{"id":"https://openalex.org/W2136993578","doi":"https://doi.org/10.7717/peerj.545","title":"Subsampled open-reference clustering creates consistent, comprehensive OTU definitions and scales to billions of sequences","display_name":"Subsampled open-reference clustering creates consistent, comprehensive OTU definitions and scales to billions of sequences","publication_year":2014,"publication_date":"2014-08-21","ids":{"openalex":"https://openalex.org/W2136993578","doi":"https://doi.org/10.7717/peerj.545","mag":"2136993578","pmid":"https://pubmed.ncbi.nlm.nih.gov/25177538","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/4145071"},"language":"en","primary_location":{"id":"doi:10.7717/peerj.545","doi":"https://doi.org/10.7717/peerj.545","is_oa":true,"landing_page_url":"https://doi.org/10.7717/peerj.545","pdf_url":null,"source":{"id":"https://openalex.org/S1983995261","display_name":"PeerJ","issn_l":"2167-8359","issn":["2167-8359"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-d","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320104","host_organization_name":"PeerJ, Inc.","host_organization_lineage":["https://openalex.org/P4310320104"],"host_organization_lineage_names":["PeerJ, Inc."],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PeerJ","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.7717/peerj.545","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045260328","display_name":"Jai Ram Rideout","orcid":"https://orcid.org/0000-0003-2587-1454","observed_orcids":["https://orcid.org/0000-0003-2587-1454"]},"institutions":[{"id":"https://openalex.org/I203172682","display_name":"Northern Arizona University","ror":"https://ror.org/0272j5188","country_code":"US","type":"education","lineage":["https://openalex.org/I203172682"]},{"id":"https://openalex.org/I98704320","display_name":"Icahn School of Medicine at Mount Sinai","ror":"https://ror.org/04a9tmd77","country_code":"US","type":"education","lineage":["https://openalex.org/I1320796813","https://openalex.org/I98704320"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jai Ram Rideout","raw_affiliation_strings":["Center for Microbial Genetics and Genomics, Northern Arizona University, Flagstaff, AZ, USA","Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Microbial Genetics and Genomics, Northern Arizona University, Flagstaff, AZ, USA","institution_ids":["https://openalex.org/I203172682"]},{"raw_affiliation_string":"Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA","institution_ids":["https://openalex.org/I98704320"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057054017","display_name":"Yan He","orcid":"https://orcid.org/0000-0002-6611-2959","observed_orcids":["https://orcid.org/0000-0002-6611-2959"]},"institutions":[{"id":"https://openalex.org/I58200834","display_name":"Southern Medical University","ror":"https://ror.org/01vjw4z39","country_code":"CN","type":"education","lineage":["https://openalex.org/I58200834"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan He","raw_affiliation_strings":["School of Public Health and Tropical Medicine, Southern Medical University, Guangzhou, Guangdong, China","State Key Laboratory of Organ Failure Prevention, and Department of Environmental Health, School of Public Health and Tropical Medicine, Southern Medical University, Guangzhou, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Public Health and Tropical Medicine, Southern Medical University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I58200834"]},{"raw_affiliation_string":"State Key Laboratory of Organ Failure Prevention, and Department of Environmental Health, School of Public Health and Tropical Medicine, Southern Medical University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I58200834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007031983","display_name":"Jose Antonio Navas-Molina","orcid":"https://orcid.org/0000-0003-4595-920X","observed_orcids":["https://orcid.org/0000-0003-4595-920X"]},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jose Antonio Navas-Molina","raw_affiliation_strings":["Department of Computer Science, University of Colorado Boulder, Boulder, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Colorado Boulder, Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025148058","display_name":"William Anton Walters","orcid":"https://orcid.org/0000-0003-1716-3984","observed_orcids":["https://orcid.org/0000-0003-1716-3984"]},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William A Walters","raw_affiliation_strings":["Department of Molecular, Cellular, and Developmental Biology, University of Colorado at Boulder, Boulder, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Molecular, Cellular, and Developmental Biology, University of Colorado at Boulder, Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026752463","display_name":"Luke K. Ursell","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luke K Ursell","raw_affiliation_strings":["Department of Chemistry and Biochemistry, University of Colorado Boulder, Boulder, CO, USA","Department of Chemistry and Biochemistry, University of Colorado at Boulder, Boulder, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Biochemistry, University of Colorado Boulder, Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]},{"raw_affiliation_string":"Department of Chemistry and Biochemistry, University of Colorado at Boulder, Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064118261","display_name":"Sean M. Gibbons","orcid":"https://orcid.org/0000-0002-8724-7916","observed_orcids":["https://orcid.org/0000-0002-8724-7916"]},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean M Gibbons","raw_affiliation_strings":["Graduate Program in Biophysical Sciences, University of Chicago, Chicago, IL, U.S.A","Institute for Genomics and Systems Biology, Argonne National Laboratory, Lemont, IL, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Program in Biophysical Sciences, University of Chicago, Chicago, IL, U.S.A","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"Institute for Genomics and Systems Biology, Argonne National Laboratory, Lemont, IL, U.S.A","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104274724","display_name":"John Chase","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I203172682","display_name":"Northern Arizona University","ror":"https://ror.org/0272j5188","country_code":"US","type":"education","lineage":["https://openalex.org/I203172682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H Chase","raw_affiliation_strings":["Department of Biological Sciences, Northern Arizona University, Flagstaff, AZ, United States","Department of Biological Sciences, Northern Arizona University, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, Northern Arizona University, Flagstaff, AZ, United States","institution_ids":["https://openalex.org/I203172682"]},{"raw_affiliation_string":"Department of Biological Sciences, Northern Arizona University, AZ, USA","institution_ids":["https://openalex.org/I203172682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022461817","display_name":"Daniel T. McDonald","orcid":"https://orcid.org/0000-0003-0876-9060","observed_orcids":["https://orcid.org/0000-0003-0876-9060"]},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel McDonald","raw_affiliation_strings":["Department of Computer Science, University of Colorado Boulder, Boulder, CO, USA","BioFrontiers Institute, University of Colorado at Boulder, Boulder, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Colorado Boulder, Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]},{"raw_affiliation_string":"BioFrontiers Institute, University of Colorado at Boulder, Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Antonio Gonzalez","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio Gonzalez","raw_affiliation_strings":["BioFrontiers Institute, University of Colorado at Boulder, Boulder, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BioFrontiers Institute, University of Colorado at Boulder, Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032960228","display_name":"Adam Robbins\u2010Pianka","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Robbins-Pianka","raw_affiliation_strings":["BioFrontiers Institute, University of Colorado at Boulder, Boulder, CO, USA","Department of Computer Science, University of Colorado Boulder, Boulder, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BioFrontiers Institute, University of Colorado at Boulder, Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]},{"raw_affiliation_string":"Department of Computer Science, University of Colorado Boulder, Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049747447","display_name":"Jos\u00e9 C. Clemente","orcid":"https://orcid.org/0000-0002-3970-9856","observed_orcids":["https://orcid.org/0000-0002-3970-9856"]},"institutions":[{"id":"https://openalex.org/I98704320","display_name":"Icahn School of Medicine at Mount Sinai","ror":"https://ror.org/04a9tmd77","country_code":"US","type":"education","lineage":["https://openalex.org/I1320796813","https://openalex.org/I98704320"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jose C Clemente","raw_affiliation_strings":["Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA","institution_ids":["https://openalex.org/I98704320"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057060580","display_name":"Jack A. Gilbert","orcid":"https://orcid.org/0000-0001-7920-7001","observed_orcids":["https://orcid.org/0000-0001-7920-7001"]},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Gilbert","raw_affiliation_strings":["Department of Ecology and Evolution, University of Chicago, Chicago, Illinois, USA","Institute for Genomics and Systems Biology, Argonne National Laboratory, Lemont, IL, U.S.A","Department of Ecology and Evolution, University of Chicago, Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Ecology and Evolution, University of Chicago, Chicago, Illinois, USA","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"Institute for Genomics and Systems Biology, Argonne National Laboratory, Lemont, IL, U.S.A","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Department of Ecology and Evolution, University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111844800","display_name":"Susan M. Huse","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Susan M Huse","raw_affiliation_strings":["Department of Pathology and Laboratory Medicine, Brown University, Providence, RI, USA","Department of Pathology and Laboratory Science, Warren Alpert Medical School, Brown University, Providence, RI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pathology and Laboratory Medicine, Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]},{"raw_affiliation_string":"Department of Pathology and Laboratory Science, Warren Alpert Medical School, Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100518876","display_name":"Hong-Wei Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I58200834","display_name":"Southern Medical University","ror":"https://ror.org/01vjw4z39","country_code":"CN","type":"education","lineage":["https://openalex.org/I58200834"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong-Wei Zhou","raw_affiliation_strings":["School of Public Health and Tropical Medicine, Southern Medical University, Guangzhou, Guangdong, China","State Key Laboratory of Organ Failure Prevention, and Department of Environmental Health, School of Public Health and Tropical Medicine, Southern Medical University, Guangzhou, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Public Health and Tropical Medicine, Southern Medical University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I58200834"]},{"raw_affiliation_string":"State Key Laboratory of Organ Failure Prevention, and Department of Environmental Health, School of Public Health and Tropical Medicine, Southern Medical University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I58200834"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033881627","display_name":"Rob D. Knight","orcid":"https://orcid.org/0000-0002-0975-9019","observed_orcids":["https://orcid.org/0000-0002-0975-9019","https://orcid.org/0000-0001-7531-0087"]},"institutions":[{"id":"https://openalex.org/I1344073410","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90","country_code":"US","type":"facility","lineage":["https://openalex.org/I1344073410"]},{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rob Knight","raw_affiliation_strings":["BioFrontiers Institute, University of Colorado at Boulder, Boulder, CO, USA","Howard Hughes Medical Institute, Boulder, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BioFrontiers Institute, University of Colorado at Boulder, Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]},{"raw_affiliation_string":"Howard Hughes Medical Institute, Boulder, CO, USA","institution_ids":["https://openalex.org/I1344073410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038626201","display_name":"J. Gregory Caporaso","orcid":"https://orcid.org/0000-0002-8865-1670","observed_orcids":["https://orcid.org/0000-0002-8865-1670"]},"institutions":[{"id":"https://openalex.org/I203172682","display_name":"Northern Arizona University","ror":"https://ror.org/0272j5188","country_code":"US","type":"education","lineage":["https://openalex.org/I203172682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J Gregory Caporaso","raw_affiliation_strings":["Department of Biological Sciences, Northern Arizona University, Flagstaff, AZ, United States","Center for Microbial Genetics and Genomics, Northern Arizona University, Flagstaff, AZ, USA","Department of Biological Sciences, Northern Arizona University, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, Northern Arizona University, Flagstaff, AZ, United States","institution_ids":["https://openalex.org/I203172682"]},{"raw_affiliation_string":"Center for Microbial Genetics and Genomics, Northern Arizona University, Flagstaff, AZ, USA","institution_ids":["https://openalex.org/I203172682"]},{"raw_affiliation_string":"Department of Biological Sciences, Northern Arizona University, AZ, USA","institution_ids":["https://openalex.org/I203172682"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1395,"currency":"USD","value_usd":1395},"apc_paid":{"value":1395,"currency":"USD","value_usd":1395},"fwci":22.5244,"has_fulltext":false,"cited_by_count":549,"citation_normalized_percentile":{"value":0.99776239,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"2","issue":null,"first_page":"e545","last_page":"e545"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8550000190734863,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8550000190734863,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.10890000313520432,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12640","display_name":"Environmental DNA in Biodiversity Studies","score":0.009100000374019146,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/subsampling","display_name":"subsampling","score":0.8199999928474426},{"id":"https://openalex.org/keywords/operational-taxonomic-units","display_name":"operational taxonomic units","score":0.8889999985694885},{"id":"https://openalex.org/keywords/16s-rrna","display_name":"16S rRNA","score":0.8320000171661377},{"id":"https://openalex.org/keywords/qiime","display_name":"QIIME","score":0.8840000033378601},{"id":"https://openalex.org/keywords/parallel-clustering","display_name":"parallel clustering","score":0.5379999876022339},{"id":"https://openalex.org/keywords/amplicon-sequence-variants","display_name":"amplicon sequence variants","score":0.7250000238418579},{"id":"https://openalex.org/keywords/earth-microbiome-project","display_name":"Earth Microbiome Project","score":0.9020000100135803},{"id":"https://openalex.org/keywords/microbial-community-analysis","display_name":"microbial community analysis","score":0.7639999985694885},{"id":"https://openalex.org/keywords/parameter-setting","display_name":"parameter setting","score":0.4729999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6494003534317017},{"id":"https://openalex.org/C2779825944","wikidata":"https://www.wikidata.org/wiki/Q7097792","display_name":"Operational taxonomic unit","level":4,"score":0.6221450567245483},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5983561873435974},{"id":"https://openalex.org/C2993206177","wikidata":"https://www.wikidata.org/wiki/Q2844457","display_name":"Amplicon sequencing","level":4,"score":0.5781190991401672},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5262559652328491},{"id":"https://openalex.org/C8185291","wikidata":"https://www.wikidata.org/wiki/Q2844457","display_name":"Amplicon","level":4,"score":0.5208926200866699},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.4737095236778259},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4493251442909241},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4268481135368347},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3629149794578552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2955520749092102},{"id":"https://openalex.org/C42062724","wikidata":"https://www.wikidata.org/wiki/Q1209205","display_name":"16S ribosomal RNA","level":3,"score":0.22319379448890686},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.20192188024520874},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10174867510795593},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0866093635559082},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.07881233096122742},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.0},{"id":"https://openalex.org/C49105822","wikidata":"https://www.wikidata.org/wiki/Q176996","display_name":"Polymerase chain reaction","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":10,"locations":[{"id":"doi:10.7717/peerj.545","doi":"https://doi.org/10.7717/peerj.545","is_oa":true,"landing_page_url":"https://doi.org/10.7717/peerj.545","pdf_url":null,"source":{"id":"https://openalex.org/S1983995261","display_name":"PeerJ","issn_l":"2167-8359","issn":["2167-8359"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-d","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320104","host_organization_name":"PeerJ, Inc.","host_organization_lineage":["https://openalex.org/P4310320104"],"host_organization_lineage_names":["PeerJ, Inc."],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PeerJ","raw_type":"journal-article"},{"id":"doi:10.7287/peerj.preprints.411","doi":"https://doi.org/10.7287/peerj.preprints.411","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.411","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"doi:10.7287/peerj.preprints.411v2","doi":"https://doi.org/10.7287/peerj.preprints.411v2","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.411v2","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmh:oai:europepmc.org:3113397","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4145071","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:4145071","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4145071","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PeerJ","raw_type":"Text"},{"id":"pmid:25177538","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25177538","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PeerJ","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:043dcb23f6bc48569887bfb4c47a95f4","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/043dcb23f6bc48569887bfb4c47a95f4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PeerJ, Vol 2, p e545 (2014)","raw_type":"article"},{"id":"pmh:oai:escholarship.org/ark:/13030/qt68m59020","doi":null,"is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/68m59020","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PeerJ, vol 2, iss 1","raw_type":"article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt68m59020","doi":null,"is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/68m59020","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PeerJ, vol 2, iss 1","raw_type":"article"},{"id":"pmh:qt68m59020","doi":null,"is_oa":false,"landing_page_url":"http://www.escholarship.org/uc/item/68m59020","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Rideout, JR; He, Y; Navas-Molina, JA; Walters, WA; Ursell, LK; Gibbons, SM; \u00c2\u00a0et al.(2014). Subsampled open-reference clustering creates consistent, comprehensive OTU definitions and scales to billions of sequences. PeerJ, 2014(1). doi: 10.7717/peerj.545. UC San Diego: Retrieved from: http://www.escholarship.org/uc/item/68m59020","raw_type":"article"}],"best_oa_location":{"id":"doi:10.7717/peerj.545","doi":"https://doi.org/10.7717/peerj.545","is_oa":true,"landing_page_url":"https://doi.org/10.7717/peerj.545","pdf_url":null,"source":{"id":"https://openalex.org/S1983995261","display_name":"PeerJ","issn_l":"2167-8359","issn":["2167-8359"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-d","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320104","host_organization_name":"PeerJ, Inc.","host_organization_lineage":["https://openalex.org/P4310320104"],"host_organization_lineage_names":["PeerJ, Inc."],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PeerJ","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6484898272","display_name":"Predoctoral Training in Signaling and Cellular Regulation","funder_award_id":"T32GM008759","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G9000909076","display_name":"Predoctoral Training Program in Signaling and Cellular Regulation","funder_award_id":"T32GM142607","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W30236741","https://openalex.org/W1988925586","https://openalex.org/W1989889539","https://openalex.org/W1996764654","https://openalex.org/W2057284376","https://openalex.org/W2072970694","https://openalex.org/W2112348586","https://openalex.org/W2115921802","https://openalex.org/W2124351063","https://openalex.org/W2126218947","https://openalex.org/W2127602818","https://openalex.org/W2130731460","https://openalex.org/W2151186216","https://openalex.org/W2154026962","https://openalex.org/W2156125289","https://openalex.org/W2156619206","https://openalex.org/W2162088497","https://openalex.org/W2166655850","https://openalex.org/W2170024099","https://openalex.org/W4241122026"],"related_works":["https://openalex.org/W21003693","https://openalex.org/W4225733754","https://openalex.org/W4407633229","https://openalex.org/W2951971263","https://openalex.org/W2909311619","https://openalex.org/W6889327659","https://openalex.org/W2293106314","https://openalex.org/W1846216853","https://openalex.org/W4285886359","https://openalex.org/W3133889526"],"abstract_inverted_index":{"We":[0,109,172],"present":[1,277],"a":[2,62,253,278],"performance-optimized":[3],"algorithm,":[4],"subsampled":[5,175,244],"open-reference":[6,82,87,103,176,190,245],"OTU":[7,38,51,83,88,104,143,170,177,191,246,272,285,317],"picking,":[8,84],"for":[9,27,122,215,293],"assigning":[10],"marker":[11],"gene":[12],"(e.g.,":[13,251],"16S":[14,130],"rRNA)":[15],"sequences":[16],"generated":[17,187],"on":[18,91,98,195,291],"next-generation":[19],"sequencing":[20],"platforms":[21],"to":[22,80,116,267,297],"operational":[23],"taxonomic":[24],"units":[25],"(OTUs)":[26],"microbial":[28],"community":[29],"analysis.":[30],"This":[31],"algorithm":[32,73,154,203],"provides":[33],"benefits":[34],"over":[35],"de":[36],"novo":[37],"picking":[39,52,89,144,178,192,247,273,286,318],"(clustering":[40],"can":[41,74,310],"be":[42,75,164,260],"performed":[43,221],"largely":[44],"in":[45,77,156,206,235,252,283,319],"parallel,":[46],"reducing":[47,301],"runtime)":[48],"and":[49,148,288],"closed-reference":[50],"(all":[53],"reads":[54],"are":[55,182],"clustered,":[56],"not":[57],"only":[58],"those":[59,186],"that":[60,111,151,174,181,239],"match":[61],"reference":[63,169],"database":[64],"sequence":[65,94],"with":[66,185],"high":[67],"similarity).":[68],"Because":[69],"more":[70],"of":[71,136,166,201,243,249,270,280,304,315],"our":[72,137,152,236],"run":[76,145],"parallel":[78],"relative":[79],"\"classic\"":[81,102,167,189],"it":[85,115],"makes":[86],"tractable":[90],"massive":[92],"amplicon":[93],"data":[95,100],"sets":[96],"(though":[97],"smaller":[99],"sets,":[101],"clustering":[105],"is":[106,140,204],"often":[107],"faster).":[108],"illustrate":[110],"here":[112],"by":[113,188,231],"applying":[114],"the":[117,123,134,141,160,207,232,302,305,313],"first":[118],"15,000":[119],"samples":[120],"sequenced":[121],"Earth":[124],"Microbiome":[125],"Project":[126],"(1.3":[127],"billion":[128],"V4":[129],"rRNA":[131],"amplicons).":[132],"To":[133],"best":[135],"knowledge,":[138],"this":[139,202],"largest":[142],"ever":[146],"performed,":[147],"we":[149,227,276],"estimate":[150],"new":[153],"runs":[155],"less":[157],"than":[158,162],"1/5":[159],"time":[161],"would":[163],"required":[165],"open":[168],"picking.":[171],"show":[173],"yields":[179],"results":[180],"highly":[183],"correlated":[184],"through":[193],"comparisons":[194],"three":[196],"well-studied":[197],"datasets.":[198],"An":[199],"implementation":[200,242],"provided":[205],"popular":[208],"QIIME":[209,250],"software":[210],"package,":[211],"which":[212],"uses":[213],"uclust":[214,224],"read":[216],"clustering.":[217],"All":[218],"analyses":[219,264],"were":[220],"using":[222],"QIIME's":[223,284],"wrappers,":[225],"though":[226],"provide":[228],"details":[229],"(aided":[230],"open-source":[233],"code":[234],"GitHub":[237],"repository)":[238],"will":[240],"allow":[241],"independently":[248],"compiled":[254],"programming":[255],"language,":[256],"where":[257],"runtimes":[258],"should":[259,265],"further":[261],"reduced).":[262],"Our":[263],"generalize":[266],"other":[268],"implementations":[269],"these":[271,294],"algorithms.":[274],"Finally,":[275],"comparison":[279],"parameter":[281],"settings":[282,292],"workflows":[287],"make":[289],"recommendations":[290],"free":[295],"parameters":[296,309],"optimize":[298],"runtime":[299,314],"without":[300],"quality":[303],"results.":[306],"These":[307],"optimized":[308],"vastly":[311],"decrease":[312],"uclust-based":[316],"QIIME.":[320]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":32},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":55},{"year":2020,"cited_by_count":72},{"year":2019,"cited_by_count":79},{"year":2018,"cited_by_count":75},{"year":2017,"cited_by_count":87},{"year":2016,"cited_by_count":59},{"year":2015,"cited_by_count":31},{"year":2014,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}