{"id":"https://openalex.org/W4281396148","doi":"https://doi.org/10.1109/cscwd54268.2022.9776028","title":"FQCSpark: Efficient Spark-based Parallel Compression Algorithm for FASTQ Genome Sequences","display_name":"FQCSpark: Efficient Spark-based Parallel Compression Algorithm for FASTQ Genome Sequences","publication_year":2022,"publication_date":"2022-05-04","ids":{"openalex":"https://openalex.org/W4281396148","doi":"https://doi.org/10.1109/cscwd54268.2022.9776028"},"language":"en","primary_location":{"id":"doi:10.1109/cscwd54268.2022.9776028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd54268.2022.9776028","pdf_url":null,"source":{"id":"https://openalex.org/S4363607909","display_name":"2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","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/A5053206926","display_name":"Yimu Ji","orcid":"https://orcid.org/0000-0001-7019-3942"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yimu Ji","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications,School of Computer Science,Nanjing,China","School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications,School of Computer Science,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055246773","display_name":"Hu Fa","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu Fa","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications,School of Computer Science,Nanjing,China","School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications,School of Computer Science,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055106904","display_name":"Haichang Yao","orcid":"https://orcid.org/0000-0002-5751-960X"},"institutions":[{"id":"https://openalex.org/I4210101451","display_name":"Nanjing Institute of Industry Technology","ror":"https://ror.org/00qf07q44","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210101451"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haichang Yao","raw_affiliation_strings":["Nanjing Institute of Industry Technology,School of Computer and Software,Nanjing,China","School of Computer and Software, Nanjing Institute of Industry Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing Institute of Industry Technology,School of Computer and Software,Nanjing,China","institution_ids":["https://openalex.org/I4210101451"]},{"raw_affiliation_string":"School of Computer and Software, Nanjing Institute of Industry Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210101451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108825823","display_name":"Sisi Shao","orcid":"https://orcid.org/0009-0005-9026-0133"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sisi Shao","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications,School of Computer Science,Nanjing,China","School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications,School of Computer Science,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043939777","display_name":"Wu Mengxue","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxue Wu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications,School of Computer Science,Nanjing,China","School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications,School of Computer Science,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037684646","display_name":"Houzhi Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houzhi Fang","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications,School of Computer Science,Nanjing,China","School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications,School of Computer Science,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409523","display_name":"Qiang Liu","orcid":"https://orcid.org/0000-0003-1375-0508"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Liu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications,School of Computer Science,Nanjing,China","School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications,School of Computer Science,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021798148","display_name":"Shangdong Liu","orcid":"https://orcid.org/0000-0002-8511-7544"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangdong Liu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications,School of Computer Science,Nanjing,China","School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications,School of Computer Science,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5053206926"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.2078,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.38122172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"671","last_page":"676"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9977999925613403,"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/T11247","display_name":"Plant nutrient uptake and metabolism","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8263694047927856},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7135969400405884},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6555672883987427},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.5036241412162781},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.49318522214889526},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4402835965156555},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43248865008354187},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.42120561003685},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07387885451316833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8263694047927856},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7135969400405884},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6555672883987427},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.5036241412162781},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.49318522214889526},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4402835965156555},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43248865008354187},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.42120561003685},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07387885451316833},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cscwd54268.2022.9776028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cscwd54268.2022.9776028","pdf_url":null,"source":{"id":"https://openalex.org/S4363607909","display_name":"2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335471","display_name":"Jiangsu Planned Projects for Postdoctoral Research Funds","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2111044311","https://openalex.org/W2114792961","https://openalex.org/W2117608012","https://openalex.org/W2119738171","https://openalex.org/W2259096502","https://openalex.org/W2538355508","https://openalex.org/W2597471102","https://openalex.org/W3011222295","https://openalex.org/W3132214945","https://openalex.org/W3137279194"],"related_works":["https://openalex.org/W1940589050","https://openalex.org/W1993191611","https://openalex.org/W4248655967","https://openalex.org/W2138520521","https://openalex.org/W2338363223","https://openalex.org/W2544870670","https://openalex.org/W3002912422","https://openalex.org/W2013149182","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"The":[0,34],"rapid":[1],"development":[2],"of":[3,17,57,65,109,121],"Next-Generation":[4],"Sequencing":[5],"(NGS)":[6],"technologies":[7],"has":[8],"posed":[9],"serious":[10],"challenges":[11],"to":[12,30,47,54,105,130],"the":[13,21,55,62,106,119,145,153,163],"storage":[14],"and":[15,20,45,112],"transmission":[16],"genomic":[18],"data,":[19],"bioinformatics":[22],"community":[23],"urgently":[24],"needs":[25],"efficient":[26,75],"genome":[27,32,39,59,81,156,172],"compression":[28,40,60,77,95,141,157,168],"algorithms":[29,41,92,132],"support":[31],"analysis.":[33],"existing":[35,91],"acceleration":[36],"approaches":[37],"for":[38,79,170],"are":[42],"mostly":[43],"multithreading":[44],"limited":[46],"a":[48,73],"single":[49],"machine,":[50],"which":[51,133,148],"cannot":[52],"adapt":[53],"demand":[56],"large-scale":[58],"in":[61,100,124],"distributed":[63],"environment":[64],"cloud":[66],"computing.":[67],"In":[68],"this":[69,125],"paper,":[70],"we":[71],"propose":[72],"Spark-based":[74,166],"parallel":[76,114,167],"algorithm":[78,169],"FASTQ":[80,171],"sequences":[82],"-":[83,159],"FQCSpark.":[84],"Experimental":[85],"results":[86],"show":[87],"that":[88],"FQCSpark":[89,138,161],"outperforms":[90],"with":[93],"good":[94,140],"ratios":[96],"by":[97],"several":[98],"times":[99],"speed.":[101],"This":[102],"is":[103,127,149,162],"due":[104],"fine-grained":[107],"degree":[108,120],"parallelism":[110,122],"design":[111,123],"well-designed":[113],"operator":[115],"flow.":[116],"More":[117],"importantly,":[118],"paper":[126],"also":[128],"applicable":[129],"other":[131],"compress":[134],"blocks":[135],"independently.":[136],"Meanwhile,":[137],"provides":[139],"ratios,":[142],"especially":[143],"on":[144],"S.cerevisiae":[146],"dataset,":[147],"15.4%":[150],"better":[151],"than":[152],"latest":[154],"open-source":[155],"tool":[158],"Genozip.":[160],"first":[164],"known":[165],"sequences.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
