{"id":"https://openalex.org/W2756231919","doi":"https://doi.org/10.1186/s12859-017-1832-4","title":"Cleaning by clustering: methodology for addressing data quality issues in biomedical metadata","display_name":"Cleaning by clustering: methodology for addressing data quality issues in biomedical metadata","publication_year":2017,"publication_date":"2017-09-18","ids":{"openalex":"https://openalex.org/W2756231919","doi":"https://doi.org/10.1186/s12859-017-1832-4","mag":"2756231919","pmid":"https://pubmed.ncbi.nlm.nih.gov/28923003"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-017-1832-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-017-1832-4","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-017-1832-4","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/s12859-017-1832-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100727084","display_name":"Wei Hu","orcid":"https://orcid.org/0000-0003-3635-6335"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Hu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, 163 Xianlin Avenue, Nanjing, 210023, Jiangsu, China","State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, 163 Xianlin Avenue, Nanjing, 210023, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053300261","display_name":"Amrapali Zaveri","orcid":"https://orcid.org/0000-0003-3239-4588"},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Amrapali Zaveri","raw_affiliation_strings":["Institute of Data Science, Maastricht University, Maastricht, 6200, MD, The Netherlands","Institute of Data Science, Maastricht University, Maastricht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Data Science, Maastricht University, Maastricht, 6200, MD, The Netherlands","institution_ids":["https://openalex.org/I34352273"]},{"raw_affiliation_string":"Institute of Data Science, Maastricht University, Maastricht, The Netherlands","institution_ids":["https://openalex.org/I34352273"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089019302","display_name":"Honglei Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honglei Qiu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, 163 Xianlin Avenue, Nanjing, 210023, Jiangsu, China","State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, 163 Xianlin Avenue, Nanjing, 210023, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044836472","display_name":"Michel Dumontier","orcid":"https://orcid.org/0000-0003-4727-9435"},"institutions":[{"id":"https://openalex.org/I34352273","display_name":"Maastricht University","ror":"https://ror.org/02jz4aj89","country_code":"NL","type":"education","lineage":["https://openalex.org/I34352273"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Michel Dumontier","raw_affiliation_strings":["Institute of Data Science, Maastricht University, Maastricht, 6200, MD, The Netherlands. michel.dumontier@maastrichtuniversity.nl","Institute of Data Science, Maastricht University, Maastricht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Data Science, Maastricht University, Maastricht, 6200, MD, The Netherlands. michel.dumontier@maastrichtuniversity.nl","institution_ids":["https://openalex.org/I34352273"]},{"raw_affiliation_string":"Institute of Data Science, Maastricht University, Maastricht, The Netherlands","institution_ids":["https://openalex.org/I34352273"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5044836472"],"corresponding_institution_ids":["https://openalex.org/I34352273"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.8108,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.71123872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"18","issue":"1","first_page":"415","last_page":"415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.6935999989509583,"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":0.6935999989509583,"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":0.18790000677108765,"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/T11719","display_name":"Data Quality and Management","score":0.0210999995470047,"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/metadata","display_name":"Metadata","score":0.7828394174575806},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6151601076126099},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5972315073013306},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5679239630699158},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4846494793891907},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3474653363227844},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33818578720092773},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1609192192554474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08737123012542725}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7828394174575806},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6151601076126099},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5972315073013306},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5679239630699158},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4846494793891907},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3474653363227844},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33818578720092773},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1609192192554474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08737123012542725},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000068598","descriptor_name":"Data Accuracy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000068598","descriptor_name":"Data Accuracy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000068598","descriptor_name":"Data Accuracy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D000071253","descriptor_name":"Metadata","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/s12859-017-1832-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-017-1832-4","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-017-1832-4","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:28923003","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28923003","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:cris.maastrichtuniversity.nl:openaire/0c7feb5f-5bbc-465b-b821-73693433bda6","is_oa":true,"landing_page_url":"https://cris.maastrichtuniversity.nl/en/publications/0c7feb5f-5bbc-465b-b821-73693433bda6","pdf_url":null,"source":{"id":"https://openalex.org/S4306402616","display_name":"Research Publications (Maastricht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I34352273","host_organization_name":"Maastricht University","host_organization_lineage":["https://openalex.org/I34352273"],"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":"Hu, W, Zaveri, A, Qiu, H & Dumontier, M 2017, 'Cleaning by clustering: methodology for addressing data quality issues in biomedical metadata', BMC Bioinformatics, vol. 18, no. 1. https://doi.org/10.1186/s12859-017-1832-4","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:doaj.org/article:95b281a1929041f8a5d6ce36331bf14f","is_oa":true,"landing_page_url":"https://doaj.org/article/95b281a1929041f8a5d6ce36331bf14f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"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 18, Iss 1, Pp 1-12 (2017)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:4532882","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5604298","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-017-1832-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-017-1832-4","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-017-1832-4","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/G2045640452","display_name":"\u57fa\u4e8e\u8bed\u4e49Web\u7684\u5b9e\u4f53\u5173\u8054\u641c\u7d22\u65b9\u6cd5\u4e0e\u6280\u672f\u7814\u7a76","funder_award_id":"61572247","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4000668045","display_name":null,"funder_award_id":"61370019 and 61572247","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4115611980","display_name":"\u57fa\u4e8e\u5927\u4f17\u53c2\u4e0e\u7684\u8bed\u4e49Web\u5b9e\u4f53\u94fe\u63a5\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61370019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2756231919.pdf","grobid_xml":"https://content.openalex.org/works/W2756231919.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W509898","https://openalex.org/W87092222","https://openalex.org/W288036102","https://openalex.org/W1544923801","https://openalex.org/W1673310716","https://openalex.org/W1878684993","https://openalex.org/W1970169482","https://openalex.org/W1986190756","https://openalex.org/W2012953300","https://openalex.org/W2057712948","https://openalex.org/W2070040136","https://openalex.org/W2094678200","https://openalex.org/W2114325274","https://openalex.org/W2118258530","https://openalex.org/W2134891969","https://openalex.org/W2137799805","https://openalex.org/W2140655242","https://openalex.org/W2141051060","https://openalex.org/W2150926065","https://openalex.org/W2250861254","https://openalex.org/W3125261728","https://openalex.org/W3204616723"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2137479650","https://openalex.org/W2245479382","https://openalex.org/W2135768893","https://openalex.org/W3139296374","https://openalex.org/W176219849","https://openalex.org/W3021414116","https://openalex.org/W4387803644","https://openalex.org/W4210350690","https://openalex.org/W2791222374"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1],"ability":[2,93],"to":[3,12,23,40,61,69,96,107,128,148,160,187,263,266,278,314,364],"efficiently":[4],"search":[5],"and":[6,87,105,113,183,190,230,299,317,342,344,352],"filter":[7],"datasets":[8,100],"depends":[9],"on":[10,99,177,214],"access":[11],"high":[13],"quality":[14,81,131],"metadata.":[15,138],"While":[16],"most":[17,296],"biomedical":[18,366],"repositories":[19],"require":[20],"data":[21,130,340,367],"submitters":[22],"provide":[24],"a":[25,108,125,155,199,234],"minimal":[26],"set":[27],"of":[28,47,94,116,145,217],"metadata,":[29],"some":[30],"such":[31],"as":[32],"the":[33,45,63,66,72,92,117,236,253,301,336,347],"Gene":[34],"Expression":[35],"Omnibus":[36],"(GEO)":[37],"allows":[38],"users":[39],"specify":[41],"additional":[42],"metadata":[43,67,150,171,297],"in":[44,76,98,133,204,346],"form":[46],"textual":[48],"key-value":[49,74],"pairs":[50,75],"(e.g.":[51],"sex:":[52],"female).":[53],"However,":[54],"since":[55],"there":[56,256,270],"is":[57,328],"no":[58],"structured":[59,112],"vocabulary":[60],"guide":[62],"submitter":[64],"regarding":[65],"terms":[68],"use,":[70],"consequently,":[71],"44,000,000+":[73],"GEO":[77],"suffer":[78],"from":[79],"numerous":[80],"issues":[82,90,132,338],"including":[83],"redundancy,":[84],"heterogeneity,":[85],"inconsistency,":[86],"incompleteness.":[88],"Such":[89],"hinder":[91],"scientists":[95],"hone":[97],"that":[101,173,259,267,279,311,323],"meet":[102],"their":[103],"requirements":[104],"point":[106],"need":[109],"for":[110,295,339],"accurate,":[111],"complete":[114],"description":[115],"data.":[118],"METHODS:":[119],"In":[120,252],"this":[121],"study,":[122],"we":[123,140,153],"propose":[124],"clustering-based":[126],"approach":[127,284,291],"address":[129],"biomedical,":[134],"specifically":[135],"gene":[136],"expression,":[137],"First,":[139],"present":[141],"three":[142],"different":[143,333],"kinds":[144],"similarity":[146],"measures":[147],"compare":[149],"keys.":[151],"Second,":[152],"design":[154],"scalable":[156],"agglomerative":[157,167],"clustering":[158,327],"algorithm":[159,169,237,308,359],"cluster":[161,168,349],"similar":[162,313],"keys":[163,172,207,243,258,273,298,310,331,345],"together.":[164,193,320],"RESULTS:":[165],"Our":[166,290,307,321,358],"identified":[170,261,309],"were":[174,208,250,257,260,271,275,312],"similar,":[175],"based":[176,213],"(i)":[178,219],"name,":[179],"(ii)":[180,221],"core":[181],"concept":[182],"(iii)":[184,224],"value":[185],"similarities,":[186],"each":[188,315],"other":[189,287,316,365],"grouped":[191,209,318],"them":[192,294,319],"We":[194,281],"evaluated":[195],"our":[196,283],"method":[197],"using":[198],"manually":[200],"created":[201],"gold":[202],"standard":[203],"which":[205,274],"359":[206],"into":[210,332],"27":[211],"clusters":[212,240,245,334],"six":[215],"types":[216],"characteristics:":[218],"age,":[220],"cell":[222],"line,":[223],"disease,":[225],"(iv)":[226],"strain,":[227],"(v)":[228],"tissue":[229],"(vi)":[231],"treatment.":[232],"As":[233],"result,":[235],"generated":[238],"18":[239,254],"containing":[241],"355":[242],"(four":[244],"with":[246,285,350],"only":[247],"one":[248],"key":[249],"excluded).":[251],"clusters,":[255],"correctly":[262],"be":[264,356,362],"related":[265,277],"cluster,":[268],"but":[269],"13":[272],"not":[276],"cluster.":[280],"compared":[282],"four":[286],"published":[288],"methods.":[289],"significantly":[292],"outperformed":[293],"achieved":[300],"best":[302],"average":[303],"F-Score":[304],"(0.63).":[305],"CONCLUSION:":[306],"intuition":[322],"underpins":[324],"cleaning":[325],"by":[326],"that,":[329],"dividing":[330],"resolves":[335],"scalability":[337],"observation":[341],"cleaning,":[343],"same":[348],"duplicates":[351],"errors":[353],"can":[354,360],"easily":[355],"found.":[357],"also":[361],"applied":[363],"types.":[368]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}