{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:57:07Z","timestamp":1780394227101,"version":"3.54.1"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"17","license":[{"start":{"date-parts":[[2020,5,27]],"date-time":"2020-05-27T00:00:00Z","timestamp":1590537600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Per-base quality values in Next Generation Sequencing data take a significant portion of storage even after compression. Lossy compression technologies could further reduce the space used by quality values. However, in many applications, lossless compression is still desired. Hence, sequencing data in multiple file formats have to be prepared for different applications.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We developed a scalable lossy to lossless compression solution for quality values named ScaleQC (Scalable Quality value Compression). ScaleQC is able to provide the so-called bit-stream level scalability that the losslessly compressed bit-stream by ScaleQC can be further truncated to lower data rates without incurring an expensive transcoding operation. Despite its scalability, ScaleQC still achieves comparable compression performance at both lossless and lossy data rates compared to the existing lossless or lossy compressors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>ScaleQC has been integrated with SAMtools as a special quality value encoding mode for CRAM. Its source codes can be obtained from our integrated SAMtools (https:\/\/github.com\/xmuyulab\/samtools) with dependency on integrated HTSlib (https:\/\/github.com\/xmuyulab\/htslib).<\/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\/btaa543","type":"journal-article","created":{"date-parts":[[2020,5,20]],"date-time":"2020-05-20T07:38:24Z","timestamp":1589960304000},"page":"4551-4559","source":"Crossref","is-referenced-by-count":6,"title":["ScaleQC: a scalable lossy to lossless solution for NGS data compression"],"prefix":"10.1093","volume":"36","author":[{"given":"Rongshan","family":"Yu","sequence":"first","affiliation":[{"name":"Digital Fujian Institute of Healthcare and Biomedical Big Data, School of Informatics, Xiamen University, Xiamen 316005, China"},{"name":"Aginome Scientific , Xiamen 316005, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5349-9680","authenticated-orcid":false,"given":"Wenxian","family":"Yang","sequence":"additional","affiliation":[{"name":"Aginome Scientific , Xiamen 316005, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2020,5,27]]},"reference":[{"key":"2023062213550709000_btaa543-B1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-015-0709-7","article-title":"Reference-free compression of high throughput sequencing data with a probabilistic de Bruijn graph","volume":"16","author":"Benoit","year":"2015","journal-title":"BMC Bioinform"},{"key":"2023062213550709000_btaa543-B2","doi-asserted-by":"crossref","first-page":"2818","DOI":"10.1093\/bioinformatics\/btu390","article-title":"The scramble conversion tool","volume":"30","author":"Bonfield","year":"2014","journal-title":"Bioinformatics"},{"key":"2023062213550709000_btaa543-B3","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":"2023062213550709000_btaa543-B4","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1093\/bioinformatics\/bty608","article-title":"Crumble: reference free lossy compression of sequence quality values","volume":"35","author":"Bonfield","year":"2019","journal-title":"Bioinformatics"},{"key":"2023062213550709000_btaa543-B5","doi-asserted-by":"crossref","first-page":"2130","DOI":"10.1093\/bioinformatics\/btu183","article-title":"Lossy compression of quality scores in genomic data","volume":"30","author":"C\u00e1novas","year":"2014","journal-title":"Bioinformatics"},{"key":"2023062213550709000_btaa543-B6","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1038\/ng.806","article-title":"A framework for variation discovery and genotyping using next-generation DNA sequencing data","volume":"43","author":"DePristo","year":"2011","journal-title":"Nat. Genet"},{"key":"2023062213550709000_btaa543-B7","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1101\/gr.114819.110","article-title":"Efficient storage of high throughput DNA sequencing data using reference-based compression","volume":"21","author":"Fritz","year":"2011","journal-title":"Genome Res"},{"key":"2023062213550709000_btaa543-B8","doi-asserted-by":"crossref","first-page":"1082","DOI":"10.1038\/nmeth.3133","article-title":"Deez: reference-based compression by local assembly","volume":"11","author":"Hach","year":"2014","journal-title":"Nat. Methods"},{"key":"2023062213550709000_btaa543-B9","author":"Hernaez","year":"2016"},{"key":"2023062213550709000_btaa543-B10","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1007\/978-1-4615-3596-6_5","volume-title":"Image and Text Compression","author":"Hirschberg","year":"1992"},{"key":"2023062213550709000_btaa543-B11","doi-asserted-by":"crossref","first-page":"e171","DOI":"10.1093\/nar\/gks754","article-title":"Compression of next-generation sequencing reads aided by highly efficient de novo assembly","volume":"40","author":"Jones","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2023062213550709000_btaa543-B12","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1002\/bies.200900181","article-title":"High-throughput DNA sequencing-concepts and limitations","volume":"32","author":"Kircher","year":"2010","journal-title":"Bioessays"},{"key":"2023062213550709000_btaa543-B13","doi-asserted-by":"crossref","first-page":"2078","DOI":"10.1093\/bioinformatics\/btp352","article-title":"The sequence alignment\/map format and samtools","volume":"25","author":"Li","year":"2009","journal-title":"Bioinformatics"},{"key":"2023062213550709000_btaa543-B14","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1109\/TCSVT.2003.815173","article-title":"Context-based adaptive binary arithmetic coding in the H.264\/AVC video compression standard","volume":"13","author":"Marpe","year":"2003","journal-title":"IEEE Trans. Circ. Syst. Video Technol"},{"key":"2023062213550709000_btaa543-B15","doi-asserted-by":"crossref","first-page":"3276","DOI":"10.1093\/bioinformatics\/btv384","article-title":"LFQC: a lossless compression algorithm for FASTQ files","volume":"31","author":"Nicolae","year":"2015","journal-title":"Bioinformatics"},{"key":"2023062213550709000_btaa543-B16","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":"2023062213550709000_btaa543-B17","doi-asserted-by":"crossref","first-page":"e27","DOI":"10.1093\/nar\/gks939","article-title":"NGC: lossless and lossy compression of aligned high-throughput sequencing data","volume":"41","author":"Popitsch","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"2023062213550709000_btaa543-B18","author":"Poplin","year":"2018"},{"key":"2023062213550709000_btaa543-B19","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1109\/PROC.1967.5493","article-title":"Results of a prototype television bandwidth compression scheme","volume":"55","author":"Robinson","year":"1967","journal-title":"Proc. IEEE"},{"key":"2023062213550709000_btaa543-B20","doi-asserted-by":"crossref","first-page":"2213","DOI":"10.1093\/bioinformatics\/btu208","article-title":"DSRC 2\u2014industry-oriented compression of FASTQ files","volume":"30","author":"Roguski","year":"2014","journal-title":"Bioinformatics"},{"key":"2023062213550709000_btaa543-B21","first-page":"202","author":"Shkarin","year":"2002"},{"key":"2023062213550709000_btaa543-B22","first-page":"241","author":"Voges","year":"2016"},{"key":"2023062213550709000_btaa543-B23","doi-asserted-by":"crossref","first-page":"1650","DOI":"10.1093\/bioinformatics\/btx737","article-title":"CALQ: compression of quality values of aligned sequencing data","volume":"34","author":"Voges","year":"2018","journal-title":"Bioinformatics"},{"key":"2023062213550709000_btaa543-B24","first-page":"520","article-title":"Arithmetic coding for data compression","volume-title":"Commun. ACM","author":"Witten","year":"1987"},{"key":"2023062213550709000_btaa543-B25","first-page":"1177","article-title":"Improving coding efficiency of mpeg-g standard using context-based arithmetic coding","author":"Yang","year":"2018"},{"key":"2023062213550709000_btaa543-B26","first-page":"IV","author":"Yu","year":"2003"},{"key":"2023062213550709000_btaa543-B27","doi-asserted-by":"crossref","first-page":"1352","DOI":"10.1109\/TSA.2005.860841","article-title":"A fine granular scalable to lossless audio coder","volume":"14","author":"Yu","year":"2006","journal-title":"IEEE Trans. Audio Speech Lang. Proc"},{"key":"2023062213550709000_btaa543-B28","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":"2023062213550709000_btaa543-B29","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1109\/TIT.1978.1055934","article-title":"Compression of individual sequences via variable-rate coding","volume":"24","author":"Ziv","year":"1978","journal-title":"IEEE Trans. Inf. Theory"},{"key":"2023062213550709000_btaa543-B30","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1038\/nbt.2835","article-title":"Integrating human sequence data sets provides a resource of benchmark SNP and indel genotype calls","volume":"32","author":"Zook","year":"2014","journal-title":"Nat. Biotechnol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa543\/33620196\/btaa543.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/17\/4551\/50677290\/btaa543.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/17\/4551\/50677290\/btaa543.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T13:21:29Z","timestamp":1687526489000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/36\/17\/4551\/5847594"}},"subtitle":[],"editor":[{"given":"Inanc","family":"Birol","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2020,5,27]]},"references-count":30,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2020,11,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa543","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.02.09.940932","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":[[2020,9,1]]},"published":{"date-parts":[[2020,5,27]]}}}