Narrow-sense heritability estimation of complex traits using identity-by-descent information

Abstract

Heritability is a fundamental parameter in genetics. Traditional estimates based on family or twin studies can be biased due to shared environmental or non-additive genetic variance. Alternatively, those based on genotyped or imputed variants typically underestimate narrow-sense heritability contributed by rare or otherwise poorly tagged causal variants. Identical-by-descent (IBD) segments of the genome share all variants between pairs of chromosomes except new mutations that have arisen since the last common ancestor. Therefore, relating phenotypic similarity to degree of IBD sharing among classically unrelated individuals is an appealing approach to estimating the near full additive genetic variance while possibly avoiding biases that can occur when modeling close relatives. We applied an IBD-based approach (GREML-IBD) to estimate heritability in unrelated individuals using phenotypic simulation with thousands of whole-genome sequences across a range of stratification, polygenicity levels, and the minor allele frequencies of causal variants (CVs). In simulations, the IBD-based approach produced unbiased heritability estimates, even when CVs were extremely rare, although precision was low. However, population stratification and non-genetic familial environmental effects shared across generations led to strong biases in IBD-based heritability. We used data on two traits in ~120,000 people from the UK Biobank to demonstrate that, depending on the trait and possible confounding environmental effects, GREML-IBD can be applied to very large genetic datasets to infer the contribution of very rare variants lost using other methods. However, we observed apparent biases in these real data, suggesting that more work may be required to understand and mitigate factors that influence IBD-based heritability estimates.

Fig. 1

Estimates of IBD-based heritability from forward-time simulated phenotypes, with GREML-SC using GRMs computed from the true IBD segments or FISHR2-estimated IBD segments with varying cM length thresholds. Mean and 95% CI shown from 70 replicates. Relatedness cutoff of 0.05 used. Shown are two sets of simulations, with and without non-genetic, vertically inherited shared environmental variance (f²), with either common (MAF > 0.05) or very rare (MAF < 0.0025) causal variants

Fig. 2

GREML-SC using an IBD-GRM. ${\hat{h}}_{IBD}^2$ estimates (mean ± 95% CI from 400 replicates). X axis indicates the IBD-shared haplotype length threshold for the IBD-GRM. Phenotypes with 1000 CVs randomly drawn from the MAF range specified in each panel. Different colors indicate degree of stratification in the sample. Relatedness cutoff of 0.05 used

Fig. 3

GREML-LDMS + IBD model. This model had 13 components, 12 LD and MAF-stratified GRMs using imputed genome-wide variants, and one GRM from IBD-shared haplotypes. Total h² estimates are shown (mean ± 95% CI from 400 replicates). X axis indicates the different IBD-shared haplotype length thresholds for the IBD-GRM. Phenotypes with 1000 CVs randomly drawn from the MAF range specified in each panel. Different colors indicate degree of stratification in the sample. Relatedness cutoff of 0.05 used

Fig. 4

GREML-LDMS + IBD. This model had 13 components, 12 LD and MAF-stratified GRMs using imputed genome-wide variants, and one GRM from IBD-shared haplotypes. Separate h² estimates for each component are given by the symbols (mean ± 95% CI from 400 replicates). Note that the “Imputed LDMS” symbol represents the sum of the imputed LDMS GRM variance estimates. X axis indicates the different IBD-shared haplotype length thresholds for the IBD-GRM. Phenotypes with 1000 CVs randomly drawn from the MAF range specified in each panel. Different colors indicate degree of stratification in the sample. Relatedness cutoff of 0.05 used

Fig. 5

Total heritability estimates for three continuous traits in the UK Biobank. a GREML-IBD, which had a single IBD-GRM. b GREML-LDMS + IBD for two continuous traits in the UK Biobank. This model had 13 components, 12 LD and MAF-stratified GRMs using imputed genome-wide variants, and one GRM from IBD-shared haplotypes. Total h² estimates are shown (±95% CI). X axis indicates the different IBD-shared haplotype length thresholds for the IBD-GRM. Relatedness cutoff of 0.05 used. Dashed lines represent, for comparison, the SNP-based estimates, using either GREML-SC (a) or GREML-LDMS (b). See Supplementary Table 1 for estimates