{"id":"https://openalex.org/W2061052291","doi":"https://doi.org/10.1109/bigdata.2014.7004306","title":"Using geometric structures to improve the error correction algorithm of high-throughput sequencing data on MapReduce framework","display_name":"Using geometric structures to improve the error correction algorithm of high-throughput sequencing data on MapReduce framework","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2061052291","doi":"https://doi.org/10.1109/bigdata.2014.7004306","mag":"2061052291"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2014.7004306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004306","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/A5083153241","display_name":"Wei-Chun Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Chun Chung","raw_affiliation_strings":["Academia Sinica, Research Center for Information Technology Innovation, Taiwan","Department of Computer Science and Information Engineering, National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Research Center for Information Technology Innovation, Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043842260","display_name":"Yu-Jung Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Jung Chang","raw_affiliation_strings":["Academia Sinica, Institute of Information Science, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Institute of Information Science, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109621956","display_name":"D. T. Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I162838928","display_name":"National Chung Hsing University","ror":"https://ror.org/05vn3ca78","country_code":"TW","type":"education","lineage":["https://openalex.org/I162838928"]},{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"D. T. Lee","raw_affiliation_strings":["Academia Sinica, Institute of Information Science, Taiwan","Department of Computer Science and Information Engineering, National Chung Hsing University, Taiwan","Department of Computer Science and Information Engineering, National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Institute of Information Science, Taiwan","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Chung Hsing University, Taiwan","institution_ids":["https://openalex.org/I162838928"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051317071","display_name":"Jan-Ming Ho","orcid":"https://orcid.org/0000-0002-2432-8233"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jan-Ming Ho","raw_affiliation_strings":["Academia Sinica, Research Center for Information Technology Innovation, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Research Center for Information Technology Innovation, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5693,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67131198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"784","last_page":"789"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9914000034332275,"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":0.9914000034332275,"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/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.9312000274658203,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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":0.9307000041007996,"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":0.7841381430625916},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.6606931686401367},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5742924213409424},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.5621253252029419},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5365924835205078},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.49271467328071594},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.45826297998428345},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.44815054535865784},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43824511766433716},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34119224548339844},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10773387551307678},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.09498152136802673},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.0796249508857727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7841381430625916},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.6606931686401367},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5742924213409424},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.5621253252029419},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5365924835205078},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.49271467328071594},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.45826297998428345},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.44815054535865784},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43824511766433716},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34119224548339844},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10773387551307678},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.09498152136802673},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0796249508857727},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"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/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2014.7004306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004306","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"},{"id":"https://openalex.org/F4320321041","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1596691921","https://openalex.org/W1965297308","https://openalex.org/W1977729554","https://openalex.org/W1980667059","https://openalex.org/W2006803276","https://openalex.org/W2009783955","https://openalex.org/W2014099509","https://openalex.org/W2022986961","https://openalex.org/W2056981018","https://openalex.org/W2057086640","https://openalex.org/W2062163414","https://openalex.org/W2065783627","https://openalex.org/W2101250487","https://openalex.org/W2113154626","https://openalex.org/W2118526609","https://openalex.org/W2119745866","https://openalex.org/W2122812051","https://openalex.org/W2127768708","https://openalex.org/W2133956160","https://openalex.org/W2134536343","https://openalex.org/W2140958272","https://openalex.org/W2148294372","https://openalex.org/W2149414426","https://openalex.org/W2152246890","https://openalex.org/W2160265768","https://openalex.org/W2160665949","https://openalex.org/W2160969485","https://openalex.org/W2173213060"],"related_works":["https://openalex.org/W4210830088","https://openalex.org/W2767590279","https://openalex.org/W3011183076","https://openalex.org/W2794893153","https://openalex.org/W2721624558","https://openalex.org/W2079322808","https://openalex.org/W2216477337","https://openalex.org/W2772185703","https://openalex.org/W2584868213","https://openalex.org/W2619753084"],"abstract_inverted_index":{"Next-generation":[0],"sequencing":[1,21,100],"(NGS)":[2],"data":[3,11],"are":[4,80],"a":[5,13,36],"rapidly":[6],"growing":[7],"example":[8],"of":[9,15,29,43,65,77,91,115,139,148,169],"big":[10],"and":[12,25,51,62,75,165],"source":[14],"new":[16],"knowledge":[17],"in":[18,39,73,102,133],"science.":[19],"However,":[20],"errors":[22,101],"remain":[23],"unavoidable":[24],"reduce":[26,162],"the":[27,40,63,89,107,113,118,128,140,145,158,167,170],"quality":[28,168],"NGS":[30,44,55,66,103],"data.":[31,104],"Error":[32],"correction,":[33],"therefore,":[34],"is":[35,70],"critical":[37],"step":[38],"successful":[41],"utilization":[42],"data,":[45],"including":[46],"de":[47,171],"novo":[48,172],"genome":[49,173],"assembly":[50],"DNA":[52],"resequencing.":[53],"Since":[54],"throughput":[56],"doubles":[57],"approximately":[58],"every":[59],"five":[60],"months":[61],"length":[64],"records":[67],"(i.e.,":[68],"reads)":[69],"increasing,":[71],"improvements":[72],"efficiency":[74],"effectiveness":[76],"computational":[78],"strategies":[79],"needed.":[81],"In":[82],"this":[83],"study,":[84],"we":[85],"aim":[86],"to":[87,98,111,135],"improve":[88,166],"performance":[90],"CloudRS,":[92],"an":[93],"open-source":[94],"MapReduce":[95],"application":[96],"designed":[97],"correct":[99],"We":[105,125],"introduce":[106],"readmessage":[108],"(RM)":[109],"diagram":[110],"represent":[112],"set":[114],"messages,":[116],"i.e.,":[117],"key-value":[119],"pairs":[120],"generated":[121],"on":[122],"each":[123,152],"read.":[124,153],"also":[126],"present":[127],"Gradient-number":[129],"Votes":[130],"(GNV)":[131],"scheme":[132,160],"order":[134],"trim":[136],"off":[137],"portions":[138],"RM":[141],"diagram,":[142],"thereby":[143],"reducing":[144],"total":[146],"size":[147],"messages":[149],"associated":[150],"with":[151],"Experimental":[154],"results":[155],"show":[156],"that":[157],"GNV":[159],"successfully":[161],"execution":[163],"time":[164],"assembly.":[174]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
