{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T21:15:13Z","timestamp":1793394913441,"version":"4.5.0"},"reference-count":57,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2019,8,22]],"date-time":"2019-08-22T00:00:00Z","timestamp":1566432000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"DOI":"10.1371\/journal.pone.0221068","type":"journal-article","created":{"date-parts":[[2019,8,22]],"date-time":"2019-08-22T13:29:55Z","timestamp":1566480595000},"page":"e0221068","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":201,"title":["TreeCluster: Clustering biological sequences using phylogenetic trees"],"prefix":"10.1371","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6947-5915","authenticated-orcid":true,"given":"Metin","family":"Balaban","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2209-8128","authenticated-orcid":true,"given":"Niema","family":"Moshiri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Uyen","family":"Mai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingfan","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siavash","family":"Mirarab","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2019,8,22]]},"reference":[{"issue":"2","key":"pone.0221068.ref001","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1016\/j.cell.2014.06.037","article-title":"Conducting a microbiome study","volume":"158","author":"JK Goodrich","year":"2014","journal-title":"Cell"},{"issue":"19","key":"pone.0221068.ref002","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":"RC Edgar","year":"2010","journal-title":"Bioinformatics"},{"issue":"3","key":"pone.0221068.ref003","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":"PD Schloss","year":"2005","journal-title":"Applied and Environmental Microbiology"},{"key":"pone.0221068.ref004","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1186\/1471-2105-14-317","article-title":"Automated analysis of phylogenetic clusters","volume":"14","author":"M Ragonnet-Cronin","year":"2013","journal-title":"BMC bioinformatics"},{"issue":"7","key":"pone.0221068.ref005","doi-asserted-by":"crossref","first-page":"1812","DOI":"10.1093\/molbev\/msy016","article-title":"HIV-TRACE (TRAnsmission Cluster Engine): a Tool for Large Scale Molecular Epidemiology of HIV-1 and Other Rapidly Evolving Pathogens","volume":"35","author":"SL Kosakovsky Pond","year":"2018","journal-title":"Molecular Biology and Evolution"},{"issue":"2","key":"pone.0221068.ref006","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1093\/sysbio\/42.2.182","article-title":"An Empirical Test of Bootstrapping as a Method for Assessing Confidence in Phylogenetic Analysis","volume":"42","author":"DM Hillis","year":"1993","journal-title":"Systematic Biology"},{"key":"pone.0221068.ref007","doi-asserted-by":"crossref","DOI":"10.1017\/9781316882313","volume-title":"Computational phylogenetics: An introduction to designing methods for phylogeny estimation","author":"T Warnow","year":"2017"},{"issue":"3","key":"pone.0221068.ref008","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0009490","article-title":"FastTree 2\u2014Approximately maximum-likelihood trees for large alignments","volume":"5","author":"MN Price","year":"2010","journal-title":"PLoS ONE"},{"issue":"05","key":"pone.0221068.ref009","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1089\/cmb.2014.0156","article-title":"PASTA: Ultra-Large Multiple Sequence Alignment for Nucleotide and Amino-Acid Sequences","volume":"22","author":"S Mirarab","year":"2015","journal-title":"Journal of Computational Biology"},{"issue":"1","key":"pone.0221068.ref010","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1186\/s13059-015-0688-z","article-title":"Ultra-large alignments using phylogeny-aware profiles","volume":"16","author":"NPDNpD Nguyen","year":"2015","journal-title":"Genome Biology"},{"issue":"7","key":"pone.0221068.ref011","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":"AJ Enright","year":"2002","journal-title":"Nucleic acids research"},{"issue":"9","key":"pone.0221068.ref012","doi-asserted-by":"crossref","first-page":"2178","DOI":"10.1101\/gr.1224503","article-title":"OrthoMCL: Identification of Ortholog Groups for Eukaryotic Genomes","volume":"13","author":"L Li","year":"2003","journal-title":"Genome Research"},{"key":"pone.0221068.ref013","article-title":"MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets","author":"M Steinegger","year":"2017","journal-title":"Nature Biotechnology"},{"key":"pone.0221068.ref014","doi-asserted-by":"crossref","first-page":"16004","DOI":"10.1038\/npjbiofilms.2016.4","article-title":"A perspective on 16S rRNA operational taxonomic unit clustering using sequence similarity","volume":"2","author":"NP Nguyen","year":"2016","journal-title":"npj Biofilms and Microbiomes"},{"issue":"1","key":"pone.0221068.ref015","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1186\/1471-2105-14-317","article-title":"Automated analysis of phylogenetic clusters","volume":"14","author":"M Ragonnet-Cronin","year":"2013","journal-title":"BMC bioinformatics"},{"issue":"8","key":"pone.0221068.ref016","doi-asserted-by":"crossref","first-page":"e0182238","DOI":"10.1371\/journal.pone.0182238","article-title":"Minimum variance rooting of phylogenetic trees and implications for species tree reconstruction","volume":"12","author":"U Mai","year":"2017","journal-title":"PLOS ONE"},{"issue":"1","key":"pone.0221068.ref017","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1007\/BF00978378","article-title":"Partitioning trees: Matching, domination, and maximum diameter","volume":"10","author":"A Parley","year":"1981","journal-title":"International Journal of Computer & Information Sciences"},{"issue":"1","key":"pone.0221068.ref018","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1137\/0206012","article-title":"A Linear Tree Partitioning Algorithm","volume":"6","author":"S Kundu","year":"1977","journal-title":"SIAM Journal on Computing"},{"key":"pone.0221068.ref019","first-page":"57","article-title":"Some Probabilistic and Statistical Problems in the Analysis of DNA Sequences","volume":"17","author":"S Tavar\u00e9","year":"1986","journal-title":"Lectures on Mathematics in the Life Sciences"},{"issue":"1","key":"pone.0221068.ref020","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/sysbio\/18.1.1","article-title":"Quantitative Phyletics and the Evolution of Anurans","volume":"18","author":"AG Kluge","year":"1969","journal-title":"Systematic Biology"},{"issue":"951","key":"pone.0221068.ref021","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1086\/282802","article-title":"Estimating Phylogenetic Trees from Distance Matrices","volume":"106","author":"JS Farris","year":"1972","journal-title":"The American Naturalist"},{"issue":"1","key":"pone.0221068.ref022","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1186\/s13059-018-1450-0","article-title":"HmmUFOtu: An HMM and phylogenetic placement based ultra-fast taxonomic assignment and OTU picking tool for microbiome amplicon sequencing studies","volume":"19","author":"Q Zheng","year":"2018","journal-title":"Genome Biology"},{"key":"pone.0221068.ref023","article-title":"TreeSwift: a massively scalable Python tree package","author":"N Moshiri","year":"2018","journal-title":"bioRxiv"},{"issue":"10","key":"pone.0221068.ref024","doi-asserted-by":"crossref","first-page":"3219","DOI":"10.1128\/AEM.02810-10","article-title":"Assessing and Improving Methods Used in Operational Taxonomic Unit-Based Approaches for 16S rRNA Gene Sequence Analysis","volume":"77","author":"PD Schloss","year":"2011","journal-title":"Applied and Environmental Microbiology"},{"issue":"8","key":"pone.0221068.ref025","doi-asserted-by":"crossref","first-page":"e70837","DOI":"10.1371\/journal.pone.0070837","article-title":"A Comparison of Methods for Clustering 16S rRNA Sequences into OTUs","volume":"8","author":"W Chen","year":"2013","journal-title":"PLoS ONE"},{"key":"pone.0221068.ref026","article-title":"The SILVA ribosomal RNA gene database project: improved data processing and web-based tools","author":"C Quast","year":"2012","journal-title":"Nucleic acids research"},{"issue":"1","key":"pone.0221068.ref027","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1093\/nar\/29.1.173","article-title":"The RDP-II (Ribosomal Database Project)","volume":"29","author":"BL Maidak","year":"2001","journal-title":"Nucleic Acids Research"},{"issue":"7","key":"pone.0221068.ref028","doi-asserted-by":"crossref","first-page":"5069","DOI":"10.1128\/AEM.03006-05","article-title":"Greengenes, a Chimera-Checked 16S rRNA Gene Database and Workbench Compatible with ARB","volume":"72","author":"TZ DeSantis","year":"2006","journal-title":"Appl Environ Microbiol"},{"issue":"10","key":"pone.0221068.ref029","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1038\/s41592-018-0141-9","article-title":"Qiita: rapid, web-enabled microbiome meta-analysis","volume":"15","author":"A Gonzalez","year":"2018","journal-title":"Nature Methods"},{"issue":"2","key":"pone.0221068.ref030","doi-asserted-by":"crossref","DOI":"10.1128\/mSystems.00191-16","article-title":"Deblur Rapidly Resolves Single-Nucleotide Community Sequence Patterns","volume":"2","author":"A Amir","year":"2017","journal-title":"mSystems"},{"key":"pone.0221068.ref031","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":"BJ Callahan","year":"2016","journal-title":"Nature Methods"},{"key":"pone.0221068.ref032","article-title":"UNOISE2: improved error-correction for Illumina 16S and ITS amplicon sequencing","author":"RC Edgar","year":"2016","journal-title":"bioRxiv"},{"issue":"14","key":"pone.0221068.ref033","doi-asserted-by":"crossref","first-page":"e95","DOI":"10.1093\/nar\/gkr349","article-title":"ESPRIT-Tree: hierarchical clustering analysis of millions of 16S rRNA pyrosequences in quasilinear computational time","volume":"39","author":"Y Cai","year":"2011","journal-title":"Nucleic Acids Research"},{"issue":"13","key":"pone.0221068.ref034","doi-asserted-by":"crossref","first-page":"1658","DOI":"10.1093\/bioinformatics\/btl158","article-title":"Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences","volume":"22","author":"W Li","year":"2006","journal-title":"Bioinformatics"},{"issue":"1","key":"pone.0221068.ref035","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/ve\/vex042","article-title":"TreeTime: Maximum-likelihood phylodynamic analysis","volume":"4","author":"P Sagulenko","year":"2018","journal-title":"Virus Evolution"},{"issue":"9","key":"pone.0221068.ref036","doi-asserted-by":"crossref","first-page":"1312","DOI":"10.1093\/bioinformatics\/btu033","article-title":"RAxML version 8: A tool for phylogenetic analysis and post-analysis of large phylogenies","volume":"30","author":"A Stamatakis","year":"2014","journal-title":"Bioinformatics"},{"issue":"20","key":"pone.0221068.ref037","doi-asserted-by":"crossref","first-page":"10864","DOI":"10.1073\/pnas.93.20.10864","article-title":"Accurate reconstruction of a known HIV-1 transmission history by phylogenetic tree analysis","volume":"93","author":"T Leitner","year":"1996","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"8","key":"pone.0221068.ref038","doi-asserted-by":"crossref","first-page":"1135","DOI":"10.1093\/cid\/cis612","article-title":"Characterizing HIV transmission networks across the United States","volume":"55","author":"JL Aldous","year":"2012","journal-title":"Clinical infectious diseases: an official publication of the Infectious Diseases Society of America"},{"issue":"5","key":"pone.0221068.ref039","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1097\/00002030-200403260-00002","article-title":"HIV-1 pol gene variation is sufficient for reconstruction of transmissions in the era of antiretroviral therapy","volume":"18","author":"S Hu\u00e9","year":"2004","journal-title":"AIDS (London, England)"},{"issue":"9","key":"pone.0221068.ref040","doi-asserted-by":"crossref","first-page":"e1000590","DOI":"10.1371\/journal.ppat.1000590","article-title":"Molecular phylodynamics of the heterosexual HIV epidemic in the United Kingdom","volume":"5","author":"GJ Hughes","year":"2009","journal-title":"PLoS pathogens"},{"issue":"9","key":"pone.0221068.ref041","doi-asserted-by":"crossref","first-page":"1463","DOI":"10.1093\/infdis\/jir550","article-title":"Transmission network parameters estimated from HIV sequences for a nationwide epidemic","volume":"204","author":"AJ Leigh Brown","year":"2011","journal-title":"Journal of Infectious Diseases"},{"issue":"10","key":"pone.0221068.ref042","doi-asserted-by":"crossref","first-page":"1529","DOI":"10.1093\/infdis\/jis231","article-title":"Associations between phylogenetic clustering and HLA profile among HIV-infected individuals in San Diego, California","volume":"205","author":"SR Mehta","year":"2012","journal-title":"Journal of Infectious Diseases"},{"issue":"12","key":"pone.0221068.ref043","doi-asserted-by":"crossref","first-page":"1918","DOI":"10.1093\/infdis\/jir651","article-title":"Analysis of genetic linkage of HIV from couples enrolled in the HIV prevention trials network 052 trial","volume":"204","author":"SH Eshleman","year":"2011","journal-title":"Journal of Infectious Diseases"},{"issue":"13","key":"pone.0221068.ref044","doi-asserted-by":"crossref","first-page":"1967","DOI":"10.1097\/QAD.0000000000000383","article-title":"Phylogenetic analyses reveal HIV-1 infections between men misclassified as heterosexual transmissions","volume":"28","author":"S Hu\u00e9","year":"2014","journal-title":"Aids"},{"issue":"11","key":"pone.0221068.ref045","doi-asserted-by":"crossref","first-page":"e1001898","DOI":"10.1371\/journal.pmed.1001898","article-title":"Dispersion of the HIV-1 Epidemic in Men Who Have Sex with Men in the Netherlands: A Combined Mathematical Model and Phylogenetic Analysis","volume":"12","author":"D Bezemer","year":"2015","journal-title":"PLoS Medicine"},{"key":"pone.0221068.ref046","article-title":"Growth of HIV-1 Molecular Transmission Clusters in New York City","author":"JO Wertheim","year":"2018","journal-title":"The Journal of Infectious Diseases"},{"issue":"3","key":"pone.0221068.ref047","first-page":"512","article-title":"Estimation of the Number of Nucleotide Substitutions in the Control Region of Mitochondrial-DNA in Humans and Chimpanzees","volume":"10","author":"K Tamura","year":"1993","journal-title":"Molecular biology and evolution"},{"key":"pone.0221068.ref048","article-title":"FAVITES: simultaneous simulation of transmission networks, phylogenetic trees and sequences","author":"N Moshiri","year":"2018","journal-title":"Bioinformatics"},{"key":"pone.0221068.ref049","doi-asserted-by":"crossref","unstructured":"Mai U, Mirarab S. TreeShrink: Efficient Detection of Outlier Tree Leaves. In: Meidanis J, Nakhleh L, editors. Comparative Genomics: 15th International Workshop, RECOMB CG 2017, Barcelona, Spain, October 4-6, 2017, Proceedings. Cham: Springer International Publishing; 2017. p. 116\u2013140. Available from: https:\/\/doi.org\/10.1007\/978-3-319-67979-2_7.","DOI":"10.1007\/978-3-319-67979-2_7"},{"issue":"5934","key":"pone.0221068.ref050","doi-asserted-by":"crossref","first-page":"1561","DOI":"10.1126\/science.1171243","article-title":"Rapid and Accurate Large-Scale Coestimation of Sequence Alignments and Phylogenetic Trees","volume":"324","author":"K Liu","year":"2009","journal-title":"Science"},{"issue":"1","key":"pone.0221068.ref051","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1093\/sysbio\/syr095","article-title":"SATe-II: Very Fast and Accurate Simultaneous Estimation of Multiple Sequence Alignments and Phylogenetic Trees","volume":"61","author":"K Liu","year":"2011","journal-title":"Systematic Biology"},{"issue":"5","key":"pone.0221068.ref052","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1089\/cmb.2014.0156","article-title":"PASTA: ultra-large multiple sequence alignment for nucleotide and amino-acid sequences","volume":"22","author":"S Mirarab","year":"2015","journal-title":"Journal of Computational Biology"},{"issue":"1","key":"pone.0221068.ref053","first-page":"205","article-title":"A new generation of homology search tools based on probabilistic inference","volume":"23","author":"SR Eddy","year":"2009","journal-title":"Genome Inform"},{"issue":"4","key":"pone.0221068.ref054","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1093\/bib\/bbn013","article-title":"Recent developments in the MAFFT multiple sequence alignment program","volume":"9","author":"K Katoh","year":"2008","journal-title":"Brief Bioinform"},{"issue":"13","key":"pone.0221068.ref055","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1093\/bioinformatics\/btm226","article-title":"Multiple alignment by aligning alignments","volume":"23","author":"TJ Wheeler","year":"2007","journal-title":"Bioinformatics"},{"issue":"8","key":"pone.0221068.ref056","doi-asserted-by":"crossref","first-page":"989","DOI":"10.1093\/bioinformatics\/btt093","article-title":"Making automated multiple alignments of very large numbers of protein sequences","volume":"29","author":"F Sievers","year":"2013","journal-title":"Bioinformatics"},{"issue":"23","key":"pone.0221068.ref057","doi-asserted-by":"crossref","first-page":"3250","DOI":"10.1093\/bioinformatics\/btr553","article-title":"FastSP: linear time calculation of alignment accuracy","volume":"27","author":"S Mirarab","year":"2011","journal-title":"Bioinformatics"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pone.0221068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,9]],"date-time":"2020-05-09T02:46:49Z","timestamp":1588992409000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0221068"}},"subtitle":[],"editor":[{"given":"Serdar","family":"Bozdag","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2019,8,22]]},"references-count":57,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2019,8,22]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0221068","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/591388","asserted-by":"object"},{"id-type":"doi","id":"10.1101\/261354","asserted-by":"object"}]},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,22]]}}}