Challenges and directions: an analysis of Genetic Analysis Workshop 17 data by collapsing rare variants within family data

Abstract

Recent studies suggest that the traditional case-control study design does not have sufficient power to discover rare risk variants. Two different methods-collapsing and family data-are suggested as alternatives for discovering these rare variants. Compared with common variants, rare variants have unique characteristics. In this paper, we assess the distribution of rare variants in family data. We notice that a large number of rare variants exist only in one or two families and that the association result is largely shaped by those families. Therefore we explore the possibility of integrating both the collapsing method and the family data method. This combinational approach offers a potential power boost for certain causal genes, including VEGFA, VEGFC, SIRT1, SREBF1, PIK3R3, VLDLR, PLAT, and FLT4, and thus deserves further investigation.

Figure 1

Distribution of rare causal SNPs within families. In the GAW17 data set, 145 of 162 casual SNPs are rare variants. Of these 145 rare variants, 103 do not exist in the family data. Eighty-five percent of the existing rare variants exist in only one or two families. The number above each bar indicates the exact number of rare SNPs in this category. It partly explains why many rare variants cannot be discovered using family data.

Figure 2

Distribution of association signals withinfamilies. Each category indicates the number of families that report an association signal for each SNP. The number above each bar indicates the total number of rare causal SNPs in this category. The distribution of association signals matches well to the distribution of rare SNPs within families. It shows that when all families are analyzed together, the final result is largely shaped by only a few families.