{"id":"https://openalex.org/W2140565514","doi":"https://doi.org/10.1109/escience.2013.42","title":"Consensus Sigma-70 Promoter Prediction Using Hadoop","display_name":"Consensus Sigma-70 Promoter Prediction Using Hadoop","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2140565514","doi":"https://doi.org/10.1109/escience.2013.42","mag":"2140565514"},"language":"en","primary_location":{"id":"doi:10.1109/escience.2013.42","is_oa":false,"landing_page_url":"https://doi.org/10.1109/escience.2013.42","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 9th International Conference on e-Science","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/A5110256734","display_name":"James M. Hogan","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"James M. Hogan","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Queensland University of Technology","Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Queensland University of Technology","institution_ids":["https://openalex.org/I160993911"]},{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033258629","display_name":"Wayne Kelly","orcid":"https://orcid.org/0000-0002-8554-4589"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wayne A. Kelly","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Queensland University of Technology","Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Queensland University of Technology","institution_ids":["https://openalex.org/I160993911"]},{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064215660","display_name":"Felicity Newell","orcid":"https://orcid.org/0000-0003-0469-2705"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Felicity S. Newell","raw_affiliation_strings":["Institute for Molecular Bioscience, University of Queensland","University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Institute for Molecular Bioscience, University of Queensland","institution_ids":["https://openalex.org/I165143802"]},{"raw_affiliation_string":"University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110256734"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":0.1462,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57160447,"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":"35","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9965999722480774,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9965999722480774,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9965000152587891,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9954000115394592,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.8355423808097839},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7887611985206604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7766490578651428},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44872161746025085},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.428046852350235},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.42175206542015076},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4193258583545685},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4151002764701843},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.39382660388946533},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3429008722305298},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.23130548000335693},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.11331647634506226},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10211434960365295}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.8355423808097839},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7887611985206604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7766490578651428},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44872161746025085},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.428046852350235},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.42175206542015076},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4193258583545685},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4151002764701843},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39382660388946533},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3429008722305298},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.23130548000335693},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.11331647634506226},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10211434960365295},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/escience.2013.42","is_oa":false,"landing_page_url":"https://doi.org/10.1109/escience.2013.42","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 9th International Conference on e-Science","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320984","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1990073900","https://openalex.org/W1994596892","https://openalex.org/W2054331129","https://openalex.org/W2055553156","https://openalex.org/W2068448872","https://openalex.org/W2087064593","https://openalex.org/W2105784079","https://openalex.org/W2117357746","https://openalex.org/W2118526609","https://openalex.org/W2121762798","https://openalex.org/W2126851025","https://openalex.org/W2131229759","https://openalex.org/W2143210482","https://openalex.org/W2149414426","https://openalex.org/W2160165249","https://openalex.org/W2170698318"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W4256502920","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2999756192","https://openalex.org/W2059697060","https://openalex.org/W4382701072","https://openalex.org/W2491314273"],"abstract_inverted_index":{"MapReduce":[0],"frameworks":[1],"such":[2],"as":[3,85],"Hadoop":[4,78,127],"are":[5],"well":[6,89],"suited":[7],"to":[8,79,176],"handling":[9],"large":[10,54],"sets":[11],"of":[12,43,53,77,81,113,126,130,137,156,173],"data":[13,62],"which":[14,64],"can":[15,141,158],"be":[16,142,159,177],"processed":[17],"separately":[18],"and":[19,27,61,106,153,165],"independently,":[20],"with":[21,46,109],"canonical":[22],"applications":[23],"in":[24,33,40,50],"information":[25],"retrieval":[26],"sales":[28],"record":[29],"analysis.":[30],"Rapid":[31],"advances":[32],"sequencing":[34],"technology":[35],"have":[36],"ensured":[37],"an":[38],"explosion":[39],"the":[41,51,67,75,110,124,135,138,154,180],"availability":[42],"genomic":[44],"data,":[45],"a":[47,88,118,170],"consequent":[48],"rise":[49],"importance":[52],"scale":[55],"comparative":[56],"genomics,":[57],"often":[58],"involving":[59],"operations":[60],"relationships":[63],"deviate":[65],"from":[66],"classical":[68],"Map":[69],"Reduce":[70],"structure.":[71],"This":[72],"work":[73],"examines":[74],"application":[76],"patterns":[80],"this":[82,131],"nature,":[83,132],"using":[84],"our":[86],"focus":[87],"established":[90],"workflow":[91],"for":[92,98,128],"identifying":[93],"promoters":[94],"-":[95,101],"binding":[96],"sites":[97],"regulatory":[99],"proteins":[100],"across":[102],"multiple":[103],"gene":[104],"regions":[105],"organisms,":[107],"coupled":[108],"unifying":[111],"step":[112],"assembling":[114],"these":[115],"results":[116],"into":[117],"consensus":[119],"sequence.":[120],"Our":[121],"approach":[122],"demonstrates":[123,149],"utility":[125],"problems":[129,175],"showing":[133],"how":[134,150],"tyranny":[136],"\"dominant":[139],"decomposition\"":[140],"at":[143],"least":[144],"partially":[145],"overcome.":[146],"It":[147],"also":[148],"load":[151],"balance":[152],"granularity":[155],"parallelism":[157],"optimized":[160],"by":[161],"pre-processing":[162],"that":[163],"splits":[164],"reorganizes":[166],"input":[167],"files,":[168],"allowing":[169],"wide":[171],"range":[172],"related":[174],"brought":[178],"under":[179],"same":[181],"computational":[182],"umbrella.":[183]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
