{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T12:06:34Z","timestamp":1747137994876,"version":"3.37.3"},"reference-count":7,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2020,8,26]],"date-time":"2020-08-26T00:00:00Z","timestamp":1598400000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61972231","U1806205"],"award-info":[{"award-number":["61972231","U1806205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Project of Joint Fund of Shandong Province","award":["ZR2019LZH007"],"award-info":[{"award-number":["ZR2019LZH007"]}]},{"name":"Shenzhen Basic Research Fund","award":["JCYJ20180507182818013"],"award-info":[{"award-number":["JCYJ20180507182818013"]}]},{"name":"Pilot National Laboratory for Marine Science and Technology"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Mash is a popular hash-based genome analysis toolkit with applications to important downstream analyses tasks such as clustering and assembly. However, Mash is currently not able to fully exploit the capabilities of modern multi-core architectures, which in turn leads to high runtimes for large-scale genomic datasets.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We present RabbitMash, an efficient highly optimized implementation of Mash which can take full advantage of modern hardware including multi-threading, vectorization and fast I\/O. We show that our approach achieves speedups of at least 1.3, 9.8, 8.5 and 4.4 compared to Mash for the operations sketch, dist, triangle and screen, respectively. Furthermore, RabbitMash is able to compute the all-versus-all distances of 100\u00a0321 genomes in &amp;lt;5\u2009min on a 40-core workstation while Mash requires over 40\u2009min.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>RabbitMash is available at https:\/\/github.com\/ZekunYin\/RabbitMash.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaa754","type":"journal-article","created":{"date-parts":[[2020,8,19]],"date-time":"2020-08-19T11:45:25Z","timestamp":1597837525000},"page":"873-875","source":"Crossref","is-referenced-by-count":5,"title":["RabbitMash: accelerating hash-based genome analysis on modern multi-core architectures"],"prefix":"10.1093","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6002-0028","authenticated-orcid":false,"given":"Zekun","family":"Yin","sequence":"first","affiliation":[{"name":"School of Software, Shandong University , Jinan 250101, China"},{"name":"Shenzhen Research Institute of Shandong University , Shenzhen 518063, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoming","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University , Jinan 250101, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinxiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University , Jinan 250101, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanjie","family":"Wei","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences , Shenzhen 518055, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bertil","family":"Schmidt","sequence":"additional","affiliation":[{"name":"Institute for Computer Science, Johannes Gutenberg University , Mainz 55128, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiguo","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University , Jinan 250101, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2020,8,26]]},"reference":[{"key":"2023051704122217300_btaa754-B1","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1038\/nbt.3238","article-title":"Assembling large genomes with single-molecule sequencing and locality-sensitive hashing","volume":"33","author":"Berlin","year":"2015","journal-title":"Nat. Biotechnol"},{"key":"2023051704122217300_btaa754-B2","doi-asserted-by":"crossref","first-page":"i748","DOI":"10.1093\/bioinformatics\/bty597","article-title":"A fast adaptive algorithm for computing whole-genome homology maps","volume":"34","author":"Jain","year":"2018","journal-title":"Bioinformatics"},{"key":"2023051704122217300_btaa754-B3","doi-asserted-by":"crossref","first-page":"3740","DOI":"10.1093\/bioinformatics\/btx520","article-title":"MetaCache: context-aware classification of metagenomic reads using minhashing","volume":"33","author":"M\u00fcller","year":"2017","journal-title":"Bioinformatics"},{"key":"2023051704122217300_btaa754-B4","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1186\/s13059-016-0997-x","article-title":"Mash: fast genome and metagenome distance estimation using minhash","volume":"17","author":"Ondov","year":"2016","journal-title":"Genome Biol"},{"key":"2023051704122217300_btaa754-B5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-019-1841-x","article-title":"Mash screen: high-throughput sequence containment estimation for genome discovery","volume":"20","author":"Ondov","year":"2019","journal-title":"Genome Biol"},{"key":"2023051704122217300_btaa754-B6","article-title":"Complete genome sequence of a 2019 novel coronavirus (sars-cov-2) strain isolated in nepal","volume":"9 e00169-20","author":"Sah","year":"2020","journal-title":"Microbiol. Resource Announc"},{"key":"2023051704122217300_btaa754-B7","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1093\/bioinformatics\/bty651","article-title":"BinDash, software for fast genome distance estimation on a typical personal laptop","volume":"35","author":"Zhao","year":"2019","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa754\/34571394\/btaa754.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/6\/873\/50356322\/btaa754.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/6\/873\/50356322\/btaa754.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,17]],"date-time":"2023-05-17T04:13:00Z","timestamp":1684296780000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/6\/873\/5897409"}},"subtitle":[],"editor":[{"given":"Arne","family":"Elofsson","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2020,8,26]]},"references-count":7,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,5,5]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa754","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"type":"print","value":"1367-4803"},{"type":"electronic","value":"1367-4811"}],"subject":[],"published-other":{"date-parts":[[2021,3,15]]},"published":{"date-parts":[[2020,8,26]]}}}