{"id":"https://openalex.org/W3116537144","doi":"https://doi.org/10.1109/mascots50786.2020.9285945","title":"Investigating Genome Analysis Pipeline Performance on GATK with Cloud Object Storage","display_name":"Investigating Genome Analysis Pipeline Performance on GATK with Cloud Object Storage","publication_year":2020,"publication_date":"2020-11-17","ids":{"openalex":"https://openalex.org/W3116537144","doi":"https://doi.org/10.1109/mascots50786.2020.9285945","mag":"3116537144"},"language":"en","primary_location":{"id":"doi:10.1109/mascots50786.2020.9285945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mascots50786.2020.9285945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS)","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/A5041846557","display_name":"Tatsuhiro Chiba","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tatsuhiro Chiba","raw_affiliation_strings":["IBM Research, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"IBM Research, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101886411","display_name":"Takeshi Yoshimura","orcid":"https://orcid.org/0000-0002-7147-4225"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Yoshimura","raw_affiliation_strings":["IBM Research, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"IBM Research, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041846557"],"corresponding_institution_ids":["https://openalex.org/I4210145865"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21189741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"526","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.995199978351593,"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":0.995199978351593,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9937000274658203,"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":0.84598708152771},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7527206540107727},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7209747433662415},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6737337708473206},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6587105989456177},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5152423977851868},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4584569036960602},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.44514578580856323},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4015713930130005},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.27885228395462036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.84598708152771},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7527206540107727},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7209747433662415},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6737337708473206},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6587105989456177},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5152423977851868},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4584569036960602},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.44514578580856323},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4015713930130005},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27885228395462036},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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/mascots50786.2020.9285945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mascots50786.2020.9285945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"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":18,"referenced_works":["https://openalex.org/W1919257374","https://openalex.org/W1996438407","https://openalex.org/W2104549677","https://openalex.org/W2106698002","https://openalex.org/W2119180969","https://openalex.org/W2119738171","https://openalex.org/W2189465200","https://openalex.org/W2411835995","https://openalex.org/W2415420807","https://openalex.org/W2613725055","https://openalex.org/W2745862296","https://openalex.org/W2805382875","https://openalex.org/W2806177468","https://openalex.org/W2912166765","https://openalex.org/W2913381374","https://openalex.org/W2994531552","https://openalex.org/W6687322159","https://openalex.org/W6715161035"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","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/W3191926225"],"abstract_inverted_index":{"Achieving":[0],"fast,":[1],"scalable,":[2],"and":[3,18,33,38,82,112,129,174],"cost-effective":[4],"genome":[5,27],"analytics":[6,47],"is":[7],"always":[8],"important":[9],"to":[10,96,121,144,160],"open":[11],"up":[12,143,159],"a":[13,45,50,65,88,93,133],"new":[14,94],"frontier":[15],"in":[16,49,64,102,165],"biomedical":[17],"life":[19],"science.":[20],"Genome":[21],"Analysis":[22],"Toolkit":[23],"(GATK),":[24],"an":[25],"industry-standard":[26],"analysis":[28],"tool,":[29],"improves":[30],"its":[31],"scalability":[32,84],"performance":[34,74,128],"by":[35],"leveraging":[36],"Spark":[37,40,79],"HDFS.":[39,150],"with":[41,80,138,149],"HDFS":[42,81],"has":[43],"been":[44],"leading":[46],"platform":[48],"past":[51],"few":[52],"years,":[53],"however,":[54],"the":[55,122,125,169],"system":[56],"cannot":[57],"exploit":[58],"full":[59],"advantage":[60],"of":[61,76,105,124],"cloud":[62],"elasticity":[63],"recent":[66],"modern":[67],"cloud.":[68],"In":[69],"this":[70,117,155],"paper":[71],"we":[72,91,135],"investigate":[73],"characteristics":[75],"GATK":[77,103,137,148],"using":[78],"identify":[83],"issues.":[85],"Based":[86],"on":[87],"quantitative":[89],"analysis,":[90],"introduce":[92],"approach":[95,118,156],"utilize":[97],"Cloud":[98],"Object":[99],"Storage":[100],"(COS)":[101],"instead":[104],"HDFS,":[106],"which":[107,167],"can":[108,119,141,157],"help":[109],"decoupling":[110],"compute":[111],"storage.":[113],"We":[114,151],"demonstrate":[115,136],"how":[116],"contribute":[120],"improvement":[123],"entire":[126],"pipeline":[127,176],"cost":[130,163],"saving.":[131],"As":[132],"result,":[134],"IBM":[139],"COS":[140],"achieve":[142,158],"28%":[145],"faster":[146],"than":[147],"also":[152],"show":[153],"that":[154],"67":[161],"%":[162],"saving":[164],"total,":[166],"includes":[168],"time":[170],"for":[171],"data":[172],"loading":[173],"whole":[175],"analysis.":[177]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}