{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T05:17:49Z","timestamp":1786079869069,"version":"3.56.0"},"reference-count":51,"publisher":"Oxford University Press (OUP)","issue":"13","license":[{"start":{"date-parts":[[2018,6,27]],"date-time":"2018-06-27T00:00:00Z","timestamp":1530057600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["5U41HG007234"],"award-info":[{"award-number":["5U41HG007234"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000888","name":"W. M. Keck Foundation","doi-asserted-by":"publisher","award":["DT06172015"],"award-info":[{"award-number":["DT06172015"]}],"id":[{"id":"10.13039\/100000888","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000893","name":"Simons Foundation","doi-asserted-by":"publisher","award":["SFLIFE# 35190"],"award-info":[{"award-number":["SFLIFE# 35190"]}],"id":[{"id":"10.13039\/100000893","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004440","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["WT206194"],"award-info":[{"award-number":["WT206194"]}],"id":[{"id":"10.13039\/100004440","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Constructing high-quality haplotype-resolved de novo assemblies of diploid genomes is important for revealing the full extent of structural variation and its role in health and disease. Current assembly approaches often collapse the two sequences into one haploid consensus sequence and, therefore, fail to capture the diploid nature of the organism under study. Thus, building an assembler capable of producing accurate and complete diploid assemblies, while being resource-efficient with respect to sequencing costs, is a key challenge to be addressed by the bioinformatics community.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We present a novel graph-based approach to diploid assembly, which combines accurate Illumina data and long-read Pacific Biosciences (PacBio) data. We demonstrate the effectiveness of our method on a pseudo-diploid yeast genome and show that we require as little as 50\u00d7 coverage Illumina data and 10\u00d7 PacBio data to generate accurate and complete assemblies. Additionally, we show that our approach has the ability to detect and phase structural variants.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>https:\/\/github.com\/whatshap\/whatshap<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/bty279","type":"journal-article","created":{"date-parts":[[2018,4,16]],"date-time":"2018-04-16T19:11:48Z","timestamp":1523905908000},"page":"i105-i114","source":"Crossref","is-referenced-by-count":69,"title":["A graph-based approach to diploid genome assembly"],"prefix":"10.1093","volume":"34","author":[{"given":"Shilpa","family":"Garg","sequence":"first","affiliation":[{"name":"Center for Bioinformatics, Saarland University, Saarland Informatics Campus E2.1, Saarbr\u00fccken, Germany"},{"name":"Department of Computational Biology & Applied Algorithmics, Max Planck Institute for Informatics, Saarland Informatics Campus E1.4, Saarbr\u00fccken, Germany"},{"name":"Saarbr\u00fccken Graduate School of Computer Science, Saarland University, Saarbr\u00fccken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mikko","family":"Rautiainen","sequence":"additional","affiliation":[{"name":"Center for Bioinformatics, Saarland University, Saarland Informatics Campus E2.1, Saarbr\u00fccken, Germany"},{"name":"Department of Computational Biology & Applied Algorithmics, Max Planck Institute for Informatics, Saarland Informatics Campus E1.4, Saarbr\u00fccken, Germany"},{"name":"Saarbr\u00fccken Graduate School of Computer Science, Saarland University, Saarbr\u00fccken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam M","family":"Novak","sequence":"additional","affiliation":[{"name":"UC Santa Cruz Genomics Institute, University of California, Santa Cruz, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik","family":"Garrison","sequence":"additional","affiliation":[{"name":"Wellcome Trust Sanger Institute, Hinxton, Cambridge, UK"},{"name":"Department of Genetics, University of Cambridge, Cambridge, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard","family":"Durbin","sequence":"additional","affiliation":[{"name":"Wellcome Trust Sanger Institute, Hinxton, Cambridge, UK"},{"name":"Department of Genetics, University of Cambridge, Cambridge, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Marschall","sequence":"additional","affiliation":[{"name":"Center for Bioinformatics, Saarland University, Saarland Informatics Campus E2.1, Saarbr\u00fccken, Germany"},{"name":"Department of Computational Biology & Applied Algorithmics, Max Planck Institute for Informatics, Saarland Informatics Campus E1.4, Saarbr\u00fccken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2018,6,27]]},"reference":[{"key":"2023051604211141100_bty279-B1","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.1093\/bioinformatics\/btv688","article-title":"hybridspades: an algorithm for hybrid assembly of short and long reads","volume":"32","author":"Antipov","year":"2016","journal-title":"Bioinformatics"},{"key":"2023051604211141100_bty279-B2","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1089\/cmb.2012.0021","article-title":"Spades: a new genome assembly algorithm and its applications to single-cell sequencing","volume":"19","author":"Bankevich","year":"2012","journal-title":"J. Comput. Biol"},{"key":"2023051604211141100_bty279-B3","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1038\/nbt.2288","article-title":"A hybrid approach for the automated finishing of bacterial genomes","volume":"30","author":"Bashir","year":"2012","journal-title":"Nat. Biotechnol"},{"key":"2023051604211141100_bty279-B4","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1038\/nbt.3238","article-title":"Assembling large genomes with single-molecule sequencing and locality-sensitive hashing","volume":"33","author":"Berlin","year":"2015","journal-title":"Nat. Biotechnol"},{"key":"2023051604211141100_bty279-B5","doi-asserted-by":"crossref","first-page":"1119","DOI":"10.1038\/nbt.2727","article-title":"Chromosome-scale scaffolding of de novo genome assemblies based on chromatin interactions","volume":"31","author":"Burton","year":"2013","journal-title":"Nat. Biotechnol"},{"key":"2023051604211141100_bty279-B6","author":"Chaisson","year":"2017"},{"key":"2023051604211141100_bty279-B7","author":"Chaisson","year":"2017"},{"key":"2023051604211141100_bty279-B8","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1038\/nmeth.2474","article-title":"Nonhybrid, finished microbial genome assemblies from long-read smrt sequencing data","volume":"10","author":"Chin","year":"2013","journal-title":"Nat. Methods"},{"key":"2023051604211141100_bty279-B9","doi-asserted-by":"crossref","first-page":"1050.","DOI":"10.1038\/nmeth.4035","article-title":"Phased diploid genome assembly with single molecule real-time sequencing","volume":"13","author":"Chin","year":"2016","journal-title":"Nat. Methods"},{"key":"2023051604211141100_bty279-B10","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1007\/s00453-007-0029-z","article-title":"The complexity of the single individual snp haplotyping problem","volume":"49","author":"Cilibrasi","year":"2007","journal-title":"Algorithmica"},{"key":"2023051604211141100_bty279-B11","author":"Garrison","year":"2017"},{"key":"2023051604211141100_bty279-B12","doi-asserted-by":"crossref","first-page":"3935","DOI":"10.1038\/s41598-017-03996-z","article-title":"De novo yeast genome assemblies from minion, pacbio and miseq platforms","volume":"7","author":"Giordano","year":"2017","journal-title":"Sci. Rep"},{"key":"2023051604211141100_bty279-B13","doi-asserted-by":"crossref","first-page":"73.","DOI":"10.1186\/s13073-014-0073-7","article-title":"Whole-genome haplotyping approaches and genomic medicine","volume":"6","author":"Glusman","year":"2014","journal-title":"Genome Med"},{"key":"2023051604211141100_bty279-B14","doi-asserted-by":"crossref","first-page":"294.","DOI":"10.1186\/s13059-015-0849-0","article-title":"Circlator: automated circularization of genome assemblies using long sequencing reads","volume":"16","author":"Hunt","year":"2015","journal-title":"Genome Biol"},{"key":"2023051604211141100_bty279-B15","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1089\/cmb.1995.2.291","article-title":"A new algorithm for dna sequence assembly","volume":"2","author":"Idury","year":"1995","journal-title":"J. Comput. Biol"},{"key":"2023051604211141100_bty279-B16","doi-asserted-by":"crossref","first-page":"1384","DOI":"10.1101\/gr.170720.113","article-title":"Efficient de novo assembly of highly heterozygous genomes from whole-genome shotgun short reads","volume":"24","author":"Kajitani","year":"2014","journal-title":"Genome Res"},{"key":"2023051604211141100_bty279-B17","author":"Klau","year":"2017"},{"key":"2023051604211141100_bty279-B18","doi-asserted-by":"crossref","first-page":"722","DOI":"10.1101\/gr.215087.116","article-title":"Canu: scalable and accurate long-read assembly via adaptive k-mer weighting and repeat separation","volume":"27","author":"Koren","year":"2017","journal-title":"Genome Res"},{"key":"2023051604211141100_bty279-B19","author":"Lancia","year":"2001"},{"key":"2023051604211141100_bty279-B20","doi-asserted-by":"crossref","first-page":"e254.","DOI":"10.1371\/journal.pbio.0050254","article-title":"The diploid genome sequence of an individual human","volume":"5","author":"Levy","year":"2007","journal-title":"PLoS Biol"},{"key":"2023051604211141100_bty279-B21","doi-asserted-by":"crossref","first-page":"2885","DOI":"10.1093\/bioinformatics\/btv290","article-title":"Bfc: correcting illumina sequencing errors","volume":"31","author":"Li","year":"2015","journal-title":"Bioinformatics"},{"key":"2023051604211141100_bty279-B22","doi-asserted-by":"crossref","first-page":"3694","DOI":"10.1093\/bioinformatics\/btv440","article-title":"Fermikit: assembly-based variant calling for illumina resequencing data","volume":"31","author":"Li","year":"2015","journal-title":"Bioinformatics"},{"key":"2023051604211141100_bty279-B23","doi-asserted-by":"crossref","first-page":"E8396","DOI":"10.1073\/pnas.1604560113","article-title":"Assembly of long error-prone reads using de bruijn graphs","volume":"113","author":"Lin","year":"2016","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051604211141100_bty279-B24","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1093\/bib\/3.1.23","article-title":"Algorithmic strategies for the single nucleotide polymorphism haplotype assembly problem","volume":"3","author":"Lippert","year":"2002","journal-title":"Brief. Bioinform"},{"key":"2023051604211141100_bty279-B25","article-title":"WhatsHap: fast and accurate read-based phasing","author":"Martin","year":"2016","journal-title":"bioRxiv"},{"key":"2023051604211141100_bty279-B26","first-page":"289","volume-title":"WABI, Vol. 4645","author":"Medvedev","year":"2007"},{"key":"2023051604211141100_bty279-B27","doi-asserted-by":"crossref","first-page":"587.","DOI":"10.1038\/nmeth.3865","article-title":"A hybrid approach for de novo human genome sequence assembly and phasing","volume":"13","author":"Mostovoy","year":"2016","journal-title":"Nat. Methods"},{"key":"2023051604211141100_bty279-B28","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1089\/cmb.1995.2.275","article-title":"Toward simplifying and accurately formulating fragment assembly","volume":"2","author":"Myers","year":"1995","journal-title":"J. Comput. Biol"},{"key":"2023051604211141100_bty279-B29","doi-asserted-by":"crossref","first-page":"ii79","DOI":"10.1093\/bioinformatics\/bti1114","article-title":"The fragment assembly string graph","volume":"21","author":"Myers","year":"2005","journal-title":"Bioinformatics"},{"key":"2023051604211141100_bty279-B30","doi-asserted-by":"crossref","first-page":"897","DOI":"10.1089\/cmb.2009.0005","article-title":"Parametric complexity of sequence assembly: theory and applications to next generation sequencing","volume":"16","author":"Nagarajan","year":"2009","journal-title":"J. Comput. Biol"},{"key":"2023051604211141100_bty279-B31","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1038\/nrg3367","article-title":"Sequence assembly demystified","volume":"14","author":"Nagarajan","year":"2013","journal-title":"Nat. Rev. Genet"},{"key":"2023051604211141100_bty279-B32","author":"Paten","year":"2017"},{"key":"2023051604211141100_bty279-B33","author":"Patterson","year":"2014"},{"key":"2023051604211141100_bty279-B34","doi-asserted-by":"crossref","first-page":"780","DOI":"10.1038\/nmeth.3454","article-title":"Assembly and diploid architecture of an individual human genome via single-molecule technologies","volume":"12","author":"Pendleton","year":"2015","journal-title":"Nat. Methods"},{"key":"2023051604211141100_bty279-B35","doi-asserted-by":"crossref","first-page":"9748","DOI":"10.1073\/pnas.171285098","article-title":"An eulerian path approach to dna fragment assembly","volume":"98","author":"Pevzner","year":"2001","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051604211141100_bty279-B36","doi-asserted-by":"crossref","first-page":"1565","DOI":"10.1101\/gr.209841.116","article-title":"Direct chromosome-length haplotyping by single-cell sequencing","volume":"26","author":"Porubsk\u00fd","year":"2016","journal-title":"Genome Res"},{"key":"2023051604211141100_bty279-B37","doi-asserted-by":"crossref","first-page":"1293.","DOI":"10.1038\/s41467-017-01389-4","article-title":"Dense and accurate whole-chromosome haplotyping of individual genomes","volume":"8","author":"Porubsky","year":"2017","journal-title":"Nat. Commun"},{"key":"2023051604211141100_bty279-B38","doi-asserted-by":"crossref","first-page":"e113","DOI":"10.1093\/nar\/gkw294","article-title":"Redundans: an assembly pipeline for highly heterozygous genomes","volume":"44","author":"Pryszcz","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023051604211141100_bty279-B39","author":"Rautiainen","year":"2017"},{"key":"2023051604211141100_bty279-B40","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s13258-015-0342-x","article-title":"Survey of computational haplotype determination methods for single individual","volume":"38","author":"Rhee","year":"2016","journal-title":"Genes Genomics"},{"key":"2023051604211141100_bty279-B41","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1038\/nature20098","article-title":"De novo assembly and phasing of a korean human genome","volume":"538","author":"Seo","year":"2016","journal-title":"Nature"},{"key":"2023051604211141100_bty279-B42","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1101\/gr.126953.111","article-title":"Efficient de novo assembly of large genomes using compressed data structures","volume":"22","author":"Simpson","year":"2012","journal-title":"Genome Res"},{"key":"2023051604211141100_bty279-B43","author":"Sovi\u0107","year":"2013"},{"key":"2023051604211141100_bty279-B44","doi-asserted-by":"crossref","first-page":"215.","DOI":"10.1038\/nrg2950","article-title":"The importance of phase information for human genomics","volume":"12","author":"Tewhey","year":"2011","journal-title":"Nat. Rev. Genet"},{"key":"2023051604211141100_bty279-B45","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1101\/gr.214270.116","article-title":"Fast and accurate de novo genome assembly from long uncorrected reads","volume":"27","author":"Vaser","year":"2017","journal-title":"Genome Res"},{"key":"2023051604211141100_bty279-B46","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1101\/gr.3722605","article-title":"Assembly of polymorphic genomes: algorithms and application to ciona savignyi","volume":"15","author":"Vinson","year":"2005","journal-title":"Genome Res"},{"key":"2023051604211141100_bty279-B47","doi-asserted-by":"crossref","first-page":"e112963.","DOI":"10.1371\/journal.pone.0112963","article-title":"Pilon: an integrated tool for comprehensive microbial variant detection and genome assembly improvement","volume":"9","author":"Walker","year":"2014","journal-title":"PLoS One"},{"key":"2023051604211141100_bty279-B48","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1101\/gr.214874.116","article-title":"Direct determination of diploid genome sequences","volume":"27","author":"Weisenfeld","year":"2017","journal-title":"Genome Res"},{"key":"2023051604211141100_bty279-B49","doi-asserted-by":"crossref","first-page":"1072","DOI":"10.1038\/nmeth.4432","article-title":"MECAT: an ultra-fast mapping, error correction and de novo assembly tool for single-molecule sequencing reads","volume":"14","author":"Xiao","year":"2016","journal-title":"Nat. Methods"},{"key":"2023051604211141100_bty279-B50","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1038\/ng.3847","article-title":"Contrasting evolutionary genome dynamics between domesticated and wild yeasts","volume":"49","author":"Yue","year":"2017","journal-title":"Nat. Genet"},{"key":"2023051604211141100_bty279-B51","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1101\/gr.213405.116","article-title":"Hybrid assembly of the large and highly repetitive genome of aegilops tauschii, a progenitor of bread wheat, with the masurca mega-reads algorithm","volume":"27","author":"Zimin","year":"2017","journal-title":"Genome Res"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/13\/i105\/50315968\/bioinformatics_34_13_i105.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/13\/i105\/50315968\/bioinformatics_34_13_i105.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T04:22:39Z","timestamp":1684210959000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/34\/13\/i105\/5045759"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,27]]},"references-count":51,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2018,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty279","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,7,1]]},"published":{"date-parts":[[2018,6,27]]}}}