Describing the genetic architecture of epilepsy through heritability analysis

Abstract

Epilepsy is a disease with substantial missing heritability; despite its high genetic component, genetic association studies have had limited success detecting common variants which influence susceptibility. In this paper, we reassess the role of common variants on epilepsy using extensions of heritability analysis. Our data set consists of 1258 UK patients with epilepsy, of which 958 have focal epilepsy, and 5129 population control subjects, with genotypes recorded for over 4 million common single nucleotide polymorphisms. Firstly, we show that on the liability scale, common variants collectively explain at least 26% (standard deviation 5%) of phenotypic variation for all epilepsy and 27% (standard deviation 5%) for focal epilepsy. Secondly we provide a new method for estimating the number of causal variants for complex traits; when applied to epilepsy, our most optimistic estimate suggests that at least 400 variants influence disease susceptibility, with potentially many thousands. Thirdly, we use bivariate analysis to assess how similar the genetic architecture of focal epilepsy is to that of non-focal epilepsy; we demonstrate both significant differences (P = 0.004) and significant similarities (P = 0.01) between the two subtypes, indicating that although the clinical definition of focal epilepsy does identify a genetically distinct epilepsy subtype, there is also scope to improve the classification of epilepsy by incorporating genotypic information. Lastly, we investigate the potential value in using genetic data to diagnose epilepsy following a single epileptic seizure; we find that a prediction model explaining 10% of phenotypic variation could have clinical utility for deciding which single-seizure individuals are likely to benefit from immediate anti-epileptic drug therapy.

Keywords: association studies; complex trait prediction; epilepsy; heritability analysis.

Figure 1

Manhattan plot for single SNP tests of association. Points report -log₁₀ P-values from single-SNP tests of association for the phenotype all epilepsy (1258 cases, 5129 controls). Red/blue points correspond to genotyped SNPs, grey to imputed. The conventional threshold for genome-wide significance (5 × 10⁻⁸) is marked by a horizontal dashed line. Manhattan plots for the phenotypes focal, non-focal and generalized epilepsy are provided in Supplementary Fig. 3.

Figure 2

Estimating the number of causal variants. We suppose heritability is distributed over causal variants either equally (black), uniformly (red), exponentially (green) or χ² (blue). (A) As the number of causal variants increases (x-axis), the average heritability of each variant decreases, and the probability of single-SNP analysis finding no significant associations increases (y-axis). For each distribution, our point estimates (lower bounds) for the number of causal variants are the numbers required for this probability to exceed 0.5 (0.05), and are marked by vertical lines. Based on the point estimates, the histograms in B show for each distribution how much heritability each causal variant explains. The values above bars report the proportion of variance explained by causal variants within each tranche.

Figure 3

Performance of prediction models for single-seizure patients. A and B illustrate the two extreme cases for the distribution of liabilities for single-seizure individuals who do not have epilepsy. In the ‘Best Case Scenario,’ their liability distribution matches that of population controls, while in the ‘Worst Case Scenario,’ their liabilities lie just below the case/control threshold. C and D show, again for the Best and Worst Case Scenarios, how the receiver operating curve depends on the proportion of variance explained by the prediction model (varied between 5% and 30%, indicated by line colour); the AUC (area under receiver operating curve) for each line is provided in parentheses.