{"id":"https://openalex.org/W2082489064","doi":"https://doi.org/10.1109/bibm.2014.6999309","title":"Fastq_clean: An optimized pipeline to clean the Illumina sequencing data with quality control","display_name":"Fastq_clean: An optimized pipeline to clean the Illumina sequencing data with quality control","publication_year":2014,"publication_date":"2014-11-01","ids":{"openalex":"https://openalex.org/W2082489064","doi":"https://doi.org/10.1109/bibm.2014.6999309","mag":"2082489064"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2014.6999309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2014.6999309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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/A5100675019","display_name":"Mi Zhang","orcid":"https://orcid.org/0000-0002-9780-136X"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]},{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mi Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Tianjin University, Tianjin, P.R.China","School of Computer Science and Technology, Tianjin University, Tianjin. 300072, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tianjin University, Tianjin, P.R.China","institution_ids":["https://openalex.org/I132369690"]},{"raw_affiliation_string":"School of Computer Science and Technology, Tianjin University, Tianjin. 300072, P. R. China","institution_ids":["https://openalex.org/I132369690","https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010862241","display_name":"Honghe Sun","orcid":"https://orcid.org/0000-0002-2468-6823"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]},{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Honghe Sun","raw_affiliation_strings":["Department of Computer Science Guangxi, University Nanning, Guangxi, P. R. CHINA","#N#        Boyce Thompson Institute for Plant Research, Cornell University, Ithaca, NY 14853, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science Guangxi, University Nanning, Guangxi, P. R. CHINA","institution_ids":["https://openalex.org/I150807315"]},{"raw_affiliation_string":"#N#        Boyce Thompson Institute for Plant Research, Cornell University, Ithaca, NY 14853, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060776410","display_name":"Zhangjun Fei","orcid":"https://orcid.org/0000-0001-9684-1450"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhangjun Fei","raw_affiliation_strings":["Boyce Thompson Inst. for Plant Research, Cornell University Ithaca, NY, USA","#N#        Boyce Thompson Institute for Plant Research, Cornell University, Ithaca, NY 14853, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boyce Thompson Inst. for Plant Research, Cornell University Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"#N#        Boyce Thompson Institute for Plant Research, Cornell University, Ithaca, NY 14853, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Feng Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]},{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhan","raw_affiliation_strings":["School of Computer Science and Technology, Tianjin University, Tianjin, P.R.China","Department of Computer Science, Guangxi University, Nanning, Guangxi 530004, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Tianjin University, Tianjin, P.R.China","institution_ids":["https://openalex.org/I132369690"]},{"raw_affiliation_string":"Department of Computer Science, Guangxi University, Nanning, Guangxi 530004, P. R. China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028698583","display_name":"Xiujun Gong","orcid":"https://orcid.org/0000-0001-9591-2237"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]},{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]},{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xiujun Gong","raw_affiliation_strings":["Boyce Thompson Inst. for Plant Research, Cornell University Ithaca, NY, USA","School of Computer Science and Technology, Tianjin University, Tianjin. 300072, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boyce Thompson Inst. for Plant Research, Cornell University Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"School of Computer Science and Technology, Tianjin University, Tianjin. 300072, P. R. China","institution_ids":["https://openalex.org/I132369690","https://openalex.org/I136765683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075249897","display_name":"Shan Gao","orcid":"https://orcid.org/0000-0002-8919-1338"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Gao","raw_affiliation_strings":["College of Life Science Nankai University, Tianjin, P. R. CHINA","College of Life Science, Nankai University, Tianjin 300071, P. R. China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Life Science Nankai University, Tianjin, P. R. CHINA","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"College of Life Science, Nankai University, Tianjin 300071, P. R. China,","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6523,"has_fulltext":false,"cited_by_count":86,"citation_normalized_percentile":{"value":0.9043706,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"44","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9987000226974487,"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":0.9987000226974487,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9919999837875366,"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/T11482","display_name":"RNA modifications and cancer","score":0.9897000193595886,"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/computer-science","display_name":"Computer science","score":0.7263469099998474},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.6921623945236206},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.586700439453125},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.49919795989990234},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.36459702253341675},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36128950119018555},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.15014302730560303},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13086679577827454},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07825019955635071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7263469099998474},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.6921623945236206},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.586700439453125},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.49919795989990234},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36459702253341675},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36128950119018555},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.15014302730560303},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13086679577827454},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07825019955635071},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm.2014.6999309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2014.6999309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1963624291","https://openalex.org/W1964025768","https://openalex.org/W1974860827","https://openalex.org/W1984352173","https://openalex.org/W1987545661","https://openalex.org/W2034285706","https://openalex.org/W2042032060","https://openalex.org/W2071551712","https://openalex.org/W2076151007","https://openalex.org/W2080958324","https://openalex.org/W2090106709","https://openalex.org/W2094859679","https://openalex.org/W2103441770","https://openalex.org/W2107915254","https://openalex.org/W2110612552","https://openalex.org/W2111589020","https://openalex.org/W2131016694","https://openalex.org/W2131271579","https://openalex.org/W2139437267","https://openalex.org/W2141599418","https://openalex.org/W2164631613","https://openalex.org/W2164641338","https://openalex.org/W2172173047"],"related_works":["https://openalex.org/W4306381730","https://openalex.org/W4229060448","https://openalex.org/W2981692913","https://openalex.org/W3184035966","https://openalex.org/W3044188621","https://openalex.org/W2485605994","https://openalex.org/W4385571108","https://openalex.org/W2133028525","https://openalex.org/W2135768893","https://openalex.org/W3021414116"],"abstract_inverted_index":{"The":[0],"usability":[1],"of":[2,11,81],"the":[3,9,12,22,57,63,69,82,98,121,144,158],"NGS":[4,145],"technologies":[5],"heavily":[6],"relies":[7],"on":[8,115],"accuracy":[10],"data.":[13],"Many":[14],"research":[15],"groups":[16],"developed":[17],"different":[18],"programs":[19],"to":[20,39,55,142,156],"clean":[21,56,143],"sequenced":[23,91],"raw":[24],"data":[25,41,61,92,99,146],"by":[26,103],"removing":[27],"adapter":[28,74],"contamination":[29,75],"and":[30,59,73,77,93,136],"trimming":[31],"low-quality":[32],"nucleotides.":[33],"However,":[34],"they":[35],"are":[36],"not":[37],"optimized":[38,52],"process":[40,90],"from":[42,62,147],"any":[43],"specific":[44],"equipment.":[45],"In":[46],"this":[47],"study,":[48],"we":[49],"present":[50],"an":[51],"pipeline":[53],"Fastq_clean":[54,66,87,119,124],"DNA-seq":[58],"RNA-seq":[60],"illumina":[64],"sequencer.":[65],"can":[67,88,138],"remove":[68],"low":[70],"quality":[71,100],"nucleotides":[72,84],"precisely":[76],"keep":[78],"as":[79,85],"many":[80],"qualified":[83],"possible.":[86],"batchly":[89],"export":[94],"statistics":[95],"information":[96],"for":[97],"control":[101],"(QC)":[102],"running":[104],"a":[105,116],"single":[106],"command":[107],"line.":[108],"Compared":[109],"with":[110],"two":[111],"most":[112],"used":[113,129,141],"tools":[114],"published":[117],"dataset,":[118],"reached":[120],"best":[122],"performance.":[123,160],"has":[125],"already":[126],"been":[127],"successfully":[128],"in":[130],"some":[131,154],"genome":[132],"or":[133],"transcriptome":[134],"projects":[135],"it":[137],"also":[139],"be":[140],"other":[148],"sequencers":[149],"(e.g.":[150],"454),":[151],"but":[152],"needs":[153],"modification":[155],"reach":[157],"rest":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":9}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}