{"id":"https://openalex.org/W4241364434","doi":"https://doi.org/10.7287/peerj.preprints.934v1","title":"A standardized, extensible framework for optimizing classification improves marker-gene taxonomic assignments","display_name":"A standardized, extensible framework for optimizing classification improves marker-gene taxonomic assignments","publication_year":2015,"publication_date":"2015-03-27","ids":{"openalex":"https://openalex.org/W4241364434","doi":"https://doi.org/10.7287/peerj.preprints.934v1"},"language":"en","primary_location":{"id":"doi:10.7287/peerj.preprints.934v1","doi":"https://doi.org/10.7287/peerj.preprints.934v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.934v1","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","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.7287/peerj.preprints.934v1","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/I4210086933","display_name":"NYU Langone Health","ror":"https://ror.org/005dvqh91","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210086933"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas A Bokulich","raw_affiliation_strings":["Department of Medicine, New York University Langone Medical Center, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medicine, New York University Langone Medical Center, New York, NY, USA","institution_ids":["https://openalex.org/I4210086933"]}]},{"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":["Center for Microbial Genetics and Genomics, Northern Arizona University, Flagstaff, AZ, 86011"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Microbial Genetics and Genomics, Northern Arizona University, Flagstaff, AZ, 86011","institution_ids":["https://openalex.org/I203172682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019512412","display_name":"Evguenia Kopylova","orcid":"https://orcid.org/0000-0003-0225-3223","observed_orcids":["https://orcid.org/0000-0003-0225-3223"]},"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":"Evguenia Kopylova","raw_affiliation_strings":["Department of Pediatrics, University of California, San Diego, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pediatrics, University of California, San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"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":["Center for Microbial Genetics and Genomics, Northern Arizona University, Flagstaff, AZ, 86011"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Microbial Genetics and Genomics, Northern Arizona University, Flagstaff, AZ, 86011","institution_ids":["https://openalex.org/I203172682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011225872","display_name":"Jessica Patnode","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":"Jessica Patnode","raw_affiliation_strings":["Department of Biological Sciences, Northern Arizona University, Flagstaff, AZ, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, Northern Arizona University, Flagstaff, AZ, United States","institution_ids":["https://openalex.org/I203172682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064036881","display_name":"Zach Ellett","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":"Zach Ellett","raw_affiliation_strings":["Department of Computer Science, Northern Arizona University, Flagstaff, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Northern Arizona University, Flagstaff, 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":["BioFrontiers Institute, University of Colorado at Boulder, Boulder, CO, United States","Department of Computer Science, University of Colorado at Boulder, Boulder, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BioFrontiers Institute, University of Colorado at Boulder, Boulder, CO, United States","institution_ids":["https://openalex.org/I188538660"]},{"raw_affiliation_string":"Department of Computer Science, University of Colorado at Boulder, Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007999872","display_name":"Benjamin E. Wolfe","orcid":"https://orcid.org/0000-0002-0194-9336","observed_orcids":["https://orcid.org/0000-0002-0194-9336"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I4210155419","display_name":"Center for Systems Biology","ror":"https://ror.org/05r3dyn47","country_code":"US","type":"facility","lineage":["https://openalex.org/I136199984","https://openalex.org/I4210087915","https://openalex.org/I4210155419","https://openalex.org/I48633490"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Wolfe","raw_affiliation_strings":["FAS Center for Systems Biology, Harvard University, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAS Center for Systems Biology, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984","https://openalex.org/I4210155419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090632251","display_name":"Corinne F. Maurice","orcid":"https://orcid.org/0000-0001-7187-3472","observed_orcids":["https://orcid.org/0000-0001-7187-3472"]},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Corinne F Maurice","raw_affiliation_strings":["Department of Microbiology and Immunology, Microbiome and Disease Tolerance Centre, McGill University, Montreal, QC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Microbiology and Immunology, Microbiome and Disease Tolerance Centre, McGill University, Montreal, QC, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088939514","display_name":"Rachel J. Dutton","orcid":"https://orcid.org/0000-0002-2944-2182","observed_orcids":["https://orcid.org/0000-0002-2944-2182"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I4210155419","display_name":"Center for Systems Biology","ror":"https://ror.org/05r3dyn47","country_code":"US","type":"facility","lineage":["https://openalex.org/I136199984","https://openalex.org/I4210087915","https://openalex.org/I4210155419","https://openalex.org/I48633490"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rachel J Dutton","raw_affiliation_strings":["FAS Center for Systems Biology, Harvard University, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAS Center for Systems Biology, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984","https://openalex.org/I4210155419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079232459","display_name":"Peter James Turnbaugh","orcid":"https://orcid.org/0000-0002-0888-2875","observed_orcids":["https://orcid.org/0000-0002-0888-2875"]},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter J Turnbaugh","raw_affiliation_strings":["Department of Microbiology and Immunology, University of California San Francisco, San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Microbiology and Immunology, University of California San Francisco, San Francisco, CA, USA","institution_ids":["https://openalex.org/I180670191"]}]},{"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":["Department of Pediatrics, University of California, San Diego, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pediatrics, University of California, San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, Northern Arizona University, Flagstaff, AZ, United States","institution_ids":["https://openalex.org/I203172682"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"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":0.9253000020980835,"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":0.9253000020980835,"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":0.026100000366568565,"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":0.02590000070631504,"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/qiime","display_name":"QIIME","score":0.6430000066757202},{"id":"https://openalex.org/keywords/microbial-identification","display_name":"microbial identification","score":0.46700000762939453}],"concepts":[{"id":"https://openalex.org/C8185291","wikidata":"https://www.wikidata.org/wiki/Q2844457","display_name":"Amplicon","level":4,"score":0.7873555421829224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6517887115478516},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.6126342415809631},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5268695950508118},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.47631415724754333},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.47423192858695984},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.4501839876174927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3965715169906616},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36031121015548706},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3325108289718628},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3265199065208435},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.32432088255882263},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2859518826007843},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22302672266960144},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.16080376505851746},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.09459859132766724},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7287/peerj.preprints.934v1","doi":"https://doi.org/10.7287/peerj.preprints.934v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.934v1","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.934v1","doi":"https://doi.org/10.7287/peerj.preprints.934v1","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.934v1","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2752925036","https://openalex.org/W2807194798","https://openalex.org/W2785306095","https://openalex.org/W2796107880","https://openalex.org/W2886687368","https://openalex.org/W2100539938","https://openalex.org/W3173436219","https://openalex.org/W2054406019","https://openalex.org/W2612975255","https://openalex.org/W4378801555"],"abstract_inverted_index":{"Background:":[0],"Taxonomic":[1],"classification":[2,57,84,119],"of":[3,15,31,56,72,118,132,134],"marker-gene":[4],"(i.e.,":[5],"amplicon)":[6],"sequences":[7],"represents":[8],"an":[9,54,76],"important":[10],"step":[11],"for":[12,39,79,94],"molecular":[13],"identification":[14],"microorganisms.":[16],"Results:":[17],"We":[18],"present":[19],"three":[20],"advances":[21],"in":[22,62,107],"our":[23,111],"ability":[24],"to":[25,46,121],"assign":[26],"and":[27,48,68,75,81,96,110,127,146],"interpret":[28],"taxonomic":[29,73],"classifications":[30],"short":[32],"marker":[33,66],"gene":[34],"sequences:":[35],"two":[36],"new":[37,83,103],"methods":[38,58,99,104,120],"taxonomy":[40],"assignment,":[41],"which":[42,86,142],"reduce":[43],"runtime":[44],"up":[45],"two-fold":[47],"achieve":[49],"high":[50],"precision":[51],"genus-level":[52],"assignments;":[53],"evaluation":[55,112],"that":[59],"highlights":[60],"differences":[61],"performance":[63],"with":[64,139],"different":[65,70],"genes":[67],"at":[69,152],"levels":[71],"resolution;":[74],"extensible":[77],"framework":[78,113],"evaluating":[80],"optimizing":[82],"methods,":[85],"we":[87],"hope":[88],"will":[89,114],"serve":[90],"as":[91],"a":[92],"model":[93],"standardized":[95],"reproducible":[97],"bioinformatics":[98,128],"evaluations.":[100],"Conclusions:":[101],"Our":[102],"are":[105],"accessible":[106],"QIIME":[108],"1.9.0,":[109],"support":[115],"ongoing":[116],"optimization":[117],"complement":[122],"rapidly":[123],"evolving":[124],"short-amplicon":[125],"sequencing":[126],"technologies.":[129],"Static":[130],"versions":[131],"all":[133,144],"the":[135],"analysis":[136,147],"notebooks":[137],"generated":[138],"this":[140],"framework,":[141],"contain":[143],"code":[145],"results,":[148],"can":[149],"be":[150],"viewed":[151],"http://bit.ly/srta-010.":[153]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2022-05-12T00:00:00"}
