{"id":"https://openalex.org/W3203222421","doi":"https://doi.org/10.1093/bioinformatics/btab696","title":"FastqCLS: a FASTQ compressor for long-read sequencing via read reordering using a novel scoring model","display_name":"FastqCLS: a FASTQ compressor for long-read sequencing via read reordering using a novel scoring model","publication_year":2021,"publication_date":"2021-10-06","ids":{"openalex":"https://openalex.org/W3203222421","doi":"https://doi.org/10.1093/bioinformatics/btab696","mag":"3203222421","pmid":"https://pubmed.ncbi.nlm.nih.gov/34623374"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab696","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab696","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","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/A5083583236","display_name":"Dohyeon Lee","orcid":"https://orcid.org/0000-0003-0977-3723"},"institutions":[{"id":"https://openalex.org/I4921948","display_name":"Pusan National University","ror":"https://ror.org/01an57a31","country_code":"KR","type":"education","lineage":["https://openalex.org/I4921948"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dohyeon Lee","raw_affiliation_strings":["School of Computer Science and Engineering, Pusan National University , Busan 46241, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Pusan National University , Busan 46241, South Korea","institution_ids":["https://openalex.org/I4921948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012853928","display_name":"Giltae Song","orcid":"https://orcid.org/0000-0001-8796-4678"},"institutions":[{"id":"https://openalex.org/I4921948","display_name":"Pusan National University","ror":"https://ror.org/01an57a31","country_code":"KR","type":"education","lineage":["https://openalex.org/I4921948"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Giltae Song","raw_affiliation_strings":["School of Computer Science and Engineering, Pusan National University , Busan 46241, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-8796-4678","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Pusan National University , Busan 46241, South Korea","institution_ids":["https://openalex.org/I4921948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5012853928"],"corresponding_institution_ids":["https://openalex.org/I4921948"],"apc_list":{"value":3478,"currency":"USD","value_usd":3478},"apc_paid":null,"fwci":1.4021,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8476284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"38","issue":"2","first_page":"351","last_page":"356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.46480000019073486,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.46480000019073486,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.4302999973297119,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.012600000016391277,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.8552308082580566},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.6090662479400635},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5645458698272705},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5609113574028015},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5456089377403259},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.5292438864707947},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21149185299873352},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08188199996948242}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8552308082580566},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6090662479400635},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5645458698272705},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5609113574028015},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5456089377403259},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5292438864707947},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21149185299873352},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08188199996948242},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btab696","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab696","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34623374","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34623374","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,"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":"Bioinformatics (Oxford, England)","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.44999998807907104,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G6276415885","display_name":null,"funder_award_id":"2021R1A2C2010775","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G6988067448","display_name":null,"funder_award_id":"2020-0-01450","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1931027898","https://openalex.org/W1982703709","https://openalex.org/W2020255088","https://openalex.org/W2092880969","https://openalex.org/W2101247207","https://openalex.org/W2104846587","https://openalex.org/W2107845669","https://openalex.org/W2109153336","https://openalex.org/W2111044311","https://openalex.org/W2114792961","https://openalex.org/W2125557405","https://openalex.org/W2153707226","https://openalex.org/W2166588423","https://openalex.org/W2170727800","https://openalex.org/W2207690983","https://openalex.org/W2464063823","https://openalex.org/W2466892528","https://openalex.org/W2527708324","https://openalex.org/W2538355508","https://openalex.org/W2735067671","https://openalex.org/W2764165465","https://openalex.org/W2807773783","https://openalex.org/W2899544675","https://openalex.org/W2905575949","https://openalex.org/W2951070849","https://openalex.org/W2952969776","https://openalex.org/W2983510300","https://openalex.org/W2999136320","https://openalex.org/W3117504517","https://openalex.org/W6697520301","https://openalex.org/W6772713401"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W2086519370","https://openalex.org/W2028665553","https://openalex.org/W2087343574","https://openalex.org/W2535915176","https://openalex.org/W4241634354","https://openalex.org/W2354111411"],"abstract_inverted_index":{"MOTIVATION:":[0],"Over":[1],"the":[2,50],"past":[3],"decades,":[4],"vast":[5],"amounts":[6],"of":[7,18,52,124,165],"genome":[8,35],"sequencing":[9,36,56,63,77,153,171],"data":[10,31,106,154,185],"have":[11,45],"been":[12,46],"produced,":[13],"requiring":[14],"an":[15],"enormous":[16],"level":[17],"storage":[19],"capacity.":[20],"The":[21],"time":[22],"and":[23,28,115,126,133],"resources":[24],"needed":[25],"to":[26,48,128],"store":[27],"transfer":[29],"such":[30],"cause":[32],"bottlenecks":[33],"in":[34,67,155,163],"analysis.":[37],"To":[38],"resolve":[39],"this":[40,156],"issue,":[41],"various":[42],"compression":[43,72,83,143,166],"techniques":[44],"proposed":[47],"reduce":[49],"size":[51,98],"original":[53],"FASTQ":[54,96,142],"raw":[55],"data,":[57],"but":[58],"these":[59],"remain":[60],"suboptimal.":[61],"Long-read":[62],"has":[64],"become":[65],"dominant":[66],"genomics,":[68],"whereas":[69],"most":[70],"existing":[71,140],"methods":[73],"focus":[74],"on":[75,86],"short-read":[76],"only.":[78],"RESULTS:":[79],"We":[80,103,135,148],"designed":[81],"a":[82,90,110,119,159],"algorithm":[84],"based":[85],"read":[87],"reordering":[88],"using":[89,145],"novel":[91],"scoring":[92],"model":[93],"for":[94,122,168],"reducing":[95],"file":[97],"with":[99,139],"no":[100],"information":[101],"loss.":[102],"integrated":[104],"all":[105],"processing":[107],"steps":[108],"into":[109],"software":[111],"package":[112],"called":[113],"FastqCLS":[114,161,176],"provided":[116],"it":[117],"as":[118],"Docker":[120],"image":[121],"ease":[123],"installation":[125],"execution":[127],"help":[129],"users":[130],"easily":[131],"install":[132],"run.":[134],"compared":[136],"our":[137],"method":[138],"major":[141],"tools":[144],"benchmark":[146],"datasets.":[147],"also":[149],"included":[150],"new":[151],"long-read":[152,170],"validation.":[157],"As":[158],"result,":[160],"outperformed":[162],"terms":[164],"ratios":[167],"storing":[169],"data.":[172],"AVAILABILITY":[173],"AND":[174],"IMPLEMENTATION:":[175],"can":[177],"be":[178],"downloaded":[179],"from":[180],"https://github.com/krlucete/FastqCLS.":[181],"SUPPLEMENTARY":[182],"INFORMATION:":[183],"Supplementary":[184],"are":[186],"available":[187],"at":[188],"Bioinformatics":[189],"online.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}
