{"id":"https://openalex.org/W4393418251","doi":"https://doi.org/10.5281/zenodo.1238858","title":"Literature Consistency Of Bioinformatics Sequence Databases Is Effective For Assessing Record Quality","display_name":"Literature Consistency Of Bioinformatics Sequence Databases Is Effective For Assessing Record Quality","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W4393418251","doi":"https://doi.org/10.5281/zenodo.1238858"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:1238858","is_oa":true,"landing_page_url":"https://zenodo.org/record/1238858","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Literature Consistency of Bioinformatics Sequence Databases is Effective for Assessing Record Quality. bax021 bax021-bax021","raw_type":"info:eu-repo/semantics/other"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/1238858","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018899731","display_name":"Mohamed Reda Bouadjenek","orcid":"https://orcid.org/0000-0003-1807-430X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The 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":"Bouadjenek, Mohamed Reda","raw_affiliation_strings":["University of Melbourne"],"affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","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":"The 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":"Verspoor, Karin","raw_affiliation_strings":["University of Melbourne"],"affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","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":"The 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":"Zobel, Justin","raw_affiliation_strings":["University of Melbourne"],"affiliations":[{"raw_affiliation_string":"University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018899731"],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.991100013256073,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.991100013256073,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9682999849319458,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.9394999742507935,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/consistency","display_name":"Consistency (knowledge bases)","score":0.661585807800293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5478371381759644},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5470127463340759},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5293655395507812},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5009300708770752},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3964245617389679},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3843575417995453},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.35700273513793945},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.35334956645965576},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.22443604469299316},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.11428800225257874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09563013911247253}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.661585807800293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5478371381759644},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5470127463340759},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5293655395507812},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5009300708770752},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3964245617389679},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3843575417995453},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.35700273513793945},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.35334956645965576},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22443604469299316},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.11428800225257874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09563013911247253},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:1238858","is_oa":true,"landing_page_url":"https://zenodo.org/record/1238858","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Literature Consistency of Bioinformatics Sequence Databases is Effective for Assessing Record Quality. bax021 bax021-bax021","raw_type":"info:eu-repo/semantics/other"},{"id":"doi:10.5281/zenodo.1238858","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.1238858","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:1238858","is_oa":true,"landing_page_url":"https://zenodo.org/record/1238858","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Literature Consistency of Bioinformatics Sequence Databases is Effective for Assessing Record Quality. bax021 bax021-bax021","raw_type":"info:eu-repo/semantics/other"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1603736412","https://openalex.org/W4304185162","https://openalex.org/W2061685118","https://openalex.org/W3006282800","https://openalex.org/W2462100143","https://openalex.org/W2003932708","https://openalex.org/W1770503332","https://openalex.org/W2284877871","https://openalex.org/W3125207769","https://openalex.org/W2577825108"],"abstract_inverted_index":{"Bioinformatics":[0],"sequence":[1,77],"databases":[2,78],"such":[3],"as":[4,27,29,123,173,202],"Genbank":[5],"or":[6],"UniProt":[7],"contain":[8],"hundreds":[9],"of":[10,12,14,48,76,82,97,112,152,176,184,246,258,267,273],"millions":[11],"records":[13,18,99,154,197,221,235],"genomic":[15],"data.":[16],"These":[17],"are":[19,117],"derived":[20],"from":[21,24,30,33,45,79],"direct":[22],"submissions":[23,32],"individual":[25],"laboratories,":[26],"well":[28],"bulk":[31],"large-scale":[34],"sequencing":[35],"centres;":[36],"their":[37],"diversity":[38],"and":[39,58,71,89,130,149,213],"scale":[40],"means":[41],"that":[42,142,144,196,228,242,278],"they":[43],"suffer":[44],"a":[46,83,110,121,124,156,174,282],"range":[47],"data":[49,74],"quality":[50,75,114,134,147,151,178],"issues":[51],"including":[52],"errors,":[53],"discrepancies,":[54],"redundancies,":[55],"ambiguities,":[56],"incompleteness":[57],"inconsistencies":[59],"with":[60,100,204,250],"the":[61,73,80,95,103,127,145,150,153,164,182,205,210,231,253,262,265,271],"published":[62,128],"literature.":[63,104,254],"In":[64],"this":[65,185],"work,":[66],"we":[67,93,108,194,240],"seek":[68],"to":[69,102,168,225,237,252],"investigate":[70],"analyze":[72],"perspective":[81],"curator,":[84],"who":[85],"must":[86],"detect":[87],"anomalous":[88],"suspicious":[90,287],"records.":[91,275,288],"Specifically,":[92],"emphasize":[94],"detection":[96,272],"inconsistent":[98,203,249,259],"respect":[101,251],"Focusing":[105],"on":[106,119,163],"GenBank,":[107],"propose":[109,167],"set":[111],"24":[113],"indicators,":[115],"which":[116,160,198],"based":[118],"treating":[120],"record":[122,170,244,260],"query":[125,133],"into":[126],"literature,":[129],"then":[131,137],"use":[132],"predictors.":[135],"We":[136,166,276],"carry":[138],"out":[139,245],"an":[140],"analysis":[141],"shows":[143],"proposed":[146],"indicators":[148],"have":[155,199],"mutual":[157],"relationship,":[158],"in":[159,209,230],"one":[161,243],"depends":[162],"other.":[165],"represent":[169],"literature":[171,206,279],"consistency":[172],"vector":[175],"these":[177],"indicators.":[179],"By":[180,218],"reducing":[181],"dimensionality":[183],"representation":[186],"for":[187,270,285],"visualization":[188],"purposes":[189],"using":[190],"principal":[191],"component":[192],"analysis,":[193],"show":[195,241],"been":[200],"reported":[201],"fall":[207,229],"roughly":[208],"same":[211,232],"area,":[212],"therefore":[214],"share":[215],"similar":[216],"characteristics.":[217],"manually":[219],"analyzing":[220],"not":[222],"previously":[223],"known":[224],"be":[226,238],"erroneous":[227],"area":[233],"than":[234],"know":[236],"inconsistent,":[239],"four":[247],"is":[248,281],"This":[255],"high":[256],"density":[257],"opens":[261],"way":[263],"towards":[264],"development":[266],"automatic":[268],"methods":[269],"faulty":[274],"conclude":[277],"inconsistency":[280],"meaningful":[283],"strategy":[284],"identifying":[286]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
