@article{Dolzhenko01112017,
author = {Dolzhenko, Egor and van Vugt, Joke J.F.A. and Shaw, Richard J. and Bekritsky, Mitchell A. and van Blitterswijk, Marka and Narzisi, Giuseppe and Ajay, Subramanian S. and Rajan, Vani and Lajoie, Bryan R. and Johnson, Nathan H. and Kingsbury, Zoya and Humphray, Sean J. and Schellevis, Raymond D. and Brands, William J. and Baker, Matt and Rademakers, Rosa and Kooyman, Maarten and Tazelaar, Gijs H.P. and van Es, Michael A. and McLaughlin, Russell and Sproviero, William and Shatunov, Aleksey and Jones, Ashley and Al Khleifat, Ahmad and Pittman, Alan and Morgan, Sarah and Hardiman, Orla and Al-Chalabi, Ammar and Shaw, Chris and Smith, Bradley and Neo, Edmund J. and Morrison, Karen and Shaw, Pamela J. and Reeves, Catherine and Winterkorn, Lara and Wexler, Nancy S. and The US–Venezuela Collaborative Research Group and Housman, David E. and Ng, Christopher W. and Li, Alina L. and Taft, Ryan J. and van den Berg, Leonard H. and Bentley, David R. and Veldink, Jan H. and Eberle, Michael A.}, 
title = {Detection of long repeat expansions from PCR-free whole-genome sequence data},
volume = {27}, 
number = {11}, 
pages = {1895-1903}, 
year = {2017}, 
doi = {10.1101/gr.225672.117}, 
abstract ={Identifying large expansions of short tandem repeats (STRs), such as those that cause amyotrophic lateral sclerosis (ALS) and fragile X syndrome, is challenging for short-read whole-genome sequencing (WGS) data. A solution to this problem is an important step toward integrating WGS into precision medicine. We developed a software tool called ExpansionHunter that, using PCR-free WGS short-read data, can genotype repeats at the locus of interest, even if the expanded repeat is larger than the read length. We applied our algorithm to WGS data from 3001 ALS patients who have been tested for the presence of the C9orf72 repeat expansion with repeat-primed PCR (RP-PCR). Compared against this truth data, ExpansionHunter correctly classified all (212/212, 95% CI [0.98, 1.00]) of the expanded samples as either expansions (208) or potential expansions (4). Additionally, 99.9% (2786/2789, 95% CI [0.997, 1.00]) of the wild-type samples were correctly classified as wild type by this method with the remaining three samples identified as possible expansions. We further applied our algorithm to a set of 152 samples in which every sample had one of eight different pathogenic repeat expansions, including those associated with fragile X syndrome, Friedreich's ataxia, and Huntington's disease, and correctly flagged all but one of the known repeat expansions. Thus, ExpansionHunter can be used to accurately detect known pathogenic repeat expansions and provides researchers with a tool that can be used to identify new pathogenic repeat expansions.}, 
URL = {http://genome.cshlp.org/content/27/11/1895.abstract}, 
eprint = {http://genome.cshlp.org/content/27/11/1895.full.pdf+html}, 
journal = {Genome Research} 
}