{"id":"https://openalex.org/W2162972849","doi":"https://doi.org/10.1093/bioinformatics/btl065","title":"Incorporating biological knowledge into distance-based clustering analysis of microarray gene expression data","display_name":"Incorporating biological knowledge into distance-based clustering analysis of microarray gene expression data","publication_year":2006,"publication_date":"2006-02-24","ids":{"openalex":"https://openalex.org/W2162972849","doi":"https://doi.org/10.1093/bioinformatics/btl065","mag":"2162972849","pmid":"https://pubmed.ncbi.nlm.nih.gov/16500932"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btl065","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl065","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022711610","display_name":"Desheng Huang","orcid":"https://orcid.org/0000-0001-7648-3625"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]},{"id":"https://openalex.org/I91656880","display_name":"China Medical University","ror":"https://ror.org/032d4f246","country_code":"CN","type":"education","lineage":["https://openalex.org/I91656880"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Desheng Huang","raw_affiliation_strings":["Department of Mathematics, China Medical University 1 \u00a0 1 \u00a0 \u00a0 Shenyang, China","Division of Biostatistics, School of Public Health, University of Minnesota 2 \u00a0 2 \u00a0 \u00a0 Minneapolis, MN 55455-0392, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, China Medical University 1 \u00a0 1 \u00a0 \u00a0 Shenyang, China","institution_ids":["https://openalex.org/I91656880"]},{"raw_affiliation_string":"Division of Biostatistics, School of Public Health, University of Minnesota 2 \u00a0 2 \u00a0 \u00a0 Minneapolis, MN 55455-0392, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018997928","display_name":"Wei Pan","orcid":"https://orcid.org/0000-0002-1159-0582"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wei Pan","raw_affiliation_strings":["Division of Biostatistics, School of Public Health, University of Minnesota 2 \u00a0 2 \u00a0 \u00a0 Minneapolis, MN 55455-0392, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Biostatistics, School of Public Health, University of Minnesota 2 \u00a0 2 \u00a0 \u00a0 Minneapolis, MN 55455-0392, USA","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018997928"],"corresponding_institution_ids":["https://openalex.org/I130238516"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":null,"fwci":6.0943,"has_fulltext":false,"cited_by_count":122,"citation_normalized_percentile":{"value":0.97354758,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"22","issue":"10","first_page":"1259","last_page":"1268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9947999715805054,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9182000160217285,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8146747946739197},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.6701359748840332},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.5522100329399109},{"id":"https://openalex.org/keywords/gene-cluster","display_name":"Gene cluster","score":0.5310395359992981},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.49831414222717285},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4834752678871155},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4668479859828949},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.4372907280921936},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4193379282951355},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3871186375617981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3629786968231201},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.3523380160331726},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.33517467975616455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.221937894821167}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8146747946739197},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.6701359748840332},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5522100329399109},{"id":"https://openalex.org/C36857842","wikidata":"https://www.wikidata.org/wiki/Q1501261","display_name":"Gene cluster","level":3,"score":0.5310395359992981},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.49831414222717285},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4834752678871155},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4668479859828949},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.4372907280921936},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4193379282951355},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3871186375617981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3629786968231201},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.3523380160331726},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.33517467975616455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.221937894821167},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"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":"D001695","descriptor_name":"Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D001695","descriptor_name":"Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D001695","descriptor_name":"Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D005103","descriptor_name":"Expert Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005103","descriptor_name":"Expert Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005103","descriptor_name":"Expert Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"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":"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},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051188","descriptor_name":"Knowledge Bases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D051188","descriptor_name":"Knowledge Bases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D051188","descriptor_name":"Knowledge Bases","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btl065","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl065","pdf_url":null,"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:16500932","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16500932","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":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6240033142","display_name":null,"funder_award_id":"HL65462","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337338","display_name":"National Heart, Lung, and Blood Institute","ror":"https://ror.org/012pb6c26"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1493454437","https://openalex.org/W1494853941","https://openalex.org/W1518360031","https://openalex.org/W1554944419","https://openalex.org/W1594031697","https://openalex.org/W1614659291","https://openalex.org/W1886306325","https://openalex.org/W1967702193","https://openalex.org/W1981246522","https://openalex.org/W1987678450","https://openalex.org/W1994181640","https://openalex.org/W2005107355","https://openalex.org/W2055867223","https://openalex.org/W2082322508","https://openalex.org/W2102794349","https://openalex.org/W2103017472","https://openalex.org/W2105860794","https://openalex.org/W2118727666","https://openalex.org/W2120413242","https://openalex.org/W2122863959","https://openalex.org/W2123106337","https://openalex.org/W2124354935","https://openalex.org/W2133098435","https://openalex.org/W2135000328","https://openalex.org/W2135187880","https://openalex.org/W2135230352","https://openalex.org/W2135364554","https://openalex.org/W2136097953","https://openalex.org/W2137784044","https://openalex.org/W2144317357","https://openalex.org/W2146264532","https://openalex.org/W2146646206","https://openalex.org/W2149097927","https://openalex.org/W2150473224","https://openalex.org/W2150926065","https://openalex.org/W2152012752","https://openalex.org/W2160875291","https://openalex.org/W2164141804","https://openalex.org/W2167119716","https://openalex.org/W2171033594","https://openalex.org/W2330820318","https://openalex.org/W2479390720","https://openalex.org/W2797545377","https://openalex.org/W2999729612","https://openalex.org/W3085162807","https://openalex.org/W3216035567"],"related_works":["https://openalex.org/W2804364458","https://openalex.org/W4298130764","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2083665254","https://openalex.org/W2393816671","https://openalex.org/W1534720161","https://openalex.org/W2804957450","https://openalex.org/W2942177010","https://openalex.org/W3200375535"],"abstract_inverted_index":{"MOTIVATION:":[0],"Because":[1],"co-expressed":[2],"genes":[3,72,103,119,133],"are":[4],"likely":[5],"to":[6,100,129,141,162],"share":[7,73],"the":[8,34,70,84,102,110,114,118,123,131,145,149,167,170,176],"same":[9],"biological":[10],"function,":[11,136],"cluster":[12,101,130],"analysis":[13],"of":[14,36,42,134,139,144,172],"gene":[15,22,31,44,51,61,76,163],"expression":[16],"profiles":[17],"has":[18],"been":[19],"applied":[20],"for":[21,117,166],"function":[23,164],"discovery.":[24],"Most":[25],"existing":[26],"clustering":[27,93,111],"methods":[28],"ignore":[29],"known":[30,50,105,121],"functions":[32,52],"in":[33,90,148],"process":[35],"clustering.":[37],"RESULTS:":[38],"To":[39],"take":[40],"advantage":[41,171],"accumulating":[43],"functional":[45],"annotations,":[46],"we":[47],"propose":[48],"incorporating":[49],"into":[53],"a":[54,60,74],"new":[55,154],"distance":[56,63,86,125],"metric,":[57],"which":[58],"shrinks":[59],"expression-based":[62,124],"towards":[64],"0":[65],"if":[66,69],"and":[67,159],"only":[68],"two":[71],"common":[75],"function.":[77],"A":[78,156],"two-step":[79],"procedure":[80],"is":[81,88,127],"used.":[82],"First,":[83],"shrinkage":[85],"metric":[87,126],"used":[89,128],"any":[91],"distance-based":[92],"method,":[94],"e.g.":[95],"K-medoids":[96],"or":[97,152],"hierarchical":[98],"clustering,":[99],"with":[104,120],"functions.":[106],"Second,":[107],"while":[108],"keeping":[109],"results":[112],"from":[113],"first":[115,150],"step":[116,151],"functions,":[122],"remaining":[132],"unknown":[135],"assigning":[137],"each":[138],"them":[140],"either":[142],"one":[143],"clusters":[146],"obtained":[147],"some":[153],"clusters.":[155],"simulation":[157],"study":[158],"an":[160],"application":[161],"prediction":[165],"yeast":[168],"demonstrate":[169],"our":[173],"proposal":[174],"over":[175],"standard":[177],"method.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":14}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
