{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T07:25:06Z","timestamp":1769844306791,"version":"3.49.0"},"reference-count":8,"publisher":"Oxford University Press (OUP)","issue":"11","license":[{"start":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T00:00:00Z","timestamp":1700092800000},"content-version":"vor","delay-in-days":15,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61972231"],"award-info":[{"award-number":["61972231"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62102231"],"award-info":[{"award-number":["62102231"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Engineering Research Center of Digital Media Technology, Ministry of Education, China"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>We propose RabbitKSSD, a high-speed genome distance estimation tool. Specifically, we leverage load-balanced task partitioning, fast I\/O, efficient intermediate result accesses, and high-performance data structures to improve overall efficiency. Our performance evaluation demonstrates that RabbitKSSD achieves speedups ranging from 5.7\u00d7 to 19.8\u00d7 over Kssd for the time-consuming sketch generation and distance computation on commonly used workstations. In addition, it significantly outperforms Mash, BinDash, and Dashing2. Moreover, RabbitKSSD can efficiently perform all-vs-all distance computation for all RefSeq complete bacterial genomes (455 GB in FASTA format) in just 2\u2009min on a 64-core workstation.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>RabbitKSSD is available at https:\/\/github.com\/RabbitBio\/RabbitKSSD.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad695","type":"journal-article","created":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T18:14:38Z","timestamp":1700158478000},"source":"Crossref","is-referenced-by-count":3,"title":["RabbitKSSD: accelerating genome distance estimation on modern multi-core architectures"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0370-2222","authenticated-orcid":false,"given":"Xiaoming","family":"Xu","sequence":"first","affiliation":[{"name":"School of Software, Shandong University , Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6002-0028","authenticated-orcid":false,"given":"Zekun","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University , Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9610-1268","authenticated-orcid":false,"given":"Lifeng","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University , Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiguang","family":"Yi","sequence":"additional","affiliation":[{"name":"Shenzhen Branch, Guangdong Laboratory for Lingnan Modern Agriculture, Genome Analysis Laboratory of the Ministry of Agriculture, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences , Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hua","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University , Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2597-8331","authenticated-orcid":false,"given":"Bertil","family":"Schmidt","sequence":"additional","affiliation":[{"name":"Institute for Computer Science, Johannes Gutenberg University , Mainz, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiguo","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University , Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2023,11,16]]},"reference":[{"key":"2023112802443698400_btad695-B1","first-page":"1218","article-title":"Genomic sketching with multiplicities and locality-sensitive hashing using dashing 2","volume":"33","author":"Baker","year":"2023","journal-title":"Genome Res"},{"key":"2023112802443698400_btad695-B2","doi-asserted-by":"crossref","first-page":"5217","DOI":"10.1093\/nar\/gkaa265","article-title":"To petabytes and beyond: recent advances in probabilistic and signal processing algorithms and their application to metagenomics","volume":"48","author":"Elworth","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2023112802443698400_btad695-B3","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":"2023112802443698400_btad695-B4","doi-asserted-by":"crossref","first-page":"232","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":"2023112802443698400_btad695-B5","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1186\/s13059-023-02961-6","article-title":"Rabbittclust: enabling fast clustering analysis of millions of bacteria genomes with minhash sketches","volume":"24","author":"Xu","year":"2023","journal-title":"Genome Biol"},{"key":"2023112802443698400_btad695-B6","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1186\/s13059-021-02303-4","article-title":"Kssd: sequence dimensionality reduction by k-mer substring space sampling enables real-time large-scale datasets analysis","volume":"22","author":"Yi","year":"2021","journal-title":"Genome Biol"},{"key":"2023112802443698400_btad695-B7","doi-asserted-by":"crossref","first-page":"2341","DOI":"10.1109\/TCBB.2022.3219114","article-title":"Rabbitfx: efficient framework for fasta\/q file parsing on modern multi-core platforms","volume":"20","author":"Zhang","year":"2023","journal-title":"IEEE ACM Trans Comput Biol Bioinform"},{"key":"2023112802443698400_btad695-B8","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":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad695\/53474281\/btad695.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/11\/btad695\/53863021\/btad695.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/11\/btad695\/53863021\/btad695.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,28]],"date-time":"2023-11-28T02:44:54Z","timestamp":1701139494000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad695\/7424710"}},"subtitle":[],"editor":[{"given":"Tobias","family":"Marschall","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2023,11,1]]},"references-count":8,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2023,11,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad695","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,11,1]]},"published":{"date-parts":[[2023,11,1]]},"article-number":"btad695"}}