De novo and rare inherited mutations implicate the transcriptional coregulator TCF20/SPBP in autism spectrum disorder

Abstract

Background: Autism spectrum disorders (ASDs) are common and have a strong genetic basis, yet the cause of ∼70-80% ASDs remains unknown. By clinical cytogenetic testing, we identified a family in which two brothers had ASD, mild intellectual disability and a chromosome 22 pericentric inversion, not detected in either parent, indicating de novo mutation with parental germinal mosaicism. We hypothesised that the rearrangement was causative of their ASD and localised the chromosome 22 breakpoints.

Methods: The rearrangement was characterised using fluorescence in situ hybridisation, Southern blotting, inverse PCR and dideoxy-sequencing. Open reading frames and intron/exon boundaries of the two physically disrupted genes identified, TCF20 and TNRC6B, were sequenced in 342 families (260 multiplex and 82 simplex) ascertained by the International Molecular Genetic Study of Autism Consortium (IMGSAC).

Results: IMGSAC family screening identified a de novo missense mutation of TCF20 in a single case and significant association of a different missense mutation of TCF20 with ASD in three further families. Through exome sequencing in another project, we independently identified a de novo frameshifting mutation of TCF20 in a woman with ASD and moderate intellectual disability. We did not identify a significant association of TNRC6B mutations with ASD.

Conclusions: TCF20 encodes a transcriptional coregulator (also termed SPBP) that is structurally and functionally related to RAI1, the critical dosage-sensitive protein implicated in the behavioural phenotypes of the Smith-Magenis and Potocki-Lupski 17p11.2 deletion/duplication syndromes, in which ASD is frequently diagnosed. This study provides the first evidence that mutations in TCF20 are also associated with ASD.

Keywords: Chromosomal; Clinical genetics; Genetics; Molecular genetics; Psychiatry.

Figure 1

Pedigree of family #1 and facial appearance of individuals heterozygous for chromosome 22 rearrangement. (A) Pedigree showing the immediate family of the proband (arrow). Filled symbols represent individuals shown to carry the rearrangement. N indicates absence of the rearrangement. (B) Normal facial appearance of the proband's older brother II-2, aged 10 years. (C) Facial appearance of the proband aged 10 months showing trigonocephaly associated with hypotelorism and mild exorbitism, caused by premature synostosis of the metopic suture.

Figure 2

Structure of the chromosome 22 rearrangement deduced from fluorescence in situ hybridization (FISH) analysis and DNA sequencing. (A–C) Representative FISH analysis and diagrammatic interpretation of structure of the rearranged chromosome (der22), shown in more detail with positions of breakpoints in (D). (A) Signals from RP11-241G19 (green), which spans breakpoint A, and the more distal RP11-49A20 (red) are adjacent on the normal chromosome 22 (arrowhead) but a split green signal is seen near the opposite end of the der22 (arrow). (B) Clones W12-1927K3 (red) and W12-1574G19 (green), which lie on either side of breakpoint B, showing hybridisation together on the normal chromosome 22 (arrowhead) and at opposite ends of the der22 (arrow). C. Single signal with W12-1570N6 on normal chromosome 22 (arrowhead), but split signal on derived 22 (arrow) indicating position of breakpoint C. (D) Ideograms of wt and derived chromosome 22. The order of BAC and fosmid clones employed in figure parts A–C is shown, together with the locations of breakpoints A–C. The 2 Mb region between breakpoints A and B is shown in light red (orientation on the derived chromosome is uncertain). Breakpoint D on the satellite short arm was not further characterised. Below left, map of the 65 kb region that includes breakpoint C, showing the positions and orientations of genes. The Southern blot analysis shows an apparent breakpoint in the patient sample (P) compared with the control (C), localising the breakpoint to the indicated segment (double-ended arrows) of ∼4 kb. Below right, the DNA sequence chromatogram spanning the breakpoints A and B is shown above an alignment of this sequence with the normal sequences at the telomeric and centromeric ends of breakpoints. Arrows indicate positions and numbering of the last intact bases on either side of the translocated region.

Figure 3

TCF20 gene structure, identification of variants in ASD cases and their location within conserved domains. (A) Schematic representation of TCF20, exons are shown to scale with the coding sequence in white and untranslated regions filled in with black. There is an alternative stop codon in the alternatively spliced exon 5. The position of the first coding nucleotide is shown in exon 2, numbers above boxes indicate cDNA numbering at last nucleotides of exon boundaries or last nucleotide of stop codons; numbers in red below lines indicate intron sizes (not to scale). The location of breakpoint A that interrupts TCF20 23350 bp 5′ of exon 2 is also indicated. (B) Pedigrees of five families with variants of TCF20 that are either novel or enriched compared with control samples. Below each pedigree is a chromatogram showing the sequence change together with the amino acids encoded by the change and by adjacent codons. Black symbols indicate individuals with a clinical and research ASD diagnosis, the white symbol indicates people without clinical ASD; where broader autism phenotype data are available this is described in the text; n/a indicates that no DNA was available for analysis. Under each symbol, the status of that individual for the change found in the proband is shown. (C) Diagram representing the TCF20 protein with previously annotated domains: P1-P3, PEST domains; N1-N3, nuclear localisation signals; MD, minimal DNA binding domain; ZNF2, zinc finger domain. The three lines above the protein denote the following domains: TAD, transactivation domain; DBD, DNA binding domain and the ePHD/ADD domain. The lower panel shows the positions and conservation of amino acid residues predicted to be substituted in ASD pedigrees. The entire PEST1 and PEST2 sequences are shown with interspecies conservation in mammals, chicken and frog. (D) Analysis of cDNA amplification product compared with genomic (gDNA) from region containing c.3518delA mutation in family #6. Restriction digestion was performed with BslI, yielding product sizes (bp) of 215, 162, 145, 72, 1 in the absence of the mutation and 233, 215, 145, 1 in the presence of the mutation. Lanes numbered as follows: 1, undigested gDNA from proband; 2, mother's gDNA; 3, father's gDNA; 4, proband's gDNA; 5, proband's cDNA and 6, −RT control for proband's cDNA. Note similar relative intensities of mutant and non-mutant fragments in lanes 4 and 5, indicating lack of significant nonsense-mediated decay associated with the frameshifting mutation.