{"id":"https://openalex.org/W2143970376","doi":"https://doi.org/10.1142/s0219720013410072","title":"MODEL-BASED CLUSTERING WITH GENE RANKING USING PENALIZED MIXTURES OF HEAVY-TAILED DISTRIBUTIONS","display_name":"MODEL-BASED CLUSTERING WITH GENE RANKING USING PENALIZED MIXTURES OF HEAVY-TAILED DISTRIBUTIONS","publication_year":2013,"publication_date":"2013-01-31","ids":{"openalex":"https://openalex.org/W2143970376","doi":"https://doi.org/10.1142/s0219720013410072","mag":"2143970376","pmid":"https://pubmed.ncbi.nlm.nih.gov/23796184"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720013410072","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720013410072","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/A5090565438","display_name":"Alberto Cozzini","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"ALBERTO COZZINI","raw_affiliation_strings":["Department of Mathematics, Imperial College London, London SW7 2AZ, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Imperial College London, London SW7 2AZ, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047259277","display_name":"Ajay Jasra","orcid":"https://orcid.org/0000-0003-4808-9131"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"AJAY JASRA","raw_affiliation_strings":["Department of Statistics and Applied Probability, National University of Singapore, Singapore 117546, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Applied Probability, National University of Singapore, Singapore 117546, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010581004","display_name":"Giovanni Montana","orcid":"https://orcid.org/0000-0003-3942-3900"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"GIOVANNI MONTANA","raw_affiliation_strings":["Department of Mathematics, Imperial College London, London SW7 2AZ, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Imperial College London, London SW7 2AZ, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5985,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69726687,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"11","issue":"03","first_page":"1341007","last_page":"1341007"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9962999820709229,"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":0.989799976348877,"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":0.806955099105835},{"id":"https://openalex.org/keywords/determining-the-number-of-clusters-in-a-data-set","display_name":"Determining the number of clusters in a data set","score":0.6284541487693787},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6203597784042358},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.5897368788719177},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.555287778377533},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.533261239528656},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4912988543510437},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.45938757061958313},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4289476275444031},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42442503571510315},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4155206084251404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38783660531044006},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.38072681427001953},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.32684504985809326},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09088218212127686}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.806955099105835},{"id":"https://openalex.org/C149872217","wikidata":"https://www.wikidata.org/wiki/Q5265701","display_name":"Determining the number of clusters in a data set","level":5,"score":0.6284541487693787},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6203597784042358},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.5897368788719177},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.555287778377533},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.533261239528656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4912988543510437},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.45938757061958313},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4289476275444031},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42442503571510315},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4155206084251404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38783660531044006},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.38072681427001953},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.32684504985809326},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09088218212127686},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D012333","descriptor_name":"RNA, Messenger","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D012333","descriptor_name":"RNA, Messenger","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D012333","descriptor_name":"RNA, Messenger","qualifier_ui":"Q000378","qualifier_name":"metabolism","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":"D016011","descriptor_name":"Normal Distribution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016011","descriptor_name":"Normal Distribution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016011","descriptor_name":"Normal Distribution","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":3,"locations":[{"id":"doi:10.1142/s0219720013410072","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720013410072","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:23796184","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23796184","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:scholarbank.nus.edu.sg:10635/125064","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/125064","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1546574627","https://openalex.org/W1579925870","https://openalex.org/W1747798576","https://openalex.org/W1972239934","https://openalex.org/W1988764623","https://openalex.org/W2002262418","https://openalex.org/W2007431287","https://openalex.org/W2013177587","https://openalex.org/W2017818759","https://openalex.org/W2020925091","https://openalex.org/W2024543108","https://openalex.org/W2025711350","https://openalex.org/W2027779334","https://openalex.org/W2028236537","https://openalex.org/W2046405061","https://openalex.org/W2048178552","https://openalex.org/W2049633694","https://openalex.org/W2068497347","https://openalex.org/W2084934278","https://openalex.org/W2085573033","https://openalex.org/W2108435369","https://openalex.org/W2124007301","https://openalex.org/W2125442898","https://openalex.org/W2128985829","https://openalex.org/W2131785519","https://openalex.org/W2131994307","https://openalex.org/W2137114211","https://openalex.org/W2137971377","https://openalex.org/W2152578842","https://openalex.org/W2153794775","https://openalex.org/W2154187696","https://openalex.org/W2157840751","https://openalex.org/W2165892974","https://openalex.org/W2465711087","https://openalex.org/W2973584309","https://openalex.org/W3105178084","https://openalex.org/W4235169531"],"related_works":["https://openalex.org/W2050713761","https://openalex.org/W2559422900","https://openalex.org/W2171610853","https://openalex.org/W2040929534","https://openalex.org/W2892323093","https://openalex.org/W2394193399","https://openalex.org/W2036298232","https://openalex.org/W2770741777","https://openalex.org/W2738096727","https://openalex.org/W2085801246"],"abstract_inverted_index":{"Cluster":[0],"analysis":[1],"of":[2,17,36,51,58,68,87,94,102,150],"biological":[3,19],"samples":[4],"using":[5],"gene":[6,37,89,110],"expression":[7,38],"measurements":[8],"is":[9,43,179],"a":[10,56,80,99,114,121],"common":[11],"task":[12],"which":[13,33,182],"aids":[14],"the":[15,34,49,65,84,91,95,117,131,138,148,160],"discovery":[16],"heterogeneous":[18],"sub-populations":[20],"having":[21],"distinct":[22],"mRNA":[23],"profiles.":[24],"Several":[25],"model-based":[26,73,107],"clustering":[27,74,108,132],"algorithms":[28,75],"have":[29],"been":[30],"proposed":[31,118],"in":[32,147],"distribution":[35],"values":[39],"within":[40],"each":[41,88],"sub-group":[42],"assumed":[44],"to":[45,82,90,127,130,143,175],"be":[46],"Gaussian.":[47],"In":[48],"presence":[50,149],"noise":[52],"and":[53,63,109,152,167],"extreme":[54],"observations,":[55],"mixture":[57,101],"Gaussian":[59,145],"densities":[60],"may":[61],"over-fit":[62],"overestimate":[64],"true":[66,161],"number":[67],"clusters.":[69],"Moreover,":[70],"commonly":[71],"used":[72],"do":[76],"not":[77],"generally":[78],"provide":[79],"mechanism":[81],"quantify":[83],"relative":[85],"contribution":[86],"final":[92],"partitioning":[93],"data.":[96],"We":[97],"propose":[98],"penalized":[100],"Student's":[103],"t":[104],"distributions":[105],"for":[106,123],"ranking.":[111],"Together":[112],"with":[113,164],"resampling":[115],"procedure,":[116],"approach":[119],"provides":[120],"means":[122],"ranking":[124],"genes":[125,163],"according":[126],"their":[128],"contributions":[129],"process.":[133],"Experimental":[134],"results":[135],"show":[136],"that":[137],"algorithm":[139,157],"performs":[140],"well":[141],"comparably":[142],"traditional":[144],"mixtures":[146],"outliers":[151],"longer":[153],"tailed":[154],"distributions.":[155],"The":[156],"also":[158,180],"identifies":[159],"informative":[162],"high":[165],"sensitivity,":[166],"achieves":[168],"improved":[169],"model":[170],"selection.":[171],"An":[172],"illustrative":[173],"application":[174],"breast":[176],"cancer":[177],"data":[178],"presented":[181],"confirms":[183],"established":[184],"tumor":[185],"sub-classes.":[186]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}