Genome-wide analyses using UK Biobank data provide insights into the genetic architecture of osteoarthritis

Abstract

Osteoarthritis is a common complex disease imposing a large public-health burden. Here, we performed a genome-wide association study for osteoarthritis, using data across 16.5 million variants from the UK Biobank resource. After performing replication and meta-analysis in up to 30,727 cases and 297,191 controls, we identified nine new osteoarthritis loci, in all of which the most likely causal variant was noncoding. For three loci, we detected association with biologically relevant radiographic endophenotypes, and in five signals we identified genes that were differentially expressed in degraded compared with intact articular cartilage from patients with osteoarthritis. We established causal effects on osteoarthritis for higher body mass index but not for triglyceride levels or genetic predisposition to type 2 diabetes.

Figure 1. Power to detect association in the discovery stage.

Odds ratios (ORs) and 95% confidence intervals as a function of minor allele frequencies (MAF). Newly reported variants are denoted in diamonds, while known variants are denoted in circles. The curves indicate 80% power at the genome-wide significance threshold of P<5.0x10^-8, for the number of cases and controls of each trait at the discovery stage.

Figure 2. Regional association plots for the nine novel osteoarthritis loci.

The y axis represents the negative logarithm (base 10) of the variant P-value and the x axis represents the position on the chromosome, with the name and location of genes and nearest genes shown in the bottom panel. The variant with the lowest P-value in the region after combined discovery and replication is marked by a purple diamond. The same variant is marked by a purple dot showing the discovery P-value. The colours of the other variants indicate their r² with the lead variant.

Figure 3. Heat map of genetic correlations between osteoarthritis phenotypes in UK Biobank and 35 traits grouped in 10 categories from GWAS consortia.

Symbols and hues depict the FDR q-values and strength of the genetic correlation (darker shade denotes stronger correlation), respectively. Red and blue indicate positive and negative correlations, respectively. RP: reproductive; SL: sleep.

Figure 4. Two-sample Mendelian randomization estimates and 95% confidence intervals of the effect of obesity-related measures, triglyceride levels, years of schooling (in standard deviations units) and type 2 diabetes liability (in ln(odds ratio) units) on different definitions of osteoarthritis.

HD: hospital diagnosed. IVW: inverse-variance weighting. MBE: mode-based estimate. MBE (1): tuning parameter φ=1. MBE (0.5): tuning parameter φ=0.5.