{"id":"https://openalex.org/W2955474241","doi":"https://doi.org/10.1093/database/baz064","title":"PubMed Text Similarity Model and its application to curation efforts in the Conserved Domain Database","display_name":"PubMed Text Similarity Model and its application to curation efforts in the Conserved Domain Database","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2955474241","doi":"https://doi.org/10.1093/database/baz064","mag":"2955474241","pmid":"https://pubmed.ncbi.nlm.nih.gov/31267135"},"language":"en","primary_location":{"id":"doi:10.1093/database/baz064","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baz064","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baz064/28895934/baz064.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/baz064/28895934/baz064.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008126200","display_name":"Rezarta Islamaj","orcid":"https://orcid.org/0000-0001-5651-1860"},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]},{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rezarta Islamaj","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111895206","display_name":"W. John Wilbur","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]},{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W John Wilbur","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068777093","display_name":"Natalie Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]},{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Natalie Xie","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049089682","display_name":"Noreen R. Gonzales","orcid":null},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noreen R Gonzales","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009507390","display_name":"Narmada Thanki","orcid":"https://orcid.org/0000-0003-1181-2509"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Narmada Thanki","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041025050","display_name":"Roxanne A. Yamashita","orcid":null},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roxanne Yamashita","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100901090","display_name":"Chanjuan Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chanjuan Zheng","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026383671","display_name":"Aron Marchler\u2010Bauer","orcid":"https://orcid.org/0000-0003-1516-0712"},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]},{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aron Marchler-Bauer","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083081872","display_name":"Zhiyong Lu","orcid":"https://orcid.org/0000-0001-9998-916X"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhiyong Lu","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, 20894, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5083081872"],"corresponding_institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1415,"currency":"GBP","value_usd":1735},"fwci":0.9448,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.7456309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2019","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":0.9988999962806702,"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":0.9988999962806702,"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":0.9970999956130981,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.7577918767929077},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7022449970245361},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6557550430297852},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5664202570915222},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.54953932762146},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5263627171516418},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.525109589099884},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.48780563473701477},{"id":"https://openalex.org/keywords/statement","display_name":"Statement (logic)","score":0.4735913872718811},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.40969008207321167},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3334510922431946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1999264359474182},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1346311867237091}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577918767929077},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7022449970245361},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6557550430297852},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5664202570915222},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.54953932762146},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5263627171516418},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.525109589099884},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.48780563473701477},{"id":"https://openalex.org/C2777026412","wikidata":"https://www.wikidata.org/wiki/Q2684591","display_name":"Statement (logic)","level":2,"score":0.4735913872718811},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.40969008207321167},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3334510922431946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1999264359474182},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1346311867237091},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000072417","descriptor_name":"Protein Domains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000072417","descriptor_name":"Protein Domains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000072417","descriptor_name":"Protein Domains","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":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/database/baz064","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baz064","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baz064/28895934/baz064.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:31267135","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31267135","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:pubmedcentral.nih.gov:6606757","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6606757","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":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Database (Oxford)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/database/baz064","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baz064","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baz064/28895934/baz064.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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2955474241.pdf","grobid_xml":"https://content.openalex.org/works/W2955474241.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W9328536","https://openalex.org/W1532325895","https://openalex.org/W1606357646","https://openalex.org/W1964670939","https://openalex.org/W1976325156","https://openalex.org/W2004622806","https://openalex.org/W2017608260","https://openalex.org/W2020278455","https://openalex.org/W2032443316","https://openalex.org/W2044420612","https://openalex.org/W2063389953","https://openalex.org/W2094726706","https://openalex.org/W2101727078","https://openalex.org/W2120939273","https://openalex.org/W2145815109","https://openalex.org/W2145870108","https://openalex.org/W2148130205","https://openalex.org/W2166240318","https://openalex.org/W2169929748","https://openalex.org/W2171313960","https://openalex.org/W2171895522","https://openalex.org/W2224056471","https://openalex.org/W2559191318","https://openalex.org/W2596180971","https://openalex.org/W2735784619","https://openalex.org/W2740887992","https://openalex.org/W2912323225","https://openalex.org/W2952894920","https://openalex.org/W2962985038","https://openalex.org/W2964061924","https://openalex.org/W3105439152","https://openalex.org/W4213009331"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W1995247875","https://openalex.org/W2073555250","https://openalex.org/W3186475613","https://openalex.org/W2165159668","https://openalex.org/W2165981566","https://openalex.org/W2054877875","https://openalex.org/W2157792067","https://openalex.org/W4255784183","https://openalex.org/W3122011053"],"abstract_inverted_index":{"This":[0,287],"study":[1],"proposes":[2,112],"a":[3,19,129,136,264,298,316],"text":[4,130,284,335,357],"similarity":[5,131,285,296,313,336,358],"model":[6],"to":[7,85,117,124,139,180,193,201,222,246,303,348,351],"help":[8],"biocuration":[9],"efforts":[10],"of":[11,44,62,95,115,146,209,228,257,267,320,326,356],"the":[12,60,88,93,107,118,144,152,155,169,175,195,198,202,212,229,250,282,332,349],"Conserved":[13],"Domain":[14],"Database":[15],"(CDD).":[16],"CDD":[17,55,99,120,165,203,283,310],"is":[18,83,128,331],"curated":[20],"resource":[21,337],"that":[22,91,105,133,189,214,338],"catalogs":[23],"annotated":[24,307],"multiple":[25],"sequence":[26],"alignment":[27],"models":[28,36],"for":[29,38,79,182,226,238,294],"ancient":[30],"domains":[31,65],"and":[32,41,66,111,277,322,344,354],"full-length":[33],"proteins.":[34],"These":[35],"allow":[37],"fast":[39],"searching":[40],"quick":[42],"identification":[43],"conserved":[45,64],"motifs":[46],"in":[47,154,197],"protein":[48,68,274],"sequences":[49],"via":[50],"Reverse":[51],"PSI-BLAST.":[52],"In":[53,211,232],"addition,":[54,233],"curators":[56,100,181,245],"prepare":[57],"summaries":[58],"detailing":[59],"function":[61,278],"these":[63,126],"specific":[67],"families,":[69],"based":[70],"on":[71,273,297],"published":[72,109],"peer-reviewed":[73],"articles.":[74],"To":[75,159,328],"facilitate":[76],"information":[77],"access":[78],"database":[80],"users,":[81],"it":[82],"desirable":[84],"specifically":[86],"identify":[87],"referenced":[89,147],"articles":[90,114,153,196,237,272],"support":[92],"assertions":[94],"curator-composed":[96],"sentences.":[97],"Moreover,":[98],"desire":[101],"an":[102,207,254,323],"alert":[103],"system":[104],"scans":[106],"newly":[108],"literature":[110],"related":[113],"relevance":[116],"existing":[119],"records.":[121],"Our":[122],"approach":[123],"address":[125],"needs":[127],"method":[132],"automatically":[134],"maps":[135],"curator-written":[137],"statement":[138],"candidate":[140],"sentences":[141,167,173,269],"extracted":[142],"from":[143,174,270,300],"list":[145,200,252],"articles,":[148],"as":[149,151],"well":[150],"PubMed":[156],"Central":[157],"database.":[158],"evaluate":[160],"this":[161,185,260,330],"proposal,":[162],"we":[163,187,190,219,234,262],"paired":[164],"description":[166,204],"with":[168,206],"top":[170],"10":[171],"matching":[172],"literature,":[176],"which":[177,241,280],"were":[178,191,220,242],"given":[179],"review.":[183],"Through":[184,259],"exercise,":[186],"discovered":[188],"able":[192,221],"map":[194],"reference":[199,251],"statements":[205],"accuracy":[208],"77%.":[210],"dataset":[213],"was":[215],"reviewed":[216],"by":[217,244,308],"curators,":[218],"successfully":[223],"provide":[224],"references":[225],"86%":[227],"curator":[230,239],"statements.":[231],"suggested":[235],"new":[236],"review,":[240],"accepted":[243],"be":[247],"added":[248],"into":[249],"at":[253],"acceptance":[255],"rate":[256],"50%.":[258],"process,":[261],"developed":[263],"substantial":[265],"corpus":[266,288],"similar":[268],"biomedical":[271,334],"sequence,":[275],"structure":[276],"research,":[279],"constitute":[281],"corpus.":[286],"contains":[289],"5159":[290],"sentence":[291],"pairs":[292],"judged":[293],"their":[295],"scale":[299],"1":[301],"(low)":[302],"5":[304],"(high)":[305],"doubly":[306],"four":[309],"curators.":[311],"Curator-assigned":[312],"scores":[314],"have":[315],"Pearson":[317],"correlation":[318],"coefficient":[319],"0.70":[321],"inter-annotator":[324],"agreement":[325],"85%.":[327],"date,":[329],"largest":[333],"has":[339],"been":[340],"manually":[341],"judged,":[342],"evaluated":[343],"made":[345],"publicly":[346],"available":[347],"community":[350],"foster":[352],"research":[353],"development":[355],"algorithms.":[359]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
