@article{Wang01052013,
author = {Wang, Yi and Lu, James and Yu, Jin and Gibbs, Richard A. and Yu, Fuli}, 
title = {An integrative variant analysis pipeline for accurate genotype/haplotype inference in population NGS data},
volume = {23}, 
number = {5}, 
pages = {833-842}, 
year = {2013}, 
doi = {10.1101/gr.146084.112}, 
abstract ={Next-generation sequencing is a powerful approach for discovering genetic variation. Sensitive variant calling and haplotype inference from population sequencing data remain challenging. We describe methods for high-quality discovery, genotyping, and phasing of SNPs for low-coverage (approximately 5×) sequencing of populations, implemented in a pipeline called SNPTools. Our pipeline contains several innovations that specifically address challenges caused by low-coverage population sequencing: (1) effective base depth (EBD), a nonparametric statistic that enables more accurate statistical modeling of sequencing data; (2) variance ratio scoring, a variance-based statistic that discovers polymorphic loci with high sensitivity and specificity; and (3) BAM-specific binomial mixture modeling (BBMM), a clustering algorithm that generates robust genotype likelihoods from heterogeneous sequencing data. Last, we develop an imputation engine that refines raw genotype likelihoods to produce high-quality phased genotypes/haplotypes. Designed for large population studies, SNPTools' input/output (I/O) and storage aware design leads to improved computing performance on large sequencing data sets. We apply SNPTools to the International 1000 Genomes Project (1000G) Phase 1 low-coverage data set and obtain genotyping accuracy comparable to that of SNP microarray.}, 
URL = {http://genome.cshlp.org/content/23/5/833.abstract}, 
eprint = {http://genome.cshlp.org/content/23/5/833.full.pdf+html}, 
journal = {Genome Research} 
}