An integration of genome-wide association study and gene expression profiling to prioritize the discovery of novel susceptibility Loci for osteoporosis-related traits

Abstract

Osteoporosis is a complex disorder and commonly leads to fractures in elderly persons. Genome-wide association studies (GWAS) have become an unbiased approach to identify variations in the genome that potentially affect health. However, the genetic variants identified so far only explain a small proportion of the heritability for complex traits. Due to the modest genetic effect size and inadequate power, true association signals may not be revealed based on a stringent genome-wide significance threshold. Here, we take advantage of SNP and transcript arrays and integrate GWAS and expression signature profiling relevant to the skeletal system in cellular and animal models to prioritize the discovery of novel candidate genes for osteoporosis-related traits, including bone mineral density (BMD) at the lumbar spine (LS) and femoral neck (FN), as well as geometric indices of the hip (femoral neck-shaft angle, NSA; femoral neck length, NL; and narrow-neck width, NW). A two-stage meta-analysis of GWAS from 7,633 Caucasian women and 3,657 men, revealed three novel loci associated with osteoporosis-related traits, including chromosome 1p13.2 (RAP1A, p = 3.6x10(-8)), 2q11.2 (TBC1D8), and 18q11.2 (OSBPL1A), and confirmed a previously reported region near TNFRSF11B/OPG gene. We also prioritized 16 suggestive genome-wide significant candidate genes based on their potential involvement in skeletal metabolism. Among them, 3 candidate genes were associated with BMD in women. Notably, 2 out of these 3 genes (GPR177, p = 2.6x10(-13); SOX6, p = 6.4x10(-10)) associated with BMD in women have been successfully replicated in a large-scale meta-analysis of BMD, but none of the non-prioritized candidates (associated with BMD) did. Our results support the concept of our prioritization strategy. In the absence of direct biological support for identified genes, we highlighted the efficiency of subsequent functional characterization using publicly available expression profiling relevant to the skeletal system in cellular or whole animal models to prioritize candidate genes for further functional validation.

Figure 1. Study design.

A four-stage approach was applied. We first performed genome-wide association analyses of the BMD and hip geometry traits in the Framingham Osteoporosis Study as a discovery stage (I) and replicated the top findings by meta-analysis (II), with a subsequent assessment of the functional relevance of the replicated findings (III and IV).

Figure 2. Quantile-Quantile plots for BMD and HSA in additive genetic models.

The distributions of observed p-values did not deviate from the null distribution, which rules out systematic bias due to bad genotyping or population substructure in our study samples.

Figure 3. Hip geometry indices.

Red arrows indicate three hip geometry indices in a typical DXA image of the right hip. NL: Femoral neck length (cm); NW: Narrow neck width (cm); and NSA: Neck-shaft angle.