{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T19:37:47Z","timestamp":1725910667345},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319598246"},{"type":"electronic","value":"9783319598260"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-59826-0_4","type":"book-chapter","created":{"date-parts":[[2017,9,18]],"date-time":"2017-09-18T11:16:01Z","timestamp":1505733361000},"page":"91-115","source":"Crossref","is-referenced-by-count":0,"title":["De Novo NGS Data Compression"],"prefix":"10.1007","author":[{"given":"Gaetan","family":"Benoit","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claire","family":"Lemaitre","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guillaume","family":"Rizk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erwan","family":"Drezen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dominique","family":"Lavenier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,9,19]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1186\/s12859-015-0709-7","volume":"16","author":"G. Benoit","year":"2015","unstructured":"Benoit, G., Lemaitre, C., Lavenier, D., Drezen, E., Dayris, T., Uricaru, R., Rizk, G.: Reference-free compression of high throughput sequencing data with a probabilistic de Bruijn graph de Bruijn graph. BMC Bioinf. 16, 288 (2015)","journal-title":"BMC Bioinf."},{"issue":"3","key":"4_CR2","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0059190","volume":"8","author":"J.K. Bonfield","year":"2013","unstructured":"Bonfield, J.K., Mahoney, M.V.: Compression of fastq and sam format sequencing data. PLoS One 8(3), e59190 (2013)","journal-title":"PLoS One"},{"key":"4_CR3","unstructured":"Burrows, M., Wheeler, D.: A block sorting lossless data compression algorithm. Technical Report 124, Digital Equipment Corporation (1994)"},{"issue":"15","key":"4_CR4","doi-asserted-by":"crossref","first-page":"2130","DOI":"10.1093\/bioinformatics\/btu183","volume":"30","author":"R. C\u00e1novas","year":"2014","unstructured":"C\u00e1novas, R., Moffat, A., Turpin, A.: Lossy compression of quality scores in genomic data. Bioinformatics 30(15), 2130\u20132136 (2014)","journal-title":"Bioinformatics"},{"issue":"1","key":"4_CR5","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1186\/1748-7188-8-22","volume":"8","author":"R. Chikhi","year":"2013","unstructured":"Chikhi, R., Rizk, G.: Space-efficient and exact de bruijn graph representation based on a bloom filter. Algorithms Mol. Biol. 8(1), 22 (2013)","journal-title":"Algorithms Mol. Biol."},{"issue":"11","key":"4_CR6","doi-asserted-by":"crossref","first-page":"1415","DOI":"10.1093\/bioinformatics\/bts173","volume":"28","author":"A.J. Cox","year":"2012","unstructured":"Cox, A.J., Bauer, M.J., Jakobi, T., Rosone, G.: Large-scale compression of genomic sequence databases with the burrows-wheeler transform. Bioinformatics 28(11), 1415\u20131419 (2012)","journal-title":"Bioinformatics"},{"issue":"6","key":"4_CR7","doi-asserted-by":"crossref","first-page":"860","DOI":"10.1093\/bioinformatics\/btr014","volume":"27","author":"S. Deorowicz","year":"2011","unstructured":"Deorowicz, S., Grabowski, S.: Compression of DNA sequence reads in fastq format. Bioinformatics 27(6), 860\u2013862 (2011)","journal-title":"Bioinformatics"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Deutsch, P., Gailly, J.: Zlib compressed data format specification version 3.3. RFC 1950 (1996)","DOI":"10.17487\/rfc1950"},{"issue":"9","key":"4_CR9","doi-asserted-by":"crossref","first-page":"1389","DOI":"10.1093\/bioinformatics\/btu844","volume":"31","author":"S. Grabowski","year":"2014","unstructured":"Grabowski, S., Deorowicz, S., Roguski, \u0141.: Disk-based compression of data from genome sequencing. Bioinformatics 31(9), 1389\u20131395 (2014)","journal-title":"Bioinformatics"},{"issue":"23","key":"4_CR10","doi-asserted-by":"crossref","first-page":"3051","DOI":"10.1093\/bioinformatics\/bts593","volume":"28","author":"F. Hach","year":"2012","unstructured":"Hach, F., Numanagic, I., Alkan, C., Sahinalp, S.C.: Scalce: boosting sequence compression algorithms using locally consistent encoding. Bioinformatics 28(23), 3051\u20133057 (2012)","journal-title":"Bioinformatics"},{"key":"4_CR11","volume-title":"A method for the construction of minimum-redundancy codes","author":"D. Huffman","year":"1952","unstructured":"Huffman, D.: A method for the construction of minimum-redundancy codes. In: Proceedings of the Institute of Radio Engineers (1952)"},{"issue":"1","key":"4_CR12","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1093\/bioinformatics\/btt257","volume":"30","author":"L. Janin","year":"2014","unstructured":"Janin, L., Rosone, G., Cox, A.J.: Adaptive reference-free compression of sequence quality scores. Bioinformatics 30(1), 24\u201330 (2014)","journal-title":"Bioinformatics"},{"issue":"22","key":"4_CR13","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gks754","volume":"40","author":"D.C. Jones","year":"2012","unstructured":"Jones, D.C., Ruzzo, W.L., Peng, X., Katze, M.G.: Compression of next-generation sequencing reads aided by highly efficient de novo assembly. Nucleic Acids Res. 40(22), e171 (2012)","journal-title":"Nucleic Acids Res."},{"issue":"14","key":"4_CR14","doi-asserted-by":"crossref","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\u2013wheeler transform. Bioinformatics 25(14), 1754\u20131760 (2009)","journal-title":"Bioinformatics"},{"issue":"16","key":"4_CR15","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., Subgroup, G.P.D.P.: The sequence alignment\/map format and samtools. Bioinformatics 25(16), 2078\u20132079 (2009). doi:\u00a0 10.1093\/bioinformatics\/btp352","journal-title":"Bioinformatics"},{"key":"4_CR16","unstructured":"Mahoney, M.: (2000) http:\/\/mattmahoney.net\/dc\/"},{"key":"4_CR17","volume-title":"Adaptive weighing of context models for lossless data compression","author":"M. Mahoney","year":"2005","unstructured":"Mahoney, M.: Adaptive weighing of context models for lossless data compression. Florida Tech. Technical Report (2005)"},{"key":"4_CR18","doi-asserted-by":"crossref","first-page":"1917","DOI":"10.1109\/26.61469","volume":"38","author":"A. Moffat","year":"1990","unstructured":"Moffat, A.: Implementing the PPM data compression scheme. IEEE Trans. Commun. 38, 1917\u20131921 (1990)","journal-title":"IEEE Trans. Commun."},{"issue":"5","key":"4_CR19","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1093\/bioinformatics\/btt020","volume":"29","author":"G. Rizk","year":"2013","unstructured":"Rizk, G., Lavenier, D., Chikhi, R.: DSK: k-mer counting with very low memory usage. Bioinformatics 29(5), 652\u2013653 (2013)","journal-title":"Bioinformatics"},{"issue":"15","key":"4_CR20","doi-asserted-by":"crossref","first-page":"2213","DOI":"10.1093\/bioinformatics\/btu208","volume":"30","author":"L. Roguski","year":"2014","unstructured":"Roguski, L., Deorowicz, S.: DSRC 2-industry-oriented compression of FASTQ files. Bioinformatics 30(15), 2213\u20132215 (2014)","journal-title":"Bioinformatics"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Saha, S., Rajasekaran, S.: Efficient algorithms for the compression of fastq files. In: 2014 IEEE International Conference on Bioinformatics and Biomedicine (2014)","DOI":"10.1109\/BIBM.2014.6999132"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Sahinalp, S.C., Vishkin, U.: Efficient approximate and dynamic matching of patterns using a labeling paradigm. In: Proceedings of the 37th Annual Symposium on Foundations of Computer Science, FOCS \u201996, Washington, DC, pp. 320\u2013328. IEEE Computer Society, Los Alamitos (1996). http:\/\/dl.acm.org\/citation.cfm?id=874062.875524","DOI":"10.1109\/SFCS.1996.548491"},{"key":"4_CR23","unstructured":"Seward, J.: (1996) bzip2: http:\/\/www.bzip.org\/1.0.3\/html\/reading.html"},{"key":"4_CR24","volume-title":"The Mathematical Theory of Communication","author":"C. Shannon","year":"1949","unstructured":"Shannon, C., Weaver, W.: The Mathematical Theory of Communication. University of Illinois Press, Urbana (1949)"},{"issue":"17","key":"4_CR25","doi-asserted-by":"crossref","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 26(17), 2192\u20132194 (2010)","journal-title":"Bioinformatics"},{"issue":"5","key":"4_CR26","doi-asserted-by":"crossref","first-page":"628","DOI":"10.1093\/bioinformatics\/btr689","volume":"28","author":"R. Wan","year":"2012","unstructured":"Wan, R., Anh, V.N., Asai, K.: Transformations for the compression of fastq quality scores of next-generation sequencing data. Bioinformatics 28(5), 628\u2013635 (2012)","journal-title":"Bioinformatics"},{"key":"4_CR27","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/MC.1984.1659158","volume":"6","author":"T. Welch","year":"1984","unstructured":"Welch, T.: A technique for high-performance data compression. Computer 6, 8\u201319 (1984)","journal-title":"Computer"},{"key":"4_CR28","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1145\/214762.214771","volume":"30","author":"I. Witten","year":"1987","unstructured":"Witten, I., Neal, R., Cleary, J.: Arithmetic coding for data compression. Commun. ACM 30, 520\u2013540 (1987)","journal-title":"Commun. ACM"},{"key":"4_CR29","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1186\/1748-7188-6-23","volume":"6","author":"V. Yanovsky","year":"2011","unstructured":"Yanovsky, V.: Recoil - an algorithm for compression of extremely large datasets of dna data. Algorithms Mol. Biol. 6, 23 (2011)","journal-title":"Algorithms Mol. Biol."},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Yu, Y.W., Yorukoglu, D., Berger, B.: Traversing the k-mer landscape of ngs read datasets for quality score sparsification. In: Research in Computational Molecular Biology, pp. 385\u2013399. Springer, Berlin (2014)","DOI":"10.1007\/978-3-319-05269-4_31"},{"issue":"3","key":"4_CR31","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1109\/TIT.1977.1055714","volume":"23","author":"J. Ziv","year":"1977","unstructured":"Ziv, J., Lempel, A.: A universal algorithm for sequential data compression. IEEE Trans. Inf. Theory 23(3), 337\u2013343 (1977)","journal-title":"IEEE Trans. Inf. Theory"}],"container-title":["Algorithms for Next-Generation Sequencing Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-59826-0_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,3]],"date-time":"2019-10-03T16:00:35Z","timestamp":1570118435000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-59826-0_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319598246","9783319598260"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-59826-0_4","relation":{},"subject":[],"published":{"date-parts":[[2017]]}}}