{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T15:30:33Z","timestamp":1786635033069,"version":"3.56.0"},"reference-count":9,"publisher":"Oxford University Press (OUP)","issue":"15","license":[{"start":{"date-parts":[[2018,12,7]],"date-time":"2018-12-07T00:00:00Z","timestamp":1544140800000},"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":"NIH","doi-asserted-by":"publisher","award":["5U01CA198943-03"],"award-info":[{"award-number":["5U01CA198943-03"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["2018-182798"],"award-info":[{"award-number":["2018-182798"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["2018-182799"],"award-info":[{"award-number":["2018-182799"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Chan Zuckerberg Initiative DAF"},{"DOI":"10.13039\/100000923","name":"SVCF","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100011021","name":"SRI","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011021","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100005302","name":"UIUC","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005302","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>High-Throughput Sequencing technologies produce huge amounts of data in the form of short genomic reads, associated quality values and read identifiers. Because of the significant structure present in these FASTQ datasets, general-purpose compressors are unable to completely exploit much of the inherent redundancy. Although there has been a lot of work on designing FASTQ compressors, most of them lack in support of one or more crucial properties, such as support for variable length reads, scalability to high coverage datasets, pairing-preserving compression and lossless compression.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>In this work, we propose SPRING, a reference-free compressor for FASTQ files. SPRING supports a wide variety of compression modes and features, including lossless compression, pairing-preserving compression, lossy compression of quality values, long read compression and random access. SPRING achieves substantially better compression than existing tools, for example, SPRING compresses 195 GB of 25\u00d7 whole genome human FASTQ from Illumina\u2019s NovaSeq sequencer to less than 7 GB, around 1.6\u00d7 smaller than previous state-of-the-art FASTQ compressors. SPRING achieves this improvement while using comparable computational resources.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>SPRING can be downloaded from https:\/\/github.com\/shubhamchandak94\/SPRING.<\/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\/bty1015","type":"journal-article","created":{"date-parts":[[2018,12,6]],"date-time":"2018-12-06T22:37:40Z","timestamp":1544135860000},"page":"2674-2676","source":"Crossref","is-referenced-by-count":80,"title":["SPRING: a next-generation compressor for FASTQ data"],"prefix":"10.1093","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1130-9762","authenticated-orcid":false,"given":"Shubham","family":"Chandak","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kedar","family":"Tatwawadi","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Idoia","family":"Ochoa","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0443-2305","authenticated-orcid":false,"given":"Mikel","family":"Hernaez","sequence":"additional","affiliation":[{"name":"Carl R. Woese Institute for Genomic Biology, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsachy","family":"Weissman","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2018,12,7]]},"reference":[{"key":"2023062713263872700_bty1015-B1","doi-asserted-by":"crossref","DOI":"10.1101\/426353","article-title":"An introduction to MPEG-G, the new ISO standard for genomic information representation","author":"Alberti","year":"2018"},{"key":"2023062713263872700_bty1015-B2","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":"2023062713263872700_bty1015-B3","doi-asserted-by":"crossref","first-page":"558","DOI":"10.1093\/bioinformatics\/btx639","article-title":"Compression of genomic sequencing reads via hash-based reordering: algorithm and analysis","volume":"34","author":"Chandak","year":"2018","journal-title":"Bioinformatics"},{"key":"2023062713263872700_bty1015-B4","doi-asserted-by":"crossref","first-page":"3051","DOI":"10.1093\/bioinformatics\/bts593","article-title":"SCALCE: boosting sequence compression algorithms using locally consistent encoding","volume":"28","author":"Hach","year":"2012","journal-title":"Bioinformatics"},{"key":"2023062713263872700_bty1015-B5","doi-asserted-by":"crossref","first-page":"3122","DOI":"10.1093\/bioinformatics\/btv330","article-title":"QVZ: lossy compression of quality values","volume":"31","author":"Malysa","year":"2015","journal-title":"Bioinformatics"},{"key":"2023062713263872700_bty1015-B6","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.1038\/nmeth.4037","article-title":"Comparison of high-throughput sequencing data compression tools","volume":"13","author":"Numanagi\u0107","year":"2016","journal-title":"Nat. Methods"},{"key":"2023062713263872700_bty1015-B7","first-page":"183","article-title":"Effect of lossy compression of quality scores on variant calling","volume":"18","author":"Ochoa","year":"2017","journal-title":"Brief. Bioinform"},{"key":"2023062713263872700_bty1015-B8","doi-asserted-by":"crossref","first-page":"2213","DOI":"10.1093\/bioinformatics\/btu208","article-title":"DSRC 2-industry-oriented compression of FASTQ files","volume":"30","author":"Roguski","year":"2014","journal-title":"Bioinformatics"},{"key":"2023062713263872700_bty1015-B9","doi-asserted-by":"crossref","first-page":"2748","DOI":"10.1093\/bioinformatics\/bty205","article-title":"Fastore: a space-saving solution for raw sequencing data","volume":"34","author":"Roguski","year":"2018","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/15\/2674\/50722542\/bioinformatics_35_15_2674.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/15\/2674\/50722542\/bioinformatics_35_15_2674.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T13:26:59Z","timestamp":1687872419000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/35\/15\/2674\/5232998"}},"subtitle":[],"editor":[{"given":"Bonnie","family":"Berger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2018,12,7]]},"references-count":9,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2019,8,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty1015","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,8,1]]},"published":{"date-parts":[[2018,12,7]]}}}