{"id":"https://openalex.org/W2206932046","doi":"https://doi.org/10.1109/bibe.2015.7367654","title":"Optimization of data-intensive next generation sequencing in high performance computing","display_name":"Optimization of data-intensive next generation sequencing in high performance computing","publication_year":2015,"publication_date":"2015-11-01","ids":{"openalex":"https://openalex.org/W2206932046","doi":"https://doi.org/10.1109/bibe.2015.7367654","mag":"2206932046"},"language":"en","primary_location":{"id":"doi:10.1109/bibe.2015.7367654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibe.2015.7367654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 15th International Conference on Bioinformatics and Bioengineering (BIBE)","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/A5045629807","display_name":"Nagarajan Kathiresan","orcid":"https://orcid.org/0000-0002-5558-6331"},"institutions":[{"id":"https://openalex.org/I4210130525","display_name":"Sidra Medical and Research Center","ror":"https://ror.org/03acdk243","country_code":"QA","type":"healthcare","lineage":["https://openalex.org/I4210130525"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Nagarajan Kathiresan","raw_affiliation_strings":["SIDRA Medical and Research Center, Biomedical Informatics division, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SIDRA Medical and Research Center, Biomedical Informatics division, Doha, Qatar","institution_ids":["https://openalex.org/I4210130525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111458710","display_name":"Rashid Al\u2010Ali","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130525","display_name":"Sidra Medical and Research Center","ror":"https://ror.org/03acdk243","country_code":"QA","type":"healthcare","lineage":["https://openalex.org/I4210130525"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Rashid Al-Ali","raw_affiliation_strings":["SIDRA Medical and Research Center, Biomedical Informatics division, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SIDRA Medical and Research Center, Biomedical Informatics division, Doha, Qatar","institution_ids":["https://openalex.org/I4210130525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046007476","display_name":"Puthen V. Jithesh","orcid":"https://orcid.org/0000-0001-7747-0930"},"institutions":[{"id":"https://openalex.org/I4210130525","display_name":"Sidra Medical and Research Center","ror":"https://ror.org/03acdk243","country_code":"QA","type":"healthcare","lineage":["https://openalex.org/I4210130525"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Puthen V. Jithesh","raw_affiliation_strings":["SIDRA Medical and Research Center, Biomedical Informatics division, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SIDRA Medical and Research Center, Biomedical Informatics division, Doha, Qatar","institution_ids":["https://openalex.org/I4210130525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000607922","display_name":"Tariq AbuZaid","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130525","display_name":"Sidra Medical and Research Center","ror":"https://ror.org/03acdk243","country_code":"QA","type":"healthcare","lineage":["https://openalex.org/I4210130525"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Tariq AbuZaid","raw_affiliation_strings":["Sidra Medical and Research Center, Doha, Ad Dawhah, QA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sidra Medical and Research Center, Doha, Ad Dawhah, QA","institution_ids":["https://openalex.org/I4210130525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075604645","display_name":"Ramzi Temanni","orcid":"https://orcid.org/0000-0001-9125-1136"},"institutions":[{"id":"https://openalex.org/I4210130525","display_name":"Sidra Medical and Research Center","ror":"https://ror.org/03acdk243","country_code":"QA","type":"healthcare","lineage":["https://openalex.org/I4210130525"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Ramzi Temanni","raw_affiliation_strings":["SIDRA Medical and Research Center, Biomedical Informatics division, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SIDRA Medical and Research Center, Biomedical Informatics division, Doha, Qatar","institution_ids":["https://openalex.org/I4210130525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055434163","display_name":"Andrey Ptitsyn","orcid":"https://orcid.org/0000-0003-1196-8757"},"institutions":[{"id":"https://openalex.org/I4210130525","display_name":"Sidra Medical and Research Center","ror":"https://ror.org/03acdk243","country_code":"QA","type":"healthcare","lineage":["https://openalex.org/I4210130525"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Andrey Ptitsyn","raw_affiliation_strings":["SIDRA Medical and Research Center, Biomedical Informatics division, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SIDRA Medical and Research Center, Biomedical Informatics division, Doha, Qatar","institution_ids":["https://openalex.org/I4210130525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210130525"],"apc_list":null,"apc_paid":null,"fwci":0.3012,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.62937017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"43","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9966999888420105,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9692000150680542,"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":0.8407167196273804},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7729315757751465},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6758180856704712},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5922896265983582},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.48199787735939026},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.46632248163223267},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.4114949107170105},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3554597795009613},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.29276883602142334},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2704339623451233},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.13859063386917114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8407167196273804},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7729315757751465},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6758180856704712},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5922896265983582},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48199787735939026},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.46632248163223267},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.4114949107170105},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3554597795009613},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29276883602142334},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2704339623451233},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.13859063386917114},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibe.2015.7367654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibe.2015.7367654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 15th International Conference on Bioinformatics and Bioengineering (BIBE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1978251004","https://openalex.org/W2002482313","https://openalex.org/W2059592599","https://openalex.org/W2069577154","https://openalex.org/W2093931624","https://openalex.org/W2103441770","https://openalex.org/W2125021394","https://openalex.org/W2131187246","https://openalex.org/W2144430639","https://openalex.org/W2157909358","https://openalex.org/W2161488606","https://openalex.org/W2168133698","https://openalex.org/W2168397218","https://openalex.org/W2168440186","https://openalex.org/W2233103831","https://openalex.org/W2306254820","https://openalex.org/W2313232876","https://openalex.org/W2338902476"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2011430815","https://openalex.org/W4321606653","https://openalex.org/W4401278057"],"abstract_inverted_index":{"Advancement":[0],"in":[1,57,99,159,205],"Next":[2],"Generation":[3],"Sequencing":[4],"(NGS)":[5],"technology":[6],"are":[7,20,49,81],"associated":[8],"with":[9,175,189],"ever-increasing":[10],"volume":[11,76,184],"of":[12,52,60,77,137,139,143,161,172,185,192],"genomic":[13,18,78],"data":[14,19,33,79,178,187],"every":[15],"year.":[16],"These":[17],"efficiently":[21],"processed":[22,32],"by":[23],"empirical":[24],"parallelism":[25],"using":[26,216],"High":[27],"Performance":[28],"Computing":[29],"(HPC).":[30],"The":[31],"can":[34],"be":[35],"used":[36,56,67,89],"for":[37,73,91,96],"genome-wide":[38],"association":[39],"studies,":[40],"genetics,":[41],"personalized":[42],"medicine":[43],"and":[44,54,69,94,107,125,156,167,169,194,202,212],"many":[45],"other":[46],"areas.":[47],"There":[48],"different":[50,58,176],"kind":[51],"algorithms":[53],"implementations":[55],"phases":[59],"genome":[61,92,177,186],"processing.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"BWAKIT":[68,90],"GATK":[70,95],"based":[71,239],"software":[72],"processing":[74,208],"larger":[75,105],"that":[80,103],"referred":[82],"as":[83],"\"NGS":[84],"workflow":[85,102,149,174,227],"at":[86],"SIDRA\".":[87],"We":[88,112,151,196],"alignment":[93],"variant":[97,123],"discovery":[98,124],"the":[100,114,132,144,147,153,231],"NGS":[101,148,173,226],"required":[104],"computation":[106],"huge":[108],"memory":[109],"requirement":[110],"respectively.":[111],"observed,":[113],"CPU":[115],"utilization":[116],"is":[117,128],"not":[118],"more":[119,183],"than":[120],"45%":[121],"during":[122,146],"hence,":[126],"it":[127],"necessary":[129],"to":[130,236],"understand":[131],"optimal":[133],"selection":[134],"(in":[135],"terms":[136,160],"number":[138],"threads":[140],"or":[141],"cores)":[142],"resources":[145],"automation.":[150],"analyzed":[152],"performance":[154,206,232],"bottleneck":[155],"application":[157,237],"optimization":[158],"\"scalability\"":[162],"(use":[163],"maximum":[164],"available":[165],"CPUs":[166,193],"memory)":[168],"\"multiple":[170],"instances":[171],"within":[179],"a":[180,222],"node\"":[181],"(process":[182],"concurrently":[188,215],"limited":[190],"set":[191],"memory).":[195],"observed":[197],"that,":[198],"40%,":[199],"65%,":[200],"71%":[201],"76%":[203,234],"improvement":[204],"while":[207],"2,":[209],"4,":[210],"8":[211],"16":[213],"samples":[214],"our":[217,224],"own":[218],"scheduling":[219],"heuristics.":[220],"As":[221],"result,":[223],"proposed":[225],"automation":[228],"will":[229],"improve":[230],"upto":[233],"compared":[235],"scalability":[238],"workflows.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}