{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T04:35:28Z","timestamp":1791434128876,"version":"4.3.3"},"reference-count":22,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T00:00:00Z","timestamp":1739232000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000051","name":"National Human Genome Research Institute","doi-asserted-by":"publisher","award":["R01HG010140"],"award-info":[{"award-number":["R01HG010140"]}],"id":[{"id":"10.13039\/100000051","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000025","name":"National Institutes of Mental Health","doi-asserted-by":"crossref","award":["R01MH124244"],"award-info":[{"award-number":["R01MH124244"]}],"id":[{"id":"10.13039\/100000025","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>The growing availability of large-scale population biobanks has the potential to significantly advance our understanding of human health and disease. However, the massive computational and storage demands of whole genome sequencing (WGS) data pose serious challenges, particularly for underfunded institutions or researchers in developing countries. This disparity in resources can limit equitable access to cutting-edge genetic research.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We present novel algorithms and regression methods that dramatically reduce both computation time and storage requirements for WGS studies, with particular attention to rare variant representation. By integrating these approaches into PLINK 2.0, we demonstrate substantial gains in efficiency without compromising analytical accuracy. In an exome-wide association analysis of 19.4 million variants for the body mass index phenotype in 125\u00a0077 individuals (AllofUs project data), we reduced runtime from 695.35\u2009min (11.5\u2009h) on a single machine to 1.57\u2009min with 30 GB of memory and 50 threads (or 8.67\u2009min with 4 threads). Additionally, the framework supports multi-phenotype analyses, further enhancing its flexibility.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Our optimized methods are fully integrated into PLINK 2.0 and can be accessed at: https:\/\/www.cog-genomics.org\/plink\/2.0\/.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf067","type":"journal-article","created":{"date-parts":[[2025,2,5]],"date-time":"2025-02-05T23:19:39Z","timestamp":1738797579000},"source":"Crossref","is-referenced-by-count":5,"title":["Efficient storage and regression computation for population-scale genome sequencing studies"],"prefix":"10.1093","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1457-9925","authenticated-orcid":false,"given":"Manuel A","family":"Rivas","sequence":"first","affiliation":[{"name":"Department of Biomedical Data Science, Stanford University , Stanford, CA 94305,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3290-3306","authenticated-orcid":false,"given":"Christopher","family":"Chang","sequence":"additional","affiliation":[{"name":"Grail Inc. , Menlo Park, CA 94025,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,2,11]]},"reference":[{"key":"2025031104020361200_btaf067-B1","doi-asserted-by":"crossref","DOI":"10.1126\/science.abf8683","article-title":"Sequencing of 640,000 exomes identifies variants associated with protection from obesity","volume":"373","author":"Akbari","year":"2021","journal-title":"Science"},{"key":"2025031104020361200_btaf067-B2","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1038\/s41586-023-06957-x","article-title":"Genomic data in the all of us research program","volume":"627","author":"All of Us Research Program Genomics Investigators","year":"2024","journal-title":"Nature"},{"key":"2025031104020361200_btaf067-B3","doi-asserted-by":"crossref","first-page":"eadf4428","DOI":"10.1126\/scitranslmed.adf4428","article-title":"Prospective study design and data analysis in UK biobank","volume":"16","author":"Allen","year":"2024","journal-title":"Sci Transl Med"},{"key":"2025031104020361200_btaf067-B4","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":"2025031104020361200_btaf067-B5","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511629211","volume-title":"Elementary Matrices","author":"Frazer","year":"1938"},{"key":"2025031104020361200_btaf067-B6","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1038\/s41586-022-05473-8","article-title":"FinnGen provides genetic insights from a well-phenotyped isolated population","volume":"613","author":"Kurki","year":"2023","journal-title":"Nature"},{"key":"2025031104020361200_btaf067-B7","author":"LAPACK\u2013linear algebra package, 2025"},{"key":"2025031104020361200_btaf067-B8","doi-asserted-by":"crossref","first-page":"4148","DOI":"10.1093\/bioinformatics\/btab452","article-title":"Fast numerical optimization for genome sequencing data in population biobanks","volume":"37","author":"Li","year":"2021","journal-title":"Bioinformatics"},{"key":"2025031104020361200_btaf067-B9","author":"Li","year":"2023"},{"key":"2025031104020361200_btaf067-B10","doi-asserted-by":"crossref","first-page":"906","DOI":"10.1038\/s41588-018-0144-6","article-title":"Mixed-model association for biobank-scale datasets","volume":"50","author":"Loh","year":"2018","journal-title":"Nat Genet"},{"key":"2025031104020361200_btaf067-B11","doi-asserted-by":"crossref","first-page":"e1004876","DOI":"10.1371\/journal.pgen.1004876","article-title":"Identification and functional characterization of G6PC2 coding variants influencing glycemic traits define an effector transcript at the G6PC2-ABCB11 locus","volume":"11","author":"Mahajan","year":"2015","journal-title":"PLoS Genet"},{"key":"2025031104020361200_btaf067-B12","first-page":"2287","article-title":"Spectral regularization algorithms for learning large incomplete matrices","volume":"11","author":"Mazumder","year":"2010","journal-title":"J Mach Learn Res"},{"key":"2025031104020361200_btaf067-B13","doi-asserted-by":"crossref","first-page":"1097","DOI":"10.1038\/s41588-021-00870-7","article-title":"Computationally efficient whole-genome regression for quantitative and binary traits","volume":"53","author":"Mbatchou","year":"2021","journal-title":"Nat Genet"},{"key":"2025031104020361200_btaf067-B14","doi-asserted-by":"crossref","first-page":"2495","DOI":"10.1093\/bioinformatics\/bty999","article-title":"Global biobank engine: enabling genotype-phenotype browsing for biobank summary statistics","volume":"35","author":"McInnes","year":"2019","journal-title":"Bioinformatics"},{"key":"2025031104020361200_btaf067-B15","doi-asserted-by":"crossref","first-page":"1891","DOI":"10.1214\/21-AOAS1575","article-title":"Large-scale multivariate sparse regression with applications to UK biobank","volume":"16","author":"Qian","year":"2022","journal-title":"Ann Appl Stat"},{"key":"2025031104020361200_btaf067-B16","doi-asserted-by":"crossref","first-page":"2419","DOI":"10.1093\/bioinformatics\/btt409","article-title":"Assessing association between protein truncating variants and quantitative traits","volume":"29","author":"Rivas","year":"2013","journal-title":"Bioinformatics"},{"key":"2025031104020361200_btaf067-B17","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1038\/s41588-020-00757-z","article-title":"Genetics of 35 blood and urine biomarkers in the UK biobank","volume":"53","author":"Sinnott-Armstrong","year":"2021","journal-title":"Nat. Genet"},{"key":"2025031104020361200_btaf067-B18","doi-asserted-by":"crossref","first-page":"R173","DOI":"10.1093\/hmg\/ddy188","article-title":"Recent advances in developing therapeutics for cystic fibrosis","volume":"27","author":"Strug","year":"2018","journal-title":"Hum Mol Genet"},{"key":"2025031104020361200_btaf067-B19","doi-asserted-by":"crossref","first-page":"4064","DOI":"10.1038\/s41467-019-11953-9","article-title":"Components of genetic associations across 2,138 phenotypes in the uk biobank highlight adipocyte biology","volume":"10","author":"Tanigawa","year":"2019","journal-title":"Nat Commun"},{"key":"2025031104020361200_btaf067-B20","doi-asserted-by":"crossref","first-page":"e1008682","DOI":"10.1371\/journal.pgen.1008682","article-title":"Rare protein-altering variants in ANGPTL7 lower intraocular pressure and protect against glaucoma","volume":"16","author":"Tanigawa","year":"2020","journal-title":"PLoS Genet"},{"key":"2025031104020361200_btaf067-B21","author":"Verma"},{"key":"2025031104020361200_btaf067-B22","doi-asserted-by":"crossref","first-page":"100361","DOI":"10.1016\/j.xgen.2023.100361","article-title":"Genotyping and population characteristics of the China Kadoorie biobank","volume":"3","author":"Walters","year":"2023","journal-title":"Cell Genom"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf067\/61850680\/btaf067.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/3\/btaf067\/61850680\/btaf067.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/3\/btaf067\/61850680\/btaf067.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T00:02:20Z","timestamp":1741651340000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf067\/8008994"}},"subtitle":[],"editor":[{"given":"Christina","family":"Kendziorski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,2,11]]},"references-count":22,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf067","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.04.11.589062","asserted-by":"object"}]},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,3]]},"published":{"date-parts":[[2025,2,11]]},"article-number":"btaf067"}}