{"id":"https://openalex.org/W2041053970","doi":"https://doi.org/10.1145/2808719.2811568","title":"Super deduper, fast PCR duplicate detection in fastq files","display_name":"Super deduper, fast PCR duplicate detection in fastq files","publication_year":2015,"publication_date":"2015-09-09","ids":{"openalex":"https://openalex.org/W2041053970","doi":"https://doi.org/10.1145/2808719.2811568","mag":"2041053970"},"language":"en","primary_location":{"id":"doi:10.1145/2808719.2811568","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2808719.2811568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5037362971","display_name":"Kristen R. Petersen","orcid":null},"institutions":[{"id":"https://openalex.org/I155093810","display_name":"University of Idaho","ror":"https://ror.org/03hbp5t65","country_code":"US","type":"education","lineage":["https://openalex.org/I155093810"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristen R. Petersen","raw_affiliation_strings":["University of Idaho, Moscow, ID"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Idaho, Moscow, ID","institution_ids":["https://openalex.org/I155093810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016796763","display_name":"David A. Streett","orcid":null},"institutions":[{"id":"https://openalex.org/I155093810","display_name":"University of Idaho","ror":"https://ror.org/03hbp5t65","country_code":"US","type":"education","lineage":["https://openalex.org/I155093810"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David A. Streett","raw_affiliation_strings":["University of Idaho, Moscow, ID"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Idaho, Moscow, ID","institution_ids":["https://openalex.org/I155093810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064906223","display_name":"Alida T. Gerritsen","orcid":"https://orcid.org/0000-0003-3148-8427"},"institutions":[{"id":"https://openalex.org/I155093810","display_name":"University of Idaho","ror":"https://ror.org/03hbp5t65","country_code":"US","type":"education","lineage":["https://openalex.org/I155093810"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alida T. Gerritsen","raw_affiliation_strings":["University of Idaho, Moscow, ID"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Idaho, Moscow, ID","institution_ids":["https://openalex.org/I155093810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013548188","display_name":"Samuel S. Hunter","orcid":"https://orcid.org/0000-0002-9358-1777"},"institutions":[{"id":"https://openalex.org/I155093810","display_name":"University of Idaho","ror":"https://ror.org/03hbp5t65","country_code":"US","type":"education","lineage":["https://openalex.org/I155093810"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel S. Hunter","raw_affiliation_strings":["University of Idaho, Moscow, ID"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Idaho, Moscow, ID","institution_ids":["https://openalex.org/I155093810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057455952","display_name":"Matthew L. Settles","orcid":"https://orcid.org/0000-0002-3424-1086"},"institutions":[{"id":"https://openalex.org/I155093810","display_name":"University of Idaho","ror":"https://ror.org/03hbp5t65","country_code":"US","type":"education","lineage":["https://openalex.org/I155093810"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew L. Settles","raw_affiliation_strings":["University of Idaho, Moscow, ID"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Idaho, Moscow, ID","institution_ids":["https://openalex.org/I155093810"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5062,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.82156717,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"491","last_page":"492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9980999827384949,"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":0.9958000183105469,"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/computer-science","display_name":"Computer science","score":0.817233145236969},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.5329602360725403},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5202078223228455},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5167057514190674},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5162570476531982},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.42104101181030273},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36509937047958374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28769823908805847},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.19533389806747437},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10699617862701416},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09691852331161499},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.09029161930084229}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817233145236969},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5329602360725403},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5202078223228455},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5167057514190674},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5162570476531982},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.42104101181030273},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36509937047958374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28769823908805847},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.19533389806747437},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10699617862701416},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09691852331161499},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.09029161930084229},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2808719.2811568","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2808719.2811568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2009637031","https://openalex.org/W2086399100","https://openalex.org/W2103441770","https://openalex.org/W2128505445","https://openalex.org/W2132378736","https://openalex.org/W2141978878","https://openalex.org/W2155266131","https://openalex.org/W2170551349","https://openalex.org/W2171336109"],"related_works":["https://openalex.org/W2357241418","https://openalex.org/W2086064646","https://openalex.org/W2119135658","https://openalex.org/W2115485936","https://openalex.org/W3022131925","https://openalex.org/W2792377126","https://openalex.org/W2349174110","https://openalex.org/W1597238586","https://openalex.org/W1536405386","https://openalex.org/W2326857978"],"abstract_inverted_index":{"Our":[0],"goal":[1],"was":[2],"to":[3,50,86],"explore":[4],"the":[5,32],"accuracy":[6],"and":[7,11,38,52,63,71,98,121],"utility":[8],"of":[9,34,44,94,111],"identifying":[10],"removing":[12],"PCR":[13,54],"duplicates":[14],"from":[15],"HTS":[16,112],"data":[17],"using":[18],"Super":[19,21,66,79,89,114],"Deduper.":[20],"Deduper":[22,80,90,115],"is":[23,81,91,116],"a":[24,41,82,95,108],"pre-alignment,":[25],"sequence":[26,47],"read":[27],"based":[28],"technique":[29],"developed":[30],"at":[31,125],"University":[33],"Idaho,":[35],"which":[36],"examines":[37],"uses":[39],"only":[40],"small":[42],"portion":[43],"each":[45],"read's":[46],"in":[48,100,107],"order":[49],"identify":[51],"remove":[53],"and/or":[55],"optical":[56],"duplicates.":[57],"Through":[58],"comparisons":[59],"with":[60],"well-known":[61],"pre-":[62],"post-alignment":[64,87],"techniques,":[65],"Deduper's":[67],"parameters":[68],"were":[69],"optimized":[70],"its":[72,105],"performance":[73],"assessed.":[74],"The":[75],"results":[76],"conclude":[77],"that":[78],"viable":[83],"pre-alignment":[84],"alternative":[85],"techniques.":[88],"both":[92],"independent":[93],"reference":[96],"genome":[97],"choice":[99],"alignment":[101],"application,":[102],"allowing":[103],"for":[104],"use":[106],"greater":[109],"variety":[110],"applications.":[113],"an":[117],"open":[118],"source":[119],"application":[120],"can":[122],"be":[123],"found":[124],"https://github.com/dstreett/Super-Deduper.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
