{"id":"https://openalex.org/W2908055786","doi":"https://doi.org/10.1142/s0129054118430086","title":"Transcriptomics: Quantifying Non-Uniform Read Distribution Using MapReduce","display_name":"Transcriptomics: Quantifying Non-Uniform Read Distribution Using MapReduce","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2908055786","doi":"https://doi.org/10.1142/s0129054118430086","mag":"2908055786"},"language":"en","primary_location":{"id":"doi:10.1142/s0129054118430086","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129054118430086","pdf_url":null,"source":{"id":"https://openalex.org/S68047077","display_name":"International Journal of Foundations of Computer Science","issn_l":"0129-0541","issn":["0129-0541","1793-6373"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Foundations of Computer Science","raw_type":"journal-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/A5064886767","display_name":"Jamie J. Alnasir","orcid":"https://orcid.org/0000-0001-8164-4753"},"institutions":[{"id":"https://openalex.org/I184558857","display_name":"Royal Holloway University of London","ror":"https://ror.org/04g2vpn86","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I184558857"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jamie J. Alnasir","raw_affiliation_strings":["Centre for Systems and Synthetic Biology, Department of Computer Science, Royal Holloway University of London, Egham, Surrey TW20 0EX, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Centre for Systems and Synthetic Biology, Department of Computer Science, Royal Holloway University of London, Egham, Surrey TW20 0EX, United Kingdom","institution_ids":["https://openalex.org/I184558857"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023617667","display_name":"Hugh Shanahan","orcid":"https://orcid.org/0000-0003-1374-6015"},"institutions":[{"id":"https://openalex.org/I184558857","display_name":"Royal Holloway University of London","ror":"https://ror.org/04g2vpn86","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I184558857"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hugh P. Shanahan","raw_affiliation_strings":["Centre for Systems and Synthetic Biology, Department of Computer Science, Royal Holloway University of London, Egham, Surrey TW20 0EX, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Centre for Systems and Synthetic Biology, Department of Computer Science, Royal Holloway University of London, Egham, Surrey TW20 0EX, United Kingdom","institution_ids":["https://openalex.org/I184558857"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064886767"],"corresponding_institution_ids":["https://openalex.org/I184558857"],"apc_list":null,"apc_paid":null,"fwci":0.0919,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49096722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"29","issue":"08","first_page":"1355","last_page":"1372"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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/T11970","display_name":"Molecular Biology Techniques and Applications","score":0.9973999857902527,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.74636310338974},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7007272243499756},{"id":"https://openalex.org/keywords/rna-seq","display_name":"RNA-Seq","score":0.5510740876197815},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5436782240867615},{"id":"https://openalex.org/keywords/transcriptome","display_name":"Transcriptome","score":0.49637967348098755},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4187433421611786},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3780681788921356},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2731761932373047},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15983575582504272},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1407032310962677},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.13108202815055847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.74636310338974},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7007272243499756},{"id":"https://openalex.org/C107397762","wikidata":"https://www.wikidata.org/wiki/Q2542347","display_name":"RNA-Seq","level":5,"score":0.5510740876197815},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5436782240867615},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.49637967348098755},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4187433421611786},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3780681788921356},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2731761932373047},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15983575582504272},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1407032310962677},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.13108202815055847},{"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/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0129054118430086","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129054118430086","pdf_url":null,"source":{"id":"https://openalex.org/S68047077","display_name":"International Journal of Foundations of Computer Science","issn_l":"0129-0541","issn":["0129-0541","1793-6373"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Foundations of Computer Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W159942249","https://openalex.org/W1557515632","https://openalex.org/W1760158404","https://openalex.org/W1913179380","https://openalex.org/W1965175512","https://openalex.org/W1966116114","https://openalex.org/W1967838552","https://openalex.org/W1981509058","https://openalex.org/W1998330439","https://openalex.org/W2000629769","https://openalex.org/W2004869583","https://openalex.org/W2020541351","https://openalex.org/W2023621259","https://openalex.org/W2054880642","https://openalex.org/W2085126246","https://openalex.org/W2089241138","https://openalex.org/W2099320873","https://openalex.org/W2104846587","https://openalex.org/W2108234281","https://openalex.org/W2109701112","https://openalex.org/W2110697718","https://openalex.org/W2116041602","https://openalex.org/W2138773756","https://openalex.org/W2142878546","https://openalex.org/W2145995659","https://openalex.org/W2151314777","https://openalex.org/W2154431984","https://openalex.org/W2154537630","https://openalex.org/W2166859993","https://openalex.org/W2168342464","https://openalex.org/W2177784250","https://openalex.org/W2236822143","https://openalex.org/W4299490599"],"related_works":["https://openalex.org/W4362511652","https://openalex.org/W4362511917","https://openalex.org/W4362511922","https://openalex.org/W4362485688","https://openalex.org/W4362530184","https://openalex.org/W4362530193","https://openalex.org/W2904597490","https://openalex.org/W4362485661","https://openalex.org/W4362592482","https://openalex.org/W4362511560"],"abstract_inverted_index":{"RNA-seq":[0,44,65],"is":[1,100,154,169,186],"a":[2,14,32,52,69,170],"high-throughput":[3],"Next-sequencing":[4],"technique":[5,30],"for":[6,103,109],"estimating":[7],"the":[8,29,48,61,94,121,128,157,163,174,182,191],"concentration":[9],"of":[10,35,55,139,156],"all":[11],"transcripts":[12],"in":[13,42,63,88,127,148,162,173],"transcriptome.":[15],"The":[16],"method":[17],"involves":[18],"complex":[19],"preparatory":[20],"and":[21,28,57,107,111,123],"post-processing":[22],"steps":[23],"which":[24],"can":[25],"introduce":[26],"bias,":[27],"produces":[31],"large":[33,105],"amount":[34,54],"data":[36,45,92],"[7,":[37],"19].":[38],"Two":[39],"important":[40],"challenges":[41],"processing":[43,104],"are":[46],"therefore":[47],"ability":[49],"to":[50,59,85],"process":[51],"vast":[53],"data,":[56,166],"methods":[58],"quantify":[60,86],"bias":[62,87],"public":[64],"datasets.":[66],"We":[67],"describe":[68],"novel":[70],"analysis":[71],"method,":[72],"based":[73],"on":[74,82,113],"analysing":[75],"sequence":[76],"motif":[77],"correlations,":[78],"that":[79,135],"employs":[80],"MapReduce":[81],"Apache":[83],"Spark":[84],"Next-generation":[89],"sequencing":[90],"(NGS)":[91],"at":[93],"deep":[95],"exon":[96,159],"level.":[97],"Our":[98],"implementation":[99],"designed":[101],"specifically":[102],"datasets":[106,180],"allows":[108],"scalability":[110],"deployment":[112],"cloud":[114],"service":[115],"providers":[116],"offering":[117],"MapReduce.":[118],"In":[119],"investigating":[120],"wild":[122,164],"mutant":[124,175],"organism":[125],"types":[126],"species":[129],"D.":[130],"melanogaster":[131],"we":[132],"have":[133],"found":[134],"motifs":[136],"with":[137,150],"runs":[138],"Gs":[140],"(or":[141],"their":[142],"complement)":[143],"exhibit":[144],"low":[145],"motif-pair":[146],"correlations":[147],"comparison":[149],"other":[151],"motif-pairs.":[152],"This":[153],"independent":[155],"mean":[158],"GC":[160],"content":[161],"type":[165],"but":[167],"there":[168,185],"mild":[171],"dependence":[172],"data.":[176],"Hence,":[177],"whilst":[178],"both":[179],"show":[181],"same":[183],"trends,":[184],"however":[187],"significant":[188],"variation":[189],"between":[190],"two":[192],"samples.":[193]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
