{"id":"https://openalex.org/W2107187602","doi":"https://doi.org/10.1142/s0219720005001053","title":"CLUSTERING AND RE-CLUSTERING FOR PATTERN DISCOVERY IN GENE EXPRESSION DATA","display_name":"CLUSTERING AND RE-CLUSTERING FOR PATTERN DISCOVERY IN GENE EXPRESSION DATA","publication_year":2005,"publication_date":"2005-04-01","ids":{"openalex":"https://openalex.org/W2107187602","doi":"https://doi.org/10.1142/s0219720005001053","mag":"2107187602","pmid":"https://pubmed.ncbi.nlm.nih.gov/15852506"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720005001053","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720005001053","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5110693170","display_name":"C. H. Patrick","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"PATRICK C. H. MA","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107049960","display_name":"Keith C. C. Chan","orcid":"https://orcid.org/0000-0001-7962-6564"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"KEITH C. C. CHAN","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102819493","display_name":"David Chiu","orcid":"https://orcid.org/0000-0002-1210-8268"},"institutions":[{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"DAVID K. Y. CHIU","raw_affiliation_strings":["Biophysics Interdepartmental Group and the Department of Computing and Information Science, University of Guelph, Guelph, Ontario, Canada N1G 2W1, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biophysics Interdepartmental Group and the Department of Computing and Information Science, University of Guelph, Guelph, Ontario, Canada N1G 2W1, Canada","institution_ids":["https://openalex.org/I79817857"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3768,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.6038578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"03","issue":"02","first_page":"281","last_page":"301"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9995999932289124,"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":0.9995999932289124,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9876999855041504,"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":0.984499990940094,"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":0.8631198406219482},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5307139158248901},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.457836389541626},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.438287615776062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4346836805343628},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.43266820907592773},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4266943633556366},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.4257006049156189},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.41809818148612976},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.41689029335975647},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37855130434036255},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.33530300855636597},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28853368759155273},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.24860936403274536}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8631198406219482},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5307139158248901},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.457836389541626},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.438287615776062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4346836805343628},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.43266820907592773},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4266943633556366},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4257006049156189},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.41809818148612976},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.41689029335975647},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37855130434036255},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.33530300855636597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28853368759155273},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.24860936403274536},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"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":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","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":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","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":3,"locations":[{"id":"doi:10.1142/s0219720005001053","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720005001053","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},{"id":"pmid:15852506","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15852506","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":"Journal of bioinformatics and computational biology","raw_type":null},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/10149","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/10149","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"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/Magazine Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1483505747","https://openalex.org/W1564049492","https://openalex.org/W1952414028","https://openalex.org/W1991848143","https://openalex.org/W1997704623","https://openalex.org/W2016381774","https://openalex.org/W2032231928","https://openalex.org/W2051893411","https://openalex.org/W2103017472","https://openalex.org/W2103453943","https://openalex.org/W2113310577","https://openalex.org/W2113962581","https://openalex.org/W2125055259","https://openalex.org/W2130618490","https://openalex.org/W2131820435","https://openalex.org/W2133504259","https://openalex.org/W2135000328","https://openalex.org/W2135187880","https://openalex.org/W2135951244","https://openalex.org/W2136061550","https://openalex.org/W2137540340","https://openalex.org/W2142460132","https://openalex.org/W2147055980","https://openalex.org/W2150926065","https://openalex.org/W2165011536","https://openalex.org/W2611831635"],"related_works":["https://openalex.org/W3168768270","https://openalex.org/W4310575853","https://openalex.org/W2389934482","https://openalex.org/W1491908038","https://openalex.org/W4200404937","https://openalex.org/W3176177124","https://openalex.org/W2356030476","https://openalex.org/W197235377","https://openalex.org/W4236597916","https://openalex.org/W4245438342"],"abstract_inverted_index":{"The":[0,26,143,234],"combined":[1],"interpretation":[2],"of":[3,15,19,39,41,58,104,114,122,133,178,180,230,270,286],"gene":[4,8,20,85,167],"expression":[5,21,27,86,115,168,193,271],"data":[6,28,116],"and":[7,96,138,155,173,191,198,247,250,268,276],"sequences":[9],"is":[10],"important":[11],"for":[12,209,224,306],"the":[13,16,23,37,49,55,61,102,112,203,216,228,264,283,287,307],"investigation":[14],"intricate":[17],"relationships":[18],"at":[22,282],"transcription":[24,67,294],"level.":[25],"produced":[29],"by":[30,48,66,119,158],"microarray":[31],"hybridization":[32],"experiments":[33,93],"can":[34,71,219,303],"lead":[35],"to":[36,80,126,244],"identification":[38],"clusters":[40,83,226],"co-expressed":[42,59,262,288,308],"genes":[43,261],"that":[44,101,215,236],"are":[45,237,242],"likely":[46],"co-regulated":[47],"same":[50,265],"regulatory":[51,63,280],"mechanisms.":[52],"By":[53],"analyzing":[54],"promoter":[56,284],"regions":[57,285],"genes,":[60,289],"common":[62],"patterns":[64,182,204,235,281],"characterized":[65,118],"factor":[68,295],"binding":[69,296,301],"sites":[70,297,302],"be":[72,108,220,245,253],"revealed.":[73],"Many":[74],"clustering":[75,113,130,136],"algorithms":[76,106],"have":[77,273],"been":[78,274],"used":[79],"uncover":[81],"inherent":[82],"in":[84,170,183,206,227,239,298],"data.":[87,233],"In":[88],"this":[89],"paper,":[90],"based":[91],"on":[92,257],"using":[94],"simulated":[95],"real":[97],"data,":[98],"we":[99,124,290],"show":[100,214],"performance":[103],"these":[105,258],"could":[107],"further":[109],"improved.":[110],"For":[111],"typically":[117],"a":[120,128,139,161,174],"lot":[121],"noise,":[123],"propose":[125],"use":[127],"two-phase":[129],"algorithm":[131,145,218,223],"consisting":[132],"an":[134,221],"initial":[135],"phase":[137],"second":[140],"re-clustering":[141],"phase.":[142],"proposed":[144,217],"has":[146],"several":[147],"desirable":[148],"features:":[149],"(i)":[150],"it":[151,187,200],"utilizes":[152],"both":[153,160],"local":[154],"global":[156],"information":[157],"computing":[159],"\"local\"":[162],"pairwise":[163],"distance":[164],"between":[165,189],"two":[166],"profiles":[169],"Phase":[171,184],"1":[172],"\"global\"":[175],"probabilistic":[176],"measure":[177],"interestingness":[179],"cluster":[181,208,241],"2,":[185],"(ii)":[186],"distinguishes":[188],"relevant":[190],"irrelevant":[192],"values":[194],"when":[195],"performing":[196],"re-clustering,":[197],"(iii)":[199],"makes":[201],"explicit":[202],"discovered":[205,238,259,292],"each":[207,240],"possible":[210],"interpretations.":[211],"Experimental":[212],"results":[213],"effective":[222],"discovering":[225],"presence":[229],"very":[231],"noisy":[232],"found":[243],"meaningful":[246],"statistically":[248],"significant,":[249],"cannot":[251],"otherwise":[252],"easily":[254],"discovered.":[255],"Based":[256],"patterns,":[260],"under":[263],"experimental":[266],"conditions":[267],"range":[269],"levels":[272],"identified":[275],"evaluated.":[277],"When":[278],"identifying":[279],"also":[291],"well-known":[293],"them.":[299],"These":[300],"provide":[304],"explanations":[305],"patterns.":[309]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
