{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T07:02:14Z","timestamp":1772521334566,"version":"3.50.1"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030452568","type":"print"},{"value":"9783030452575","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-45257-5_10","type":"book-chapter","created":{"date-parts":[[2020,4,20]],"date-time":"2020-04-20T16:05:35Z","timestamp":1587398735000},"page":"152-168","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Representation of $$k$$-mer Sets Using Spectrum-Preserving String Sets"],"prefix":"10.1007","author":[{"given":"Amatur","family":"Rahman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul","family":"Medvedev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,4,21]]},"reference":[{"key":"10_CR1","unstructured":"Chikhi, R., Holub, J., Medvedev, P.: Data structures to represent sets of k-long DNA sequences. arXiv:1903.12312 [cs, q-bio], March 2019"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Harris, R.S., Medvedev, P.: Improved representation of sequence bloom trees. bioRxiv (2018)","DOI":"10.1101\/501452"},{"issue":"4","key":"10_CR3","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1093\/bioinformatics\/btq697","volume":"27","author":"TC Conway","year":"2011","unstructured":"Conway, T.C., Bromage, A.J.: Succinct data structures for assembling large genomes. Bioinformatics 27(4), 479\u2013486 (2011)","journal-title":"Bioinformatics"},{"key":"10_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-319-05269-4_4","volume-title":"Research in Computational Molecular Biology","author":"R Chikhi","year":"2014","unstructured":"Chikhi, R., Limasset, A., Jackman, S., Simpson, J.T., Medvedev, P.: On the representation of de Bruijn graphs. In: Sharan, R. (ed.) RECOMB 2014. LNCS, vol. 8394, pp. 35\u201355. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-05269-4_4"},{"issue":"12","key":"10_CR5","doi-asserted-by":"publisher","first-page":"i201","DOI":"10.1093\/bioinformatics\/btw279","volume":"32","author":"R Chikhi","year":"2016","unstructured":"Chikhi, R., Limasset, A., Medvedev, P.: Compacting de Bruijn graphs from sequencing data quickly and in low memory. Bioinformatics 32(12), i201\u2013i208 (2016)","journal-title":"Bioinformatics"},{"key":"10_CR6","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1109\/TCBB.2018.2858797","volume":"17","author":"T Pan","year":"2018","unstructured":"Pan, T., Nihalani, R., Aluru, S.: Fast de Bruijn graph compaction in distributed memory environments. IEEE\/ACM Trans. Comput. Biol. Bioinf. 17, 136\u2013148 (2018)","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinf."},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Guo, H., Fu, Y., Gao, Y., Li, J., Wang, Y., Liu, B.: deGSM: memory scalable construction of large scale de Bruijn graph. IEEE\/ACM Trans. Comput. Biol. Bioinf. (2019)","DOI":"10.1101\/388454"},{"issue":"13","key":"10_CR8","doi-asserted-by":"publisher","first-page":"i169","DOI":"10.1093\/bioinformatics\/bty292","volume":"34","author":"F Almodaresi","year":"2018","unstructured":"Almodaresi, F., Sarkar, H., Srivastava, A., Patro, R.: A space and time-efficient index for the compacted colored de Bruijn graph. Bioinformatics 34(13), i169\u2013i177 (2018)","journal-title":"Bioinformatics"},{"key":"10_CR9","unstructured":"Marchet, C., Kerbiriou, M., Limasset, A.: Indexing de Bruijn graphs with minimizers. bioRxiv (2019)"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Holley, G., Melsted, P.: Bifrost-highly parallel construction and indexing of colored and compacted de Bruijn graphs, p. 695338. bioRxiv (2019)","DOI":"10.1101\/695338"},{"issue":"4","key":"10_CR11","doi-asserted-by":"publisher","first-page":"1376","DOI":"10.1093\/bib\/bby003","volume":"20","author":"P Medvedev","year":"2018","unstructured":"Medvedev, P.: Modeling biological problems in computer science: a case study in genome assembly. Brief. Bioinform. 20(4), 1376\u20131383 (2018)","journal-title":"Brief. Bioinform."},{"key":"10_CR12","doi-asserted-by":"publisher","unstructured":"B\u0159inda, K.: Novel computational techniques for mapping and classifying next-generation sequencing data. Ph.D. dissertation, Universit\u00e9 Paris-Est, November 2016. https:\/\/doi.org\/10.5281\/zenodo.1045317","DOI":"10.5281\/zenodo.1045317"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"B\u0159inda, K., Baym, M., Kucherov, G.: Simplitigs as an efficient and scalable representation of de Bruijn graphs. bioRxiv (2020)","DOI":"10.1101\/2020.01.12.903443"},{"issue":"22","key":"10_CR14","doi-asserted-by":"publisher","first-page":"e171","DOI":"10.1093\/nar\/gks754","volume":"40","author":"DC 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\u2013e171 (2012)","journal-title":"Nucleic Acids Res."},{"issue":"8","key":"10_CR15","doi-asserted-by":"publisher","first-page":"1494","DOI":"10.1038\/nprot.2013.084","volume":"8","author":"BJ Haas","year":"2013","unstructured":"Haas, B.J., et al.: De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis. Nat. Protoc. 8(8), 1494 (2013)","journal-title":"Nat. Protoc."},{"issue":"5","key":"10_CR16","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1038\/s41587-019-0072-8","volume":"37","author":"M Kolmogorov","year":"2019","unstructured":"Kolmogorov, M., Yuan, J., Lin, Y., Pevzner, P.A.: Assembly of long, error-prone reads using repeat graphs. Nat. Biotechnol. 37(5), 540 (2019)","journal-title":"Nat. Biotechnol."},{"issue":"17","key":"10_CR17","doi-asserted-by":"publisher","first-page":"2759","DOI":"10.1093\/bioinformatics\/btx304","volume":"33","author":"M Kokot","year":"2017","unstructured":"Kokot, M., D\u0142ugosz, M., Deorowicz, S.: KMC 3: counting and manipulating k-mer statistics. Bioinformatics 33(17), 2759\u20132761 (2017)","journal-title":"Bioinformatics"},{"issue":"5","key":"10_CR18","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 29(5), 652\u2013653 (2013)","journal-title":"Bioinformatics"},{"issue":"6","key":"10_CR19","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1093\/bioinformatics\/btr011","volume":"27","author":"G Mar\u00e7ais","year":"2011","unstructured":"Mar\u00e7ais, G., Kingsford, C.: A fast, lock-free approach for efficient parallel counting of occurrences of k-mers. Bioinformatics 27(6), 764\u2013770 (2011)","journal-title":"Bioinformatics"},{"issue":"4","key":"10_CR20","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1093\/bioinformatics\/btx636","volume":"34","author":"P Pandey","year":"2017","unstructured":"Pandey, P., Bender, M.A., Johnson, R., Patro, R.: Squeakr: an exact and approximate k-mer counting system. Bioinformatics 34(4), 568\u2013575 (2017)","journal-title":"Bioinformatics"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Pandey, P., Bender, M.A., Johnson, R., Patro, R.: A general-purpose counting filter: making every bit count. In: Proceedings of the 2017 ACM International Conference on Management of Data, pp. 775\u2013787. ACM (2017)","DOI":"10.1145\/3035918.3035963"},{"issue":"4","key":"10_CR22","doi-asserted-by":"publisher","first-page":"56","DOI":"10.3390\/info7040056","volume":"7","author":"M Hosseini","year":"2016","unstructured":"Hosseini, M., Pratas, D., Pinho, A.: A survey on data compression methods for biological sequences. Information 7(4), 56 (2016)","journal-title":"Information"},{"key":"10_CR23","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1146\/annurev-biodatasci-072018-021229","volume":"2","author":"M Hernaez","year":"2019","unstructured":"Hernaez, M., Pavlichin, D., Weissman, T., Ochoa, I.: Genomic data compression. Ann. Rev. Biomed. Data Sci. 2, 19\u201337 (2019)","journal-title":"Ann. Rev. Biomed. Data Sci."},{"issue":"12","key":"10_CR24","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1038\/nmeth.4037","volume":"13","author":"I Numanagi\u0107","year":"2016","unstructured":"Numanagi\u0107, I., et al.: Comparison of high-throughput sequencing data compression tools. Nat. Methods 13(12), 1005 (2016)","journal-title":"Nat. Methods"},{"issue":"1","key":"10_CR25","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1093\/bib\/bbs015","volume":"14","author":"X Yang","year":"2012","unstructured":"Yang, X., Chockalingam, S.P., Aluru, S.: A survey of error-correction methods for next-generation sequencing. Brief. Bioinform. 14(1), 56\u201366 (2012)","journal-title":"Brief. Bioinform."},{"issue":"10","key":"10_CR26","doi-asserted-by":"publisher","first-page":"e1005777","DOI":"10.1371\/journal.pcbi.1005777","volume":"13","author":"Y Orenstein","year":"2017","unstructured":"Orenstein, Y., Pellow, D., Mar\u00e7ais, G., Shamir, R., Kingsford, C.: Designing small universal k-mer hitting sets for improved analysis of high-throughput sequencing. PLoS Comput. Biol. 13(10), e1005777 (2017)","journal-title":"PLoS Comput. Biol."},{"issue":"1","key":"10_CR27","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1186\/s12864-019-5996-3","volume":"20","author":"S Rangavittal","year":"2019","unstructured":"Rangavittal, S., Stopa, N., Tomaszkiewicz, M., Sahlin, K., Makova, K.D., Medvedev, P.: DiscoverY: a classifier for identifying Y chromosome sequences in male assemblies. BMC Genomics 20(1), 641 (2019)","journal-title":"BMC Genomics"},{"key":"10_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/978-3-030-17083-7_14","volume-title":"Research in Computational Molecular Biology","author":"K Sahlin","year":"2019","unstructured":"Sahlin, K., Medvedev, P.: De Novo clustering of long-read transcriptome data using a greedy, quality-value based algorithm. In: Cowen, L.J. (ed.) RECOMB 2019. LNCS, vol. 11467, pp. 227\u2013242. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-17083-7_14"},{"key":"10_CR29","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1146\/annurev-biodatasci-072018-021156","volume":"2","author":"G Mar\u00e7ais","year":"2019","unstructured":"Mar\u00e7ais, G., Solomon, B., Patro, R., Kingsford, C.: Sketching and sublinear data structures in genomics. Ann. Rev. Biomed. Data Sci. 2, 93\u2013118 (2019)","journal-title":"Ann. Rev. Biomed. Data Sci."},{"issue":"1","key":"10_CR30","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1186\/s13059-019-1809-x","volume":"20","author":"WP Rowe","year":"2019","unstructured":"Rowe, W.P.: When the levee breaks: a practical guide to sketching algorithms for processing the flood of genomic data. Genome Biol. 20(1), 199 (2019)","journal-title":"Genome Biol."},{"key":"10_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1007\/978-3-642-33122-0_18","volume-title":"Algorithms in Bioinformatics","author":"A Bowe","year":"2012","unstructured":"Bowe, A., Onodera, T., Sadakane, K., Shibuya, T.: Succinct de Bruijn graphs. In: Raphael, B., Tang, J. (eds.) WABI 2012. LNCS, vol. 7534, pp. 225\u2013235. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33122-0_18"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Boucher, C., Bowe, A., Gagie, T., Puglisi, S.J., Sadakane, K.: Variable-order de Bruijn graphs. In: Data Compression Conference, pp. 383\u2013392. IEEE (2015)","DOI":"10.1109\/DCC.2015.70"},{"key":"10_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1007\/978-3-662-49529-2_13","volume-title":"LATIN 2016: Theoretical Informatics","author":"D Belazzougui","year":"2016","unstructured":"Belazzougui, D., Gagie, T., M\u00e4kinen, V., Previtali, M., Puglisi, S.J.: Bidirectional variable-order de Bruijn graphs. In: Kranakis, E., Navarro, G., Ch\u00e1vez, E. (eds.) LATIN 2016. LNCS, vol. 9644, pp. 164\u2013178. Springer, Heidelberg (2016). https:\/\/doi.org\/10.1007\/978-3-662-49529-2_13"},{"key":"10_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/978-3-319-46049-9_14","volume-title":"String Processing and Information Retrieval","author":"D Belazzougui","year":"2016","unstructured":"Belazzougui, D., Gagie, T., M\u00e4kinen, V., Previtali, M.: Fully dynamic de Bruijn graphs. In: Inenaga, S., Sadakane, K., Sakai, T. (eds.) SPIRE 2016. LNCS, vol. 9954, pp. 145\u2013152. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46049-9_14"},{"issue":"24","key":"10_CR35","doi-asserted-by":"publisher","first-page":"4189","DOI":"10.1093\/bioinformatics\/bty500","volume":"34","author":"VG Crawford","year":"2018","unstructured":"Crawford, V.G., Kuhnle, A., Boucher, C., Chikhi, R., Gagie, T.: Practical dynamic de Bruijn graphs. Bioinformatics 34(24), 4189\u20134195 (2018)","journal-title":"Bioinformatics"},{"issue":"1","key":"10_CR36","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/s13015-016-0066-8","volume":"11","author":"G Holley","year":"2016","unstructured":"Holley, G., Wittler, R., Stoye, J.: Bloom Filter Trie: an alignment-free and reference-free data structure for pan-genome storage. Algorithms Mol. Biol. 11(1), 3 (2016). https:\/\/doi.org\/10.1186\/s13015-016-0066-8","journal-title":"Algorithms Mol. Biol."},{"issue":"14","key":"10_CR37","doi-asserted-by":"publisher","first-page":"i133","DOI":"10.1093\/bioinformatics\/btx261","volume":"33","author":"P Pandey","year":"2017","unstructured":"Pandey, P., Bender, M.A., Johnson, R., Patro, R.: deBGR: an efficient and near-exact representation of the weighted de Bruijn graph. Bioinformatics 33(14), i133\u2013i141 (2017)","journal-title":"Bioinformatics"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Diestel, R.: Graph Theory, vol. 101 (2005)","DOI":"10.1007\/978-3-642-14279-6_7"},{"issue":"1","key":"10_CR39","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1093\/bioinformatics\/btt594","volume":"30","author":"AJ Pinho","year":"2013","unstructured":"Pinho, A.J., Pratas, D.: MFCompress: a compression tool for FASTA and multi-FASTA data. Bioinformatics 30(1), 117\u2013118 (2013)","journal-title":"Bioinformatics"},{"key":"10_CR40","unstructured":"Ferragina, P., Manzini, G.: Opportunistic data structures with applications. In: Proceedings 41st Annual Symposium on Foundations of Computer Science, pp. 390\u2013398. IEEE (2000)"},{"key":"10_CR41","unstructured":"https:\/\/github.com\/jts\/dbgfm"},{"key":"10_CR42","unstructured":"https:\/\/github.com\/cosmo-team\/cosmo\/tree\/VARI"},{"issue":"2","key":"10_CR43","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1038\/s41587-018-0010-1","volume":"37","author":"P Bradley","year":"2019","unstructured":"Bradley, P., den Bakker, H.C., Rocha, E.P., McVean, G., Iqbal, Z.: Ultrafast search of all deposited bacterial and viral genomic data. Nat. Biotechnol. 37(2), 152 (2019)","journal-title":"Nat. Biotechnol."},{"key":"10_CR44","doi-asserted-by":"crossref","unstructured":"Bingmann, T., Bradley, P., Gauger, F., Iqbal, Z.: COBS: a compact bit-sliced signature index. arXiv preprint arXiv:1905.09624 (2019)","DOI":"10.1007\/978-3-030-32686-9_21"},{"key":"10_CR45","unstructured":"http:\/\/ftp.ebi.ac.uk\/pub\/software\/bigsi\/nat_biotech_2018\/ctx\/"}],"container-title":["Lecture Notes in Computer Science","Research in Computational Molecular Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-45257-5_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,4]],"date-time":"2024-08-04T09:16:43Z","timestamp":1722763003000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-45257-5_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030452568","9783030452575"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-45257-5_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"21 April 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"RECOMB","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Research in Computational Molecular Biology","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Padua","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 May 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 May 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"recomb2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.recomb2020.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"13","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"54% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"9","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}