{"id":"https://openalex.org/W2519201369","doi":"https://doi.org/10.1186/s12859-016-1245-9","title":"EnsCat: clustering of categorical data via ensembling","display_name":"EnsCat: clustering of categorical data via ensembling","publication_year":2016,"publication_date":"2016-09-15","ids":{"openalex":"https://openalex.org/W2519201369","doi":"https://doi.org/10.1186/s12859-016-1245-9","mag":"2519201369","pmid":"https://pubmed.ncbi.nlm.nih.gov/27634377"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-016-1245-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-016-1245-9","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-016-1245-9","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-016-1245-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060291820","display_name":"Bertrand Clarke","orcid":"https://orcid.org/0000-0001-5793-7265"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bertrand S. Clarke","raw_affiliation_strings":["Department of Statistics, University of Nebraska-Lincoln, Lincoln, NE, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Nebraska-Lincoln, Lincoln, NE, USA","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080157851","display_name":"Saeid Amiri","orcid":"https://orcid.org/0000-0003-2028-092X"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saeid Amiri","raw_affiliation_strings":["Department of Natural and Applied Sciences, University of Wisconsin Madison, Iowa City, IA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Natural and Applied Sciences, University of Wisconsin Madison, Iowa City, IA, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034823498","display_name":"Jennifer Clarke","orcid":"https://orcid.org/0000-0002-2723-7249"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jennifer L. Clarke","raw_affiliation_strings":["Department of Food Science and Technology, University of Nebraska-Lincoln, Lincoln, NE, USA. jclarke3@unl.edu","Department of Statistics, University of Nebraska-Lincoln, Lincoln, NE, USA. jclarke3@unl.edu","Department of Statistics, University of Nebraska-Lincoln, Lincoln, NE, USA","Department of Food Science and Technology, University of Nebraska-Lincoln, Lincoln, NE, USA"],"raw_orcid":"https://orcid.org/0000-0002-2723-7249","affiliations":[{"raw_affiliation_string":"Department of Food Science and Technology, University of Nebraska-Lincoln, Lincoln, NE, USA. jclarke3@unl.edu","institution_ids":["https://openalex.org/I114395901"]},{"raw_affiliation_string":"Department of Statistics, University of Nebraska-Lincoln, Lincoln, NE, USA. jclarke3@unl.edu","institution_ids":["https://openalex.org/I114395901"]},{"raw_affiliation_string":"Department of Statistics, University of Nebraska-Lincoln, Lincoln, NE, USA","institution_ids":["https://openalex.org/I114395901"]},{"raw_affiliation_string":"Department of Food Science and Technology, University of Nebraska-Lincoln, Lincoln, NE, USA","institution_ids":["https://openalex.org/I114395901"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034823498"],"corresponding_institution_ids":["https://openalex.org/I114395901"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":1.2993,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87196157,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"17","issue":"1","first_page":"380","last_page":"380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.3402000069618225,"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"}},"topics":[{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.3402000069618225,"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/T10885","display_name":"Gene expression and cancer classification","score":0.13249999284744263,"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":0.09489999711513519,"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":0.7563626766204834},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.661410927772522},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.6420716047286987},{"id":"https://openalex.org/keywords/consensus-clustering","display_name":"Consensus clustering","score":0.5946512222290039},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5813515782356262},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.497421532869339},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.4884592592716217},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.39938902854919434},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38196223974227905},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36226212978363037},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.35709887742996216}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7563626766204834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.661410927772522},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6420716047286987},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.5946512222290039},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5813515782356262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.497421532869339},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.4884592592716217},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.39938902854919434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38196223974227905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36226212978363037},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.35709887742996216}],"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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","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":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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-016-1245-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-016-1245-9","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-016-1245-9","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:27634377","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27634377","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:digitalcommons.unl.edu:statisticsfacpub-1038","is_oa":true,"landing_page_url":"https://digitalcommons.unl.edu/statisticsfacpub/34","pdf_url":null,"source":{"id":"https://openalex.org/S4306400577","display_name":"Lincoln (University of Nebraska)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114395901","host_organization_name":"University of Nebraska\u2013Lincoln","host_organization_lineage":["https://openalex.org/I114395901"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Department of Statistics: Faculty Publications","raw_type":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:5025633","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5025633","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-016-1245-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-016-1245-9","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-016-1245-9","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2070079483","display_name":null,"funder_award_id":"DMS-1120404","funder_id":"https://openalex.org/F4320332186","funder_display_name":"Defense Threat Reduction Agency"},{"id":"https://openalex.org/G2460435146","display_name":null,"funder_award_id":"DMS-1120404","funder_id":"https://openalex.org/F4320332172","funder_display_name":"Directorate for Mathematical and Physical Sciences"},{"id":"https://openalex.org/G8393442714","display_name":"ATD: Collaborative Research: Statistical Ensembles for the Identification of Bacterial Genomes","funder_award_id":"1120404","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332172","display_name":"Directorate for Mathematical and Physical Sciences","ror":"https://ror.org/029b7h395"},{"id":"https://openalex.org/F4320332186","display_name":"Defense Threat Reduction Agency","ror":"https://ror.org/04tz64554"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2519201369.pdf","grobid_xml":"https://content.openalex.org/works/W2519201369.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W109865423","https://openalex.org/W575548124","https://openalex.org/W1672197616","https://openalex.org/W2021210077","https://openalex.org/W2048178552","https://openalex.org/W2049020723","https://openalex.org/W2057712948","https://openalex.org/W2069022975","https://openalex.org/W2094909687","https://openalex.org/W2102880413","https://openalex.org/W2115346774","https://openalex.org/W2115462905","https://openalex.org/W2115817918","https://openalex.org/W2125310307","https://openalex.org/W2137111266","https://openalex.org/W2144549472","https://openalex.org/W2149230623","https://openalex.org/W2160378127","https://openalex.org/W2170111518","https://openalex.org/W2234615877","https://openalex.org/W2320026594","https://openalex.org/W2519201369","https://openalex.org/W2582743722","https://openalex.org/W2911964244","https://openalex.org/W2912934387","https://openalex.org/W3104318432"],"related_works":["https://openalex.org/W2111119584","https://openalex.org/W2606552659","https://openalex.org/W4301002638","https://openalex.org/W3186815950","https://openalex.org/W2406185607","https://openalex.org/W2163563073","https://openalex.org/W2311450085","https://openalex.org/W3035964814","https://openalex.org/W3124860551","https://openalex.org/W2309230723"],"abstract_inverted_index":{"BACKGROUND:":[0],"Clustering":[1],"is":[2,20,49,188,254],"a":[3,16,98,128,133,142,208,217],"widely":[4],"used":[5,22],"collection":[6],"of":[7,40,70,76,118,121,130,132,185,196],"unsupervised":[8],"learning":[9],"techniques":[10,243],"for":[11,58,90,105,149,244],"identifying":[12],"natural":[13],"classes":[14],"within":[15],"data":[17,30,63,92,187],"set.":[18],"It":[19,145],"often":[21,32,50,72],"in":[23,112,160,230],"bioinformatics":[24],"to":[25,80,97,169,199,215],"infer":[26],"population":[27],"substructure.":[28],"Genomic":[29],"are":[31,136],"categorical":[33,54,91,245],"and":[34,67,86,138,212,232,252],"high":[35,61],"dimensional,":[36],"e.g.,":[37],"long":[38],"sequences":[39],"nucleotides.":[41],"This":[42],"makes":[43],"inference":[44],"challenging:":[45],"The":[46,247],"distance":[47],"metric":[48],"not":[51,94],"well-defined":[52],"on":[53],"data;":[55],"running":[56],"time":[57],"computations":[59],"using":[60,222],"dimensional":[62],"can":[64],"be":[65],"considerable;":[66],"the":[68,74,77,81,84,119,122,155,183,186],"Curse":[69],"Dimensionality":[71],"impedes":[73],"interpretation":[75],"results.":[78],"Up":[79],"present,":[82],"however,":[83],"literature":[85],"software":[87,104],"addressing":[88],"clustering":[89,180,242],"has":[93,146],"yet":[95],"led":[96],"standard":[99],"approach.":[100],"RESULTS:":[101],"We":[102,171],"present":[103],"an":[106,125],"ensemble":[107,126],"method":[108,127],"that":[109,151,157],"performs":[110],"well":[111],"comparison":[113],"with":[114,178,250],"other":[115,241],"methods":[116],"regardless":[117],"dimensionality":[120],"data.":[123,246],"In":[124],"variety":[129],"instantiations":[131],"statistical":[134],"object":[135],"found":[137],"then":[139],"combined":[140],"into":[141,207],"consensus":[143],"value.":[144],"been":[147],"known":[148],"decades":[150],"ensembling":[152,167],"generally":[153],"outperforms":[154],"components":[156],"comprise":[158],"it":[159],"many":[161,175],"settings.":[162],"Here,":[163],"we":[164,190,203],"apply":[165],"this":[166,214],"principle":[168],"clustering.":[170],"begin":[172],"by":[173],"generating":[174],"hierarchical":[176],"clusterings":[177,206],"different":[179],"sizes.":[181],"When":[182],"dimension":[184],"high,":[189],"also":[191,195],"randomly":[192],"select":[193],"subspaces":[194],"variable":[197],"size,":[198],"generate":[200],"clusterings.":[201],"Then,":[202],"combine":[204],"these":[205],"single":[209],"membership":[210],"matrix":[211,221],"use":[213],"obtain":[216],"new,":[218],"ensembled":[219],"dissimilarity":[220],"Hamming":[223],"distance.":[224],"CONCLUSIONS:":[225],"Ensemble":[226],"clustering,":[227],"as":[228],"implemented":[229],"R":[231],"called":[233],"EnsCat,":[234],"gives":[235],"more":[236],"clearly":[237],"separated":[238],"clusters":[239],"than":[240],"latest":[248],"version":[249],"manual":[251],"examples":[253],"available":[255],"at":[256],"https://github.com/jlp2duke/EnsCat":[257],".":[258]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
