{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T07:52:50Z","timestamp":1778226770855,"version":"3.51.4"},"reference-count":46,"publisher":"Oxford University Press (OUP)","issue":"D1","funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC02-05CH11231"],"award-info":[{"award-number":["DE-AC02-05CH11231"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,1,8]]},"DOI":"10.1093\/nar\/gky901","type":"journal-article","created":{"date-parts":[[2018,9,24]],"date-time":"2018-09-24T15:13:14Z","timestamp":1537801994000},"page":"D666-D677","source":"Crossref","is-referenced-by-count":821,"title":["IMG\/M v.5.0: an integrated data management and comparative analysis system for microbial genomes and microbiomes"],"prefix":"10.1093","volume":"47","author":[{"given":"I-Min A","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Energy, Joint Genome Institute, 2800 Mitchell Drive, Walnut Creek, CA 94598, USA"}]},{"given":"Ken","family":"Chu","sequence":"additional","affiliation":[{"name":"Department of Energy, Joint Genome Institute, 2800 Mitchell Drive, Walnut Creek, CA 94598, USA"}]},{"given":"Krishna","family":"Palaniappan","sequence":"additional","affiliation":[{"name":"Department of Energy, Joint Genome Institute, 2800 Mitchell Drive, Walnut Creek, CA 94598, USA"}]},{"given":"Manoj","family":"Pillay","sequence":"additional","affiliation":[{"name":"Department of Energy, Joint Genome Institute, 2800 Mitchell Drive, Walnut Creek, CA 94598, USA"}]},{"given":"Anna","family":"Ratner","sequence":"additional","affiliation":[{"name":"Department of Energy, Joint Genome Institute, 2800 Mitchell Drive, Walnut Creek, CA 94598, USA"}]},{"given":"Jinghua","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Energy, Joint Genome Institute, 2800 Mitchell Drive, Walnut Creek, CA 94598, USA"}]},{"given":"Marcel","family":"Huntemann","sequence":"additional","affiliation":[{"name":"Department of Energy, Joint Genome Institute, 2800 Mitchell Drive, Walnut Creek, CA 94598, USA"}]},{"given":"Neha","family":"Varghese","sequence":"additional","affiliation":[{"name":"Department of Energy, Joint Genome Institute, 2800 Mitchell Drive, Walnut Creek, CA 94598, USA"}]},{"given":"James R","family":"White","sequence":"additional","affiliation":[{"name":"Resphera Biosciences, Baltimore, MD, USA"}]},{"given":"Rekha","family":"Seshadri","sequence":"additional","affiliation":[{"name":"Department of Energy, Joint Genome Institute, 2800 Mitchell Drive, Walnut Creek, CA 94598, USA"}]},{"given":"Tatyana","family":"Smirnova","sequence":"additional","affiliation":[{"name":"Department of Energy, Joint Genome Institute, 2800 Mitchell Drive, Walnut Creek, CA 94598, USA"}]},{"given":"Edward","family":"Kirton","sequence":"additional","affiliation":[{"name":"Department of Energy, Joint Genome Institute, 2800 Mitchell Drive, Walnut Creek, CA 94598, USA"}]},{"given":"Sean P","family":"Jungbluth","sequence":"additional","affiliation":[{"name":"Department of Energy, Joint Genome Institute, 2800 Mitchell Drive, Walnut Creek, CA 94598, USA"}]},{"given":"Tanja","family":"Woyke","sequence":"additional","affiliation":[{"name":"Department of Energy, Joint Genome Institute, 2800 Mitchell Drive, Walnut Creek, CA 94598, USA"}]},{"given":"Emiley A","family":"Eloe-Fadrosh","sequence":"additional","affiliation":[{"name":"Department of Energy, Joint Genome Institute, 2800 Mitchell Drive, Walnut Creek, CA 94598, USA"}]},{"given":"Natalia N","family":"Ivanova","sequence":"additional","affiliation":[{"name":"Department of Energy, Joint Genome Institute, 2800 Mitchell Drive, Walnut Creek, CA 94598, USA"}]},{"given":"Nikos C","family":"Kyrpides","sequence":"additional","affiliation":[{"name":"Department of Energy, Joint Genome Institute, 2800 Mitchell Drive, Walnut Creek, CA 94598, USA"}]}],"member":"286","published-online":{"date-parts":[[2018,10,5]]},"reference":[{"key":"key\n\t\t\t\t2019010800382294800_B1","doi-asserted-by":"crossref","first-page":"D36","DOI":"10.1093\/nar\/gks1195","article-title":"GenBank","volume":"41","author":"Benson","year":"2013","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019010800382294800_B2","doi-asserted-by":"crossref","first-page":"D446","DOI":"10.1093\/nar\/gkw992","article-title":"Genomes OnLine Database (GOLD) v.6: data updates and feature enhancements","volume":"45","author":"Mukherjee","year":"2017","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019010800382294800_B3","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1186\/s40793-015-0077-y","article-title":"The standard operating procedure of the DOE-JGI microbial genome annotation pipeline (MGAP v. 4)","volume":"10","author":"Huntemann","year":"2015","journal-title":"Stand. Genomic Sci."},{"key":"key\n\t\t\t\t2019010800382294800_B4","doi-asserted-by":"crossref","first-page":"599","DOI":"10.4056\/sigs.5559608","article-title":"Genomic standards consortium projects","volume":"9","author":"Field","year":"2014","journal-title":"Stand Genomic Sci."},{"key":"key\n\t\t\t\t2019010800382294800_B5","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1186\/1471-2105-8-209","article-title":"CRISPR Recognition Tool (CRT): a tool for automatic detection of clustered regularly interspaced palindromic repeats","volume":"8","author":"Bland","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"key\n\t\t\t\t2019010800382294800_B6","doi-asserted-by":"crossref","first-page":"2933","DOI":"10.1093\/bioinformatics\/btt509","article-title":"Infernal 1.1: 100-fold faster RNA homology searches","volume":"29","author":"Nawrocki","year":"2013","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t2019010800382294800_B7","doi-asserted-by":"crossref","first-page":"D335","DOI":"10.1093\/nar\/gkx1038","article-title":"Rfam 13.0: shifting to a genome-centric resource for non-coding RNA familes","volume":"46","author":"Kalvari","year":"2018","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019010800382294800_B8","doi-asserted-by":"crossref","first-page":"1335","DOI":"10.1093\/bioinformatics\/btp157","article-title":"Infernal 1.0: inference of RNA alignments","volume":"25","author":"Nawrocki","year":"2009","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t2019010800382294800_B9","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1186\/1471-2105-11-119","article-title":"Prodigal: prokaryotic gene recognition and translation initiation site identification","volume":"11","author":"Hyatt","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"key\n\t\t\t\t2019010800382294800_B10","doi-asserted-by":"crossref","first-page":"953","DOI":"10.1038\/nprot.2007.131","article-title":"Locating proteins in the cell using TargetP, SignalP, and related tools","volume":"2","author":"Emanuelsson","year":"2007","journal-title":"Nat. Protoc."},{"key":"key\n\t\t\t\t2019010800382294800_B11","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1093\/bioinformatics\/17.7.646","article-title":"Evaluation of methods for the prediction of membrane spanning regions","volume":"17","author":"Moller","year":"2001","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t2019010800382294800_B12","doi-asserted-by":"crossref","first-page":"D261","DOI":"10.1093\/nar\/gku1223","article-title":"Expanded microbial genome coverage and improved protein family annotation in the COG database","volume":"43","author":"Galperin","year":"2015","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019010800382294800_B13","doi-asserted-by":"crossref","first-page":"D279","DOI":"10.1093\/nar\/gkv1344","article-title":"The Pfam protein families database: towards a more sustainable future","volume":"44","author":"Finn","year":"2016","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019010800382294800_B14","doi-asserted-by":"crossref","first-page":"D387","DOI":"10.1093\/nar\/gks1234","article-title":"TIGRFAMs and Genome Properties in 2013","volume":"41","author":"Haft","year":"2013","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019010800382294800_B15","doi-asserted-by":"crossref","first-page":"W30","DOI":"10.1093\/nar\/gkv397","article-title":"HMMER web server: 2015 update","volume":"43","author":"Finn","year":"2015","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019010800382294800_B16","doi-asserted-by":"crossref","first-page":"1236","DOI":"10.1093\/bioinformatics\/btu031","article-title":"InterProScan 5: genome-scale protein function classification","volume":"30","author":"Jones","year":"2014","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t2019010800382294800_B17","doi-asserted-by":"crossref","first-page":"D457","DOI":"10.1093\/nar\/gkv1070","article-title":"KEGG as a reference resource for gene and protein annotation","volume":"44","author":"Kanehisa","year":"2016","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019010800382294800_B18","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1101\/gr.113985.110","article-title":"Adaptive seeds tame genomic sequence comparison","volume":"21","author":"Kielbasa","year":"2011","journal-title":"Genome Res."},{"key":"key\n\t\t\t\t2019010800382294800_B19","doi-asserted-by":"crossref","first-page":"D471","DOI":"10.1093\/nar\/gkv1164","article-title":"The MetaCyc database of metabolic pathways and enzymes and the BioCyc collection of pathway\/genome databases","volume":"44","author":"Caspi","year":"2016","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019010800382294800_B20","volume-title":"Metabolic Reconstruction of Microbial Genomes and Microbial Community Metagenomes","author":"Ivanova","year":"2007"},{"key":"key\n\t\t\t\t2019010800382294800_B21","doi-asserted-by":"crossref","first-page":"e54859","DOI":"10.1371\/journal.pone.0054859","article-title":"Improving microbial genome annotations in an integrated database context","volume":"8","author":"Chen","year":"2013","journal-title":"PLoS One"},{"key":"key\n\t\t\t\t2019010800382294800_B22","doi-asserted-by":"crossref","first-page":"6761","DOI":"10.1093\/nar\/gkv657","article-title":"Microbial species delineation using whole genome sequences","volume":"43","author":"Varghese","year":"2015","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019010800382294800_B23","doi-asserted-by":"crossref","first-page":"e7979","DOI":"10.1371\/journal.pone.0007979","article-title":"Gene context analysis in the Integrated Microbial Genomes (IMG) data management system, accepted for publication","volume":"4","author":"Mavromatis","year":"2009","journal-title":"PLoS One"},{"key":"key\n\t\t\t\t2019010800382294800_B24","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1038\/47056","article-title":"Protein interaction maps for complete genomes based on gene fusion events","volume":"402","author":"Enright","year":"1999","journal-title":"Nature"},{"key":"key\n\t\t\t\t2019010800382294800_B25","doi-asserted-by":"crossref","first-page":"D560","DOI":"10.1093\/nar\/gkw1103","article-title":"IMG-ABC: new features for bacterial secondary metabolism analysis and targeted biosynthetic gene cluster discovery in thousands of microbial genomes","volume":"45","author":"Hadjithomas","year":"2017","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019010800382294800_B26","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1186\/s40793-016-0138-x","article-title":"The standard operating procedure of the DOE-JGI metagenome annotation pipeline (MAP v. 4)","volume":"11","author":"Huntemann","year":"2015","journal-title":"Stand. Genomic Sci."},{"key":"key\n\t\t\t\t2019010800382294800_B27","doi-asserted-by":"crossref","first-page":"D507","DOI":"10.1093\/nar\/gkw929","article-title":"IMG\/M: integrated genome and metagenome comparative data analysis system","volume":"45","author":"Chen","year":"2017","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019010800382294800_B28","doi-asserted-by":"crossref","first-page":"D457","DOI":"10.1093\/nar\/gkw1030","article-title":"IMG\/VR: a database of cultured and uncultured DNA viruses and retroviruses","volume":"45","author":"Paez-Espino","year":"2016","journal-title":"Nucleic Acids Res."},{"key":"key\n\t\t\t\t2019010800382294800_B29","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1186\/s12864-016-2629-y","article-title":"Supporting community annotation and user collaboration in the integrated microbial genomes (IMG) system","volume":"17","author":"Chen","year":"2016","journal-title":"BMC Genomics"},{"key":"key\n\t\t\t\t2019010800382294800_B30","article-title":"Mathematics of a lady tasting tea","volume-title":"The World of Mathematics","author":"Fisher","year":"1956"},{"key":"key\n\t\t\t\t2019010800382294800_B31","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1214\/aoms\/1177730491","article-title":"On a test of whether one of two random variables is stochastically larger than the other","volume":"18","author":"Mann","year":"1947","journal-title":"Ann. Math. Stat."},{"key":"key\n\t\t\t\t2019010800382294800_B32","first-page":"28","article-title":"The generalization of Student's problem when several different population variances are involved","volume":"34","author":"Welch","year":"1947","journal-title":"Biometrika"},{"key":"key\n\t\t\t\t2019010800382294800_B33","first-page":"3","article-title":"On the probable error of a coefficient of correlation deduced from a small sample","volume":"1","author":"Fisher","year":"1921","journal-title":"Metron"},{"key":"key\n\t\t\t\t2019010800382294800_B34","volume-title":"Discovering Statistics using SPSS","author":"Field","year":"2009"},{"key":"key\n\t\t\t\t2019010800382294800_B35","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the false discovery rate: a practical and powerful approach to multiple testing","volume":"57","author":"Benjamini","year":"1995","journal-title":"J. R. Stat. Soc. B (Methodological)"},{"key":"key\n\t\t\t\t2019010800382294800_B36","doi-asserted-by":"crossref","first-page":"17","DOI":"10.21775\/cimb.024.017","article-title":"Guidelines to statistical analysis of microbial composition data inferred from metagenomic sequencing","volume":"24","author":"Odintsova","year":"2017","journal-title":"Curr. Issues Mol. Biol."},{"key":"key\n\t\t\t\t2019010800382294800_B37","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1186\/s40168-016-0154-5","article-title":"Recovering complete and draft population genomes from metagenome datasets","volume":"4","author":"Sangwan","year":"2016","journal-title":"Microbiome"},{"key":"key\n\t\t\t\t2019010800382294800_B38","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1038\/nbt.3935","article-title":"Shotgun metagenomics, from sampling to analysis","volume":"35","author":"Quince","year":"2017","journal-title":"Nat. Biotechnol."},{"key":"key\n\t\t\t\t2019010800382294800_B39","doi-asserted-by":"crossref","first-page":"1533","DOI":"10.1038\/s41564-017-0012-7","article-title":"Recovery of nearly 8,000 metagenome-assembled genomes substantially expands the tree of life","volume":"2","author":"Parks","year":"2017","journal-title":"Nat. Microbiol."},{"key":"key\n\t\t\t\t2019010800382294800_B40","doi-asserted-by":"crossref","first-page":"170203","DOI":"10.1038\/sdata.2017.203","article-title":"The reconstruction of 2,631 draft metagenome-assembled genomes from the global oceans","volume":"5","author":"Tully","year":"2018","journal-title":"Scientific Data"},{"key":"key\n\t\t\t\t2019010800382294800_B41","doi-asserted-by":"crossref","first-page":"1063","DOI":"10.1038\/nmeth.4458","article-title":"Critical Assessment of Metagenome Interpretation-a benchmark of metagenomics software","volume":"14","author":"Sczyrba","year":"2017","journal-title":"Nat. Methods"},{"key":"key\n\t\t\t\t2019010800382294800_B42","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1038\/nbt.3893","article-title":"Minimum information about a single amplified genome (MISAG) and a metagenome-assembled genome (MIMAG) of bacteria and archaea","volume":"35","author":"Bowers","year":"2017","journal-title":"Nat. Biotechnol."},{"key":"key\n\t\t\t\t2019010800382294800_B43","doi-asserted-by":"crossref","first-page":"e1165","DOI":"10.7717\/peerj.1165","article-title":"MetaBAT, an efficient tool for accurately reconstructing single genomes from complex microbial communities","volume":"3","author":"Kang","year":"2015","journal-title":"PeerJ"},{"key":"key\n\t\t\t\t2019010800382294800_B44","doi-asserted-by":"crossref","first-page":"1043","DOI":"10.1101\/gr.186072.114","article-title":"CheckM: assessing the quality of microbial genomes recovered from isolates, single cells, and metagenomes","volume":"25","author":"Parks","year":"2015","journal-title":"Genome Res."},{"key":"key\n\t\t\t\t2019010800382294800_B45","doi-asserted-by":"crossref","DOI":"10.1145\/2618243.2618244","volume-title":"Maintaining a Microbial Genome & Metagenome Data Analysis System in an Academic Setting","author":"Chen","year":"2014"},{"key":"key\n\t\t\t\t2019010800382294800_B46","doi-asserted-by":"crossref","first-page":"W36","DOI":"10.1093\/nar\/gkx319","article-title":"antiSMASH 4.0 \u2013 improvements in chemistry prediction and gene cluster boundary identification","volume":"45","author":"Blin","year":"2017","journal-title":"Nucleic Acids Res."}],"container-title":["Nucleic Acids Research"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/nar\/article-pdf\/47\/D1\/D666\/27436299\/gky901.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,24]],"date-time":"2019-10-24T15:42:31Z","timestamp":1571931751000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/nar\/article\/47\/D1\/D666\/5115825"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,5]]},"references-count":46,"journal-issue":{"issue":"D1","published-online":{"date-parts":[[2018,10,5]]},"published-print":{"date-parts":[[2019,1,8]]}},"URL":"https:\/\/doi.org\/10.1093\/nar\/gky901","relation":{},"ISSN":["0305-1048","1362-4962"],"issn-type":[{"value":"0305-1048","type":"print"},{"value":"1362-4962","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,1,8]]},"published":{"date-parts":[[2018,10,5]]}}}