{"id":"https://openalex.org/W2054945727","doi":"https://doi.org/10.1109/bigdata.2014.7004291","title":"Random projection based clustering for population genomics","display_name":"Random projection based clustering for population genomics","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2054945727","doi":"https://doi.org/10.1109/bigdata.2014.7004291","mag":"2054945727"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2014.7004291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5039205111","display_name":"Sotiris K. Tasoulis","orcid":"https://orcid.org/0000-0001-9536-4090"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"id":"https://openalex.org/I32943570","display_name":"Helsinki Institute for Information Technology","ror":"https://ror.org/05kph4940","country_code":"FI","type":"facility","lineage":["https://openalex.org/I133731052","https://openalex.org/I32943570","https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Sotiris Tasoulis","raw_affiliation_strings":["Department of Computer Science, University of Helsinki, Finland","Helsinki Institute for Information Technology HIIT, Department of Computer Science University of Helsinki, Finland#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]},{"raw_affiliation_string":"Helsinki Institute for Information Technology HIIT, Department of Computer Science University of Helsinki, Finland#TAB#","institution_ids":["https://openalex.org/I32943570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100724398","display_name":"Lu Cheng","orcid":"https://orcid.org/0000-0002-6391-2360"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"id":"https://openalex.org/I32943570","display_name":"Helsinki Institute for Information Technology","ror":"https://ror.org/05kph4940","country_code":"FI","type":"facility","lineage":["https://openalex.org/I133731052","https://openalex.org/I32943570","https://openalex.org/I9927081"]},{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Lu Cheng","raw_affiliation_strings":["Department of Computer Science, University of Helsinki, Finland","Helsinki Institute for Information Technology HIIT, Department of Information and Computer Science, Aalto University, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]},{"raw_affiliation_string":"Helsinki Institute for Information Technology HIIT, Department of Information and Computer Science, Aalto University, Finland","institution_ids":["https://openalex.org/I32943570","https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070318939","display_name":"Niko V\u00e4lim\u00e4ki","orcid":"https://orcid.org/0000-0001-9200-9560"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Niko Valimaki","raw_affiliation_strings":["Department of Information and Computer Science, Aalto University, Finland","Department of Computer Science, University of Helsinki, Finland,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Computer Science, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Computer Science, University of Helsinki, Finland,","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029973916","display_name":"Nicholas J. Croucher","orcid":"https://orcid.org/0000-0001-6303-8768"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"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":["FI","GB"],"is_corresponding":false,"raw_author_name":"Nicholas J. Croucher","raw_affiliation_strings":["Department of Computer Science, University of Helsinki, Finland","Department of Infectious Disease Epidemiology; Imperial College London; UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]},{"raw_affiliation_string":"Department of Infectious Disease Epidemiology; Imperial College London; UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049639550","display_name":"Simon R. Harris","orcid":"https://orcid.org/0000-0003-1512-6194"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]}],"countries":["FI","GB"],"is_corresponding":false,"raw_author_name":"Simon R. Harris","raw_affiliation_strings":["Department of Computer Science, University of Helsinki, Finland","**Wellcome Trust Sanger Institute, Hinxton, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]},{"raw_affiliation_string":"**Wellcome Trust Sanger Institute, Hinxton, Cambridge, UK","institution_ids":["https://openalex.org/I2802476451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040018261","display_name":"William P. Hanage","orcid":"https://orcid.org/0000-0002-6319-7336"},"institutions":[{"id":"https://openalex.org/I1338678786","display_name":"Center for Disease Dynamics, Economics & Policy","ror":"https://ror.org/01skhd946","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1338678786"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William P. Hanage","raw_affiliation_strings":["Department of Epidemiology, Harvard School of Public Health, Boston, Massachusetts, USA","Center for Communicable Disease Dynamics, Department of Epidemiology, Harvard School of Public Health, Boston, Massachusetts, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Epidemiology, Harvard School of Public Health, Boston, Massachusetts, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Center for Communicable Disease Dynamics, Department of Epidemiology, Harvard School of Public Health, Boston, Massachusetts, USA","institution_ids":["https://openalex.org/I1338678786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066842476","display_name":"Teemu Roos","orcid":"https://orcid.org/0000-0001-9470-3759"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"id":"https://openalex.org/I32943570","display_name":"Helsinki Institute for Information Technology","ror":"https://ror.org/05kph4940","country_code":"FI","type":"facility","lineage":["https://openalex.org/I133731052","https://openalex.org/I32943570","https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Teemu Roos","raw_affiliation_strings":["Department of Computer Science, University of Helsinki, Finland","Helsinki Institute for Information Technology HIIT, Department of Computer Science University of Helsinki, Finland#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]},{"raw_affiliation_string":"Helsinki Institute for Information Technology HIIT, Department of Computer Science University of Helsinki, Finland#TAB#","institution_ids":["https://openalex.org/I32943570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013196979","display_name":"Jukka Corander","orcid":"https://orcid.org/0000-0002-7752-1942"},"institutions":[{"id":"https://openalex.org/I1323065761","display_name":"Statistics Finland","ror":"https://ror.org/01n1rg855","country_code":"FI","type":"other","lineage":["https://openalex.org/I1323065761"]},{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"id":"https://openalex.org/I32943570","display_name":"Helsinki Institute for Information Technology","ror":"https://ror.org/05kph4940","country_code":"FI","type":"facility","lineage":["https://openalex.org/I133731052","https://openalex.org/I32943570","https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jukka Corander","raw_affiliation_strings":["Department of Mathematics and Statistics, University of Helsinki, Finland","Helsinki Institute for Information Technology HIIT, Department of Mathematics and Statistics, University of Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, University of Helsinki, Finland","institution_ids":["https://openalex.org/I1323065761","https://openalex.org/I133731052"]},{"raw_affiliation_string":"Helsinki Institute for Information Technology HIIT, Department of Mathematics and Statistics, University of Helsinki, Finland","institution_ids":["https://openalex.org/I32943570","https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9963,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.75161222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"675","last_page":"682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","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/T10015","display_name":"Genomics and Phylogenetic Studies","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/T10885","display_name":"Gene expression and cancer classification","score":0.9947999715805054,"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":0.9850999712944031,"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":0.7674530148506165},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7150912880897522},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5913798809051514},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5351724624633789},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5219518542289734},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5136610865592957},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.4928574562072754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29014497995376587},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.20683428645133972},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13227114081382751}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7674530148506165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7150912880897522},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5913798809051514},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5351724624633789},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5219518542289734},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5136610865592957},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.4928574562072754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29014497995376587},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.20683428645133972},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13227114081382751},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata.2014.7004291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:https://orca.cardiff.ac.uk:120717","is_oa":false,"landing_page_url":"https://orca.cardiff.ac.uk/id/eprint/120717/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401195","display_name":"ORCA Online Research @Cardiff (Cardiff University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79510175","host_organization_name":"Cardiff University","host_organization_lineage":["https://openalex.org/I79510175"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W60013210","https://openalex.org/W66628090","https://openalex.org/W1492327544","https://openalex.org/W1531259569","https://openalex.org/W1956647075","https://openalex.org/W1973089001","https://openalex.org/W1991874243","https://openalex.org/W1993505853","https://openalex.org/W2012457803","https://openalex.org/W2039262446","https://openalex.org/W2053171205","https://openalex.org/W2063392856","https://openalex.org/W2065811242","https://openalex.org/W2068282118","https://openalex.org/W2081699408","https://openalex.org/W2089497633","https://openalex.org/W2097665501","https://openalex.org/W2106961803","https://openalex.org/W2110105238","https://openalex.org/W2112210867","https://openalex.org/W2117355841","https://openalex.org/W2130492588","https://openalex.org/W2138615112","https://openalex.org/W2160969485","https://openalex.org/W2952682616","https://openalex.org/W4244268470","https://openalex.org/W4254311734","https://openalex.org/W6632006871","https://openalex.org/W6674684338","https://openalex.org/W6680970901"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W4233347783","https://openalex.org/W2910064364","https://openalex.org/W4255224757","https://openalex.org/W2499527417"],"abstract_inverted_index":{"Recent":[0],"data":[1,15,39,79,103,135,155],"revolution":[2],"in":[3,28,162,173,179],"population":[4,95],"genomics":[5,163],"for":[6,153,159,168],"bacteria":[7],"has":[8],"increased":[9],"the":[10,29,48,93,99,127,139,148,174],"size":[11],"of":[12,20,37,51,82,84,122,129],"aligned":[13],"sequence":[14,61,102],"sets":[16,104],"by":[17,92],"two-to-three":[18],"orders":[19,121],"magnitude.":[21],"This":[22,74],"trend":[23],"is":[24,144],"expected":[25],"to":[26,41,58,67,72,76,106,126],"continue":[27],"near":[30],"future,":[31],"putting":[32],"an":[33],"emphasis":[34],"on":[35],"applicability":[36],"big":[38,154],"techniques":[40,63],"leverage":[42],"biologically":[43],"important":[44,160],"insights.":[45],"Moreover,":[46],"with":[47,65,80,138],"increasing":[49],"density":[50],"sampling,":[52],"it":[53],"may":[54],"also":[55],"be":[56,90],"necessary":[57],"consider":[59],"alignment-free":[60,133],"analysis":[62,128,142,170],"combined":[64],"clustering":[66,114,151],"yield":[68],"a":[69,116,180],"sufficient":[70],"insight":[71],"data.":[73],"leads":[75],"ultra":[77],"high-dimensional":[78],"tens":[81],"millions":[83],"variables,":[85],"which":[86],"can":[87],"no":[88],"longer":[89],"handled":[91],"existing":[94],"genomic":[96],"methods.":[97],"Using":[98],"largest":[100],"bacterial":[101],"published":[105],"date,":[107],"we":[108],"demonstrate":[109],"that":[110,143],"random":[111],"projection":[112],"based":[113],"provides":[115],"highly":[117],"accurate":[118],"and":[119,132,164],"several":[120],"magnitude":[123],"faster":[124],"approach":[125],"both":[130],"alignment-based":[131],"genome":[134],"sets,":[136],"compared":[137],"Bayesian":[140],"model-based":[141],"currently":[145],"considered":[146],"as":[147],"state-of-the-art.":[149],"Hence,":[150],"methods":[152],"harbor":[156],"considerable":[157],"potential":[158],"applications":[161],"could":[165],"pave":[166],"way":[167],"novel":[169],"pipelines":[171],"even":[172],"online":[175],"setting":[176],"when":[177],"executed":[178],"massively":[181],"parallel":[182],"computing":[183],"environment.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
