{"id":"https://openalex.org/W2133531097","doi":"https://doi.org/10.1093/bioinformatics/btq697","title":"Succinct data structures for assembling large genomes","display_name":"Succinct data structures for assembling large genomes","publication_year":2011,"publication_date":"2011-01-17","ids":{"openalex":"https://openalex.org/W2133531097","doi":"https://doi.org/10.1093/bioinformatics/btq697","mag":"2133531097","pmid":"https://pubmed.ncbi.nlm.nih.gov/21245053"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btq697","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btq697","pdf_url":null,"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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046030886","display_name":"Thomas Conway","orcid":"https://orcid.org/0000-0003-3966-5109"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Thomas C. Conway","raw_affiliation_strings":["NICTA Victoria Research Laboratory, Department of Computer Science and Engineering, The University of Melbourne, Parkville, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NICTA Victoria Research Laboratory, Department of Computer Science and Engineering, The University of Melbourne, Parkville, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018478843","display_name":"Andrew Bromage","orcid":null},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Andrew J. Bromage","raw_affiliation_strings":["NICTA Victoria Research Laboratory, Department of Computer Science and Engineering, The University of Melbourne, Parkville, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NICTA Victoria Research Laboratory, Department of Computer Science and Engineering, The University of Melbourne, Parkville, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046030886"],"corresponding_institution_ids":["https://openalex.org/I165779595","https://openalex.org/I42894916"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":6.6533,"has_fulltext":false,"cited_by_count":149,"citation_normalized_percentile":{"value":0.97686867,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"27","issue":"4","first_page":"479","last_page":"486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.7408000230789185,"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":0.7408000230789185,"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":0.09589999914169312,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.06120000034570694,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.8632931709289551},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.7307672500610352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7200844287872314},{"id":"https://openalex.org/keywords/structural-variation","display_name":"Structural variation","score":0.646446704864502},{"id":"https://openalex.org/keywords/de-bruijn-graph","display_name":"De Bruijn graph","score":0.6305747032165527},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.5291638374328613},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4636897146701813},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.45863282680511475},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.4518813192844391},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4454859495162964},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44547489285469055},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4341820180416107},{"id":"https://openalex.org/keywords/biomedicine","display_name":"Biomedicine","score":0.42368248105049133},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.28242963552474976},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.2765270173549652},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.17513194680213928},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.16238471865653992},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11513933539390564}],"concepts":[{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.8632931709289551},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.7307672500610352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7200844287872314},{"id":"https://openalex.org/C151020129","wikidata":"https://www.wikidata.org/wiki/Q7625067","display_name":"Structural variation","level":4,"score":0.646446704864502},{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.6305747032165527},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.5291638374328613},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4636897146701813},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.45863282680511475},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.4518813192844391},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4454859495162964},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44547489285469055},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4341820180416107},{"id":"https://openalex.org/C66782513","wikidata":"https://www.wikidata.org/wiki/Q864601","display_name":"Biomedicine","level":2,"score":0.42368248105049133},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.28242963552474976},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.2765270173549652},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.17513194680213928},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.16238471865653992},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11513933539390564},{"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/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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[{"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":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","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}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btq697","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btq697","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:21245053","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21245053","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W134891914","https://openalex.org/W1523949762","https://openalex.org/W1530061632","https://openalex.org/W1537803653","https://openalex.org/W1551461028","https://openalex.org/W1584822585","https://openalex.org/W1602427779","https://openalex.org/W1848935688","https://openalex.org/W1850079471","https://openalex.org/W1949346071","https://openalex.org/W1966822396","https://openalex.org/W1972924519","https://openalex.org/W1974033543","https://openalex.org/W1992751852","https://openalex.org/W2012016911","https://openalex.org/W2019338982","https://openalex.org/W2022910024","https://openalex.org/W2026377243","https://openalex.org/W2027244654","https://openalex.org/W2057223122","https://openalex.org/W2094424649","https://openalex.org/W2109089989","https://openalex.org/W2116387239","https://openalex.org/W2136651963","https://openalex.org/W2149243190","https://openalex.org/W2155011418","https://openalex.org/W2157174514","https://openalex.org/W2160969485","https://openalex.org/W2913618476","https://openalex.org/W4206871748","https://openalex.org/W6631377939","https://openalex.org/W6631472589","https://openalex.org/W6633123767","https://openalex.org/W6636039619","https://openalex.org/W6638737306","https://openalex.org/W6641128955","https://openalex.org/W6648198226","https://openalex.org/W6758925993"],"related_works":["https://openalex.org/W2120956621","https://openalex.org/W2915362964","https://openalex.org/W3215786367","https://openalex.org/W3205360317","https://openalex.org/W4318940746","https://openalex.org/W3200242814","https://openalex.org/W4282946044","https://openalex.org/W4214573178","https://openalex.org/W4387083702","https://openalex.org/W2133531097"],"abstract_inverted_index":{"Abstract":[0],"Motivation:":[1],"Second-generation":[2],"sequencing":[3,153],"technology":[4],"makes":[5],"it":[6,45,155],"feasible":[7],"for":[8,35,66,83,185],"many":[9],"researches":[10],"to":[11,16,112],"obtain":[12],"enough":[13],"sequence":[14,58,79],"reads":[15],"attempt":[17],"the":[18,63,73,76,86,91,94,118,134,150,189],"de":[19,67,119,190],"novo":[20,28,68],"assembly":[21,29,69,121,170,192],"of":[22,50,78,90,98,117,129,136,152,167,171,183],"higher":[23],"eukaryotes":[24],"(including":[25],"mammals).":[26],"De":[27],"not":[30,71],"only":[31],"provides":[32],"a":[33,47,114,127,168,172,177],"tool":[34],"understanding":[36],"wide":[37],"scale":[38],"biological":[39],"variation,":[40],"but":[41],"within":[42],"human":[43,173],"biomedicine,":[44],"offers":[46],"direct":[48],"way":[49],"observing":[51],"both":[52],"large-scale":[53],"structural":[54],"variation":[55],"and":[56,93,187],"fine-scale":[57],"variation.":[59],"Unfortunately,":[60],"improvements":[61,74],"in":[62,75,149],"computational":[64,88],"feasibility":[65],"have":[70],"matched":[72],"gathering":[77],"data.":[80],"This":[81],"is":[82,146],"two":[84],"reasons:":[85],"inherent":[87],"complexity":[89],"problem":[92],"in-practice":[95],"memory":[96],"requirements":[97],"tools.":[99],"Results:":[100],"In":[101],"this":[102],"article,":[103],"we":[104],"use":[105],"entropy":[106,147],"compressed":[107],"or":[108],"succinct":[109],"data":[110,203],"structures":[111,137],"create":[113],"practical":[115],"representation":[116,145],"Bruijn":[120,191],"graph,":[122],"which":[123],"requires":[124],"at":[125,206],"least":[126],"factor":[128],"10":[130],"less":[131],"storage":[132],"than":[133,161],"kinds":[135],"used":[138],"by":[139],"deployed":[140],"methods.":[141],"Moreover,":[142],"because":[143],"our":[144],"compressed,":[148],"presence":[151],"errors":[154],"has":[156],"better":[157],"scaling":[158],"behaviour":[159],"asymptotically":[160],"conventional":[162],"approaches.":[163],"We":[164],"present":[165],"results":[166],"proof-of-concept":[169],"genome":[174],"performed":[175],"on":[176],"modest":[178],"commodity":[179],"server.":[180],"Availability:":[181],"Binaries":[182],"programs":[184],"constructing":[186],"traversing":[188],"graph":[193],"are":[194,204],"available":[195,205],"from":[196],"http://www.genomics.csse.unimelb.edu.au/succinctAssembly.":[197],"Contact:":[198],"tom.conway@nicta.com.au":[199],"Supplementary":[200,202],"information:":[201],"Bioinformatics":[207],"online.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":15}],"updated_date":"2026-06-23T06:36:01.041984","created_date":"2025-10-10T00:00:00"}