{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T21:27:38Z","timestamp":1771709258370,"version":"3.50.1"},"reference-count":19,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2021,7,9]],"date-time":"2021-07-09T00:00:00Z","timestamp":1625788800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000936","name":"Gordon and Betty Moore Foundation","doi-asserted-by":"publisher","award":["GBMF5275"],"award-info":[{"award-number":["GBMF5275"]}],"id":[{"id":"10.13039\/100000936","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Klaus Tschira Foundation, and the Deutsche Forschungsgemeinschaft","award":["#DU1319\/5-1"],"award-info":[{"award-number":["#DU1319\/5-1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Previously we presented swarm, an open-source amplicon clustering programme that produces fine-scale molecular operational taxonomic units (OTUs) that are free of arbitrary global clustering thresholds. Here, we present swarm v3 to address issues of contemporary datasets that are growing towards tera-byte sizes.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>When compared with previous swarm versions, swarm v3 has modernized C++ source code, reduced memory footprint by up to 50%, optimized CPU-usage and multithreading (more than 7 times faster with default parameters), and it has been extensively tested for its robustness and logic.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Source code and binaries are available at https:\/\/github.com\/torognes\/swarm.<\/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\/btab493","type":"journal-article","created":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T12:30:15Z","timestamp":1625142615000},"page":"267-269","source":"Crossref","is-referenced-by-count":106,"title":["Swarm v3: towards tera-scale amplicon clustering"],"prefix":"10.1093","volume":"38","author":[{"given":"Fr\u00e9d\u00e9ric","family":"Mah\u00e9","sequence":"first","affiliation":[{"name":"UMR PHIM, CIRAD , Montpellier, France"},{"name":"PHIM Plant Health Institute, Univ Montpellier, CIRAD, INRAE, Institut Agro, IRD , Montpellier, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1340-9644","authenticated-orcid":false,"given":"Lucas","family":"Czech","sequence":"additional","affiliation":[{"name":"Computational Molecular Evolution Group, Heidelberg Institute for Theoretical Studies , Heidelberg, Germany"},{"name":"Department of Plant Biology, Carnegie Institution for Science , Stanford, CA, USA"}]},{"given":"Alexandros","family":"Stamatakis","sequence":"additional","affiliation":[{"name":"Computational Molecular Evolution Group, Heidelberg Institute for Theoretical Studies , Heidelberg, Germany"},{"name":"Institute of Theoretical Informatics, Karlsruhe Institute of Technology , Karlsruhe, Germany"}]},{"given":"Christopher","family":"Quince","sequence":"additional","affiliation":[{"name":"Organisms and Ecosystems, Earlham Institute , Norwich, UK"},{"name":"Gut Microbes and Health, Quadram Institute , Norwich, UK"},{"name":"Warwick Medical School, University of Warwick , Coventry, UK"}]},{"given":"Colomban","family":"de Vargas","sequence":"additional","affiliation":[{"name":"Sorbonne Universit\u00e9, CNRS, Station Biologique de Roscoff , UMR7144, ECOMAP, Roscoff, France"},{"name":"Research Federation for the study of Global Ocean Systems Ecology and Evolution , FR2022\/Tara GOSEE, Paris, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1376-4109","authenticated-orcid":false,"given":"Micah","family":"Dunthorn","sequence":"additional","affiliation":[{"name":"Natural History Museum, University of Oslo , Oslo, Norway"},{"name":"Eukaryotic Microbiology, University of Duisburg-Essen , Essen, Germany"}]},{"given":"Torbj\u00f8rn","family":"Rognes","sequence":"additional","affiliation":[{"name":"Department of Informatics, University of Oslo , Oslo, Norway"},{"name":"Department of Microbiology, Oslo University Hospital , Rikshospitalet, Oslo, Norway"}]}],"member":"286","published-online":{"date-parts":[[2021,7,9]]},"reference":[{"key":"2023020108383433100_btab493-B1","doi-asserted-by":"crossref","first-page":"e00191-16","DOI":"10.1128\/mSystems.00191-16","article-title":"Deblur rapidly resolves single-nucleotide community sequence patterns","volume":"2","author":"Amir","year":"2017","journal-title":"mSystems"},{"key":"2023020108383433100_btab493-B2","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1111\/jeu.12414","article-title":"UniEuk: time to speak a common language in protistology!","volume":"64","author":"Berney","year":"2017","journal-title":"J. Euk. Microbiol"},{"key":"2023020108383433100_btab493-B3","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1038\/nmeth.3869","article-title":"DADA2: high-resolution sample inference from Illumina amplicon data","volume":"13","author":"Callahan","year":"2016","journal-title":"Nat. Meth"},{"key":"2023020108383433100_btab493-B4","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.1093\/molbev\/msy014","article-title":"The state of software for evolutionary biology","volume":"35","author":"Darriba","year":"2018","journal-title":"Mol. Biol. Evol"},{"key":"2023020108383433100_btab493-B5","doi-asserted-by":"crossref","first-page":"2460","DOI":"10.1093\/bioinformatics\/btq461","article-title":"Search and clustering orders of magnitude faster than BLAST","volume":"26","author":"Edgar","year":"2010","journal-title":"Bioinformatics"},{"key":"2023020108383433100_btab493-B6","article-title":"Evaluating geographic variation within molecular operational taxonomic units (OTUs) using network analyses in Scandinavian lakes","volume":"2020","author":"Forster","year":"2020","journal-title":"BioRxiv"},{"key":"2023020108383433100_btab493-B7","doi-asserted-by":"crossref","first-page":"1188","DOI":"10.1038\/s41467-017-01312-x","article-title":"Algorithm for post-clustering curation of DNA amplicon data yields reliable biodiversity estimates","volume":"8","author":"Fr\u00f8slev","year":"2017","journal-title":"Nat. Commun"},{"key":"2023020108383433100_btab493-B8","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1038\/s41396-019-0506-9","article-title":"Marked changes in diversity and relative activity of picoeukaryotes with depth in the world ocean","volume":"14","author":"Giner","year":"2020","journal-title":"ISME J"},{"key":"2023020108383433100_btab493-B9","doi-asserted-by":"crossref","first-page":"e593","DOI":"10.7717\/peerj.593","article-title":"Swarm: robust and fast clustering method for amplicon-based studies","volume":"2","author":"Mah\u00e9","year":"2014","journal-title":"PeerJ"},{"key":"2023020108383433100_btab493-B10","doi-asserted-by":"crossref","first-page":"e1420","DOI":"10.7717\/peerj.1420","article-title":"Swarm v2: highly-scalable and high-resolution amplicon clustering","volume":"3","author":"Mah\u00e9","year":"2015","journal-title":"PeerJ"},{"key":"2023020108383433100_btab493-B11","doi-asserted-by":"crossref","first-page":"0091","DOI":"10.1038\/s41559-017-0091","article-title":"Parasites dominate hyperdiverse soil protist communities in Neotropical rainforests","volume":"1","author":"Mah\u00e9","year":"2017","journal-title":"Nat. Ecol. Evol"},{"key":"2023020108383433100_btab493-B12","first-page":"4","article-title":"Cache-, hash- and space-efficient bloom filters","volume":"14","author":"Putze","year":"2009","journal-title":"J. Experi. Algorithm"},{"key":"2023020108383433100_btab493-B13","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1111\/jeu.12813","article-title":"Perspectives from ten years of protist studies by high-throughput metabarcoding","volume":"67","author":"Santoferrara","year":"2020","journal-title":"J. Eukaryot. Microbiol"},{"key":"2023020108383433100_btab493-B14","doi-asserted-by":"crossref","first-page":"1501","DOI":"10.1128\/AEM.71.3.1501-1506.2005","article-title":"Introducing DOTUR, a computer program for defining operational taxonomic units and estimating species richness","volume":"71","author":"Schloss","year":"2005","journal-title":"Appli. Environ. Microbiol"},{"key":"2023020108383433100_btab493-B15","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1038\/nature24621","article-title":"A communal catalogue reveals Earth\u2019s multiscale microbial diversity","volume":"551","author":"Thompson","year":"2017","journal-title":"Nature"},{"key":"2023020108383433100_btab493-B16","doi-asserted-by":"crossref","first-page":"1261605","DOI":"10.1126\/science.1261605","article-title":"Eukaryotic plankton diversity in the sunlit global ocean","volume":"348","author":"de Vargas","year":"2015","journal-title":"Science"},{"key":"2023020108383433100_btab493-B17","doi-asserted-by":"crossref","first-page":"e1001745","DOI":"10.1371\/journal.pbio.1001745","article-title":"Best practices for scientific computing","volume":"12","author":"Wilson","year":"2014","journal-title":"PLoS Biol"},{"key":"2023020108383433100_btab493-B18","article-title":"SoftWipe\u2014a tool and benchmark to assess scientific software quality","volume":"2020","author":"Zapletal","year":"2020","journal-title":"BioRxiv"},{"key":"2023020108383433100_btab493-B19","author":"Zobrist","year":"1970"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btab493\/39509758\/btab493.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/1\/267\/49006260\/btab493.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/1\/267\/49006260\/btab493.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T19:53:49Z","timestamp":1675281229000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/38\/1\/267\/6318385"}},"subtitle":[],"editor":[{"given":"Inanc","family":"Birol","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,7,9]]},"references-count":19,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12,22]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab493","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,1,1]]},"published":{"date-parts":[[2021,7,9]]}}}