{"id":"https://openalex.org/W2747842027","doi":"https://doi.org/10.1145/3107411.3107446","title":"SeqyClean","display_name":"SeqyClean","publication_year":2017,"publication_date":"2017-08-20","ids":{"openalex":"https://openalex.org/W2747842027","doi":"https://doi.org/10.1145/3107411.3107446","mag":"2747842027"},"language":"en","primary_location":{"id":"doi:10.1145/3107411.3107446","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3107411.3107446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th ACM International 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/A5059151412","display_name":"Ilya Y. Zhbannikov","orcid":"https://orcid.org/0000-0002-6502-6514"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ilya Y. Zhbannikov","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"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, USA"],"affiliations":[{"raw_affiliation_string":"University of Idaho, Moscow, ID, USA","institution_ids":["https://openalex.org/I155093810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061637086","display_name":"James A. Foster","orcid":"https://orcid.org/0000-0002-6770-6521"},"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":"James A. Foster","raw_affiliation_strings":["University of Idaho, Moscow, ID, USA"],"affiliations":[{"raw_affiliation_string":"University of Idaho, Moscow, ID, USA","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/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew L. Settles","raw_affiliation_strings":["University of California, Davis, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059151412"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":2.7647,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.91340645,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"407","last_page":"416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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":0.9998999834060669,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9847000241279602,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7652896046638489},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7536897659301758},{"id":"https://openalex.org/keywords/mit-license","display_name":"MIT License","score":0.7011063098907471},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6462910175323486},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.6253100633621216},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.5742543935775757},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5502460598945618},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48933619260787964},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.4718221127986908},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.44141340255737305},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.34618571400642395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23341938853263855},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.15072757005691528},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0805158019065857}],"concepts":[{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7652896046638489},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7536897659301758},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.7011063098907471},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6462910175323486},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6253100633621216},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.5742543935775757},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5502460598945618},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48933619260787964},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.4718221127986908},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.44141340255737305},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.34618571400642395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23341938853263855},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15072757005691528},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0805158019065857},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3107411.3107446","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3107411.3107446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology,and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1204923956","display_name":null,"funder_award_id":"P20GM016454, P20GM16448","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2768337057","display_name":null,"funder_award_id":"DBI0939454","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1985726486","https://openalex.org/W2007703905","https://openalex.org/W2036897871","https://openalex.org/W2080958324","https://openalex.org/W2094100452","https://openalex.org/W2107772251","https://openalex.org/W2128711701","https://openalex.org/W2131271579","https://openalex.org/W2136068873","https://openalex.org/W2142619120","https://openalex.org/W2152073175","https://openalex.org/W2160734881","https://openalex.org/W2170551349","https://openalex.org/W2263582186"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W138569904","https://openalex.org/W2390914021","https://openalex.org/W2389417819"],"abstract_inverted_index":{"Modern":[0],"high-throughput":[1],"sequencing":[2,17,19],"instruments":[3],"produce":[4],"massive":[5],"amounts":[6],"of":[7,16,43,58,73,127],"data,":[8],"which":[9],"often":[10],"contains":[11],"noise":[12,25,74],"in":[13,75,111],"the":[14,39,112,116,125,148],"form":[15],"errors,":[18],"adaptors,":[20],"and":[21,51,103,120,137],"contaminating":[22],"reads.":[23],"This":[24],"complicates":[26],"genomics":[27,113],"studies.":[28],"Although":[29],"many":[30,42],"preprocessing":[31,65,88,93],"software":[32,66,146],"tools":[33],"have":[34,107],"been":[35,132],"developed":[36],"to":[37,82],"reduce":[38],"sequence":[40,78],"noise,":[41],"them":[44],"cannot":[45],"handle":[46],"data":[47,79,94],"from":[48],"multiple":[49,71],"technologies":[50],"few":[52],"address":[53],"more":[54],"than":[55],"one":[56],"type":[57],"noise.":[59],"We":[60,90,106],"present":[61],"SeqyClean,":[62],"a":[63],"comprehensive":[64],"pipeline.":[67],"SeqyClean":[68,96,109,140],"effectively":[69],"removes":[70],"sources":[72],"high":[76],"throughput":[77],"and,":[80],"according":[81],"our":[83],"tests,":[84],"outperforms":[85],"other":[86],"available":[87,142],"tools.":[89],"show":[91],"that":[92],"with":[95,134],"first":[97],"improves":[98],"both":[99,135],"de-novo":[100],"genome":[101,104],"assembly":[102],"mapping.":[105],"used":[108],"extensively":[110],"core":[114],"at":[115,124,151],"Institute":[117],"for":[118],"Bioinformatics":[119],"Evolutionary":[121],"STudies":[122],"(IBEST)":[123],"University":[126],"Idaho,":[128],"so":[129],"it":[130],"has":[131],"validated":[133],"test":[136],"production":[138],"data.":[139],"is":[141],"as":[143],"open":[144],"source":[145],"under":[147],"MIT":[149],"License":[150],"http://github.com/ibest/seqyclean":[152]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2017-08-31T00:00:00"}