{"id":"https://openalex.org/W2951349772","doi":"https://doi.org/10.1093/bioinformatics/btx299","title":"FlashPCA2: principal component analysis of Biobank-scale genotype datasets","display_name":"FlashPCA2: principal component analysis of Biobank-scale genotype datasets","publication_year":2017,"publication_date":"2017-05-04","ids":{"openalex":"https://openalex.org/W2951349772","doi":"https://doi.org/10.1093/bioinformatics/btx299","mag":"2951349772"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btx299","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx299","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/17/2776/25163845/btx299.pdf","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"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/33/17/2776/25163845/btx299.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037544210","display_name":"Gad Abraham","orcid":"https://orcid.org/0000-0003-4853-0118"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Gad Abraham","raw_affiliation_strings":["Centre for Systems Genomics, School of BioSciences, University of Melbourne, Parkville, VIC, Australia","Department of Pathology, University of Melbourne, Parkville, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Centre for Systems Genomics, School of BioSciences, University of Melbourne, Parkville, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"Department of Pathology, University of Melbourne, Parkville, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101665647","display_name":"Yixuan Qiu","orcid":"https://orcid.org/0000-0003-0109-6692"},"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":"Yixuan Qiu","raw_affiliation_strings":["Department of Statistics, Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056977453","display_name":"Michael Inouye","orcid":"https://orcid.org/0000-0001-9413-6520"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Michael Inouye","raw_affiliation_strings":["Centre for Systems Genomics, School of BioSciences, University of Melbourne, Parkville, VIC, Australia","Department of Pathology, University of Melbourne, Parkville, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Centre for Systems Genomics, School of BioSciences, University of Melbourne, Parkville, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"Department of Pathology, University of Melbourne, Parkville, VIC, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037544210"],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":10.1027,"has_fulltext":false,"cited_by_count":443,"citation_normalized_percentile":{"value":0.98822915,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"33","issue":"17","first_page":"2776","last_page":"2778"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9993000030517578,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9993000030517578,"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/T11468","display_name":"Genetic Mapping and Diversity in Plants and Animals","score":0.9980999827384949,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.8521917462348938},{"id":"https://openalex.org/keywords/biobank","display_name":"Biobank","score":0.8100377321243286},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6056699156761169},{"id":"https://openalex.org/keywords/genotyping","display_name":"Genotyping","score":0.5506271719932556},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.48997846245765686},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4736924171447754},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.43767163157463074},{"id":"https://openalex.org/keywords/robust-principal-component-analysis","display_name":"Robust principal component analysis","score":0.4236922860145569},{"id":"https://openalex.org/keywords/genotype","display_name":"Genotype","score":0.3402090072631836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24655106663703918},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.23367390036582947},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.21993446350097656},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.17840459942817688},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.08897596597671509}],"concepts":[{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.8521917462348938},{"id":"https://openalex.org/C116567970","wikidata":"https://www.wikidata.org/wiki/Q864217","display_name":"Biobank","level":2,"score":0.8100377321243286},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6056699156761169},{"id":"https://openalex.org/C31467283","wikidata":"https://www.wikidata.org/wiki/Q912147","display_name":"Genotyping","level":4,"score":0.5506271719932556},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.48997846245765686},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4736924171447754},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.43767163157463074},{"id":"https://openalex.org/C2777749129","wikidata":"https://www.wikidata.org/wiki/Q17148469","display_name":"Robust principal component analysis","level":3,"score":0.4236922860145569},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.3402090072631836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24655106663703918},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.23367390036582947},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.21993446350097656},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.17840459942817688},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.08897596597671509},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","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},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/bioinformatics/btx299","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx299","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/17/2776/25163845/btx299.pdf","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"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btx299","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx299","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/17/2776/25163845/btx299.pdf","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"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334705","display_name":"National Health and Medical Research Council","ror":"https://ror.org/011kf5r70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951349772.pdf","grobid_xml":"https://content.openalex.org/works/W2951349772.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1974611538","https://openalex.org/W2009588715","https://openalex.org/W2060427373","https://openalex.org/W2082704080","https://openalex.org/W2099085143","https://openalex.org/W2102381029","https://openalex.org/W2104549677","https://openalex.org/W2108169091","https://openalex.org/W2284253967","https://openalex.org/W2950232131"],"related_works":["https://openalex.org/W4283792950","https://openalex.org/W2124460284","https://openalex.org/W2563483704","https://openalex.org/W3124370832","https://openalex.org/W3003801099","https://openalex.org/W2003667605","https://openalex.org/W62130100","https://openalex.org/W1980960407","https://openalex.org/W2365825610","https://openalex.org/W659321198"],"abstract_inverted_index":{"Abstract":[0],"Motivation":[1],"Principal":[2],"component":[3],"analysis":[4],"(PCA)":[5],"is":[6,49],"a":[7,17,62],"crucial":[8],"step":[9],"in":[10],"quality":[11],"control":[12],"of":[13,28,34,36],"genomic":[14],"data":[15,89],"and":[16,83],"common":[18],"approach":[19],"for":[20],"understanding":[21],"population":[22],"genetic":[23],"structure.":[24],"With":[25],"the":[26,46],"advent":[27],"large":[29],"genotyping":[30],"studies":[31],"involving":[32],"hundreds":[33],"thousands":[35],"individuals,":[37],"standard":[38],"approaches":[39],"are":[40,90],"no":[41],"longer":[42],"feasible.":[43],"However,":[44],"when":[45],"full":[47],"decomposition":[48],"not":[50],"required,":[51],"substantial":[52],"computational":[53],"savings":[54],"can":[55,65],"be":[56],"made.":[57],"Results":[58],"We":[59],"present":[60],"FlashPCA2,":[61],"tool":[63],"that":[64],"perform":[66],"partial":[67],"PCA":[68],"on":[69],"1":[70],"million":[71],"individuals":[72],"faster":[73],"than":[74],"competing":[75],"approaches,":[76],"while":[77],"requiring":[78],"substantially":[79],"less":[80],"memory.":[81],"Availability":[82],"implementation":[84],"https://github.com/gabraham/flashpca.":[85],"Supplementary":[86,88],"information":[87],"available":[91],"at":[92],"Bioinformatics":[93],"online.":[94]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":67},{"year":2024,"cited_by_count":55},{"year":2023,"cited_by_count":70},{"year":2022,"cited_by_count":73},{"year":2021,"cited_by_count":72},{"year":2020,"cited_by_count":49},{"year":2019,"cited_by_count":30},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2019-06-27T00:00:00"}
