{"id":"https://openalex.org/W2950451697","doi":"https://doi.org/10.15781/t2k35mh0f","title":"Efficient Parallel and Out of Core Algorithms for Constructing Large Bi-Directed De Bruijn Graphs","display_name":"Efficient Parallel and Out of Core Algorithms for Constructing Large Bi-Directed De Bruijn Graphs","publication_year":2010,"publication_date":"2010-03-09","ids":{"openalex":"https://openalex.org/W2950451697","doi":"https://doi.org/10.15781/t2k35mh0f","mag":"2950451697"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1003.1940","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1003.1940","pdf_url":"https://arxiv.org/pdf/1003.1940","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1003.1940","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kundeti, Vamsi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kundeti, Vamsi","raw_affiliation_strings":["Department of Computer Science and Engineering University of Connecticut , Storrs , CT 06269"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering University of Connecticut , Storrs , CT 06269","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034177039","display_name":"Sanguthevar Rajasekaran","orcid":"https://orcid.org/0000-0002-0137-4843","observed_orcids":["https://orcid.org/0000-0002-0137-4843"]},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajasekaran, Sanguthevar","raw_affiliation_strings":["Department of Computer Science and Engineering University of Connecticut , Storrs , CT 06269"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering University of Connecticut , Storrs , CT 06269","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073118724","display_name":"Hieu Dinh","orcid":"https://orcid.org/0009-0000-4759-2064","observed_orcids":["https://orcid.org/0009-0000-4759-2064"]},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinh, Hieu","raw_affiliation_strings":["Department of Computer Science and Engineering University of Connecticut , Storrs , CT 06269"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering University of Connecticut , Storrs , CT 06269","institution_ids":["https://openalex.org/I140172145"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I140172145"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.8389000296592712,"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":0.8389000296592712,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.13840000331401825,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.008100000210106373,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/de-bruijn-graph","display_name":"de Bruijn graph","score":0.8930000066757202},{"id":"https://openalex.org/keywords/parallel-algorithms","display_name":"parallel algorithms","score":0.7039999961853027},{"id":"https://openalex.org/keywords/out-of-core-algorithms","display_name":"out-of-core algorithms","score":0.9919999837875366},{"id":"https://openalex.org/keywords/short-read-sequencing","display_name":"short-read sequencing","score":0.8519999980926514},{"id":"https://openalex.org/keywords/communication-complexity","display_name":"communication complexity","score":0.8040000200271606},{"id":"https://openalex.org/keywords/i-o-complexity","display_name":"I/O complexity","score":0.9890000224113464},{"id":"https://openalex.org/keywords/overlap-graphs","display_name":"overlap graphs","score":0.5600000023841858}],"concepts":[{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.9304293990135193},{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.7222095131874084},{"id":"https://openalex.org/C79470037","wikidata":"https://www.wikidata.org/wiki/Q279748","display_name":"Out-of-core algorithm","level":2,"score":0.672715425491333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6244632601737976},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5754302740097046},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.542849063873291},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.5213714241981506},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.4364888072013855},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38941842317581177},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3641678988933563},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2739230990409851},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2696652412414551},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"pmh:oai:arXiv.org:1003.1940","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1003.1940","pdf_url":"https://arxiv.org/pdf/1003.1940","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2950451697","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1003.1940v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.763.269","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.763.269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1003.1940.pdf","raw_type":"text"},{"id":"pmh:oai:repositories.lib.utexas.edu:2152/43195","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2152/43195","pdf_url":null,"source":{"id":"https://openalex.org/S4306400568","display_name":"Texas ScholarWorks (Texas Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210102904","host_organization_name":"Texas Digital Library","host_organization_lineage":["https://openalex.org/I4210102904"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"doi:10.48550/arxiv.1003.1940","doi":"https://doi.org/10.48550/arxiv.1003.1940","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1003.1940","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.15781/t2k35mh0f","doi":"https://doi.org/10.15781/t2k35mh0f","is_oa":true,"landing_page_url":"https://doi.org/10.15781/t2k35mh0f","pdf_url":null,"source":{"id":"https://openalex.org/S4306402198","display_name":"Texas Digital Library (University of Texas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86519309","host_organization_name":"The University of Texas at Austin","host_organization_lineage":["https://openalex.org/I86519309"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1003.1940","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1003.1940","pdf_url":"https://arxiv.org/pdf/1003.1940","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G3238539651","display_name":"EMT/NANO: Computing with Protein Based Associative Memory Processors","funder_award_id":"0829916","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4707202857","display_name":"ITR:      Information Extraction from Massive Data Sets","funder_award_id":"0326155","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1635391495","https://openalex.org/W1850079471","https://openalex.org/W1984236772","https://openalex.org/W2112120145","https://openalex.org/W2136651963","https://openalex.org/W2144662851","https://openalex.org/W2160969485"],"related_works":["https://openalex.org/W7095608230","https://openalex.org/W2887897252","https://openalex.org/W2165106352","https://openalex.org/W79056793","https://openalex.org/W2438121987","https://openalex.org/W4407232637","https://openalex.org/W3085875665","https://openalex.org/W2123639580","https://openalex.org/W3178314485","https://openalex.org/W147480410"],"abstract_inverted_index":{"Assembling":[0],"genomic":[1],"sequences":[2],"from":[3],"a":[4,50,72,139,152,158,211],"set":[5],"of":[6,11,118,126,164,175,200,206,216,221],"overlapping":[7],"reads":[8],"is":[9,115,123,168,230],"one":[10],"the":[12,21,32,46,56,116,119,124,187,204,238],"most":[13],"fundamental":[14],"problems":[15],"in":[16,59,75,89,191],"computational":[17],"biology.":[18],"Algorithms":[19],"addressing":[20],"assembly":[22],"problem":[23],"fall":[24],"into":[25],"two":[26],"broad":[27],"categories":[28],"--":[29],"based":[30,67,93],"on":[31,94,210],"data":[33],"structures":[34],"which":[35,135],"they":[36],"employ.":[37],"The":[38,173],"first":[39],"class":[40],"uses":[41,49],"an":[42,102,196],"overlap/string":[43],"graph":[44,66],"and":[45,121,141,167,190],"second":[47],"type":[48],"de":[51,64,83],"Bruijn":[52,65,84],"graph.":[53],"However":[54],"with":[55,138,157,219],"recent":[57],"advances":[58],"short":[60,95],"read":[61],"sequencing":[62,91],"technology,":[63],"algorithms":[68,78,236],"seem":[69],"to":[70,162,171,182,186],"play":[71],"vital":[73],"role":[74],"practice.":[76],"Efficient":[77],"for":[79,110,237],"building":[80],"these":[81],"massive":[82],"graphs":[85],"are":[86],"very":[87,180],"essential":[88],"large":[90],"projects":[92],"reads.":[96],"In":[97,147],"Jackson":[98,222],"et.":[99,223],"al.":[100,224],"ICPP-2008,":[101],"$O(n/p)$":[103],"time":[104,154],"parallel":[105,155,165,208],"algorithm":[106,129,156,177,209,218,229],"has":[107,195],"been":[108],"given":[109],"this":[111,148,192],"problem.":[112,242],"Here":[113],"$n$":[114],"size":[117],"input":[120],"$p$":[122],"number":[125],"processors.":[127],"This":[128],"enumerates":[130],"all":[131],"possible":[132],"bi-directed":[133,239],"edges":[134],"can":[136],"overlap":[137],"node":[140],"ends":[142],"up":[143],"generating":[144],"$\u0398(n\u03a3)$":[145],"messages.":[146],"paper":[149],"we":[150],"present":[151],"$\u0398(n/p)$":[153],"communication":[159],"complexity":[160,199],"equal":[161],"that":[163,220,227],"sorting":[166],"not":[169],"sensitive":[170],"$\u03a3$.":[172],"generality":[174],"our":[176,207,217,228],"makes":[178],"it":[179,184,194],"easy":[181],"extend":[183],"even":[185],"out-of-core":[188],"model":[189],"case":[193],"optimal":[197],"I/O":[198],"$\u0398(\\frac{n\\log(n/B)}{B\\log(M/B)})$.":[201],"We":[202,232],"demonstrate":[203],"scalability":[205],"SGI/Altix":[212],"computer.":[213],"A":[214],"comparison":[215],"ICPP-2008":[225],"reveals":[226],"faster.":[231],"also":[233],"provide":[234],"efficient":[235],"chain":[240],"compaction":[241]},"counts_by_year":[],"updated_date":"2026-10-02T10:15:12.560889","created_date":"2019-06-27T00:00:00"}