{"id":"https://openalex.org/W4214950035","doi":"https://doi.org/10.1109/paap54281.2021.9720451","title":"Efficient Distributed Parallel Aligning Reads and Reference Genome with Many Repetitive Subsequences Using Compact de Bruijn Graph","display_name":"Efficient Distributed Parallel Aligning Reads and Reference Genome with Many Repetitive Subsequences Using Compact de Bruijn Graph","publication_year":2021,"publication_date":"2021-12-10","ids":{"openalex":"https://openalex.org/W4214950035","doi":"https://doi.org/10.1109/paap54281.2021.9720451"},"language":"en","primary_location":{"id":"doi:10.1109/paap54281.2021.9720451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/paap54281.2021.9720451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Parallel Architectures, Algorithms and Programming (PAAP)","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/A5100727373","display_name":"Yao Li","orcid":"https://orcid.org/0000-0001-8720-3027"},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yao Li","raw_affiliation_strings":["School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University,Key Laboratory of Parallel,Nanning,China","Key Laboratory of Parallel, School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University,Key Laboratory of Parallel,Nanning,China","institution_ids":["https://openalex.org/I150807315"]},{"raw_affiliation_string":"Key Laboratory of Parallel, School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101747550","display_name":"Cheng Zhong","orcid":"https://orcid.org/0000-0002-5560-2151"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Zhong","raw_affiliation_strings":["School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University,Key Laboratory of Parallel,Nanning,China","Key Laboratory of Parallel, School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University,Key Laboratory of Parallel,Nanning,China","institution_ids":["https://openalex.org/I150807315"]},{"raw_affiliation_string":"Key Laboratory of Parallel, School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652781","display_name":"Danyang Chen","orcid":"https://orcid.org/0009-0006-2124-6845"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danyang Chen","raw_affiliation_strings":["School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University,Key Laboratory of Parallel,Nanning,China","Key Laboratory of Parallel, School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University,Key Laboratory of Parallel,Nanning,China","institution_ids":["https://openalex.org/I150807315"]},{"raw_affiliation_string":"Key Laboratory of Parallel, School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049834143","display_name":"Jinxiong Zhang","orcid":"https://orcid.org/0000-0002-8733-4622"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxiong Zhang","raw_affiliation_strings":["School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University,Key Laboratory of Parallel,Nanning,China","Key Laboratory of Parallel, School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University,Key Laboratory of Parallel,Nanning,China","institution_ids":["https://openalex.org/I150807315"]},{"raw_affiliation_string":"Key Laboratory of Parallel, School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104039802","display_name":"Mengxiao Yin","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxiao Yin","raw_affiliation_strings":["School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University,Key Laboratory of Parallel,Nanning,China","Key Laboratory of Parallel, School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University, Nanning, China"],"affiliations":[{"raw_affiliation_string":"School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University,Key Laboratory of Parallel,Nanning,China","institution_ids":["https://openalex.org/I150807315"]},{"raw_affiliation_string":"Key Laboratory of Parallel, School of Computer, Electronics and Information, Distributed Computing Technology in Guangxi Universities Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100727373"],"corresponding_institution_ids":["https://openalex.org/I150807315"],"apc_list":null,"apc_paid":null,"fwci":0.2435,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.54478057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9782999753952026,"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/T10434","display_name":"Chromosomal and Genetic Variations","score":0.9386000037193298,"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/de-bruijn-graph","display_name":"De Bruijn graph","score":0.8684966564178467},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.8420795202255249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7888455390930176},{"id":"https://openalex.org/keywords/smith\u2013waterman-algorithm","display_name":"Smith\u2013Waterman algorithm","score":0.48335665464401245},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.46149763464927673},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.41567462682724},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.38794824481010437},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.34961622953414917},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.322738379240036},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3214935064315796},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.26101645827293396},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12595820426940918}],"concepts":[{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.8684966564178467},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.8420795202255249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7888455390930176},{"id":"https://openalex.org/C72802188","wikidata":"https://www.wikidata.org/wiki/Q1683352","display_name":"Smith\u2013Waterman algorithm","level":5,"score":0.48335665464401245},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46149763464927673},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.41567462682724},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38794824481010437},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.34961622953414917},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.322738379240036},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3214935064315796},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.26101645827293396},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12595820426940918},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/paap54281.2021.9720451","is_oa":false,"landing_page_url":"https://doi.org/10.1109/paap54281.2021.9720451","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Parallel Architectures, Algorithms and Programming (PAAP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2353777085","display_name":null,"funder_award_id":"61962004,61462005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1813440684","https://openalex.org/W1990073900","https://openalex.org/W2017928178","https://openalex.org/W2103441770","https://openalex.org/W2121762798","https://openalex.org/W2124960286","https://openalex.org/W2124985265","https://openalex.org/W2171777347","https://openalex.org/W2398924165","https://openalex.org/W2474973645","https://openalex.org/W2783921626","https://openalex.org/W2952681371","https://openalex.org/W4394666350","https://openalex.org/W6674561012"],"related_works":["https://openalex.org/W2120956621","https://openalex.org/W2915362964","https://openalex.org/W3215786367","https://openalex.org/W3205360317","https://openalex.org/W4214573178","https://openalex.org/W2562683361","https://openalex.org/W3200242814","https://openalex.org/W4200364103","https://openalex.org/W4282946044","https://openalex.org/W2340761128"],"abstract_inverted_index":{"A":[0],"large":[1],"number":[2,107],"of":[3,108,117,152],"reads":[4,41,87,183],"generated":[5],"by":[6],"the":[7,29,36,81,92,97,102,106,115,130,150,154,170,178],"next":[8],"generation":[9],"sequencing":[10],"platform":[11],"will":[12,26],"contain":[13],"many":[14,46],"repetitive":[15,24,47,189],"subsequences.":[16,190],"Effective":[17],"localizing":[18],"and":[19,42,79,88,105,162,184],"identifying":[20],"genomic":[21,31],"regions":[22],"containing":[23],"subsequences":[25],"contribute":[27],"to":[28,74,84,91,95,113],"subsequent":[30],"data":[32,71,98],"analysis.":[33],"To":[34],"accelerate":[35],"alignment":[37,59,138,144,157,168,179],"between":[38,180],"large-scale":[39,181],"short":[40,86,182],"reference":[43,89,185],"genome":[44,90,186],"with":[45,129,164,187],"subsequences,":[48],"this":[49],"paper":[50],"develops":[51],"a":[52,160],"compact":[53,131],"de":[54,132],"Bruijn":[55,133],"graph":[56,134],"based":[57,135],"short-read":[58,137],"algorithm":[60,67,145,173],"on":[61,101,123,149],"distributed":[62,70,142,166],"parallel":[63,118,143,167,172],"computing":[64,93],"platform.":[65],"The":[66],"uses":[68],"resilient":[69],"sets":[72],"(RDDS)":[73],"perform":[75],"calculations":[76],"in":[77],"memory,":[78],"executes":[80],"broadcast":[82],"method":[83],"distribute":[85],"nodes":[94],"reduce":[96],"communication":[99],"time":[100],"cluster":[103],"system,":[104],"RDD":[109],"partitions":[110],"is":[111],"set":[112],"optimize":[114],"performance":[116],"aligning":[119],"algorithm.":[120],"Experimental":[121],"results":[122],"real":[124],"datasets":[125],"show":[126],"that":[127],"compared":[128,163],"sequential":[136],"algorithm,":[139],"our":[140],"implemented":[141,171],"achieves":[146],"good":[147],"acceleration":[148],"premise":[151],"obtaining":[153],"same":[155],"correct":[156],"percentage":[158],"as":[159],"whole,":[161],"existing":[165],"algorithms,":[169],"can":[174],"more":[175],"quickly":[176],"complete":[177],"highly":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}