{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T22:30:04Z","timestamp":1778884204006,"version":"3.51.4"},"reference-count":40,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2017,1,31]],"date-time":"2017-01-31T00:00:00Z","timestamp":1485820800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/about_us\/legal\/notices"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61503314"],"award-info":[{"award-number":["61503314"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61561146396"],"award-info":[{"award-number":["61561146396"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61203282"],"award-info":[{"award-number":["61203282"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua TNLIST Big Data Grant"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,5,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Combining a 16S rRNA (16S) gene database with metagenomic shotgun sequences promises unbiased identification of known and novel microbes.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>To achieve this, we herein report reference-based ribosome assembly (RAMBL), a computational pipeline, which integrates taxonomic tree search and Dirichlet process clustering to reconstruct full-length 16S gene sequences from metagenomic sequencing data with high accuracy. By benchmarking against the synthetic and real shotgun sequences, we demonstrated that full-length 16S gene assemblies of RAMBL were a good proxy for known and putative microbes, including Candidate Phyla Radiation. We found that 30\u201340% of bacteria genera in the terrestrial and intestinal biomes have no closely related genome sequences. We also observed that RAMBL was able to generate a more accurate determination of environmental microbial diversity and yield better disease classification, suggesting that full-length 16S gene assemblies are a powerful alternative to marker gene set and 16S short reads. RAMBL first realizes the access to full-length 16S gene sequences in the near-terabase-scale metagenomic shotgun sequences, which markedly improve metagenomic data analysis and interpretation.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and Implementation<\/jats:title>\n                  <jats:p>RAMBL is available at https:\/\/github.com\/homopolymer\/RAMBL for academic use.<\/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\/btx018","type":"journal-article","created":{"date-parts":[[2017,1,30]],"date-time":"2017-01-30T13:28:22Z","timestamp":1485782902000},"page":"1447-1456","source":"Crossref","is-referenced-by-count":15,"title":["Large-scale 16S gene assembly using metagenomics shotgun sequences"],"prefix":"10.1093","volume":"33","author":[{"given":"Feng","family":"Zeng","sequence":"first","affiliation":[{"name":"Department of Automation, Xiamen University, Xiamen, Fujian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zicheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Bioinformatics Division, TNLIST and Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Automation, Xiamen University, Xiamen, Fujian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jizhong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute for Environmental Genomics and Department of Microbiology and Plant Biology, University of Oklahoma, Norman, OK, USA"},{"name":"State Key Joint Laboratory of Environment Simulation and Pollution Control, School of Environment, Tsinghua University, Beijing, China"},{"name":"Earth Science Division, Lawrence Berkeley National Laboratory, Berkeley, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Chen","sequence":"additional","affiliation":[{"name":"Bioinformatics Division, TNLIST, and Department of Computer Science and Technology, Tsinghua University, Beijing, China"},{"name":"Program in Computational Biology and Bioinformatics, University of Southern California, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2017,1,31]]},"reference":[{"key":"2023020205111749300_btx018-B1","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":"Caporaso","year":"2010","journal-title":"Nat. Methods"},{"key":"2023020205111749300_btx018-B2","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1016\/j.mimet.2007.02.005","article-title":"A detailed analysis of 16S ribosomal RNA gene segments for the diagnosis of pathogenic bacteria","volume":"69","author":"Chakravorty","year":"2007","journal-title":"J. Microbiol. Methods"},{"key":"2023020205111749300_btx018-B3","doi-asserted-by":"crossref","first-page":"D633","DOI":"10.1093\/nar\/gkt1244","article-title":"Ribosomal Database Project: data and tools for high throughput rRNA analysis","volume":"42","author":"Cole","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2023020205111749300_btx018-B4","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":"DeSantis","year":"2006","journal-title":"Appl. Environ. Microbiol"},{"key":"2023020205111749300_btx018-B5","doi-asserted-by":"crossref","first-page":"1792","DOI":"10.1093\/nar\/gkh340","article-title":"MUSCLE: multiple sequence alignment with high accuracy and high throughput","volume":"32","author":"Edgar","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2023020205111749300_btx018-B6","doi-asserted-by":"crossref","first-page":"15032.","DOI":"10.1038\/nmicrobiol.2015.32","article-title":"Metagenomics uncovers gaps in amplicon-based detection of microbial diversity","author":"Eloe-Fadrosh","year":"2016","journal-title":"Nat. Microbiol"},{"key":"2023020205111749300_btx018-B7","doi-asserted-by":"crossref","first-page":"21390","DOI":"10.1073\/pnas.1215210110","article-title":"Cross-biome metagenomic analyses of soil microbial communities and their functional attributes","volume":"109","author":"Fierer","year":"2012","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023020205111749300_btx018-B8","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1073\/pnas.0507535103","article-title":"The diversity and biogeography of soil bacterial communities","volume":"103","author":"Fierer","year":"2006","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023020205111749300_btx018-B9","doi-asserted-by":"crossref","first-page":"1740","DOI":"10.1016\/j.celrep.2014.04.055","article-title":"High-definition reconstruction of clonal composition in cancer","volume":"7","author":"Fischer","year":"2014","journal-title":"Cell Rep"},{"key":"2023020205111749300_btx018-B10","doi-asserted-by":"crossref","first-page":"e41294.","DOI":"10.1371\/journal.pone.0041294","article-title":"The \u2018Most Wanted\u2019 taxa from the human microbiome for whole genome sequencing","volume":"7","author":"Fodor","year":"2012","journal-title":"PLoS One"},{"key":"2023020205111749300_btx018-B11","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1038\/nrmicro3451","article-title":"Sequencing and beyond: integrating molecular \u2018omics\u2019 for microbial community profiling","volume":"13","author":"Franzosa","year":"2015","journal-title":"Nat. Rev. Microbiol"},{"key":"2023020205111749300_btx018-B12","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1101\/gr.112730.110","article-title":"Chimeric 16S rRNA sequence formation and detection in Sanger and 454-pyrosequenced PCR amplicons","volume":"21","author":"Haas","year":"2011","journal-title":"Genome Res"},{"key":"2023020205111749300_btx018-B13","author":"Holtgrewe","year":"2010"},{"key":"2023020205111749300_btx018-B14","doi-asserted-by":"crossref","first-page":"84.","DOI":"10.3389\/fcimb.2015.00084","article-title":"Insights into the role of erysipelotrichaceae in the human host","volume":"5","author":"Kaakoush","year":"2015","journal-title":"Front. Cell. Infect. Microbiol"},{"key":"2023020205111749300_btx018-B15","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1093\/nar\/29.1.181","article-title":"rrndb: the ribosomal RNA operon copy number database","volume":"29","author":"Klappenbach","year":"2001","journal-title":"Nucleic Acids Res"},{"key":"2023020205111749300_btx018-B16","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/nmeth.1923","article-title":"Fast gapped-read alignment with Bowtie 2","volume":"9","author":"Langmead","year":"2012","journal-title":"Nat. Methods"},{"key":"2023020205111749300_btx018-B17","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1093\/bioinformatics\/18.3.452","article-title":"Multiple sequence alignment using partial order graphs","volume":"18","author":"Lee","year":"2002","journal-title":"Bioinformatics"},{"key":"2023020205111749300_btx018-B18","doi-asserted-by":"crossref","first-page":"2078","DOI":"10.1093\/bioinformatics\/btp352","article-title":"The Sequence Alignment\/Map format and SAMtools","volume":"25","author":"Li","year":"2009","journal-title":"Bioinformatics"},{"key":"2023020205111749300_btx018-B19","doi-asserted-by":"crossref","first-page":"R44.","DOI":"10.1186\/gb-2011-12-5-r44","article-title":"EMIRGE: reconstruction of full-length ribosomal genes from microbial community short read sequencing data","volume":"12","author":"Miller","year":"2011","journal-title":"Genome Biol"},{"key":"2023020205111749300_btx018-B20","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":"2023020205111749300_btx018-B21","doi-asserted-by":"crossref","first-page":"822","DOI":"10.1038\/nbt.2939","article-title":"Identification and assembly of genomes and genetic elements in complex metagenomic samples without using reference genomes","volume":"32","author":"Nielsen","year":"2014","journal-title":"Nat. Biotechnol"},{"key":"2023020205111749300_btx018-B22","first-page":"847","author":"Paisley","year":"2010"},{"key":"2023020205111749300_btx018-B23","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1093\/molbev\/msp077","article-title":"FastTree: computing large minimum evolution trees with profiles instead of a distance matrix","volume":"26","author":"Price","year":"2009","journal-title":"Mol. Biol. Evol"},{"key":"2023020205111749300_btx018-B24","doi-asserted-by":"crossref","first-page":"7188","DOI":"10.1093\/nar\/gkm864","article-title":"SILVA: a comprehensive online resource for quality checked and aligned ribosomal RNA sequence data compatible with ARB","volume":"35","author":"Pruesse","year":"2007","journal-title":"Nucleic Acids Res"},{"key":"2023020205111749300_btx018-B25","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1038\/nature08821","article-title":"A human gut microbial gene catalogue established by metagenomic sequencing","volume":"464","author":"Qin","year":"2010","journal-title":"Nature"},{"key":"2023020205111749300_btx018-B26","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1038\/nature11450","article-title":"A metagenome-wide association study of gut microbiota in type 2 diabetes","volume":"490","author":"Qin","year":"2012","journal-title":"Nature"},{"key":"2023020205111749300_btx018-B27","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1038\/nature11711","article-title":"Genomic variation landscape of the human gut microbiome","volume":"493","author":"Schloissnig","year":"2013","journal-title":"Nature"},{"key":"2023020205111749300_btx018-B28","doi-asserted-by":"crossref","first-page":"1057","DOI":"10.1126\/science.1247023","article-title":"Genomes from Metagenomics","volume":"342","author":"Sharon","year":"2013","journal-title":"Science (80-.)"},{"key":"2023020205111749300_btx018-B29","doi-asserted-by":"crossref","DOI":"10.1038\/ismej.2015.249","article-title":"High-resolution phylogenetic microbial community profiling","author":"Singer","year":"2016","journal-title":"ISME J"},{"key":"2023020205111749300_btx018-B30","doi-asserted-by":"crossref","first-page":"e89323.","DOI":"10.1371\/journal.pone.0089323","article-title":"Parallel-META 2.0: enhanced metagenomic data analysis with functional annotation, high performance computing and advanced visualization","volume":"9","author":"Su","year":"2014","journal-title":"PLoS One"},{"key":"2023020205111749300_btx018-B31","doi-asserted-by":"crossref","first-page":"1196","DOI":"10.1038\/nmeth.2693","article-title":"Metagenomic species profiling using universal phylogenetic marker genes","volume":"10","author":"Sunagawa","year":"2013","journal-title":"Nat. Methods"},{"key":"2023020205111749300_btx018-B32","doi-asserted-by":"crossref","first-page":"1261359.","DOI":"10.1126\/science.1261359","article-title":"Ocean plankton. Structure and function of the global ocean microbiome","volume":"348","author":"Sunagawa","year":"2015","journal-title":"Science"},{"key":"2023020205111749300_btx018-B33","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1038\/nature11209","article-title":"A framework for human microbiome research","volume":"486","author":"Consortium","year":"2012","journal-title":"Nature"},{"key":"2023020205111749300_btx018-B34","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1089\/cmb.2012.0232","article-title":"Probabilistic inference of viral quasispecies subject to recombination","volume":"20","author":"T\u00f6pfer","year":"2013","journal-title":"J. Comput. Biol"},{"key":"2023020205111749300_btx018-B35","doi-asserted-by":"crossref","first-page":"902","DOI":"10.1038\/nmeth.3589","article-title":"MetaPhlAn2 for enhanced metagenomic taxonomic profiling","volume":"12","author":"Truong","year":"2015","journal-title":"Nat. Methods"},{"key":"2023020205111749300_btx018-B36","doi-asserted-by":"crossref","first-page":"832","DOI":"10.1038\/ismej.2014.179","article-title":"Diet is a major factor governing the fecal butyrate-producing community structure across Mammalia, Aves and Reptilia","volume":"9","author":"Vital","year":"2015","journal-title":"ISME J"},{"key":"2023020205111749300_btx018-B37","doi-asserted-by":"crossref","first-page":"5261","DOI":"10.1128\/AEM.00062-07","article-title":"Naive Bayesian classifier for rapid assignment of rRNA sequences into the new bacterial taxonomy","volume":"73","author":"Wang","year":"2007","journal-title":"Appl. Environ. Microbiol"},{"key":"2023020205111749300_btx018-B38","doi-asserted-by":"crossref","first-page":"i35","DOI":"10.1093\/bioinformatics\/btv231","article-title":"Reconstructing 16S rRNA genes in metagenomic data","volume":"31","author":"Yuan","year":"2015","journal-title":"Bioinformatics"},{"key":"2023020205111749300_btx018-B39","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1089\/10665270050081478","article-title":"A greedy algorithm for aligning DNA sequences","volume":"7","author":"Zhang","year":"2000","journal-title":"J. Comput. Biol"},{"key":"2023020205111749300_btx018-B40","doi-asserted-by":"crossref","first-page":"e02288","DOI":"10.1128\/mBio.02288-14","article-title":"High-throughput metagenomic technologies for complex microbial community analysis: open and closed formats","volume":"6","author":"Zhou","year":"2015","journal-title":"MBio"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/10\/1447\/49039091\/bioinformatics_33_10_1447.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/10\/1447\/49039091\/bioinformatics_33_10_1447.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T05:18:00Z","timestamp":1675315080000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/33\/10\/1447\/2964788"}},"subtitle":[],"editor":[{"given":"John","family":"Hancock","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2017,1,31]]},"references-count":40,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2017,5,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btx018","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2017,5,15]]},"published":{"date-parts":[[2017,1,31]]}}}