@article{Gustafson01112024,
author = {Gustafson, Jonas A. and Gibson, Sophia B. and Damaraju, Nikhita and Zalusky, Miranda P.G. and Hoekzema, Kendra and Twesigomwe, David and Yang, Lei and Snead, Anthony A. and Richmond, Phillip A. and De Coster, Wouter and Olson, Nathan D. and Guarracino, Andrea and Li, Qiuhui and Miller, Angela L. and Goffena, Joy and Anderson, Zachary B. and Storz, Sophie H.R. and Ward, Sydney A. and Sinha, Maisha and Gonzaga-Jauregui, Claudia and Clarke, Wayne E. and Basile, Anna O. and Corvelo, André and Reeves, Catherine and Helland, Adrienne and Musunuri, Rajeeva Lochan and Revsine, Mahler and Patterson, Karynne E. and Paschal, Cate R. and Zakarian, Christina and Goodwin, Sara and Jensen, Tanner D. and Robb, Esther and The 1000 Genomes ONT Sequencing Consortium and University of Washington Center for Rare Disease Research (UW-CRDR) and Genomics Research to Elucidate the Genetics of Rare Diseases (GREGoR) Consortium and McCombie, William Richard and Sedlazeck, Fritz J. and Zook, Justin M. and Montgomery, Stephen B. and Garrison, Erik and Kolmogorov, Mikhail and Schatz, Michael C. and McLaughlin, Richard N. and Dashnow, Harriet and Zody, Michael C. and Loose, Matt and Jain, Miten and Eichler, Evan E. and Miller, Danny E.}, 
title = {High-coverage nanopore sequencing of samples from the 1000 Genomes Project to build a comprehensive catalog of human genetic variation},
volume = {34}, 
number = {11}, 
pages = {2061-2073}, 
year = {2024}, 
doi = {10.1101/gr.279273.124}, 
abstract ={Fewer than half of individuals with a suspected Mendelian or monogenic condition receive a precise molecular diagnosis after comprehensive clinical genetic testing. Improvements in data quality and costs have heightened interest in using long-read sequencing (LRS) to streamline clinical genomic testing, but the absence of control data sets for variant filtering and prioritization has made tertiary analysis of LRS data challenging. To address this, the 1000 Genomes Project (1KGP) Oxford Nanopore Technologies Sequencing Consortium aims to generate LRS data from at least 800 of the 1KGP samples. Our goal is to use LRS to identify a broader spectrum of variation so we may improve our understanding of normal patterns of human variation. Here, we present data from analysis of the first 100 samples, representing all 5 superpopulations and 19 subpopulations. These samples, sequenced to an average depth of coverage of 37× and sequence read N50 of 54 kbp, have high concordance with previous studies for identifying single nucleotide and indel variants outside of homopolymer regions. Using multiple structural variant (SV) callers, we identify an average of 24,543 high-confidence SVs per genome, including shared and private SVs likely to disrupt gene function as well as pathogenic expansions within disease-associated repeats that were not detected using short reads. Evaluation of methylation signatures revealed expected patterns at known imprinted loci, samples with skewed X-inactivation patterns, and novel differentially methylated regions. All raw sequencing data, processed data, and summary statistics are publicly available, providing a valuable resource for the clinical genetics community to discover pathogenic SVs.}, 
URL = {http://genome.cshlp.org/content/34/11/2061.abstract}, 
eprint = {http://genome.cshlp.org/content/34/11/2061.full.pdf+html}, 
journal = {Genome Research} 
}