Heritability Estimation of Cognitive Phenotypes in the ABCD Study® Using Mixed Models

Abstract

Twin and family studies have historically aimed to partition phenotypic variance into components corresponding to additive genetic effects (A), common environment (C), and unique environment (E). Here we present the ACE Model and several extensions in the Adolescent Brain Cognitive Development℠ Study (ABCD Study^®), employed using the new Fast Efficient Mixed Effects Analysis (FEMA) package. In the twin sub-sample (n = 924; 462 twin pairs), heritability estimates were similar to those reported by prior studies for height (twin heritability = 0.86) and cognition (twin heritability between 0.00 and 0.61), respectively. Incorporating SNP-derived genetic relatedness and using the full ABCD Study^® sample (n = 9,742) led to narrower confidence intervals for all parameter estimates. By leveraging the sparse clustering method used by FEMA to handle genetic relatedness only for participants within families, we were able to take advantage of the diverse distribution of genetic relatedness within the ABCD Study^® sample.

Keywords: Cognition; Height; Heritability; Mixed models; Random effects; Twin studies.

Fig. 1

ACE Model (Model 1) in FEMA versus OpenMx, twin sub-sample at baseline. (A) Comparison of model estimates. Horizontal error bars represent confidence interval calculated in FEMA; vertical error bars represent confidence intervals calculated in OpenMx. (B) Difference in Akaike Information Criterion in FEMA versus in OpenMx. (C) Random effects estimates from FEMA.

Fig. 2

ACE Model using kinship-derived (Model 1) versus SNP-derived GRM (Model 2), twin sub-sample at baseline. (A) Comparison of model estimates. Horizontal error bars represent confidence interval calculated in Model 2; vertical error bars represent confidence intervals calculated in Model 1. (B) Difference in Akaike Information Criterion in Model 2 versus in Model 1. (C) Random effects estimates from Model 2.

Fig. 3

ACE Model using full sample (Model 3) compared to twin sub-sample (Model 2) at baseline. (A) Comparison of model estimates. Horizontal error bars represent confidence interval calculated in Model 3; vertical error bars represent confidence intervals calculated in Model 2. (B) Difference in total residual variance in Model 3 versus in Model 2. (C) Random effects estimates from Model 3.

Fig. 4

ACE and ACSE Model in full sample, baseline only (Model 3) versus baseline + year 2 (Models 5 and 6). (A) Comparison of estimates from Model 5 versus Model 3. Horizontal error bars represent confidence interval calculated in Model 5; vertical error bars represent confidence intervals calculated in Model 3. (B) Difference in total residual variance in Model 5 versus in Model 3. (C) Random effects estimates from Model 5. (D) Comparison of estimates from Model 6 versus Model 5. Horizontal error bars represent confidence interval calculated in Model 6; vertical error bars represent confidence intervals calculated in Model 5. (E) Difference in Akaike Information Criterion in Model 6 versus in Model 5. (F) Random effects estimates from Model 6.

Fig. 5

ACSE model using SNP-derived (Model 6) versus kinship-derived genetic relatedness (Model 9), full sample, baseline + year 2. (A) Comparison of estimates from Model 9 versus Model 6. Horizontal error bars represent confidence interval calculated in Model 9; vertical error bars represent confidence intervals calculated in Model 6. (B) Difference in Akaike Information Criterion in Model 9 versus in Model 6. (C) Random effects estimates from Model 9.

Fig. 6

ACE model in twin sub-sample at baseline, residualizing for all covariates (Model 10) versus age and sex only (Model 1). (A) Comparison of estimates from Model 10 versus Model 1. Horizontal error bars represent confidence interval calculated in Model 10; vertical error bars represent confidence intervals calculated in Model 1. (B) Difference in total residual variance in Model 10 versus in Model 1. (C) Random effects estimates from Model 10.

Fig. 7

ACSE model in full sample omitting twin registry participants, baseline + year 2 longitudinal sample (Model 15). Comparison model is equivalent but includes the full sample inclusive of twin registry participants (Model 14). (A) Comparison of estimates from Model 15 versus Model 14. Horizontal error bars represent confidence interval calculated in Model 15; vertical error bars represent confidence intervals calculated in Model 14. (B) Difference in total residual variance in Model 15 versus in Model 14. (C) Random effects estimates from Model 15.