{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:47:12Z","timestamp":1780418832984,"version":"3.54.1"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,9,14]],"date-time":"2015-09-14T00:00:00Z","timestamp":1442188800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1186\/s12859-015-0709-7","type":"journal-article","created":{"date-parts":[[2015,9,14]],"date-time":"2015-09-14T17:00:57Z","timestamp":1442250057000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":92,"title":["Reference-free compression of high throughput sequencing data with a probabilistic de Bruijn graph"],"prefix":"10.1186","volume":"16","author":[{"given":"Ga\u00ebtan","family":"Benoit","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claire","family":"Lemaitre","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dominique","family":"Lavenier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erwan","family":"Drezen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thibault","family":"Dayris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raluca","family":"Uricaru","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillaume","family":"Rizk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2015,9,14]]},"reference":[{"key":"709_CR1","first-page":"1019","volume":"39","author":"R Leinonen","year":"2010","unstructured":"Leinonen R, Sugawara H, Shumway M. The sequence read archive. Nucleic Acids Res. 2010; 39:1019.","journal-title":"Nucleic Acids Res"},{"issue":"22","key":"709_CR2","doi-asserted-by":"publisher","first-page":"171","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):171. doi: 10.1093\/nar\/gks754 `.","journal-title":"Nucleic Acids Res"},{"key":"709_CR3","doi-asserted-by":"publisher","first-page":"734","DOI":"10.1101\/gr.114819.110","volume":"21","author":"MHY Fritz","year":"2011","unstructured":"Fritz MHY, Leinonen R, Cochrane G, Birney E. Efficient storage of high throughput sequencing data using reference-based compression. Genome Res. 2011; 21:734\u201340. doi: 10.1101\/gr.114819.110 .","journal-title":"Genome Res"},{"key":"709_CR4","doi-asserted-by":"publisher","first-page":"071","DOI":"10.1093\/bioinformatics\/btv071","volume":"31","author":"C Kingsford","year":"2015","unstructured":"Kingsford C, Patro R. Reference-based compression of short-read sequences using path encoding. Bioinformatics. 2015; 31:071.","journal-title":"Bioinformatics"},{"issue":"3","key":"709_CR5","doi-asserted-by":"publisher","first-page":"59190","DOI":"10.1371\/journal.pone.0059190","volume":"8","author":"JK Bonfield","year":"2013","unstructured":"Bonfield JK, Mahoney MV. Compression of fastq and sam format sequencing data. PLoS One. 2013; 8(3):59190. doi: 10.1371\/journal.pone.0059190 .","journal-title":"PLoS One"},{"issue":"23","key":"709_CR6","doi-asserted-by":"publisher","first-page":"3051","DOI":"10.1093\/bioinformatics\/bts593","volume":"28","author":"F Hach","year":"2012","unstructured":"Hach F, Numanagic I, Alkan C, Sahinalp SC. Scalce: boosting sequence compression algorithms using locally consistent encoding. Bioinformatics. 2012; 28(23):3051\u2013057. doi: 10.1093\/bioinformatics\/bts593 .","journal-title":"Bioinformatics"},{"issue":"6","key":"709_CR7","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 dna sequence reads in fastq format. Bioinformatics. 2011; 27(6):860\u20132.","journal-title":"Bioinformatics"},{"key":"709_CR8","first-page":"844","volume":"31","author":"S Grabowski","year":"2014","unstructured":"Grabowski S, Deorowicz S, Roguski \u0141. Disk-based compression of data from genome sequencing. Bioinformatics. 2014; 31:844.","journal-title":"Bioinformatics"},{"key":"709_CR9","first-page":"387","volume":"30","author":"L Janin","year":"2014","unstructured":"Janin L, Schulz-Trieglaff O, Cox AJ. Beetl-fastq: a searchable compressed archive for dna reads. Bioinformatics. 2014; 30:387.","journal-title":"Bioinformatics"},{"key":"709_CR10","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1093\/bioinformatics\/btv248","volume":"31","author":"R Patro","year":"2015","unstructured":"Patro R, Kingsford C. Data-dependent bucketing improves reference-free compression of sequencing reads. Bioinformatics. 2015; 31:248.","journal-title":"Bioinformatics"},{"issue":"11","key":"709_CR11","doi-asserted-by":"publisher","first-page":"1415","DOI":"10.1093\/bioinformatics\/bts173","volume":"28","author":"AJ Cox","year":"2012","unstructured":"Cox AJ, Bauer MJ, Jakobi T, Rosone G. Large-scale compression of genomic sequence databases with the burrows\u2013wheeler transform. Bioinformatics. 2012; 28(11):1415\u20139.","journal-title":"Bioinformatics"},{"issue":"5","key":"709_CR12","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1093\/bioinformatics\/btr689","volume":"28","author":"R Wan","year":"2012","unstructured":"Wan R, Anh VN, Asai K. Transformations for the compression of fastq quality scores of next-generation sequencing data. Bioinformatics. 2012; 28(5):628\u201335.","journal-title":"Bioinformatics"},{"issue":"15","key":"709_CR13","doi-asserted-by":"publisher","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. 2014; 30(15):2130\u2013136.","journal-title":"Bioinformatics"},{"key":"709_CR14","first-page":"257","volume":"30","author":"L Janin","year":"2013","unstructured":"Janin L, Rosone G, Cox AJ. Adaptive reference-free compression of sequence quality scores. Bioinformatics. 2013; 30:257.","journal-title":"Bioinformatics"},{"key":"709_CR15","doi-asserted-by":"crossref","unstructured":"Yu YW, Yorukoglu D, Berger B. Traversing the k-mer landscape of ngs read datasets for quality score sparsification. In: Research in computational molecular biology. Springer: 2014. p. 385\u201399.","DOI":"10.1007\/978-3-319-05269-4_31"},{"key":"709_CR16","doi-asserted-by":"crossref","unstructured":"Kirsch A, Mitzenmacher M. Less hashing, same performance: Building a better bloom filter. Algorithms-ESA 2006. 2006:456\u201367.","DOI":"10.1007\/11841036_42"},{"key":"709_CR17","first-page":"310","volume":"30","author":"R Chikhi","year":"2013","unstructured":"Chikhi R, Medvedev P. Informed and automated k-mer size selection for genome assembly. Bioinformatics. 2013; 30:310.","journal-title":"Bioinformatics"},{"issue":"2","key":"709_CR18","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1038\/ng.1028","volume":"44","author":"Z Iqbal","year":"2012","unstructured":"Iqbal Z, Caccamo M, Turner I, Flicek P, McVean G. De novo assembly and genotyping of variants using colored de bruijn graphs. Nat Genet. 2012; 44(2):226\u201332.","journal-title":"Nat Genet"},{"issue":"33","key":"709_CR19","doi-asserted-by":"publisher","first-page":"13272","DOI":"10.1073\/pnas.1121464109","volume":"109","author":"J Pell","year":"2012","unstructured":"Pell J, Hintze A, Canino-Koning R, Howe A, Tiedje JM, Brown CT. Scaling metagenome sequence assembly with probabilistic de bruijn graphs. Proc Natl Acad Sci. 2012; 109(33):13272\u20137.","journal-title":"Proc Natl Acad Sci"},{"issue":"1","key":"709_CR20","doi-asserted-by":"publisher","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. 2013; 8(1):22. doi: 10.1186\/1748-7188-8-22 .","journal-title":"Algorithms Mol Biol"},{"key":"709_CR21","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1007\/978-3-642-40453-5_28","volume":"9","author":"K Salikhov","year":"2013","unstructured":"Salikhov K, Sacomoto G, Kucherov G. Using cascading bloom filters to improve the memory usage for de brujin graphs. Algoritm Bioinforma. 2013; 9:364\u201376.","journal-title":"Algoritm Bioinforma"},{"key":"709_CR22","doi-asserted-by":"publisher","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. 1987; 30:520\u2013540.","journal-title":"Commun ACM"},{"key":"709_CR23","doi-asserted-by":"crossref","unstructured":"Drezen E, Rizk G, Chikhi R, Deltel C, Lemaitre C, Peterlongo P, et al. Gatb: Genome assembly and analysis tool box. Bioinformatics. 2014. doi: 10.1093\/bioinformatics\/btu406 .","DOI":"10.1093\/bioinformatics\/btu406"},{"issue":"5","key":"709_CR24","doi-asserted-by":"publisher","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. 2013; 29(5):652\u20133. doi: 10.1093\/bioinformatics\/btt020 .","journal-title":"Bioinformatics"},{"key":"709_CR25","doi-asserted-by":"publisher","first-page":"022","DOI":"10.1093\/bioinformatics\/btv022","volume":"31","author":"S Deorowicz","year":"2015","unstructured":"Deorowicz S, Kokot M, Grabowski S, Debudaj-Grabysz A. Kmc 2: Fast and resource-frugal k-mer counting. Bioinformatics. 2015; 31:022.","journal-title":"Bioinformatics"},{"issue":"16","key":"709_CR26","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, et al. The sequence alignment\/map format and samtools. Bioinformatics. 2009; 25(16):2078\u2013079.","journal-title":"Bioinformatics"},{"issue":"14","key":"709_CR27","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\u2013wheeler transform. Bioinformatics. 2009; 25(14):1754\u201360.","journal-title":"Bioinformatics"},{"issue":"3","key":"709_CR28","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1038\/nbt.3170","volume":"33","author":"YW Yu","year":"2015","unstructured":"Yu YW, Yorukoglu D, Peng J, Berger B. Quality score compression improves genotyping accuracy. Nat Biotechnol. 2015; 33(3):240\u20133.","journal-title":"Nat Biotechnol"},{"key":"709_CR29","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1007\/978-3-319-07953-0_10","volume":"8542","author":"C Lemaitre","year":"2014","unstructured":"Lemaitre C, Ciortuz L, Peterlongo P. Mapping-free and assembly-free discovery of inversion breakpoints from raw ngs reads. Algoritm Comput Biol. 2014; 8542:119\u201330. doi: 10.1007\/978-3-319-07953-0_10 .","journal-title":"Algoritm Comput Biol"},{"issue":"2","key":"709_CR30","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1093\/nar\/gku1187","volume":"43","author":"R Uricaru","year":"2015","unstructured":"Uricaru R, Rizk G, Lacroix V, Quillery E, Plantard O, Chikhi R, et al. Reference-free detection of isolated snps. Nucleic Acids Res. 2015; 43(2):11.","journal-title":"Nucleic Acids Res"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-015-0709-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12859-015-0709-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-015-0709-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,30]],"date-time":"2019-08-30T14:02:21Z","timestamp":1567173741000},"score":1,"resource":{"primary":{"URL":"http:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-015-0709-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,9,14]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["709"],"URL":"https:\/\/doi.org\/10.1186\/s12859-015-0709-7","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,9,14]]},"article-number":"288"}}