{"id":"https://openalex.org/W2948074652","doi":"https://doi.org/10.1109/tcbb.2019.2920912","title":"Scalable De Novo Genome Assembly Using a Pregel-Like Graph-Parallel System","display_name":"Scalable De Novo Genome Assembly Using a Pregel-Like Graph-Parallel System","publication_year":2019,"publication_date":"2019-06-05","ids":{"openalex":"https://openalex.org/W2948074652","doi":"https://doi.org/10.1109/tcbb.2019.2920912","mag":"2948074652","pmid":"https://pubmed.ncbi.nlm.nih.gov/31180898"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2019.2920912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2019.2920912","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/A5101909744","display_name":"Guimu Guo","orcid":"https://orcid.org/0000-0002-3573-7446"},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guimu Guo","raw_affiliation_strings":["University of Alabama at Birmingham, Birmingham, AL, USA"],"affiliations":[{"raw_affiliation_string":"University of Alabama at Birmingham, Birmingham, AL, USA","institution_ids":["https://openalex.org/I32389192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101653376","display_name":"Hongzhi Chen","orcid":"https://orcid.org/0000-0002-0085-3463"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhi Chen","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070582509","display_name":"Da Yan","orcid":"https://orcid.org/0000-0002-4653-0408"},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Da Yan","raw_affiliation_strings":["University of Alabama at Birmingham, Birmingham, AL, USA"],"affiliations":[{"raw_affiliation_string":"University of Alabama at Birmingham, Birmingham, AL, USA","institution_ids":["https://openalex.org/I32389192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016082884","display_name":"James Cheng","orcid":"https://orcid.org/0000-0001-6313-6288"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"James Cheng","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058469124","display_name":"Jake Y. Chen","orcid":"https://orcid.org/0000-0001-8829-7504"},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jake Y. Chen","raw_affiliation_strings":["Informatics Institute, School of Medicine, University of Alabama at Birmingham, Birmingham, AL, USA"],"affiliations":[{"raw_affiliation_string":"Informatics Institute, School of Medicine, University of Alabama at Birmingham, Birmingham, AL, USA","institution_ids":["https://openalex.org/I32389192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043524225","display_name":"Zechen Chong","orcid":"https://orcid.org/0000-0001-5750-1808"},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zechen Chong","raw_affiliation_strings":["University of Alabama at Birmingham, Birmingham, AL, USA"],"affiliations":[{"raw_affiliation_string":"University of Alabama at Birmingham, Birmingham, AL, USA","institution_ids":["https://openalex.org/I32389192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101909744"],"corresponding_institution_ids":["https://openalex.org/I32389192"],"apc_list":null,"apc_paid":null,"fwci":0.2557,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.55243848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"18","issue":"2","first_page":"731","last_page":"744"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12029","display_name":"DNA and Biological Computing","score":0.9962999820709229,"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/T12029","display_name":"DNA and Biological Computing","score":0.9962999820709229,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9945999979972839,"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":0.9830999970436096,"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/scalability","display_name":"Scalability","score":0.6600035429000854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5692648887634277},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47838178277015686},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.4728803038597107},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4284909963607788},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.41823506355285645},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3484385907649994},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3013869524002075},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.23205751180648804},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.12862429022789001},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.09053495526313782}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6600035429000854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5692648887634277},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47838178277015686},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.4728803038597107},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4284909963607788},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.41823506355285645},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3484385907649994},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3013869524002075},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.23205751180648804},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12862429022789001},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.09053495526313782},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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}],"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":"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},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbb.2019.2920912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2019.2920912","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:31180898","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31180898","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/G4151218855","display_name":null,"funder_award_id":"3U01HG007301-06S1","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G4262330540","display_name":null,"funder_award_id":"U54MD000502","funder_id":"https://openalex.org/F4320337534","funder_display_name":"National Institute on Minority Health and Health Disparities"}],"funders":[{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"},{"id":"https://openalex.org/F4320337534","display_name":"National Institute on Minority Health and Health Disparities","ror":"https://ror.org/0493hgw16"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1448681276","https://openalex.org/W1501254937","https://openalex.org/W1966822396","https://openalex.org/W1969970763","https://openalex.org/W1980606681","https://openalex.org/W1988872142","https://openalex.org/W2004350101","https://openalex.org/W2009119978","https://openalex.org/W2033292629","https://openalex.org/W2060380866","https://openalex.org/W2084734290","https://openalex.org/W2107772251","https://openalex.org/W2115501618","https://openalex.org/W2120902911","https://openalex.org/W2121911035","https://openalex.org/W2127768708","https://openalex.org/W2129933858","https://openalex.org/W2130530163","https://openalex.org/W2131975293","https://openalex.org/W2136651963","https://openalex.org/W2157539385","https://openalex.org/W2160969485","https://openalex.org/W2170616854","https://openalex.org/W2213505663","https://openalex.org/W2214884049","https://openalex.org/W2219156867","https://openalex.org/W2219764230","https://openalex.org/W2232745072","https://openalex.org/W2296407087","https://openalex.org/W2422143336","https://openalex.org/W2888691145","https://openalex.org/W2951415398","https://openalex.org/W2963886609","https://openalex.org/W4289117690","https://openalex.org/W6628546715","https://openalex.org/W6679815717","https://openalex.org/W6757176122"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W4235240664","https://openalex.org/W2965083567","https://openalex.org/W1838576100","https://openalex.org/W2095886385","https://openalex.org/W2889616422","https://openalex.org/W2794386548","https://openalex.org/W4381279187","https://openalex.org/W2013063066","https://openalex.org/W1841715584"],"abstract_inverted_index":{"De":[0],"novo":[1,48],"genome":[2,27,49],"assembly":[3,50],"is":[4,87,115],"the":[5,32,75,120],"process":[6],"of":[7,34],"stitching":[8],"short":[9],"DNA":[10,15],"sequences":[11],"to":[12,68],"generate":[13],"longer":[14],"sequences,":[16],"without":[17],"using":[18],"any":[19],"reference":[20],"sequence":[21],"for":[22,46,82],"alignment.":[23],"It":[24],"enables":[25],"high-throughput":[26],"sequencing":[28,71,125],"and":[29,64,84,109],"thus":[30],"accelerates":[31],"discovery":[33],"new":[35],"genomes.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40],"present":[41],"a":[42,52,90,102],"toolkit,":[43],"called":[44],"PPA-assembler,":[45],"de":[47,77],"in":[51,57,92,101],"distributed":[53],"setting.":[54],"The":[55],"operations":[56],"our":[58],"toolkit":[59],"provide":[60],"strong":[61],"performance":[62],"guarantees,":[63],"can":[65,97],"be":[66,98],"assembled":[67],"implement":[69],"various":[70],"strategies.":[72],"PPA-assembler":[73,114,127],"adopts":[74],"popular":[76],"Bruijn":[78],"graph":[79],"based":[80],"approach":[81],"sequencing,":[83],"each":[85],"operation":[86],"implemented":[88],"as":[89],"program":[91],"Google's":[93],"Pregel":[94],"framework":[95],"which":[96],"easily":[99],"deployed":[100],"generic":[103],"cluster.":[104],"Experiments":[105],"on":[106],"large":[107],"real":[108],"simulated":[110],"datasets":[111],"demonstrate":[112],"that":[113],"much":[116],"more":[117],"efficient":[118],"than":[119],"state-of-the-arts":[121],"while":[122],"providing":[123],"comparable":[124],"quality.":[126],"has":[128],"been":[129],"open-sourced":[130],"at":[131],"https://github.com/yaobaiwei/PPA-Assembler.":[132]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
