{"id":"https://openalex.org/W2126631032","doi":"https://doi.org/10.1093/bioinformatics/btl555","title":"Towards clustering of incomplete microarray data without the use of imputation","display_name":"Towards clustering of incomplete microarray data without the use of imputation","publication_year":2006,"publication_date":"2006-10-31","ids":{"openalex":"https://openalex.org/W2126631032","doi":"https://doi.org/10.1093/bioinformatics/btl555","mag":"2126631032","pmid":"https://pubmed.ncbi.nlm.nih.gov/17077099"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btl555","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl555","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/23/1/107/49816333/bioinformatics_23_1_107.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/23/1/107/49816333/bioinformatics_23_1_107.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100764464","display_name":"Dae\u2010Won Kim","orcid":"https://orcid.org/0000-0001-7124-1141"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Dae-Won Kim","raw_affiliation_strings":["School of Computer Science and Engineering, Chung-Ang University 1 \u00a0 1 \u00a0 \u00a0 Seoul City, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Chung-Ang University 1 \u00a0 1 \u00a0 \u00a0 Seoul City, Republic of Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100719658","display_name":"Kiyoung Lee","orcid":"https://orcid.org/0000-0003-2432-6614"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ki-Young Lee","raw_affiliation_strings":["Advanced Information Technology Research Center, KAIST 3 \u00a0 3 \u00a0 \u00a0 Daejeon, Republic of Korea","Department of Bioengineering, University of California at San Diego 2 \u00a0 2 \u00a0 \u00a0 California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Information Technology Research Center, KAIST 3 \u00a0 3 \u00a0 \u00a0 Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Department of Bioengineering, University of California at San Diego 2 \u00a0 2 \u00a0 \u00a0 California, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057288463","display_name":"Kwang H. Lee","orcid":"https://orcid.org/0000-0002-3733-6427"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kwang H. Lee","raw_affiliation_strings":["Advanced Information Technology Research Center, KAIST 3 \u00a0 3 \u00a0 \u00a0 Daejeon, Republic of Korea","Department of Bioengineering, University of California at San Diego 2 \u00a0 2 \u00a0 \u00a0 California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Information Technology Research Center, KAIST 3 \u00a0 3 \u00a0 \u00a0 Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Department of Bioengineering, University of California at San Diego 2 \u00a0 2 \u00a0 \u00a0 California, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037879375","display_name":"Doheon Lee","orcid":"https://orcid.org/0000-0001-9070-4316"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Doheon Lee","raw_affiliation_strings":["Department of BioSystems, KAIST 4 \u00a0 4 \u00a0 \u00a0 Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of BioSystems, KAIST 4 \u00a0 4 \u00a0 \u00a0 Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100764464"],"corresponding_institution_ids":["https://openalex.org/I67900169"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.4052,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.62093423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"23","issue":"1","first_page":"107","last_page":"113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.946399986743927,"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/T10885","display_name":"Gene expression and cancer classification","score":0.946399986743927,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.009200000204145908,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.006899999920278788,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8914211988449097},{"id":"https://openalex.org/keywords/imputation","display_name":"Imputation (statistics)","score":0.7594394087791443},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.7214391231536865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6498477458953857},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.632591187953949},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.5983898639678955},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.48135310411453247},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.47362229228019714},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.4465996026992798},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.42857763171195984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29611289501190186},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18928155303001404}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8914211988449097},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.7594394087791443},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.7214391231536865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6498477458953857},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.632591187953949},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.5983898639678955},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.48135310411453247},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.47362229228019714},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.4465996026992798},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.42857763171195984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29611289501190186},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18928155303001404}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","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},{"descriptor_ui":"D017143","descriptor_name":"Fuzzy Logic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017143","descriptor_name":"Fuzzy Logic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017143","descriptor_name":"Fuzzy Logic","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":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btl555","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl555","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/23/1/107/49816333/bioinformatics_23_1_107.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:17077099","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17077099","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":"Bioinformatics (Oxford, England)","raw_type":null}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btl555","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl555","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/23/1/107/49816333/bioinformatics_23_1_107.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1508853606","https://openalex.org/W1604959358","https://openalex.org/W2023971898","https://openalex.org/W2096863518","https://openalex.org/W2100268885","https://openalex.org/W2102471334","https://openalex.org/W2103017472","https://openalex.org/W2107208924","https://openalex.org/W2107383984","https://openalex.org/W2109174028","https://openalex.org/W2110544411","https://openalex.org/W2111104102","https://openalex.org/W2119253710","https://openalex.org/W2125780188","https://openalex.org/W2127284416","https://openalex.org/W2131456395","https://openalex.org/W2135000328","https://openalex.org/W2135187880","https://openalex.org/W2135364554","https://openalex.org/W2135951244","https://openalex.org/W2138036661","https://openalex.org/W2142460132","https://openalex.org/W2147246240","https://openalex.org/W2150926065","https://openalex.org/W2165011536","https://openalex.org/W2165298438","https://openalex.org/W2170040895","https://openalex.org/W6679045453","https://openalex.org/W6684139453"],"related_works":["https://openalex.org/W2556490192","https://openalex.org/W2892323093","https://openalex.org/W2361242132","https://openalex.org/W3071522575","https://openalex.org/W3140018618","https://openalex.org/W2406185607","https://openalex.org/W2389934482","https://openalex.org/W2374506950","https://openalex.org/W2353443653","https://openalex.org/W4308301473"],"abstract_inverted_index":{"MOTIVATION:":[0],"Clustering":[1,140],"technique":[2],"is":[3,77,124,153,297,300],"used":[4],"to":[5,110,170,256],"find":[6,171],"groups":[7],"of":[8,31,67,73,82,98,116,160,183,207,236,248,263],"genes":[9],"that":[10,34,78,292],"show":[11],"similar":[12],"expression":[13,275],"patterns":[14],"under":[15],"multiple":[16],"experimental":[17],"conditions.":[18],"Nonetheless,":[19],"the":[20,29,56,64,80,88,112,158,181,188,205,208,212,233,240,249,257,290,303],"results":[21,247],"obtained":[22,104],"by":[23,28,186],"cluster":[24,189,193],"analysis":[25],"are":[26,85,92,108,252],"influenced":[27],"existence":[30],"missing":[32,57,83,102,128,184],"values":[33,58,84,103,129,185,199],"commonly":[35],"arise":[36],"in":[37,63,87,105,147,162,200],"microarray":[38],"experiments.":[39],"Because":[40],"a":[41,45,70,120,137,149],"clustering":[42,117,122,132,176,217,225,234,246,272],"method":[43,62,123,138,152,179,238,251],"requires":[44],"complete":[46],"data":[47,106,142,229],"matrix":[48],"as":[49,192],"an":[50,60,166],"input,":[51],"previous":[52],"studies":[53],"have":[54],"estimated":[55,101],"using":[59,143,239,282],"imputation":[61,151,161],"preprocessing":[65,89,107],"step":[66],"clustering.":[68],"However,":[69],"common":[71],"limitation":[72],"these":[74],"conventional":[75,215],"approaches":[76],"once":[79],"estimates":[81,173,182],"fixed":[86],"step,":[90],"they":[91],"not":[93,154],"changed":[94],"during":[95,130,174],"subsequent":[96],"processes":[97],"clustering;":[99],"badly":[100],"likely":[109],"deteriorate":[111],"quality":[113],"and":[114,195,214,231,269,285],"reliability":[115],"results.":[118],"Thus,":[119],"new":[121],"required":[125],"for":[126,139,224,271],"improving":[127],"iterative":[131,175],"process.":[133,177],"RESULTS:":[134],"We":[135],"present":[136],"Incomplete":[141],"Alternating":[144],"Optimization":[145],"(CIAO)":[146],"which":[148],"prior":[150],"required.":[155],"To":[156,203],"reduce":[157],"influence":[159],"preprocessing,":[163],"we":[164,210],"take":[165],"alternative":[167],"optimization":[168],"approach":[169],"better":[172],"This":[178],"improves":[180],"exploiting":[187],"information":[190],"such":[191],"centroids":[194],"all":[196],"available":[197,301],"non-missing":[198],"each":[201,237],"iteration.":[202],"test":[204],"performance":[206],"CIAO,":[209],"applied":[211],"CIAO":[213,250],"imputation-based":[216],"methods,":[218,265],"e.g.":[219],"k-means":[220],"based":[221],"on":[222,289],"KNNimpute,":[223],"two":[226],"yeast":[227],"incomplete":[228,273],"sets,":[230],"compared":[232],"result":[235],"Saccharomyces":[241],"Genome":[242],"Database":[243],"annotations.":[244],"The":[245,278],"more":[253],"significantly":[254],"relevant":[255],"biological":[258],"gene":[259,274],"annotations":[260],"than":[261],"those":[262],"other":[264],"indicating":[266],"its":[267],"effectiveness":[268],"potential":[270],"data.":[276],"AVAILABILITY:":[277],"software":[279],"was":[280],"developed":[281],"Java":[283],"language,":[284],"can":[286],"be":[287],"executed":[288],"platforms":[291],"JVM":[293],"(Java":[294],"Virtual":[295],"Machine)":[296],"running.":[298],"It":[299],"from":[302],"authors":[304],"upon":[305],"request.":[306]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-23T06:36:01.041984","created_date":"2025-10-10T00:00:00"}