{"id":"https://openalex.org/W2006192792","doi":"https://doi.org/10.1109/ispass.2009.4919646","title":"Characterizing and optimizing the memory footprint of de novo short read DNA sequence assembly","display_name":"Characterizing and optimizing the memory footprint of de novo short read DNA sequence assembly","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2006192792","doi":"https://doi.org/10.1109/ispass.2009.4919646","mag":"2006192792"},"language":"en","primary_location":{"id":"doi:10.1109/ispass.2009.4919646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2009.4919646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Performance Analysis of Systems and Software","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/A5021065409","display_name":"Jeffrey Cook","orcid":"https://orcid.org/0000-0002-7859-4131"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jeffrey J. Cook","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, USA","Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, USA#TAB#","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066756473","display_name":"Craig Zilles","orcid":"https://orcid.org/0000-0003-4601-4398"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Craig Zilles","raw_affiliation_strings":["Department of Computer Science, University of Illinois, Urbana-Champaign, USA","[Dept. of Computer Science, Univ. of Illinois at Urbana, Champaign, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[Dept. of Computer Science, Univ. of Illinois at Urbana, Champaign, USA]","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021065409"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.09692073,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"143","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9919000267982483,"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":0.9915000200271606,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/de-bruijn-graph","display_name":"De Bruijn graph","score":0.8246667981147766},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.7435171604156494},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7369812726974487},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.7101650834083557},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.7071644067764282},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.5427861213684082},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5070345401763916},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5016632080078125},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.45101338624954224},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.43012911081314087},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4221477508544922},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33784711360931396},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.33428484201431274},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2917385697364807},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.17051300406455994},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.16193485260009766},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.09162765741348267}],"concepts":[{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.8246667981147766},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.7435171604156494},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7369812726974487},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.7101650834083557},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.7071644067764282},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.5427861213684082},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5070345401763916},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5016632080078125},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.45101338624954224},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43012911081314087},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4221477508544922},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33784711360931396},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.33428484201431274},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2917385697364807},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.17051300406455994},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.16193485260009766},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.09162765741348267},{"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","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/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispass.2009.4919646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2009.4919646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Symposium on Performance Analysis of Systems and Software","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2016974511","https://openalex.org/W2023911006","https://openalex.org/W2124117796","https://openalex.org/W2136651963","https://openalex.org/W2138270253","https://openalex.org/W2142749416","https://openalex.org/W2151017710","https://openalex.org/W2160969485","https://openalex.org/W6678394647"],"related_works":["https://openalex.org/W2120956621","https://openalex.org/W2915362964","https://openalex.org/W2991626973","https://openalex.org/W3215786367","https://openalex.org/W3205360317","https://openalex.org/W4318940746","https://openalex.org/W2562683361","https://openalex.org/W2006192792","https://openalex.org/W4387083702","https://openalex.org/W2133531097"],"abstract_inverted_index":{"In":[0,31],"this":[1,120,137],"work,":[2],"we":[3,33,68,85,91,114,134,162],"analyze":[4,34],"the":[5,17,35,51,70,75,117,123,128],"memory-intensive":[6],"bioinformatics":[7,61],"problem":[8],"of":[9,19,111,119],"ldquode":[10],"novordquo":[11],"DNA":[12,22],"sequence":[13,82,99],"assembly,":[14,44],"which":[15,45,63],"is":[16,46],"process":[18],"assembling":[20],"short":[21],"sequences":[23],"obtained":[24],"by":[25,54],"experiment":[26],"into":[27,145],"larger":[28,102,158],"contiguous":[29],"sequences.":[30],"particular,":[32],"performance":[36,77,125,167],"scaling":[37],"challenges":[38],"inherent":[39],"to":[40,73,104,127,148,154,156],"de":[41,80,150],"Bruijn":[42,151],"graph-based":[43,152],"particularly":[47],"well":[48],"suited":[49],"for":[50,79],"data":[52],"produced":[53],"ldquonext":[55],"generationrdquo":[56],"sequencing":[57],"machines.":[58],"Unlike":[59],"many":[60],"codes":[62],"are":[64],"computation-intensive":[65],"or":[66],"control-intensive,":[67],"find":[69],"memory":[71],"footprint":[72],"be":[74,105,143,169],"primary":[76],"issue":[78],"novo":[81],"assembly.":[83],"Specifically,":[84],"make":[86],"four":[87],"main":[88],"contributions:":[89],"1)":[90],"demonstrate":[92,135,163],"analytically":[93],"that":[94,116],"performing":[95],"error":[96,139],"correction":[97,140],"before":[98],"assembly":[100,130,153],"enables":[101],"genomes":[103],"assembled":[106],"in":[107],"a":[108],"given":[109],"amount":[110],"memory,":[112],"2)":[113],"identify":[115],"use":[118],"technique":[121,141],"provides":[122],"key":[124],"advantage":[126],"leading":[129],"code,":[131],"Velvet,":[132],"3)":[133],"how":[136,164],"pre-assembly":[138],"can":[142,168],"subdivided":[144],"multiple":[146],"passes":[147],"enable":[149],"scale":[155],"even":[157],"genomes,":[159],"and":[160],"4)":[161],"Velvet's":[165],"in-core":[166],"improved":[170],"using":[171],"memory-centric":[172],"optimizations.":[173]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}