@article{Edge01052017,
author = {Edge, Peter and Bafna, Vineet and Bansal, Vikas}, 
title = {HapCUT2: robust and accurate haplotype assembly for diverse sequencing technologies},
volume = {27}, 
number = {5}, 
pages = {801-812}, 
year = {2017}, 
doi = {10.1101/gr.213462.116}, 
abstract ={Many tools have been developed for haplotype assembly—the reconstruction of individual haplotypes using reads mapped to a reference genome sequence. Due to increasing interest in obtaining haplotype-resolved human genomes, a range of new sequencing protocols and technologies have been developed to enable the reconstruction of whole-genome haplotypes. However, existing computational methods designed to handle specific technologies do not scale well on data from different protocols. We describe a new algorithm, HapCUT2, that extends our previous method (HapCUT) to handle multiple sequencing technologies. Using simulations and whole-genome sequencing (WGS) data from multiple different data types—dilution pool sequencing, linked-read sequencing, single molecule real-time (SMRT) sequencing, and proximity ligation (Hi-C) sequencing—we show that HapCUT2 rapidly assembles haplotypes with best-in-class accuracy for all data types. In particular, HapCUT2 scales well for high sequencing coverage and rapidly assembled haplotypes for two long-read WGS data sets on which other methods struggled. Further, HapCUT2 directly models Hi-C specific error modalities, resulting in significant improvements in error rates compared to HapCUT, the only other method that could assemble haplotypes from Hi-C data. Using HapCUT2, haplotype assembly from a 90× coverage whole-genome Hi-C data set yielded high-resolution haplotypes (78.6% of variants phased in a single block) with high pairwise phasing accuracy (∼98% across chromosomes). Our results demonstrate that HapCUT2 is a robust tool for haplotype assembly applicable to data from diverse sequencing technologies.}, 
URL = {http://genome.cshlp.org/content/27/5/801.abstract}, 
eprint = {http://genome.cshlp.org/content/27/5/801.full.pdf+html}, 
journal = {Genome Research} 
}