Meta-analysis of genome-wide scans for total body BMD in children and adults reveals allelic heterogeneity and age-specific effects at the WNT16 locus

Abstract

To identify genetic loci influencing bone accrual, we performed a genome-wide association scan for total-body bone mineral density (TB-BMD) variation in 2,660 children of different ethnicities. We discovered variants in 7q31.31 associated with BMD measurements, with the lowest P = 4.1 × 10(-11) observed for rs917727 with minor allele frequency of 0.37. We sought replication for all SNPs located ± 500 kb from rs917727 in 11,052 additional individuals from five independent studies including children and adults, together with de novo genotyping of rs3801387 (in perfect linkage disequilibrium (LD) with rs917727) in 1,014 mothers of children from the discovery cohort. The top signal mapping in the surroundings of WNT16 was replicated across studies with a meta-analysis P = 2.6 × 10(-31) and an effect size explaining between 0.6%-1.8% of TB-BMD variance. Conditional analyses on this signal revealed a secondary signal for total body BMD (P = 1.42 × 10(-10)) for rs4609139 and mapping to C7orf58. We also examined the genomic region for association with skull BMD to test if the associations were independent of skeletal loading. We identified two signals influencing skull BMD variation, including rs917727 (P = 1.9 × 10(-16)) and rs7801723 (P = 8.9 × 10(-28)), also mapping to C7orf58 (r(2) = 0.50 with rs4609139). Wnt16 knockout (KO) mice with reduced total body BMD and gene expression profiles in human bone biopsies support a role of C7orf58 and WNT16 on the BMD phenotypes observed at the human population level. In summary, we detected two independent signals influencing total body and skull BMD variation in children and adults, thus demonstrating the presence of allelic heterogeneity at the WNT16 locus. One of the skull BMD signals mapping to C7orf58 is mostly driven by children, suggesting temporal determination on peak bone mass acquisition. Our life-course approach postulates that these genetic effects influencing peak bone mass accrual may impact the risk of osteoporosis later in life.

Figure 1. Genome-wide association of TB-BMD in the discovery cohort.

A. Q-Q plot showing the inflation of the test statistics when correction for data structure is not applied (green dots) and the loss of power when no weight correction is applied (red dots) in comparison with the applied model (black dots) and B. Manhattan Plot of the genome wide association analysis of TB-BMD in the Generation R (discovery) cohort of model correcting by age, gender and body weight.

Figure 2. TB-BMD across cohorts and meta-analysis.

A. Mean Total Body BMD in each cohort by gender showing the highest BMD levels in young adults and overall higher levels in male than in female participants. B. Forest plot of the association of TB-BMD and rs917727. Results are reported per copy of the G-allele (MAF = 0.27).

Figure 3. Association plots for TB-BMD.

A. SNP association plot for TB-BMD-associated region of Chromosome 7q31.31. B. SNP association plot for TB-BMD-associated region of Chromosome 7q31.31 after conditioning on rs3801382. Genetic coordinates are as per Hapmap phase II-CEU. *Data from the mothers of Generation R is not included.

Figure 4. Skull-BMD across cohorts and meta-analysis.

A. Gender-specific mean Skull BMD for each cohort. B. Forrest plot of the association of skull BMD with rs7801723. The results are reported per copy of the T-allele (MAF = 0.37).

Figure 5. Association plots for skull-BMD.

SNP association plot for the skull BMD-associated region in chromosome 7q31.31, based on 13,712 individuals from the five different cohorts with GWAS information.