{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T10:20:24Z","timestamp":1775038824890,"version":"3.50.1"},"reference-count":7,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2019,9,3]],"date-time":"2019-09-03T00:00:00Z","timestamp":1567468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"French","award":["ANR-14-CE23-0001"],"award-info":[{"award-number":["ANR-14-CE23-0001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,2,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>De novo comparative metagenomics is one of the most straightforward ways to analyze large sets of metagenomic data. Latest methods use the fraction of shared k-mers to estimate genomic similarity between read sets. However, those methods, while extremely efficient, are still limited by computational needs for practical usage outside of large computing facilities.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We present SimkaMin, a quick comparative metagenomics tool with low disk and memory footprints, thanks to an efficient data subsampling scheme used to estimate Bray-Curtis and Jaccard dissimilarities. One billion metagenomic reads can be analyzed in &amp;lt;3 min, with tiny memory (1.09 GB) and disk (\u22480.3 GB) requirements and without altering the quality of the downstream comparative analyses, making of SimkaMin a tool perfectly tailored for very large-scale metagenomic projects.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>https:\/\/github.com\/GATB\/simka.<\/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\/btz685","type":"journal-article","created":{"date-parts":[[2019,8,29]],"date-time":"2019-08-29T19:28:43Z","timestamp":1567106923000},"page":"1275-1276","source":"Crossref","is-referenced-by-count":16,"title":["SimkaMin: fast and resource frugal <i>de novo<\/i> comparative metagenomics"],"prefix":"10.1093","volume":"36","author":[{"given":"Ga\u00ebtan","family":"Benoit","sequence":"first","affiliation":[{"name":"Univ Rennes, Inria, CNRS , IRISA, F-35000 Rennes, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahendra","family":"Mariadassou","sequence":"additional","affiliation":[{"name":"MaIAGE, INRA, Universit\u00e9 Paris-Saclay , 78350 Jouy-en-Josas, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"St\u00e9phane","family":"Robin","sequence":"additional","affiliation":[{"name":"UMR MIA-Paris, AgroParisTech , INRA, Universit\u00e9 Paris-Saclay, 75005 Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sophie","family":"Schbath","sequence":"additional","affiliation":[{"name":"MaIAGE, INRA, Universit\u00e9 Paris-Saclay , 78350 Jouy-en-Josas, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0776-6407","authenticated-orcid":false,"given":"Pierre","family":"Peterlongo","sequence":"additional","affiliation":[{"name":"Univ Rennes, Inria, CNRS , IRISA, F-35000 Rennes, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8675-170X","authenticated-orcid":false,"given":"Claire","family":"Lemaitre","sequence":"additional","affiliation":[{"name":"Univ Rennes, Inria, CNRS , IRISA, F-35000 Rennes, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2019,9,3]]},"reference":[{"key":"2023013110153409300_btz685-B1","doi-asserted-by":"crossref","first-page":"e94.","DOI":"10.7717\/peerj-cs.94","article-title":"Multiple comparative metagenomics using multiset k-mer counting","volume":"2","author":"Benoit","year":"2016","journal-title":"PeerJ Comput. Sci"},{"key":"2023013110153409300_btz685-B2","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1126\/science.aac5605","article-title":"Tara oceans studies plankton at planetary scale","volume":"348","author":"Bork","year":"2015","journal-title":"Science"},{"key":"2023013110153409300_btz685-B3","first-page":"21","volume-title":"Proceedings of Compression and Complexity of Sequences 1997","author":"Broder","year":"1997"},{"key":"2023013110153409300_btz685-B4","doi-asserted-by":"crossref","first-page":"2959","DOI":"10.1093\/bioinformatics\/btu406","article-title":"GATB: genome assembly & analysis tool box","volume":"30","author":"Drezen","year":"2014","journal-title":"Bioinformatics"},{"key":"2023013110153409300_btz685-B5","doi-asserted-by":"crossref","first-page":"61.","DOI":"10.1038\/nature23889","article-title":"Strains, functions and dynamics in the expanded human microbiome project","volume":"550","author":"Lloyd-Price","year":"2017","journal-title":"Nature"},{"key":"2023013110153409300_btz685-B6","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":"2023013110153409300_btz685-B7","doi-asserted-by":"crossref","first-page":"1261447.","DOI":"10.1126\/science.1261447","article-title":"Environmental characteristics of Agulhas rings affect interocean plankton transport","volume":"348","author":"Villar","year":"2015","journal-title":"Science"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btz685\/30062704\/btz685.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/4\/1275\/48983907\/bioinformatics_36_4_1275.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/4\/1275\/48983907\/bioinformatics_36_4_1275.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T20:17:04Z","timestamp":1675196224000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/36\/4\/1275\/5559271"}},"subtitle":[],"editor":[{"given":"John","family":"Hancock","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2019,9,3]]},"references-count":7,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,2,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btz685","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,2,15]]},"published":{"date-parts":[[2019,9,3]]}}}