{"id":"https://openalex.org/W2912187550","doi":"https://doi.org/10.1109/bibm.2018.8621549","title":"ParLECH: Parallel Long-Read Error Correction with Hadoop","display_name":"ParLECH: Parallel Long-Read Error Correction with Hadoop","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2912187550","doi":"https://doi.org/10.1109/bibm.2018.8621549","mag":"2912187550"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2018.8621549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2018.8621549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.lsu.edu/eecs_pubs/2551","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007929301","display_name":"Arghya Das","orcid":"https://orcid.org/0000-0003-0989-2175"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Arghya Kusum Das","raw_affiliation_strings":["Division of Computer Science and Engineering, School of Electrical Engineering and Computer Science, Center for Computation and Technology, Louisiana State University, Baton Rouge, Louisiana"],"affiliations":[{"raw_affiliation_string":"Division of Computer Science and Engineering, School of Electrical Engineering and Computer Science, Center for Computation and Technology, Louisiana State University, Baton Rouge, Louisiana","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103148122","display_name":"Kisung Lee","orcid":"https://orcid.org/0000-0003-4367-4374"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kisung Lee","raw_affiliation_strings":["Division of Computer Science and Engineering, School of Electrical Engineering and Computer Science, Center for Computation and Technology, Louisiana State University, Baton Rouge, Louisiana"],"affiliations":[{"raw_affiliation_string":"Division of Computer Science and Engineering, School of Electrical Engineering and Computer Science, Center for Computation and Technology, Louisiana State University, Baton Rouge, Louisiana","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079637252","display_name":"Seung\u2010Jong Park","orcid":"https://orcid.org/0000-0001-7821-7793"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seung-Jong Park","raw_affiliation_strings":["Division of Computer Science and Engineering, School of Electrical Engineering and Computer Science, Center for Computation and Technology, Louisiana State University, Baton Rouge, Louisiana"],"affiliations":[{"raw_affiliation_string":"Division of Computer Science and Engineering, School of Electrical Engineering and Computer Science, Center for Computation and Technology, Louisiana State University, Baton Rouge, Louisiana","institution_ids":["https://openalex.org/I121820613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007929301"],"corresponding_institution_ids":["https://openalex.org/I121820613"],"apc_list":null,"apc_paid":null,"fwci":0.0919,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49226471,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"341","last_page":"348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9990000128746033,"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":0.9990000128746033,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9861999750137329,"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/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.9506999850273132,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7977858185768127},{"id":"https://openalex.org/keywords/de-bruijn-graph","display_name":"De Bruijn graph","score":0.7098241448402405},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6854516267776489},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5006790161132812},{"id":"https://openalex.org/keywords/illumina-dye-sequencing","display_name":"Illumina dye sequencing","score":0.4850722849369049},{"id":"https://openalex.org/keywords/hybrid-genome-assembly","display_name":"Hybrid genome assembly","score":0.48182860016822815},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.44802555441856384},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3048397898674011},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.2960802912712097},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1288817822933197},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12685328722000122},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11078214645385742},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.08101359009742737},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.0728524923324585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7977858185768127},{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.7098241448402405},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6854516267776489},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5006790161132812},{"id":"https://openalex.org/C106337198","wikidata":"https://www.wikidata.org/wiki/Q13564012","display_name":"Illumina dye sequencing","level":4,"score":0.4850722849369049},{"id":"https://openalex.org/C113425843","wikidata":"https://www.wikidata.org/wiki/Q5953213","display_name":"Hybrid genome assembly","level":5,"score":0.48182860016822815},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.44802555441856384},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3048397898674011},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.2960802912712097},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1288817822933197},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12685328722000122},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11078214645385742},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08101359009742737},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0728524923324585},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bibm.2018.8621549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2018.8621549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.lsu.edu:eecs_pubs-3553","is_oa":true,"landing_page_url":"https://repository.lsu.edu/eecs_pubs/2551","pdf_url":null,"source":{"id":"https://openalex.org/S4210169993","display_name":"Civil War Book Review","issn_l":"1528-6592","issn":["1528-6592"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310315936","host_organization_name":"Louisiana State University","host_organization_lineage":["https://openalex.org/P4310315936"],"host_organization_lineage_names":["Louisiana State University"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:repository.lsu.edu:eecs_pubs-3553","is_oa":true,"landing_page_url":"https://repository.lsu.edu/eecs_pubs/2551","pdf_url":null,"source":{"id":"https://openalex.org/S4210169993","display_name":"Civil War Book Review","issn_l":"1528-6592","issn":["1528-6592"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310315936","host_organization_name":"Louisiana State University","host_organization_lineage":["https://openalex.org/P4310315936"],"host_organization_lineage_names":["Louisiana State University"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1980667059","https://openalex.org/W2001079689","https://openalex.org/W2005202728","https://openalex.org/W2014099509","https://openalex.org/W2041126213","https://openalex.org/W2054226908","https://openalex.org/W2060380866","https://openalex.org/W2103441770","https://openalex.org/W2113154626","https://openalex.org/W2119745866","https://openalex.org/W2133956160","https://openalex.org/W2137759177","https://openalex.org/W2139306346","https://openalex.org/W2152246890","https://openalex.org/W2157888653","https://openalex.org/W2160177274","https://openalex.org/W2160265768","https://openalex.org/W2160665949","https://openalex.org/W2179392581","https://openalex.org/W2216435802","https://openalex.org/W2340761128","https://openalex.org/W2396849069","https://openalex.org/W2518374209","https://openalex.org/W2584834695","https://openalex.org/W2619089911","https://openalex.org/W2756025122","https://openalex.org/W2885240937","https://openalex.org/W2950354111","https://openalex.org/W3046027090"],"related_works":["https://openalex.org/W4383426117","https://openalex.org/W2934828429","https://openalex.org/W280975","https://openalex.org/W3210858261","https://openalex.org/W4250456191","https://openalex.org/W2092772380","https://openalex.org/W2585341293","https://openalex.org/W2921468924","https://openalex.org/W2001935963","https://openalex.org/W4249457750"],"abstract_inverted_index":{"Long-read":[0],"sequencing":[1,7,24,39,46],"is":[2,50,74,117],"emerging":[3],"as":[4],"a":[5,65,122,145,160,179,199,209,217],"promising":[6],"technology":[8],"because":[9],"it":[10,30],"can":[11,193,207],"tackle":[12],"the":[13,23,84,87,92,98,111,129,133,138,149,155,163,169],"short":[14,94,114,140,171],"length":[15],"limitation":[16],"of":[17,56,137,148,162],"second-generation":[18],"sequencing,":[19],"which":[20,153],"has":[21,31],"dominated":[22],"market":[25],"in":[26,86,159,178,198,225],"past":[27],"years.":[28],"However,":[29],"substantially":[32],"higher":[33],"error":[34,68,100,176],"rates":[35],"compared":[36],"to":[37],"short-read":[38,57],"(e.g.,":[40],"13%":[41],"vs.":[42],"0.1%),":[43],"and":[44,76,121,201],"its":[45,183],"cost":[47],"per":[48],"base":[49],"typically":[51],"more":[52],"expensive":[53],"than":[54,227],"that":[55,73,96,191],"sequencing.":[58],"To":[59,108,126],"address":[60],"these":[61],"limitations,":[62],"we":[63,143,206],"present":[64],"distributed":[66,123,146],"hybrid":[67],"correction":[69],"framework,":[70],"called":[71],"ParLECH,":[72,205],"scalable":[75,200],"cost-efficient":[77],"for":[78],"PacBio":[79,214],"long":[80,88,180],"reads.":[81,141,172],"For":[82],"correcting":[83],"errors":[85],"reads,":[89,115],"ParLECH":[90,116,131,192],"utilizes":[91,132],"Illumina":[93,113,139,170,220],"reads":[95],"have":[97],"low":[99,106],"rate":[101],"with":[102,119,182,216],"high":[103],"coverage":[104,135,158],"at":[105],"cost.":[107],"efficiently":[109],"analyze":[110],"high-throughput":[112],"equipped":[118],"Hadoop":[120],"NoSQL":[124],"system.":[125],"further":[127],"improve":[128],"accuracy,":[130],"k-mer":[134,157],"information":[136],"Specifically,":[142],"develop":[144],"version":[147],"widest":[150,185],"path":[151,161],"algorithm,":[152],"maximizes":[154],"minimum":[156],"de":[164],"Bruijn":[165],"graph":[166],"constructed":[167],"from":[168],"We":[173],"replace":[174],"an":[175],"region":[177],"read":[181],"corresponding":[184],"path.":[186],"Our":[187],"experimental":[188],"results":[189],"show":[190],"handle":[194],"large-scale":[195],"real-world":[196],"datasets":[197],"accurate":[202],"manner.":[203],"Using":[204],"process":[208],"312":[210],"GB":[211,219],"human":[212],"genome":[213],"dataset,":[215,221],"452":[218],"on":[222],"128":[223],"nodes":[224],"less":[226],"29":[228],"hours.":[229]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
