{"id":"https://openalex.org/W2006893094","doi":"https://doi.org/10.1101/pdb.prot5409","title":"Identifying and Removing Artificial Replicates from 454 Pyrosequencing Data","display_name":"Identifying and Removing Artificial Replicates from 454 Pyrosequencing Data","publication_year":2010,"publication_date":"2010-04-01","ids":{"openalex":"https://openalex.org/W2006893094","doi":"https://doi.org/10.1101/pdb.prot5409","mag":"2006893094","pmid":"https://pubmed.ncbi.nlm.nih.gov/20360363"},"language":"en","primary_location":{"id":"doi:10.1101/pdb.prot5409","doi":"https://doi.org/10.1101/pdb.prot5409","is_oa":false,"landing_page_url":"https://doi.org/10.1101/pdb.prot5409","pdf_url":null,"source":{"id":"https://openalex.org/S119953358","display_name":"Cold Spring Harbor Protocols","issn_l":"1559-6095","issn":["1559-6095","1940-3402"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","medline","norway-1","poland-70","russia-white-list-1"],"host_organization":"https://openalex.org/P4310315909","host_organization_name":"Cold Spring Harbor Laboratory Press","host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cold Spring Harbor Protocols","raw_type":"journal-article"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004423042","display_name":"Tracy K. Teal","orcid":"https://orcid.org/0000-0002-9180-9598","observed_orcids":["https://orcid.org/0000-0002-9180-9598"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tracy K. Teal","raw_affiliation_strings":["Department of Microbiology and Molecular Genetics, Michigan State University, East Lansing, MI 48824, USA. tkteal@msu.edu","Department of Microbiology and Molecular Genetics, Michigan State University, East Lansing, MI 48824, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Microbiology and Molecular Genetics, Michigan State University, East Lansing, MI 48824, USA. tkteal@msu.edu","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"Department of Microbiology and Molecular Genetics, Michigan State University, East Lansing, MI 48824, USA,","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037972215","display_name":"Thomas Mitchell Schmidt","orcid":"https://orcid.org/0000-0002-8209-6055","observed_orcids":["https://orcid.org/0000-0002-8209-6055"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas M. Schmidt","raw_affiliation_strings":["Department of Microbiology and Molecular Genetics, Michigan State University, East Lansing, MI 48824, USA","Michigan State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Microbiology and Molecular Genetics, Michigan State University, East Lansing, MI 48824, USA","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5004423042"],"corresponding_institution_ids":["https://openalex.org/I87216513"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2010","issue":"4","first_page":"pdb.prot5409","last_page":"pdb.prot5409"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9868000149726868,"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":0.9868000149726868,"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/T12640","display_name":"Environmental DNA in Biodiversity Studies","score":0.005900000222027302,"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/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.0027000000700354576,"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/454-pyrosequencing","display_name":"454 pyrosequencing","score":0.9739999771118164},{"id":"https://openalex.org/keywords/sequence-duplication","display_name":"sequence duplication","score":0.35600000619888306},{"id":"https://openalex.org/keywords/cd-hit-clustering","display_name":"CD-HIT clustering","score":0.7390000224113464},{"id":"https://openalex.org/keywords/sequencing-artifacts","display_name":"sequencing artifacts","score":0.5419999957084656},{"id":"https://openalex.org/keywords/metagenomics","display_name":"metagenomics","score":0.6990000009536743},{"id":"https://openalex.org/keywords/transcriptomics","display_name":"transcriptomics","score":0.9900000095367432}],"concepts":[{"id":"https://openalex.org/C125009961","wikidata":"https://www.wikidata.org/wiki/Q2342248","display_name":"Pyrosequencing","level":3,"score":0.9567515850067139},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.5555840730667114},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5491216778755188},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.528526782989502},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.4662688374519348},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.43993720412254333},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.36902281641960144},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.24448665976524353},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09978687763214111},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09031075239181519}],"mesh":[{"descriptor_ui":"D003951","descriptor_name":"Diagnostic Errors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013223","descriptor_name":"Statistics as Topic","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1101/pdb.prot5409","doi":"https://doi.org/10.1101/pdb.prot5409","is_oa":false,"landing_page_url":"https://doi.org/10.1101/pdb.prot5409","pdf_url":null,"source":{"id":"https://openalex.org/S119953358","display_name":"Cold Spring Harbor Protocols","issn_l":"1559-6095","issn":["1559-6095","1940-3402"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","medline","norway-1","poland-70","russia-white-list-1"],"host_organization":"https://openalex.org/P4310315909","host_organization_name":"Cold Spring Harbor Laboratory Press","host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cold Spring Harbor Protocols","raw_type":"journal-article"},{"id":"pmid:20360363","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20360363","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":"Cold Spring Harbor protocols","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2037532428","https://openalex.org/W2087671769","https://openalex.org/W2156125289"],"related_works":["https://openalex.org/W2156049845","https://openalex.org/W2108166985","https://openalex.org/W2065310919","https://openalex.org/W2037532428","https://openalex.org/W2011637810","https://openalex.org/W2037612360","https://openalex.org/W7097553500","https://openalex.org/W3146578834","https://openalex.org/W2106308757","https://openalex.org/W7098317855"],"abstract_inverted_index":{"An":[0],"intrinsic":[1],"artifact":[2],"of":[3,10,12,21,69,162,181],"454-based":[4,120],"pyrosequencing":[5,31,121,141],"leads":[6],"to":[7,27,78,94,112,153,172],"artificial":[8,19,97,144],"overrepresentation":[9],">10%":[11],"the":[13,30,50,67,106,139,174],"original":[14],"DNA":[15],"sequencing":[16,64,161],"templates.":[17],"This":[18,124,166],"amplification":[20,136],"sequences":[22,47,118,183],"is":[23,76,92],"unbiased":[24],"with":[25],"regard":[26],"position":[28,52],"on":[29,170],"plate":[32],"or":[33,57,61,88,188],"sequence":[34,71],"identity,":[35],"and":[36,53,114,177],"it":[37,91],"occurs":[38],"in":[39,59,72,119,160,186],"all":[40],"currently":[41],"available":[42],"454":[43],"technologies.":[44],"The":[45],"amplified":[46,163],"start":[48],"at":[49],"same":[51],"are":[54],"identical":[55],"(duplicates),":[56],"vary":[58],"length,":[60],"contain":[62],"a":[63,73,179],"discrepancy.":[65],"If":[66],"abundance":[68],"any":[70],"data":[74,122,130],"set":[75],"going":[77],"be":[79,127,147],"enumerated,":[80],"either":[81],"for":[82,129,184],"comparative":[83],"community":[84],"analysis,":[85],"transcriptional":[86],"analysis":[87],"other":[89],"applications,":[90],"important":[93],"remove":[95,115],"these":[96],"replicates":[98,145],"before":[99,138],"analysis.":[100],"A":[101],"web-based":[102],"tool":[103,125],"that":[104,132],"incorporates":[105],"clustering":[107],"algorithm":[108],"cd-hit":[109],"was":[110],"developed":[111],"identify":[113],"artificially":[116],"replicated":[117],"sets.":[123],"cannot":[126,146],"used":[128],"sets":[131],"have":[133],"an":[134],"initial":[135],"step":[137],"standard":[140],"procedure,":[142],"because":[143],"distinguished":[148],"from":[149],"expected":[150],"replication":[151],"due":[152],"polymerase":[154],"chain":[155],"reaction":[156],"(PCR)":[157],"amplification,":[158],"e.g.,":[159],"gene":[164],"\"tags.\"":[165],"protocol":[167],"provides":[168],"details":[169],"how":[171],"use":[173,185],"replicate":[175],"filter":[176],"obtain":[178],"file":[180],"unique":[182],"metagenomic":[187],"transcriptomic":[189],"analyses.":[190]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2016-06-24T00:00:00"}
