{"id":"https://openalex.org/W2275908958","doi":"https://doi.org/10.1145/2831244.2831252","title":"Performance evaluation and tuning of BioPig for genomic analysis","display_name":"Performance evaluation and tuning of BioPig for genomic analysis","publication_year":2015,"publication_date":"2015-11-11","ids":{"openalex":"https://openalex.org/W2275908958","doi":"https://doi.org/10.1145/2831244.2831252","mag":"2275908958"},"language":"en","primary_location":{"id":"doi:10.1145/2831244.2831252","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2831244.2831252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 International Workshop on Data-Intensive Scalable Computing Systems","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/A5051631233","display_name":"Lizhen Shi","orcid":"https://orcid.org/0000-0002-8776-4470"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lizhen Shi","raw_affiliation_strings":["Florida State Univ"],"affiliations":[{"raw_affiliation_string":"Florida State Univ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100781872","display_name":"Zhong Wang","orcid":"https://orcid.org/0000-0002-6307-0458"},"institutions":[{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong Wang","raw_affiliation_strings":["Joint Genome Inst"],"affiliations":[{"raw_affiliation_string":"Joint Genome Inst","institution_ids":["https://openalex.org/I196679689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070216261","display_name":"Weikuan Yu","orcid":"https://orcid.org/0000-0002-8754-0311"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weikuan Yu","raw_affiliation_strings":["Florida State Univ"],"affiliations":[{"raw_affiliation_string":"Florida State Univ","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077701341","display_name":"Xiandong Meng","orcid":"https://orcid.org/0000-0002-3382-5274"},"institutions":[{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiandong Meng","raw_affiliation_strings":["Joint Genome Inst"],"affiliations":[{"raw_affiliation_string":"Joint Genome Inst","institution_ids":["https://openalex.org/I196679689"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051631233"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1459,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56713322,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.992900013923645,"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/T10885","display_name":"Gene expression and cancer classification","score":0.992900013923645,"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":0.9918000102043152,"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":0.9901000261306763,"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/terabyte","display_name":"Terabyte","score":0.8744277954101562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8279018402099609},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7038534879684448},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.564441978931427},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48846474289894104},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.42131465673446655},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37519192695617676},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.360110342502594},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.35873734951019287},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3475055694580078}],"concepts":[{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.8744277954101562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8279018402099609},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7038534879684448},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.564441978931427},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48846474289894104},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.42131465673446655},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37519192695617676},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.360110342502594},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.35873734951019287},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3475055694580078},{"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:10.1145/2831244.2831252","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2831244.2831252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 International Workshop on Data-Intensive Scalable Computing Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1969346416","https://openalex.org/W2058340614","https://openalex.org/W2079955672","https://openalex.org/W2083854815","https://openalex.org/W2098935637","https://openalex.org/W2118526609","https://openalex.org/W2145709037","https://openalex.org/W2149059931","https://openalex.org/W2173213060","https://openalex.org/W2189125735","https://openalex.org/W6671485122","https://openalex.org/W6677816918"],"related_works":["https://openalex.org/W2936171637","https://openalex.org/W1586214342","https://openalex.org/W2260589296","https://openalex.org/W3157828377","https://openalex.org/W181157820","https://openalex.org/W3137329302","https://openalex.org/W4241817935","https://openalex.org/W2937168573","https://openalex.org/W2805468299","https://openalex.org/W2990494149"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3],"aim":[4],"to":[5,9,43,70,115],"optimize":[6],"Hadoop":[7,33,97,112],"parameters":[8,67,98,113],"improve":[10],"the":[11,50,64,76],"performance":[12,117],"of":[13,45,87,124,137],"BioPig":[14,20,60,128],"on":[15,32,62,104,127,154],"Amazon":[16],"Web":[17],"Service":[18],"(AWS).":[19],"is":[21,30,49,81],"a":[22,84,105,146],"toolkit":[23],"for":[24,149],"large-scale":[25],"sequencing":[26],"data":[27,92],"analysis":[28,93],"and":[29,34,41],"built":[31],"Pig":[35],"that":[36],"enables":[37],"easy":[38],"parallel":[39],"programming":[40],"scaling":[42],"datasets":[44],"terabyte":[46],"sizes.":[47],"AWS":[48],"most":[51],"popular":[52],"cloud-computing":[53],"platform":[54],"offered":[55],"by":[56,131],"Amazon.":[57],"When":[58],"running":[59],"jobs":[61],"AWS,":[63],"default":[65],"configuration":[66],"may":[68],"lead":[69],"high":[71],"computational":[72],"costs.":[73],"We":[74,95,108],"select":[75],"k-mer":[77,125],"counting":[78,126],"as":[79,145],"it":[80],"used":[82],"in":[83],"large":[85],"number":[86],"next":[88],"generation":[89],"sequence":[90],"(NGS)":[91],"tools.":[94],"tuned":[96],"from":[99],"five":[100],"different":[101,111],"perspectives":[102],"based":[103],"baseline":[106],"configuration.":[107],"found":[109],"tuning":[110,143],"led":[114],"various":[116],"improvements.":[118],"The":[119],"overall":[120],"job":[121],"execution":[122],"time":[123],"was":[129],"reduced":[130],"50%":[132],"using":[133],"an":[134],"optimized":[135],"set":[136],"parameters.":[138],"This":[139],"paper":[140],"documents":[141],"our":[142],"experiments":[144],"valuable":[147],"reference":[148],"future":[150],"Hadoop-based":[151],"analytics":[152],"applications":[153],"genomics":[155],"datasets.":[156]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}