{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:51:27Z","timestamp":1783698687390,"version":"3.55.0"},"reference-count":75,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2014,4,3]],"date-time":"2014-04-03T00:00:00Z","timestamp":1396483200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"DOI":"10.1371\/journal.pcbi.1003531","type":"journal-article","created":{"date-parts":[[2014,4,3]],"date-time":"2014-04-03T16:28:31Z","timestamp":1396542511000},"page":"e1003531","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":2614,"title":["Waste Not, Want Not: Why Rarefying Microbiome Data Is Inadmissible"],"prefix":"10.1371","volume":"10","author":[{"given":"Paul J.","family":"McMurdie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Susan","family":"Holmes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2014,4,3]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"1084","DOI":"10.1038\/nbt.2421","article-title":"The expanding scope of DNA sequencing","volume":"30","author":"J Shendure","year":"2012","journal-title":"Nature Biotechnology"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"1135","DOI":"10.1038\/nbt1486","article-title":"Next-generation DNA sequencing","volume":"26","author":"J Shendure","year":"2008","journal-title":"Nature Biotechnology"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1038\/nmeth.1226","article-title":"Mapping and quantifying mammalian transcriptomes by RNA-Seq","volume":"5","author":"A Mortazavi","year":"2008","journal-title":"Nature Methods"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1126\/science.276.5313.734","article-title":"A molecular view of microbial diversity and the biosphere","volume":"276","author":"NR Pace","year":"1997","journal-title":"Science"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"2535","DOI":"10.1128\/AEM.68.5.2535-2541.2002","article-title":"High-Density Microarray of Small-Subunit Ribosomal DNA Probes","volume":"68","author":"KH Wilson","year":"2002","journal-title":"Appl Environ Microbiol"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"e1000255","DOI":"10.1371\/journal.pgen.1000255","article-title":"Exploring microbial diversity and taxonomy using SSU rRNA hypervariable tag sequencing","volume":"4","author":"SM Huse","year":"2008","journal-title":"PLoS Genetics"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1146\/annurev.genet.38.072902.091216","article-title":"Metagenomics: genomic analysis of microbial communities","volume":"38","author":"CS Riesenfeld","year":"2004","journal-title":"Annual Review of Genetics"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1038\/nrg1749","article-title":"Microarray Data Analysis: from Disarray to Consolidation and Consensus","volume":"7","author":"DB Allison","year":"2006","journal-title":"Nature Reviews Genetics"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1509","DOI":"10.1101\/gr.079558.108","article-title":"RNA-Seq: an assessment of technical reproducibility and comparison with gene expression arrays","volume":"18","author":"JC Marioni","year":"2008","journal-title":"Genome Research"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1186\/1471-2105-6-165","article-title":"Identifying differential expression in multiple SAGE libraries: an overdispersed log-linear model approach","volume":"6","author":"J Lu","year":"2005","journal-title":"BMC Bioinformatics"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1093\/biostatistics\/kxm030","article-title":"Small-sample estimation of negative binomial dispersion, with applications to SAGE data","volume":"9","author":"MD Robinson","year":"2007","journal-title":"Biostatistics (Oxford, England)"},{"key":"ref12","doi-asserted-by":"crossref","unstructured":"Cameron AC, Trivedi P (2013) Regression analysis of count data, volume 53. Cambridge University Press.","DOI":"10.1017\/CBO9781139013567"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"R106","DOI":"10.1186\/gb-2010-11-10-r106","article-title":"Differential expression analysis for sequence count data","volume":"11","author":"S Anders","year":"2010","journal-title":"Genome Biology"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"1275","DOI":"10.1093\/bioinformatics\/btt143","article-title":"Shrinkage estimation of dispersion in Negative Binomial models for RNASeq experiments with small sample size","volume":"29","author":"D Yu","year":"2013","journal-title":"Bioinformatics (Oxford, England)"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1016\/j.mimet.2013.08.011","article-title":"High throughput sequencing methods and analysis for microbiome research","volume":"95","author":"JM Di Bella","year":"2013","journal-title":"Journal of Microbiological Methods"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"666","DOI":"10.1038\/msb.2013.22","article-title":"Computational meta&apos;omics for microbial community studies","volume":"9","author":"N Segata","year":"2013","journal-title":"Molecular Systems Biology"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1016\/B978-0-12-407863-5.00019-8","article-title":"Advancing Our Understanding of the Human Microbiome Using QIIME","volume":"531","author":"JA Navas-Molina","year":"2013","journal-title":"Methods in Enzymology"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1016\/S0076-6879(05)97017-1","article-title":"The application of rarefaction techniques to molecular inventories of microbial diversity","volume":"397","author":"JB Hughes","year":"2005","journal-title":"Methods in Enzymology"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"e1002863","DOI":"10.1371\/journal.pcbi.1002863","article-title":"A guide to enterotypes across the human body: meta-analysis of microbial community structures in human microbiome datasets","volume":"9","author":"O Koren","year":"2013","journal-title":"PLoS Computational Biology"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1086\/282541","article-title":"Marine benthic diversity: A comparative study","volume":"102","author":"HL Sanders","year":"1968","journal-title":"The American Naturalist"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1046\/j.1461-0248.2001.00230.x","article-title":"Quantifying biodiversity: procedures and pitfalls in the measurement and comparison of species richness","volume":"4","author":"NJ Gotelli","year":"2001","journal-title":"Ecology Letters"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1890\/04-1078","article-title":"Estimation of Species Richness: Mixture Models, the Role of Rare Species, and Inferential Challenges","volume":"86","author":"CX Mao","year":"2005","journal-title":"Ecology"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"8228","DOI":"10.1128\/AEM.71.12.8228-8235.2005","article-title":"UniFrac: a new phylogenetic method for comparing microbial communities","volume":"71","author":"C Lozupone","year":"2005","journal-title":"Applied and Environmental Microbiology"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1038\/ismej.2010.133","article-title":"UniFrac: an effective distance metric for microbial community comparison","volume":"5","author":"C Lozupone","year":"2011","journal-title":"The ISME Journal"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1038\/nmeth.1184","article-title":"Error-correcting barcoded primers for pyrosequencing hundreds of samples in multiplex","volume":"5","author":"M Hamady","year":"2008","journal-title":"Nature Methods"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"e120","DOI":"10.1093\/nar\/gkn491","article-title":"Accurate taxonomy assignments from 16S rRNA sequences produced by highly parallel pyrosequencers","volume":"36","author":"Z Liu","year":"2008","journal-title":"Nucleic Acids Research"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1038\/ismej.2009.97","article-title":"Fast UniFrac: facilitating high-throughput phylogenetic analyses of microbial communities including analysis of pyrosequencing and PhyloChip data","volume":"4","author":"M Hamady","year":"2010","journal-title":"The ISME Journal"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1038\/nature11053","article-title":"Human gut microbiome viewed across age and geography","volume":"486","author":"T Yatsunenko","year":"2012","journal-title":"Nature"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1038\/nmeth.f.303","article-title":"QIIME allows analysis of high-throughput community sequencing data","volume":"7","author":"J Caporaso","year":"2010","journal-title":"Nature Methods"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"7537","DOI":"10.1128\/AEM.01541-09","article-title":"Introducing mothur: Open-Source, Platform-Independent, Community-Supported Software for Describing and Comparing Microbial Communities","volume":"75","author":"PD Schloss","year":"2009","journal-title":"Applied and Environmental Microbiology"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"3132","DOI":"10.1111\/j.1462-2920.2009.02017.x","article-title":"The seasonal structure of microbial communities in the Western English Channel","volume":"11","author":"JA Gilbert","year":"2009","journal-title":"Environmental Microbiology"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"e61217","DOI":"10.1371\/journal.pone.0061217","article-title":"phyloseq: an R package for reproducible interactive analysis and graphics of microbiome census data","volume":"8","author":"PJ McMurdie","year":"2013","journal-title":"PLoS ONE"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"e15216","DOI":"10.1371\/journal.pone.0015216","article-title":"Disordered microbial communities in the upper respiratory tract of cigarette smokers","volume":"5","author":"ES Charlson","year":"2010","journal-title":"PLoS ONE"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"e8422","DOI":"10.1371\/journal.pone.0008422","article-title":"The effects of circumcision on the penis microbiome","volume":"5","author":"LB Price","year":"2010","journal-title":"PLoS ONE"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"1469","DOI":"10.1038\/ismej.2011.211","article-title":"Architectural design influences the diversity and structure of the built environment microbiome","volume":"6","author":"SW Kembel","year":"2012","journal-title":"The ISME Journal"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1111\/1462-2920.12036","article-title":"Diversity, distribution and sources of bacteria in residential kitchens","volume":"15","author":"GE Flores","year":"2013","journal-title":"Environmental Microbiology"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"e68322","DOI":"10.1371\/journal.pone.0068322","article-title":"Reduced incidence of Prevotella and other fermenters in intestinal microflora of autistic children","volume":"8","author":"DW Kang","year":"2013","journal-title":"PLoS ONE"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"R42","DOI":"10.1186\/gb-2012-13-6-r42","article-title":"Composition of the adult digestive tract bacterial microbiome based on seven mouth surfaces, tonsils, throat and stool samples","volume":"13","author":"N Segata","year":"2012","journal-title":"Genome Biology"},{"key":"ref39","doi-asserted-by":"crossref","first-page":"e1000352","DOI":"10.1371\/journal.pcbi.1000352","article-title":"Statistical methods for detecting differentially abundant features in clinical metagenomic samples","volume":"5","author":"JR White","year":"2009","journal-title":"PLoS Computational Biology"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"1200","DOI":"10.1038\/nmeth.2658","article-title":"Differential abundance analysis for microbial marker-gene surveys","volume":"10","author":"JN Paulson","year":"2013","journal-title":"Nature Methods"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1093\/bioinformatics\/btp616","article-title":"edgeR: a Bioconductor package for differential expression analysis of digital gene expression data","volume":"26","author":"MD Robinson","year":"2009","journal-title":"Bioinformatics (Oxford, England)"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1093\/biomet\/53.3-4.325","article-title":"Some distance properties of latent root and vector methods used in multivariate analysis","volume":"53","author":"JC Gower","year":"1966","journal-title":"Biometrika"},{"key":"ref43","unstructured":"Oksanen J, Blanchet FG, Kindt R, Legendre P, O&apos;Hara RB, <etal>et al<\/etal>.. (2011) vegan: Community Ecology Package. R package version 1.17-10."},{"key":"ref44","first-page":"32","article-title":"A new method for non-parametric multivariate analysis of variance","volume":"26","author":"M Anderson","year":"2001","journal-title":"Austral Ecology"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"325","DOI":"10.2307\/1942268","article-title":"An Ordination of the Upland Forest Communities of Southern Wisconsin","volume":"27","author":"JR Bray","year":"1957","journal-title":"Ecological Monographs"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"2493","DOI":"10.1214\/11-AOAS493","article-title":"Classification and clustering of sequencing data using a Poisson model","volume":"5","author":"DM Witten","year":"2011","journal-title":"The Annals of Applied Statistics"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"1576","DOI":"10.1128\/AEM.01996-06","article-title":"Quantitative and qualitative beta diversity measures lead to different insights into factors that structure microbial communities","volume":"73","author":"CA Lozupone","year":"2007","journal-title":"Applied and Environmental Microbiology"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"4516","DOI":"10.1073\/pnas.1000080107","article-title":"Global patterns of 16S rRNA diversity at a depth of millions of sequences per sample","volume":"108","author":"JG Caporaso","year":"2011","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"ref49","doi-asserted-by":"crossref","unstructured":"Kaufman L, Rousseeuw PJ (1990) Finding Groups in Data: An Introduction to Cluster Analysis, JohnWiley &amp; Sons, chapter 2.","DOI":"10.1002\/9780470316801"},{"key":"ref50","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1007\/s10852-005-9022-1","article-title":"Clustering rules: A comparison of partitioning and hierarchical clustering algorithms","volume":"5","author":"A Reynolds","year":"2006","journal-title":"Journal of Mathematical Modelling and Algorithms"},{"key":"ref51","unstructured":"Pollard KS, Gilbert HN, Ge Y, Taylor S, Dudoit S (2010) multtest: Resampling-based multiple hypothesis testing. R package version 2.4.0."},{"key":"ref52","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":"Y Benjamini","year":"1995","journal-title":"Journal of the Royal Statistical Society Series B (Methodological)"},{"key":"ref53","unstructured":"Allaire J, Horner J, Marti V, Porte N (2014) markdown: Markdown rendering for R. R package version 0.6.4."},{"key":"ref54","unstructured":"Maechler M, Rousseeuw P, Struyf A, Hubert M, Hornik K (2013) cluster: Cluster Analysis Basics and Extensions."},{"key":"ref55","unstructured":"Revolution Analytics (2011) foreach: Foreach looping construct for R. R package version 1.3.2."},{"key":"ref56","doi-asserted-by":"crossref","unstructured":"Wickham H (2009) ggplot2: elegant graphics for data analysis. Springer New York.","DOI":"10.1007\/978-0-387-98141-3"},{"key":"ref57","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v040.i01","article-title":"The split-apply-combine strategy for data analysis","volume":"40","author":"H Wickham","year":"2011","journal-title":"Journal of Statistical Software"},{"key":"ref58","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v021.i12","article-title":"Reshaping data with the reshape package","volume":"21","author":"H Wickham","year":"2007","journal-title":"Journal of Statistical Software"},{"key":"ref59","doi-asserted-by":"crossref","first-page":"3940","DOI":"10.1093\/bioinformatics\/bti623","article-title":"ROCR: visualizing classifier performance in R","volume":"21","author":"T Sing","year":"2005","journal-title":"Bioinformatics (Oxford, England)"},{"key":"ref60","unstructured":"R Development Core Team (2011) R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria. ISBN 3-900051-07-0."},{"key":"ref61","volume":"chapter 6","unstructured":"Hastie TJ, Pregibon D (1992) Generalized linear models. In: Chambers JM, Hastie TJ, editors, Statistical Models in S, Chapman &amp; Hall\/CRC, <volume>chapter 6<\/volume>.."},{"key":"ref62","doi-asserted-by":"crossref","first-page":"10084","DOI":"10.1093\/nar\/gks804","article-title":"A comprehensive comparison of RNA-Seq-based transcriptome analysis from reads to differential gene expression and crosscomparison with microarrays: a case study in Saccharomyces cerevisiae","volume":"40","author":"I Nookaew","year":"2012","journal-title":"Nucleic Acids Research"},{"key":"ref63","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1186\/1471-2105-11-94","article-title":"Evaluation of statistical methods for normalization and differential expression in mRNA-Seq experiments","volume":"11","author":"J Bullard","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"ref64","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1186\/1471-2105-14-219","article-title":"TCC: an R package for comparing tag count data with robust normalization strategies","volume":"14","author":"J Sun","year":"2013","journal-title":"BMC Bioinformatics"},{"key":"ref65","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1186\/1471-2105-14-91","article-title":"A comparison of methods for differential expression analysis of RNA-Seq data","volume":"14","author":"C Soneson","year":"2013","journal-title":"BMC Bioinformatics"},{"key":"ref66","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1186\/1471-2105-11-422","article-title":"baySeq: empirical Bayesian methods for identifying differential expression in sequence count data","volume":"11","author":"TJ Hardcastle","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"ref67","doi-asserted-by":"crossref","first-page":"S11","DOI":"10.1186\/1471-2164-13-S8-S11","article-title":"DFI: gene feature discovery in RNA-Seq experiments from multiple sources","volume":"13 Suppl 8","author":"HG Ozer","year":"2012","journal-title":"BMC Genomics"},{"key":"ref68","doi-asserted-by":"crossref","first-page":"9546","DOI":"10.1073\/pnas.0914005107","article-title":"Independent filtering increases detection power for highthroughput experiments","volume":"107","author":"R Bourgon","year":"2010","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"ref69","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1111\/j.1461-0248.2004.00707.x","article-title":"A new statistical approach for assessing similarity of species composition with incidence and abundance data","volume":"8","author":"A Chao","year":"2005","journal-title":"Ecology Letters"},{"key":"ref70","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1038\/ismej.2008.5","article-title":"Evaluating different approaches that test whether microbial communities have the same structure","volume":"2","author":"PD Schloss","year":"2008","journal-title":"The ISME Journal"},{"key":"ref71","first-page":"1","article-title":"Statistical analyses and reproducible research","volume":"1","author":"R Gentleman","year":"2004","journal-title":"Bioconductor Project Working Papers"},{"key":"ref72","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.1126\/science.1213847","article-title":"Reproducible research in computational science","volume":"334","author":"RD Peng","year":"2011","journal-title":"Science"},{"key":"ref73","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1093\/biostatistics\/kxq028","article-title":"An invitation to reproducible computational research","volume":"11","author":"DL Donoho","year":"2010","journal-title":"Biostatistics (Oxford, England)"},{"key":"ref74","doi-asserted-by":"crossref","first-page":"R80","DOI":"10.1186\/gb-2004-5-10-r80","article-title":"Bioconductor: open software development for computational biology and bioinformatics","volume":"5","author":"RC Gentleman","year":"2004","journal-title":"Genome Biology"},{"key":"ref75","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1126\/science.1208344","article-title":"Linking long-term dietary patterns with gut microbial enterotypes","volume":"334","author":"GD Wu","year":"2011","journal-title":"Science"}],"container-title":["PLoS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pcbi.1003531","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,9]],"date-time":"2019-08-09T01:51:18Z","timestamp":1565315478000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1003531"}},"subtitle":[],"editor":[{"given":"Alice Carolyn","family":"McHardy","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2014,4,3]]},"references-count":75,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2014,4,3]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1003531","relation":{"has-review":[{"id-type":"doi","id":"10.3410\/f.718338388.793493396","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,4,3]]}}}