{"id":"https://openalex.org/W2202435095","doi":"https://doi.org/10.1109/bibm.2015.7359893","title":"Cluster-based Apache Spark implementation of the GATK DNA analysis pipeline","display_name":"Cluster-based Apache Spark implementation of the GATK DNA analysis pipeline","publication_year":2015,"publication_date":"2015-11-01","ids":{"openalex":"https://openalex.org/W2202435095","doi":"https://doi.org/10.1109/bibm.2015.7359893","mag":"2202435095"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2015.7359893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2015.7359893","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5002503405","display_name":"Hamid Mushtaq","orcid":"https://orcid.org/0000-0003-4129-9056"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hamid Mushtaq","raw_affiliation_strings":["Computer Engineering Laboratory Delft University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering Laboratory Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021955713","display_name":"Zaid Al-Ars","orcid":"https://orcid.org/0000-0001-7670-8572"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Zaid Al-Ars","raw_affiliation_strings":["Computer Engineering Laboratory Delft University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering Laboratory Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":4.2358,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.95728196,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1471","last_page":"1477"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987999796867371,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987999796867371,"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/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/T11478","display_name":"Caching and Content Delivery","score":0.9908000230789185,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.876005232334137},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8587484359741211},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7714290618896484},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7699902057647705},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7210577726364136},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5745915174484253},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5335901975631714},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4752623438835144},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4606601595878601},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.4521988034248352},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4222705662250519},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.42079296708106995},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.38769441843032837},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3860143721103668},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.18617814779281616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.0920664370059967},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.070392906665802}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.876005232334137},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8587484359741211},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7714290618896484},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7699902057647705},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7210577726364136},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5745915174484253},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5335901975631714},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4752623438835144},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4606601595878601},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.4521988034248352},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4222705662250519},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.42079296708106995},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.38769441843032837},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3860143721103668},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.18617814779281616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0920664370059967},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.070392906665802},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm.2015.7359893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2015.7359893","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W938539187","https://openalex.org/W1919257374","https://openalex.org/W2095680943","https://openalex.org/W2131187246","https://openalex.org/W2159670728","https://openalex.org/W2166588423","https://openalex.org/W2168440186","https://openalex.org/W2610179052","https://openalex.org/W4394666350","https://openalex.org/W6674561012","https://openalex.org/W6684425937"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2799508461","https://openalex.org/W4246264554","https://openalex.org/W2962431048","https://openalex.org/W3112375919","https://openalex.org/W4233648438","https://openalex.org/W2793083950","https://openalex.org/W2969378954","https://openalex.org/W2510748453","https://openalex.org/W4213304158"],"abstract_inverted_index":{"Fast":[0],"progress":[1],"in":[2,15,34,92,127],"next":[3],"generation":[4],"sequencing":[5],"has":[6,30,139],"dramatically":[7],"increased":[8],"the":[9,16,32,48,93,112,128,131,154],"throughout":[10],"of":[11,18,56,59,63,90,111,153],"DNA":[12,20,28,95],"sequencing,":[13],"resulting":[14],"availability":[17],"large":[19],"data":[21,37,125],"sets":[22],"ready":[23],"for":[24],"analysis.":[25,50],"However,":[26],"post-sequencing":[27],"analysis":[29,53,96],"become":[31],"bottleneck":[33],"using":[35,115,150],"these":[36],"sets,":[38],"as":[39],"it":[40,138],"requires":[41],"powerful":[42],"and":[43,81,133],"scalable":[44],"tools":[45,74],"to":[46],"perform":[47],"needed":[49],"A":[51],"typical":[52],"pipeline":[54,114],"consists":[55],"a":[57,69,77,103,140,159,175],"number":[58],"steps,":[60],"not":[61],"all":[62],"which":[64],"can":[65],"readily":[66],"scale":[67],"on":[68,158],"distributed":[70,109],"computing":[71],"infrastructure.":[72],"Recently,":[73],"like":[75],"Halvade,":[76],"Hadoop":[78,176],"MapReduce":[79,177],"solution,":[80,86],"Churchill,":[82],"an":[83,107],"HPC":[84],"cluster-based":[85],"addressed":[87],"this":[88,99,169],"issue":[89],"scalability":[91],"GATK":[94,113],"pipeline.":[97],"In":[98,136],"paper,":[100],"we":[101],"present":[102],"framework":[104,119],"that":[105,145,168],"implements":[106],"in-memory":[108],"version":[110],"Apache":[116],"Spark.":[117],"Our":[118],"reduced":[120],"execution":[121],"time":[122],"by":[123],"keeping":[124],"active":[126,155],"memory":[129],"between":[130],"map":[132],"reduce":[134],"steps.":[135],"addition,":[137],"dynamic":[141],"load":[142],"balancing":[143],"algorithm":[144],"better":[146],"utilizes":[147],"system":[148],"performance":[149],"runtime":[151],"statistics":[152],"workload.":[156],"Experiments":[157],"4":[160],"node":[161],"cluster":[162],"with":[163],"64":[164],"virtual":[165],"cores":[166],"show":[167],"approach":[170],"is":[171],"63%":[172],"faster":[173],"than":[174],"based":[178],"solution.":[179]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}