Association score testing for rare variants and binary traits in family data with shared controls

Abstract

Genome-wide association studies have been an important approach used to localize trait loci, with primary focus on common variants. The multiple rare variant-common disease hypothesis may explain the missing heritability remaining after accounting for identified common variants. Advances of sequencing technologies with their decreasing costs, coupled with methodological advances in the context of association studies in large samples, now make the study of rare variants at a genome-wide scale feasible. The resurgence of family-based association designs because of their advantage in studying rare variants has also stimulated more methods development, mainly based on linear mixed models (LMMs). Other tests such as score tests can have advantages over the LMMs, but to date have mainly been proposed for single-marker association tests. In this article, we extend several score tests (χcorrected2, WQLS, and SKAT) to the multiple variant association framework. We evaluate and compare their statistical performances relative with the LMM. Moreover, we show that three tests can be cast as the difference between marker allele frequencies (AFs) estimated in each of the group of affected and unaffected subjects. We show that these tests are flexible, as they can be based on related, unrelated or both related and unrelated subjects. They also make feasible an increasingly common design that only sequences a subset of affected subjects (related or unrelated) and uses for comparison publicly available AFs estimated in a group of healthy subjects. Finally, we show the great impact of linkage disequilibrium on the performance of all these tests.

Figure 1

Comparison between tests’ P-values (represented as −log₁₀ P) in the 100 affected related subjects, LowLD scenario and nonassociated SNPs (20 SNPs) included in the test. Top left: W_QLS versus W_corrected in Cor1 scenario; top right: W_QLS versus LMM in Cor1 scenario; bottom left: W_QLS versus LMM in Cor2; bottom right: W_QLS versus LMM in Cor3.

Figure 2

Power of W_corrected, W_QLS, LMM and SKAT in the scenario of 100 related affected subjects under: (A) LowLD, (B) HighLD patterns. Power was estimated using α = 0.01. Mix0: all SNPs have positive direction of effects. Mix30: 30% of the SNPs have positive direction of effects. A: number of associated SNPs. U: number of nonassociated SNPs.

Figure 3

Power of W_QLS in the scenario of 100 affected (related: dark grey; unrelated: light grey) subjects under LowLD patterns. Power was estimated using α = 0.01.