{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T21:50:23Z","timestamp":1781733023219,"version":"3.54.5"},"reference-count":11,"publisher":"Oxford University Press (OUP)","issue":"22","license":[{"start":{"date-parts":[[2016,10,2]],"date-time":"2016-10-02T00:00:00Z","timestamp":1475366400000},"content-version":"vor","delay-in-days":440,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,11,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Summary: A typical prokaryote population sequencing study can now consist of hundreds or thousands of isolates. Interrogating these datasets can provide detailed insights into the genetic structure of prokaryotic genomes. We introduce Roary, a tool that rapidly builds large-scale pan genomes, identifying the core and accessory genes. Roary makes construction of the pan genome of thousands of prokaryote samples possible on a standard desktop without compromising on the accuracy of results. Using a single CPU Roary can produce a pan genome consisting of 1000 isolates in 4.5 hours using 13 GB of RAM, with further speedups possible using multiple processors.<\/jats:p>\n                  <jats:p>Availability and implementation: Roary is implemented in Perl and is freely available under an open source GPLv3 license from http:\/\/sanger-pathogens.github.io\/Roary<\/jats:p>\n                  <jats:p>Contact: \u00a0roary@sanger.ac.uk<\/jats:p>\n                  <jats:p>Supplementary information: \u00a0Supplementary data are available at Bioinformatics online.<\/jats:p>","DOI":"10.1093\/bioinformatics\/btv421","type":"journal-article","created":{"date-parts":[[2015,7,21]],"date-time":"2015-07-21T20:20:09Z","timestamp":1437510009000},"page":"3691-3693","source":"Crossref","is-referenced-by-count":5342,"title":["Roary: rapid large-scale prokaryote pan genome analysis"],"prefix":"10.1093","volume":"31","author":[{"given":"Andrew J.","family":"Page","sequence":"first","affiliation":[{"name":"1 Pathogen Genomics, The Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carla A.","family":"Cummins","sequence":"additional","affiliation":[{"name":"1 Pathogen Genomics, The Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Hunt","sequence":"additional","affiliation":[{"name":"1 Pathogen Genomics, The Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vanessa K.","family":"Wong","sequence":"additional","affiliation":[{"name":"1 Pathogen Genomics, The Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge,"},{"name":"2 Department of Medicine, University of Cambridge, Cambridge,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sandra","family":"Reuter","sequence":"additional","affiliation":[{"name":"2 Department of Medicine, University of Cambridge, Cambridge,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew T.G.","family":"Holden","sequence":"additional","affiliation":[{"name":"3 School of Medicine, University of St. Andrews, North Haugh, St Andrews and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria","family":"Fookes","sequence":"additional","affiliation":[{"name":"1 Pathogen Genomics, The Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Falush","sequence":"additional","affiliation":[{"name":"4 College of Medicine, Swansea University, Swansea, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacqueline A.","family":"Keane","sequence":"additional","affiliation":[{"name":"1 Pathogen Genomics, The Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian","family":"Parkhill","sequence":"additional","affiliation":[{"name":"1 Pathogen Genomics, The Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge,"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2015,7,20]]},"reference":[{"key":"2023020202411027700_btv421-B2","doi-asserted-by":"crossref","first-page":"1575","DOI":"10.1093\/nar\/30.7.1575","article-title":"An efficient algorithm for large-scale detection of protein families","volume":"30","author":"Enright","year":"2002","journal-title":"Nucleic Acids Res."},{"key":"2023020202411027700_btv421-B3","doi-asserted-by":"crossref","first-page":"e172","DOI":"10.1093\/nar\/gks757","article-title":"PanOCT: automated clustering of orthologs using conserved gene neighborhood for pan-genomic analysis of bacterial strains and closely related species","volume":"40","author":"Fouts","year":"2012","journal-title":"Nucleic Acids Res."},{"key":"2023020202411027700_btv421-B4","doi-asserted-by":"crossref","first-page":"3150","DOI":"10.1093\/bioinformatics\/bts565","article-title":"CD-HIT: accelerated for clustering the next-generation sequencing data","volume":"28","author":"Fu","year":"2012","journal-title":"Bioinformatics"},{"key":"2023020202411027700_btv421-B5","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1016\/j.gde.2005.09.006","article-title":"The microbial pan-genome","volume":"15","author":"Medini","year":"2005","journal-title":"Curr. Opin. Genet. Dev."},{"key":"2023020202411027700_btv421-B6","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1007\/978-3-319-05269-4_17","article-title":"Building a pangenome reference for a population","volume-title":"Research in Computational Molecular Biology","author":"Nguyen","year":"2014"},{"key":"2023020202411027700_btv421-B7","doi-asserted-by":"crossref","first-page":"e332","DOI":"10.7717\/peerj.332","article-title":"The large-scale blast score ratio (LS-BSR) pipeline: a method to rapidly compare genetic content between bacterial genomes","volume":"2","author":"Sahl","year":"2014","journal-title":"PeerJ"},{"key":"2023020202411027700_btv421-B8","doi-asserted-by":"crossref","first-page":"2068","DOI":"10.1093\/bioinformatics\/btu153","article-title":"Prokka: rapid prokaryotic genome annotation","volume":"30","author":"Seemann","year":"2014","journal-title":"Bioinformatics"},{"key":"2023020202411027700_btv421-B9","article-title":"Generic feature format version 3 (GFF3)","volume":"1.21","author":"Stein","year":"2013","journal-title":"Seq. Ontol. Proj."},{"key":"2023020202411027700_btv421-B10","first-page":"42","article-title":"GNU parallel\u2014the command-line power tool.;login: The USENIX Magazine","volume":"36","author":"Tang","year":"2011"},{"key":"2023020202411027700_btv421-B11","first-page":"148","article-title":"Ten years of pan-genome analyses","volume":"23C","author":"Vernikos","year":"2014","journal-title":"Curr. Opin. Microbiol."},{"key":"2023020202411027700_btv421-B12","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1093\/bioinformatics\/btr655","article-title":"PGAP: pan-genomes analysis pipeline","volume":"28","author":"Zhao","year":"2012","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/31\/22\/3691\/49036081\/bioinformatics_31_22_3691.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/31\/22\/3691\/49036081\/bioinformatics_31_22_3691.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T22:56:05Z","timestamp":1675292165000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/31\/22\/3691\/240757"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,20]]},"references-count":11,"journal-issue":{"issue":"22","published-print":{"date-parts":[[2015,11,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btv421","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/019315","asserted-by":"object"}]},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2015,11,15]]},"published":{"date-parts":[[2015,7,20]]}}}