{"id":"https://openalex.org/W2887377515","doi":"https://doi.org/10.1371/journal.pcbi.1006390","title":"Scaling up data curation using deep learning: An application to literature triage in genomic variation resources","display_name":"Scaling up data curation using deep learning: An application to literature triage in genomic variation resources","publication_year":2018,"publication_date":"2018-08-13","ids":{"openalex":"https://openalex.org/W2887377515","doi":"https://doi.org/10.1371/journal.pcbi.1006390","mag":"2887377515","pmid":"https://pubmed.ncbi.nlm.nih.gov/30102703"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1006390","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1006390","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1006390&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1006390&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004629166","display_name":"Kyubum Lee","orcid":"https://orcid.org/0000-0003-2015-3939"},"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":"Kyubum Lee","raw_affiliation_strings":["National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH), Bethesda, Maryland, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-2015-3939","affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH), Bethesda, Maryland, United States of America","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102899719","display_name":"Maria Livia Famiglietti","orcid":"https://orcid.org/0000-0002-5283-6593"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Maria Livia Famiglietti","raw_affiliation_strings":["Swiss-Prot Group, SIB Swiss Institute of Bioinformatics, Geneva, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swiss-Prot Group, SIB Swiss Institute of Bioinformatics, Geneva, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083575875","display_name":"Aoife McMahon","orcid":"https://orcid.org/0000-0003-0978-0309"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Aoife McMahon","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, Cambridge, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-0978-0309","affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058918482","display_name":"Chih-Hsuan Wei","orcid":"https://orcid.org/0000-0001-5094-7321"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chih-Hsuan Wei","raw_affiliation_strings":["National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH), Bethesda, Maryland, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH), Bethesda, Maryland, United States of America","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003927093","display_name":"Jacqueline A. L. MacArthur","orcid":"https://orcid.org/0000-0002-3550-9769"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jacqueline Ann Langdon MacArthur","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082490970","display_name":"Sylvain Poux","orcid":"https://orcid.org/0000-0001-7299-6685"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Sylvain Poux","raw_affiliation_strings":["Swiss-Prot Group, SIB Swiss Institute of Bioinformatics, Geneva, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swiss-Prot Group, SIB Swiss Institute of Bioinformatics, Geneva, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047948695","display_name":"Lionel Breuza","orcid":"https://orcid.org/0000-0002-8075-8625"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Lionel Breuza","raw_affiliation_strings":["Swiss-Prot Group, SIB Swiss Institute of Bioinformatics, Geneva, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swiss-Prot Group, SIB Swiss Institute of Bioinformatics, Geneva, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090916579","display_name":"Alan Bridge","orcid":"https://orcid.org/0000-0003-2148-9135"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Alan Bridge","raw_affiliation_strings":["Swiss-Prot Group, SIB Swiss Institute of Bioinformatics, Geneva, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-2148-9135","affiliations":[{"raw_affiliation_string":"Swiss-Prot Group, SIB Swiss Institute of Bioinformatics, Geneva, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007575726","display_name":"Fiona Cunningham","orcid":"https://orcid.org/0000-0002-7445-2419"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Fiona Cunningham","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065825020","display_name":"Ioannis X\u00e9narios","orcid":"https://orcid.org/0000-0002-3413-6841"},"institutions":[{"id":"https://openalex.org/I114457229","display_name":"University of Geneva","ror":"https://ror.org/01swzsf04","country_code":"CH","type":"education","lineage":["https://openalex.org/I114457229"]},{"id":"https://openalex.org/I97565354","display_name":"University of Lausanne","ror":"https://ror.org/019whta54","country_code":"CH","type":"education","lineage":["https://openalex.org/I97565354"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Ioannis Xenarios","raw_affiliation_strings":["Center for Integrative Genomics, University of Lausanne, Lausanne Switzerland","Department of Chemistry and Biochemistry, University of Geneva, Geneva, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Integrative Genomics, University of Lausanne, Lausanne Switzerland","institution_ids":["https://openalex.org/I97565354"]},{"raw_affiliation_string":"Department of Chemistry and Biochemistry, University of Geneva, Geneva, Switzerland","institution_ids":["https://openalex.org/I114457229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083081872","display_name":"Zhiyong Lu","orcid":"https://orcid.org/0000-0001-9998-916X"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhiyong Lu","raw_affiliation_strings":["National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH), Bethesda, Maryland, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-9998-916X","affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH), Bethesda, Maryland, United States of America","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5003927093","https://openalex.org/A5004629166","https://openalex.org/A5007575726","https://openalex.org/A5047948695","https://openalex.org/A5058918482","https://openalex.org/A5065825020","https://openalex.org/A5082490970","https://openalex.org/A5083081872","https://openalex.org/A5083575875","https://openalex.org/A5090916579","https://openalex.org/A5102899719"],"corresponding_institution_ids":["https://openalex.org/I114457229","https://openalex.org/I12708293","https://openalex.org/I1299303238","https://openalex.org/I1303153112","https://openalex.org/I4210109390","https://openalex.org/I97565354"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":2.5983,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":{"value":0.90725323,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"14","issue":"8","first_page":"e1006390","last_page":"e1006390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9993000030517578,"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":0.9993000030517578,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9958000183105469,"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":0.9929999709129333,"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/uniprot","display_name":"UniProt","score":0.8562301397323608},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8235678672790527},{"id":"https://openalex.org/keywords/triage","display_name":"Triage","score":0.7675849199295044},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6298350691795349},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5450965166091919},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.48808014392852783},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.47646403312683105},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46320855617523193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4305543899536133},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4267506003379822},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4052931070327759},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37446919083595276},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3385726511478424},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.09531408548355103}],"concepts":[{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.8562301397323608},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8235678672790527},{"id":"https://openalex.org/C2777120189","wikidata":"https://www.wikidata.org/wiki/Q780067","display_name":"Triage","level":2,"score":0.7675849199295044},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6298350691795349},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5450965166091919},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.48808014392852783},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.47646403312683105},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46320855617523193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4305543899536133},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4267506003379822},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4052931070327759},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37446919083595276},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3385726511478424},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.09531408548355103},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"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/C194828623","wikidata":"https://www.wikidata.org/wiki/Q2861470","display_name":"Emergency medicine","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}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011642","descriptor_name":"Publications","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011642","descriptor_name":"Publications","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011642","descriptor_name":"Publications","qualifier_ui":null,"qualifier_name":null,"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":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051188","descriptor_name":"Knowledge Bases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051188","descriptor_name":"Knowledge Bases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051188","descriptor_name":"Knowledge Bases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D066289","descriptor_name":"Data Curation","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false}],"locations_count":8,"locations":[{"id":"doi:10.1371/journal.pcbi.1006390","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1006390","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1006390&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:30102703","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30102703","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":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:serval.unil.ch:BIB_916AEEE29E4F","is_oa":true,"landing_page_url":"https://serval.unil.ch/notice/serval:BIB_916AEEE29E4F","pdf_url":null,"source":{"id":"https://openalex.org/S4306401797","display_name":"SERVAL (Universit\u00e9 de Lausanne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210093590","host_organization_name":"Swiss School of Archaeology in Greece","host_organization_lineage":["https://openalex.org/I4210093590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS computational biology, vol. 14, no. 8, pp. e1006390","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:iris.unil.ch:iris/219477","is_oa":true,"landing_page_url":"https://iris.unil.ch/handle/iris/219477","pdf_url":"https://iris.unil.ch/bitstreams/49875977-4ed7-4b1f-a7b1-be69ae0e34eb/download","source":{"id":"https://openalex.org/S7407055444","display_name":"IRIS","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"},{"id":"pmh:oai:RePEc:plo:pcbi00:1006390","is_oa":false,"landing_page_url":"https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1006390","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"},{"id":"pmh:oai:doaj.org/article:376e555f409d4b71af420208bc0e11d0","is_oa":true,"landing_page_url":"https://doaj.org/article/376e555f409d4b71af420208bc0e11d0","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 14, Iss 8, p e1006390 (2018)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:5064416","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC6107285","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:6107285","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6107285","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1006390","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1006390","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1006390&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1626001152","display_name":null,"funder_award_id":"U41HG007823","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2602465823","display_name":null,"funder_award_id":"U41HG007823","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G4745618442","display_name":null,"funder_award_id":"UniProt 5U41HG007822-02","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320307844","display_name":"European Molecular Biology Organization","ror":"https://ror.org/04wfr2810"},{"id":"https://openalex.org/F4320314023","display_name":"European Molecular Biology Laboratory","ror":"https://ror.org/050589e39"},{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320335238","display_name":"Staatssekretariat f\u00fcr Bildung, Forschung und Innovation","ror":"https://ror.org/01kw63t33"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2887377515.pdf","grobid_xml":"https://content.openalex.org/works/W2887377515.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1538131130","https://openalex.org/W1832693441","https://openalex.org/W1964670939","https://openalex.org/W1969099570","https://openalex.org/W2025573625","https://openalex.org/W2037451280","https://openalex.org/W2062707524","https://openalex.org/W2094726706","https://openalex.org/W2098650870","https://openalex.org/W2101234009","https://openalex.org/W2102140136","https://openalex.org/W2112796928","https://openalex.org/W2118582067","https://openalex.org/W2129800387","https://openalex.org/W2141125852","https://openalex.org/W2141158585","https://openalex.org/W2144354855","https://openalex.org/W2148130205","https://openalex.org/W2150288223","https://openalex.org/W2150850055","https://openalex.org/W2153579005","https://openalex.org/W2154139219","https://openalex.org/W2155454737","https://openalex.org/W2155518941","https://openalex.org/W2158899491","https://openalex.org/W2167321327","https://openalex.org/W2168943507","https://openalex.org/W2169997311","https://openalex.org/W2171374484","https://openalex.org/W2171895522","https://openalex.org/W2271840356","https://openalex.org/W2485374661","https://openalex.org/W2489933339","https://openalex.org/W2515248967","https://openalex.org/W2527896214","https://openalex.org/W2529194139","https://openalex.org/W2559028527","https://openalex.org/W2593634001","https://openalex.org/W2752636837","https://openalex.org/W2785059970","https://openalex.org/W2950371387","https://openalex.org/W2952230511","https://openalex.org/W2952894920","https://openalex.org/W2963083845","https://openalex.org/W4210702584","https://openalex.org/W4242191001","https://openalex.org/W4294170691","https://openalex.org/W4297749952","https://openalex.org/W4301785137","https://openalex.org/W6675354045","https://openalex.org/W6683738474","https://openalex.org/W6684758323"],"related_works":["https://openalex.org/W24553703","https://openalex.org/W4211000692","https://openalex.org/W4212920271","https://openalex.org/W2612240612","https://openalex.org/W2129800387","https://openalex.org/W2080497949","https://openalex.org/W2397655851","https://openalex.org/W4287199895","https://openalex.org/W2146638336","https://openalex.org/W2146486983"],"abstract_inverted_index":{"Manually":[0],"curating":[1],"biomedical":[2],"knowledge":[3,11,247],"from":[4,87],"publications":[5,28,86,124,201],"is":[6,32,38,65,227],"necessary":[7],"to":[8,21,67,119,133,242],"build":[9],"a":[10,77,100,167],"based":[12,108],"service":[13],"that":[14,147,175,202,233],"provides":[15],"highly":[16],"precise":[17],"and":[18,44,57,63,91,96,121,141,160,170,185,226],"organized":[19],"information":[20],"users.":[22],"The":[23],"process":[24,138,223],"of":[25,139,183,206,246],"retrieving":[26],"relevant":[27,200],"for":[29,103,125],"curation,":[30],"which":[31],"also":[33],"known":[34],"as":[35,99],"document":[36],"triage,":[37],"usually":[39],"carried":[40],"out":[41],"by":[42,177],"querying":[43],"reading":[45],"articles":[46],"in":[47,230],"PubMed.":[48],"However,":[49],"this":[50],"query-based":[51,155,180,204],"method":[52,132,151,165,196,205,218],"often":[53],"obtains":[54],"unsatisfactory":[55],"precision":[56,168],"recall":[58],"on":[59,109,238],"the":[60,92,116,134,142,153,178,186,203,221,244],"retrieved":[61],"results,":[62],"it":[64],"difficult":[66],"manually":[68],"generate":[69],"optimal":[70],"queries.":[71],"To":[72],"address":[73],"this,":[74],"we":[75,129],"propose":[76],"machine-learning":[78],"assisted":[79],"triage":[80,150,156,181,222],"method.":[81],"We":[82,113,145],"collect":[83],"previously":[84],"curated":[85,162],"two":[88],"databases":[89],"UniProtKB/Swiss-Prot":[90,140,184,207],"NHGRI-EBI":[93],"GWAS":[94,143,187],"Catalog,":[95,188],"used":[97],"them":[98],"gold-standard":[101],"dataset":[102],"training":[104],"deep":[105],"learning":[106],"models":[107,118],"convolutional":[110],"neural":[111],"networks.":[112],"then":[114],"use":[115],"trained":[117],"classify":[120],"rank":[122],"new":[123],"curation.":[126],"For":[127],"evaluation,":[128],"apply":[130],"our":[131,148,195,215],"real-world":[135],"manual":[136],"curation":[137],"Catalog.":[144],"demonstrate":[146],"machine-assisted":[149],"outperforms":[152],"current":[154,179],"methods,":[157],"improves":[158],"efficiency,":[159],"enriches":[161],"content.":[163],"Our":[164],"achieves":[166],"1.81":[169],"2.99":[171],"times":[172],"higher":[173],"than":[174],"obtained":[176],"methods":[182],"respectively,":[189],"without":[190],"compromising":[191],"recall.":[192],"In":[193],"fact,":[194],"retrieves":[197],"many":[198],"additional":[199],"could":[208],"not":[209],"find.":[210],"As":[211],"these":[212],"results":[213],"show,":[214],"machine":[216],"learning-based":[217],"can":[219,236],"make":[220],"more":[224,239],"efficient":[225],"being":[228],"implemented":[229],"production":[231],"so":[232],"human":[234],"curators":[235],"focus":[237],"challenging":[240],"tasks":[241],"improve":[243],"quality":[245],"bases.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
