A phenotypic spectrum of autism is attributable to the combined effects of rare variants, polygenic risk and sex

Abstract

The genetic etiology of autism spectrum disorder (ASD) is multifactorial, but how combinations of genetic factors determine risk is unclear. In a large family sample, we show that genetic loads of rare and polygenic risk are inversely correlated in cases and greater in females than in males, consistent with a liability threshold that differs by sex. De novo mutations (DNMs), rare inherited variants and polygenic scores were associated with various dimensions of symptom severity in children and parents. Parental age effects on risk for ASD in offspring were attributable to a combination of genetic mechanisms, including DNMs that accumulate in the paternal germline and inherited risk that influences behavior in parents. Genes implicated by rare variants were enriched in excitatory and inhibitory neurons compared with genes implicated by common variants. Our results suggest that a phenotypic spectrum of ASD is attributable to a spectrum of genetic factors that impact different neurodevelopmental processes.

Extended Data Fig. 1. Rates of de novo mutations stratified by cohort and evaluation of potential confounders.

a, Rates of de novo synonymous (dnSyn) variants were not associated with ASD in the combined sample, but were enriched 1.1-fold in the SPARK cohort (P = 0.021). b, We evaluated whether quality metrics or other confounders could explain the slight excess of dnSyn variants in SPARK cases. Quality metrics did not differ in cases and controls including coverage, transition:transversion ratio (Ti/Tv) or ratio of heterozygous calls (Het/Hom). c, Paternal age did not differ significantly between cases and controls.

Extended Data Fig. 2. The combined effects of dnLoF, inhLoF and sex on the transmission of rare variants in families.

a, A significant liability threshold for rare variants was evident based on a negative correlation of dnLoF and inhLoF (linear regression P = 0.03), and this effect did not differ significantly by sex. b, Case-control odds ratios were compared for the transmission rates in families by sex (father-daughter, mother-daughter, father-son, mother-son). Both maternal and paternal rare variants contribute to ASD with a significant over-transmission from mother to daughter and from father to son. We did not observe a significant sex bias in the transmission of rare variants in families. In particular, we did not observe an enriched transmission from mother to male cases as we have previously hypothesized.

Extended Data Fig. 3. Sex differences in the correlation of rare variant and common variant risk was not robust across multiple polygenic scoring methods.

a, An early analysis of this dataset using polygenic score estimates from PRSice observed that the negative correlation of RVRS and CVRS was stronger in males than in females, consistent with males having less tolerance of genetic risk. The heatmap displays the correlations between polygenic scores and rare variants in males and females separately. Correlations were tested by linear regression controlling for cohort, case status and ancestry PCs, and a gene-by-sex interaction was tested in the combined sample (^ǂgene-by-sex P < 0.05). b, With polygenic scores calculated using SBayesR, there was a similar trend with the correlation of CVRS and RVRS being stronger in males; however, the gene-by-sex interaction was not statistically significant.

Extended Data Fig. 4. Correlation of de novo mutation rate with parental age.

a,b, Correlation of total autosomal de novo SNVs with age of fathers (a) and mothers (b). See also Figure 6a. n = 4,518 trios for which age-at-birth was available for the mother and father.

Extended Data Fig. 5. Comparison of the predictive values of polygenic scoring methods PRSice and SBayesR.

Polygenic scores calculated using SBayesR had greater predictive value for polygenic scores for ASD (PS_ASD), schizophrenia (PS_SZ) and educational attainment (PS_EA).

Figure 1 |. Risk for ASD is attributable to multiple genetic factors including DNMs, rare inherited variants and polygenic risk.

Multiple genetic factors that have been previously associated with ASD were confirmed in our combined sample. “**” denotes associations that were significant after correction for 11 tests (P < 0.0045). Error bars represent the 95% confidence intervals. a, Damaging DNMs in genes that are functionally constrained (LOEUF < 0.37 and MPC ≥ 2), including missense variants (dnMIS), and protein-truncating SNVs and indels (dnLoF) and SVs (dnSV), occur at higher frequencies in cases than in sibling controls. P-values were based on two-sided t-tests. b, Protein-truncating SNVs and indels (inhLOF) and SVs (SVLoF) and non-coding SVs that disrupt cis-regulatory elements (CRE-SVs) were associated with ASD based on a TDT test. c, Polygenic TDT (pTDT) was significant for all three polygenic scores for autism (PS_ASD), schizophrenia (PS_SZ), and educational attainment (PS_EA). Rare variant associations (a,b) were tested in the full sample (n = 37,375). Polygenic pTDT association was tested in samples of European ancestry (n = 25,391). Results for a-c and full lists of rare de novo and inherited variants in constrained genes are provided in Supplementary Tables 3–10.

Figure 2 |. Multivariable regression of six genetic factors to create a composite genomic risk score.

a, Variance in case status explained (r² and 95% CI) by each genetic factor individually and in combination. Combined effects of rare variants (Rare combined) polygenic scores (PS combined) and all genetic factors (All combined) were estimated in the European-ancestry sample (n = 25,391) by multivariable logistic regression controlling for sex, cohort and principal components. b, log₁₀ odds-ratios of case/control proportions for the composite genetic risk scores RVRS, CVRS, and GRS at multiple thresholds (deciles). Across all thresholds, effect sizes for the GRS was 41–42% greater than for RVRS or CVRS alone. See results in Supplementary Tables 13 and 14.

Figure 3 |. Increased genetic load in females with ASD compared to males.

a,b, Increased burden of genetic risk in female cases compared to male cases is evident for combined rare de novo and inherited variants (RVRS) (a) and combined polygenic scores (CVRS) (b). P-values from a two-sample t-test are shown. Participants consisted of 5,247 cases (4,256 males and 991 females) and 3,054 controls (1,504 males and 1,550 females) of European ancestry. c, Sex differences in the combined genetic load (GRS) is evident across the full distribution. d, A fill plot comparing the densities of distributions illustrates that the GRS of females (cases and controls) are skewed upward relative to males.

Figure 4 |. Negative correlation of rare variants and polygenic risk is consistent with a liability threshold model.

a, Transmission of polygenic risk (pTDT) is reduced to cases that carry damaging DNMs (dnLoF and dnMIS combined), but the result was not significant in females. P-values were based on two-sided t-tests. n = 4,256 male cases (423 DNM and 3,833 no DNM) and 991 females (1,504 DNM and 1,550 no DNM) of European ancestry. b, A heatmap displaying the strength of the correlations between polygenic scores and rare variants. P-values were derived from linear regression. Results are provided in Supplementary Table 15.

Figure 5 |. Differential effects of rare and common variation on behavioral traits in cases, sibling controls and parents.

a, The effects of genetic factors were tested on five phenotype measures in children: repetitive behavior (RBS), social responsiveness (SRS), social communication (SCQ), vineland adaptive behavior (VABS) and developmental motor coordination (DCDQ). Note that RBS, SRS, SCQ and BAPQ are measures of “deficit”; thus, in the heatmap, red corresponds to increased severity. VABS and DCDQ are measures of “skill”; thus, blue corresponds to increased severity on these two instruments. Gene-phenotype correlations were tested by linear regression controlling for sex, age, cohort and PCs. Effect size is given as standard deviation (sd) of phenotype per unit of genetic factor. b, Genetic effects on parental behavior were tested for autism-related symptoms (BAPQ, SRS), educational attainment and parental age. In total, six gene-trait correlations were significant after Bonferroni correction for 72 tests (**P ≤ 0.0007), 18 were nominally significant (*P ≤ 0.05), and 11 showed evidence of sex-biased effects (gene-by-sex interaction P ≤ 0.05). Male or female sex bias indicates which sex had the greatest absolute value of effect size. Sample sizes for each phenotype ranged from 3,429 to 11,485. Sample numbers and results are summarized in Supplementary Tables 16 and 17. Analysis was restricted to individuals of European ancestry.

Figure 6 |. The genetic basis of parental-age effects on ASD risk in offspring is multifactorial.

a, Multiple genetic risk factors for ASD are correlated with parental age with effects that differ by sex. Correlations of genetic factors with parental age (standard deviation of age per unit of genetic load) were estimated for 11,485 individuals (5,749 mothers and 5,736 fathers). P-values based on linear regression are given for individual effects with P < 0.05. Sex-stratified results for genetic effects on parental age are in Supplementary Table 18. b, The effects of six genetic factors on parental age were positively correlated with their effects on educational attainment, and the strongest correlate of parental age was PS_EA. c, The effects of six genetic factors on parental age were negatively correlated with their effects on the SRS in parents. P-values were derived from linear regression. Whiskers represent 95% confidence intervals.

Figure 7 |. ASD susceptibility genes implicated by rare variants are enriched in neuronal cell types of the developing brain.

Expression levels of protein-coding genes in bulk tissue (BrainSpan) and in 16 cortical cell types (CoDEx) were compared between 115 genes identified with a rare variant association test in this study (TADA) and 114 genes implicated by common variants in Grove et al. (GWAS). a, Expression of GWAS genes across all periods and brain regions was enriched relative to the full distribution, and the expression of TADA genes was further enriched relative to GWAS. Boxes and whiskers represent the interquartile range (IQR) and 1.5*IQR, respectively. b, The expression of ASD genes in the developing cortex (after normalizing genes in BrainSpan to mean expression of 1 across periods) was enriched during prenatal development relative to null distribution consisting of 1,000 randomly protein-coding genes, with TADA genes being enriched to a greater extent. Shaded regions represent mean of the 95% CI from lowess smoothing. c, Mean expression of the GWAS and TADA genes were estimated within 16 cell types in the CoDEx datset and compared to the null distribution of randomly sampled genes (811/1,000 genes that were included in CoDEx) by a two-sample t-test. After Bonferroni correction for 32 tests (*P ≤ 0.0016), expression of TADA genes was significantly increased relative to the null in five neuronal cell types. Error bars represent standard error of the mean (s.e.m.), and P-values were derived from two-sided t-test. Gene sets and cell-type expression results are provided in Supplementary Tables 20 and 21. RG, radial glia; MP, mitotic progenitor; IP, intermediate progenitor; EN, excitatory neuron; IN, interneuron; O, oligodendrocyte precursor; E, endothelial cell; P, pericyte; M, microglia.