{"id":"https://openalex.org/W2174781996","doi":"https://doi.org/10.1093/nar/gkv1113","title":"A novel conceptual approach to read-filtering in high-throughput amplicon sequencing studies","display_name":"A novel conceptual approach to read-filtering in high-throughput amplicon sequencing studies","publication_year":2015,"publication_date":"2015-11-08","ids":{"openalex":"https://openalex.org/W2174781996","doi":"https://doi.org/10.1093/nar/gkv1113","mag":"2174781996","pmid":"https://pubmed.ncbi.nlm.nih.gov/26553806","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/4770208"},"language":"en","primary_location":{"id":"doi:10.1093/nar/gkv1113","doi":"https://doi.org/10.1093/nar/gkv1113","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkv1113","pdf_url":"https://academic.oup.com/nar/article-pdf/44/4/e40/16668528/gkv1113.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/nar/article-pdf/44/4/e40/16668528/gkv1113.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018336423","display_name":"Fernando Puente\u2010S\u00e1nchez","orcid":"https://orcid.org/0000-0002-6341-3692","observed_orcids":["https://orcid.org/0000-0002-6341-3692"]},"institutions":[{"id":"https://openalex.org/I134820265","display_name":"Consejo Superior de Investigaciones Cient\u00edficas","ror":"https://ror.org/02gfc7t72","country_code":"ES","type":"government","lineage":["https://openalex.org/I134820265"]},{"id":"https://openalex.org/I4210117279","display_name":"Instituto Nacional de T\u00e9cnica Aeroespacial","ror":"https://ror.org/02m44ak47","country_code":"ES","type":"government","lineage":["https://openalex.org/I4210117279"]},{"id":"https://openalex.org/I4210129022","display_name":"Centro de Astrobiolog\u00eda","ror":"https://ror.org/038szmr31","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210117279","https://openalex.org/I4210129022"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Fernando Puente-S\u00e1nchez","raw_affiliation_strings":["Department of Molecular Evolution, Centro de Astrobiolog\u00eda (INTA-CSIC). Instituto Nacional de T\u00e9cnica Aeroespacial, Ctra de Torrej\u00f3n a Ajalvir km 4. 28850 Torrej\u00f3n de Ardoz, Madrid, Spain fpusan@gmail.com","Department of Molecular Evolution, Centro de Astrobiolog\u00eda (INTA-CSIC). Instituto Nacional de T\u00e9cnica Aeroespacial, Ctra de Torrej\u00f3n a Ajalvir km 4. 28850 Torrej\u00f3n de Ardoz, Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0002-6341-3692","affiliations":[{"raw_affiliation_string":"Department of Molecular Evolution, Centro de Astrobiolog\u00eda (INTA-CSIC). Instituto Nacional de T\u00e9cnica Aeroespacial, Ctra de Torrej\u00f3n a Ajalvir km 4. 28850 Torrej\u00f3n de Ardoz, Madrid, Spain fpusan@gmail.com","institution_ids":["https://openalex.org/I134820265","https://openalex.org/I4210117279","https://openalex.org/I4210129022"]},{"raw_affiliation_string":"Department of Molecular Evolution, Centro de Astrobiolog\u00eda (INTA-CSIC). Instituto Nacional de T\u00e9cnica Aeroespacial, Ctra de Torrej\u00f3n a Ajalvir km 4. 28850 Torrej\u00f3n de Ardoz, Madrid, Spain","institution_ids":["https://openalex.org/I134820265","https://openalex.org/I4210117279","https://openalex.org/I4210129022"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027512307","display_name":"Jacobo Aguirre","orcid":"https://orcid.org/0000-0003-2196-5103","observed_orcids":["https://orcid.org/0000-0003-2196-5103"]},"institutions":[{"id":"https://openalex.org/I134820265","display_name":"Consejo Superior de Investigaciones Cient\u00edficas","ror":"https://ror.org/02gfc7t72","country_code":"ES","type":"government","lineage":["https://openalex.org/I134820265"]},{"id":"https://openalex.org/I4210104776","display_name":"Centro Nacional de Biotecnolog\u00eda","ror":"https://ror.org/015w4v032","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210104776"]},{"id":"https://openalex.org/I4210117279","display_name":"Instituto Nacional de T\u00e9cnica Aeroespacial","ror":"https://ror.org/02m44ak47","country_code":"ES","type":"government","lineage":["https://openalex.org/I4210117279"]},{"id":"https://openalex.org/I4210129022","display_name":"Centro de Astrobiolog\u00eda","ror":"https://ror.org/038szmr31","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210117279","https://openalex.org/I4210129022"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jacobo Aguirre","raw_affiliation_strings":["Department of Molecular Evolution, Centro de Astrobiolog\u00eda (INTA-CSIC). Instituto Nacional de T\u00e9cnica Aeroespacial, Ctra de Torrej\u00f3n a Ajalvir km 4. 28850 Torrej\u00f3n de Ardoz, Madrid, Spain Centro Nacional de Biotecnolog\u00eda (CSIC). c/ Darwin 3, 28049 Madrid, Spain Grupo Interdisciplinar de Sistemas Complejos (GISC), Madrid, Spain","Centro Nacional de Biotecnolog\u00eda (CSIC). c/ Darwin 3, 28049 Madrid, Spain","Department of Molecular Evolution, Centro de Astrobiolog\u00eda (INTA-CSIC). Instituto Nacional de T\u00e9cnica Aeroespacial, Ctra de Torrej\u00f3n a Ajalvir km 4. 28850 Torrej\u00f3n de Ardoz, Madrid, Spain","Grupo Interdisciplinar de Sistemas Complejos (GISC), Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0003-2196-5103","affiliations":[{"raw_affiliation_string":"Department of Molecular Evolution, Centro de Astrobiolog\u00eda (INTA-CSIC). Instituto Nacional de T\u00e9cnica Aeroespacial, Ctra de Torrej\u00f3n a Ajalvir km 4. 28850 Torrej\u00f3n de Ardoz, Madrid, Spain Centro Nacional de Biotecnolog\u00eda (CSIC). c/ Darwin 3, 28049 Madrid, Spain Grupo Interdisciplinar de Sistemas Complejos (GISC), Madrid, Spain","institution_ids":["https://openalex.org/I134820265","https://openalex.org/I4210104776","https://openalex.org/I4210117279","https://openalex.org/I4210129022"]},{"raw_affiliation_string":"Centro Nacional de Biotecnolog\u00eda (CSIC). c/ Darwin 3, 28049 Madrid, Spain","institution_ids":["https://openalex.org/I134820265","https://openalex.org/I4210104776"]},{"raw_affiliation_string":"Department of Molecular Evolution, Centro de Astrobiolog\u00eda (INTA-CSIC). Instituto Nacional de T\u00e9cnica Aeroespacial, Ctra de Torrej\u00f3n a Ajalvir km 4. 28850 Torrej\u00f3n de Ardoz, Madrid, Spain","institution_ids":["https://openalex.org/I134820265","https://openalex.org/I4210117279","https://openalex.org/I4210129022"]},{"raw_affiliation_string":"Grupo Interdisciplinar de Sistemas Complejos (GISC), Madrid, Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055212063","display_name":"V\u00edctor Parro","orcid":"https://orcid.org/0000-0003-3738-0724","observed_orcids":["https://orcid.org/0000-0003-3738-0724"]},"institutions":[{"id":"https://openalex.org/I134820265","display_name":"Consejo Superior de Investigaciones Cient\u00edficas","ror":"https://ror.org/02gfc7t72","country_code":"ES","type":"government","lineage":["https://openalex.org/I134820265"]},{"id":"https://openalex.org/I4210117279","display_name":"Instituto Nacional de T\u00e9cnica Aeroespacial","ror":"https://ror.org/02m44ak47","country_code":"ES","type":"government","lineage":["https://openalex.org/I4210117279"]},{"id":"https://openalex.org/I4210129022","display_name":"Centro de Astrobiolog\u00eda","ror":"https://ror.org/038szmr31","country_code":"ES","type":"facility","lineage":["https://openalex.org/I134820265","https://openalex.org/I4210117279","https://openalex.org/I4210129022"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"V\u00edctor Parro","raw_affiliation_strings":["Department of Molecular Evolution, Centro de Astrobiolog\u00eda (INTA-CSIC). Instituto Nacional de T\u00e9cnica Aeroespacial, Ctra de Torrej\u00f3n a Ajalvir km 4. 28850 Torrej\u00f3n de Ardoz, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Molecular Evolution, Centro de Astrobiolog\u00eda (INTA-CSIC). Instituto Nacional de T\u00e9cnica Aeroespacial, Ctra de Torrej\u00f3n a Ajalvir km 4. 28850 Torrej\u00f3n de Ardoz, Madrid, Spain","institution_ids":["https://openalex.org/I134820265","https://openalex.org/I4210117279","https://openalex.org/I4210129022"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018336423"],"corresponding_institution_ids":["https://openalex.org/I134820265","https://openalex.org/I4210117279","https://openalex.org/I4210129022"],"apc_list":{"value":3992,"currency":"USD","value_usd":3992},"apc_paid":{"value":3992,"currency":"USD","value_usd":3992},"fwci":1.3836,"has_fulltext":true,"cited_by_count":51,"citation_normalized_percentile":{"value":0.79367718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"44","issue":"4","first_page":"e40","last_page":"e40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9541000127792358,"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":0.9541000127792358,"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":0.02370000071823597,"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":0.011099999770522118,"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/read-filtering","display_name":"read filtering","score":0.9929999709129333},{"id":"https://openalex.org/keywords/sequencing-errors","display_name":"sequencing errors","score":0.7549999952316284},{"id":"https://openalex.org/keywords/operational-taxonomic-units","display_name":"operational taxonomic units","score":0.9269999861717224},{"id":"https://openalex.org/keywords/quality-scores","display_name":"quality scores","score":0.671999990940094},{"id":"https://openalex.org/keywords/error-probability-estimation","display_name":"error probability estimation","score":0.5590000152587891},{"id":"https://openalex.org/keywords/mock-microbial-community","display_name":"mock microbial community","score":0.8410000205039978},{"id":"https://openalex.org/keywords/454-pyrosequencing","display_name":"454 pyrosequencing","score":0.6320000290870667},{"id":"https://openalex.org/keywords/illumina-miseq","display_name":"Illumina MiSeq","score":0.8579999804496765},{"id":"https://openalex.org/keywords/ion-torrent-pgm","display_name":"Ion Torrent PGM","score":0.796999990940094},{"id":"https://openalex.org/keywords/mothur","display_name":"mothur","score":0.6399999856948853},{"id":"https://openalex.org/keywords/qiime","display_name":"QIIME","score":0.9950000047683716},{"id":"https://openalex.org/keywords/usearch","display_name":"USearch","score":0.996999979019165}],"concepts":[{"id":"https://openalex.org/C2993206177","wikidata":"https://www.wikidata.org/wiki/Q2844457","display_name":"Amplicon sequencing","level":4,"score":0.7640491724014282},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.7381377816200256},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7003701329231262},{"id":"https://openalex.org/C8185291","wikidata":"https://www.wikidata.org/wiki/Q2844457","display_name":"Amplicon","level":4,"score":0.6045728921890259},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.517231285572052},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5045069456100464},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.5000267028808594},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.45146915316581726},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.44758692383766174},{"id":"https://openalex.org/C192800701","wikidata":"https://www.wikidata.org/wiki/Q6784807","display_name":"Massive parallel sequencing","level":4,"score":0.4207743704319},{"id":"https://openalex.org/C132917006","wikidata":"https://www.wikidata.org/wiki/Q5250436","display_name":"Deep sequencing","level":4,"score":0.4184768795967102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.34583568572998047},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24022746086120605},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.21749895811080933},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.15029475092887878},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1493140459060669},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11631596088409424},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.08151489496231079},{"id":"https://openalex.org/C49105822","wikidata":"https://www.wikidata.org/wiki/Q176996","display_name":"Polymerase chain reaction","level":3,"score":0.07587486505508423},{"id":"https://openalex.org/C42062724","wikidata":"https://www.wikidata.org/wiki/Q1209205","display_name":"16S ribosomal RNA","level":3,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011786","descriptor_name":"Quality Control","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D044822","descriptor_name":"Biodiversity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":7,"locations":[{"id":"doi:10.1093/nar/gkv1113","doi":"https://doi.org/10.1093/nar/gkv1113","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkv1113","pdf_url":"https://academic.oup.com/nar/article-pdf/44/4/e40/16668528/gkv1113.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},{"id":"pmid:26553806","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26553806","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":"Nucleic acids research","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:4770208","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC4770208/","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":"Nucleic Acids Res","raw_type":"Text"},{"id":"pmh:oai:arXiv.org:1506.00453","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1506.00453","pdf_url":"https://arxiv.org/pdf/1506.00453","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:digital.csic.es:10261/343808","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10261/343808","pdf_url":null,"source":{"id":"https://openalex.org/S4306400616","display_name":"DIGITAL.CSIC (Spanish National Research Council (CSIC))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I134820265","host_organization_name":"Consejo Superior de Investigaciones Cient\u00edficas","host_organization_lineage":["https://openalex.org/I134820265"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"art\u00edculo"},{"id":"pmh:oai:open-archive.highwire.org:nar:44/4/e40","doi":null,"is_oa":false,"landing_page_url":"http://nar.oxfordjournals.org/cgi/content/short/44/4/e40","pdf_url":null,"source":{"id":"https://openalex.org/S4406923041","display_name":"HighWire Press Open Archive","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"TEXT"},{"id":"doi:10.48550/arxiv.1506.00453","doi":"https://doi.org/10.48550/arxiv.1506.00453","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1506.00453","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1093/nar/gkv1113","doi":"https://doi.org/10.1093/nar/gkv1113","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkv1113","pdf_url":"https://academic.oup.com/nar/article-pdf/44/4/e40/16668528/gkv1113.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3830309485","display_name":null,"funder_award_id":"FIS2014-57686-P","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G5152710322","display_name":"Science and technology development for in situ detection and cjharacterization of subsurface life on the Iberian Pyritic Belt","funder_award_id":"250350","funder_id":"https://openalex.org/F4320338352","funder_display_name":"FP7 Ideas: European Research Council"},{"id":"https://openalex.org/G8028007949","display_name":null,"funder_award_id":"FIS2011-27569","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"}],"funders":[{"id":"https://openalex.org/F4320313831","display_name":"Comunidad de Madrid","ror":null},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320334857","display_name":"Consejo Superior de Investigaciones Cient\u00edficas","ror":"https://ror.org/02gfc7t72"},{"id":"https://openalex.org/F4320338352","display_name":"FP7 Ideas: European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2174781996.pdf","grobid_xml":"https://content.openalex.org/works/W2174781996.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1512323415","https://openalex.org/W1773483230","https://openalex.org/W1963981961","https://openalex.org/W1971584645","https://openalex.org/W1983047294","https://openalex.org/W1989889539","https://openalex.org/W1991486768","https://openalex.org/W1993837111","https://openalex.org/W2000072710","https://openalex.org/W2034285706","https://openalex.org/W2034833171","https://openalex.org/W2044495601","https://openalex.org/W2047669659","https://openalex.org/W2052359965","https://openalex.org/W2059670608","https://openalex.org/W2072970694","https://openalex.org/W2080283023","https://openalex.org/W2082464084","https://openalex.org/W2086865963","https://openalex.org/W2088833470","https://openalex.org/W2097606916","https://openalex.org/W2101120467","https://openalex.org/W2103412200","https://openalex.org/W2105368763","https://openalex.org/W2106308757","https://openalex.org/W2108718991","https://openalex.org/W2111358533","https://openalex.org/W2115701239","https://openalex.org/W2117457769","https://openalex.org/W2119284644","https://openalex.org/W2124351063","https://openalex.org/W2136879569","https://openalex.org/W2146580089","https://openalex.org/W2162088497","https://openalex.org/W2162578061","https://openalex.org/W2162667876","https://openalex.org/W2166171121"],"related_works":["https://openalex.org/W565360940","https://openalex.org/W2596926044","https://openalex.org/W2086865963","https://openalex.org/W7099586531","https://openalex.org/W1921009424","https://openalex.org/W2026777696","https://openalex.org/W2804197582","https://openalex.org/W2616000159","https://openalex.org/W4231411653","https://openalex.org/W2162667876"],"abstract_inverted_index":{"Adequate":[0],"read":[1],"filtering":[2,64],"is":[3,178],"critical":[4],"when":[5],"processing":[6],"high-throughput":[7],"data":[8],"in":[9,46,128,144,167,175,186],"marker-gene-based":[10],"studies.":[11],"Sequencing":[12,41],"errors":[13,42],"can":[14,182],"cause":[15],"the":[16,24,36,54,61,73,104,125,162,168,172],"mis-clustering":[17],"of":[18,26,38,53,76,161],"otherwise":[19],"similar":[20],"reads,":[21],"artificially":[22],"increasing":[23],"number":[25],"retrieved":[27],"Operational":[28],"Taxonomic":[29],"Units":[30],"(OTUs)":[31],"and":[32,99,109,113,131,146,159,181],"therefore":[33],"leading":[34],"to":[35,85,117],"overestimation":[37],"microbial":[39,101,164],"diversity.":[40],"will":[43],"also":[44],"result":[45],"OTUs":[47],"that":[48],"are":[49],"not":[50],"accurate":[51,148],"reconstructions":[52],"original":[55],"biological":[56],"sequences.":[57],"Herein":[58],"we":[59,89],"present":[60,166],"Poisson":[62],"binomial":[63],"algorithm":[65,134],"(PBF),":[66],"which":[67],"minimizes":[68],"both":[69,157],"problems":[70],"by":[71,96],"calculating":[72],"error-probability":[74],"distribution":[75],"a":[77],"sequence":[78],"from":[79],"its":[80,140],"quality":[81],"scores.":[82],"In":[83],"order":[84],"validate":[86],"our":[87,115],"method,":[88],"quality-filtered":[90],"37":[91],"publicly":[92],"available":[93],"datasets":[94],"obtained":[95,119],"sequencing":[97],"mock":[98],"environmental":[100],"communities":[102],"with":[103,120,188],"Roche":[105],"454,":[106],"Illumina":[107],"MiSeq":[108],"IonTorrent":[110],"PGM":[111],"platforms,":[112],"compared":[114],"results":[116],"those":[118],"previous":[121],"approaches":[122],"such":[123],"as":[124],"ones":[126],"included":[127],"mothur,":[129],"QIIME":[130],"USEARCH.":[132],"Our":[133],"retained":[135],"substantially":[136],"more":[137,147,154],"reads":[138],"than":[139],"predecessors,":[141],"while":[142],"resulting":[143],"fewer":[145],"OTUs.":[149],"This":[150],"improved":[151],"sensitiveness":[152],"produced":[153],"faithful":[155],"representations,":[156],"quantitatively":[158],"qualitatively,":[160],"true":[163],"diversity":[165],"studied":[169],"samples.":[170],"Furthermore,":[171],"method":[173],"introduced":[174],"this":[176],"work":[177],"computationally":[179],"inexpensive":[180],"be":[183],"readily":[184],"applied":[185],"conjunction":[187],"any":[189],"existent":[190],"analysis":[191],"pipeline.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}
