{"id":"https://openalex.org/W2913381374","doi":"https://doi.org/10.1109/bibm.2018.8621208","title":"Optimization of Genomics Analysis Pipeline for Scalable Performance in a Cloud Environment","display_name":"Optimization of Genomics Analysis Pipeline for Scalable Performance in a Cloud Environment","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2913381374","doi":"https://doi.org/10.1109/bibm.2018.8621208","mag":"2913381374"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2018.8621208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2018.8621208","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/A5102349258","display_name":"Carlos H. \u00c3. Costa","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Carlos H.A. Costa","raw_affiliation_strings":["IBM Research, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007904705","display_name":"Claudia Misale","orcid":"https://orcid.org/0000-0003-3737-7373"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Claudia Misale","raw_affiliation_strings":["IBM Research, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006587869","display_name":"Frank Liu","orcid":"https://orcid.org/0000-0001-6615-0739"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank Liu","raw_affiliation_strings":["IBM Research, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106032001","display_name":"M\u00e1rcio Silva","orcid":"https://orcid.org/0000-0002-2804-6903"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcio Silva","raw_affiliation_strings":["IBM Research, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038903691","display_name":"Hubertus Franke","orcid":"https://orcid.org/0009-0005-0150-1055"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hubertus Franke","raw_affiliation_strings":["IBM Research, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009418528","display_name":"P. Crumley","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Crumley","raw_affiliation_strings":["IBM Research, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035616527","display_name":"Bruce D\u2019Amora","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bruce D'Amora","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, US"],"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, US","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102349258"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3269,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58557779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"207","issue":null,"first_page":"1147","last_page":"1154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11407","display_name":"Innovative Microfluidic and Catalytic Techniques Innovation","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11407","display_name":"Innovative Microfluidic and Catalytic Techniques Innovation","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.984499990940094,"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":0.8031757473945618},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7508029937744141},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7442895174026489},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6559341549873352},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.5861865282058716},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.47673049569129944},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.405036598443985},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21438398957252502}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8031757473945618},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7508029937744141},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7442895174026489},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6559341549873352},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.5861865282058716},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.47673049569129944},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.405036598443985},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21438398957252502},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm.2018.8621208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2018.8621208","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":[{"score":0.6499999761581421,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1919257374","https://openalex.org/W2103441770","https://openalex.org/W2104846587","https://openalex.org/W2189371416","https://openalex.org/W2189465200","https://openalex.org/W2550585696","https://openalex.org/W2745862296","https://openalex.org/W2770095154","https://openalex.org/W6687322159","https://openalex.org/W6746163975"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4394895745","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W4308507533","https://openalex.org/W2407107767","https://openalex.org/W2799508461"],"abstract_inverted_index":{"Cost-effective":[0],"and":[1,49,68,81,97],"scalable":[2],"analysis":[3,32],"of":[4,13,19,70,95,108,117],"the":[5,11,20,56,66,86,109,115],"human":[6,137],"genome":[7,138],"is":[8],"crucial":[9],"for":[10,29,45,135],"democratization":[12],"precision":[14],"medicine.":[15],"The":[16],"new":[17],"version":[18],"Genome":[21],"Analysis":[22],"Toolkit":[23],"(GATK4),":[24],"an":[25,91],"industry-standard":[26],"end-to-end":[27],"tool":[28],"variant":[30],"discovery":[31],"in":[33,102],"next-generation":[34,75],"sequencing":[35],"(NGS)":[36],"data,":[37],"introduces":[38],"Apache":[39],"Spark":[40,96],"support":[41],"to":[42],"improve":[43],"scaling":[44,82],"both":[46],"local":[47],"multithreading":[48],"cluster-wide":[50],"parallelization,":[51],"as":[52,54],"well":[53],"facilitate":[55],"deployment":[57],"on":[58,73,122],"cloud":[59,76],"infrastructures.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64,84],"evaluate":[65],"performance":[67],"scalability":[69],"GATK4-Spark":[71],"running":[72],"a":[74,123],"platform.":[77],"After":[78],"identifying":[79],"bottlenecks":[80],"challenges,":[83],"optimize":[85],"software":[87],"stack":[88],"that":[89],"includes":[90],"optimized":[92],"JVM,":[93],"enhancements":[94],"targeted":[98],"configuration":[99],"tuning,":[100],"which":[101],"turn":[103],"enables":[104],"more":[105],"effective":[106],"use":[107],"underlying":[110],"computing":[111],"resources.":[112],"We":[113],"demonstrate":[114],"effectiveness":[116],"our":[118],"comprehensive":[119],"optimization":[120],"techniques":[121],"reference":[124],"Single":[125],"Nucleotide":[126],"Polymorphisms":[127],"(SNPs)":[128],"pipeline,":[129],"achieving":[130],"\u22641":[131],"hr":[132],"computation":[133],"time":[134],"whole":[136],"analysis.":[139]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}