{"id":"https://openalex.org/W2098566726","doi":"https://doi.org/10.1093/bioinformatics/bth124","title":"Evaluation and optimization of clustering in gene expression data analysis","display_name":"Evaluation and optimization of clustering in gene expression data analysis","publication_year":2004,"publication_date":"2004-02-12","ids":{"openalex":"https://openalex.org/W2098566726","doi":"https://doi.org/10.1093/bioinformatics/bth124","mag":"2098566726","pmid":"https://pubmed.ncbi.nlm.nih.gov/14962920"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bth124","doi":"https://doi.org/10.1093/bioinformatics/bth124","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth124","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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://nrc-publications.canada.ca/eng/view/accepted/?id=7b1a57ef-d70d-46db-8bf6-578f42951f41","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089654819","display_name":"A. Fazel Famili","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"A. Fazel Famili","raw_affiliation_strings":["Institute for Information Technology, National Research Council of Canada, Ottawa, ON, Canada, K1A 0R6"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Information Technology, National Research Council of Canada, Ottawa, ON, Canada, K1A 0R6","institution_ids":["https://openalex.org/I4210159778"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ganming Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ganming Liu","raw_affiliation_strings":["Institute for Information Technology, National Research Council of Canada, Ottawa, ON, Canada, K1A 0R6"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Information Technology, National Research Council of Canada, Ottawa, ON, Canada, K1A 0R6","institution_ids":["https://openalex.org/I4210159778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033923794","display_name":"Ziying Liu","orcid":"https://orcid.org/0000-0001-7821-6723","observed_orcids":["https://orcid.org/0000-0001-7821-6723"]},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ziying Liu","raw_affiliation_strings":["Institute for Information Technology, National Research Council of Canada, Ottawa, ON, Canada, K1A 0R6"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Information Technology, National Research Council of Canada, Ottawa, ON, Canada, K1A 0R6","institution_ids":["https://openalex.org/I4210159778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5089654819"],"corresponding_institution_ids":["https://openalex.org/I4210159778"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":null,"fwci":1.7576,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":{"value":0.83475518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"20","issue":"10","first_page":"1535","last_page":"1545"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9945999979972839,"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":0.9945999979972839,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.004600000102072954,"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":9.999999747378752e-05,"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/gene-expression-clustering","display_name":"gene expression clustering","score":0.9079999923706055},{"id":"https://openalex.org/keywords/cluster-stability","display_name":"cluster stability","score":0.8180000185966492},{"id":"https://openalex.org/keywords/cluster-quality-assessment","display_name":"cluster quality assessment","score":0.7480000257492065},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.7459999918937683},{"id":"https://openalex.org/keywords/gene-expression-profiles","display_name":"gene expression profiles","score":0.7490000128746033},{"id":"https://openalex.org/keywords/cluster-validity","display_name":"cluster validity","score":0.5009999871253967},{"id":"https://openalex.org/keywords/gene-function-identification","display_name":"gene function identification","score":0.5889999866485596}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8161793947219849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6527110934257507},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5979933142662048},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5969458818435669},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5915389060974121},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.539912223815918},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5171148777008057},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.47697505354881287},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.46156683564186096},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4325956404209137},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.42867547273635864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40915948152542114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37911707162857056},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2949732542037964},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.21122866868972778},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.17188385128974915},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.15510591864585876},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14436781406402588},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.11334502696990967},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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":"D007938","descriptor_name":"Leukemia","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","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":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015003","descriptor_name":"Yeasts","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","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":true},{"descriptor_ui":"D016174","descriptor_name":"Hepacivirus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016678","descriptor_name":"Genome","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":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D042822","descriptor_name":"Genomic Instability","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1093/bioinformatics/bth124","doi":"https://doi.org/10.1093/bioinformatics/bth124","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth124","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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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:14962920","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/14962920","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,"listed_in":[],"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":"Comparative Study"},{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:8913653","doi":null,"is_oa":true,"landing_page_url":"https://nrc-publications.canada.ca/fra/voir/objet/?id=7b1a57ef-d70d-46db-8bf6-578f42951f41","pdf_url":"https://nrc-publications.canada.ca/eng/view/accepted/?id=7b1a57ef-d70d-46db-8bf6-578f42951f41","source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.104.5897","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.104.5897","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/cgi/reprint/bth124v1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.844.4056","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.844.4056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/20/10/1535.full.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:8913653","doi":null,"is_oa":true,"landing_page_url":"https://nrc-publications.canada.ca/fra/voir/objet/?id=7b1a57ef-d70d-46db-8bf6-578f42951f41","pdf_url":"https://nrc-publications.canada.ca/eng/view/accepted/?id=7b1a57ef-d70d-46db-8bf6-578f42951f41","source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2098566726.pdf","grobid_xml":"https://content.openalex.org/works/W2098566726.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W5606438","https://openalex.org/W1491749498","https://openalex.org/W1505395986","https://openalex.org/W1586476557","https://openalex.org/W1747798576","https://openalex.org/W1886306325","https://openalex.org/W1987971958","https://openalex.org/W1994181640","https://openalex.org/W1999345637","https://openalex.org/W2013809387","https://openalex.org/W2090266429","https://openalex.org/W2109363337","https://openalex.org/W2112783609","https://openalex.org/W2131456395","https://openalex.org/W2135187880","https://openalex.org/W2137297622","https://openalex.org/W2137572914","https://openalex.org/W2142460132","https://openalex.org/W2150926065","https://openalex.org/W2165298438"],"related_works":["https://openalex.org/W2131456395","https://openalex.org/W2119387804","https://openalex.org/W180127808","https://openalex.org/W7096749343","https://openalex.org/W7098199299","https://openalex.org/W2100807713","https://openalex.org/W1992763738","https://openalex.org/W1491901908","https://openalex.org/W1972547451","https://openalex.org/W2185440481"],"abstract_inverted_index":{"MOTIVATION:":[0],"A":[1],"measurement":[2],"of":[3,12,19,30,41,58,79],"cluster":[4,70],"quality":[5,71],"is":[6,23],"needed":[7],"to":[8,35,44],"choose":[9],"potential":[10],"clusters":[11,40],"genes":[13,42],"that":[14,117],"contain":[15],"biologically":[16],"relevant":[17],"patterns":[18],"gene":[20,31,59,62,80,109],"expression.":[21],"This":[22],"strongly":[24],"desirable":[25],"when":[26],"a":[27,68,92],"large":[28],"number":[29],"expression":[32,81,110],"profiles":[33],"have":[34],"be":[36,45,84],"analyzed":[37],"and":[38,101,111],"proper":[39],"need":[43],"identified":[46],"for":[47,54],"further":[48],"analysis,":[49],"such":[50],"as":[51,135,137],"the":[52,125,144],"search":[53],"meaningful":[55],"patterns,":[56],"identification":[57],"functions":[60],"or":[61],"response":[63],"analysis.":[64],"RESULTS:":[65],"We":[66,97,115],"propose":[67],"new":[69],"method,":[72],"called":[73],"stability,":[74],"by":[75],"which":[76],"unsupervised":[77],"learning":[78],"data":[82],"can":[83],"performed":[85],"efficiently.":[86],"The":[87,127],"method":[88,100,119,128],"takes":[89],"into":[90],"account":[91],"cluster's":[93],"stability":[94],"on":[95],"partition.":[96],"evaluate":[98],"this":[99],"demonstrate":[102,116],"its":[103],"performance":[104],"using":[105],"four":[106],"independent,":[107],"real":[108],"three":[112],"simulated":[113],"datasets.":[114],"our":[118],"outperforms":[120],"other":[121],"techniques":[122],"listed":[123],"in":[124,131],"literature.":[126],"has":[129],"applications":[130],"evaluating":[132],"clustering":[133],"validity":[134],"well":[136],"identifying":[138],"stable":[139],"clusters.":[140],"AVAILABILITY:":[141],"Please":[142],"contact":[143],"first":[145],"author.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}