{"id":"https://openalex.org/W3196454481","doi":"https://doi.org/10.1145/3459930.3469523","title":"Fast and memory-efficient scRNA-seq <i>k</i> -means clustering with various distances","display_name":"Fast and memory-efficient scRNA-seq <i>k</i> -means clustering with various distances","publication_year":2021,"publication_date":"2021-07-30","ids":{"openalex":"https://openalex.org/W3196454481","doi":"https://doi.org/10.1145/3459930.3469523","mag":"3196454481","pmid":"https://pubmed.ncbi.nlm.nih.gov/34778889"},"language":"en","primary_location":{"id":"doi:10.1145/3459930.3469523","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3459930.3469523","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3459930.3469523","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3459930.3469523","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056210064","display_name":"Daniel N. Baker","orcid":"https://orcid.org/0000-0002-0513-6893"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel N. Baker","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083059115","display_name":"Nathan Dyjack","orcid":"https://orcid.org/0000-0001-6944-6252"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I1299907687","display_name":"Bloomberg (United States)","ror":"https://ror.org/02rdpzb15","country_code":"US","type":"company","lineage":["https://openalex.org/I1299907687"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan Dyjack","raw_affiliation_strings":["Johns Hopkins University, Bloomberg"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Bloomberg","institution_ids":["https://openalex.org/I1299907687","https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053736722","display_name":"Vladimir Braverman","orcid":"https://orcid.org/0000-0001-7709-8753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vladimir Braverman","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028505800","display_name":"Stephanie C. Hicks","orcid":"https://orcid.org/0000-0002-7858-0231"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I1299907687","display_name":"Bloomberg (United States)","ror":"https://ror.org/02rdpzb15","country_code":"US","type":"company","lineage":["https://openalex.org/I1299907687"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephanie C. Hicks","raw_affiliation_strings":["Johns Hopkins University, Bloomberg"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Bloomberg","institution_ids":["https://openalex.org/I1299907687","https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009556658","display_name":"Ben Langmead","orcid":"https://orcid.org/0000-0003-2437-1976"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Langmead","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5056210064"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.4022,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.59039423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"2021","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9991999864578247,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9991999864578247,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9772999882698059,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.968500018119812,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7973835468292236},{"id":"https://openalex.org/keywords/bhattacharyya-distance","display_name":"Bhattacharyya distance","score":0.7668291330337524},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.7596023082733154},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6809890270233154},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.5493353605270386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.508796751499176},{"id":"https://openalex.org/keywords/distance-matrix","display_name":"Distance matrix","score":0.4395100474357605},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.41247910261154175},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4024029076099396},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3489059507846832},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33519506454467773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30998528003692627},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2866078019142151}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7973835468292236},{"id":"https://openalex.org/C24145651","wikidata":"https://www.wikidata.org/wiki/Q2901249","display_name":"Bhattacharyya distance","level":2,"score":0.7668291330337524},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.7596023082733154},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6809890270233154},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.5493353605270386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.508796751499176},{"id":"https://openalex.org/C111208986","wikidata":"https://www.wikidata.org/wiki/Q901698","display_name":"Distance matrix","level":2,"score":0.4395100474357605},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.41247910261154175},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4024029076099396},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3489059507846832},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33519506454467773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30998528003692627},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2866078019142151},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3459930.3469523","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3459930.3469523","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3459930.3469523","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},{"id":"pmid:34778889","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34778889","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":"ACM-BCB ... ... : the ... ACM Conference on Bioinformatics, Computational Biology and Biomedicine. ACM Conference on Bioinformatics, Computational Biology and Biomedicine","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8586878","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8586878","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM BCB","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3459930.3469523","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3459930.3469523","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3459930.3469523","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5119885683","display_name":null,"funder_award_id":"CZF2019-00244","funder_id":"https://openalex.org/F4320315474","funder_display_name":"Chan Zuckerberg Initiative"},{"id":"https://openalex.org/G7607639174","display_name":null,"funder_award_id":"R01GM118568","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320315474","display_name":"Chan Zuckerberg Initiative","ror":"https://ror.org/02qenvm24"},{"id":"https://openalex.org/F4320317236","display_name":"Maryland Advanced Research Computing Center","ror":null},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3196454481.pdf","grobid_xml":"https://content.openalex.org/works/W3196454481.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2025828346","https://openalex.org/W2030764127","https://openalex.org/W2062723323","https://openalex.org/W2142838865","https://openalex.org/W2144335278","https://openalex.org/W2150593711","https://openalex.org/W2162287622","https://openalex.org/W2766959028","https://openalex.org/W2916020270","https://openalex.org/W2940317904","https://openalex.org/W2949681238","https://openalex.org/W2950132609","https://openalex.org/W2951506174","https://openalex.org/W2994976879","https://openalex.org/W2995010870","https://openalex.org/W2997591727","https://openalex.org/W2998065416","https://openalex.org/W3003444384","https://openalex.org/W3022699626","https://openalex.org/W3041220471","https://openalex.org/W3103302162","https://openalex.org/W3103797259","https://openalex.org/W3104343495","https://openalex.org/W3105559803","https://openalex.org/W3123418868","https://openalex.org/W3165246254","https://openalex.org/W4301017680","https://openalex.org/W6635823127"],"related_works":["https://openalex.org/W2149197198","https://openalex.org/W2150461503","https://openalex.org/W139051966","https://openalex.org/W2105321464","https://openalex.org/W2138467869","https://openalex.org/W2887774187","https://openalex.org/W2388220555","https://openalex.org/W1551075943","https://openalex.org/W1554844486","https://openalex.org/W1520875569"],"abstract_inverted_index":{"Single-cell":[0],"RNA-sequencing":[1],"(scRNA-seq)":[2],"analyses":[3],"typically":[4],"begin":[5],"by":[6],"clustering":[7,40,192],"a":[8,27,82,101,164,176],"gene-by-cell":[9],"expression":[10,20],"matrix":[11],"to":[12,76,120],"empirically":[13],"define":[14],"groups":[15],"of":[16,41,104,140,145,168,186],"cells":[17],"with":[18,46,60,138,152,213],"similar":[19],"profiles.":[21],"We":[22,161],"describe":[23],"new":[24,28],"methods":[25],"and":[26,38,111,123,171,195],"open":[29],"source":[30],"library,":[31],"minicore,":[32],"for":[33,81,135],"efficient":[34],"<i>k</i>-means++":[35,79],"center":[36],"finding":[37],"<i>k</i>-means":[39,173],"scRNA-seq":[42,55,136],"data.":[43],"Minicore":[44,92],"works":[45],"sparse":[47],"count":[48,121],"data,":[49],"as":[50,57,59],"it":[51,75],"emerges":[52],"from":[53,63],"typical":[54],"experiments,":[56],"well":[58],"dense":[61],"data":[62,122],"after":[64],"dimensionality":[65],"reduction.":[66],"Minicore's":[67],"novel":[68],"vectorized":[69],"weighted":[70],"reservoir":[71],"sampling":[72],"algorithm":[73],"allows":[74],"find":[77],"initial":[78],"centers":[80],"4-million":[83,177],"cell":[84,178,215],"dataset":[85,179],"in":[86,180],"1.5":[87],"minutes":[88],"using":[89,95,182],"20":[90],"threads.":[91],"can":[93,116,174],"cluster":[94,175],"Euclidean":[96],"distance,":[97,114],"but":[98],"also":[99],"supports":[100],"wider":[102],"class":[103],"measures":[105,151,206],"like":[106],"Jensen-Shannon":[107],"Divergence,":[108,110],"Kullback-Leibler":[109],"the":[112],"Bhattachaiyya":[113],"which":[115,204],"be":[117],"directly":[118],"applied":[119],"probability":[124],"distributions.":[125],"Further,":[126],"minicore":[127,147,165],"produces":[128],"lower-cost":[129],"centerings":[130],"more":[131],"efficiently":[132],"than":[133,184],"scikit-learn":[134],"datasets":[137],"millions":[139],"cells.":[141],"With":[142],"careful":[143],"handling":[144],"priors,":[146],"implements":[148],"these":[149],"distance":[150,205],"only":[153],"minor":[154],"(<2-fold)":[155],"speed":[156],"differences":[157],"among":[158],"all":[159],"distances.":[160],"show":[162],"that":[163,209],"pipeline":[166],"consisting":[167],"<i>k</i>-means++,":[169],"localsearch++":[170],"mini-batch":[172],"minutes,":[181],"less":[183],"10GiB":[185],"RAM.":[187],"This":[188],"memory-efficiency":[189],"enables":[190],"atlas-scale":[191],"on":[193,203],"laptops":[194],"other":[196],"commodity":[197],"hardware.":[198],"Finally,":[199],"we":[200],"report":[201],"findings":[202],"give":[207],"clusterings":[208],"are":[210],"most":[211],"consistent":[212],"known":[214],"type":[216],"labels.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-09-13T00:00:00"}