{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T22:55:34Z","timestamp":1778108134218,"version":"3.51.4"},"reference-count":11,"publisher":"Oxford University Press (OUP)","issue":"D1","funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,1,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The Sequence Read Archive (SRA, https:\/\/www.ncbi.nlm.nih.gov\/sra\/) stores raw sequencing data and alignment information to enhance reproducibility and facilitate new discoveries through data analysis. Here we note changes in storage designed to increase access and highlight analyses that augment metadata with taxonomic insight to help users select data. In addition, we present three unanticipated applications of taxonomic analysis.<\/jats:p>","DOI":"10.1093\/nar\/gkab1053","type":"journal-article","created":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T11:34:56Z","timestamp":1634643296000},"page":"D387-D390","source":"Crossref","is-referenced-by-count":389,"title":["The Sequence Read Archive: a decade more of explosive growth"],"prefix":"10.1093","volume":"50","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9134-4559","authenticated-orcid":false,"given":"Kenneth","family":"Katz","sequence":"first","affiliation":[{"name":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA"}]},{"given":"Oleg","family":"Shutov","sequence":"additional","affiliation":[{"name":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA"}]},{"given":"Richard","family":"Lapoint","sequence":"additional","affiliation":[{"name":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA"}]},{"given":"Michael","family":"Kimelman","sequence":"additional","affiliation":[{"name":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA"}]},{"given":"J\u00a0Rodney","family":"Brister","sequence":"additional","affiliation":[{"name":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA"}]},{"given":"Christopher","family":"O\u2019Sullivan","sequence":"additional","affiliation":[{"name":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA"}]}],"member":"286","published-online":{"date-parts":[[2021,11,24]]},"reference":[{"key":"2022010507370663200_B1","doi-asserted-by":"crossref","first-page":"D54","DOI":"10.1093\/nar\/gkr854","article-title":"The Sequence Read Archive: explosive growth of sequencing data","volume":"40","author":"Kodama","year":"2012","journal-title":"Nucleic Acids Res."},{"key":"2022010507370663200_B2","first-page":"3","article-title":"The FAIR Guiding Principles for scientific data management and stewardship","volume":"15","author":"Wilkinson","year":"2016","journal-title":"Sci. Data."},{"key":"2022010507370663200_B3","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1038\/nbt.3170","article-title":"Quality score compression improves genotyping accuracy","volume":"33","author":"Yu","year":"2015","journal-title":"Nat. Biotechnol."},{"key":"2022010507370663200_B4","doi-asserted-by":"crossref","first-page":"e59190","DOI":"10.1371\/journal.pone.0059190","article-title":"Compression of FASTQ and SAM format sequencing data","volume":"8","author":"Bonfield","year":"2013","journal-title":"PLoS One"},{"key":"2022010507370663200_B5","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkab1112","article-title":"Database resources of the National Center for Biotechnology Information","author":"Sayers","year":"2021","journal-title":"Nucleic Acids Res."},{"key":"2022010507370663200_B6","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1186\/s13059-021-02490-0","article-title":"STAT: A fast, scalable, MinHash-based k-mer tool to assess Sequence Read Archive next generation sequence submissions","volume":"22","author":"Katz","year":"2021","journal-title":"Genome Biol."},{"key":"2022010507370663200_B7","doi-asserted-by":"crossref","first-page":"D733","DOI":"10.1093\/nar\/gkv1189","article-title":"Reference sequence (RefSeq) database at NCBI: current status, taxonomic expansion, and functional annotation","volume":"44","author":"O\u2019Leary","year":"2016","journal-title":"Nucleic Acids Res."},{"key":"2022010507370663200_B8","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1186\/s13059-020-02023-1","article-title":"Terminating contamination: large-scale search identifies more than 2,000,000 contaminated entries in GenBank","volume":"21","author":"Steinegger","year":"2020","journal-title":"Genome Biol."},{"key":"2022010507370663200_B9","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1136\/mp.56.1.11","article-title":"Demystified. Human endogenous retroviruses","volume":"56","author":"Nelson","year":"2003","journal-title":"Mol. Pathol."},{"key":"2022010507370663200_B10","doi-asserted-by":"crossref","first-page":"D136","DOI":"10.1093\/nar\/gkr1178","article-title":"The NCBI Taxonomy database","volume":"40","author":"Federhen","year":"2012","journal-title":"Nucleic. Acids. Res."},{"key":"2022010507370663200_B11","doi-asserted-by":"crossref","first-page":"baaa062","DOI":"10.1093\/database\/baaa062","article-title":"NCBI Taxonomy: a comprehensive update on curation, resources and tools","volume":"2020","author":"Schoch","year":"2020","journal-title":"Database (Oxford)"}],"container-title":["Nucleic Acids Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/nar\/article-pdf\/50\/D1\/D387\/42058225\/gkab1053.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/nar\/article-pdf\/50\/D1\/D387\/42058225\/gkab1053.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T08:08:56Z","timestamp":1641370136000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/nar\/article\/50\/D1\/D387\/6438001"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,24]]},"references-count":11,"journal-issue":{"issue":"D1","published-online":{"date-parts":[[2021,11,24]]},"published-print":{"date-parts":[[2022,1,7]]}},"URL":"https:\/\/doi.org\/10.1093\/nar\/gkab1053","relation":{},"ISSN":["0305-1048","1362-4962"],"issn-type":[{"value":"0305-1048","type":"print"},{"value":"1362-4962","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,1,7]]},"published":{"date-parts":[[2021,11,24]]}}}