{"id":"https://openalex.org/W2572737325","doi":"https://doi.org/10.1109/bibm.2016.7822641","title":"Mining sequential patterns from uncertain big DNA in the spark framework","display_name":"Mining sequential patterns from uncertain big DNA in the spark framework","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2572737325","doi":"https://doi.org/10.1109/bibm.2016.7822641","mag":"2572737325"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2016.7822641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2016.7822641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100688754","display_name":"Fan Jiang","orcid":"https://orcid.org/0000-0002-1641-5804"},"institutions":[{"id":"https://openalex.org/I46247651","display_name":"University of Manitoba","ror":"https://ror.org/02gfys938","country_code":"CA","type":"education","lineage":["https://openalex.org/I46247651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Fan Jiang","raw_affiliation_strings":["Department of Computer Science, University of Manitoba, Winnipeg, MB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Manitoba, Winnipeg, MB, Canada","institution_ids":["https://openalex.org/I46247651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016113718","display_name":"Carson K. Leung","orcid":"https://orcid.org/0000-0002-7541-9127"},"institutions":[{"id":"https://openalex.org/I46247651","display_name":"University of Manitoba","ror":"https://ror.org/02gfys938","country_code":"CA","type":"education","lineage":["https://openalex.org/I46247651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Carson K. Leung","raw_affiliation_strings":["Department of Computer Science, University of Manitoba, Winnipeg, MB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Manitoba, Winnipeg, MB, Canada","institution_ids":["https://openalex.org/I46247651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083957020","display_name":"Oluwafemi A. Sarumi","orcid":"https://orcid.org/0000-0001-6463-1029"},"institutions":[{"id":"https://openalex.org/I180664298","display_name":"Federal University of Technology","ror":"https://ror.org/01pvx8v81","country_code":"NG","type":"education","lineage":["https://openalex.org/I180664298"]},{"id":"https://openalex.org/I46247651","display_name":"University of Manitoba","ror":"https://ror.org/02gfys938","country_code":"CA","type":"education","lineage":["https://openalex.org/I46247651"]}],"countries":["CA","NG"],"is_corresponding":false,"raw_author_name":"Oluwafemi A. Sarumi","raw_affiliation_strings":["Department of Computer Science, The Federal University of Technology, Akure, Ondo State, Nigeria","Department of Computer Science, University of Manitoba, Winnipeg, MB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The Federal University of Technology, Akure, Ondo State, Nigeria","institution_ids":["https://openalex.org/I180664298"]},{"raw_affiliation_string":"Department of Computer Science, University of Manitoba, Winnipeg, MB, Canada","institution_ids":["https://openalex.org/I46247651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074614182","display_name":"Christine Y. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I46247651","display_name":"University of Manitoba","ror":"https://ror.org/02gfys938","country_code":"CA","type":"education","lineage":["https://openalex.org/I46247651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Christine Y. Zhang","raw_affiliation_strings":["Max Rady College of Medicine, University of Manitoba, Winnipeg, MB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Rady College of Medicine, University of Manitoba, Winnipeg, MB, Canada","institution_ids":["https://openalex.org/I46247651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8344,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.877368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2016","issue":null,"first_page":"874","last_page":"881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9994999766349792,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9878000020980835,"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/big-data","display_name":"Big data","score":0.727372944355011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6995257139205933},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6695576906204224},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6007552742958069},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.5839428901672363},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.49414947628974915},{"id":"https://openalex.org/keywords/biomedicine","display_name":"Biomedicine","score":0.44398602843284607},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38805532455444336},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.30484241247177124},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.21756911277770996},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1776883602142334},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13570663332939148}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.727372944355011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995257139205933},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6695576906204224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6007552742958069},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.5839428901672363},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.49414947628974915},{"id":"https://openalex.org/C66782513","wikidata":"https://www.wikidata.org/wiki/Q864601","display_name":"Biomedicine","level":2,"score":0.44398602843284607},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38805532455444336},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.30484241247177124},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.21756911277770996},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1776883602142334},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13570663332939148},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":2,"locations":[{"id":"doi:10.1109/bibm.2016.7822641","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2016.7822641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},{"id":"mag:2746455863","is_oa":false,"landing_page_url":"http://jglobal.jst.go.jp/en/public/20090422/201702243484981515","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W2049211","https://openalex.org/W51427095","https://openalex.org/W207625154","https://openalex.org/W820072188","https://openalex.org/W1211953102","https://openalex.org/W1483118879","https://openalex.org/W1641039719","https://openalex.org/W1676985236","https://openalex.org/W1987670185","https://openalex.org/W1990800901","https://openalex.org/W1994453025","https://openalex.org/W2023186718","https://openalex.org/W2039886920","https://openalex.org/W2048952423","https://openalex.org/W2062826247","https://openalex.org/W2063364984","https://openalex.org/W2068383400","https://openalex.org/W2077981172","https://openalex.org/W2083140545","https://openalex.org/W2101793436","https://openalex.org/W2105338744","https://openalex.org/W2110893883","https://openalex.org/W2111276329","https://openalex.org/W2122465391","https://openalex.org/W2131975293","https://openalex.org/W2133224197","https://openalex.org/W2137548844","https://openalex.org/W2139874739","https://openalex.org/W2147694185","https://openalex.org/W2149227645","https://openalex.org/W2153527568","https://openalex.org/W2155113671","https://openalex.org/W2158454296","https://openalex.org/W2162434736","https://openalex.org/W2164814636","https://openalex.org/W2166951489","https://openalex.org/W2189465200","https://openalex.org/W2191117394","https://openalex.org/W2198051699","https://openalex.org/W2270940528","https://openalex.org/W2272368399","https://openalex.org/W2777453820","https://openalex.org/W4239125441","https://openalex.org/W4254829975","https://openalex.org/W6602072312","https://openalex.org/W6636681434","https://openalex.org/W6676769087","https://openalex.org/W6679815717","https://openalex.org/W6682094280","https://openalex.org/W6683918989","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W2017899917","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W4308507533","https://openalex.org/W2407107767","https://openalex.org/W2901787049","https://openalex.org/W2792181990"],"abstract_inverted_index":{"Big":[0],"data":[1,13,37,105,119,164],"has":[2],"become":[3],"ubiquitous":[4],"as":[5,53,88],"high":[6,28,182,201],"volumes":[7],"of":[8,11,14,65,81,100,115,125,130,168,180,188,214],"wide":[9],"varieties":[10],"valuable":[12],"different":[15],"veracities":[16],"(e.g.,":[17,137],"precise,":[18],"imprecise":[19],"or":[20,112],"uncertain":[21,118,142,229],"data)":[22],"are":[23,106,120,155],"made":[24],"available":[25],"at":[26],"a":[27,75,123,146,175,197,211,243],"velocity":[29],"through":[30],"fast":[31],"throughput":[32],"machines":[33],"and":[34,39,49,59,92,150,157,184],"techniques":[35],"for":[36,200],"gathering":[38],"curation":[40],"in":[41,46,127,148,219],"many":[42],"real":[43],"life":[44],"applications":[45],"various":[47],"domains":[48],"application":[50],"areas":[51],"such":[52,87],"bioinformatics,":[54,63],"biomedicine,":[55],"finance,":[56],"social":[57],"networking,":[58],"weather":[60],"forecasting.":[61],"In":[62,192],"terabytes":[64],"deoxyribonucleic":[66],"acid":[67],"(DNA)":[68],"sequences":[69,144,173],"can":[70],"now":[71],"be":[72],"generated":[73,104],"within":[74,242],"few":[76],"hours":[77],"with":[78,109,122],"the":[79,98,128,181,185],"use":[80],"next":[82],"generation":[83],"sequencing":[84],"(NGS)":[85],"technologies":[86],"Illumina":[89,93],"HiSeq":[90],"X":[91],"Genome":[94],"Analyzer.":[95],"Due":[96],"to":[97,224],"nature":[99],"these":[101,140,189],"NGS":[102],"technologies,":[103],"usually":[107],"inherent":[108],"some":[110],"noise":[111],"other":[113],"forms":[114],"error.":[116],"These":[117],"embedded":[121],"wealth":[124],"information":[126],"form":[129],"frequent":[131],"patterns.":[132],"Mining":[133,167],"frequently":[134],"occurring":[135],"patterns":[136],"motifs)":[138],"from":[139,170,228],"big":[141,171,230],"DNA":[143,159,172,190,231],"is":[145,174],"challenge":[147],"bioinformatics":[149],"biomedicine.":[151],"Many":[152],"existing":[153],"algorithms":[154],"serial":[156],"mine":[158,225],"sequence":[160,226],"motifs":[161,169,227,241],"using":[162],"precise":[163],"mining":[165],"methods.":[166],"computationally":[176],"intensive":[177],"task":[178],"because":[179],"volume":[183],"associated":[186],"uncertainty":[187],"sequences.":[191],"this":[193],"paper,":[194],"we":[195],"propose":[196],"scalable":[198],"algorithm":[199,209,238],"performance":[202],"computing":[203,222],"on":[204],"bioinformatics.":[205],"Specifically,":[206],"our":[207,237],"parallel":[208],"uses":[210],"fault-tolerant":[212],"collection":[213],"resilient":[215],"distributed":[216],"datasets":[217],"(RDDs)":[218],"Apache":[220],"Spark":[221],"framework":[223],"data.":[232],"Experimental":[233],"results":[234],"show":[235],"that":[236],"extracts":[239],"accurate":[240],"short":[244],"time":[245],"frame.":[246]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}