Discovery of genomic loci associated with sleep apnea risk through multi-trait GWAS analysis with snoring

Abstract

Study objectives: Despite its association with severe health conditions, the etiology of sleep apnea (SA) remains understudied. This study sought to identify genetic variants robustly associated with SA risk.

Methods: We performed a genome-wide association study (GWAS) meta-analysis of SA across five cohorts (NTotal = 523 366), followed by a multi-trait analysis of GWAS (multi-trait analysis of genome-wide association summary statistics [MTAG]) to boost power, leveraging the high genetic correlation between SA and snoring. We then adjusted our results for the genetic effects of body mass index (BMI) using multi-trait-based conditional and joint analysis (mtCOJO) and sought replication of lead hits in a large cohort of participants from 23andMe, Inc (NTotal = 1 477 352; Ncases = 175 522). We also explored genetic correlations with other complex traits and performed a phenome-wide screen for causally associated phenotypes using the latent causal variable method.

Results: Our SA meta-analysis identified five independent variants with evidence of association beyond genome-wide significance. After adjustment for BMI, only one genome-wide significant variant was identified. MTAG analyses uncovered 49 significant independent loci associated with SA risk. Twenty-nine variants were replicated in the 23andMe GWAS adjusting for BMI. We observed genetic correlations with several complex traits, including multisite chronic pain, diabetes, eye disorders, high blood pressure, osteoarthritis, chronic obstructive pulmonary disease, and BMI-associated conditions.

Conclusion: Our study uncovered multiple genetic loci associated with SA risk, thus increasing our understanding of the etiology of this condition and its relationship with other complex traits.

Keywords: GWAS; genetics; sleep apnea; snoring.

Graphical Abstract

Figure 1.

Discovery of genetic associations with sleep apnea (SA) risk. Miami plots depict the meta-analysis results for SA before and after adjusting for BMI using mtCOJO (A) or MTAG for SA plus snoring before and after adjusting for BMI using mtCOJO (B). Each dot represents a genetic variant. The x-axis represents the variant’s genomic position, and the y-axis depicts the significance of the association with SA. In the BMI-adjusted analyses, highlighted variants show the genome-wide hits of the unadjusted GWAS.

Figure 2.

Sleep apnea (SA) is genetically correlated with psychiatric, behavioral, and cardiorespiratory traits. Forest plots showing genetic correlations calculated using CTG-VL [44] between SA meta-analysis, MTAG between SA and snoring (SAmtagSnoring) and MTAG between SA and snoring adjusted for BMI (SAmtagSnoringBMIadj). Markers depict the genetic correlation estimate (r_g), whereas lines represent 95% confidence intervals derived from the r_g standard error. Not all traits with a significant association (FDR < 0.05) are shown. See the Supplementary Data for other traits.

Figure 3.

Sleep apnea (SA) polygenic prediction. (A) Plot showing the odds ratio (OR) per change in polygenic risk score (PRS) decile. Error bars depict the 95% confidence intervals. (B) Example of a receiver operating characteristic (ROC) curve derived from assessing the ability of logistic regression to predict SA using either a base model (covariates only) or the base model plus the PRS of interest. The higher the area under the curve, the higher the model’s predictive power. (C) Average area under ROC curve after 100 iterations of leave out validation randomly assigning training and testing subsamples. Error bars depict the standard deviation of the mean. Full results (100 ROC curves per model) are available in Supplementary Figure 9. Abbreviations: SA, sleep apnea meta-analysis; SAmtagSnoring, sleep apnea plus snoring MTAG.