{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T02:48:01Z","timestamp":1785379681184,"version":"3.55.0"},"reference-count":17,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T00:00:00Z","timestamp":1667347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["HG002385"],"award-info":[{"award-number":["HG002385"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["HG010169"],"award-info":[{"award-number":["HG010169"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["1F32GM134558"],"award-info":[{"award-number":["1F32GM134558"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000011","name":"Howard Hughes Medical Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000011","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Highly contiguous de novo phased diploid genome assemblies are now feasible for large numbers of species and individuals. Methods are needed to validate assembly accuracy and detect misassemblies with orthologous sequencing data to allow for confident downstream analyses.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We developed GAVISUNK, an open-source pipeline that detects misassemblies and produces a set of reliable regions genome-wide by assessing concordance of distances between unique k-mers in Pacific Biosciences high-fidelity assemblies and raw Oxford Nanopore Technologies reads.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>GAVISUNK is available at https:\/\/github.com\/pdishuck\/GAVISUNK.<\/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\/btac714","type":"journal-article","created":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T11:19:53Z","timestamp":1667387993000},"source":"Crossref","is-referenced-by-count":12,"title":["GAVISUNK: genome assembly validation via inter-SUNK distances in Oxford Nanopore reads"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2223-9787","authenticated-orcid":false,"given":"Philip C","family":"Dishuck","sequence":"first","affiliation":[{"name":"Department of Genome Sciences, University of Washington School of Medicine , Seattle, WA 98195, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Allison N","family":"Rozanski","sequence":"additional","affiliation":[{"name":"Department of Genome Sciences, University of Washington School of Medicine , Seattle, WA 98195, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Glennis A","family":"Logsdon","sequence":"additional","affiliation":[{"name":"Department of Genome Sciences, University of Washington School of Medicine , Seattle, WA 98195, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Porubsky","sequence":"additional","affiliation":[{"name":"Department of Genome Sciences, University of Washington School of Medicine , Seattle, WA 98195, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evan E","family":"Eichler","sequence":"additional","affiliation":[{"name":"Department of Genome Sciences, University of Washington School of Medicine , Seattle, WA 98195, USA"},{"name":"Howard Hughes Medical Institute, University of Washington , Seattle, WA 98195, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,11,2]]},"reference":[{"key":"2023010107520884300_btac714-B1","doi-asserted-by":"crossref","first-page":"9354","DOI":"10.1038\/s41598-019-45839-z","article-title":"The ENCODE blacklist: identification of problematic regions of the genome","volume":"9","author":"Amemiya","year":"2019","journal-title":"Sci. Rep"},{"key":"2023010107520884300_btac714-B2","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1038\/s41592-020-01056-5","article-title":"Haplotype-resolved de novo assembly using phased assembly graphs with hifiasm","volume":"18","author":"Cheng","year":"2021","journal-title":"Nat. Methods"},{"key":"2023010107520884300_btac714-B3","doi-asserted-by":"crossref","first-page":"eabf7117","DOI":"10.1126\/science.abf7117","article-title":"Haplotype-resolved diverse human genomes and integrated analysis of structural variation","volume":"372","author":"Ebert","year":"2021","journal-title":"Science"},{"key":"2023010107520884300_btac714-B4","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1101\/gr.213462.116","article-title":"HapCUT2: robust and accurate haplotype assembly for diverse sequencing technologies","volume":"27","author":"Edge","year":"2017","journal-title":"Genome Res."},{"key":"2023010107520884300_btac714-B5","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"2023010107520884300_btac714-B6","doi-asserted-by":"crossref","first-page":"1362","DOI":"10.1101\/gr.078477.108","article-title":"DupMasker: a tool for annotating primate segmental duplications","volume":"18","author":"Jiang","year":"2008","journal-title":"Genome Res"},{"key":"2023010107520884300_btac714-B7","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":"2023010107520884300_btac714-B8","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1038\/s41576-020-0236-x","article-title":"Long-read human genome sequencing and its applications","volume":"21","author":"Logsdon","year":"2020","journal-title":"Nat. Rev. Genet"},{"key":"2023010107520884300_btac714-B9","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1038\/s41586-021-03420-7","article-title":"The structure, function and evolution of a complete human chromosome 8","volume":"593","author":"Logsdon","year":"2021","journal-title":"Nature"},{"key":"2023010107520884300_btac714-B10","doi-asserted-by":"crossref","first-page":"764","DOI":"10.1093\/bioinformatics\/btr011","article-title":"A fast, lock-free approach for efficient parallel counting of occurrences of k-mers","volume":"27","author":"Mar\u00e7ais","year":"2011","journal-title":"Bioinformatics"},{"key":"2023010107520884300_btac714-B11","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1038\/s41586-020-2547-7","article-title":"Telomere-to-telomere assembly of a complete human X chromosome","volume":"585","author":"Miga","year":"2020","journal-title":"Nature"},{"key":"2023010107520884300_btac714-B12","doi-asserted-by":"crossref","first-page":"i75","DOI":"10.1093\/bioinformatics\/btaa440","article-title":"TandemTools: mapping long reads and assessing\/improving assembly quality in extra-long tandem repeats","volume":"36","author":"Mikheenko","year":"2020","journal-title":"Bioinformatics"},{"key":"2023010107520884300_btac714-B13","doi-asserted-by":"crossref","first-page":"33","DOI":"10.12688\/f1000research.29032.2","article-title":"Sustainable data analysis with snakemake","volume":"10","author":"M\u00f6lder","year":"2021","journal-title":"F1000Res"},{"key":"2023010107520884300_btac714-B14","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1126\/science.abj6987","article-title":"The complete sequence of a human genome","volume":"376","author":"Nurk","year":"2022","journal-title":"Science"},{"key":"2023010107520884300_btac714-B15","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1038\/s41586-021-03451-0","article-title":"Towards complete and error-free genome assemblies of all vertebrate species","volume":"592","author":"Rhie","year":"2021","journal-title":"Nature"},{"key":"2023010107520884300_btac714-B16","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1126\/science.1197005","article-title":"Diversity of human copy number variation and multicopy genes","volume":"330","author":"Sudmant","year":"2010","journal-title":"Science"},{"key":"2023010107520884300_btac714-B17","doi-asserted-by":"crossref","first-page":"eabj6965","DOI":"10.1126\/science.abj6965","article-title":"Segmental duplications and their variation in a complete human genome","volume":"376","author":"Vollger","year":"2022","journal-title":"Science"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac714\/46946714\/btac714.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/1\/btac714\/48448747\/btac714.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/1\/btac714\/48448747\/btac714.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T05:09:09Z","timestamp":1672549749000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btac714\/6793851"}},"subtitle":[],"editor":[{"given":"Pier Luigi","family":"Martelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,11,2]]},"references-count":17,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,11,2]]},"published-print":{"date-parts":[[2023,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac714","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2022.06.17.496619","asserted-by":"object"}]},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,1,1]]},"published":{"date-parts":[[2022,11,2]]},"article-number":"btac714"}}