{"id":"https://openalex.org/W4297093422","doi":"https://doi.org/10.1080/10618600.2022.2127739","title":"A Dirichlet Model of Alignment Cost in Mixed-Membership Unsupervised Clustering","display_name":"A Dirichlet Model of Alignment Cost in Mixed-Membership Unsupervised Clustering","publication_year":2022,"publication_date":"2022-09-26","ids":{"openalex":"https://openalex.org/W4297093422","doi":"https://doi.org/10.1080/10618600.2022.2127739","pmid":"https://pubmed.ncbi.nlm.nih.gov/37982130"},"language":"en","primary_location":{"id":"doi:10.1080/10618600.2022.2127739","is_oa":true,"landing_page_url":"https://doi.org/10.1080/10618600.2022.2127739","pdf_url":null,"source":{"id":"https://openalex.org/S76159266","display_name":"Journal of Computational and Graphical Statistics","issn_l":"1061-8600","issn":["1061-8600","1537-2715"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547","https://openalex.org/P4310320449"],"host_organization_lineage_names":["Taylor & Francis","Informa"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational and Graphical Statistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1080/10618600.2022.2127739","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062439187","display_name":"Xiran Liu","orcid":"https://orcid.org/0000-0002-3955-9026"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiran Liu","raw_affiliation_strings":["Institute for Computational and Mathematical Engineering, Stanford University","Institute for Computational and Mathematical Engineering, Stanford University, Stanford, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Computational and Mathematical Engineering, Stanford University","institution_ids":[]},{"raw_affiliation_string":"Institute for Computational and Mathematical Engineering, Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001003373","display_name":"Naama M. Kopelman","orcid":"https://orcid.org/0000-0002-9091-9517"},"institutions":[{"id":"https://openalex.org/I157943965","display_name":"Holon Institute of Technology","ror":"https://ror.org/02prqh017","country_code":"IL","type":"education","lineage":["https://openalex.org/I157943965"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Naama M. Kopelman","raw_affiliation_strings":["Faculty of Sciences, Holon Institute of Technology","Faculty of Sciences, Holon Institute of Technology, Holon, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Sciences, Holon Institute of Technology","institution_ids":["https://openalex.org/I157943965"]},{"raw_affiliation_string":"Faculty of Sciences, Holon Institute of Technology, Holon, Israel","institution_ids":["https://openalex.org/I157943965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013539361","display_name":"Noah A. Rosenberg","orcid":"https://orcid.org/0000-0002-1829-8664"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Noah A. Rosenberg","raw_affiliation_strings":["Department of Biology, Stanford University","Department of Biology, Stanford University, Stanford, CA"],"raw_orcid":"https://orcid.org/0000-0002-1829-8664","affiliations":[{"raw_affiliation_string":"Department of Biology, Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Biology, Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013539361"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.1243,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56095325,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"32","issue":"3","first_page":"1145","last_page":"1159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9988999962806702,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9988999962806702,"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":0.9735999703407288,"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":0.9697999954223633,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.7157385945320129},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5862038731575012},{"id":"https://openalex.org/keywords/hierarchical-dirichlet-process","display_name":"Hierarchical Dirichlet process","score":0.5400541424751282},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5287919640541077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49042174220085144},{"id":"https://openalex.org/keywords/dirichlet-process","display_name":"Dirichlet process","score":0.4443780481815338},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4313579797744751},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3863765299320221},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37819623947143555},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32017871737480164},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.3091176152229309},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.12626400589942932}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.7157385945320129},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5862038731575012},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.5400541424751282},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5287919640541077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49042174220085144},{"id":"https://openalex.org/C2781280628","wikidata":"https://www.wikidata.org/wiki/Q5280766","display_name":"Dirichlet process","level":3,"score":0.4443780481815338},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4313579797744751},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3863765299320221},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37819623947143555},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32017871737480164},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.3091176152229309},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.12626400589942932}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1080/10618600.2022.2127739","is_oa":true,"landing_page_url":"https://doi.org/10.1080/10618600.2022.2127739","pdf_url":null,"source":{"id":"https://openalex.org/S76159266","display_name":"Journal of Computational and Graphical Statistics","issn_l":"1061-8600","issn":["1061-8600","1537-2715"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547","https://openalex.org/P4310320449"],"host_organization_lineage_names":["Taylor & Francis","Informa"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational and Graphical Statistics","raw_type":"journal-article"},{"id":"pmid:37982130","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37982130","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 computational and graphical statistics : a joint publication of American Statistical Association, Institute of Mathematical Statistics, Interface Foundation of North America","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10656040","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10656040","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10656040/pdf/nihms-1853456.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Comput Graph Stat","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1080/10618600.2022.2127739","is_oa":true,"landing_page_url":"https://doi.org/10.1080/10618600.2022.2127739","pdf_url":null,"source":{"id":"https://openalex.org/S76159266","display_name":"Journal of Computational and Graphical Statistics","issn_l":"1061-8600","issn":["1061-8600","1537-2715"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547","https://openalex.org/P4310320449"],"host_organization_lineage_names":["Taylor & Francis","Informa"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational and Graphical Statistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1786583586","display_name":"Population genetics for large-scale sequencing studies of diverse populations","funder_award_id":"2r01hg005855-11","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2591291833","display_name":null,"funder_award_id":"BCS-2116322","funder_id":"https://openalex.org/F4320320373","funder_display_name":"National Stroke Foundation"},{"id":"https://openalex.org/G4755611226","display_name":null,"funder_award_id":"R01 HG005855","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G7142001485","display_name":"Genealogical ancestors, admixture, and population history","funder_award_id":"2116322","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/F4320320373","display_name":"National Stroke Foundation","ror":"https://ror.org/004ckc033"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1161645253","https://openalex.org/W1278605765","https://openalex.org/W1579925870","https://openalex.org/W1886810706","https://openalex.org/W2035756456","https://openalex.org/W2087101057","https://openalex.org/W2098126593","https://openalex.org/W2111750074","https://openalex.org/W2119444539","https://openalex.org/W2121512231","https://openalex.org/W2125092464","https://openalex.org/W2141042406","https://openalex.org/W2147299002","https://openalex.org/W2397077215","https://openalex.org/W2415143115","https://openalex.org/W2476974423","https://openalex.org/W3037587105"],"related_works":["https://openalex.org/W2914864478","https://openalex.org/W2008338582","https://openalex.org/W2097627380","https://openalex.org/W1999586157","https://openalex.org/W4291700620","https://openalex.org/W22044811","https://openalex.org/W2625329765","https://openalex.org/W2766840109","https://openalex.org/W2955328590","https://openalex.org/W2255612897"],"abstract_inverted_index":{"Mixed-membership":[0],"unsupervised":[1,24,86],"clustering":[2,27,34,63,87],"is":[3,133],"widely":[4],"used":[5],"to":[6,53,99,135,208,218,230,237],"extract":[7],"informative":[8],"patterns":[9],"from":[10,221],"data":[11,19,209],"in":[12,32,62,75,175,187],"many":[13],"application":[14,203],"areas.":[15],"For":[16,126],"a":[17,67,90,113,162],"shared":[18],"set,":[20],"the":[21,45,56,80,109,116,120,130,138,194,202,205,212],"stochasticity":[22],"and":[23,119,197],"nature":[25],"of":[26,44,55,71,82,84,93,115,150,182,204,223,241],"algorithms":[28,234],"can":[29,50,228],"cause":[30],"difficulties":[31],"comparing":[33],"results":[35,107,186,207,227],"produced":[36],"by":[37,179],"different":[38],"algorithms,":[39],"or":[40,59],"even":[41],"multiple":[42],"runs":[43],"same":[46],"algorithm,":[47],"as":[48,112,177,215,217],"outcomes":[49],"differ":[51],"owing":[52],"permutation":[54,122,165,196],"cluster":[57,94,232],"labels":[58],"genuine":[60],"differences":[61],"results.":[64],"Here,":[65],"with":[66,137,145],"focus":[68],"on":[69],"inference":[70,222],"individual":[72],"genetic":[73],"ancestry":[74],"population-genetic":[76],"studies,":[77],"we":[78,104],"study":[79],"cost":[81,111,132,169],"misalignment":[83,159],"mixed-membership":[85],"replicates":[88],"under":[89,211],"theoretical":[91,106,206],"model":[92,100],"memberships.":[95],"Using":[96],"Dirichlet":[97,117,128,213],"distributions":[98],"membership":[101,151,183,219],"coefficient":[102],"vectors,":[103],"provide":[105],"quantifying":[108],"alignment":[110,131,188,233],"function":[114],"parameters":[118],"Hamming":[121,139],"difference":[123],"between":[124,141,193],"replicates.":[125,242],"fixed":[127],"parameters,":[129],"seen":[134],"increase":[136],"distance":[140],"permutations.":[142,172,199],"Data":[143],"sets":[144],"low":[146],"variance":[147,181],"across":[148],"individuals":[149],"coefficients":[152],"for":[153],"specific":[154],"clusters":[155],"generally":[156,185],"produce":[157],"high":[158],"costs-so":[160],"that":[161,190,235],"single":[163],"optimal":[164,195,239],"has":[166],"far":[167],"lower":[168],"than":[170],"suboptimal":[171,198],"Higher":[173],"variability":[174],"data,":[176],"represented":[178],"greater":[180],"coefficients,":[184],"costs":[189],"are":[191],"similar":[192],"We":[200],"demonstrate":[201],"simulated":[210],"model,":[214],"well":[216],"estimates":[220],"human-genetic":[224],"ancestry.":[225],"The":[226],"contribute":[229],"improving":[231],"seek":[236],"find":[238],"permutations":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}