{"id":"https://openalex.org/W2735897904","doi":"https://doi.org/10.1093/bioinformatics/btx261","title":"deBGR: an efficient and near-exact representation of the weighted de Bruijn graph","display_name":"deBGR: an efficient and near-exact representation of the weighted de Bruijn graph","publication_year":2017,"publication_date":"2017-04-20","ids":{"openalex":"https://openalex.org/W2735897904","doi":"https://doi.org/10.1093/bioinformatics/btx261","mag":"2735897904","pmid":"https://pubmed.ncbi.nlm.nih.gov/28881995"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btx261","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx261","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/14/i133/25157228/btx261.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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/33/14/i133/25157228/btx261.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014159929","display_name":"Prashant Pandey","orcid":"https://orcid.org/0000-0001-5576-0320"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prashant Pandey","raw_affiliation_strings":["Department of Computer Science, Stony Brook University, Stony Brook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068761590","display_name":"Michael A. Bender","orcid":"https://orcid.org/0000-0001-7639-530X"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael A Bender","raw_affiliation_strings":["Department of Computer Science, Stony Brook University, Stony Brook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101626826","display_name":"Rob Johnson","orcid":"https://orcid.org/0000-0002-0784-7410"},"institutions":[{"id":"https://openalex.org/I4391768063","display_name":"VMware (United States)","ror":"https://ror.org/01mwmh458","country_code":null,"type":"company","lineage":["https://openalex.org/I4391768063"]},{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rob Johnson","raw_affiliation_strings":["Department of Computer Science, Stony Brook University, Stony Brook, NY, USA","VMWare, Inc., Palo Alto, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]},{"raw_affiliation_string":"VMWare, Inc., Palo Alto, CA","institution_ids":["https://openalex.org/I4391768063"]}]},{"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/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rob Patro","raw_affiliation_strings":["Department of Computer Science, Stony Brook University, Stony Brook, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Stony Brook University, Stony Brook, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014584023"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":2.1288,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.87954726,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"33","issue":"14","first_page":"i133","last_page":"i141"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9732999801635742,"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":0.9732999801635742,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.004900000058114529,"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":0.003100000089034438,"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-graph","display_name":"De Bruijn graph","score":0.9512397646903992},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.9476922750473022},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.667361319065094},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.45913201570510864},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.44781258702278137},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33919334411621094},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.3201984167098999},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24468913674354553}],"concepts":[{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.9512397646903992},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.9476922750473022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.667361319065094},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.45913201570510864},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.44781258702278137},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33919334411621094},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3201984167098999},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24468913674354553}],"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":"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":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","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":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btx261","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx261","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/14/i133/25157228/btx261.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:28881995","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28881995","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:osti.gov:1430372","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1430372","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},{"id":"pmh:oai:pubmedcentral.nih.gov:5870571","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5870571","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btx261","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx261","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/14/i133/25157228/btx261.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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1446125321","display_name":null,"funder_award_id":"IIS\u00a01251137","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4941088576","display_name":null,"funder_award_id":"CCF\u00a01439084","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G726746010","display_name":null,"funder_award_id":"CNS 1408695","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7536231128","display_name":null,"funder_award_id":"BBSRC-NSF/BIO-1564917","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7692725557","display_name":null,"funder_award_id":"IIS 1247726","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8750242959","display_name":null,"funder_award_id":"CCF-1617618","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/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W6247929","https://openalex.org/W1964377951","https://openalex.org/W1966822396","https://openalex.org/W2041391522","https://openalex.org/W2080234606","https://openalex.org/W2105371278","https://openalex.org/W2105656684","https://openalex.org/W2115546424","https://openalex.org/W2116435146","https://openalex.org/W2123845384","https://openalex.org/W2126419817","https://openalex.org/W2136651963","https://openalex.org/W2156841387","https://openalex.org/W2157539385","https://openalex.org/W2160969485","https://openalex.org/W2163584430","https://openalex.org/W2163830511","https://openalex.org/W2171963266","https://openalex.org/W2179064901","https://openalex.org/W2198888083","https://openalex.org/W2266239166","https://openalex.org/W2276982311","https://openalex.org/W2312323279","https://openalex.org/W2340761128","https://openalex.org/W2417068752","https://openalex.org/W2477408078","https://openalex.org/W2500932352","https://openalex.org/W2529108608","https://openalex.org/W2563930566","https://openalex.org/W2598785105","https://openalex.org/W2612838847","https://openalex.org/W2949074212","https://openalex.org/W2950354111","https://openalex.org/W2952036159","https://openalex.org/W6698701264","https://openalex.org/W6703756101","https://openalex.org/W6764731151"],"related_works":["https://openalex.org/W2562683361","https://openalex.org/W3087469195","https://openalex.org/W3125399386","https://openalex.org/W2354744388","https://openalex.org/W2949121831","https://openalex.org/W3215786367","https://openalex.org/W4301429973","https://openalex.org/W2951695076","https://openalex.org/W1964377951","https://openalex.org/W2122316710"],"abstract_inverted_index":{"MOTIVATION:":[0],"Almost":[1],"all":[2,178],"de":[3,17,69,77,87,134,163,180,199],"novo":[4],"short-read":[5],"genome":[6],"and":[7,63,185,194],"transcriptome":[8,122],"assemblers":[9],"start":[10],"by":[11,48,155],"building":[12],"a":[13,127,174],"representation":[14,146,166],"of":[15,20,73,76,92,102,111,191],"the":[16,21,74,109,132,152,161],"Bruijn":[18,70,78,88,135,164,181,200],"Graph":[19,136],"reads":[22],"they":[23],"are":[24,32,214],"given":[25],"as":[26],"input.":[27],"Even":[28],"when":[29,38],"other":[30],"approaches":[31],"used":[33],"for":[34,60,85,129],"subsequent":[35],"assembly":[36],"(e.g.":[37],"one":[39],"is":[40,57,119,171,187],"using":[41],"'long":[42],"read'":[43],"technologies":[44],"like":[45],"those":[46],"offered":[47],"PacBio":[49],"or":[50],"Oxford":[51],"Nanopore),":[52],"efficient":[53],"k":[54,115],"-mer":[55,116],"processing":[56],"still":[58],"crucial":[59],"accurate":[61],"assembly,":[62],"state-of-the-art":[64],"long-read":[65],"error-correction":[66],"methods":[67,84,104],"use":[68],"Graphs.":[71],"Because":[72],"centrality":[75],"Graphs,":[79],"researchers":[80],"have":[81],"proposed":[82],"numerous":[83],"representing":[86,131],"Graphs":[89,182],"compactly.":[90],"Some":[91],"these":[93,103],"proposals":[94],"sacrifice":[95],"accuracy":[96],"to":[97,160,189],"save":[98],"space.":[99],"Further,":[100],"none":[101],"store":[105],"abundance":[106,139],"information,":[107],"i.e.":[108],"number":[110],"times":[112],"that":[113,177],"each":[114],"occurs,":[117],"which":[118],"key":[120],"in":[121,167,196],"assemblers.":[123],"RESULTS:":[124],"We":[125],"present":[126],"method":[128],"compactly":[130],"weighted":[133,179,198],"(i.e.":[137],"with":[138,141],"information)":[140],"essentially":[142],"no":[143],"errors.":[144],"Our":[145,169],"yields":[147],"zero":[148],"errors":[149],"while":[150],"increasing":[151],"space":[153],"requirements":[154],"less":[156],"than":[157],"18-28%":[158],"compared":[159],"approximate":[162],"graph":[165],"Squeakr.":[168],"technique":[170],"based":[172],"on":[173],"simple":[175],"invariant":[176],"must":[183],"satisfy,":[184],"hence":[186],"likely":[188],"be":[190],"general":[192],"interest":[193],"applicable":[195],"most":[197],"Graph-based":[201],"systems.":[202],"AVAILABILITY":[203],"AND":[204],"IMPLEMENTATION:":[205],"https://github.com/splatlab/debgr":[206],".":[207],"CONTACT:":[208],"rob.patro@cs.stonybrook.edu.":[209],"SUPPLEMENTARY":[210],"INFORMATION:":[211],"Supplementary":[212],"data":[213],"available":[215],"at":[216],"Bioinformatics":[217],"online.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}