{"id":"https://openalex.org/W2785306095","doi":"https://doi.org/10.7287/peerj.preprints.3208v1","title":"Optimizing taxonomic classification of marker gene sequences","display_name":"Optimizing taxonomic classification of marker gene sequences","publication_year":2017,"publication_date":"2017-08-30","ids":{"openalex":"https://openalex.org/W2785306095","doi":"https://doi.org/10.7287/peerj.preprints.3208v1","mag":"2785306095"},"language":"en","primary_location":{"id":"doi:10.7287/peerj.preprints.3208v1","doi":"https://doi.org/10.7287/peerj.preprints.3208v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.3208v1","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.7287/peerj.preprints.3208v1","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000165682","display_name":"Nicholas A. Bokulich","orcid":"https://orcid.org/0000-0002-1784-8935","observed_orcids":["https://orcid.org/0000-0002-1784-8935"]},"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":"Nicholas A Bokulich","raw_affiliation_strings":["The Pathogen and Microbiome Institute, Northern Arizona University, Flagstaff, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pathogen and Microbiome Institute, Northern Arizona University, Flagstaff, AZ, USA","institution_ids":["https://openalex.org/I203172682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069233200","display_name":"Benjamin D. Kaehler","orcid":"https://orcid.org/0000-0002-5318-9551","observed_orcids":["https://orcid.org/0000-0002-5318-9551"]},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Benjamin D Kaehler","raw_affiliation_strings":["Research School of Biology, Australian National University, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research School of Biology, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jai Ram Rideout","raw_affiliation_strings":["The Pathogen and Microbiome Institute, Northern Arizona University, Flagstaff, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pathogen and Microbiome Institute, Northern Arizona University, Flagstaff, AZ, USA","institution_ids":["https://openalex.org/I203172682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044141437","display_name":"Matthew R. Dillon","orcid":"https://orcid.org/0000-0002-7713-1952","observed_orcids":["https://orcid.org/0000-0002-7713-1952"]},"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":"Matthew Dillon","raw_affiliation_strings":["The Pathogen and Microbiome Institute, Northern Arizona University, Flagstaff, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pathogen and Microbiome Institute, Northern Arizona University, Flagstaff, AZ, USA","institution_ids":["https://openalex.org/I203172682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014309302","display_name":"Evan K Bolyen","orcid":"https://orcid.org/0000-0002-5362-6782","observed_orcids":["https://orcid.org/0000-0002-5362-6782"]},"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":"Evan Bolyen","raw_affiliation_strings":["The Pathogen and Microbiome Institute, Northern Arizona University, Flagstaff, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pathogen and Microbiome Institute, Northern Arizona University, Flagstaff, AZ, USA","institution_ids":["https://openalex.org/I203172682"]}]},{"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/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rob Knight","raw_affiliation_strings":["Departments of Pediatrics and Computer Science & Engineering, and Center for Microbiome Innovation, University of California, San Diego, La Jolla, California, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departments of Pediatrics and Computer Science & Engineering, and Center for Microbiome Innovation, University of California, San Diego, La Jolla, California, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091335490","display_name":"Gavin A. Huttley","orcid":"https://orcid.org/0000-0001-7224-2074","observed_orcids":["https://orcid.org/0000-0001-7224-2074"]},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Gavin A. Huttley","raw_affiliation_strings":["Research School of Biology, Australian National University, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research School of Biology, Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"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, Arizona, United States","The Pathogen and Microbiome Institute, Northern Arizona University, Flagstaff, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, Northern Arizona University, Flagstaff, Arizona, United States","institution_ids":["https://openalex.org/I203172682"]},{"raw_affiliation_string":"The Pathogen and Microbiome Institute, Northern Arizona University, Flagstaff, AZ, USA","institution_ids":["https://openalex.org/I203172682"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8970000147819519,"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":0.8970000147819519,"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":0.03790000081062317,"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":0.031599998474121094,"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/taxonomic-classification","display_name":"taxonomic classification","score":0.9819999933242798},{"id":"https://openalex.org/keywords/tax-credits","display_name":"tax credits","score":0.7250000238418579},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.7870000004768372},{"id":"https://openalex.org/keywords/vsearch","display_name":"VSEARCH","score":0.8230000138282776},{"id":"https://openalex.org/keywords/rdp-classifier","display_name":"RDP classifier","score":0.6290000081062317},{"id":"https://openalex.org/keywords/blast","display_name":"BLAST","score":0.8130000233650208},{"id":"https://openalex.org/keywords/classifier-parameter-tuning","display_name":"classifier parameter tuning","score":0.7860000133514404},{"id":"https://openalex.org/keywords/microbiome-analysis","display_name":"microbiome analysis","score":0.8370000123977661}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7779328227043152},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.7038588523864746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6643410325050354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6527294516563416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.589504063129425},{"id":"https://openalex.org/C4924752","wikidata":"https://www.wikidata.org/wiki/Q184148","display_name":"Plug-in","level":2,"score":0.5741968154907227},{"id":"https://openalex.org/C185207860","wikidata":"https://www.wikidata.org/wiki/Q17004744","display_name":"Bayes classifier","level":4,"score":0.5454379916191101},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45549923181533813},{"id":"https://openalex.org/C139532973","wikidata":"https://www.wikidata.org/wiki/Q2679259","display_name":"Linear classifier","level":3,"score":0.4102247953414917},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.20464906096458435},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7287/peerj.preprints.3208v1","doi":"https://doi.org/10.7287/peerj.preprints.3208v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.3208v1","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"}],"best_oa_location":{"id":"doi:10.7287/peerj.preprints.3208v1","doi":"https://doi.org/10.7287/peerj.preprints.3208v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.3208v1","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2752925036","https://openalex.org/W2807194798","https://openalex.org/W226769816","https://openalex.org/W2886687368","https://openalex.org/W3173436219","https://openalex.org/W2100539938","https://openalex.org/W2800231416","https://openalex.org/W4384523012","https://openalex.org/W2612975255","https://openalex.org/W2897766421"],"abstract_inverted_index":{"Background.":[0],"Taxonomic":[1],"classification":[2,34,47],"of":[3,36,75,93],"marker-gene":[4],"sequences":[5],"is":[6],"an":[7],"important":[8],"step":[9],"in":[10],"microbiome":[11],"analysis.":[12],"Results.":[13],"We":[14,39],"present":[15],"q2-feature-classifier":[16,97],"(https://github.com/qiime2/q2-feature-classifier),":[17],"a":[18,91],"QIIME":[19],"2":[20],"plugin":[21],"containing":[22],"several":[23,43,54],"novel":[24],"machine-learning":[25,61],"and":[26,41,53,63,65,82,98],"alignment-based":[27,67],"taxonomy":[28],"classifiers":[29],"that":[30],"meet":[31],"or":[32],"exceed":[33],"accuracy":[35],"existing":[37],"methods.":[38],"evaluated":[40],"optimized":[42],"commonly":[44],"used":[45],"taxonomic":[46],"methods":[48,56],"(RDP,":[49],"BLAST,":[50],"BLAST+,":[51],"UCLUST)":[52],"new":[55],"(a":[57],"scikit-learn":[58],"naive":[59],"Bayes":[60],"classifier,":[62],"VSEARCH":[64],"SortMeRNA":[66],"methods).":[68],"Conclusions.":[69],"Our":[70],"results":[71],"illustrate":[72],"the":[73],"importance":[74],"parameter":[76,88],"tuning":[77],"for":[78,90],"optimizing":[79],"classifier":[80],"performance,":[81],"we":[83],"make":[84],"explicit":[85],"recommendations":[86],"regarding":[87],"choices":[89],"range":[92],"standard":[94],"operating":[95],"conditions.":[96],"our":[99],"evaluation":[100],"framework,":[101],"tax-credit,":[102],"are":[103],"both":[104],"free,":[105],"open-source,":[106],"BSD-licensed":[107],"packages":[108],"available":[109],"on":[110],"GitHub.":[111]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2018-02-02T00:00:00"}
