{"id":"https://openalex.org/W2084134542","doi":"https://doi.org/10.1186/1471-2105-12-354","title":"Parallelized short read assembly of large genomes using de Bruijn graphs","display_name":"Parallelized short read assembly of large genomes using de Bruijn graphs","publication_year":2011,"publication_date":"2011-08-25","ids":{"openalex":"https://openalex.org/W2084134542","doi":"https://doi.org/10.1186/1471-2105-12-354","mag":"2084134542","pmid":"https://pubmed.ncbi.nlm.nih.gov/21867511"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-12-354","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-354","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-354","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-354","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100617992","display_name":"Yongchao Liu","orcid":"https://orcid.org/0000-0003-3440-9675"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yongchao Liu","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore. liuy0039@ntu.edu.sg","School of Computer Engineering, Nanyang Technological University,,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore. liuy0039@ntu.edu.sg","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University,,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020388832","display_name":"Bertil Schmidt","orcid":"https://orcid.org/0000-0003-2597-8331"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Bertil Schmidt","raw_affiliation_strings":["Institut f\u00fcr Informatik, Johannes Gutenberg University Mainz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Informatik, Johannes Gutenberg University Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059218594","display_name":"Douglas L. Maskell","orcid":"https://orcid.org/0000-0002-6588-4762"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Douglas L Maskell","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore","School of Computer Engineering, Nanyang Technological University,,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University,,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020388832","https://openalex.org/A5100617992"],"corresponding_institution_ids":["https://openalex.org/I172675005","https://openalex.org/I197323543"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":3.1629,"has_fulltext":true,"cited_by_count":76,"citation_normalized_percentile":{"value":0.9266389,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"12","issue":"1","first_page":"354","last_page":"354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8964999914169312,"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":0.8964999914169312,"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":0.012500000186264515,"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":0.008299999870359898,"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":0.8216373920440674},{"id":"https://openalex.org/keywords/de-bruijn-graph","display_name":"De Bruijn graph","score":0.7827054858207703},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5833433866500854},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5804314613342285},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.5636432766914368},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5039169192314148},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.5000443458557129},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.44686949253082275},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.33761951327323914},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.20986711978912354},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1766088604927063},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11968547105789185}],"concepts":[{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.8216373920440674},{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.7827054858207703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5833433866500854},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5804314613342285},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.5636432766914368},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5039169192314148},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.5000443458557129},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.44686949253082275},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.33761951327323914},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.20986711978912354},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1766088604927063},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11968547105789185},{"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}],"mesh":[{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"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":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-12-354","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-354","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-354","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:21867511","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21867511","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:3e92e6b67be34b2f8c813a468ddb2600","is_oa":true,"landing_page_url":"https://doaj.org/article/3e92e6b67be34b2f8c813a468ddb2600","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 12, Iss 1, p 354 (2011)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:2175053","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3167803","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-12-354","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-354","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-354","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2084134542.pdf","grobid_xml":"https://content.openalex.org/works/W2084134542.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1966822396","https://openalex.org/W1982827785","https://openalex.org/W2012016911","https://openalex.org/W2022986961","https://openalex.org/W2046594687","https://openalex.org/W2118335502","https://openalex.org/W2126552018","https://openalex.org/W2127651281","https://openalex.org/W2133531097","https://openalex.org/W2133956160","https://openalex.org/W2136145671","https://openalex.org/W2136651963","https://openalex.org/W2139518905","https://openalex.org/W2142749416","https://openalex.org/W2159998739","https://openalex.org/W2160969485","https://openalex.org/W2161546116","https://openalex.org/W2171475724"],"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/W2756186577","https://openalex.org/W2991626973","https://openalex.org/W4387083702","https://openalex.org/W4318940746","https://openalex.org/W2133531097"],"abstract_inverted_index":{"BACKGROUND:":[0],"Next-generation":[1],"sequencing":[2,13],"technologies":[3],"have":[4,16],"given":[5],"rise":[6],"to":[7,41,80,97,107,128,195,224],"the":[8,18,140,152,167,196,226],"explosive":[9,197],"increase":[10],"in":[11,103,172,233],"DNA":[12],"throughput,":[14],"and":[15,34,76,83,113,159,215,232],"promoted":[17],"recent":[19],"development":[20],"of":[21,38,47,66,71,149,157,164,200,210],"de":[22,60],"novo":[23],"short":[24,48,56,202],"read":[25,57,203],"assemblers.":[26],"However,":[27],"existing":[28],"assemblers":[29,184],"require":[30],"high":[31,230],"execution":[32,137],"times":[33],"a":[35,54],"large":[36,43,118,186],"amount":[37],"compute":[39,78,142,179,219,238],"resources":[40],"assemble":[42,225],"genomes":[44,187],"from":[45],"quantities":[46],"reads.":[49],"RESULTS:":[50],"We":[51],"present":[52],"PASHA,":[53],"parallelized":[55],"assembler":[58],"using":[59,86,236],"Bruijn":[61],"graphs,":[62],"which":[63],"takes":[64],"advantage":[65],"hybrid":[67,207],"computing":[68],"architectures":[69],"consisting":[70,209],"both":[72],"shared-memory":[73],"multi-core":[74,213],"CPUs":[75,214],"distributed-memory":[77],"clusters":[79],"gain":[81],"efficiency":[82],"scalability.":[84],"Evaluation":[85],"three":[87,108],"small-scale":[88],"real":[89],"paired-end":[90],"datasets":[91,120],"shows":[92],"that":[93],"PASHA":[94,130,221],"is":[95,121,170,222],"able":[96,223],"produce":[98],"more":[99],"contiguous":[100],"high-quality":[101],"assemblies":[102],"shorter":[104],"time":[105,235],"compared":[106],"leading":[109],"assemblers:":[110],"Velvet,":[111],"ABySS":[112],"SOAPdenovo.":[114],"PASHA's":[115],"scalability":[116],"for":[117,185],"genome":[119,125,228],"demonstrated":[122],"with":[123,135,151,176,229],"human":[124,168,227],"assembly.":[126],"Compared":[127],"ABySS,":[129],"achieves":[131],"competitive":[132],"assembly":[133,169],"quality":[134,231],"faster":[136],"speed":[138],"on":[139,212,218],"same":[141],"resources,":[143],"yielding":[144],"an":[145,160],"NG50":[146,161],"contig":[147,155],"size":[148,156,163,198],"503":[150],"longest":[153],"correct":[154],"18,252,":[158],"scaffold":[162],"2,294.":[165],"Moreover,":[166],"completed":[171],"about":[173],"21":[174],"hours":[175],"only":[177],"modest":[178,237],"resources.":[180,239],"CONCLUSIONS:":[181],"Developing":[182],"parallel":[183],"has":[188],"been":[189],"garnering":[190],"significant":[191],"research":[192],"efforts":[193],"due":[194],"growth":[199],"high-throughput":[201],"datasets.":[204],"By":[205],"employing":[206],"parallelism":[208],"multi-threading":[211],"message":[216],"passing":[217],"clusters,":[220],"reasonable":[234]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
