{"id":"https://openalex.org/W2949155040","doi":"https://doi.org/10.1093/database/baw163","title":"Duplicates, redundancies and inconsistencies in the primary nucleotide databases: a descriptive study","display_name":"Duplicates, redundancies and inconsistencies in the primary nucleotide databases: a descriptive study","publication_year":2016,"publication_date":"2016-11-24","ids":{"openalex":"https://openalex.org/W2949155040","doi":"https://doi.org/10.1093/database/baw163","mag":"2949155040","pmid":"https://pubmed.ncbi.nlm.nih.gov/28077566"},"language":"en","primary_location":{"id":"doi:10.1093/database/baw163","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baw163","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baw163/19228854/baw163.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/baw163/19228854/baw163.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042874172","display_name":"Qingyu Chen","orcid":"https://orcid.org/0000-0002-6036-1516"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Qingyu Chen","raw_affiliation_strings":["Department of Computing and Information Systems, The University of Melbourne, Parkville, VIC, 3010, Australia"],"affiliations":[{"raw_affiliation_string":"Department of Computing and Information Systems, The University of Melbourne, Parkville, VIC, 3010, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041495909","display_name":"Justin Zobel","orcid":"https://orcid.org/0000-0001-6622-032X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Justin Zobel","raw_affiliation_strings":["Department of Computing and Information Systems, The University of Melbourne, Parkville, VIC, 3010, Australia"],"affiliations":[{"raw_affiliation_string":"Department of Computing and Information Systems, The University of Melbourne, Parkville, VIC, 3010, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067214173","display_name":"Karin Verspoor","orcid":"https://orcid.org/0000-0002-8661-1544"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Karin Verspoor","raw_affiliation_strings":["Department of Computing and Information Systems, The University of Melbourne, Parkville, VIC, 3010, Australia"],"affiliations":[{"raw_affiliation_string":"Department of Computing and Information Systems, The University of Melbourne, Parkville, VIC, 3010, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042874172"],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1415,"currency":"GBP","value_usd":1735},"fwci":3.1376,"has_fulltext":true,"cited_by_count":69,"citation_normalized_percentile":{"value":0.92029736,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"2017","issue":null,"first_page":"baw163","last_page":"baw163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9980999827384949,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9980999827384949,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9965000152587891,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9941999912261963,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6161775588989258},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5606661438941956},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5041488409042358},{"id":"https://openalex.org/keywords/descriptive-research","display_name":"Descriptive research","score":0.43521618843078613},{"id":"https://openalex.org/keywords/primary","display_name":"Primary (astronomy)","score":0.426763653755188},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.36098718643188477},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08739495277404785}],"concepts":[{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6161775588989258},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5606661438941956},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5041488409042358},{"id":"https://openalex.org/C142546437","wikidata":"https://www.wikidata.org/wiki/Q2661195","display_name":"Descriptive research","level":2,"score":0.43521618843078613},{"id":"https://openalex.org/C2777977315","wikidata":"https://www.wikidata.org/wiki/Q7243056","display_name":"Primary (astronomy)","level":2,"score":0.426763653755188},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.36098718643188477},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08739495277404785},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D007564","descriptor_name":"Japan","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007564","descriptor_name":"Japan","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007564","descriptor_name":"Japan","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":true},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":"Q000458","qualifier_name":"organization & administration","is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":"Q000458","qualifier_name":"organization & administration","is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":"Q000458","qualifier_name":"organization & administration","is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/database/baw163","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baw163","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baw163/19228854/baw163.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:28077566","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28077566","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:jupiter.its.unimelb.edu.au:11343/257855","is_oa":true,"landing_page_url":"http://hdl.handle.net/11343/257855","pdf_url":"http://hdl.handle.net/11343/257855","source":{"id":"https://openalex.org/S4377196259","display_name":"Minerva Access (University of Melbourne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165779595","host_organization_name":"The University of Melbourne","host_organization_lineage":["https://openalex.org/I165779595"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:5225397","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5225397","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Database (Oxford)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/database/baw163","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baw163","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/baw163/19228854/baw163.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":[{"score":0.5299999713897705,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G3459733074","display_name":null,"funder_award_id":"DP150101550","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G611870384","display_name":null,"funder_award_id":"grant","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320320974","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2949155040.pdf","grobid_xml":"https://content.openalex.org/works/W2949155040.grobid-xml"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W114024208","https://openalex.org/W160070906","https://openalex.org/W1597164057","https://openalex.org/W1854015338","https://openalex.org/W1965664689","https://openalex.org/W1971647276","https://openalex.org/W1975914194","https://openalex.org/W1976369037","https://openalex.org/W2002180966","https://openalex.org/W2018604728","https://openalex.org/W2019096410","https://openalex.org/W2021250792","https://openalex.org/W2021952182","https://openalex.org/W2022296304","https://openalex.org/W2023448865","https://openalex.org/W2024231807","https://openalex.org/W2032838501","https://openalex.org/W2050428267","https://openalex.org/W2056646105","https://openalex.org/W2062296203","https://openalex.org/W2074456979","https://openalex.org/W2076048958","https://openalex.org/W2081315067","https://openalex.org/W2084258053","https://openalex.org/W2088027966","https://openalex.org/W2093794723","https://openalex.org/W2094108329","https://openalex.org/W2099131261","https://openalex.org/W2106302492","https://openalex.org/W2106831214","https://openalex.org/W2107903674","https://openalex.org/W2108991785","https://openalex.org/W2111858111","https://openalex.org/W2114592527","https://openalex.org/W2116699248","https://openalex.org/W2118597789","https://openalex.org/W2120141270","https://openalex.org/W2120158278","https://openalex.org/W2121442708","https://openalex.org/W2124410686","https://openalex.org/W2125054694","https://openalex.org/W2125515637","https://openalex.org/W2126409637","https://openalex.org/W2129800387","https://openalex.org/W2133935621","https://openalex.org/W2138565208","https://openalex.org/W2138790911","https://openalex.org/W2146980885","https://openalex.org/W2148448264","https://openalex.org/W2154969423","https://openalex.org/W2164260925","https://openalex.org/W2170747616","https://openalex.org/W2173732482","https://openalex.org/W2184640004","https://openalex.org/W2191378904","https://openalex.org/W2191986163","https://openalex.org/W2224056471","https://openalex.org/W2225557190","https://openalex.org/W2290831969","https://openalex.org/W2399636967","https://openalex.org/W2546947138","https://openalex.org/W2739999456","https://openalex.org/W2786418370","https://openalex.org/W2964648167","https://openalex.org/W3146259567","https://openalex.org/W4230612844","https://openalex.org/W4242729757","https://openalex.org/W4299497146"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2949989742","https://openalex.org/W2168220598","https://openalex.org/W1983513655","https://openalex.org/W2149733294","https://openalex.org/W2022577323","https://openalex.org/W2168601525","https://openalex.org/W1987197564","https://openalex.org/W1981065997","https://openalex.org/W2417708373"],"abstract_inverted_index":{"GenBank,":[0],"the":[1,7,15,24,72,75,101,118,128,186,223,270,278],"EMBL":[2],"European":[3],"Nucleotide":[4,17],"Archive":[5],"and":[6,50,52,68,100,131,189,200,242],"DNA":[8],"DataBank":[9],"of":[10,48,56,77,80,103,120,133,142,159,166,185,191,214,217,225,239,269,272],"Japan,":[11],"known":[12],"collectively":[13],"as":[14],"International":[16],"Sequence":[18],"Database":[19],"Collaboration":[20],"or":[21],"INSDC,":[22],"are":[23,33,150,281],"three":[25],"most":[26],"significant":[27],"nucleotide":[28],"sequence":[29,199],"databases.":[30,147],"Their":[31],"records":[32,280],"derived":[34],"from":[35,179],"laboratory":[36],"work":[37],"undertaken":[38],"by":[39,42],"different":[40,43,209,212],"individuals,":[41],"teams,":[44],"with":[45,97,171,203],"a":[46,54,59,63,139,155,231,266],"range":[47],"technologies":[49],"assumptions":[51],"over":[53],"period":[55],"decades.":[57],"As":[58],"consequence,":[60],"they":[61],"contain":[62],"great":[64],"many":[65],"duplicates,":[66,236],"redundancies":[67],"inconsistencies,":[69],"but":[70,253],"neither":[71],"prevalence":[73,213],"nor":[74],"characteristics":[76],"various":[78],"types":[79,188],"duplicates":[81,104,134,160,196,226,248],"have":[82,211],"been":[83,110],"rigorously":[84],"assessed.":[85],"Existing":[86],"duplicate":[87,95,174],"detection":[88],"methods":[89],"in":[90,105,135,145,163,183,237,274],"bioinformatics":[91,106,136],"only":[92,250],"address":[93],"specific":[94],"types,":[96],"inconsistent":[98,257],"assumptions;":[99],"impact":[102,132,229],"databases":[107,181],"has":[108,227],"not":[109,249],"carefully":[111],"assessed,":[112],"making":[113],"it":[114],"difficult":[115],"to":[116,126,256,265],"judge":[117],"value":[119],"such":[121],"methods.":[122],"Our":[123,148,262],"goal":[124],"is":[125],"assess":[127],"scale,":[129],"kinds":[130,216],"databases,":[137],"through":[138],"retrospective":[140],"analysis":[141],"merged":[143,169,279],"groups":[144,170],"INSDC":[146,180],"outcomes":[149],"threefold:":[151],"(1)":[152],"We":[153,194,220,245],"analyse":[154],"benchmark":[156],"dataset":[157,165],"consisting":[158],"manually":[161],"identified":[162],"INSDC-a":[164],"67":[167],"888":[168],"111":[172],"823":[173],"pairs":[175],"across":[176],"21":[177],"organisms":[178,210],"-":[182],"terms":[184,238],"prevalence,":[187],"impacts":[190],"duplicates.":[192],"(2)":[193],"categorize":[195],"at":[197,283],"both":[198],"annotation":[201],"level,":[202],"supporting":[204],"quantitative":[205],"statistics,":[206],"showing":[207],"that":[208,222,247],"distinct":[215],"duplicate.":[218],"(3)":[219],"show":[221],"presence":[224],"practical":[228],"via":[230],"simple":[232],"case":[233],"study":[234],"on":[235],"GC":[240],"content":[241],"melting":[243],"temperature.":[244],"demonstrate":[246],"introduce":[251],"redundancy,":[252],"can":[254],"lead":[255,264],"results":[258],"for":[259],"certain":[260],"tasks.":[261],"findings":[263],"better":[267],"understanding":[268],"problem":[271],"duplication":[273],"biological":[275],"databases.Database":[276],"URL:":[277],"available":[282],"https://cloudstor.aarnet.edu.au/plus/index.php/s/Xef2fvsebBEAv9w.":[284]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
