{"id":"https://openalex.org/W2716620671","doi":"https://doi.org/10.1101/153783","title":"CD-HIT-OTU-MiSeq, an Improved Approach for Clustering and Analyzing Paired End MiSeq 16S rRNA Sequences","display_name":"CD-HIT-OTU-MiSeq, an Improved Approach for Clustering and Analyzing Paired End MiSeq 16S rRNA Sequences","publication_year":2017,"publication_date":"2017-06-22","ids":{"openalex":"https://openalex.org/W2716620671","doi":"https://doi.org/10.1101/153783","mag":"2716620671"},"language":"en","primary_location":{"id":"doi:10.1101/153783","doi":"https://doi.org/10.1101/153783","is_oa":true,"landing_page_url":"https://doi.org/10.1101/153783","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2017/06/22/153783.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2017/06/22/153783.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027145422","display_name":"Weizhong Li","orcid":"https://orcid.org/0000-0003-1804-9403","observed_orcids":["https://orcid.org/0000-0003-1804-9403"]},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Weizhong Li","raw_affiliation_strings":["J Craig Venter Institute, La Jolla, California, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-1804-9403","affiliations":[{"raw_affiliation_string":"J Craig Venter Institute, La Jolla, California, United States of America","institution_ids":["https://openalex.org/I1301553790"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030348326","display_name":"Yuanyuan Chang","orcid":"https://orcid.org/0000-0001-8562-3781","observed_orcids":["https://orcid.org/0000-0001-8562-3781"]},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanyuan Chang","raw_affiliation_strings":["J Craig Venter Institute, La Jolla, California, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"J Craig Venter Institute, La Jolla, California, United States of America","institution_ids":["https://openalex.org/I1301553790"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5027145422"],"corresponding_institution_ids":["https://openalex.org/I1301553790"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":25,"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":0.9678000211715698,"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":0.9678000211715698,"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":0.019500000402331352,"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":0.0032999999821186066,"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/paired-end-reads","display_name":"paired-end reads","score":0.6819999814033508},{"id":"https://openalex.org/keywords/16s-rrna-gene-sequencing","display_name":"16S rRNA gene sequencing","score":0.9010000228881836},{"id":"https://openalex.org/keywords/otu-clustering","display_name":"OTU clustering","score":0.7429999709129333},{"id":"https://openalex.org/keywords/open-source-bioinformatics-software","display_name":"open-source bioinformatics software","score":0.5979999899864197}],"concepts":[{"id":"https://openalex.org/C59582021","wikidata":"https://www.wikidata.org/wiki/Q1128751","display_name":"Contig","level":4,"score":0.9396286010742188},{"id":"https://openalex.org/C125009961","wikidata":"https://www.wikidata.org/wiki/Q2342248","display_name":"Pyrosequencing","level":3,"score":0.558962345123291},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5499672889709473},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5457413196563721},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5074803233146667},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.49395352602005005},{"id":"https://openalex.org/C42062724","wikidata":"https://www.wikidata.org/wiki/Q1209205","display_name":"16S ribosomal RNA","level":3,"score":0.4751436710357666},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.4638153910636902},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.44984906911849976},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.386192262172699},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.24663841724395752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18967923521995544},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.15775710344314575},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.08032944798469543},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1101/153783","doi":"https://doi.org/10.1101/153783","is_oa":true,"landing_page_url":"https://doi.org/10.1101/153783","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2017/06/22/153783.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.1101/153783","doi":"https://doi.org/10.1101/153783","is_oa":true,"landing_page_url":"https://doi.org/10.1101/153783","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2017/06/22/153783.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2317123873","display_name":null,"funder_award_id":"2013-67015-22957","funder_id":"https://openalex.org/F4320332299","funder_display_name":"National Institute of Food and Agriculture"},{"id":"https://openalex.org/G8023369778","display_name":null,"funder_award_id":"2013-67015","funder_id":"https://openalex.org/F4320332299","funder_display_name":"National Institute of Food and Agriculture"}],"funders":[{"id":"https://openalex.org/F4320306114","display_name":"U.S. Department of Agriculture","ror":"https://ror.org/01na82s61"},{"id":"https://openalex.org/F4320332299","display_name":"National Institute of Food and Agriculture","ror":"https://ror.org/05qx3fv49"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2716620671.pdf","grobid_xml":"https://content.openalex.org/works/W2716620671.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1986908904","https://openalex.org/W1988925586","https://openalex.org/W1991486768","https://openalex.org/W2000072710","https://openalex.org/W2072970694","https://openalex.org/W2091922579","https://openalex.org/W2097606916","https://openalex.org/W2101120467","https://openalex.org/W2103828958","https://openalex.org/W2106308757","https://openalex.org/W2108211735","https://openalex.org/W2108718991","https://openalex.org/W2117457769","https://openalex.org/W2128711701","https://openalex.org/W2130208436","https://openalex.org/W2131271579","https://openalex.org/W2132548846","https://openalex.org/W2135083016","https://openalex.org/W2136879569","https://openalex.org/W2150914285","https://openalex.org/W2155066423","https://openalex.org/W2156125289","https://openalex.org/W2157107905","https://openalex.org/W2160681728","https://openalex.org/W2343340722"],"related_works":["https://openalex.org/W2193346577","https://openalex.org/W1986908904","https://openalex.org/W1963710004","https://openalex.org/W2771387624","https://openalex.org/W3045180534","https://openalex.org/W6977454629","https://openalex.org/W1925478155","https://openalex.org/W1920522451","https://openalex.org/W2521965455","https://openalex.org/W1974739180"],"abstract_inverted_index":{"Abstract":[0],"In":[1,118],"recent":[2],"years,":[3],"Illumina":[4],"MiSeq":[5,21],"sequencers":[6],"replaced":[7],"pyrosequencing":[8],"platforms":[9],"and":[10,128,228,248,261],"became":[11],"dominant":[12],"in":[13,104,115],"16S":[14,48,131,202],"rRNA":[15,49],"sequencing.":[16],"One":[17],"unique":[18],"feature":[19],"of":[20,66,75,84,100,163],"technology,":[22],"compared":[23],"with":[24,32,218,265],"Pyrosequencing,":[25],"is":[26,254,262,275],"the":[27,47,52,64,67,93,97,105,116,164,194,206,212,271,277],"Paired":[28],"End":[29],"(PE)":[30],"reads,":[31],"each":[33],"read":[34],"can":[35,87,146,157,191,210,222],"be":[36,57,89],"sequenced":[37],"to":[38,41,56,181],"250-300":[39],"bases":[40,174],"cover":[42],"multiple":[43],"variable":[44],"regions":[45],"on":[46],"gene.":[50],"However,":[51],"PE":[53,77,85,102,148,165,207,214],"reads":[54,78,86,103,149,166],"need":[55],"assembled":[58,91],"into":[59,79,153,205],"a":[60,81,123,159,188,200],"single":[61],"contig":[62],"at":[63,96],"beginning":[65],"analysis.":[68,117],"Although":[69],"there":[70],"are":[71,113,236],"many":[72,111],"methods":[73],"capable":[74],"assembling":[76],"contigs,":[80],"big":[82],"portion":[83,162],"not":[88],"accurately":[90],"because":[92],"poor":[94],"quality":[95,161,183],"3\u2019":[98],"ends":[99],"both":[101],"overlapping":[106],"region.":[107],"This":[108,135],"causes":[109],"that":[110,190],"sequences":[112,235],"discarded":[114],"this":[119],"study,":[120],"we":[121,221],"developed":[122],"novel":[124,141],"approach":[125,137],"for":[126,167],"clustering":[127,147],"annotation":[129],"MiSeq-based":[130],"sequence":[132],"data,":[133],"CD-HIT-OTU-MiSeq.":[134],"new":[136],"has":[138],"four":[139],"distinct":[140],"features.":[142],"(1)":[143],"The":[144,243,251],"package":[145,244,253,260],"without":[150],"joining":[151],"them":[152],"contigs.":[154],"(2)":[155],"Users":[156],"choose":[158],"high":[160,246,249],"analysis":[168],"(e.g.":[169,197],"first":[170],"200":[171],"/":[172,177],"150":[173],"from":[175,199,267],"forward":[176],"reverse":[178],"reads),":[179],"according":[180],"base":[182],"profile.":[184],"(3)":[185],"We":[186],"implemented":[187],"tool":[189],"splice":[192],"out":[193],"target":[195],"region":[196],"V3-V4)":[198],"full-length":[201],"reference":[203,215],"database":[204,216],"sequences.":[208],"CD-HIT-OTU-MiSeq":[209,274],"cluster":[211],"spliced":[213],"together":[217],"samples,":[219],"so":[220],"derive":[223],"Operational":[224],"Taxonomic":[225],"Units":[226],"(OTUs)":[227],"annotate":[229],"these":[230],"OTUs":[231],"concurrently.":[232],"(4)":[233],"Chimeric":[234],"effectively":[237],"identified":[238],"through":[239],"de":[240],"novo":[241],"approach.":[242],"offers":[245],"speed":[247],"accuracy.":[250],"software":[252],"freely":[255],"available":[256],"as":[257],"open":[258],"source":[259],"distributed":[263],"along":[264],"CD-HIT":[266,272],"http://cd-hit.org":[268],".":[269],"Within":[270],"package,":[273],"within":[276],"usecase":[278],"folder.":[279]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2017-06-30T00:00:00"}