Rates, distribution and implications of postzygotic mosaic mutations in autism spectrum disorder

Abstract

We systematically analyzed postzygotic mutations (PZMs) in whole-exome sequences from the largest collection of trios (5,947) with autism spectrum disorder (ASD) available, including 282 unpublished trios, and performed resequencing using multiple independent technologies. We identified 7.5% of de novo mutations as PZMs, 83.3% of which were not described in previous studies. Damaging, nonsynonymous PZMs within critical exons of prenatally expressed genes were more common in ASD probands than controls (P < 1 × 10^-6), and genes carrying these PZMs were enriched for expression in the amygdala (P = 5.4 × 10^-3). Two genes (KLF16 and MSANTD2) were significantly enriched for PZMs genome-wide, and other PZMs involved genes (SCN2A, HNRNPU and SMARCA4) whose mutation is known to cause ASD or other neurodevelopmental disorders. PZMs constitute a significant proportion of de novo mutations and contribute importantly to ASD risk.

Figure 1. De novo mutations in ASD show an excess of low alternate allele frequencies, consistent with post-zygotic mosaicism

(a) There is an excess of variants with low AAFs among the de novo mutations, which are likely to be post-zygotic mutations. (b) Rates of mutations in the datasets for all de novos in Group A, as well as mosaics in Groups B and C. (c) Correlation of AAFs for PZMs across the AAF spectrum using multiple technologies (n=49 mutations for CloneSeq, n=46 mutations for Pyroseq, n=42 mutations for MiSeq), with higher correlations (Pearson's r²=0.85 for CloneSeq and MiSeq, r²=0.63 for CloneSeq and Pyroseq). (d) Percentages of identified de novo variants that were identified by previous analyses or novel from Groups A, B and C. The majority of high-confidence PZMs from Group C were not detected by previous calling algorithms.

Figure 2. Post-zygotic mutations in ASD show excess deleterious mutations in critical exons of early developmental brain expressed genes

(a) There is no statistically significant global excess of Group C PZMs in the probands (red) compared to their unaffected siblings (blue), hypergeometric P=0.32 for fraction of LoF variants in probands compared to siblings. (b) As expected, there are highly significant excesses in overall gDNMs (Group A) for genes expressed in prenatal and adult brains. For Groups B and C, representing potential and high-confidence PZMs, there is a strong excess of LoF and missense mutations in critical exons that are expressed in EPN (early prenatal) and LPN (late prenatal), 1-tailed Wilcoxon rank sum test P<1×10^-5, but not ECH (early childhood) or ADU (adult) post-mortem brain samples in the probands, 1-tailed Wilcoxon rank sum test P>1×10^-5.

Figure 3. Post-zygotic mutations implicate the prenatal amygdala in ASD

Spatial representation of the regions that are enriched for PZMs in Group C in the probands, and the 1-tailed Wilcoxon rank sum test P=5.4×10^-3 for the top brain region (AMY – amygdala).

Figure 4. Recurrent non-synonymous post-zygotic mosaic mutations implicate novel genes with more mutations than expected false calls

(a) Sanger sequencing traces for the 3 SMARCA4 mutations. (b) SMARCA4 mutations reported in cancers, Coffin-Siris syndrome and ASD. (c) qPCR results for GRIN2B after overexpression and selection of wildtype and mutant (p.P143A and p.I184T) human SMARCA4 in N2A cells, with the values for each replicate experiment (N=3 each for WT, P143A and I184T) in red dots (unpaired t-test P=0.0031 for P143A compared to wildtype and P=0.015 for I184T compared to wildtype).