Frequency and Complexity of De Novo Structural Mutation in Autism

Abstract

Genetic studies of autism spectrum disorder (ASD) have established that de novo duplications and deletions contribute to risk. However, ascertainment of structural variants (SVs) has been restricted by the coarse resolution of current approaches. By applying a custom pipeline for SV discovery, genotyping, and de novo assembly to genome sequencing of 235 subjects (71 affected individuals, 26 healthy siblings, and their parents), we compiled an atlas of 29,719 SV loci (5,213/genome), comprising 11 different classes. We found a high diversity of de novo mutations, the majority of which were undetectable by previous methods. In addition, we observed complex mutation clusters where combinations of de novo SVs, nucleotide substitutions, and indels occurred as a single event. We estimate a high rate of structural mutation in humans (20%) and propose that genetic risk for ASD is attributable to an elevated frequency of gene-disrupting de novo SVs, but not an elevated rate of genome rearrangement.

Figure 1

Structural Variation Detected from WGS in 235 Individuals Circos plot in which concentric circles represent the following (from outermost to inner): ideogram of the human genome with colored karyotype bands (UCSC Genome Browser build hg19), deletions, MEIs (four different classes), tandem duplications, balanced inversions, and complex SVs (four different classes). Circles indicate the location of de novo SVs, and their colors match the five SV types. Arrows represent interchromosomal duplications.

Figure 2

Frequency of De Novo SVs A forest plot indicates the average mutation frequency per genome (μ) from published microarray studies of ASD, from the ASD-affected and control individuals in our study, and from a whole-genome study from the GoNL Consortium. Error bars represent the 95% CIs according to a Poisson distribution, and boxes are proportional to the sample sizes tested.

Figure 3

Detection, Genotyping, and Sequence Characterization of De Novo SVs (A) Heatmaps show a deletion signal from the total sequence coverage (copy number) and the number of discordant paired ends. (B) SVs were genotyped with gtCNV, a SVM algorithm we developed. The contour plot shows the Phred-scaled genotype likelihoods for homozygous reference (green), heterozygous (blue), and homozygous (red) genotypes (for simplicity, only read depth and discordant paired ends are plotted). The colored diamonds indicate the genotype likelihoods for the proband and the parents. (C) A majority of SNP alleles between the deletion boundaries were derived from the mother (shown in black), confirming a deletion of the paternal haplotype. (D) De novo assembly of clipped reads resolved the breakpoint to single-base-pair resolution. Unaligned sequences within clipped reads are highlighted in gray. (E) Aligning the assembled contig to the genome revealed the deletion breakpoint. Unique sequence proximal and distal to the breakpoint suggests a non-homologous-end-joining (NHEJ) mechanism. (F) The mutant transcript of CACNG2 was sequenced from a fibroblast line derived from the individual and results in an in-frame deletion of exon 2.

Figure 4

De Novo SVs of Genes Detectable through Genome Sequencing Discordant paired-end mapping identified de novo SVs. (A) A de novo AluYb8 element insertion into the 3′ UTR of C3orf35. Discordant paired ends and split reads mapped to both the 3′ and 5′ sides of the insert point, as well as the Alu. The partial AluYb8 (134 bp) was inserted into the positive strand with a 14 bp target-site duplication (shown in blue). (B) A 1.52 Mb simple inversion with a distal breakpoint in intron 3 of CDH8. (C) A non-tandem duplication and a non-tandem inverted duplication inserted into the promoter of LSMEM1 with a concomitant deletion at the insertion point (note that segments are not shown to scale). Arrows indicate the discordant orientation and location of paired-end reads in relation to the reference genome (UCSC Genome Browser build hg19) and the concordant pattern of paired-end reads in relation to the resolved structure. Black segments are unchanged in the SV events, green segments are inverted, blue segments are duplicated, and red segments are deleted.

Figure 5

Mutational Clustering of SVs, Indels, and SNVs Two examples of complex mutation clusters are shown in individuals. (A) REACH000182, a 143 bp sequence near the 3′ UTR of SLC38A6, was duplicated and inserted into intron 16 of the gene with a concomitant deletion of 23 bp at the insertion site. Additionally, a de novo indel and SNV occurred at 211 bp and 34,611 bp proximal to the insertion site. (B) REACH000300, a 6.2 kb de novo deletion, was detected at 5q22.2, and three de novo SNVs occurred within 100 kb of the breakpoints. The 200 kb zoomed-in locus below the ideogram shows the positions of the de novo mutations in relation to each other. Gene tracks below the mutation show the longest transcript of each gene within the locus (arrows indicate the strand, and bars indicate the exons of genes).

Figure 6

Identification and Validation of the Pathogenic NRXN1 Deletion (A) A 166 kb deletion disrupting three exons of NRXN1 leads to a frameshift in the longer isoform (α-NRXN1). (B) Breakpoint mapping shows a unique sequence flanking the breakpoint, suggesting a NHEJ mechanism. (C) A forward PCR primer was designed proximal to the breakpoint, and two reverse primers were designed (one within the deletion region produces a 302 bp product, and one spanning the breakpoints produces a 225 bp product in the presence of a deletion). We confirmed the deletion in this pedigree in the proband (III-2) and mother (II-1), but not in the father, sibling, or maternal grandparents. (D) Pedigree of the family affected by multiplex ASD. The NRXN1 deletion occurred de novo in the mother and was passed on to her younger son. The mother is unaffected, and the older son has ASD but did not inherit the deletion, suggesting that other de novo and/or inherited variants contribute to ASD in this family. (E) Sanger sequencing of rs2042471 within the NRXN1 locus indicated that this deletion originated on the grandmaternal haplotype.