{"id":"https://openalex.org/W2912166765","doi":"https://doi.org/10.1109/bibm.2018.8621495","title":"CloudGT: A High Performance Genome Analysis Toolkit Leveraging Pipeline Optimization on Spark","display_name":"CloudGT: A High Performance Genome Analysis Toolkit Leveraging Pipeline Optimization on Spark","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2912166765","doi":"https://doi.org/10.1109/bibm.2018.8621495","mag":"2912166765"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2018.8621495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2018.8621495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5068977983","display_name":"Anghong Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Anghong Xiao","raw_affiliation_strings":["Communication & Computer Network Lab of Guangdong, South China University of Technology Wushan Road 381, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Communication & Computer Network Lab of Guangdong, South China University of Technology Wushan Road 381, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052760299","display_name":"Shoubin Dong","orcid":"https://orcid.org/0000-0003-0153-850X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shoubin Dong","raw_affiliation_strings":["Communication & Computer Network Lab of Guangdong, South China University of Technology Wushan Road 381, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Communication & Computer Network Lab of Guangdong, South China University of Technology Wushan Road 381, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384309","display_name":"Cheng Liu","orcid":"https://orcid.org/0000-0002-5542-7306"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Liu","raw_affiliation_strings":["Communication & Computer Network Lab of Guangdong, South China University of Technology Wushan Road 381, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Communication & Computer Network Lab of Guangdong, South China University of Technology Wushan Road 381, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078250463","display_name":"Lingqi Zhang","orcid":"https://orcid.org/0000-0002-2452-1551"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingqi Zhang","raw_affiliation_strings":["Communication & Computer Network Lab of Guangdong, South China University of Technology Wushan Road 381, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Communication & Computer Network Lab of Guangdong, South China University of Technology Wushan Road 381, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053349477","display_name":"Zongze Wu","orcid":"https://orcid.org/0000-0002-2115-8670"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongze Wu","raw_affiliation_strings":["Communication & Computer Network Lab of Guangdong, South China University of Technology Wushan Road 381, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"Communication & Computer Network Lab of Guangdong, South China University of Technology Wushan Road 381, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068977983"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.1845,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58520719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"43","issue":null,"first_page":"1343","last_page":"1350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.968500018119812,"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/spark","display_name":"SPARK (programming language)","score":0.819722592830658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7711420655250549},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7570645809173584},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.756340503692627},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5381160378456116},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5265588760375977},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46153438091278076},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4600309133529663},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4496050179004669},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3221358060836792},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2610342800617218},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2038705050945282},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12098151445388794},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07504376769065857}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.819722592830658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7711420655250549},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7570645809173584},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.756340503692627},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5381160378456116},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5265588760375977},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46153438091278076},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4600309133529663},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4496050179004669},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3221358060836792},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2610342800617218},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2038705050945282},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12098151445388794},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07504376769065857},{"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm.2018.8621495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2018.8621495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1909034474","https://openalex.org/W1919257374","https://openalex.org/W2058087601","https://openalex.org/W2103441770","https://openalex.org/W2105821863","https://openalex.org/W2108234281","https://openalex.org/W2131187246","https://openalex.org/W2149140091","https://openalex.org/W2149992227","https://openalex.org/W2159670728","https://openalex.org/W2166588423","https://openalex.org/W2202435095","https://openalex.org/W2217498234","https://openalex.org/W2542459869","https://openalex.org/W2575651982","https://openalex.org/W2579188339","https://openalex.org/W2745862296","https://openalex.org/W6733087648"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W2799508461","https://openalex.org/W2781863720"],"abstract_inverted_index":{"The":[0,160],"rapid":[1],"development":[2],"of":[3,13,39,70,83],"NGS":[4],"(Next":[5],"Generation":[6],"Sequencing)":[7],"leads":[8],"to":[9,22,79,97,116,131],"the":[10,34,81,99,106,132,138,172],"explosive":[11],"increase":[12],"genome":[14,40,52,64,84,144],"data.":[15],"Massive":[16],"data":[17,25],"pose":[18],"a":[19,49,87,151],"great":[20],"challenge":[21],"post-sequencing":[23],"genomic":[24],"analysis":[26,41,53,65,85],"process":[27,66],"and":[28,36,72,102,114,122,127,135,154,158,168,174,181],"put":[29],"forward":[30],"higher":[31,187],"requirements":[32],"for":[33],"performance":[35,51,82,157],"pipeline":[37,56,88,133,162],"optimization":[38,57,89,134],"tools.":[42],"In":[43,77,141],"this":[44],"paper,":[45],"we":[46],"present":[47],"CloudGT,":[48],"high":[50,156],"toolkit":[54],"leveraging":[55],"based":[58,91,183],"on":[59,92,150,184],"Apache":[60],"Spark.":[61],"CloudGT":[62,147],"accelerates":[63],"by":[67],"implementing":[68],"parallelization":[69],"multi-core":[71],"multi-node":[73],"using":[74],"Spark":[75],"framework.":[76],"order":[78],"improve":[80,137],"process,":[86],"strategy":[90],"Parquet":[93],"storage":[94,100,166],"is":[95,148,175],"presented":[96],"reduce":[98],"space":[101,167],"I/O":[103],"overhead":[104],"throughout":[105],"process.":[107],"Three":[108],"main":[109],"tools":[110],"including":[111],"CloudBWAMem,":[112],"CloudDuplicateMark":[113],"CloudHaplotypeCaller":[115],"support":[117],"read":[118],"aligning,":[119],"duplicate":[120],"marking":[121],"variant":[123],"calling":[124],"are":[125],"optimized":[126,161],"implemented":[128],"which":[129],"adapt":[130],"further":[136],"overall":[139],"performance.":[140],"our":[142],"whole":[143],"sequencing":[145],"experiments,":[146],"evaluated":[149],"10-node":[152],"cluster":[153,185],"achieves":[155],"scalability.":[159],"totally":[163],"reduces":[164],"80.95%":[165],"14.32%":[169],"runtime":[170],"than":[171,178],"unoptimized":[173],"26.6%-74.9%":[176],"faster":[177],"state-of-the-art":[179],"toolkits":[180],"approaches":[182],"with":[186],"accuracy.":[188]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
