{"id":"https://openalex.org/W3175550653","doi":"https://doi.org/10.31274/etd-20210609-9","title":"Towards data cleaning in large public biological databases","display_name":"Towards data cleaning in large public biological databases","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3175550653","doi":"https://doi.org/10.31274/etd-20210609-9","mag":"3175550653"},"language":"en","primary_location":{"id":"doi:10.31274/etd-20210609-9","is_oa":true,"landing_page_url":"https://doi.org/10.31274/etd-20210609-9","pdf_url":"https://dr.lib.iastate.edu/bitstreams/ed1215b9-174a-4abf-8324-1d0f1ffe47dd/download","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iowa State University","raw_type":"dissertation"},"type":"dissertation","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dr.lib.iastate.edu/bitstreams/ed1215b9-174a-4abf-8324-1d0f1ffe47dd/download","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024822802","display_name":"Hamid Bagheri","orcid":"https://orcid.org/0000-0003-1540-7797"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hamid Bagheri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5024822802"],"corresponding_institution_ids":[],"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9757999777793884,"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":0.9757999777793884,"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":0.975600004196167,"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":0.9746000170707703,"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/metadata","display_name":"Metadata","score":0.8697330951690674},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7139649391174316},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6694340705871582},{"id":"https://openalex.org/keywords/biological-database","display_name":"Biological database","score":0.5746759176254272},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5524592995643616},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.51182621717453},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.49527135491371155},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4939587712287903},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.48395422101020813},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4829842150211334},{"id":"https://openalex.org/keywords/biological-data","display_name":"Biological data","score":0.4260195791721344},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41554999351501465},{"id":"https://openalex.org/keywords/public-domain","display_name":"Public domain","score":0.41358980536460876},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4007470905780792},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18448656797409058},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1224408745765686},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.11779284477233887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11586740612983704},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10121208429336548}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8697330951690674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7139649391174316},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6694340705871582},{"id":"https://openalex.org/C20901353","wikidata":"https://www.wikidata.org/wiki/Q4117139","display_name":"Biological database","level":2,"score":0.5746759176254272},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5524592995643616},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.51182621717453},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.49527135491371155},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4939587712287903},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.48395422101020813},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4829842150211334},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.4260195791721344},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41554999351501465},{"id":"https://openalex.org/C512654426","wikidata":"https://www.wikidata.org/wiki/Q19652","display_name":"Public domain","level":2,"score":0.41358980536460876},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4007470905780792},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18448656797409058},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1224408745765686},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.11779284477233887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11586740612983704},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10121208429336548},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.31274/etd-20210609-9","is_oa":true,"landing_page_url":"https://doi.org/10.31274/etd-20210609-9","pdf_url":"https://dr.lib.iastate.edu/bitstreams/ed1215b9-174a-4abf-8324-1d0f1ffe47dd/download","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iowa State University","raw_type":"dissertation"},{"id":"pmh:oai:lib.dr.iastate.edu:etd-9455","is_oa":false,"landing_page_url":"https://lib.dr.iastate.edu/cgi/viewcontent.cgi?article=9455&context=etd","pdf_url":null,"source":{"id":"https://openalex.org/S4377196104","display_name":"Iowa State University Digital Repository (Iowa State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173911158","host_organization_name":"Iowa State University","host_organization_lineage":["https://openalex.org/I173911158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Graduate Theses and Dissertations","raw_type":"text"},{"id":"pmh:oai:dr.lib.iastate.edu:20.500.12876/dvmqEmbv","is_oa":false,"landing_page_url":"https://dr.lib.iastate.edu/handle/20.500.12876/dvmqEmbv","pdf_url":null,"source":{"id":"https://openalex.org/S4377196104","display_name":"Iowa State University Digital Repository (Iowa State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173911158","host_organization_name":"Iowa State University","host_organization_lineage":["https://openalex.org/I173911158"],"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":"dissertation"}],"best_oa_location":{"id":"doi:10.31274/etd-20210609-9","is_oa":true,"landing_page_url":"https://doi.org/10.31274/etd-20210609-9","pdf_url":"https://dr.lib.iastate.edu/bitstreams/ed1215b9-174a-4abf-8324-1d0f1ffe47dd/download","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Iowa State University","raw_type":"dissertation"},"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4381571608","https://openalex.org/W4392894140","https://openalex.org/W2936116675","https://openalex.org/W2291027050","https://openalex.org/W2307569040","https://openalex.org/W1018570427","https://openalex.org/W1483126190","https://openalex.org/W2131941936","https://openalex.org/W4214664950","https://openalex.org/W4242570880"],"abstract_inverted_index":{"As":[0,17],"the":[1,6,24,42,48,54,72,81,84,111,118,124,135,139,142,167,172,184,194,199,205,223,240,289,293,306,315,352,355,379,388,404,408,439,462,474,487,502,508,543],"cost":[2],"of":[3,8,50,53,113,129,134,141,183,196,201,239,245,292,308,354,381,394,465,480,486,492,539,542],"sequencing":[4,18],"decreases,":[5],"amount":[7,200],"data":[9,19,32,51,290],"being":[10],"deposited":[11],"into":[12,368],"public":[13,43,58,143,148,241,356,526,544],"repositories":[14,45,144],"isincreasing":[15],"rapidly.":[16],"continues":[20],"to":[21,33,71,79,93,109,121,171,219,247,272,285,332,341,350,424,501,535],"accumulate":[22],"in":[23,67,166,204,438,468,494,507,514,522],"online":[25],"repositories,":[26],"scientists":[27],"can":[28],"increasingly":[29],"use":[30],"multi-tiered":[31],"better":[34],"answer":[35],"biological":[36,44,250],"questions.":[37],"One":[38],"main":[39],"challenge":[40],"that":[41,328,364,373,387,442,461],"have":[46,62,161,338,434,443],"is":[47,414,418,477],"problem":[49],"quality":[52,128,291,353],"metadata.":[55],"Unfortunately,":[56],"most":[57],"databases":[59,545],"do":[60,80,159],"not":[61,160,209],"methods":[63,162],"for":[64,74,163,174,255,376,403,422,504],"identifying":[65,164],"errors":[66,165,541],"their":[68],"metadata,":[69,169],"leading":[70,170],"potential":[73,173,466,503],"error":[75,175,505],"propagation.":[76,176],"In":[77,96,344],"order":[78],"cleaning":[82,140,523],"at":[83,145,276,470,546],"large":[85],"scale,":[86],"scalable":[87],"infrastructure":[88,390],"and":[89,104,127,158,214,221,227,264,298,324,399,417,428],"algorithms":[90],"are":[91,329,454,484],"needed":[92],"be":[94,518,533],"developed.":[95],"this":[97,345,515],"dissertation,":[98,346],"we":[99,295,318,347,530],"built":[100],"a":[101,180,301,361,369,497,519],"domain-specific":[102],"language":[103],"large-scale":[105,405,525],"infrastructure,":[106],"called":[107],"BoaG,":[108],"analyze":[110],"wealth":[112],"genomics":[114,357],"data.":[115],"We":[116,212,231,268,359,385,433,458],"used":[117,235],"BoaG\u2019s":[119,412],"interface":[120],"reason":[122],"about":[123],"provenance,":[125],"frequencies,":[126],"annotations.":[130,230],"The":[131,243,411,528],"second":[132],"part":[133],"dissertation":[136,516],"focuses":[137],"on":[138,155,179,190,305,407],"scale.":[146,547],"Most":[147],"databases,":[149],"such":[150],"as":[151],"non-redundant":[152],"(NR),":[153],"rely":[154],"user":[156],"input":[157],"provided":[168,300,391,400],"Previous":[177],"research":[178],"small":[181],"subset":[182],"NR":[185,274,409,440,495],"database":[186,207,441],"analyzed":[187],"misclassification":[188,203],"based":[189,304],"sequence":[191,236],"similarity.":[192],"To":[193,287],"best":[195],"our":[197],"knowledge,":[198],"taxonomic":[202,225,448],"entire":[206],"has":[208,252,496],"been":[210,253,339],"quantified.":[211],"proposed":[213,360,513,531],"developed":[215],"an":[216],"automatic":[217,401],"approach":[218],"detect":[220,333],"remove":[222],"suspicious":[224],"assignments":[226],"mispredicted":[228,335],"functional":[229,256,316,382],"also":[232,415,459],"addressed":[233],"widely":[234],"clustering":[237],"information":[238],"databases.":[242,358,527],"usefulness":[244],"clusters":[246,469],"explore":[248],"different":[249,277,426],"analyses":[251,406],"shown":[254],"annotation,":[257],"family":[258],"classification,":[259],"systems":[260],"biology,":[261],"structural":[262],"genomics,":[263],"phylogenetic":[265],"analysis":[266],"[73].":[267],"utilized":[269,319,340],"CD-HIT":[270],"[33]":[271],"cluster":[273],"sequences":[275,310],"similarity":[278],"levels,":[279],"i.e.":[280],"95%,":[281],"90%,":[282],"85%,":[283],"down":[284],"65%.":[286],"improve":[288,351],"clusters,":[294,482],"removed":[296],"anomalies":[297],"then":[299],"confidence":[302],"score":[303],"lineage":[307],"all":[309],"within":[311],"each":[312],"cluster.":[313],"For":[314],"annotations,":[317],"protein":[320],"ontology":[321,366],"(PRO)":[322],"[58]":[323],"Gene":[325],"Ontology":[326],"[11]":[327],"knowledge-based":[330],"graphs":[331,367],"potentially":[334,455],"functions.":[336],"Ontologies":[337],"express":[342],"knowledge.":[343],"leveraged":[348],"them":[349,430],"computational":[362],"method":[363,512],"abstracts":[365],"lower-dimensional":[370],"network":[371],"representation":[372],"makes":[374],"reasoning":[375],"inconsistencies":[377],"among":[378,431,450],"list":[380],"annotations":[383],"easier.":[384],"found":[386,460],"BoaG":[389],"fewer":[392],"lines":[393],"code,":[395],"reduced":[396],"storage":[397],"size,":[398],"parallelization":[402],"dataset.":[410],"web-interface":[413],"implemented":[416],"made":[419],"publicly":[420],"available":[421],"researchers":[423],"test":[425],"hypotheses":[427],"share":[429],"others.":[432],"identified":[435],"\u201c29,175,336\"":[436],"proteins":[437],"more":[444],"than":[445],"one":[446],"distinct":[447],"assignments,":[449],"which":[451,483],"\u201c2,238,230\"":[452],"(7.6%)":[453],"taxonomically":[456],"misclassified.":[457],"total":[463,488],"number":[464],"misclassifications":[467,493],"95%":[471],"similarity,":[472],"above":[473],"genus":[475],"level,":[476],"\u201c3,689,089\"":[478],"out":[479],"88M":[481],"4%":[485],"clusters.":[489],"This":[490,511],"percentage":[491],"significant":[498],"impact":[499],"due":[500],"propagation":[506],"downstream":[509],"analysis.":[510],"will":[517],"valuable":[520],"tool":[521],"up":[524],"technique":[529],"could":[532],"extended":[534],"address":[536],"other":[537],"kinds":[538],"annotation":[540]},"counts_by_year":[],"updated_date":"2026-05-19T21:40:30.786675","created_date":"2025-10-10T00:00:00"}