{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T11:24:00Z","timestamp":1782905040060,"version":"3.54.5"},"reference-count":18,"publisher":"Oxford University Press (OUP)","issue":"22","license":[{"start":{"date-parts":[[2019,6,20]],"date-time":"2019-06-20T00:00:00Z","timestamp":1560988800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/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\/100000051","name":"National Human Genome Research Institute","doi-asserted-by":"publisher","award":["5U54HG003079"],"award-info":[{"award-number":["5U54HG003079"]}],"id":[{"id":"10.13039\/100000051","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000051","name":"National Human Genome Research Institute","doi-asserted-by":"publisher","award":["1UM1HG008853"],"award-info":[{"award-number":["1UM1HG008853"]}],"id":[{"id":"10.13039\/100000051","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Summary<\/jats:title>\n                    <jats:p>Large-scale human genetics studies are now employing whole genome sequencing with the goal of conducting comprehensive trait mapping analyses of all forms of genome variation. However, methods for structural variation (SV) analysis have lagged far behind those for smaller scale variants, and there is an urgent need to develop more efficient tools that scale to the size of human populations. Here, we present a fast and highly scalable software toolkit (svtools) and cloud-based pipeline for assembling high quality SV maps\u2014including deletions, duplications, mobile element insertions, inversions and other rearrangements\u2014in many thousands of human genomes. We show that this pipeline achieves similar variant detection performance to established per-sample methods (e.g. LUMPY), while providing fast and affordable joint analysis at the scale of \u2265100\u00a0000 genomes. These tools will help enable the next generation of human genetics studies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>svtools is implemented in Python and freely available (MIT) from https:\/\/github.com\/hall-lab\/svtools.<\/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\/btz492","type":"journal-article","created":{"date-parts":[[2019,6,17]],"date-time":"2019-06-17T15:11:28Z","timestamp":1560784288000},"page":"4782-4787","source":"Crossref","is-referenced-by-count":72,"title":["svtools: population-scale analysis of structural variation"],"prefix":"10.1093","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7934-5906","authenticated-orcid":false,"given":"David E","family":"Larson","sequence":"first","affiliation":[{"name":"McDonnell Genome Institute, Washington University School of Medicine, St. Louis, MO 63108, USA"},{"name":"Department of Genetics, Washington University School of Medicine, St. Louis, MO 63110, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haley J","family":"Abel","sequence":"additional","affiliation":[{"name":"McDonnell Genome Institute, Washington University School of Medicine, St. Louis, MO 63108, USA"},{"name":"Department of Genetics, Washington University School of Medicine, St. Louis, MO 63110, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Colby","family":"Chiang","sequence":"additional","affiliation":[{"name":"McDonnell Genome Institute, Washington University School of Medicine, St. Louis, MO 63108, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhijit","family":"Badve","sequence":"additional","affiliation":[{"name":"McDonnell Genome Institute, Washington University School of Medicine, St. Louis, MO 63108, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Indraniel","family":"Das","sequence":"additional","affiliation":[{"name":"McDonnell Genome Institute, Washington University School of Medicine, St. Louis, MO 63108, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James M","family":"Eldred","sequence":"additional","affiliation":[{"name":"McDonnell Genome Institute, Washington University School of Medicine, St. Louis, MO 63108, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryan M","family":"Layer","sequence":"additional","affiliation":[{"name":"Biofrontiers Institute, University of Colorado, Boulder, CO 80309, USA"},{"name":"Department of Computer Science, University of Colorado, Boulder, CO 80309, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ira M","family":"Hall","sequence":"additional","affiliation":[{"name":"McDonnell Genome Institute, Washington University School of Medicine, St. Louis, MO 63108, USA"},{"name":"Department of Genetics, Washington University School of Medicine, St. Louis, MO 63110, USA"},{"name":"Department of Medicine, Washington University School of Medicine, St. Louis, MO 63110, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2019,6,20]]},"reference":[{"key":"2023013108341248000_btz492-B1","author":"Abel","year":"2018"},{"key":"2023013108341248000_btz492-B2","doi-asserted-by":"crossref","first-page":"974","DOI":"10.1101\/gr.114876.110","article-title":"CNVnator: an approach to discover, genotype, and characterize typical and atypical CNVs from family and population genome sequencing","volume":"21","author":"Abyzov","year":"2011","journal-title":"Genome Res"},{"key":"2023013108341248000_btz492-B3","doi-asserted-by":"crossref","first-page":"966","DOI":"10.1038\/nmeth.3505","article-title":"SpeedSeq: ultra-fast personal genome analysis and interpretation","volume":"12","author":"Chiang","year":"2015","journal-title":"Nat. Methods"},{"key":"2023013108341248000_btz492-B4","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1038\/ng.3834","article-title":"The impact of structural variation on human gene expression","volume":"49","author":"Chiang","year":"2017","journal-title":"Nat. Genet"},{"key":"2023013108341248000_btz492-B5","doi-asserted-by":"crossref","first-page":"704","DOI":"10.1038\/nature08516","article-title":"Origins and functional impact of copy number variation in the human genome","volume":"464","author":"Conrad","year":"2009","journal-title":"Nature"},{"key":"2023013108341248000_btz492-B6","doi-asserted-by":"crossref","first-page":"2156","DOI":"10.1093\/bioinformatics\/btr330","article-title":"The variant call format and VCFtools","volume":"27","author":"Danecek","year":"2011","journal-title":"Bioinformatics"},{"key":"2023013108341248000_btz492-B7","doi-asserted-by":"crossref","first-page":"1083","DOI":"10.1093\/bioinformatics\/btw789","article-title":"SVScore: an impact prediction tool for structural variation","volume":"33","author":"Ganel","year":"2017","journal-title":"Bioinformatics"},{"key":"2023013108341248000_btz492-B8","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1038\/ng.768","article-title":"Discovery and genotyping of genome structural polymorphism by sequencing on a population scale","volume":"43","author":"Handsaker","year":"2011","journal-title":"Nat. Genet"},{"key":"2023013108341248000_btz492-B9","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1038\/ng.3200","article-title":"Large multiallelic copy number variations in humans","volume":"47","author":"Handsaker","year":"2015","journal-title":"Nat. Genet"},{"key":"2023013108341248000_btz492-B10","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1101\/gr.114819.110","article-title":"Efficient storage of high throughput DNA sequencing data using reference-based compression","volume":"21","author":"Hsi-Yang Fritz","year":"2011","journal-title":"Genome Res"},{"key":"2023013108341248000_btz492-B11","doi-asserted-by":"crossref","first-page":"R84","DOI":"10.1186\/gb-2014-15-6-r84","article-title":"LUMPY: a probabilistic framework for structural variant discovery","volume":"15","author":"Layer","year":"2014","journal-title":"Genome Biol"},{"key":"2023013108341248000_btz492-B12","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1038\/nature09708","article-title":"Mapping copy number variation by population-scale genome sequencing","volume":"470","author":"Mills","year":"2011","journal-title":"Nature"},{"key":"2023013108341248000_btz492-B13","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1093\/bioinformatics\/btq033","article-title":"BEDTools: a flexible suite of utilities for comparing genomic features","volume":"26","author":"Quinlan","year":"2010","journal-title":"Bioinformatics"},{"key":"2023013108341248000_btz492-B14","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1038\/nature05329","article-title":"Global variation in copy number in the human genome","volume":"444","author":"Redon","year":"2006","journal-title":"Nature"},{"key":"2023013108341248000_btz492-B15","doi-asserted-by":"crossref","first-page":"4038","DOI":"10.1038\/s41467-018-06159-4","article-title":"Functional equivalence of genome sequencing analysis pipelines enables harmonized variant calling across human genetics projects","volume":"9","author":"Regier","year":"2018","journal-title":"Nat. Commun"},{"key":"2023013108341248000_btz492-B16","doi-asserted-by":"crossref","first-page":"aab3761","DOI":"10.1126\/science.aab3761","article-title":"Global diversity, population stratification, and selection of human copy-number variation","volume":"349","author":"Sudmant","year":"2015","journal-title":"Science"},{"key":"2023013108341248000_btz492-B17","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1038\/nature15394","article-title":"An integrated map of structural variation in 2, 504 human genomes","volume":"526","author":"Sudmant","year":"2015","journal-title":"Nature"},{"key":"2023013108341248000_btz492-B18","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1038\/nature08979","article-title":"Genome-wide association study of CNVs in 16, 000 cases of eight common diseases and 3, 000 shared controls","volume":"464","year":"2010","journal-title":"Nature"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btz492\/28914376\/btz492.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/22\/4782\/48977784\/bioinformatics_35_22_4782.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/22\/4782\/48977784\/bioinformatics_35_22_4782.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,17]],"date-time":"2023-09-17T10:24:16Z","timestamp":1694946256000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/35\/22\/4782\/5520944"}},"subtitle":[],"editor":[{"given":"Alfonso","family":"Valencia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2019,6,20]]},"references-count":18,"journal-issue":{"issue":"22","published-print":{"date-parts":[[2019,11,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btz492","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/494203","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,11,15]]},"published":{"date-parts":[[2019,6,20]]}}}