{"id":"https://openalex.org/W3007500409","doi":"https://doi.org/10.1109/bigdata47090.2019.9006397","title":"Exploiting Anti-Monotonic Constraints in Mining Palindromic Motifs from Big Genomic Data","display_name":"Exploiting Anti-Monotonic Constraints in Mining Palindromic Motifs from Big Genomic Data","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007500409","doi":"https://doi.org/10.1109/bigdata47090.2019.9006397","mag":"3007500409"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9006397","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","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/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"]}],"countries":["NG"],"is_corresponding":true,"raw_author_name":"Oluwafemi A. Sarumi","raw_affiliation_strings":["Department of Computer Science, The Federal University of Technology - Akure (FUTA), Akure, Ondo State Nigeria"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The Federal University of Technology - Akure (FUTA), Akure, Ondo State Nigeria","institution_ids":["https://openalex.org/I180664298"]}]},{"author_position":"last","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"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Manitoba, Winnipeg, MB, Canada","institution_ids":["https://openalex.org/I46247651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083957020"],"corresponding_institution_ids":["https://openalex.org/I180664298"],"apc_list":null,"apc_paid":null,"fwci":3.4651,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.94278815,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4864","last_page":"4873"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9983000159263611,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9983000159263611,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9966999888420105,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9926999807357788,"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/palindrome","display_name":"Palindrome","score":0.6915597915649414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5964902639389038},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.5080385208129883},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5064417123794556},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.49956297874450684},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.49585017561912537},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.47654491662979126},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.46952763199806213},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4559607207775116},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4445219039916992},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.352316677570343},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3286937475204468},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.30356767773628235},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.28247928619384766},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2521374523639679},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.14152616262435913}],"concepts":[{"id":"https://openalex.org/C44667518","wikidata":"https://www.wikidata.org/wiki/Q12321","display_name":"Palindrome","level":4,"score":0.6915597915649414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5964902639389038},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.5080385208129883},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5064417123794556},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.49956297874450684},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.49585017561912537},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.47654491662979126},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.46952763199806213},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4559607207775116},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4445219039916992},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.352316677570343},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3286937475204468},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.30356767773628235},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.28247928619384766},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2521374523639679},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.14152616262435913},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9006397","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006397","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W97034364","https://openalex.org/W1888464276","https://openalex.org/W1972870286","https://openalex.org/W1983506100","https://openalex.org/W1987636695","https://openalex.org/W1989574513","https://openalex.org/W1994453025","https://openalex.org/W2009450264","https://openalex.org/W2015159527","https://openalex.org/W2032731918","https://openalex.org/W2057778735","https://openalex.org/W2063364984","https://openalex.org/W2066070009","https://openalex.org/W2068671326","https://openalex.org/W2077981172","https://openalex.org/W2078064242","https://openalex.org/W2085638007","https://openalex.org/W2089875224","https://openalex.org/W2090534409","https://openalex.org/W2093875620","https://openalex.org/W2094866040","https://openalex.org/W2095326628","https://openalex.org/W2096717068","https://openalex.org/W2101793436","https://openalex.org/W2131975293","https://openalex.org/W2145872581","https://openalex.org/W2148693963","https://openalex.org/W2150433972","https://openalex.org/W2191117394","https://openalex.org/W2210278139","https://openalex.org/W2272368399","https://openalex.org/W2395766643","https://openalex.org/W2539646971","https://openalex.org/W2545204805","https://openalex.org/W2561695300","https://openalex.org/W2572737325","https://openalex.org/W2578513034","https://openalex.org/W2738583842","https://openalex.org/W2889202450","https://openalex.org/W2920294799","https://openalex.org/W2982365687","https://openalex.org/W3105371730","https://openalex.org/W4240380158","https://openalex.org/W4250975638","https://openalex.org/W4251092169","https://openalex.org/W4254176946","https://openalex.org/W6681989899","https://openalex.org/W6687061732","https://openalex.org/W6732062164"],"related_works":["https://openalex.org/W280853923","https://openalex.org/W2386899214","https://openalex.org/W2367209271","https://openalex.org/W2599438866","https://openalex.org/W2376418607","https://openalex.org/W1736872950","https://openalex.org/W1927503049","https://openalex.org/W2577361510","https://openalex.org/W3151292803","https://openalex.org/W3007500409"],"abstract_inverted_index":{"The":[0,143],"advent":[1],"of":[2,18,34,45,51,59,64,83,99,145,172,211,222,240,247,256,267,288],"high-throughput":[3],"technologies":[4],"such":[5],"as":[6,135],"Illumina":[7],"HiSeq":[8],"X,":[9],"mass":[10],"spectrometry,":[11],"and":[12,47,165,169,219,302],"microarray":[13],"heralds":[14],"a":[15,57,84,96,178,203,230,254,257,317],"new":[16],"era":[17],"big":[19],"biological":[20],"datasets":[21],"in":[22,28,61,79,93,126,139,160,180],"computational":[23,182],"biology.":[24],"This":[25],"digital":[26],"revolution":[27],"bioinformatics":[29],"has":[30],"generated":[31],"unprecedented":[32],"volumes":[33,210,266],"omics":[35,52],"data":[36,53,295],"(e.g.,":[37,102,148],"transcriptomes,":[38],"genomes,":[39],"proteomes,":[40],"metabolomes)":[41],"with":[42,56],"various":[43],"degrees":[44],"veracities":[46],"values.":[48],"These":[49],"deluge":[50],"are":[54,73,91,108,124],"awash":[55],"wealth":[58],"information":[60],"the":[62,80,111,127,133,140,161,173,181,186,208,212,223,243,248,276,293],"form":[63],"frequently":[65],"repeated":[66,75],"contiguous":[67,76],"patterns-namely,":[68],"sequence":[69,100],"motifs.":[70],"Sequence":[71],"motifs":[72,101,199,263,315],"short":[74,318],"subsequences":[77],"located":[78],"promoter":[81],"region":[82],"genome":[85,278],"sequence.":[86],"On":[87],"some":[88,238],"occasions,":[89],"users":[90,155],"interested":[92],"mining":[94,187,197,234,261],"only":[95],"particular":[97],"type":[98],"palindromic":[103,198,262,314],"motifs).":[104],"In":[105],"genomics,":[106],"palindromes":[107],"sequences":[109,138,214,301],"from":[110,114,200,207,264,292],"nucleotide":[112],"bases":[113],"deoxyribonucleic":[115],"acid":[116,120],"(DNA)":[117],"or":[118],"ribonucleic":[119],"(RNA)":[121],"strands":[122],"that":[123,129,236,309],"symmetrical":[125],"sense":[128],"they":[130],"read":[131],"exactly":[132],"same":[134],"their":[136,158],"complementary":[137],"reverse":[141],"direction.":[142],"use":[144],"classical":[146],"constraints":[147],"anti-monotonic,":[149],"succinct,":[150],"and/or":[151],"convertible":[152],"constraints)":[153],"allows":[154],"to":[156,177,216],"specify":[157],"interest":[159],"universal":[162],"search":[163,174],"space,":[164],"thus":[166],"enhancing":[167],"distinct":[168],"effective":[170],"pruning":[171],"space-":[175],"leading":[176,215],"reduction":[179],"time":[183,221],"required":[184],"for":[185,196],"process.":[188],"Despite":[189],"several":[190],"attempts":[191],"made":[192],"by":[193],"existing":[194],"algorithms":[195],"DNA":[201,213,268],"sequences,":[202],"major":[204],"drawback":[205],"stems":[206],"high":[209,217,265],"complexities":[218],"turnaround":[220,319],"algorithms.":[224],"To":[225,270],"this":[226],"end,":[227],"we":[228,274],"propose":[229],"parallel":[231],"scalable":[232],"sequential":[233],"algorithm":[235,311],"exploits":[237],"features":[239],"anti-monotonic":[241],"constraints-using":[242],"in-memory":[244],"computing":[245],"model":[246],"Apache":[249],"Spark":[250],"framework":[251],"deployed":[252],"on":[253],"cluster":[255],"homogeneous":[258],"distributed-memory":[259],"system-for":[260],"sequences.":[269,305],"evaluate":[271],"our":[272,310],"algorithm,":[273],"obtained":[275],"human":[277],"(Homo":[279],"sapiens)":[280],"assemblies":[281],"GRCh37":[282],"patch":[283],"13":[284],"(hg19),":[285],"which":[286],"is":[287],"size":[289],"3.2":[290],"GB":[291],"Ensembl":[294],"repository.":[296],"It":[297],"contains":[298],"104,763":[299],"protein-coding":[300],"24,513":[303],"non-coding":[304],"Evaluation":[306],"results":[307],"show":[308],"extracts":[312],"accurate":[313],"using":[316],"time.":[320]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":12}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}