{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T05:51:12Z","timestamp":1778133072238,"version":"3.51.4"},"reference-count":12,"publisher":"Oxford University Press (OUP)","issue":"22","license":[{"start":{"date-parts":[[2021,5,14]],"date-time":"2021-05-14T00:00:00Z","timestamp":1620950400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["3R01HL-117626-02S1"],"award-info":[{"award-number":["3R01HL-117626-02S1"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U01HL137182"],"award-info":[{"award-number":["U01HL137182"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,11,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>The sparse allele vectors file format is an efficient storage format for large-scale DNA variation data and is designed for high throughput association analysis by leveraging techniques for fast deserialization of data into computer memory. A command line interface has been developed to complement the storage format and supports basic features like importing, exporting and subsetting. Additionally, a C++ programming API is available allowing for easy integration into analysis software.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>https:\/\/github.com\/statgen\/savvy.<\/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\/btab378","type":"journal-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:22:08Z","timestamp":1620933728000},"page":"4248-4250","source":"Crossref","is-referenced-by-count":16,"title":["Sparse allele vectors and the savvy software suite"],"prefix":"10.1093","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3668-6086","authenticated-orcid":false,"given":"Jonathon","family":"LeFaive","sequence":"first","affiliation":[{"name":"Department of Biostatistics, University of Michigan School of Public Health , Ann Arbor, MI 48109, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Albert V","family":"Smith","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, University of Michigan School of Public Health , Ann Arbor, MI 48109, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyun Min","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, University of Michigan School of Public Health , Ann Arbor, MI 48109, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gon\u00e7alo","family":"Abecasis","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, University of Michigan School of Public Health , Ann Arbor, MI 48109, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2021,5,14]]},"reference":[{"key":"2023051607081891400_btab378-B1","first-page":"308296","article-title":"BGEN: a binary file format for imputed genotype and haplotype data","author":"Band","year":"2018","journal-title":"bioRxiv"},{"key":"2023051607081891400_btab378-B2","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41586-018-0579-z","article-title":"The UK Biobank resource with deep phenotyping and genomic data","volume":"562","author":"Bycroft","year":"2018","journal-title":"Nature"},{"key":"2023051607081891400_btab378-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":"2023051607081891400_btab378-B4","doi-asserted-by":"crossref","first-page":"1266","DOI":"10.1093\/bioinformatics\/btu014","article-title":"Efficient haplotype matching and storage using the positional Burrows\u2013Wheeler transform (PBWT","volume":"30","author":"Durbin","year":"2014","journal-title":"Bioinformatics"},{"key":"2023051607081891400_btab378-B5","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1038\/nmeth.3654","article-title":"Efficient genotype compression and analysis of large genetic-variation data sets","volume":"13","author":"Layer","year":"2016","journal-title":"Nat. Methods"},{"key":"2023051607081891400_btab378-B6","doi-asserted-by":"crossref","first-page":"2987","DOI":"10.1093\/bioinformatics\/btr509","article-title":"A statistical framework for SNP calling, mutation discovery, association mapping and population genetical parameter estimation from sequencing data","volume":"27","author":"Li","year":"2011","journal-title":"Bioinformatics"},{"key":"2023051607081891400_btab378-B7","doi-asserted-by":"crossref","first-page":"718","DOI":"10.1093\/bioinformatics\/btq671","article-title":"Tabix: fast retrieval of sequence features from generic TAB-delimited files","volume":"27","author":"Li","year":"2011","journal-title":"Bioinformatics"},{"key":"2023051607081891400_btab378-B8","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1093\/bioinformatics\/btv613","article-title":"BGT: efficient and flexible genotype query across many samples","volume":"32","author":"Li","year":"2016","journal-title":"Bioinformatics"},{"key":"2023051607081891400_btab378-B9","first-page":", 5537\u20135538","article-title":"Sparse project VCF: efficient encoding of population genotype matrices","volume":"36","author":"Lin","year":"2020","journal-title":"Bioinformatics"},{"key":"2023051607081891400_btab378-B10","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1101\/gr.107524.110","article-title":"The genome analysis toolkit: a MapReduce framework for analyzing next-generation DNA sequencing data","volume":"20","author":"McKenna","year":"2010","journal-title":"Genome Res"},{"key":"2023051607081891400_btab378-B11","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1038\/s41586-021-03205-y","article-title":"Sequencing of 53,831 diverse genomes from the NHLBI TOPMed program","volume":"590","author":"Taliun","year":"2021","journal-title":"Nature"},{"key":"2023051607081891400_btab378-B12","doi-asserted-by":"crossref","first-page":"2251","DOI":"10.1093\/bioinformatics\/btx145","article-title":"SeqArray\u2014a storage-efficient high-performance data format for WGS variant calls","volume":"33","author":"Zheng","year":"2017","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btab378\/38612353\/btab378.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/22\/4248\/50335089\/btab378.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/22\/4248\/50335089\/btab378.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T07:09:26Z","timestamp":1684220966000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/22\/4248\/6275747"}},"subtitle":[],"editor":[{"given":"Pier Luigi","family":"Martelli","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,5,14]]},"references-count":12,"journal-issue":{"issue":"22","published-print":{"date-parts":[[2021,11,18]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab378","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,11,15]]},"published":{"date-parts":[[2021,5,14]]}}}