{"id":"https://openalex.org/W2938965511","doi":"https://doi.org/10.1093/bioinformatics/btz157","title":"TeraPCA: a fast and scalable software package to study genetic variation in tera-scale genotypes","display_name":"TeraPCA: a fast and scalable software package to study genetic variation in tera-scale genotypes","publication_year":2019,"publication_date":"2019-04-04","ids":{"openalex":"https://openalex.org/W2938965511","doi":"https://doi.org/10.1093/bioinformatics/btz157","mag":"2938965511","pmid":"https://pubmed.ncbi.nlm.nih.gov/30957838"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btz157","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz157","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","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/A5037001958","display_name":"Aritra Bose","orcid":"https://orcid.org/0000-0002-8665-056X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aritra Bose","raw_affiliation_strings":["Computer Science Department, Purdue University , West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0002-8665-056X","affiliations":[{"raw_affiliation_string":"Computer Science Department, Purdue University , West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044753727","display_name":"Vassilis Kalantzis","orcid":"https://orcid.org/0000-0002-4614-6422"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vassilis Kalantzis","raw_affiliation_strings":["IBM Research, Thomas J. Watson Research Center , Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Thomas J. Watson Research Center , Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033478628","display_name":"Eugenia-Maria Kontopoulou","orcid":"https://orcid.org/0000-0001-6121-1416"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugenia-Maria Kontopoulou","raw_affiliation_strings":["Computer Science Department, Purdue University , West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Purdue University , West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060465845","display_name":"Mai Elkady","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mai Elkady","raw_affiliation_strings":["Computer Science Department, Purdue University , West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Purdue University , West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039262584","display_name":"Peristera Paschou","orcid":"https://orcid.org/0000-0002-9783-1024"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Peristera Paschou","raw_affiliation_strings":["Department of Biological Sciences, Purdue University , West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, Purdue University , West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081378199","display_name":"Petros Drineas","orcid":"https://orcid.org/0000-0003-1994-8670"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Petros Drineas","raw_affiliation_strings":["Computer Science Department, Purdue University , West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Purdue University , West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5039262584"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":4.6695,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.94934982,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"35","issue":"19","first_page":"3679","last_page":"3683"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9437999725341797,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9437999725341797,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11468","display_name":"Genetic Mapping and Diversity in Plants and Animals","score":0.023099999874830246,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.0035000001080334187,"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/tera","display_name":"Tera-","score":0.9813048839569092},{"id":"https://openalex.org/keywords/genotype","display_name":"Genotype","score":0.6171440482139587},{"id":"https://openalex.org/keywords/software-package","display_name":"Software package","score":0.5795063972473145},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5479554533958435},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5255911350250244},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5137723684310913},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.43209099769592285},{"id":"https://openalex.org/keywords/genetic-variation","display_name":"Genetic variation","score":0.4296434223651886},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.36236393451690674},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.29156285524368286},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20569917559623718},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08993932604789734},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06052565574645996}],"concepts":[{"id":"https://openalex.org/C2775904623","wikidata":"https://www.wikidata.org/wiki/Q108529","display_name":"Tera-","level":2,"score":0.9813048839569092},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.6171440482139587},{"id":"https://openalex.org/C3020440742","wikidata":"https://www.wikidata.org/wiki/Q1176855","display_name":"Software package","level":3,"score":0.5795063972473145},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5479554533958435},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5255911350250244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5137723684310913},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.43209099769592285},{"id":"https://openalex.org/C68873052","wikidata":"https://www.wikidata.org/wiki/Q349856","display_name":"Genetic variation","level":3,"score":0.4296434223651886},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.36236393451690674},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.29156285524368286},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20569917559623718},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08993932604789734},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06052565574645996},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014644","descriptor_name":"Genetic Variation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btz157","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz157","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:30957838","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30957838","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":"Bioinformatics (Oxford, England)","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G424087150","display_name":null,"funder_award_id":"IIS-1715202","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7371123796","display_name":null,"funder_award_id":"IIS-1661756","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8147652040","display_name":null,"funder_award_id":"IIS-1661760","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1480928214","https://openalex.org/W1563653928","https://openalex.org/W1966936164","https://openalex.org/W1969595149","https://openalex.org/W1997476591","https://openalex.org/W2009588715","https://openalex.org/W2024027525","https://openalex.org/W2025341678","https://openalex.org/W2040387238","https://openalex.org/W2059586807","https://openalex.org/W2067603242","https://openalex.org/W2071128523","https://openalex.org/W2072706575","https://openalex.org/W2081965566","https://openalex.org/W2097576041","https://openalex.org/W2098126593","https://openalex.org/W2108169091","https://openalex.org/W2117756735","https://openalex.org/W2119444539","https://openalex.org/W2133148918","https://openalex.org/W2157752701","https://openalex.org/W2284253967","https://openalex.org/W2294798173","https://openalex.org/W2394933259","https://openalex.org/W2480854438","https://openalex.org/W2516218596","https://openalex.org/W2549134075","https://openalex.org/W2559655401","https://openalex.org/W2734969812","https://openalex.org/W2950232131","https://openalex.org/W2951349772","https://openalex.org/W2963441460","https://openalex.org/W3001040093","https://openalex.org/W3032683009","https://openalex.org/W3136389637","https://openalex.org/W3192262364","https://openalex.org/W4229666556","https://openalex.org/W4231311503","https://openalex.org/W6741275414","https://openalex.org/W6813131194"],"related_works":["https://openalex.org/W4389191251","https://openalex.org/W1919398273","https://openalex.org/W1548284058","https://openalex.org/W2306752770","https://openalex.org/W4236091150","https://openalex.org/W2622728018","https://openalex.org/W2522074681","https://openalex.org/W3135717286","https://openalex.org/W4252920320","https://openalex.org/W3011889816"],"abstract_inverted_index":{"MOTIVATION:":[0],"Principal":[1,65],"Component":[2,66],"Analysis":[3,67],"is":[4,80,154,160],"a":[5,54,90,95,109,121,124,129],"key":[6],"tool":[7],"in":[8,14,23,33],"the":[9,30,34,46,58,113,142,167],"study":[10],"of":[11,57,68,93,112],"population":[12],"structure":[13],"human":[15],"genetics.":[16],"As":[17],"modern":[18],"datasets":[19],"become":[20,40],"increasingly":[21],"larger":[22],"size,":[24],"traditional":[25],"approaches":[26],"based":[27],"on":[28,86,103,128],"loading":[29],"entire":[31],"dataset":[32,122],"system":[35,91],"memory":[36,92],"(Random":[37],"Access":[38],"Memory)":[39],"impractical":[41],"and":[42,77,79,106,115,157,159,175],"out-of-core":[43,78],"implementations":[44],"are":[45,177,186],"only":[47,107],"viable":[48],"alternative.":[49],"RESULTS:":[50],"We":[51],"present":[52],"TeraPCA,":[53],"C++":[55],"implementation":[56],"Randomized":[59],"Subspace":[60],"Iteration":[61],"method":[62],"to":[63,82,120,139],"perform":[64],"large-scale":[69],"datasets.":[70],"TeraPCA":[71,99,132,153],"can":[72],"be":[73],"applied":[74,119],"both":[75,155,178],"in-core":[76],"able":[81],"successfully":[83],"operate":[84],"even":[85],"commodity":[87],"hardware":[88],"with":[89,162],"just":[94],"few":[96],"gigabytes.":[97],"Moreover,":[98],"has":[100],"minimal":[101],"dependencies":[102],"external":[104],"libraries":[105],"requires":[108,133],"working":[110],"installation":[111],"BLAS":[114],"LAPACK":[116],"libraries.":[117],"When":[118],"containing":[123],"million":[125,130],"individuals":[126],"genotyped":[127],"markers,":[131],"<5":[134],"h":[135],"(in":[136],"multi-threaded":[137],"mode)":[138],"accurately":[140],"compute":[141],"10":[143],"leading":[144],"principal":[145],"components.":[146],"An":[147],"extensive":[148],"experimental":[149],"analysis":[150],"shows":[151],"that":[152],"fast":[156],"accurate":[158],"competitive":[161],"current":[163],"state-of-the-art":[164],"software":[165],"for":[166],"same":[168],"task.":[169],"AVAILABILITY":[170],"AND":[171],"IMPLEMENTATION:":[172],"Source":[173],"code":[174],"documentation":[176],"available":[179,187],"at":[180,188],"https://github.com/aritra90/TeraPCA.":[181],"SUPPLEMENTARY":[182],"INFORMATION:":[183],"Supplementary":[184],"data":[185],"Bioinformatics":[189],"online.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
