Genome-wide association study of habitual physical activity in over 377,000 UK Biobank participants identifies multiple variants including CADM2 and APOE

Abstract

Background/objectives: Physical activity (PA) protects against a wide range of diseases. Habitual PA appears to be heritable, motivating the search for specific genetic variants that may inform efforts to promote PA and target the best type of PA for each individual.

Subjects/methods: We used data from the UK Biobank to perform the largest genome-wide association study of PA to date, using three measures based on self-report (n_max = 377,234) and two measures based on wrist-worn accelerometry data (n_max = 91,084). We examined genetic correlations of PA with other traits and diseases, as well as tissue-specific gene expression patterns. With data from the Atherosclerosis Risk in Communities (ARIC; n = 8,556) study, we performed a meta-analysis of our top hits for moderate-to-vigorous PA (MVPA).

Results: We identified ten loci across all PA measures that were significant in both a basic and a fully adjusted model (p < 5 × 10^-9). Upon meta-analysis of the nine top hits for MVPA with results from ARIC, eight were genome-wide significant. Interestingly, among these, the rs429358 variant in the APOE gene was the most strongly associated with MVPA, whereby the allele associated with higher Alzheimer's risk was associated with greater MVPA. However, we were not able to rule out possible selection bias underlying this result. Variants in CADM2, a gene previously implicated in obesity, risk-taking behavior and other traits, were found to be associated with habitual PA. We also identified three loci consistently associated (p < 5 × 10^-5) with PA across both self-report and accelerometry, including CADM2. We found genetic correlations of PA with educational attainment, chronotype, psychiatric traits, and obesity-related traits. Tissue enrichment analyses implicate the brain and pituitary gland as locations where PA-associated loci may exert their actions.

Conclusions: These results provide new insight into the genetic basis of habitual PA, and the genetic links connecting PA with other traits and diseases.

Figure 1

Manhattan plot of GWAS for self-reported MVPA and VPA, strenuous sports or other exercises (abbreviated as SS or Other Exer.), and for accelerometer-based average accelerations and fraction of accelerations > 425 mg. Negative log10-transformed p-value for each SNP is plotted by chromosome and position (x-axis). The red horizontal line represents the threshold for genome-wide significant associations (p<5 × 10⁻⁹).

Figure 2

Genetic correlation of self-reported PA variables with other traits and diseases across the three statistical models employed. Traits/diseases shown are those that are in the top 10 of genetically correlated traits/diseases (according to p-value) for at least one of the 3 models. Traits/diseases are ordered from top to bottom in order of increasing p-value for Model 1. Horizontal position of bars corresponds to the genetic correlation (r_g) between PA and the respective trait/disease. Error bars represent 95% confidence intervals for r_g estimates. Bright green bars represent traits that showed a correlation with p-value <2.5 × 10⁻⁴, and light green bars represent traits with genetic correlation p<0.05. We excluded highly redundant traits (e.g. obesity, overweight) after leaving higher ranked one in.

Figure 3

Genetic correlation of accelerometry-based PA variables with other traits and diseases across the three statistical models employed. Traits/diseases shown are those that are in the top 10 of genetically correlated traits/diseases (according to p-value) for at least one of the 3 models. Traits/diseases are ordered from top to bottom in order of increasing p-value for Model 1. Horizontal position of bars corresponds to the genetic correlation (r_g) between PA and the respective trait/disease. Error bars represent 95% confidence intervals for r_g estimates. Bright green bars represent traits that showed a correlation with p-value <2.5 × 10⁻⁴, and light green bars represent traits with genetic correlation p<0.05. We excluded highly redundant traits (e.g. obesity, overweight) after leaving higher ranked one in.

Figure 4

Results of gene-based enrichment analysis for 30 general tissue types for PA-associated loci. Dashed line represents the Bonferroni-corrected significance threshold.