{"id":"https://openalex.org/W1698298084","doi":"https://doi.org/10.1142/s0218194003001482","title":"MODEL-BASED CLUSTERING IN GENE EXPRESSION MICROARRAYS: AN APPLICATION TO BREAST CANCER DATA","display_name":"MODEL-BASED CLUSTERING IN GENE EXPRESSION MICROARRAYS: AN APPLICATION TO BREAST CANCER DATA","publication_year":2003,"publication_date":"2003-12-01","ids":{"openalex":"https://openalex.org/W1698298084","doi":"https://doi.org/10.1142/s0218194003001482","mag":"1698298084"},"language":"en","primary_location":{"id":"doi:10.1142/s0218194003001482","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218194003001482","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","raw_type":"journal-article"},"type":"article","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/A5025645526","display_name":"Jessica C. Mar","orcid":"https://orcid.org/0000-0002-5147-9299"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"J. C. MAR","raw_affiliation_strings":["Department of Mathematics, University of Queensland, Australia","Department of Mathematics , University of Queensland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Queensland, Australia","institution_ids":["https://openalex.org/I165143802"]},{"raw_affiliation_string":"Department of Mathematics , University of Queensland","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057375178","display_name":"Geoffrey J. McLachlan","orcid":"https://orcid.org/0000-0002-5921-3145"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"G. J. MCLACHLAN","raw_affiliation_strings":["Department of Mathematics, University of Queensland, Australia","Department of Mathematics , University of Queensland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Queensland, Australia","institution_ids":["https://openalex.org/I165143802"]},{"raw_affiliation_string":"Department of Mathematics , University of Queensland","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165143802"],"apc_list":null,"apc_paid":null,"fwci":0.1084,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.43096964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"06","first_page":"579","last_page":"592"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9998999834060669,"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":0.9998999834060669,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9951000213623047,"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":0.9882000088691711,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8797796964645386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6525143384933472},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.622628927230835},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5434986352920532},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.4776291251182556},{"id":"https://openalex.org/keywords/breast-cancer","display_name":"Breast cancer","score":0.46712926030158997},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4645191431045532},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.45256713032722473},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.4279107451438904},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.41656693816185},{"id":"https://openalex.org/keywords/consensus-clustering","display_name":"Consensus clustering","score":0.41115912795066833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40829381346702576},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.3745802044868469},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34830111265182495},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.32560640573501587},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.2918645143508911},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1929681897163391},{"id":"https://openalex.org/keywords/cancer","display_name":"Cancer","score":0.17802748084068298},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.13985633850097656},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1088746190071106}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8797796964645386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6525143384933472},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.622628927230835},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5434986352920532},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.4776291251182556},{"id":"https://openalex.org/C530470458","wikidata":"https://www.wikidata.org/wiki/Q128581","display_name":"Breast cancer","level":3,"score":0.46712926030158997},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4645191431045532},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.45256713032722473},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.4279107451438904},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.41656693816185},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.41115912795066833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40829381346702576},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.3745802044868469},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34830111265182495},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.32560640573501587},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2918645143508911},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1929681897163391},{"id":"https://openalex.org/C121608353","wikidata":"https://www.wikidata.org/wiki/Q12078","display_name":"Cancer","level":2,"score":0.17802748084068298},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.13985633850097656},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1088746190071106},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1142/s0218194003001482","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218194003001482","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.218.9645","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.218.9645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.maths.uq.edu.au/~gjm/mm_ijseke03.pdf","raw_type":"text"},{"id":"pmh:oai:espace.library.uq.edu.au:UQ:2c0094f","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402388","display_name":"Queensland's institutional digital repository (The University of Queensland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165143802","host_organization_name":"The University of Queensland","host_organization_lineage":["https://openalex.org/I165143802"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"mag:1698298084","is_oa":false,"landing_page_url":"http://crpit.com/confpapers/CRPITV19Mar.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306417749","display_name":"Asia-Pacific Bioinformatics Conference","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Asia-Pacific Bioinformatics Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1572134371","https://openalex.org/W2105260721","https://openalex.org/W2107956883","https://openalex.org/W2109970232","https://openalex.org/W2118727666","https://openalex.org/W2128985829","https://openalex.org/W2136097953","https://openalex.org/W2146646206","https://openalex.org/W2147246240","https://openalex.org/W2150926065","https://openalex.org/W2152012752"],"related_works":["https://openalex.org/W2109908629","https://openalex.org/W1013519362","https://openalex.org/W2109372695","https://openalex.org/W1831210132","https://openalex.org/W2546959060","https://openalex.org/W2284869703","https://openalex.org/W2165624043","https://openalex.org/W2969529490","https://openalex.org/W2016348435","https://openalex.org/W2735812438","https://openalex.org/W2049680032","https://openalex.org/W300185981","https://openalex.org/W2738748219","https://openalex.org/W2135667059","https://openalex.org/W2170192148","https://openalex.org/W1541132003","https://openalex.org/W119053326","https://openalex.org/W2189320680","https://openalex.org/W2124052810","https://openalex.org/W158069192"],"abstract_inverted_index":{"In":[0,18],"microarray":[1],"studies,":[2],"the":[3,16,19,25,59,90,98,111,116,133,137,141,144,152,158,172,191,195,203,228],"application":[4,112],"of":[5,51,61,92,113,135,143,154,160,175,197,205,209],"clustering":[6,27,74,91,136],"techniques":[7],"is":[8,54,65,147],"often":[9],"used":[10],"to":[11,30,42,57,72,115,178],"derive":[12],"meaningful":[13],"insights":[14],"into":[15],"data.":[17,231],"past,":[20],"hierarchical":[21,35],"methods":[22,53,219],"have":[23,37,220],"been":[24,38],"primary":[26],"tool":[28],"employed":[29],"perform":[31],"this":[32,77,187],"task.":[33],"The":[34,184],"algorithms":[36],"mainly":[39],"applied":[40],"heuristically":[41],"these":[43,52,73],"cluster":[44],"analysis":[45,131,188],"problems.":[46,75],"Further,":[47],"a":[48,66,69,84,102,107,148,179,206,222],"major":[49],"limitation":[50],"their":[55],"inability":[56],"determine":[58],"number":[60,153,159],"clusters.":[62],"Thus":[63],"there":[64],"need":[67],"for":[68,89,227],"model-based":[70,86,103],"approach":[71],"To":[76,95],"end,":[78],"McLachlan":[79],"et":[80,127],"al.":[81,128],"[7]":[82],"developed":[83],"mixture":[85],"algorithm":[87],"(EMMIX-GENE)":[88],"tissue":[93,138,161,200],"samples.":[94,162],"further":[96],"investigate":[97],"EMMIX-GENE":[99,114,166],"procedure":[100],"as":[101,120],"approach,":[104],"we":[105],"present":[106],"case":[108],"study":[109],"involving":[110],"breast":[117,229],"cancer":[118,230],"data":[119],"studied":[121],"recently":[122],"in":[123,170],"van":[124],"'t":[125],"Veer":[126],"[10].":[129],"Our":[130],"considers":[132],"problem":[134,150],"samples":[139],"on":[140,202,216],"basis":[142,204],"genes":[145,155,176],"which":[146],"non-standard":[149],"because":[151],"greatly":[156],"exceed":[157],"We":[163],"demonstrate":[164],"how":[165],"can":[167],"be":[168],"useful":[169],"reducing":[171],"initial":[173],"set":[174],"down":[177],"more":[180],"computationally":[181],"manageable":[182],"size.":[183],"results":[185,212],"from":[186],"also":[189,213],"emphasise":[190],"difficulty":[192],"associated":[193],"with":[194],"task":[196],"separating":[198],"two":[199],"groups":[201],"particular":[207],"subset":[208],"genes.":[210],"These":[211],"shed":[214],"light":[215],"why":[217],"supervised":[218],"such":[221],"high":[223],"misallocation":[224],"error":[225],"rate":[226]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}