{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T15:31:52Z","timestamp":1771342312660,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,6,8]],"date-time":"2013-06-08T00:00:00Z","timestamp":1370649600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2013,12]]},"DOI":"10.1186\/1471-2105-14-187","type":"journal-article","created":{"date-parts":[[2013,6,8]],"date-time":"2013-06-08T08:14:09Z","timestamp":1370679249000},"source":"Crossref","is-referenced-by-count":48,"title":["QualComp: a new lossy compressor for quality scores based on rate distortion theory"],"prefix":"10.1186","volume":"14","author":[{"given":"Idoia","family":"Ochoa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Himanshu","family":"Asnani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinesh","family":"Bharadia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mainak","family":"Chowdhury","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsachy","family":"Weissman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Golan","family":"Yona","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,6,8]]},"reference":[{"issue":"6822","key":"5956_CR1","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1038\/35057062","volume":"409","author":"E Lander","year":"2001","unstructured":"Lander E, Linton L, Birren B, Nusbaum C, Zody M, Baldwin J, Devon K, Dewar K, Doyle M, FitzHugh W, Funke R, Gage D, Harris K, Heaford A, Howland J, Kann L, Lehoczky J, LeVine R, McEwan P, McKernan K, Meldrim J, Mesirov J, Miranda C, Morris W, Naylor J, Raymond C, Rosetti M, Santos R, Sheridan A, et al: Initial sequencing and analysis of the human genome. Nature. 2001, 409 (6822): 860-921. 10.1038\/35057062.","journal-title":"Nature"},{"key":"5956_CR2","unstructured":"Genome sequencing cost. http:\/\/www.genome.gov\/sequencingcosts\/ ,"},{"issue":"6016","key":"5956_CR3","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1126\/science.1200387","volume":"331","author":"M Hess","year":"2011","unstructured":"Hess M, Sczyrba A, Egan R, Kim T, Chokhawala H, Schroth G, Luo S, Clark D, Chen F, Zhang T, Mackie R, Pennacchio L, Tringe S, Visel A, Woyke T, Wang Z, Rubin E: Metagenomic discovery of biomass-degrading genes and genomes from cow rumen. Science. 2011, 331 (6016): 463-10.1126\/science.1200387.","journal-title":"Science"},{"issue":"7285","key":"5956_CR4","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1038\/nature08821","volume":"464","author":"J Qin","year":"2010","unstructured":"Qin J, Li R, Raes J, Arumugam M, Burgdorf K, Manichanh C, Nielsen T, Pons N, Levenez F, Yamada T, Mende D, Li J, Xu J, Li S, Li D, Cao J, Wang B, Liang H, Zheng H, Xie Y, Tap J, Lepage P, Bertalan M, Batto J, Hansen T, Paslier D, Linneber A, Bjorn Nielsen H, Pelletier E, Renault P et el.: A human gut microbial gene catalogue established by metagenomic sequencing. Nature. 2010, 464 (7285): 59-65. 10.1038\/nature08821.","journal-title":"Nature"},{"key":"5956_CR5","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1093\/nar\/gkq1019","volume":"39","author":"R Leinonen","year":"2011","unstructured":"Leinonen R, Sugawara H, Shumway M: The Sequence Read Archive. Nucleic Acids Res. 2011, 39: 19-21. 10.1093\/nar\/gkq768.","journal-title":"Nucleic Acids Res"},{"key":"5956_CR6","doi-asserted-by":"publisher","first-page":"1767","DOI":"10.1093\/nar\/gkp1137","volume":"38","author":"PJA Cock","year":"2009","unstructured":"Cock PJA, Fields CJ, Goto N, Heuer ML, Rice PM: The Sanger FASTQ format for sequences with quality scores, and the Solexa\/Illumina FASTQ variants. Nucleic Acids Res. 2009, 38: 1767-1771.","journal-title":"Nucleic Acids Res"},{"issue":"W1","key":"5956_CR7","doi-asserted-by":"publisher","first-page":"W622","DOI":"10.1093\/nar\/gks540","volume":"40","author":"M Lohse","year":"2012","unstructured":"Lohse M, Bolger A, Nagel A, Fernie A, Lunn J, Stitt M, Usadel B: RobiNA: a user-friendly, integrated software solution for RNA-Seq-based transcriptomics. Nucleic Acids Res. 2012, 40 (W1): W622-627. 10.1093\/nar\/gks540.","journal-title":"Nucleic Acids Res"},{"key":"5956_CR8","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1186\/1471-2105-11-485","volume":"11","author":"M Cox","year":"2010","unstructured":"Cox M, Peterson D, Biggs P: SolexaQA: At-a-glance quality assessment of Illumina second-generation sequencing data. BMC Bioinformatics. 2010, 11: 485-10.1186\/1471-2105-11-485.","journal-title":"BMC Bioinformatics"},{"issue":"11","key":"5956_CR9","doi-asserted-by":"publisher","first-page":"1851","DOI":"10.1101\/gr.078212.108","volume":"18","author":"H Li","year":"2008","unstructured":"Li H, Ruan J, Durbin R: Mapping short DNA sequencing reads and calling variants using mapping quality scores. Genome Res. 2008, 18 (11): 1851-1858. 10.1101\/gr.078212.108.","journal-title":"Genome Res"},{"issue":"3","key":"5956_CR10","doi-asserted-by":"publisher","first-page":"R25","DOI":"10.1186\/gb-2009-10-3-r25","volume":"10","author":"B Langmead","year":"2009","unstructured":"Langmead B, Trapnell C, Pop M, Salzberg S: Ultrafast and memory-efficient alignment of short DNA sequences to the human genome. Genome Biol. 2009, 10 (3): R25-10.1186\/gb-2009-10-3-r25.","journal-title":"Genome Biol"},{"issue":"14","key":"5956_CR11","doi-asserted-by":"publisher","first-page":"1754","DOI":"10.1093\/bioinformatics\/btp324","volume":"25","author":"H Li","year":"2009","unstructured":"Li H, Durbin R: Fast and accurate short read alignment with Burrows-Wheeler transform. Bioinformatics. 2009, 25 (14): 1754-1760. 10.1093\/bioinformatics\/btp324.","journal-title":"Bioinformatics"},{"issue":"6","key":"5956_CR12","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1101\/gr.111120.110","volume":"21","author":"G Lunter","year":"2011","unstructured":"Lunter G, Goodson M: Stampy: A statistical algorithm for sensitive and fast mapping of Illumina sequence reads. Genome Res. 2011, 21 (6): 936-939. 10.1101\/gr.111120.110.","journal-title":"Genome Res"},{"issue":"9","key":"5956_CR13","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.1101\/gr.107524.110","volume":"20","author":"A McKenna","year":"2010","unstructured":"McKenna A, Hanna M, Banks E, Sivachenko A, Cibulskis K, Kernytsky A, Garimella K, Altshuler D, Gabriel S, Daly M, DePristo M: The Genome Analysis Toolkit: a MapReduce framework for analyzing next-generation DNA sequencing data. Genome Res. 2010, 20 (9): 1297-1303. 10.1101\/gr.107524.110.","journal-title":"Genome Res"},{"issue":"5","key":"5956_CR14","doi-asserted-by":"publisher","first-page":"e53","DOI":"10.1371\/journal.pcbi.0010053","volume":"1","author":"J Zhang","year":"2005","unstructured":"Zhang J, Wheeler D, Yakub I, Wei S, Sood R, Rowe W, Liu P, Gibbs R, Buetow K: SNPdetector: a software tool for sensitive and accurate SNP detection. PLoS Comput Biol. 2005, 1 (5): e53-10.1371\/journal.pcbi.0010053.","journal-title":"PLoS Comput Biol"},{"key":"5956_CR15","first-page":"43","volume-title":"Data Compression Conference, 2007. DCC\u201907","author":"M Cao","year":"2007","unstructured":"Cao M, Dix T, Allison L, Mears C: A simple statistical algorithm for biological sequence compression. Data Compression Conference, 2007. DCC\u201907. 2007, Snowbird, UT, USA: IEEE, 43-52."},{"key":"5956_CR16","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/332306.332352","volume-title":"Proceedings of the Fourth Annual International Conference on Computational Molecular Biology","author":"X Chen","year":"2000","unstructured":"Chen X, Kwon S, Li M: A compression algorithm for DNA sequences and its applications in genome comparison. Proceedings of the Fourth Annual International Conference on Computational Molecular Biology. 2000, Tokyo, Japan: ACM, 107-107."},{"key":"5956_CR17","doi-asserted-by":"publisher","first-page":"1696","DOI":"10.1093\/bioinformatics\/18.12.1696","volume":"18","author":"X Chen","year":"2002","unstructured":"Chen X, Li M, Ma B, Tromp J: DNACompress: Fast and effective DNA sequence compression. Bioinformatics. 2002, 18: 1696-1698. 10.1093\/bioinformatics\/18.12.1696.","journal-title":"Bioinformatics"},{"issue":"6","key":"5956_CR18","doi-asserted-by":"publisher","first-page":"e21588","DOI":"10.1371\/journal.pone.0021588","volume":"6","author":"AJ Pinho","year":"2011","unstructured":"Pinho AJ, Ferreira P, Neves A, Bastos C: On the representability of complete genomes by multiple competing finite-context (Markov) models. PLoS ONE. 2011, 6 (6): e21588-10.1371\/journal.pone.0021588.","journal-title":"PLoS ONE"},{"key":"5956_CR19","first-page":"512","volume":"12","author":"H Sato","year":"2001","unstructured":"Sato H, Yoshioka T, Konagaya A, Toyoda T: DNA data compression in the post genome era. Genome Inf. 2001, 12: 512-514.","journal-title":"Genome Inf"},{"key":"5956_CR20","first-page":"274","volume":"25","author":"S Christley","year":"2008","unstructured":"Christley S, Lu Y, Li C, Xie X: Human Genomes as email attachments. Genome Inf. 2008, 25: 274-275.","journal-title":"Genome Inf"},{"issue":"4","key":"5956_CR21","doi-asserted-by":"publisher","first-page":"e27","DOI":"10.1093\/nar\/gkr1124","volume":"40","author":"AJ Pinho","year":"2011","unstructured":"Pinho AJ, Pratas D, Garciaa SP: GReEn: a tool for efficient compression of genome resequencing data. Nucleic Acids Res. 2011, 40 (4): e27-27.","journal-title":"Nucleic Acids Res"},{"key":"5956_CR22","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/978-3-642-16321-0_20","volume-title":"String Processing and Information Retrieval","author":"S Kuruppu","year":"2010","unstructured":"Kuruppu S, Puglisi SJ, Zobel J: Relative Lempel-Ziv compression of genomes for large-scale storage and retrieval. String Processing and Information Retrieval. 2010, Los Cabos, Mexico: Springer, 201-206."},{"key":"5956_CR23","volume-title":"Proceeding of ACSC","author":"S Kuruppu","year":"2011","unstructured":"Kuruppu S, Puglisi SJ, Zobel J: Optimized relative Lempel-Ziv compression of genomes. Proceeding of ACSC. 2011, Perth, Australia: Australasian Computer Science Conference (ACSC)"},{"key":"5956_CR24","first-page":"38","volume":"9","author":"LS Heath","year":"2010","unstructured":"Heath LS, Hou A, Xia H, Zhang L: A genome compression algorithm supporting manipulation. Proc LSS Comput Syst Bioinform Conf. 2010, 9: 38-49.","journal-title":"Proc LSS Comput Syst Bioinform Conf"},{"key":"5956_CR25","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/ISIT.2012.6283542","volume-title":"Information Theory Proceedings (ISIT), 2012 IEEE International Symposium on","author":"N Ma","year":"2012","unstructured":"Ma N, Ramchandran K, Tse D: A Compression Algorithm Using Mis-aligned side information. Information Theory Proceedings (ISIT), 2012 IEEE International Symposium on. 2012, Cambridge, Massachusetts, USA: IEEE, 16-20."},{"issue":"7","key":"5956_CR26","doi-asserted-by":"publisher","first-page":"e45","DOI":"10.1093\/nar\/gkr009","volume":"39","author":"C Wang","year":"2011","unstructured":"Wang C, Zhang D: A novel compression tool for efficient storage of genome resequencing data. Nucleic Acids Res. 2011, 39 (7): e45-45. 10.1093\/nar\/gkr009.","journal-title":"Nucleic Acids Res"},{"key":"5956_CR27","first-page":"427","volume-title":"IEEE Inf Theory Workshop, ITW","author":"BG Chern","year":"2012","unstructured":"Chern BG, Ochoa I, Manolakos A, No A, Venkat K, Weissman T: Reference based genome compression. IEEE Inf Theory Workshop, ITW. 2012, Lausanne, Switzerland: IEEE, 427-431."},{"issue":"1","key":"5956_CR28","first-page":"242","volume":"9","author":"W Timothy","year":"2008","unstructured":"Timothy W, White J, Hendy MD: Compressing DNA sequence databases with coil. Bioinformatics. 2008, 9 (1): 242-","journal-title":"Bioinformatics"},{"issue":"6","key":"5956_CR29","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1093\/bioinformatics\/btr014","volume":"27","author":"S Deorowicz","year":"2011","unstructured":"Deorowicz S, Grabowski S: Compression of genomic sequences in FASTQ format. Bioinformatics. 2011, 27 (6): 860-862. 10.1093\/bioinformatics\/btr014.","journal-title":"Bioinformatics"},{"key":"5956_CR30","doi-asserted-by":"publisher","first-page":"2192","DOI":"10.1093\/bioinformatics\/btq346","volume":"26","author":"W Tembe","year":"2010","unstructured":"Tembe W, Lowey J, Suh E: G-SQZ: compact encoding of genomic sequence and quality data. Bioinformatics. 2010, 26: 2192-2194. 10.1093\/bioinformatics\/btq346.","journal-title":"Bioinformatics"},{"issue":"22","key":"5956_CR31","doi-asserted-by":"publisher","first-page":"e171","DOI":"10.1093\/nar\/gks754","volume":"40","author":"DC Jones","year":"2012","unstructured":"Jones DC, Ruzzo WL, Peng X, Katze MG: Compression of next-generation sequencing reads aided by highly efficient de novo assembly. Nucleic Acids Res. 2012, 40 (22): e171-171. 10.1093\/nar\/gks754.","journal-title":"Nucleic Acids Res"},{"key":"5956_CR32","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1089\/cmb.2010.0253","volume":"18","author":"C Kozanitis","year":"2011","unstructured":"Kozanitis C, Saunders C, Kruglyak S, Bafna V, Varghese G: Compressing genomic sequence fragments using SlimGene. J Comput Biol J Comput Mol Cell Biol. 2011, 18: 401-413. 10.1089\/cmb.2010.0253.","journal-title":"J Comput Biol J Comput Mol Cell Biol"},{"key":"5956_CR33","doi-asserted-by":"publisher","first-page":"734","DOI":"10.1101\/gr.114819.110","volume":"21","author":"MH Fritz","year":"2011","unstructured":"Fritz MH, Leinonen R, Cochrane G, Birney E: Efficient storage of high throughput sequencing data using reference-based compression. Genome Res. 2011, 21: 734-774. 10.1101\/gr.114819.110.","journal-title":"Genome Res"},{"key":"5956_CR34","unstructured":"fastqz. http:\/\/mattmahoney.net\/dc\/fastqz\/ ,"},{"issue":"23","key":"5956_CR35","doi-asserted-by":"publisher","first-page":"3051","DOI":"10.1093\/bioinformatics\/bts593","volume":"28","author":"F Hach","year":"2012","unstructured":"Hach F, Numanagi\u0107 I, Alkan C, Sahinalp SC: SCALCE: boosting sequence compression algorithms using locally consistent encoding. Bioinformatics. 2012, 28 (23): 3051-3057. 10.1093\/bioinformatics\/bts593.","journal-title":"Bioinformatics"},{"key":"5956_CR36","unstructured":"Cramtools. https:\/\/github.com\/vadimzalunin\/crammer ,"},{"key":"5956_CR37","unstructured":"The Pistoia Alliance. http:\/\/www.sequencesqueeze.org\/ ,"},{"key":"5956_CR38","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/2047-217X-1-2","volume":"1","author":"G Cochrane","year":"2012","unstructured":"Cochrane G, Cook C, Birney E: The future of DNA sequence archiving. GigaScience. 2012, 1: 2-10.1186\/2047-217X-1-2. http:\/\/www.gigasciencejournal.com\/content\/1\/1\/2 ,","journal-title":"GigaScience"},{"issue":"5","key":"5956_CR39","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1093\/bioinformatics\/btr689","volume":"28","author":"R Wan","year":"2011","unstructured":"Wan R, Anh VN, Asai K: Transformations for the compression of FASTQ quality scores of next generation sequencing data. Bioinformatics. 2011, 28 (5): 628-635.","journal-title":"Bioinformatics"},{"issue":"1","key":"5956_CR40","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/18.567644","volume":"43","author":"A Lapidoth","year":"1997","unstructured":"Lapidoth A: On the role of mismatch in rate distortion theory. Inf Theory, IEEE Trans. 1997, 43 (1): 38-47. 10.1109\/18.567644.","journal-title":"Inf Theory, IEEE Trans"},{"key":"5956_CR41","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611","volume-title":"Elements of Information Theory, Volume 6","author":"T Cover","year":"1991","unstructured":"Cover T, Thomas J: Elements of Information Theory, Volume 6. 1991"},{"issue":"2","key":"5956_CR42","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","volume":"28","author":"S Lloyd","year":"1982","unstructured":"Lloyd S: Least squares quantization in PCM. Inf Theory, IEEE Trans on. 1982, 28 (2): 129-137. 10.1109\/TIT.1982.1056489.","journal-title":"Inf Theory, IEEE Trans on"},{"key":"5956_CR43","first-page":"14","volume-title":"Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Volume 1","author":"J MacQueen","year":"1967","unstructured":"MacQueen J: Some methods for classification and analysis of multivariate observations. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Volume 1. 1967, California: University of California Press, 14-14."},{"key":"5956_CR44","unstructured":"SRR032209 data. http:\/\/trace.ddbj.nig.ac.jp\/DRASearch\/run?acc=SRR032209 ,"},{"key":"5956_CR45","unstructured":"SRR089526 data. http:\/\/trace.ddbj.nig.ac.jp\/DRASearch\/run?acc=SRR089526 ,"},{"key":"5956_CR46","unstructured":"PhiX data. http:\/\/bix.ucsd.edu\/projects\/singlecell\/nbt\\_data.html ,"},{"key":"5956_CR47","unstructured":"QualComp website. https:\/\/sourceforge.net\/projects\/qualcomp\/ ,"},{"key":"5956_CR48","unstructured":"PhiX174 Genome. http:\/\/www.ncbi.nlm.nih.gov\/nuccore\/NC \\_001422"},{"issue":"16","key":"5956_CR49","doi-asserted-by":"publisher","first-page":"2078","DOI":"10.1093\/bioinformatics\/btp352","volume":"25","author":"H Li","year":"2009","unstructured":"Li H, Handsaker B, Wysoker A, Fennell T, Ruan J, Homer N, Marth G, Abecasis G, Durbin R: The sequence alignment\/map format and SAMtools. Bioinformatics. 2009, 25 (16): 2078-2079. 10.1093\/bioinformatics\/btp352.","journal-title":"Bioinformatics"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-14-187.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1471-2105-14-187\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-14-187.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,24]],"date-time":"2022-02-24T13:35:16Z","timestamp":1645709716000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/1471-2105-14-187"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,6,8]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,12]]}},"alternative-id":["5956"],"URL":"https:\/\/doi.org\/10.1186\/1471-2105-14-187","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,6,8]]},"article-number":"187"}}