{"id":"https://openalex.org/W2142795379","doi":"https://doi.org/10.1109/csb.2004.1332427","title":"Minimum entropy clustering and applications to gene expression analysis","display_name":"Minimum entropy clustering and applications to gene expression analysis","publication_year":2004,"publication_date":"2004-11-08","ids":{"openalex":"https://openalex.org/W2142795379","doi":"https://doi.org/10.1109/csb.2004.1332427","mag":"2142795379","pmid":"https://pubmed.ncbi.nlm.nih.gov/16448008"},"language":"en","primary_location":{"id":"doi:10.1109/csb.2004.1332427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2004.1332427","pdf_url":null,"source":{"id":"https://openalex.org/S4363608884","display_name":"Proceedings. 2004 IEEE Computational Systems Bioinformatics Conference, 2004. CSB 2004.","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 2004 IEEE Computational Systems Bioinformatics Conference, 2004. CSB 2004.","raw_type":"proceedings-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/A5100398345","display_name":"Haifeng Li","orcid":"https://orcid.org/0000-0002-3972-5573"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Haifeng Li","raw_affiliation_strings":["University of California at Riverside, 92521, USA. hli@cs.ucr.edu"],"affiliations":[{"raw_affiliation_string":"University of California at Riverside, 92521, USA. hli@cs.ucr.edu","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055875299","display_name":"Keshu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keshu Zhang","raw_affiliation_strings":["Rensselaer Polytechnic Institute, Troy, NY, USA"],"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101911266","display_name":"Tao Jiang","orcid":"https://orcid.org/0000-0003-3833-4498"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Jiang","raw_affiliation_strings":["University of California, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100398345"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":7.2679,"has_fulltext":false,"cited_by_count":96,"citation_normalized_percentile":{"value":0.95812808,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"136","last_page":"145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9994999766349792,"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":0.9994999766349792,"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/T10057","display_name":"Face and Expression Recognition","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9843000173568726,"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":0.7473447322845459},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6332862377166748},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5398238897323608},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5394158959388733},{"id":"https://openalex.org/keywords/k-medians-clustering","display_name":"k-medians clustering","score":0.5309369564056396},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.5203613638877869},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.5081300735473633},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.48425742983818054},{"id":"https://openalex.org/keywords/nearest-neighbor-chain-algorithm","display_name":"Nearest-neighbor chain algorithm","score":0.4575454592704773},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3788124918937683},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3545626997947693},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.328909695148468},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32668036222457886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28964102268218994},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.28723466396331787},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.23033055663108826},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0663209855556488}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7473447322845459},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6332862377166748},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5398238897323608},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5394158959388733},{"id":"https://openalex.org/C115328559","wikidata":"https://www.wikidata.org/wiki/Q4041956","display_name":"k-medians clustering","level":5,"score":0.5309369564056396},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.5203613638877869},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.5081300735473633},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.48425742983818054},{"id":"https://openalex.org/C102164700","wikidata":"https://www.wikidata.org/wiki/Q17162702","display_name":"Nearest-neighbor chain algorithm","level":5,"score":0.4575454592704773},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3788124918937683},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3545626997947693},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.328909695148468},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32668036222457886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28964102268218994},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.28723466396331787},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.23033055663108826},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0663209855556488},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"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":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","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":"D015870","descriptor_name":"Gene Expression","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015870","descriptor_name":"Gene Expression","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015870","descriptor_name":"Gene Expression","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":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","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":true},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","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}],"locations_count":4,"locations":[{"id":"doi:10.1109/csb.2004.1332427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2004.1332427","pdf_url":null,"source":{"id":"https://openalex.org/S4363608884","display_name":"Proceedings. 2004 IEEE Computational Systems Bioinformatics Conference, 2004. CSB 2004.","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 2004 IEEE Computational Systems Bioinformatics Conference, 2004. CSB 2004.","raw_type":"proceedings-article"},{"id":"pmid:16448008","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16448008","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":"Proceedings. IEEE Computational Systems Bioinformatics Conference","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.107.3873","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.107.3873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://conferences.computer.org/bioinformatics/CSB2004/PDF/014_Li_H_Entropy.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.83.3658","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.83.3658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucr.edu/~hli/paper/hli04mec.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1587849410","https://openalex.org/W1638203394","https://openalex.org/W1679913846","https://openalex.org/W1770825568","https://openalex.org/W1971784203","https://openalex.org/W1995875735","https://openalex.org/W2014268383","https://openalex.org/W2032407804","https://openalex.org/W2033403400","https://openalex.org/W2049633694","https://openalex.org/W2050913223","https://openalex.org/W2067257063","https://openalex.org/W2087684630","https://openalex.org/W2090634555","https://openalex.org/W2099111195","https://openalex.org/W2118020555","https://openalex.org/W2122111042","https://openalex.org/W2122882636","https://openalex.org/W2125310307","https://openalex.org/W2135000328","https://openalex.org/W2135346934","https://openalex.org/W2140190241","https://openalex.org/W2142460132","https://openalex.org/W2146264532","https://openalex.org/W2150926065","https://openalex.org/W2164628006","https://openalex.org/W2168846334","https://openalex.org/W2263958071","https://openalex.org/W2612166593","https://openalex.org/W2993383518","https://openalex.org/W3017143921","https://openalex.org/W4230960895","https://openalex.org/W4235169531","https://openalex.org/W4244030505","https://openalex.org/W4245176872","https://openalex.org/W6678323213","https://openalex.org/W6693264812"],"related_works":["https://openalex.org/W2360225591","https://openalex.org/W2188840951","https://openalex.org/W3092684173","https://openalex.org/W2376412895","https://openalex.org/W2393816671","https://openalex.org/W2056194206","https://openalex.org/W2367377022","https://openalex.org/W3209217468","https://openalex.org/W4285809405","https://openalex.org/W2386689530"],"abstract_inverted_index":{"Clustering":[0],"is":[1,39,81,97,104,121,165],"a":[2,16,34,55,109,114],"common":[3],"methodology":[4],"for":[5,58,106,112],"analyzing":[6],"the":[7,29,40,46,62,73,84,88,101,126,133,160,185],"gene":[8],"expression":[9],"data.":[10],"In":[11,167],"this":[12],"paper,":[13],"we":[14,27],"present":[15],"new":[17],"clustering":[18,134,170],"algorithm":[19,120,135,154],"from":[20],"an":[21,117],"information-theoretic":[22],"point":[23],"of":[24,43,87,148,163,177,187],"view.":[25],"First,":[26],"propose":[28],"minimum":[30,74],"entropy":[31,42,67,75],"(measured":[32],"on":[33,78],"posteriori":[35,115],"probabilities)":[36],"criterion,":[37],"which":[38],"conditional":[41],"clusters":[44,164],"given":[45],"observations.":[47],"Fano's":[48],"inequality":[49],"indicates":[50],"that":[51,100,132],"it":[52],"could":[53],"be":[54],"good":[56,105],"criterion":[57,63,76,103],"clustering.":[59,107],"We":[60],"generalize":[61],"by":[64],"replacing":[65],"Shannon's":[66],"with":[68],"Havrda-Charvat's":[69],"structural":[70,79],"alpha-entropy.":[71],"Interestingly,":[72],"based":[77],"alpha-entropy":[80],"equal":[82],"to":[83,124],"probability":[85],"error":[86],"nearest":[89],"neighbor":[90],"method":[91,181],"when":[92,159],"alpha":[93],"=":[94],"2.":[95],"This":[96],"another":[98],"evidence":[99],"proposed":[102],"With":[108],"non-parametric":[110],"approach":[111],"estimating":[113],"probabilities,":[116],"efficient":[118],"iterative":[119],"then":[122],"established":[123],"minimize":[125],"entropy.":[127],"The":[128],"experimental":[129],"results":[130],"show":[131],"performs":[136,155],"significantly":[137],"better":[138],"than":[139],"k-means/medians,":[140],"hierarchical":[141],"clustering,":[142],"SOM,":[143],"and":[144,189],"EM":[145],"in":[146,175],"terms":[147],"adjusted":[149],"Rand":[150],"index.":[151],"Particularly,":[152],"our":[153,180],"very":[156],"well":[157],"even":[158],"correct":[161],"number":[162],"unknown.":[166],"addition,":[168],"most":[169],"algorithms":[171],"produce":[172],"poor":[173],"partitions":[174],"presence":[176],"outliers":[178,192],"while":[179],"can":[182],"correctly":[183],"reveal":[184],"structure":[186],"data":[188],"effectively":[190],"identify":[191],"simultaneously.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":8}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}