{"id":"https://openalex.org/W2605012530","doi":"https://doi.org/10.1109/tpds.2017.2692782","title":"A Hybrid MPI-OpenMP Strategy to Speedup the Compression of Big Next-Generation Sequencing Datasets","display_name":"A Hybrid MPI-OpenMP Strategy to Speedup the Compression of Big Next-Generation Sequencing Datasets","publication_year":2017,"publication_date":"2017-04-12","ids":{"openalex":"https://openalex.org/W2605012530","doi":"https://doi.org/10.1109/tpds.2017.2692782","mag":"2605012530"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2017.2692782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2017.2692782","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5056166836","display_name":"Sandino Vargas Perez","orcid":"https://orcid.org/0000-0002-5778-6142"},"institutions":[{"id":"https://openalex.org/I141649380","display_name":"Western Michigan University","ror":"https://ror.org/04j198w64","country_code":"US","type":"education","lineage":["https://openalex.org/I141649380"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandino Vargas-Perez","raw_affiliation_strings":["Department of Computer Science, Western Michigan University, Kalamazoo, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Western Michigan University, Kalamazoo, MI","institution_ids":["https://openalex.org/I141649380"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102729196","display_name":"Fahad Saeed","orcid":"https://orcid.org/0000-0002-3410-9552"},"institutions":[{"id":"https://openalex.org/I141649380","display_name":"Western Michigan University","ror":"https://ror.org/04j198w64","country_code":"US","type":"education","lineage":["https://openalex.org/I141649380"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fahad Saeed","raw_affiliation_strings":["Department of Electrical and Computer Engineering and Department of Computer Science, Western Michigan University, Kalamazoo, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and Department of Computer Science, Western Michigan University, Kalamazoo, MI","institution_ids":["https://openalex.org/I141649380"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141649380"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":1.5972,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.86211544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"28","issue":"10","first_page":"2760","last_page":"2769"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991000294685364,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8896269202232361},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7926194667816162},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7271609306335449},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.71711266040802},{"id":"https://openalex.org/keywords/terabyte","display_name":"Terabyte","score":0.49287843704223633},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4847976267337799},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4607452154159546},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.448871910572052},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.41663995385169983},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27158981561660767},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14673811197280884},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1387231945991516},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13758933544158936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8896269202232361},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7926194667816162},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7271609306335449},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.71711266040802},{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.49287843704223633},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4847976267337799},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4607452154159546},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.448871910572052},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.41663995385169983},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27158981561660767},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14673811197280884},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1387231945991516},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13758933544158936},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpds.2017.2692782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2017.2692782","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:scholarworks.wmich.edu:pcds_reports-1006","is_oa":false,"landing_page_url":"https://scholarworks.wmich.edu/pcds_reports/7","pdf_url":null,"source":{"id":"https://openalex.org/S4377196527","display_name":"ScholarWorks - WMU (Western Michigan University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I141649380","host_organization_name":"Western Michigan University","host_organization_lineage":["https://openalex.org/I141649380"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Parallel Computing and Data Science Lab Technical Reports","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1054929489","display_name":"CRII: SHF: HPC Solutions to Big NGS Data Compression","funder_award_id":"1464268","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1598728340","display_name":"CAREER: Towards Fast and Scalable Algorithms for Big Proteogenomics Data Analytics","funder_award_id":"1651724","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320316545","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W31923072","https://openalex.org/W120259676","https://openalex.org/W584777913","https://openalex.org/W1548134937","https://openalex.org/W1575350781","https://openalex.org/W1813030236","https://openalex.org/W1875083619","https://openalex.org/W1931027898","https://openalex.org/W1974158449","https://openalex.org/W1980202838","https://openalex.org/W1982703709","https://openalex.org/W1983041039","https://openalex.org/W2001775237","https://openalex.org/W2006088692","https://openalex.org/W2011305818","https://openalex.org/W2039716761","https://openalex.org/W2049585661","https://openalex.org/W2060650167","https://openalex.org/W2079942837","https://openalex.org/W2083838623","https://openalex.org/W2111044311","https://openalex.org/W2114792961","https://openalex.org/W2117608012","https://openalex.org/W2119277127","https://openalex.org/W2121236443","https://openalex.org/W2129512728","https://openalex.org/W2136214128","https://openalex.org/W2138196010","https://openalex.org/W2138782497","https://openalex.org/W2159683766","https://openalex.org/W2164372370","https://openalex.org/W2165100134","https://openalex.org/W2166588423","https://openalex.org/W2341986315","https://openalex.org/W2396359228","https://openalex.org/W4236772720","https://openalex.org/W4254265573","https://openalex.org/W6712560353"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2936171637","https://openalex.org/W1586214342","https://openalex.org/W2260589296","https://openalex.org/W3157828377","https://openalex.org/W181157820","https://openalex.org/W2937168573","https://openalex.org/W3137329302","https://openalex.org/W2805468299","https://openalex.org/W2990494149"],"abstract_inverted_index":{"DNA":[0],"sequencing":[1],"has":[2],"moved":[3],"into":[4],"the":[5,12,54,62,99,114,125,129],"realm":[6],"of":[7,15,56,64,127,161,191],"Big":[8],"Data":[9],"due":[10],"to":[11,31,52,112,151,163,187,198,211,218],"rapid":[13],"development":[14],"high-throughput,":[16],"low":[17],"cost":[18],"Next-Generation":[19],"Sequencing":[20],"(NGS)":[21],"technologies.":[22],"Sequential":[23],"data":[24,59,116,192],"compression":[25,55,142,206,225],"solutions":[26],"that":[27,109,139,148],"once":[28],"were":[29,149,185],"sufficient":[30],"efficiently":[32],"store":[33],"and":[34,67,77,85,93,120,169,181],"distribute":[35],"this":[36,43,230],"information":[37],"are":[38],"now":[39],"falling":[40],"behind.":[41],"In":[42],"paper":[44],"we":[45,102],"introduce":[46,103],"phyNGSC,":[47],"a":[48,104,118,223],"hybrid":[49],"MPI-OpenMP":[50],"strategy":[51],"speedup":[53],"big":[57,145],"NGS":[58,146],"by":[60,82,88,204],"combining":[61],"features":[63],"both":[65],"distributed":[66,119],"shared":[68],"memory":[69,80],"architectures.":[70],"Our":[71,135,166],"algorithm":[72,100],"balances":[73],"work-load":[74],"among":[75],"processes":[76],"threads,":[78],"alleviates":[79],"latency":[81],"exploiting":[83],"locality,":[84],"accelerates":[86],"I/O":[87],"reducing":[89],"excessive":[90],"read/write":[91],"operations":[92],"inter-node":[94],"message":[95],"exchange.":[96],"To":[97],"make":[98],"scalable,":[101],"novel":[105],"timestamp-based":[106],"file":[107],"structure":[108],"allows":[110],"us":[111],"write":[113],"compressed":[115],"in":[117,193],"non-deterministic":[121],"fashion":[122],"while":[123,221],"retaining":[124],"capability":[126],"reconstructing":[128],"dataset":[130],"with":[131,159,175],"its":[132],"original":[133],"order.":[134],"experimental":[136,170],"results":[137,171],"show":[138],"phyNGSC":[140,215],"achieved":[141,216],"times":[143],"for":[144,229],"datasets":[147,177],"45":[150],"98":[152],"percent":[153],"faster":[154],"than":[155,200],"NGS-specific":[156,205],"sequential":[157],"compressors":[158],"throughputs":[160],"up":[162,217],"3":[164],"GB/s.":[165],"theoretical":[167],"analysis":[168],"suggest":[172],"strong":[173],"scalability":[174],"some":[176],"yielding":[178],"super-linear":[179],"speedups":[180,220],"constant":[182],"efficiency.":[183],"We":[184],"able":[186],"compress":[188],"1":[189],"terabyte":[190],"under":[194],"8":[195],"minutes":[196],"compared":[197],"more":[199],"5":[201],"hours":[202],"taken":[203],"algorithms":[207],"running":[208],"sequentially.":[209],"Compared":[210],"other":[212],"parallel":[213],"solutions,":[214],"6x":[219],"maintaining":[222],"higher":[224],"ratio.":[226],"The":[227],"code":[228],"implementation":[231],"is":[232],"available":[233],"at":[234],"https://github.com/pcdslab/PHYNGSC.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}