{"id":"https://openalex.org/W3138547708","doi":"https://doi.org/10.1109/bigdata50022.2020.9377979","title":"Distributed de novo assembler for large-scale long-read datasets","display_name":"Distributed de novo assembler for large-scale long-read datasets","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3138547708","doi":"https://doi.org/10.1109/bigdata50022.2020.9377979","mag":"3138547708"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9377979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","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/2541","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038227075","display_name":"S.C. Goswami","orcid":"https://orcid.org/0000-0002-7519-524X"},"institutions":[{"id":"https://openalex.org/I26489229","display_name":"Louisiana State University in Shreveport","ror":"https://ror.org/02c4cbt39","country_code":"US","type":"education","lineage":["https://openalex.org/I26489229"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sayan Goswami","raw_affiliation_strings":["Department of Computer Science, Louisiana State University Shreveport"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Louisiana State University Shreveport","institution_ids":["https://openalex.org/I26489229"]}]},{"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":["School of Electrical Engineering & Computer Science, Louisiana State University"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering & Computer Science, Louisiana State University","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":["School of Electrical Engineering & Computer Science, Center for Computation & Technology, Louisiana State University"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering & Computer Science, Center for Computation & Technology, Louisiana State University","institution_ids":["https://openalex.org/I121820613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038227075"],"corresponding_institution_ids":["https://openalex.org/I26489229"],"apc_list":null,"apc_paid":null,"fwci":0.0829,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46466421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"44","issue":null,"first_page":"1166","last_page":"1175"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10207","display_name":"Advanced biosensing and bioanalysis techniques","score":0.988099992275238,"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":0.7842495441436768},{"id":"https://openalex.org/keywords/nanopore-sequencing","display_name":"Nanopore sequencing","score":0.6913982629776001},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.5811220407485962},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5483591556549072},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.5230254530906677},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5099443197250366},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47187772393226624},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4632744789123535},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4614924192428589},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.44299063086509705},{"id":"https://openalex.org/keywords/hybrid-genome-assembly","display_name":"Hybrid genome assembly","score":0.43158793449401855},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.38069579005241394},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.3452628552913666},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2673749327659607},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18267372250556946},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.16562870144844055},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.14461231231689453},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12142553925514221}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842495441436768},{"id":"https://openalex.org/C126513998","wikidata":"https://www.wikidata.org/wiki/Q8973627","display_name":"Nanopore sequencing","level":4,"score":0.6913982629776001},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.5811220407485962},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5483591556549072},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.5230254530906677},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5099443197250366},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47187772393226624},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4632744789123535},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4614924192428589},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.44299063086509705},{"id":"https://openalex.org/C113425843","wikidata":"https://www.wikidata.org/wiki/Q5953213","display_name":"Hybrid genome assembly","level":5,"score":0.43158793449401855},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38069579005241394},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.3452628552913666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2673749327659607},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18267372250556946},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.16562870144844055},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.14461231231689453},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12142553925514221},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9377979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.lsu.edu:eecs_pubs-3543","is_oa":true,"landing_page_url":"https://repository.lsu.edu/eecs_pubs/2541","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-3543","is_oa":true,"landing_page_url":"https://repository.lsu.edu/eecs_pubs/2541","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W179815580","https://openalex.org/W1579534339","https://openalex.org/W1635391495","https://openalex.org/W1778776476","https://openalex.org/W1982579644","https://openalex.org/W1983403167","https://openalex.org/W2063678249","https://openalex.org/W2094740601","https://openalex.org/W2144560237","https://openalex.org/W2154323564","https://openalex.org/W2158714788","https://openalex.org/W2179507357","https://openalex.org/W2194172909","https://openalex.org/W2246743638","https://openalex.org/W2335878612","https://openalex.org/W2337261418","https://openalex.org/W2397469828","https://openalex.org/W2536287248","https://openalex.org/W2538143681","https://openalex.org/W2574300709","https://openalex.org/W2575750030","https://openalex.org/W2584834695","https://openalex.org/W2607669908","https://openalex.org/W2885240937","https://openalex.org/W2906966778","https://openalex.org/W2950354111","https://openalex.org/W2993563049","https://openalex.org/W2994735876","https://openalex.org/W3099661149","https://openalex.org/W6757231586","https://openalex.org/W7075604223"],"related_works":["https://openalex.org/W3167837387","https://openalex.org/W2521004200","https://openalex.org/W2949198880","https://openalex.org/W3090794301","https://openalex.org/W2189047836","https://openalex.org/W3100700403","https://openalex.org/W2767590279","https://openalex.org/W2213265806","https://openalex.org/W2763726643","https://openalex.org/W2607669908"],"abstract_inverted_index":{"Third-generation":[0],"DNA":[1],"sequencing":[2,8,12],"technologies":[3],"such":[4],"as":[5],"single-molecule":[6],"real-time":[7],"(SMRT)":[9],"and":[10,41],"nanopore":[11],"have":[13,52],"the":[14,18,21,26,59,123,171],"potential":[15],"to":[16,71,81,162],"fill":[17],"gaps":[19],"in":[20,44,113,154],"existing":[22,66],"genome":[23,145],"databases":[24],"since":[25,65],"raw":[27],"sequences":[28],"produced":[29],"by":[30],"these":[31,49],"machines":[32],"are":[33,69],"much":[34],"longer":[35],"than":[36,164],"those":[37],"of":[38,86,110,115],"previous":[39],"generations":[40],"therefore":[42],"result":[43],"more":[45,163],"contiguous":[46],"assemblies.":[47],"However,":[48],"long":[50],"reads":[51],"a":[53,74,97,128,134,142],"high":[54],"error":[55],"rate,":[56],"which":[57],"makes":[58],"assembly":[60,118],"process":[61],"computationally":[62],"challenging.":[63],"Moreover,":[64],"long-read":[67,99],"assemblers":[68],"designed":[70],"run":[72,84],"on":[73,88,108],"single":[75],"machine,":[76],"they":[77],"either":[78],"take":[79],"days":[80],"complete":[82],"or":[83],"out":[85],"memory":[87],"even":[89],"moderate-sized":[90],"datasets.":[91],"In":[92],"this":[93],"paper,":[94],"we":[95,139],"present":[96],"distributed":[98,129],"assembler":[100],"that":[101],"can":[102,140],"assemble":[103,141],"large-scale":[104],"noisy":[105],"sequence":[106],"datasets":[107],"thousands":[109],"cores,":[111],"resulting":[112],"orders":[114],"magnitude":[116],"faster":[117],"times.":[119],"By":[120],"effectively":[121],"using":[122,133],"map-reduce":[124],"computation":[125],"model":[126],"with":[127,147,170],"hash-map,":[130],"both":[131],"built":[132],"high-performance":[135],"active":[136],"messaging":[137],"middleware,":[138],"PacBio":[143],"human":[144],"dataset":[146],"139":[148],"billion":[149],"base-pairs":[150],"(about":[151],"130":[152],"GB)":[153],"about":[155],"33":[156],"minutes":[157],"(using":[158,167],"2,560":[159],"cores)":[160,169],"compared":[161],"38":[165],"hours":[166],"28":[168],"current":[172],"state-of-the-art":[173],"assembler.":[174]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
