{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T08:09:48Z","timestamp":1776326988011,"version":"3.50.1"},"reference-count":10,"publisher":"Oxford University Press (OUP)","issue":"17","license":[{"start":{"date-parts":[[2017,5,5]],"date-time":"2017-05-05T00:00:00Z","timestamp":1493942400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/about_us\/legal\/notices"}],"funder":[{"DOI":"10.13039\/501100000925","name":"National Health and Medical Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000925","name":"NHMRC","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000925","name":"NHMRC","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000925","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Principal component analysis (PCA) is a crucial step in quality control of genomic data and a common approach for understanding population genetic structure. With the advent of large genotyping studies involving hundreds of thousands of individuals, standard approaches are no longer feasible. However, when the full decomposition is not required, substantial computational savings can be made.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We present FlashPCA2, a tool that can perform partial PCA on 1 million individuals faster than competing approaches, while requiring substantially less memory.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>https:\/\/github.com\/gabraham\/flashpca.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary information<\/jats:title>\n                    <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btx299","type":"journal-article","created":{"date-parts":[[2017,5,4]],"date-time":"2017-05-04T07:10:22Z","timestamp":1493881822000},"page":"2776-2778","source":"Crossref","is-referenced-by-count":393,"title":["FlashPCA2: principal component analysis of Biobank-scale genotype datasets"],"prefix":"10.1093","volume":"33","author":[{"given":"Gad","family":"Abraham","sequence":"first","affiliation":[{"name":"Centre for Systems Genomics, School of BioSciences, University of Melbourne, Parkville, VIC, Australia"},{"name":"Department of Pathology, University of Melbourne, Parkville, VIC, Australia"}]},{"given":"Yixuan","family":"Qiu","sequence":"additional","affiliation":[{"name":"Department of Statistics, Purdue University, West Lafayette, IN, USA"}]},{"given":"Michael","family":"Inouye","sequence":"additional","affiliation":[{"name":"Centre for Systems Genomics, School of BioSciences, University of Melbourne, Parkville, VIC, Australia"},{"name":"Department of Pathology, University of Melbourne, Parkville, VIC, Australia"}]}],"member":"286","published-online":{"date-parts":[[2017,5,5]]},"reference":[{"key":"2023020206272018500_btx299-B1","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1038\/nature15393","article-title":"A global reference for human genetic variation","volume":"526","author":"1000 Genomes Project Consortium","year":"2015","journal-title":"Nature"},{"key":"2023020206272018500_btx299-B2","doi-asserted-by":"crossref","first-page":"e93766","DOI":"10.1371\/journal.pone.0093766","article-title":"Fast principal component analysis of large-scale genome-wide data","volume":"9","author":"Abraham","year":"2014","journal-title":"PLoS One"},{"key":"2023020206272018500_btx299-B3","doi-asserted-by":"crossref","first-page":"7.","DOI":"10.1186\/s13742-015-0047-8","article-title":"Second-generation PLINK: rising to the challenge of larger and richer datasets","volume":"4","author":"Chang","year":"2015","journal-title":"GigaScience"},{"key":"2023020206272018500_btx299-B4","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1056\/NEJMp1500523","article-title":"A new initiative on precision medicine","volume":"372","author":"Collins","year":"2015","journal-title":"N. Engl. J. Med"},{"key":"2023020206272018500_btx299-B5","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1016\/j.ajhg.2015.12.022","article-title":"Fast principal-component analysis reveals convergent evolution of ADH1B in Europe and East Asia","volume":"98","author":"Galinsky","year":"2016","journal-title":"Am. J. Hum. Genet"},{"key":"2023020206272018500_btx299-B6","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1038\/ng.139","article-title":"Interpreting principal component analyses of spatial population genetic variation","volume":"40","author":"Novembre","year":"2008","journal-title":"Nat. Genet"},{"key":"2023020206272018500_btx299-B7","doi-asserted-by":"crossref","first-page":"e190.","DOI":"10.1371\/journal.pgen.0020190","article-title":"Population structure and eigenanalysis","volume":"2","author":"Patterson","year":"2006","journal-title":"PLoS Genet"},{"key":"2023020206272018500_btx299-B8","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1038\/nrg2813","article-title":"New approaches to population stratification in genome-wide association studies","volume":"11","author":"Price","year":"2010","journal-title":"Nat. Rev. Genet"},{"key":"2023020206272018500_btx299-B9","doi-asserted-by":"crossref","first-page":"2304","DOI":"10.1093\/bioinformatics\/btr341","article-title":"HAPGEN2: simulation of multiple disease SNPs","volume":"27","author":"Su","year":"2011","journal-title":"Bioinformatics"},{"key":"2023020206272018500_btx299-B10","doi-asserted-by":"crossref","first-page":"e1001779.","DOI":"10.1371\/journal.pmed.1001779","article-title":"UK Biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age","volume":"12","author":"Sudlow","year":"2015","journal-title":"PLoS Med"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/17\/2776\/49040964\/bioinformatics_33_17_2776.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/17\/2776\/49040964\/bioinformatics_33_17_2776.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T01:29:38Z","timestamp":1675301378000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/33\/17\/2776\/3798630"}},"subtitle":[],"editor":[{"given":"Oliver","family":"Stegle","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2017,5,5]]},"references-count":10,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2017,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btx299","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/094714","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2017,9,1]]},"published":{"date-parts":[[2017,5,5]]}}}