Phenotypic and ancestry-related assortative mating in autism

Abstract

Background: Positive assortative mating (AM) in several neuropsychiatric traits, including autism, has been noted. However, it is unknown whether the pattern of AM is different in phenotypically defined autism subgroups [e.g., autism with and without intellectually disability (ID)]. It is also unclear what proportion of the phenotypic AM can be explained by the genetic similarity between parents of children with an autism diagnosis, and the consequences of AM on the genetic structure of the population.

Methods: To address these questions, we analyzed two family-based autism collections: the Simons Foundation Powering Autism Research for Knowledge (SPARK) (1575 families) and the Simons Simplex Collection (SSC) (2283 families).

Results: We found a similar degree of phenotypic and ancestry-related AM in parents of children with an autism diagnosis regardless of the presence of ID. We did not find evidence of AM for autism based on autism polygenic scores (PGS) (at a threshold of |r|> 0.1). The adjustment of ancestry-related AM or autism PGS accounted for only 0.3-4% of the fractional change in the estimate of the phenotypic AM. The ancestry-related AM introduced higher long-range linkage disequilibrium (LD) between single nucleotide polymorphisms (SNPs) on different chromosomes that are highly ancestry-informative compared to SNPs that are less ancestry-informative (D² on the order of 1 × 10^-5).

Limitations: We only analyzed participants of European ancestry, limiting the generalizability of our results to individuals of non-European ancestry. SPARK and SSC were both multicenter studies. Therefore, there could be ancestry-related AM in SPARK and SSC due to geographic stratification. The study participants from each site were unknown, so we were unable to evaluate for geographic stratification.

Conclusions: This study showed similar patterns of AM in autism with and without ID, and demonstrated that the common genetic influences of autism are likely relevant to both autism groups. The adjustment of ancestry-related AM and autism PGS accounted for < 5% of the fractional change in the estimate of the phenotypic AM. Future studies are needed to evaluate if the small increase of long-range LD induced by ancestry-related AM has impact on the downstream analysis.

Keywords: Assortative mating; Autism; Genetic ancestry; Intellectual disability; Linkage disequilibrium; Polygenic scores.

Fig. 1

Phenotypic and ancestry-related AM in autism w/ and w/o CI/ID families of European ancestry in SPARK and SSC. A Spousal correlations and 95% confidence intervals of genetic ancestry PC1-PC2 (from the PCA with 1000 Genomes participants of European ancestry), autism PGS, and intelligence PGS in autism w/ and w/o CI families in SPARK. B Spousal correlations and 95% confidence intervals of genetic ancestry PC1-PC2 (from the PCA with 1000 Genomes participants of European ancestry), autism PGS, intelligence PGS, and measures of quantitative autistic traits (SRS and BAPQ) in autism w/ and w/o ID families in SSC. C Over-transmission of autism PGS and 95% confidence intervals in autism w/ and w/o CI/ID families in SPARK and SSC. D Over-transmission of intelligence PGS and 95% confidence intervals in autism w/ and w/o CI/ID families in SPARK and SSC. *p < 0.05/336 = 0.000149

Fig. 2

The proportion of phenotypic AM explained by ancestry-related AM, autism PGS, intelligence PGS, and demographic variables in SSC families of European ancestry. A Spearman’s correlation coefficients within and between SRS and BAPQ total scores and subscales for SSC parents. B The spousal correlations and 95% confidence intervals of SRS and BAPQ total scores after adjusting age, highest education, the top 10 genetic ancestry PCs, autism PGS, and intelligence PGS in SSC. Independent variables in the full model: age, highest education, top 10 genetic ancestry PCs, autism PGS, and intelligence PGS

Fig. 3

Intra-locus correlations (measured by Wright’s F) and inter-locus correlations (measured by D²) between SNPs on different chromosomes in SPARK and SSC families of European ancestry. A Mean Wright’s F at 200 SNPs that loaded the heaviest on |PC1| (|PC1| top 200) compared to mean Wright’s F at 200 SNPs that loaded the least on |PC1| (|PC1| bottom 200) in SPARK. B Mean Wright’s F at 200 SNPs that loaded the heaviest on |PC1| (|PC1| top 200) compared to mean Wright’s F at 200 SNPs that loaded the least on |PC1| (|PC1| bottom 200) in SSC. C Mean D² between 200 SNPs that loaded the heaviest on |PC1| (|PC1| top 200) that were on different chromosomes compared to mean D² between 200 SNPs that loaded the least on |PC1| (|PC1| bottom 200) that were on different chromosomes in SPARK. D Mean D² between 200 SNPs that loaded the heaviest on |PC1| (|PC1| top 200) that were on different chromosomes compared to mean D² between 200 SNPs that loaded the least on |PC1| (|PC1| bottom 200) that were on different chromosomes in SSC. |PC1|: the absolute value of the first PC from the PCA with 1000 Genomes participants of European ancestry