{"id":"https://openalex.org/W2887897252","doi":"https://doi.org/10.1109/tcbb.2018.2858797","title":"Fast de Bruijn Graph Compaction in Distributed Memory Environments","display_name":"Fast de Bruijn Graph Compaction in Distributed Memory Environments","publication_year":2018,"publication_date":"2018-07-31","ids":{"openalex":"https://openalex.org/W2887897252","doi":"https://doi.org/10.1109/tcbb.2018.2858797","mag":"2887897252","pmid":"https://pubmed.ncbi.nlm.nih.gov/30072337"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2018.2858797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2018.2858797","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5105460573","display_name":"Tony Pan","orcid":"https://orcid.org/0000-0001-7945-6534"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tony Pan","raw_affiliation_strings":["School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090757326","display_name":"Rahul Nihalani","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Nihalani","raw_affiliation_strings":["School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074347913","display_name":"Srinivas Aluru","orcid":"https://orcid.org/0000-0003-4279-469X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinivas Aluru","raw_affiliation_strings":["School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5105460573"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.9281,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.74511691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"17","issue":"1","first_page":"136","last_page":"148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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":0.9998999834060669,"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/T10434","display_name":"Chromosomal and Genetic Variations","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9850999712944031,"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":0.8588866591453552},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.7823654413223267},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7422126531600952},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5935397744178772},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.5143672227859497},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.47686752676963806},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.46925589442253113},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.42807555198669434},{"id":"https://openalex.org/keywords/compaction","display_name":"Compaction","score":0.4249248504638672},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35453498363494873},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.16679170727729797},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15474972128868103}],"concepts":[{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.8588866591453552},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.7823654413223267},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422126531600952},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5935397744178772},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.5143672227859497},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.47686752676963806},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46925589442253113},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42807555198669434},{"id":"https://openalex.org/C196715460","wikidata":"https://www.wikidata.org/wiki/Q1414356","display_name":"Compaction","level":2,"score":0.4249248504638672},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35453498363494873},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.16679170727729797},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15474972128868103},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbb.2018.2858797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2018.2858797","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:30072337","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30072337","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1795292305","display_name":null,"funder_award_id":"CNS-1229081","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2567864256","display_name":null,"funder_award_id":"CCF-1360593","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2736701487","display_name":null,"funder_award_id":"CCF-1361053","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7469405548","display_name":null,"funder_award_id":"IIS-1416259","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/F4320317220","display_name":"National Energy Research Scientific Computing Center","ror":"https://ror.org/05v3mvq14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W79056793","https://openalex.org/W1766349993","https://openalex.org/W1850079471","https://openalex.org/W1966822396","https://openalex.org/W1968819403","https://openalex.org/W1989437487","https://openalex.org/W2005202728","https://openalex.org/W2022986961","https://openalex.org/W2037859624","https://openalex.org/W2042200819","https://openalex.org/W2060380866","https://openalex.org/W2084134542","https://openalex.org/W2115501618","https://openalex.org/W2120902911","https://openalex.org/W2127768708","https://openalex.org/W2129933858","https://openalex.org/W2133531097","https://openalex.org/W2136651963","https://openalex.org/W2139518905","https://openalex.org/W2141370774","https://openalex.org/W2160969485","https://openalex.org/W2438121987","https://openalex.org/W2557391416","https://openalex.org/W2761301729","https://openalex.org/W6638157315"],"related_works":["https://openalex.org/W2562683361","https://openalex.org/W3087469195","https://openalex.org/W2354744388","https://openalex.org/W3125399386","https://openalex.org/W2949121831","https://openalex.org/W1908987670","https://openalex.org/W2756186577","https://openalex.org/W2735897904","https://openalex.org/W3215786367","https://openalex.org/W3021341025"],"abstract_inverted_index":{"De":[0],"Bruijn":[1,82,142],"graph":[2,49,143],"based":[3],"genome":[4,140],"assembly":[5,17],"has":[6],"gained":[7],"popularity":[8],"as":[9,36],"short":[10],"read":[11,148],"sequencers":[12],"become":[13],"ubiquitous.":[14],"A":[15],"core":[16],"operation":[18],"is":[19,168,192],"the":[20,31,92,102,105,121,124,177,190],"generation":[21],"of":[22,76,87,99,104,118,123,132,189],"unitigs,":[23],"which":[24,54],"are":[25,34,56],"sequences":[26,42],"corresponding":[27],"to":[28,96,110,130],"chains":[29,78,114],"in":[30,43,79,101,120,150,159,176],"graph.":[32],"Unitigs":[33],"used":[35],"building":[37],"blocks":[38],"for":[39,73,180],"generating":[40],"longer":[41],"many":[44],"assemblers,":[45],"and":[46,108,135,158,170,182],"can":[47,136],"facilitate":[48],"compression.":[50],"Chain":[51],"compaction,":[52],"by":[53],"unitigs":[55],"generated,":[57],"remains":[58],"a":[59,68,138,145],"critical":[60],"computational":[61,133],"task.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"present":[67],"distributed":[69,155,181],"memory":[70,156,165,184],"parallel":[71],"algorithm":[72,89,128,191],"simultaneous":[74],"compaction":[75,94],"all":[77],"bi-directed":[80],"de":[81,141],"graphs.":[83],"The":[84],"key":[85],"advantages":[86],"our":[88],"include":[90],"bounding":[91],"chain":[93],"run-time":[95],"logarithmic":[97,116],"number":[98,117],"iterations":[100,119],"length":[103,122],"longest":[106,125],"chain,":[107],"ability":[109],"differentiate":[111],"cycles":[112],"from":[113,144],"within":[115],"cycle.":[126],"Our":[127],"scales":[129],"thousands":[131],"cores,":[134,157],"compact":[137],"whole":[139],"human":[146],"sequence":[147],"set":[149],"7.3":[151],"seconds":[152],"using":[153,162],"7680":[154],"12.9":[160],"minutes":[161],"64":[163],"shared":[164,183],"cores.":[166],"It":[167],"3.7\u00d7":[169],"2.0\u00d7":[171],"faster":[172],"than":[173],"equivalent":[174],"steps":[175],"state-of-the-art":[178],"tools":[179],"environments,":[185],"respectively.":[186],"An":[187],"implementation":[188],"available":[193],"at":[194],"https://github.com/ParBLiSS/bruno.":[195]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}