{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T09:57:44Z","timestamp":1775037464648,"version":"3.50.1"},"reference-count":99,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms Mol Biol"],"published-print":{"date-parts":[[2013,1]]},"DOI":"10.1186\/1748-7188-8-25","type":"journal-article","created":{"date-parts":[[2013,11,19]],"date-time":"2013-11-19T16:03:40Z","timestamp":1384877020000},"source":"Crossref","is-referenced-by-count":80,"title":["Data compression for sequencing data"],"prefix":"10.1186","volume":"8","author":[{"given":"Sebastian","family":"Deorowicz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Szymon","family":"Grabowski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,11,19]]},"reference":[{"key":"202_CR1","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/nrg2626","volume":"11","author":"ML Metzker","year":"2010","unstructured":"Metzker ML: Sequencing technologies\u2013the next generation. Nat Rev Genet. 2010, 11: 31-46.","journal-title":"Nat Rev Genet"},{"key":"202_CR2","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1126\/science.1197891","volume":"331","author":"SD Kahn","year":"2011","unstructured":"Kahn SD: On the future of genomic data. Science. 2011, 331: 728-729.","journal-title":"Science"},{"issue":"6","key":"202_CR3","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1038\/nbt0613-470","volume":"31","author":"JP Roberts","year":"2013","unstructured":"Roberts JP: Million veterans sequenced. Nat Biotechnol. 2013, 31 (6): 470-10.1038\/nbt0613-470.","journal-title":"Nat Biotechnol"},{"issue":"5","key":"202_CR4","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1186\/gb-2013-14-5-115","volume":"14","author":"N Hall","year":"2013","unstructured":"Hall N: After the gold rush. Genome Biol. 2013, 14 (5): 115.","journal-title":"Genome Biol"},{"key":"202_CR5","unstructured":"National Human Genome Research Institute, DNA Sequencing Costs. [ http:\/\/www.genome.gov\/sequencingcosts\/ ] (accessed February 14,2013), [] (accessed February 14,2013)"},{"issue":"2","key":"202_CR6","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1109\/TCBB.2011.146","volume":"9","author":"S Steinbiss","year":"2012","unstructured":"Steinbiss S, Kurtz S: A new efficient data structure for storage and retrieval of multiplebiosequences. IEEE\/ACM Trans Comput Biol Bioinformatics. 2012, 9 (2): 345-357.","journal-title":"IEEE\/ACM Trans Comput Biol Bioinformatics"},{"issue":"Database issue","key":"202_CR7","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1093\/nar\/gkr854","volume":"40","author":"Y Kodama","year":"2012","unstructured":"Kodama Y, Shumway M, Leinonen R: The sequence read archive: explosive growth of sequencing data. Nucleic Acids Res. 2012, 40 (Database issue): 54-56.","journal-title":"Nucleic Acids Res"},{"key":"202_CR8","volume-title":"The future of DNA sequence archiving","author":"G Cochrane","year":"2012","unstructured":"Cochrane G, Cook CE, Birney E: The future of DNA sequence archiving. GigaScience. 2012, 1 (1): article no. 2"},{"issue":"13","key":"202_CR9","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1093\/bioinformatics\/btp117","volume":"25","author":"R Giancarlo","year":"2009","unstructured":"Giancarlo R, Scaturro D, Utro F: Textual data compression in computational biology: A synopsis. Bioinformatics. 2009, 25 (13): 1575-1586.","journal-title":"Bioinformatics"},{"issue":"1","key":"202_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cosrev.2011.11.001","volume":"6","author":"R Giancarlo","year":"2012","unstructured":"Giancarlo R, Scaturro D, Utro F: Textual data compression in computational biology: Algorithmic techniques. Comput Sci Rev. 2012, 6 (1): 1-25. 10.1016\/j.cosrev.2011.11.001.","journal-title":"Comput Sci Rev"},{"issue":"15","key":"202_CR11","doi-asserted-by":"publisher","first-page":"6993","DOI":"10.1093\/nar\/gks408","volume":"40","author":"M Vyverman","year":"2012","unstructured":"Vyverman M, De Baets B, Fack V, Dawyndt P: Prospects and limitations of full-text index structures in genomeanalysis. Nucleic Acids Res. 2012, 40 (15): 6993-7015.","journal-title":"Nucleic Acids Res"},{"key":"202_CR12","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84882-903-9","volume-title":"Handbook of data compression","author":"D Salomon","year":"2010","unstructured":"Salomon D, Motta G: Handbook of data compression. 2010, London: Springer"},{"key":"202_CR13","first-page":"1098","volume-title":"Proceedings of the Institute of Radio Engineers","author":"D Huffman","year":"1952","unstructured":"Huffman D: A method for the construction of minimum-redundancy codes. Proceedings of the Institute of Radio Engineers. 1952, 1098-1101."},{"key":"202_CR14","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1109\/TIT.1977.1055714","volume":"IT-23","author":"J Ziv","year":"1977","unstructured":"Ziv J, Lempel A: A universal algorithm for sequential data compression. IEEE Trans Inf Theory. 1977, IT-23: 337-343.","journal-title":"IEEE Trans Inf Theory"},{"key":"202_CR15","unstructured":"Burrows M, Wheeler D: A block sorting lossless data compression algorithm. Technical Report 124, Digital Equipment Corporation 1994, http:\/\/www.hpl.hp.com\/techreports\/Compaq-DEC\/SRC-RR-124.pdf ., Technical Report 124, Digital Equipment Corporation 1994."},{"issue":"6","key":"202_CR16","doi-asserted-by":"publisher","first-page":"1767","DOI":"10.1093\/nar\/gkp1137","volume":"38","author":"PJA Cock","year":"2010","unstructured":"Cock PJA, Fields CJ, Goto N, Heuer ML, Rive PM: The Sanger FASTQ file format for sequences with quality scores, and theSolexa\/Illumina FASTQ variants. Nucleic Acids Res. 2010, 38 (6): 1767-1771.","journal-title":"Nucleic Acids Res"},{"issue":"6","key":"202_CR17","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1093\/bioinformatics\/btr014","volume":"27","author":"S Deorowicz","year":"2011","unstructured":"Deorowicz S, Grabowski Sz: Compression of DNA sequence reads in FASTQ format. Bioinformatics. 2011, 27 (6): 860-862.","journal-title":"Bioinformatics"},{"key":"202_CR18","first-page":"147","volume-title":"Proceedings of the IEEE International Conference on Bioinformatics andBiomedicine","author":"V Bhola","year":"2011","unstructured":"Bhola V, Bopardikar AS, Narayanan R, Lee K, Ahn T: No-reference compression of genomic data stored in FASTQ format. Proceedings of the IEEE International Conference on Bioinformatics andBiomedicine. Edited by: Wu F-X, Zaki M, Morishita S, Pan Y, Wong S, Christianson A, Hu X. 2011, 147-150. Atlanta, USA: IEEE Computer Society"},{"issue":"6","key":"202_CR19","doi-asserted-by":"publisher","first-page":"1837","DOI":"10.1109\/TCBB.2012.123","volume":"9","author":"E Grassi","year":"2012","unstructured":"Grassi E, Di Gregorio F, Molineris I: KungFQ: A Simple and Powerful Approach to Compress Fastq Files. IEEE\/ACM Trans Comput Biol Bioinformatics. 2012, 9 (6): 1837-1842.","journal-title":"IEEE\/ACM Trans Comput Biol Bioinformatics"},{"key":"202_CR20","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1186\/1748-7188-6-23","volume":"6","author":"V Yanovsky","year":"2011","unstructured":"Yanovsky V: ReCoil\u2014an algorithm for compression of extremely large datasets of DNAdata. Algo Mol Biol. 2011, 6: 23-10.1186\/1748-7188-6-23.","journal-title":"Algo Mol Biol"},{"issue":"11","key":"202_CR21","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 theBurrows-Wheeler transform. Bioinformatics. 2012, 28 (11): 1415-1419.","journal-title":"Bioinformatics"},{"issue":"23","key":"202_CR22","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, Sahinapl SC: SCALCE: boosting Sequence Compression Algorithms using Locally ConsistentEncoding. Bioinformatics. 2012, 28 (23): 3051-3057.","journal-title":"Bioinformatics"},{"issue":"6","key":"202_CR23","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1016\/j.ygeno.2010.03.001","volume":"95","author":"JR Miller","year":"2010","unstructured":"Miller JR, Koren S, Sutton G: Assembly algorithms for next-generation sequencing data. Genomics. 2010, 95 (6): 315-327.","journal-title":"Genomics"},{"issue":"5","key":"202_CR24","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 nextgeneration sequencing data. Bioinformatics. 2011, 28 (5): 628-635.","journal-title":"Bioinformatics"},{"issue":"3","key":"202_CR25","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. 2011, 18 (3): 401-413.","journal-title":"J Comput Biol"},{"key":"202_CR26","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1186\/1471-2105-14-187","volume":"14","author":"I Ochoa","year":"2013","unstructured":"Ochoa I, Asnani H, Bharadia D, Chowdhury M, Weissman T, Yona G: QualComp: a new lossy compressor for quality scores based on rate distortiontheory. BMC Bioinformatics. 2013, 14: 187.","journal-title":"BMC Bioinformatics"},{"key":"202_CR27","volume-title":"Casava v. 1.8.2 Documentation","author":"Illumina","year":"2013","unstructured":", : Casava v. 1.8.2 Documentation. 2013, [ http:\/\/support.illumina.com\/sequencing\/sequencing_software\/casava.ilmn ]."},{"issue":"1","key":"202_CR28","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1109\/TCBB.2012.160","volume":"10","author":"M Howison","year":"2013","unstructured":"Howison M: High-throughput compression of FASTQ data with SeqDB. IEEE\/ACM Trans Comput Biol Bioinformatics. 2013, 10 (1): 213-218.","journal-title":"IEEE\/ACM Trans Comput Biol Bioinformatics"},{"issue":"22","key":"202_CR29","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 denovo assembly. Nucleic Acids Res. 2012, 40 (22): e171.","journal-title":"Nucleic Acids Res"},{"issue":"3","key":"202_CR30","doi-asserted-by":"publisher","first-page":"e59190","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): e59190.","journal-title":"PLoS ONE"},{"issue":"17","key":"202_CR31","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 (17): 2192-2194.","journal-title":"Bioinformatics"},{"issue":"16","key":"202_CR32","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 , Abecasis G, Durbin R, : The sequence alignment\/map (SAM) format and SAMtools. Bioinformatics. 2009, 25 (16): 2078-2079.","journal-title":"Bioinformatics"},{"key":"202_CR33","doi-asserted-by":"publisher","first-page":"734","DOI":"10.1101\/gr.114819.110","volume":"21","author":"MH-Y Fritz","year":"2011","unstructured":"Fritz MH-Y, Leinonen R, Cochrane G, Birney E: Efficient storage of high throughput DNA sequencing data usingreference-based compression. Genome Res. 2011, 21: 734-740.","journal-title":"Genome Res"},{"issue":"12","key":"202_CR34","doi-asserted-by":"publisher","first-page":"e28251","DOI":"10.1371\/journal.pone.0028251","volume":"6","author":"MN Sakib","year":"2011","unstructured":"Sakib MN, Tang J, Zheng WJ, Huang C-T: Improving transmission efficiency of large sequence alignment\/map (SAM)files. PLoS ONE. 2011, 6 (12): e28251.","journal-title":"PLoS ONE"},{"issue":"14","key":"202_CR35","doi-asserted-by":"publisher","first-page":"1397","DOI":"10.1002\/spe.619","volume":"34","author":"G Manzini","year":"2004","unstructured":"Manzini G, Rastero M: A simple and fast DNA compressor. Softw Pract Exp. 2004, 34 (14): 1397-1411. 10.1002\/spe.619.","journal-title":"Softw Pract Exp"},{"issue":"6","key":"202_CR36","doi-asserted-by":"publisher","first-page":"e21588","DOI":"10.1371\/journal.pone.0021588","volume":"6","author":"AJ Pinho","year":"2011","unstructured":"Pinho AJ, Ferreira PJSG, Neves AJR, Bastos CAC: On the representability of complete genomes by multiple competingfinite-context (Markov) models. PLoS ONE. 2011, 6 (6): e21588-","journal-title":"PLoS ONE"},{"key":"202_CR37","first-page":"43","volume-title":"Proceedings of the Data Compression Conference","author":"MD Cao","year":"2007","unstructured":"Cao MD, Dix TI, Allison L, Mears C: A simple statistical algorithm for biological sequence compression. Proceedings of the Data Compression Conference. Washington, DC, USA: IEEE Computer Society Press,2007, 43-52."},{"key":"202_CR38","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1186\/1748-7188-7-30","volume":"7","author":"S Wandelt","year":"2012","unstructured":"Wandelt S, Leser U: Adaptive efficient compression of genomes. Algo Mol Biol. 2012, 7: 30-10.1186\/1748-7188-7-30.","journal-title":"Algo Mol Biol"},{"issue":"11","key":"202_CR39","doi-asserted-by":"publisher","first-page":"2979","DOI":"10.1093\/bioinformatics\/btr505","volume":"27","author":"S Deorowicz","year":"2011","unstructured":"Deorowicz S, Grabowski Sz: Robust relative compression of genomes with random access. Bioinformatics. 2011, 27 (11): 2979-2986.","journal-title":"Bioinformatics"},{"issue":"4","key":"202_CR40","doi-asserted-by":"publisher","first-page":"e27","DOI":"10.1093\/nar\/gkr1124","volume":"40","author":"AJ Pinho","year":"2012","unstructured":"Pinho AJ, Pratas D, Garcia SP: GReEn: a tool for efficient compression of genome resequencing data. Nucleic Acids Res. 2012, 40 (4): e27.","journal-title":"Nucleic Acids Res"},{"issue":"7","key":"202_CR41","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 resequencingdata. Nucleic Acids Res. 2011, 39 (7): e45.","journal-title":"Nucleic Acids Res"},{"key":"202_CR42","first-page":"91","volume-title":"Proceedings of the ACSC Australasian Computer Science Conference","author":"S Kuruppu","year":"2011","unstructured":"Kuruppu S, Puglisi SJ, Zobel J: Optimized relative Lempel-Ziv compression of genomes. Proceedings of the ACSC Australasian Computer Science Conference. Edited by: Reynolds M. 2011, 91-98. Sydney, Australia: Australian Computer Society, Inc."},{"key":"202_CR43","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511574931","volume-title":"Algorithms on strings, trees and sequences: Computer science andcomputational biology","author":"D Gusfield","year":"1997","unstructured":"Gusfield D: Algorithms on strings, trees and sequences: Computer science andcomputational biology. 1997, Cambridge, UK: Cambridge University Press"},{"key":"202_CR44","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1186\/1471-2105-11-514","volume":"11","author":"K Daily","year":"2010","unstructured":"Daily K, Rigor P, Christley S, Hie X, Baldi P: Data structures and compression algorithms for high-throughput sequencingtechnologies. BMC Bioinformatics. 2010, 11: 514-","journal-title":"BMC Bioinformatics"},{"issue":"1","key":"202_CR45","doi-asserted-by":"publisher","first-page":"e27","DOI":"10.1093\/nar\/gks939","volume":"41","author":"N Popitsch","year":"2013","unstructured":"Popitsch N, von Haeseler A: NGC: lossless and lossy compression of aligned high-throughput sequencingdata. Nucleic Acids Res. 2013, 41 (1): e27-","journal-title":"Nucleic Acids Res"},{"issue":"5","key":"202_CR46","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1093\/bioinformatics\/btq671","volume":"27","author":"H Li","year":"2011","unstructured":"Li H: Tabix: fast retrieval of sequence features from generic TAB-delimitedfiles. Bioinformatics. 2011, 27 (5): 718-719.","journal-title":"Bioinformatics"},{"issue":"10","key":"202_CR47","doi-asserted-by":"publisher","first-page":"e254","DOI":"10.1371\/journal.pbio.0050254","volume":"5","author":"S Levy","year":"2007","unstructured":"Levy S, Sutton G, Ng PC, Feuk L, Halpern AL, Walenz BP, Axelrod N, Huang J, Kirkness EF, Denisov G, Lin Y, MacDonald JR, Pang AWC, Shago M, Stockwell TB, Tsiamouri A, Bafna V, Bansal V, Kravitz SA, Busam DA, Beeson KY, McIntosh TC, Remington KA, Abril JF, Gill J, Borman J, Rogers YH, Frazier ME, Scherer SW, Strausberg RL, Venter JC: The diploid genome sequence of an individual human. PLoS Biol. 2007, 5 (10): e254-","journal-title":"PLoS Biol"},{"issue":"2","key":"202_CR48","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1093\/bioinformatics\/btn582","volume":"25","author":"S Christley","year":"2009","unstructured":"Christley S, Lu Y, Li C, Xie X: Human genomes as email attachments. Bioinformatics. 2009, 25 (2): 274-275.","journal-title":"Bioinformatics"},{"issue":"17","key":"202_CR49","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.1093\/bioinformatics\/btt362","volume":"29","author":"D Pavlichin","year":"2013","unstructured":"Pavlichin D, Weissman T, Yona G: The human genome contracts again. Bioinformatics. 2013, 29 (17): 2199-2202.","journal-title":"Bioinformatics"},{"issue":"20","key":"202_CR50","doi-asserted-by":"publisher","first-page":"2572","DOI":"10.1093\/bioinformatics\/btt460","volume":"29","author":"S Deorowicz","year":"2013","unstructured":"Deorowicz S, Danek A, Grabowski Sz: Genome compression: a novel approach for large collections. Bioinformatics. 2013, 29 (20): 2572-2578.","journal-title":"Bioinformatics"},{"key":"202_CR51","doi-asserted-by":"crossref","unstructured":"Chern BG, Ochoa I, Manolakos A, No A, Venkat K, Weissman T: Reference based genome compression. Publicly available preprint arXiv:1204.1912v1 2012","DOI":"10.1109\/ITW.2012.6404708"},{"key":"202_CR52","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1007\/978-3-642-16321-0_20","volume-title":"Proceedings of the 17th International Symposium on String Matching andInformation Retrieval (SPIRE)","author":"S Kuruppu","year":"2010","unstructured":"Kuruppu S, Puglisi SJ, Zobel J: Relative Lempel\u2013Ziv compression of genomes for large-scale storage andretrieval. Proceedings of the 17th International Symposium on String Matching andInformation Retrieval (SPIRE). Edited by: Ch\u00e1vez E, Lonardi S. 2010, 201-206. Springer-Verlag, Berlin-Heidelberg: Springer, LNCS 6393"},{"key":"202_CR53","first-page":"239","volume-title":"Proceedings of the Data Compression Conference","author":"S Kreft","year":"2010","unstructured":"Kreft S, Navarro G: LZ77-like compression with fast random access. Proceedings of the Data Compression Conference. 2010, 239-248. Washington, DC, USA: IEEE Computer Society"},{"key":"202_CR54","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1007\/978-3-642-16321-0_34","volume-title":"Proceedings of the 17th International Symposium on String Matching andInformation Retrieval (SPIRE)","author":"E Ohlebusch","year":"2010","unstructured":"Ohlebusch E, Fischer J, Gog S: CST++. Proceedings of the 17th International Symposium on String Matching andInformation Retrieval (SPIRE). Edited by: Ch\u00e1vez E, Lonardi S. 2010, 322-333. Springer-Verlag, Berlin-Heidelberg: Springer, LNCS 6393"},{"issue":"11","key":"202_CR55","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1038\/nbt.2023","volume":"29","author":"PE Compeau","year":"2011","unstructured":"Compeau PE, Pevzner PA, Tesler G: How to apply de Bruijn graphs to genome assembly. Nat Biotechnol. 2011, 29 (11): 987-991.","journal-title":"Nat Biotechnol"},{"issue":"4","key":"202_CR56","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1093\/bioinformatics\/btq697","volume":"27","author":"TC Conway","year":"2011","unstructured":"Conway TC, Bromage AJ: Succinct data structures for assembling large genomes. Bioinformatics. 2011, 27 (4): 479-486.","journal-title":"Bioinformatics"},{"issue":"7","key":"202_CR57","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1145\/362686.362692","volume":"13","author":"BH Bloom","year":"1970","unstructured":"Bloom BH: Space\/time trade-offs in hash coding with allowable errors. Commun ACM. 1970, 13 (7): 422-426. 10.1145\/362686.362692.","journal-title":"Commun ACM"},{"key":"202_CR58","first-page":"236","volume-title":"Proceedings of the 12th International Workshop on Algorithms inBioinformatics (WABI)","author":"R Chikhi","year":"2012","unstructured":"Chikhi R, Rizk G: Space-efficient and exact de Bruijn graph representation based on a Bloomfilter. Proceedings of the 12th International Workshop on Algorithms inBioinformatics (WABI). Edited by: Raphael BJ, Tang J. 2012, 236-248. Springer-Verlag, Berlin-Heidelberg: Springer, LNCS 7534"},{"key":"202_CR59","first-page":"364","volume-title":"Proceedings of the 13th International Workshop on Algorithms inBioinformatics (WABI)","author":"K Salikhov","year":"2013","unstructured":"Salikhov K, Sacomoto G, Kucherov G: Using cascading Bloom filters to improve the memory usage for de Brujingraphs. Proceedings of the 13th International Workshop on Algorithms inBioinformatics (WABI). Edited by: Darling A. E., Stoye J. 2013, 364-376. Springer-Verlag, Berlin-Heidelberg: Springer, LNCS 8126"},{"issue":"Suppl 6","key":"202_CR60","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1186\/1471-2105-13-S6-S1","volume":"13","author":"C Ye","year":"2012","unstructured":"Ye C, Ma ZS, Cannon CH, Pop M, Yu DW: Exploiting sparseness in de novo genome assembly. BMC Bioinformatics. 2012, 13 (Suppl 6): S1-10.1186\/1471-2105-13-S6-S1.","journal-title":"BMC Bioinformatics"},{"issue":"suppl 2","key":"202_CR61","doi-asserted-by":"publisher","first-page":"ii79","DOI":"10.1093\/bioinformatics\/bti1114","volume":"21","author":"EW Myers","year":"2005","unstructured":"Myers EW: The fragment assembly string graph. Bioinformatics. 2005, 21 (suppl 2): ii79-ii85.","journal-title":"Bioinformatics"},{"key":"202_CR62","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1101\/gr.126953.111","volume":"22","author":"JT Simpson","year":"2012","unstructured":"Simpson JT, Durbin R: Efficient de novo assembly of large genomes using compressed datastructures. Genome Res. 2012, 22: 549-556.","journal-title":"Genome Res"},{"key":"202_CR63","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1109\/SFCS.2000.892127","volume-title":"Proceedings of the 41st Annual Symposium on Foundations of Computer Science(FOCS)","author":"P Ferragina","year":"2000","unstructured":"Ferragina P, Manzini G: Opportunistic data structures with applications. Proceedings of the 41st Annual Symposium on Foundations of Computer Science(FOCS). 2000, 390-398. Redondo Beach, California, USA: IEEE Computer Society"},{"key":"202_CR64","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1186\/1471-2105-13-82","volume":"13","author":"G Gonnella","year":"2012","unstructured":"Gonnella G, Kurtz S: Readjoiner: a fast and memory efficient string graph-based sequenceassembler. BMC Bioinformatics. 2012, 13: 82.","journal-title":"BMC Bioinformatics"},{"key":"202_CR65","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1145\/1216370.1216372","volume":"39","author":"G Navarro","year":"2007","unstructured":"Navarro G, M\u00e4kinen V: Compressed full-text indexes. ACM Computing Surv. 2007, 39: 2-10.1145\/1216370.1216372.","journal-title":"ACM Computing Surv"},{"key":"202_CR66","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.tcs.2012.02.006","volume":"483","author":"S Kreft","year":"2013","unstructured":"Kreft S, Navarro G: On compressing and indexing repetitive sequences. Theor Comput Sci. 2013, 483: 115-133.","journal-title":"Theor Comput Sci"},{"key":"202_CR67","first-page":"240","volume-title":"Proceedings of the 6th International Conference on Language and AutomataTheory and Applications (LATA)","author":"T Gagie","year":"2012","unstructured":"Gagie T, Gawrychowski P, K\u00e4rkk\u00e4inen J, Nekrich Y, Puglisi SJ: A faster grammar-based self-index. Proceedings of the 6th International Conference on Language and AutomataTheory and Applications (LATA). 2012, 240-251. Springer-Verlag, Berlin-Heidelberg: LNCS 7183"},{"key":"202_CR68","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1007\/978-3-642-29700-7_27","volume-title":"Proceedings of the Joint International Conference on Frontiers inAlgorithmics and Algorithmic Aspects in Information and Management(FAW-AAIM)","author":"HH Do","year":"2012","unstructured":"Do HH, Jansson J, Sadakane K, Sung W-K: Fast relative Lempel-Ziv self-index for similar sequences. Proceedings of the Joint International Conference on Frontiers inAlgorithmics and Algorithmic Aspects in Information and Management(FAW-AAIM). 2012, 291-302. Springer-Verlag, Berlin-Heidelberg: LNCS 7285"},{"key":"202_CR69","first-page":"653","volume-title":"Proceedings of the 22nd International Symposium on Algorithms andComputation (ISAAC)","author":"T Gagie","year":"2011","unstructured":"Gagie T, Gawrychowski P, Puglisi SJ: Faster approximate pattern matching in compressed repetitive texts. Proceedings of the 22nd International Symposium on Algorithms andComputation (ISAAC). 2011, 653-662. Springer-Verlag, Berlin-Heidelberg: LNCS 7074"},{"issue":"6","key":"202_CR70","doi-asserted-by":"publisher","first-page":"e41","DOI":"10.1093\/nar\/gkr1246","volume":"40","author":"A Ahmadi","year":"2012","unstructured":"Ahmadi A, Behm A, Honnalli N, Li C, Weng L, Xie X: Hobbes: optimized gram-based methods for efficient read alignment. Nucleic Acids Res. 2012, 40 (6): e41.","journal-title":"Nucleic Acids Res"},{"issue":"3","key":"202_CR71","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 SL: Ultrafast and memory-efficient alignment of short DNA sequences to the humangenome. Genome Biol. 2009, 10 (3): R25.","journal-title":"Genome Biol"},{"key":"202_CR72","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/nmeth.1923","volume":"9","author":"B Langmead","year":"2012","unstructured":"Langmead B, Salzberg SL: Fast gapped-read alignment with Bowtie. Nature Methods. 2012, 9: 357-359.","journal-title":"Nature Methods"},{"issue":"14","key":"202_CR73","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\u2013Wheelertransform. Bioinformatics. 2009, 25 (14): 1754-1760.","journal-title":"Bioinformatics"},{"issue":"5","key":"202_CR74","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1093\/bioinformatics\/btp698","volume":"26","author":"H Li","year":"2010","unstructured":"Li H, Durbin R: Fast and accurate long-read alignment with Burrows\u2013Wheelertransform. Bioinformatics. 2010, 26 (5): 589-595.","journal-title":"Bioinformatics"},{"issue":"15","key":"202_CR75","doi-asserted-by":"publisher","first-page":"1966","DOI":"10.1093\/bioinformatics\/btp336","volume":"25","author":"R Li","year":"2009","unstructured":"Li R, Yu C, Li Y, Lam T-W, Yiu S-M, Kristiansen K, Wang J: SOAP2: an improved ultrafast tool for short read alignment. Bioinformatics. 2009, 25 (15): 1966-1967.","journal-title":"Bioinformatics"},{"issue":"12","key":"202_CR76","doi-asserted-by":"publisher","first-page":"1185","DOI":"10.1038\/nmeth.2221","volume":"9","author":"S Marco-Sola","year":"2012","unstructured":"Marco-Sola S, Sammeth M, Guig\u00f3 R, Ribeca P: The GEM mapper: fast, accurate and versatile alignment by filtration. Nat Methods. 2012, 9 (12): 1185-1188.","journal-title":"Nat Methods"},{"key":"202_CR77","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.tcs.2007.07.018","volume":"387","author":"J K\u00e4rkk\u00e4inen","year":"2007","unstructured":"K\u00e4rkk\u00e4inen J: Fast BWT in small space by blockwise suffix sorting. Theor Comput Sci. 2007, 387: 249-257. 10.1016\/j.tcs.2007.07.018.","journal-title":"Theor Comput Sci"},{"issue":"3","key":"202_CR78","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1007\/s00453-011-9535-0","volume":"63","author":"P Ferragina","year":"2012","unstructured":"Ferragina P, Gagie T, Manzini G: Lightweight data indexing and compression in external memory. Algorithmica. 2012, 63 (3): 707-730. 10.1007\/s00453-011-9535-0.","journal-title":"Algorithmica"},{"issue":"1","key":"202_CR79","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1038\/nrg2484","volume":"10","author":"Z Wang","year":"2009","unstructured":"Wang Z, Gerstein M, Snyder M: RNA-Seq: a revolutionary tool for transcriptomics. Nat Rev Genet. 2009, 10 (1): 57-63.","journal-title":"Nat Rev Genet"},{"issue":"9","key":"202_CR80","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1093\/bioinformatics\/btp120","volume":"25","author":"C Trapnell","year":"2009","unstructured":"Trapnell C, Pachter L, Salzberg SL: TopHat: discovering splice junctions with RNA-Seq. Bioinformatics. 2009, 25 (9): 1105-1111.","journal-title":"Bioinformatics"},{"issue":"3","key":"202_CR81","doi-asserted-by":"publisher","first-page":"R30","DOI":"10.1186\/gb-2013-14-3-r30","volume":"14","author":"E Rivals","year":"2013","unstructured":"Rivals E: CRAC: an integrated approach to the analysis of RNA-seq reads. Genome Biol. 2013, 14 (3): R30.","journal-title":"Genome Biol"},{"key":"202_CR82","unstructured":"Alamancos GP, Agirre E, Eyras E: Methods to study splicing from high-throughput RNA Sequencing data. Publicly available preprint arXiv:1304.5952v1"},{"issue":"14","key":"202_CR83","doi-asserted-by":"publisher","first-page":"1838","DOI":"10.1093\/bioinformatics\/bts280","volume":"28","author":"H Li","year":"2012","unstructured":"Li H: Exploring single-sample SNP and INDEL calling with whole-genome de novoassembly. Bioinformatics. 2012, 28 (14): 1838-1844.","journal-title":"Bioinformatics"},{"issue":"6","key":"202_CR84","doi-asserted-by":"publisher","first-page":"878","DOI":"10.1093\/bioinformatics\/bts061","volume":"28","author":"C-M Liu","year":"2012","unstructured":"Liu C-M, Wong TKF, Wu E, Luo R, Yiu S-M, Li Y, Wang B, Yu C, Chu X, Zhao K, Li R, Lam TW: SOAP3: ultra-fast GPU-based parallel alignment tool for short reads. Bioinformatics. 2012, 28 (6): 878-879.","journal-title":"Bioinformatics"},{"issue":"5","key":"202_CR85","doi-asserted-by":"publisher","first-page":"e65632","DOI":"10.1371\/journal.pone.0065632","volume":"8","author":"R Luo","year":"2013","unstructured":"Luo R, Wong T, Zhu J, Liu C-M, Zhu X, Wu E, Lee L-K, Lin H, Zhu W, Cheung DW, Ting H-F, Yiu S-M, Peng S, Yu C, Li Y, Li R, Lam TW: SOAP3-dp: Fast, accurate and sensitive GPU-based short read aligner. PLoS ONE. 2013, 8 (5): e65632-","journal-title":"PLoS ONE"},{"key":"202_CR86","volume-title":"Softw Pract Exp","author":"S Gog","year":"2013","unstructured":"Gog S, Petri M: Optimized succinct data structures for massive data. Softw Pract Exp. 2013, doi: 10.1002\/spe.2198"},{"issue":"7","key":"202_CR87","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1038\/nbt.2241","volume":"30","author":"P-R Loh","year":"2012","unstructured":"Loh P-R, Baym M, Berger B: Compressive genomics. Nat Biotechnol. 2012, 30 (7): 627-630.","journal-title":"Nat Biotechnol"},{"issue":"3","key":"202_CR88","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","volume":"215","author":"SF Altschul","year":"1990","unstructured":"Altschul SF, Gish W, Miller W, Myers EW, Lipman DJ: Basic local alignment search tool. J Mol Biol. 1990, 215 (3): 403-410.","journal-title":"J Mol Biol"},{"issue":"4","key":"202_CR89","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1101\/gr.229202. Article published online before March 2002","volume":"12","author":"WJ Kent","year":"2002","unstructured":"Kent WJ: BLAT\u2013the BLAST-like alignment tool. Genome Res. 2002, 12 (4): 656-664.","journal-title":"Genome Res"},{"key":"202_CR90","doi-asserted-by":"publisher","first-page":"Article no. 160","DOI":"10.1186\/1471-2105-14-160","volume":"14","author":"S Deorowicz","year":"2013","unstructured":"Deorowicz S, Debudaj-Grabysz A, Grabowski Sz: Disk-based k-mer counting on a PC. BMC Bioinformatics. 2013, 14: Article no. 160-10.1186\/1471-2105-14-160.","journal-title":"BMC Bioinformatics"},{"issue":"5","key":"202_CR91","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1101\/gr.074492.107","volume":"18","author":"DR Zerbino","year":"2008","unstructured":"Zerbino DR, Birney E: Velvet: algorithms for de novo short read assembly using de Bruijn graphs. Genome Res. 2008, 18 (5): 821-829.","journal-title":"Genome Res"},{"issue":"6","key":"202_CR92","doi-asserted-by":"publisher","first-page":"1117","DOI":"10.1101\/gr.089532.108","volume":"19","author":"JT Simpson","year":"2009","unstructured":"Simpson JT, Wong K, Jackman SD, Schein JE, Jones SJM, Birol I: ABySS: A parallel assembler for short read sequence data. Genome Res. 2009, 19 (6): 1117-1123.","journal-title":"Genome Res"},{"issue":"1","key":"202_CR93","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1186\/1471-2105-11-599","volume":"11","author":"MD Cao","year":"2010","unstructured":"Cao MD, Dix TI, Allison L: A genome alignment algorithm based on compression. BMC Bioinformatics. 2010, 11 (1): 599.","journal-title":"BMC Bioinformatics"},{"issue":"8","key":"202_CR94","doi-asserted-by":"publisher","first-page":"1174","DOI":"10.1093\/bioinformatics\/bts100","volume":"28","author":"A Bhaduri","year":"2012","unstructured":"Bhaduri A, Qu K, Lee CS, Ungewickell A, Khavari P: Rapid identification of nonhuman sequences in high throughput sequencing datasets. Bioinformatics. 2012, 28 (8): 1174-1175.","journal-title":"Bioinformatics"},{"key":"202_CR95","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1186\/1471-2105-8-252","volume":"8","author":"P Ferragina","year":"2007","unstructured":"Ferragina P, Giancarlo R, Greco V, Manzini G, Valiente G: Compression-based classification of biological sequences and structures viathe universal similarity metric: experimental assessment. BMC Bioinformatics. 2007, 8: 252-","journal-title":"BMC Bioinformatics"},{"issue":"12","key":"202_CR96","doi-asserted-by":"publisher","first-page":"3250","DOI":"10.1109\/TIT.2004.838101","volume":"50","author":"M Li","year":"2004","unstructured":"Li M, Chen X, Li X, Ma B, Vit\u00e1nyi PMB: The similarity metric. IEEE Trans Inf Theory. 2004, 50 (12): 3250-3264. 10.1109\/TIT.2004.838101.","journal-title":"IEEE Trans Inf Theory"},{"key":"202_CR97","doi-asserted-by":"publisher","first-page":"171","DOI":"10.4137\/EBO.S9131","volume":"8","author":"V Freschi","year":"2012","unstructured":"Freschi V, Bogliolo A: A lossy compression technique enabling duplication-aware sequencealignment. Evol Bioinformatics. 2012, 8: 171-180.","journal-title":"Evol Bioinformatics"},{"key":"202_CR98","volume-title":"HiSeq 2500 system user guide","author":"Illumina","year":"2012","unstructured":"Illumina: HiSeq 2500 system user guide. 2012. [ http:\/\/supportres.illumina.com\/documents\/myillumina\/223bf628-0b46-409f-aa3d-4f3495fe4f69\/hiseq2500_ug_15035786_a_public.pdf ]"},{"key":"202_CR99","volume-title":"New algorithms increase computing efficiency for IGN whole-genomeanalysis","author":"Illumina","year":"2013","unstructured":"Illumina: New algorithms increase computing efficiency for IGN whole-genomeanalysis. 2013. [ http:\/\/res.illumina.com\/documents\/products\/technotes\/technote_ign_isaac_software.pdf ]"}],"container-title":["Algorithms for Molecular Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1748-7188-8-25.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1748-7188-8-25\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1748-7188-8-25.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,19]],"date-time":"2024-05-19T19:28:07Z","timestamp":1716146887000},"score":1,"resource":{"primary":{"URL":"https:\/\/almob.biomedcentral.com\/articles\/10.1186\/1748-7188-8-25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,1]]},"references-count":99,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,1]]}},"alternative-id":["202"],"URL":"https:\/\/doi.org\/10.1186\/1748-7188-8-25","relation":{},"ISSN":["1748-7188"],"issn-type":[{"value":"1748-7188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,1]]},"article-number":"25"}}