{"id":"https://openalex.org/W2039506348","doi":"https://doi.org/10.1504/ijiq.2007.013376","title":"Biological data cleaning: a case study","display_name":"Biological data cleaning: a case study","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2039506348","doi":"https://doi.org/10.1504/ijiq.2007.013376","mag":"2039506348"},"language":"en","primary_location":{"id":"doi:10.1504/ijiq.2007.013376","doi":"https://doi.org/10.1504/ijiq.2007.013376","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijiq.2007.013376","pdf_url":null,"source":{"id":"https://openalex.org/S175820504","display_name":"International Journal of Information Quality","issn_l":"1751-0457","issn":["1751-0457","1751-0465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","poland-20"],"host_organization":"https://openalex.org/P4310317825","host_organization_name":"Inderscience Publishers","host_organization_lineage":["https://openalex.org/P4310317825"],"host_organization_lineage_names":["Inderscience Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Information Quality","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090641466","display_name":"Katherine G. Herbert","orcid":"https://orcid.org/0000-0001-6663-8187","observed_orcids":["https://orcid.org/0000-0001-6663-8187"]},"institutions":[{"id":"https://openalex.org/I166088655","display_name":"Montclair State University","ror":"https://ror.org/01nxc2t48","country_code":"US","type":"education","lineage":["https://openalex.org/I166088655"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine G. Herbert","raw_affiliation_strings":["Department of Computer Science, Montclair State University, Montclair, New Jersey, 07043, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Montclair State University, Montclair, New Jersey, 07043, USA","institution_ids":["https://openalex.org/I166088655"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071617030","display_name":"Jason T.L. Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason T.L. Wang","raw_affiliation_strings":["Bioinformatics Center and Department of Computer Science, New Jersey Institute of Technology, University Heights, Newark, NJ 07102, USA","Bioinformatics Center and Department of Computer Science, New Jersey Institute of Technology, University Heights, Newark, NJ 07102, USA.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Center and Department of Computer Science, New Jersey Institute of Technology, University Heights, Newark, NJ 07102, USA","institution_ids":["https://openalex.org/I118118575"]},{"raw_affiliation_string":"Bioinformatics Center and Department of Computer Science, New Jersey Institute of Technology, University Heights, Newark, NJ 07102, USA.#TAB#","institution_ids":["https://openalex.org/I118118575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5846,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.81079727,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"1","issue":"1","first_page":"60","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11937","display_name":"Research Data Management Practices","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0,"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/data-quality","display_name":"data quality","score":0.9850000143051147},{"id":"https://openalex.org/keywords/biological-databases","display_name":"biological databases","score":0.9399999976158142},{"id":"https://openalex.org/keywords/data-uniformity","display_name":"data uniformity","score":0.9380000233650208},{"id":"https://openalex.org/keywords/data-duplication","display_name":"data duplication","score":0.9940000176429749},{"id":"https://openalex.org/keywords/treebase","display_name":"TreeBASE","score":0.9679999947547913},{"id":"https://openalex.org/keywords/phylogenetic-data","display_name":"phylogenetic data","score":0.9599999785423279},{"id":"https://openalex.org/keywords/data-standardization","display_name":"data standardization","score":0.8629999756813049}],"concepts":[{"id":"https://openalex.org/C504723692","wikidata":"https://www.wikidata.org/wiki/Q134471","display_name":"Ajax","level":3,"score":0.8059715628623962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562078237533569},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.7337154150009155},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.6290396451950073},{"id":"https://openalex.org/C20901353","wikidata":"https://www.wikidata.org/wiki/Q4117139","display_name":"Biological database","level":2,"score":0.5853493213653564},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5639598965644836},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5214497447013855},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4479838013648987},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44114065170288086},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4369394779205322},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3734024465084076},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24604493379592896},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.11596530675888062},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.11401912569999695},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08205941319465637},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1504/ijiq.2007.013376","doi":"https://doi.org/10.1504/ijiq.2007.013376","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijiq.2007.013376","pdf_url":null,"source":{"id":"https://openalex.org/S175820504","display_name":"International Journal of Information Quality","issn_l":"1751-0457","issn":["1751-0457","1751-0465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","poland-20"],"host_organization":"https://openalex.org/P4310317825","host_organization_name":"Inderscience Publishers","host_organization_lineage":["https://openalex.org/P4310317825"],"host_organization_lineage_names":["Inderscience Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Information Quality","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335661","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W24499750","https://openalex.org/W1485156179","https://openalex.org/W1551385575","https://openalex.org/W1594907713","https://openalex.org/W1610496399","https://openalex.org/W1612155886","https://openalex.org/W1992673035","https://openalex.org/W1999823970","https://openalex.org/W2020191321","https://openalex.org/W2024770506","https://openalex.org/W2044968452","https://openalex.org/W2063337053","https://openalex.org/W2065199439","https://openalex.org/W2071346253","https://openalex.org/W2075203604","https://openalex.org/W2075268020","https://openalex.org/W2082246635","https://openalex.org/W2087183379","https://openalex.org/W2103538877","https://openalex.org/W2105423800","https://openalex.org/W2106895292","https://openalex.org/W2107159615","https://openalex.org/W2110993096","https://openalex.org/W2112620675","https://openalex.org/W2147809382","https://openalex.org/W2338532967"],"related_works":["https://openalex.org/W7095146544","https://openalex.org/W2913916970","https://openalex.org/W2044968452","https://openalex.org/W7098495526","https://openalex.org/W4225140077","https://openalex.org/W4230493542","https://openalex.org/W7099309401","https://openalex.org/W2898111732","https://openalex.org/W2003951409","https://openalex.org/W2978395240"],"abstract_inverted_index":{"As":[0],"databases":[1,16],"become":[2],"more":[3],"pervasive":[4],"through":[5],"the":[6,33,50],"biological":[7,53,78],"sciences,":[8],"various":[9],"data":[10,20,24,26,29,54,79,84,113],"quality":[11,21,80],"concerns":[12],"are":[13],"emerging.":[14],"Biological":[15],"tend":[17],"to":[18,32,55,66,83,92],"develop":[19],"issues":[22,76],"regarding":[23],"legacy,":[25],"uniformity":[27],"and":[28,44,58,61,70,102],"duplication.":[30],"Due":[31],"nature":[34],"of":[35,39,109],"this":[36],"data,":[37],"each":[38],"these":[40,94],"problems":[41,48],"is":[42],"non-trivial":[43],"can":[45],"cause":[46],"many":[47],"for":[49,100,104],"database.":[51],"For":[52],"be":[56,64],"corrected":[57],"standardised,":[59],"methods":[60],"frameworks":[62],"must":[63],"developed":[65,91],"handle":[67],"both":[68],"structural":[69],"traditional":[71],"data.":[72],"This":[73],"paper":[74],"discusses":[75],"concerning":[77],"with":[81],"respect":[82],"cleaning.":[85],"It":[86,96],"presents":[87],"BIO-AJAX,":[88],"a":[89],"framework":[90],"address":[93],"issues.":[95],"finally":[97],"describes":[98],"BIO-JAX":[99],"TreeBASE":[101],"BIO-AJAX":[103,110],"Lineage":[105],"Path,":[106],"two":[107],"implementations":[108],"on":[111],"phylogenetic":[112],"sets.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}
