institution_ids":["https://openalex.org/I196679689","https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027568646","display_name":"Dan Gunter","orcid":"https://orcid.org/0000-0002-2779-2744"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Gunter","raw_affiliation_strings":["Scientific Data Division, Lawrence Berkeley National Laboratory , 1 Cyclotron road, Berkeley, CA 94720,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scientific Data Division, Lawrence Berkeley National Laboratory , 1 Cyclotron road, Berkeley, CA 94720,","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058345403","display_name":"Kjiersten Fagnan","orcid":"https://orcid.org/0000-0002-6504-849X"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kjiersten Fagnan","raw_affiliation_strings":["DOE Joint Genome Institute, Lawrence Berkeley National Laboratory , 1 Cyclotron road, Berkeley, CA 94720,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DOE Joint Genome Institute, Lawrence Berkeley National Laboratory , 1 Cyclotron road, Berkeley, CA 94720,","institution_ids":["https://openalex.org/I196679689","https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038208900","display_name":"Lavanya Ramakrishnan","orcid":"https://orcid.org/0000-0003-1761-4132"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lavanya Ramakrishnan","raw_affiliation_strings":["Scientific Data Division, Lawrence Berkeley National Laboratory , 1 Cyclotron road, Berkeley, CA 94720,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scientific Data Division, Lawrence Berkeley National Laboratory , 1 Cyclotron road, Berkeley, CA 94720,","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5047606322"],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1415,"currency":"GBP","value_usd":1735},"fwci":0.6212,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74453743,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"2024","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9965999722480774,"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/T10028","display_name":"Topic Modeling","score":0.9745000004768372,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.9103120565414429},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8268285989761353},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6734561920166016},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.610988974571228},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5951915979385376},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.5013175010681152},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4712420105934143},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4205830991268158},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4173503518104553},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34930750727653503},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3365022540092468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23020902276039124}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9103120565414429},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8268285989761353},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6734561920166016},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.610988974571228},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5951915979385376},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.5013175010681152},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4712420105934143},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4205830991268158},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4173503518104553},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34930750727653503},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3365022540092468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23020902276039124},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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}],"locations_count":5,"locations":[{"id":"doi:10.1093/database/baae093","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baae093","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baae093/59376480/baae093.pdf","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:39331731","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39331731","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:escholarship.org:ark:/13030/qt8vk507m4","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/8vk507m4","pdf_url":"https://escholarship.org/content/qt8vk507m4/qt8vk507m4.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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, vol 2024","raw_type":"article"},{"id":"pmh:oai:osti.gov:2476191","is_oa":true,"landing_page_url":"https://www.osti.gov/servlets/purl/2476191","pdf_url":"https://www.osti.gov/biblio/2476191","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11959184","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11959184","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11959184/pdf/baae093.pdf","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Database (Oxford)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/database/baae093","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baae093","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baae093/59376480/baae093.pdf","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":[{"display_name":"Industry, innovation and infrastructure","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1286236842","display_name":null,"funder_award_id":"-AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1677143136","display_name":null,"funder_award_id":"05CH11231","funder_id":"https://openalex.org/F4320317220","funder_display_name":"National Energy Research Scientific Computing Center"},{"id":"https://openalex.org/G1799333409","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G3083819904","display_name":null,"funder_award_id":"05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3944918260","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4501827968","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4565140552","display_name":null,"funder_award_id":"-AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G498139845","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G5076365615","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320317220","funder_display_name":"National Energy Research Scientific Computing Center"},{"id":"https://openalex.org/G6348972864","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6558272803","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G969889393","display_name":null,"funder_award_id":"DE-AC02-","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320317220","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4402919780.pdf"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1525595230","https://openalex.org/W1654805921","https://openalex.org/W1935434993","https://openalex.org/W2021074129","https://openalex.org/W2040298461","https://openalex.org/W2097877306","https://openalex.org/W2103017472","https://openalex.org/W2124991490","https://openalex.org/W2141541659","https://openalex.org/W2142678031","https://openalex.org/W2148084209","https://openalex.org/W2167329753","https://openalex.org/W2317515691","https://openalex.org/W2521644033","https://openalex.org/W2573248010","https://openalex.org/W2604700393","https://openalex.org/W2605099106","https://openalex.org/W2767691613","https://openalex.org/W2769436351","https://openalex.org/W2775795276","https://openalex.org/W2789995212","https://openalex.org/W2906830849","https://openalex.org/W2911448018","https://openalex.org/W2913793036","https://openalex.org/W2964656262","https://openalex.org/W2973226110","https://openalex.org/W2974528752","https://openalex.org/W2985504173","https://openalex.org/W3010293452","https://openalex.org/W3035051717","https://openalex.org/W3103975738","https://openalex.org/W3106224367","https://openalex.org/W3112600195","https://openalex.org/W3128710690","https://openalex.org/W3170771812","https://openalex.org/W3201090304","https://openalex.org/W4205536551","https://openalex.org/W4213163645","https://openalex.org/W4287207962","https://openalex.org/W4287817164","https://openalex.org/W4292779060","https://openalex.org/W4307306490","https://openalex.org/W4322759378","https://openalex.org/W4327810158","https://openalex.org/W4366563389","https://openalex.org/W4384918448","https://openalex.org/W4385571140","https://openalex.org/W4385571411","https://openalex.org/W4390547901","https://openalex.org/W4390569775","https://openalex.org/W4391158659","https://openalex.org/W6631501603","https://openalex.org/W6637382961","https://openalex.org/W6684644441","https://openalex.org/W6732025539","https://openalex.org/W6778883912","https://openalex.org/W6783283564","https://openalex.org/W6785847369","https://openalex.org/W6809328155","https://openalex.org/W6847221308"],"related_works":["https://openalex.org/W2058118494","https://openalex.org/W2392768766","https://openalex.org/W2361861616","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2263699433","https://openalex.org/W2106424170","https://openalex.org/W2377979023","https://openalex.org/W2082577974","https://openalex.org/W2561631357"],"abstract_inverted_index":{"Advanced":[0],"omics":[1],"technologies":[2],"and":[3,26,90,125,139,233,278],"facilities":[4],"generate":[5,275],"a":[6,35,54,78,97,194,299],"wealth":[7],"of":[8,32,41,111,136,141,161,178,221,240,257,291],"valuable":[9],"data":[10,14,43,62,145,222],"daily;":[11],"however,":[12],"the":[13,17,39,65,109,159,176,207,211,226,255,269,284,292],"often":[15],"lack":[16,31],"essential":[18],"metadata":[19,33,48,66,137,163,263],"required":[20],"for":[21,68,158,164,190,261,283],"researchers":[22],"to":[23,58,99,107,182,196,205,225,289],"find,":[24],"curate,":[25],"search":[27],"them":[28],"effectively.":[29],"The":[30,213,235],"poses":[34],"significant":[36],"challenge":[37],"in":[38,81,105,119,134,170,210,254],"utilization":[40],"these":[42,252],"sets.":[44,146],"Machine":[45],"learning":[46],"(ML)-based":[47],"extraction":[49,302],"techniques":[50,104,174],"have":[51,129],"emerged":[52],"as":[53,122,231],"potentially":[55],"viable":[56],"approach":[57],"automatically":[59],"annotating":[60],"scientific":[61,112],"sets":[63],"with":[64,167,287,295],"necessary":[67],"enabling":[69],"effective":[70],"search.":[71],"Text":[72],"labeling,":[73],"usually":[74],"performed":[75],"manually,":[76],"plays":[77],"crucial":[79],"role":[80],"validating":[82],"machine-extracted":[83],"metadata.":[84],"However,":[85],"manual":[86],"labeling":[87,103,156],"is":[88,96,116,187],"time-consuming":[89],"not":[91],"always":[92],"feasible;":[93],"thus,":[94],"there":[95],"need":[98,115],"develop":[100],"automated":[101,154],"text":[102,143,155,281],"order":[106],"accelerate":[108],"process":[110],"innovation.":[113],"This":[114],"particularly":[117],"urgent":[118],"fields":[120],"such":[121,230],"environmental":[123,171,258],"genomics":[124,259],"microbiome":[126],"science,":[127],"which":[128,200],"historically":[130],"received":[131],"less":[132],"attention":[133],"terms":[135],"curation":[138],"creation":[140],"gold-standard":[142],"mining":[144],"In":[147,246],"this":[148,247],"paper,":[149,248],"we":[150,249],"present":[151],"two":[152,179],"novel":[153],"approaches":[157,253,273],"validation":[160],"ML-generated":[162,262],"unlabeled":[165,285],"texts,":[166,286],"specific":[168,280],"applications":[169],"genomics.":[172],"Our":[173,265],"show":[175,267],"potential":[177],"new":[180],"ways":[181],"leverage":[183],"existing":[184],"information":[185],"that":[186,268],"only":[188],"available":[189],"select":[191],"documents":[192,209],"within":[193],"corpus":[195],"validate":[197],"ML":[198,300],"models,":[199],"can":[201,274],"then":[202],"be":[203],"used":[204],"describe":[206],"remaining":[208],"corpus.":[212],"first":[214],"technique":[215,237],"exploits":[216],"relationships":[217],"between":[218],"different":[219],"types":[220],"sources":[223],"related":[224],"same":[227],"research":[228,260],"study,":[229],"publications":[232],"proposals.":[234],"second":[236],"takes":[238],"advantage":[239],"domain-specific":[241],"controlled":[242],"vocabularies":[243],"or":[244],"ontologies.":[245],"detail":[250],"applying":[251],"context":[256],"validation.":[264],"results":[266],"proposed":[270],"label":[271],"assignment":[272],"both":[276],"generic":[277],"highly":[279],"labels":[282,293],"up":[288],"44%":[290],"matching":[294],"those":[296],"suggested":[297],"by":[298],"keyword":[301],"algorithm.":[303]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-02T09:04:35.204637","created_date":"2025-10-10T00:00:00"}
