{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T21:27:35Z","timestamp":1774128455551,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1005777","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2017,10,17]],"date-time":"2017-10-17T00:00:00Z","timestamp":1508198400000}}],"reference-count":21,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2017,10,2]],"date-time":"2017-10-02T00:00:00Z","timestamp":1506902400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003977","name":"Israel Science Foundation","doi-asserted-by":"publisher","award":["ISF-NSFC joint program 2015-2018"],"award-info":[{"award-number":["ISF-NSFC joint program 2015-2018"]}],"id":[{"id":"10.13039\/501100003977","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Edmond J. Safra Center for Bioinformatics at Tel Aviv University","award":["Ph.D. fellowship"],"award-info":[{"award-number":["Ph.D. fellowship"]}]},{"name":"Gordon and Betty Moore Foundation (US)","award":["Data-Driven Discovery Initiative through Grant GBMF4554"],"award-info":[{"award-number":["Data-Driven Discovery Initiative through Grant GBMF4554"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1256087"],"award-info":[{"award-number":["CCF-1256087"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1319998"],"award-info":[{"award-number":["CCF-1319998"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01HG007104"],"award-info":[{"award-number":["R01HG007104"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000879","name":"Alfred P. Sloan Foundation","doi-asserted-by":"publisher","award":["Fellow"],"award-info":[{"award-number":["Fellow"]}],"id":[{"id":"10.13039\/100000879","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"DOI":"10.1371\/journal.pcbi.1005777","type":"journal-article","created":{"date-parts":[[2017,10,2]],"date-time":"2017-10-02T13:38:03Z","timestamp":1506951483000},"page":"e1005777","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":52,"title":["Designing small universal k-mer hitting sets for improved analysis of high-throughput sequencing"],"prefix":"10.1371","volume":"13","author":[{"given":"Yaron","family":"Orenstein","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Pellow","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5083-5925","authenticated-orcid":true,"given":"Guillaume","family":"Mar\u00e7ais","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1889-9870","authenticated-orcid":true,"given":"Ron","family":"Shamir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carl","family":"Kingsford","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2017,10,2]]},"reference":[{"issue":"18","key":"ref1","doi-asserted-by":"crossref","first-page":"3363","DOI":"10.1093\/bioinformatics\/bth408","article-title":"Reducing storage requirements for biological sequence comparison","volume":"20","author":"M Roberts","year":"2004","journal-title":"Bioinformatics"},{"key":"ref2","unstructured":"Schleimer S, Wilkerson DS, Aiken A. Winnowing: Local Algorithms for Document Fingerprinting. In: Proceedings of the 2003 ACM SIGMOD International Conference on Management of Data. SIGMOD\u201903. New York, NY, USA: ACM; 2003. p. 76\u201385. Available from: <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/doi.acm.org\/10.1145\/872757.872770\" xlink:type=\"simple\">http:\/\/doi.acm.org\/10.1145\/872757.872770<\/ext-link>."},{"key":"ref3","doi-asserted-by":"crossref","unstructured":"Karkkainen J, Ukkonen E. Sparse Suffix Trees. In: Computing and Combinatorics: 2nd Annual International Conference, COCOON\u201996. vol. 2. Springer; 1996. p. 219\u2013230.","DOI":"10.1007\/3-540-61332-3_155"},{"key":"ref4","doi-asserted-by":"crossref","unstructured":"Grabowski S, Raniszewski M. Sampling the Suffix Array with Minimizers. In: Proceedings of the 22nd International Symposium on String Processing and Information Retrieval. vol. 9309. Springer-Verlag New York, Inc.; 2015. p. 287\u2013298.","DOI":"10.1007\/978-3-319-23826-5_28"},{"issue":"3","key":"ref5","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1038\/nbt.3442","article-title":"Fast search of thousands of short-read sequencing experiments","volume":"34","author":"B Solomon","year":"2016","journal-title":"Nature Biotech"},{"key":"ref6","article-title":"Improved Search of Large Transcriptomic Sequencing Databases Using Split Sequence Bloom Trees","author":"B Solomon","year":"2016","journal-title":"bioRxiv"},{"key":"ref7","doi-asserted-by":"crossref","unstructured":"Movahedi NS, Forouzmand E, Chitsaz H. De novo co-assembly of bacterial genomes from multiple single cells. In: 2012 IEEE International Conference on Bioinformatics and Biomedicine (BIBM); 2012. p. 1\u20135.","DOI":"10.1109\/BIBM.2012.6392618"},{"issue":"10","key":"ref8","doi-asserted-by":"crossref","first-page":"1569","DOI":"10.1093\/bioinformatics\/btv022","article-title":"KMC 2: fast and resource-frugal k-mer counting","volume":"31","author":"S Deorowicz","year":"2015","journal-title":"Bioinformatics"},{"issue":"5","key":"ref9","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1089\/cmb.2014.0160","article-title":"On the representation of de Bruijn graphs","volume":"22","author":"R Chikhi","year":"2015","journal-title":"Journal of Computational Biology"},{"key":"ref10","doi-asserted-by":"crossref","unstructured":"Li Y, Kamousi P, Han F, Yang S, Yan X, Suri S. Memory efficient minimum substring partitioning. In: Proceedings of the VLDB Endowment. vol. 6. VLDB Endowment; 2013. p. 169\u2013180.","DOI":"10.14778\/2535569.2448951"},{"issue":"6","key":"ref11","doi-asserted-by":"crossref","first-page":"S1","DOI":"10.1186\/1471-2105-13-S6-S1","article-title":"Exploiting sparseness in de novo genome assembly","volume":"13","author":"C Ye","year":"2012","journal-title":"BMC Bioinformatics"},{"issue":"3","key":"ref12","doi-asserted-by":"crossref","first-page":"R46","DOI":"10.1186\/gb-2014-15-3-r46","article-title":"Kraken: ultrafast metagenomic sequence classification using exact alignments","volume":"15","author":"DE Wood","year":"2014","journal-title":"Genome Biology"},{"key":"ref13","doi-asserted-by":"crossref","unstructured":"Sahinalp SC, Vishkin U. Efficient approximate and dynamic matching of patterns using a labeling paradigm. In: 37th Annual Symposium on Foundations of Computer Science, Proceedings; 1996. p. 320\u2013328.","DOI":"10.1109\/SFCS.1996.548491"},{"issue":"23","key":"ref14","doi-asserted-by":"crossref","first-page":"3051","DOI":"10.1093\/bioinformatics\/bts593","article-title":"SCALCE: boosting sequence compression algorithms using locally consistent encoding","volume":"28","author":"F Hach","year":"2012","journal-title":"Bioinformatics"},{"key":"ref15","doi-asserted-by":"crossref","unstructured":"Orenstein Y, Pellow D, Mar\u00e7ais G, Shamir R, Kingsford C. Compact universal k-mer hitting sets. In: International Workshop on Algorithms in Bioinformatics. vol. 9838. Springer; 2016. p. 257\u2013268.","DOI":"10.1007\/978-3-319-43681-4_21"},{"issue":"02","key":"ref16","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1142\/S0218196704001700","article-title":"Unavoidable sets of constant length","volume":"14","author":"JM Champarnaud","year":"2004","journal-title":"International Journal of Algebra and Computation"},{"issue":"1","key":"ref17","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/0095-8956(72)90006-8","article-title":"A proof of Golomb\u2019s conjecture for the de Bruijn graph","volume":"13","author":"J Mykkeltveit","year":"1972","journal-title":"Journal of Combinatorial Theory, Series B"},{"issue":"3","key":"ref18","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1287\/moor.4.3.233","article-title":"A greedy heuristic for the set-covering problem","volume":"4","author":"V Chvatal","year":"1979","journal-title":"Mathematics of Operations Research"},{"issue":"5","key":"ref19","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1016\/j.gpb.2015.08.002","article-title":"PacBio sequencing and its applications","volume":"13","author":"A Rhoads","year":"2015","journal-title":"Genomics, proteomics & bioinformatics"},{"issue":"10","key":"ref20","doi-asserted-by":"crossref","first-page":"1146","DOI":"10.1038\/nbt.1495","article-title":"The potential and challenges of nanopore sequencing","volume":"26","author":"D Branton","year":"2008","journal-title":"Nature biotechnology"},{"key":"ref21","unstructured":"Gurobi Optimization, Inc. Gurobi Optimizer Reference Manual; 2016. Available from: <ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/www.gurobi.com\" xlink:type=\"simple\">http:\/\/www.gurobi.com<\/ext-link>."}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1005777","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2017,10,17]],"date-time":"2017-10-17T00:00:00Z","timestamp":1508198400000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pcbi.1005777","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,10,23]],"date-time":"2018-10-23T17:14:11Z","timestamp":1540314851000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1005777"}},"subtitle":[],"editor":[{"given":"Benjamin J.","family":"Raphael","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2017,10,2]]},"references-count":21,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2017,10,2]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1005777","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pcbi.1005777","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,10,2]]}}}