{"id":"https://openalex.org/W4386585098","doi":"https://doi.org/10.1145/3569951.3597577","title":"FASTQ File Compression Benchmarking Using Lossless General Purpose Algorithms","display_name":"FASTQ File Compression Benchmarking Using Lossless General Purpose Algorithms","publication_year":2023,"publication_date":"2023-07-23","ids":{"openalex":"https://openalex.org/W4386585098","doi":"https://doi.org/10.1145/3569951.3597577"},"language":"en","primary_location":{"id":"doi:10.1145/3569951.3597577","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3569951.3597577","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3569951.3597577","source":{"id":"https://openalex.org/S4306523034","display_name":"Practice and Experience in Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3569951.3597577","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063231154","display_name":"Erick Joel McGhee","orcid":"https://orcid.org/0000-0002-3386-7028"},"institutions":[{"id":"https://openalex.org/I4210159558","display_name":"Joint Institute for Computational Sciences","ror":"https://ror.org/05277x335","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294","https://openalex.org/I4210159558","https://openalex.org/I75027704"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Erick Joel Mcghee","raw_affiliation_strings":["University of Tennessee, National Institute for Computational Sciences, USA"],"raw_orcid":"https://orcid.org/0000-0002-3386-7028","affiliations":[{"raw_affiliation_string":"University of Tennessee, National Institute for Computational Sciences, USA","institution_ids":["https://openalex.org/I4210159558","https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066351517","display_name":"S.V. Milton","orcid":"https://orcid.org/0000-0002-7748-1055"},"institutions":[{"id":"https://openalex.org/I4210159558","display_name":"Joint Institute for Computational Sciences","ror":"https://ror.org/05277x335","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294","https://openalex.org/I4210159558","https://openalex.org/I75027704"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Milton","raw_affiliation_strings":["University of Tennessee, National Institute for Computational Sciences, USA"],"raw_orcid":"https://orcid.org/0000-0002-7748-1055","affiliations":[{"raw_affiliation_string":"University of Tennessee, National Institute for Computational Sciences, USA","institution_ids":["https://openalex.org/I4210159558","https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5063231154"],"corresponding_institution_ids":["https://openalex.org/I4210159558","https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12607905,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"201","issue":null,"first_page":"315","last_page":"319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11245","display_name":"Advanced Numerical Analysis Techniques","score":0.9646000266075134,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11245","display_name":"Advanced Numerical Analysis Techniques","score":0.9646000266075134,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9448000192642212,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/lossless-compression","display_name":"Lossless compression","score":0.8455267548561096},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.815325140953064},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7121899127960205},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.6215061545372009},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5711988210678101},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4761195778846741}],"concepts":[{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.8455267548561096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.815325140953064},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7121899127960205},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.6215061545372009},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5711988210678101},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4761195778846741},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3569951.3597577","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3569951.3597577","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3569951.3597577","source":{"id":"https://openalex.org/S4306523034","display_name":"Practice and Experience in Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3569951.3597577","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3569951.3597577","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3569951.3597577","source":{"id":"https://openalex.org/S4306523034","display_name":"Practice and Experience in Advanced Research Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386585098.pdf","grobid_xml":"https://content.openalex.org/works/W4386585098.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2755344367"],"related_works":["https://openalex.org/W2948148442","https://openalex.org/W2461250372","https://openalex.org/W2394342941","https://openalex.org/W2169853506","https://openalex.org/W2547124190","https://openalex.org/W2350586049","https://openalex.org/W2385628723","https://openalex.org/W2057878850","https://openalex.org/W2169871401","https://openalex.org/W3008492011"],"abstract_inverted_index":{"FASTQ":[0,37,89,163],"format":[1,5],"is":[2,77,118],"a":[3,8,54,97,100,157],"text-based":[4,25],"for":[6,20,88,141,162],"storing":[7],"biological":[9],"sequence":[10],"(usually":[11],"nucleotide":[12],"sequence)":[13],"and":[14,35,43,74,115,178],"its":[15],"corresponding":[16],"quality":[17],"scores":[18],"used":[19,59],"genome":[21],"sequencing.":[22],"While":[23],"most":[24,66,107],"formats":[26],"compress":[27,45],"well":[28,46,175],"using":[29,47],"traditional":[30],"methods":[31,135],"such":[32],"as":[33,156],"tar":[34],"gzip,":[36],"files":[38,90],"are":[39,69,110,148],"generally":[40],"quite":[41],"large":[42],"don\u2019t":[44],"these":[48,62],"methods,":[49],"leading":[50],"to":[51,60,91],"much":[52],"of":[53,96,132],"file":[55],"system\u2019s":[56],"space":[57],"being":[58],"store":[61],"data":[63],"sets.":[64],"As":[65,106],"computing":[67,108],"platforms":[68,109],"shared":[70,111,149],"resources,":[71,112],"balancing":[72,113],"compression":[73,86,114,126,130,160,168],"resource":[75,116],"allocation":[76,117],"vital.":[78,119],"This":[79],"paper":[80],"investigates":[81],"the":[82,94,128,133],"best":[83],"general":[84],"use":[85],"software":[87],"run":[92],"at":[93,170],"end":[95],"job":[98],"in":[99,137],"mixed-use":[101],"throughput":[102],"high-performance":[103],"compute":[104],"cluster.":[105],"It":[120,165],"was":[121],"found":[122],"that":[123],"zpaq":[124],"high":[125,167],"delivers":[127,166],"highest":[129],"ratios":[131,169],"fifty-seven":[134],"tested":[136],"this":[138],"paper.":[139],"However,":[140],"more":[142],"real-world":[143],"scenarios":[144],"where":[145],"system":[146],"resources":[147],"or":[150],"limited,":[151],"we":[152],"recommend":[153],"pzstd":[154],"medium":[155],"good":[158],"all-around":[159],"method":[161],"files.":[164],"fast":[171],"speeds":[172],"while":[173],"performing":[174],"on":[176],"CPU":[177],"memory":[179],"efficiency.":[180]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}
