{"id":"https://openalex.org/W3005482262","doi":"https://doi.org/10.1109/bibm47256.2019.8983385","title":"DGCF: A Distributed Greedy Clustering Framework for Large-scale Genomic Sequences","display_name":"DGCF: A Distributed Greedy Clustering Framework for Large-scale Genomic Sequences","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3005482262","doi":"https://doi.org/10.1109/bibm47256.2019.8983385","mag":"3005482262"},"language":"en","primary_location":{"id":"doi:10.1109/bibm47256.2019.8983385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm47256.2019.8983385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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/A5091033464","display_name":"Zekun Yin","orcid":"https://orcid.org/0000-0001-6002-0028"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]},{"id":"https://openalex.org/I4210105229","display_name":"City University of Hong Kong, Shenzhen Research Institute","ror":"https://ror.org/00xc0ma20","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210105229"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zekun Yin","raw_affiliation_strings":["Shenzhen Research Institute of Shandong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Shandong University","institution_ids":["https://openalex.org/I4210105229","https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024616744","display_name":"XU Xiao-ming","orcid":"https://orcid.org/0000-0002-0370-2222"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Xu","raw_affiliation_strings":["School of Software, Shandong University,Jinan,China","School of Software, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University,Jinan,China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008037948","display_name":"Kaichao Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaichao Fan","raw_affiliation_strings":["School of Software, Shandong University,Jinan,China","School of Software, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University,Jinan,China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046581897","display_name":"Ruilin Li","orcid":"https://orcid.org/0000-0001-9593-1235"},"institutions":[{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruilin Li","raw_affiliation_strings":["Computer Network Information Center, Chinese Academy of Sciences, University of Chinese Academy of Sciences,Beijing,China","Computer Network Information Center, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Network Information Center, Chinese Academy of Sciences, University of Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Computer Network Information Center, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027145422","display_name":"Weizhong Li","orcid":"https://orcid.org/0000-0003-1804-9403"},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weizhong Li","raw_affiliation_strings":["J. Craig Venter Institute,La Jolla,CA,USA,92037","J. Craig Venter Institute, La Jolla, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"J. Craig Venter Institute,La Jolla,CA,USA,92037","institution_ids":["https://openalex.org/I1301553790"]},{"raw_affiliation_string":"J. Craig Venter Institute, La Jolla, CA, USA","institution_ids":["https://openalex.org/I1301553790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620772","display_name":"Weiguo Liu","orcid":"https://orcid.org/0000-0001-8834-0453"},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiguo Liu","raw_affiliation_strings":["National Supercomputing Center in Wuxi,China","National Supercomputing Center in Wuxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Supercomputing Center in Wuxi,China","institution_ids":["https://openalex.org/I4210158984"]},{"raw_affiliation_string":"National Supercomputing Center in Wuxi, China","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008702128","display_name":"Beifang Niu","orcid":"https://orcid.org/0000-0002-7448-7793"},"institutions":[{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Beifang Niu","raw_affiliation_strings":["Computer Network Information Center, Chinese Academy of Sciences, University of Chinese Academy of Sciences,Beijing,China","Computer Network Information Center, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Network Information Center, Chinese Academy of Sciences, University of Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Computer Network Information Center, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.13898906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2272","last_page":"2279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9983000159263611,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9959999918937683,"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":0.8313992023468018},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7763845920562744},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.690645694732666},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.5503923892974854},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.47009703516960144},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.45702430605888367},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.42429038882255554},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.41957178711891174},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.41765299439430237},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38228556513786316},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23514437675476074},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.17249354720115662},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12746760249137878}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8313992023468018},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7763845920562744},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.690645694732666},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.5503923892974854},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.47009703516960144},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.45702430605888367},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42429038882255554},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.41957178711891174},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.41765299439430237},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38228556513786316},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23514437675476074},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.17249354720115662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12746760249137878},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm47256.2019.8983385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm47256.2019.8983385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2035890032","https://openalex.org/W2055043387","https://openalex.org/W2073548709","https://openalex.org/W2074231493","https://openalex.org/W2075996757","https://openalex.org/W2080728354","https://openalex.org/W2108211735","https://openalex.org/W2115313399","https://openalex.org/W2124351063","https://openalex.org/W2137995988","https://openalex.org/W2145853890","https://openalex.org/W2156125289","https://openalex.org/W2163681976","https://openalex.org/W2167519901","https://openalex.org/W2170747616","https://openalex.org/W2171196697","https://openalex.org/W2171963266","https://openalex.org/W2210475017","https://openalex.org/W2564293829","https://openalex.org/W2884258548","https://openalex.org/W2950954328","https://openalex.org/W4236236547","https://openalex.org/W6688119904","https://openalex.org/W6753675497"],"related_works":["https://openalex.org/W4401278057","https://openalex.org/W2027852278","https://openalex.org/W1570944919","https://openalex.org/W2070983336","https://openalex.org/W2150824771","https://openalex.org/W1837558792","https://openalex.org/W322664006","https://openalex.org/W1991465874","https://openalex.org/W2363502211","https://openalex.org/W2335046331"],"abstract_inverted_index":{"Clustering":[0,91],"is":[1,56,94],"a":[2,32,88,106,125,146],"very":[3],"fundamental":[4],"while":[5],"time-consuming":[6],"compute":[7],"operation":[8],"in":[9,73],"biological":[10],"sequence":[11],"analysis.":[12],"New":[13],"sequencing":[14],"technologies":[15],"such":[16,67],"as":[17,45,47,77,79],"NGS":[18],"and":[19,28,60,100,123],"3GS":[20],"have":[21],"dramatically":[22],"increased":[23],"both":[24,74],"the":[25,29],"dataset":[26],"size":[27],"length":[30],"of":[31,66],"single":[33],"read":[34],"sequence.":[35],"However,":[36],"existing":[37],"tools":[38],"lack":[39],"scalability":[40],"for":[41],"handling":[42],"large-scale":[43,98],"datasets":[44,99],"well":[46,78],"long":[48,101,135],"sequences.":[49,102,136],"A":[50],"feasible":[51],"solution":[52],"to":[53,57,96],"this":[54,83],"problem":[55],"use":[58],"parallel":[59],"distributed":[61,117,147],"systems.":[62],"The":[63],"efficient":[64],"deployment":[65],"systems,":[68],"however,":[69],"requires":[70],"high":[71],"parallelism":[72],"software":[75],"implementations":[76],"algorithmic":[80],"optimizations.":[81],"In":[82],"paper,":[84],"we":[85],"propose":[86],"DGCF,":[87],"Distributed":[89],"Greedy":[90],"Framework":[92],"which":[93,110],"capable":[95],"handle":[97],"Our":[103],"framework":[104,141],"adopts":[105],"greedy":[107],"clustering":[108],"strategy":[109],"overlaps":[111],"communication":[112],"with":[113],"computation":[114],"among":[115],"many":[116],"computing":[118],"nodes.":[119],"We":[120],"also":[121],"design":[122],"implement":[124],"sparse":[126],"suffix":[127],"array":[128],"(SSA)-based":[129],"alignment":[130],"algorithm":[131],"that":[132,139],"can":[133],"support":[134],"Experiments":[137],"show":[138],"our":[140],"achieves":[142],"near-linear":[143],"speedups":[144],"on":[145],"memory":[148],"cluster.":[149]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
