{"id":"https://openalex.org/W2798646702","doi":"https://doi.org/10.1186/s12859-018-2121-6","title":"A statistical approach to identify, monitor, and manage incomplete curated data sets","display_name":"A statistical approach to identify, monitor, and manage incomplete curated data sets","publication_year":2018,"publication_date":"2018-04-02","ids":{"openalex":"https://openalex.org/W2798646702","doi":"https://doi.org/10.1186/s12859-018-2121-6","mag":"2798646702","pmid":"https://pubmed.ncbi.nlm.nih.gov/29609549"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-018-2121-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-018-2121-6","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-018-2121-6","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-018-2121-6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075534795","display_name":"Douglas G. Howe","orcid":"https://orcid.org/0000-0001-5831-7439"},"institutions":[{"id":"https://openalex.org/I181233156","display_name":"University of Oregon","ror":"https://ror.org/0293rh119","country_code":"US","type":"education","lineage":["https://openalex.org/I181233156"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Douglas G. Howe","raw_affiliation_strings":["The Institute of Neuroscience, University of Oregon, Eugene, OR, USA. dhowe@zfin.org","The Institute of Neuroscience, University of Oregon, Eugene, USA"],"affiliations":[{"raw_affiliation_string":"The Institute of Neuroscience, University of Oregon, Eugene, OR, USA. dhowe@zfin.org","institution_ids":[]},{"raw_affiliation_string":"The Institute of Neuroscience, University of Oregon, Eugene, USA","institution_ids":["https://openalex.org/I181233156"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5075534795"],"corresponding_institution_ids":["https://openalex.org/I181233156"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.0931,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46848736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"19","issue":"1","first_page":"110","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9995999932289124,"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":0.9995999932289124,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9954000115394592,"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/T11719","display_name":"Data Quality and Management","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6336396336555481},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5892698168754578},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.5647516846656799},{"id":"https://openalex.org/keywords/gene-nomenclature","display_name":"Gene nomenclature","score":0.54481440782547},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5258182287216187},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5063608884811401},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49522462487220764},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.4622708261013031},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.428725928068161},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.42503225803375244},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.35278820991516113},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.283766508102417},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.23562979698181152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22745797038078308},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22695091366767883},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.21001344919204712},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.13738316297531128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6336396336555481},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5892698168754578},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.5647516846656799},{"id":"https://openalex.org/C62177273","wikidata":"https://www.wikidata.org/wiki/Q5531556","display_name":"Gene nomenclature","level":4,"score":0.54481440782547},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5258182287216187},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5063608884811401},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49522462487220764},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.4622708261013031},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.428725928068161},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.42503225803375244},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.35278820991516113},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.283766508102417},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.23562979698181152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22745797038078308},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22695091366767883},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.21001344919204712},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.13738316297531128},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"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/C514705636","wikidata":"https://www.wikidata.org/wiki/Q863247","display_name":"Nomenclature","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005786","descriptor_name":"Gene Expression Regulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005786","descriptor_name":"Gene Expression Regulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005786","descriptor_name":"Gene Expression Regulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012044","descriptor_name":"Regression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012044","descriptor_name":"Regression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012044","descriptor_name":"Regression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013223","descriptor_name":"Statistics as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013223","descriptor_name":"Statistics as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013223","descriptor_name":"Statistics as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015027","descriptor_name":"Zebrafish","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015027","descriptor_name":"Zebrafish","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015027","descriptor_name":"Zebrafish","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","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":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030801","descriptor_name":"Animals, Genetically Modified","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030801","descriptor_name":"Animals, Genetically Modified","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030801","descriptor_name":"Animals, Genetically Modified","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-018-2121-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-018-2121-6","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-018-2121-6","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:29609549","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29609549","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:5879614","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5879614","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:d94adaa35f244a0d86646b15b775431c","is_oa":true,"landing_page_url":"https://doaj.org/article/d94adaa35f244a0d86646b15b775431c","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 19, Iss 1, Pp 1-12 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12859-018-2121-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-018-2121-6","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-018-2121-6","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2324095473","display_name":null,"funder_award_id":"HG002659","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4491286837","display_name":null,"funder_award_id":"HG002659","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G8468295366","display_name":null,"funder_award_id":"U41 HG002659","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8494250139","display_name":null,"funder_award_id":"U41 HG002659","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798646702.pdf","grobid_xml":"https://content.openalex.org/works/W2798646702.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1505191356","https://openalex.org/W1591180101","https://openalex.org/W2053673723","https://openalex.org/W2093541638","https://openalex.org/W2104544690","https://openalex.org/W2122420884","https://openalex.org/W2123171788","https://openalex.org/W2150850055","https://openalex.org/W2168866167","https://openalex.org/W2168943507","https://openalex.org/W2343964059","https://openalex.org/W2538299754","https://openalex.org/W2549115005","https://openalex.org/W2558838260","https://openalex.org/W2602583424","https://openalex.org/W2736466919","https://openalex.org/W2747278505"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2169425537","https://openalex.org/W1922686488","https://openalex.org/W2127546476","https://openalex.org/W2059565715","https://openalex.org/W2116418175","https://openalex.org/W2922695482","https://openalex.org/W1598794494"],"abstract_inverted_index":{"This":[0,23],"method":[1],"can":[2,25],"be":[3,37],"used":[4],"to":[5,39,45],"identify":[6],"data":[7,19,31,44],"sets":[8],"that":[9],"are":[10],"incompletely":[11],"curated,":[12],"as":[13],"demonstrated":[14],"using":[15],"the":[16,47],"gene":[17],"expression":[18],"set":[20],"from":[21],"ZFIN.":[22],"information":[24],"help":[26],"both":[27],"database":[28],"resources":[29],"and":[30],"consumers":[32],"gauge":[33],"when":[34],"it":[35],"may":[36],"useful":[38],"look":[40],"further":[41],"for":[42],"published":[43],"augment":[46],"existing":[48],"expertly":[49],"curated":[50],"information.":[51]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
