{"id":"https://openalex.org/W3178314485","doi":"https://doi.org/10.1093/bioinformatics/btab309","title":"Cuttlefish: fast, parallel and low-memory compaction of de Bruijn graphs from large-scale genome collections","display_name":"Cuttlefish: fast, parallel and low-memory compaction of de Bruijn graphs from large-scale genome collections","publication_year":2021,"publication_date":"2021-04-30","ids":{"openalex":"https://openalex.org/W3178314485","doi":"https://doi.org/10.1093/bioinformatics/btab309","mag":"3178314485","pmid":"https://pubmed.ncbi.nlm.nih.gov/34252958"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab309","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab309","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/Supplement_1/i177/39620518/btab309.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/37/Supplement_1/i177/39620518/btab309.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072999292","display_name":"Jamshed Khan","orcid":"https://orcid.org/0000-0002-5129-9749"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jamshed Khan","raw_affiliation_strings":["Center for Bioinformatics and Computational Biology, University of Maryland, College Park , MD 20742, USA","Department of Computer Science, University of Maryland, College Park , MD 20742, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Bioinformatics and Computational Biology, University of Maryland, College Park , MD 20742, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Department of Computer Science, University of Maryland, College Park , MD 20742, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014584023","display_name":"Rob Patro","orcid":"https://orcid.org/0000-0001-8463-1675"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rob Patro","raw_affiliation_strings":["Center for Bioinformatics and Computational Biology, University of Maryland, College Park , MD 20742, USA","Department of Computer Science, University of Maryland, College Park , MD 20742, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Bioinformatics and Computational Biology, University of Maryland, College Park , MD 20742, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Department of Computer Science, University of Maryland, College Park , MD 20742, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5014584023"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":2.3696,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.90008745,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"37","issue":"Supplement_1","first_page":"i177","last_page":"i186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8917999863624573,"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":0.8917999863624573,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.04309999942779541,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.0215000007301569,"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/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.849727213382721},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6642255783081055},{"id":"https://openalex.org/keywords/cuttlefish","display_name":"Cuttlefish","score":0.61635822057724},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5359073281288147},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4653490483760834},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40591299533843994},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3125060498714447},{"id":"https://openalex.org/keywords/fishery","display_name":"Fishery","score":0.21187081933021545},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.16480767726898193},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16326987743377686},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.11712384223937988},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.11079075932502747}],"concepts":[{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.849727213382721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6642255783081055},{"id":"https://openalex.org/C2779790239","wikidata":"https://www.wikidata.org/wiki/Q184479","display_name":"Cuttlefish","level":2,"score":0.61635822057724},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5359073281288147},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4653490483760834},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40591299533843994},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3125060498714447},{"id":"https://openalex.org/C505870484","wikidata":"https://www.wikidata.org/wiki/Q180538","display_name":"Fishery","level":1,"score":0.21187081933021545},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.16480767726898193},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16326987743377686},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.11712384223937988},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.11079075932502747},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049832","descriptor_name":"Decapodiformes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049832","descriptor_name":"Decapodiformes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049832","descriptor_name":"Decapodiformes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btab309","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab309","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/Supplement_1/i177/39620518/btab309.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34252958","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34252958","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8275350","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8275350","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btab309","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab309","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/Supplement_1/i177/39620518/btab309.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3184792579","display_name":null,"funder_award_id":"CCF-1750472","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6262999909","display_name":null,"funder_award_id":"R01 HG009937","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6785428991","display_name":null,"funder_award_id":"CNS-1763680","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8518319274","display_name":null,"funder_award_id":"R01 HG009937","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"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"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W6247929","https://openalex.org/W1867886327","https://openalex.org/W1964377951","https://openalex.org/W1966822396","https://openalex.org/W1982827785","https://openalex.org/W2010361633","https://openalex.org/W2012241850","https://openalex.org/W2048124712","https://openalex.org/W2096128575","https://openalex.org/W2105656684","https://openalex.org/W2112888168","https://openalex.org/W2120902911","https://openalex.org/W2120956621","https://openalex.org/W2121911035","https://openalex.org/W2123845384","https://openalex.org/W2127901812","https://openalex.org/W2129933858","https://openalex.org/W2136651963","https://openalex.org/W2141370774","https://openalex.org/W2142749416","https://openalex.org/W2151017710","https://openalex.org/W2151752966","https://openalex.org/W2160969485","https://openalex.org/W2161546116","https://openalex.org/W2163830511","https://openalex.org/W2278452282","https://openalex.org/W2438121987","https://openalex.org/W2474973645","https://openalex.org/W2477408078","https://openalex.org/W2543005225","https://openalex.org/W2554926829","https://openalex.org/W2583363792","https://openalex.org/W2759261668","https://openalex.org/W2784936077","https://openalex.org/W2793466413","https://openalex.org/W2809649683","https://openalex.org/W2887897252","https://openalex.org/W2949672921","https://openalex.org/W2952379095","https://openalex.org/W2953117120","https://openalex.org/W2954511508","https://openalex.org/W2957382730","https://openalex.org/W2963158913","https://openalex.org/W2995995746","https://openalex.org/W3011785159","https://openalex.org/W3033322505","https://openalex.org/W3085875665","https://openalex.org/W3134677442","https://openalex.org/W3145128584","https://openalex.org/W3168724350","https://openalex.org/W4236459334","https://openalex.org/W4246219036","https://openalex.org/W6765333668"],"related_works":["https://openalex.org/W415064416","https://openalex.org/W2984552890","https://openalex.org/W2141970274","https://openalex.org/W1487044041","https://openalex.org/W2023718331","https://openalex.org/W2028059501","https://openalex.org/W1966452280","https://openalex.org/W2028516245","https://openalex.org/W2213060787","https://openalex.org/W1868411906"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,220],"construction":[2,77],"of":[3,11,17,45,78,110,121,171,196,218,237,246],"the":[4,47,60,79,96,101,166,169,172,183,204,228],"compacted":[5,49,103,205],"de":[6,50,104,123],"Bruijn":[7,51,105,124],"graph":[8,52,80,106,125,184,206],"from":[9,81,107],"collections":[10],"reference":[12,82],"genomes":[13,188],"is":[14,53,84,147,253,258],"a":[15,42,91,108,118,177],"task":[16],"increasing":[18],"interest":[19],"in":[20,95,189,211,255],"genomic":[21,68],"analyses.":[22],"These":[23],"graphs":[24],"are":[25,271],"increasingly":[26],"used":[27,55],"as":[28,37,59,127,165],"sequence":[29,39],"indices":[30],"for":[31,62,185],"short-":[32],"and":[33,40,57,75,130,150,168,239,257],"long-read":[34],"alignment.":[35],"Also,":[36],"we":[38],"assemble":[41],"greater":[43],"diversity":[44],"genomes,":[46,203],"colored":[48],"being":[54],"more":[56,58,113],"basis":[61],"efficient":[63],"methods":[64],"to":[65,99,135],"perform":[66],"comparative":[67],"analyses":[69],"on":[70,227],"these":[71,132,225],"genomes.":[72],"Therefore,":[73],"time-":[74],"memory-efficient":[76],"sequences":[83],"an":[85,261],"important":[86],"problem.":[87],"RESULTS:":[88],"We":[89],"introduce":[90],"new":[92],"algorithm,":[93],"implemented":[94,254],"tool":[97,223],"Cuttlefish,":[98],"construct":[100],"(colored)":[102],"collection":[109],"one":[111],"or":[112],"genome":[114],"references.":[115],"Cuttlefish":[116,146,181,210,252],"introduces":[117],"novel":[119],"approach":[120],"modeling":[122],"vertices":[126],"finite-state":[128],"automata,":[129],"constrains":[131],"automata's":[133],"state-space":[134],"enable":[136],"tracking":[137],"their":[138],"transitioning":[139],"states":[140],"with":[141],"very":[142],"low":[143],"memory":[144],"usage.":[145],"also":[148],"fast":[149],"highly":[151],"parallelizable.":[152],"Experimental":[153],"results":[154],"demonstrate":[155],"that":[156],"it":[157],"scales":[158],"much":[159],"better":[160],"than":[161],"existing":[162],"approaches,":[163],"especially":[164],"number":[167],"scale":[170],"input":[173],"references":[174],"grow.":[175],"On":[176,198],"typical":[178],"shared-memory":[179],"machine,":[180],"constructed":[182,208],"100":[186],"human":[187],"under":[190,212,260],"9":[191,213],"h,":[192,214],"using":[193,215,234,243],"\u223c29":[194],"GB":[195,217,236,245],"memory.":[197,219],"11":[199],"diverse":[200],"conifer":[201],"plant":[202],"was":[207],"by":[209],"\u223c84":[216],"only":[221],"other":[222],"completing":[224],"tasks":[226],"hardware":[229],"took":[230],"over":[231,240],"23":[232],"h":[233,242],"\u223c126":[235],"memory,":[238,247],"16":[241],"\u223c289":[244],"respectively.":[248],"AVAILABILITY":[249],"AND":[250],"IMPLEMENTATION:":[251],"C++14,":[256],"available":[259,272],"open":[262],"source":[263],"license":[264],"at":[265,273],"https://github.com/COMBINE-lab/cuttlefish.":[266],"SUPPLEMENTARY":[267],"INFORMATION:":[268],"Supplementary":[269],"data":[270],"Bioinformatics":[274],"online.":[275]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":5}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
