Novel Candidate Genes and a Wide Spectrum of Structural and Point Mutations Responsible for Inherited Retinal Dystrophies Revealed by Exome Sequencing

Abstract

Background: NGS-based genetic diagnosis has completely revolutionized the human genetics field. In this study, we have aimed to identify new genes and mutations by Whole Exome Sequencing (WES) responsible for inherited retinal dystrophies (IRD).

Methods: A cohort of 33 pedigrees affected with a variety of retinal disorders was analysed by WES. Initial prioritization analysis included around 300 IRD-associated genes. In non-diagnosed families a search for pathogenic mutations in novel genes was undertaken.

Results: Genetic diagnosis was attained in 18 families. Moreover, a plausible candidate is proposed for 10 more cases. Two thirds of the mutations were novel, including 4 chromosomal rearrangements, which expand the IRD allelic heterogeneity and highlight the contribution of private mutations. Our results prompted clinical re-evaluation of some patients resulting in assignment to a syndromic instead of non-syndromic IRD. Notably, WES unveiled four new candidates for non-syndromic IRD: SEMA6B, CEP78, CEP250, SCLT1, the two latter previously associated to syndromic disorders. We provide functional data supporting that missense mutations in CEP250 alter cilia formation.

Conclusion: The diagnostic efficiency of WES, and strictly following the ACMG/AMP criteria is 55% in reported causative genes or functionally supported new candidates, plus 30% families in which likely pathogenic or VGUS/VUS variants were identified in plausible candidates. Our results highlight the clinical utility of WES for molecular diagnosis of IRD, provide a wider spectrum of mutations and concomitant genetic variants, and challenge our view on syndromic vs non-syndromic, and causative vs modifier genes.

Fig 1. Segregation of mutations in selected pedigrees.

Pedigrees bearing new IRD candidates and chromosomal rearrangements are shown. Pedigrees where mutations in several genes co-segregate with the disease are also depicted. Alleles and carrier status are indicated below each analysed individual. Grey symbols (in H) shown patients bearing a different chromosomal rearrangement. The rest of the pedigrees are available as S3 Fig.

Fig 2. Identification of EYS and CRX deletions.

A-F) Two different gross heterozygous deletions in genes EYS and CRX were respectively identified as the causative mutation in families 68ORG and 10NCE. The probands (B and D) showed a reduction in the coverage of some exons compared to the respective controls (A and C). The segregation of SNPs located in the expected deleted region showing that mother and child were homozygous for different alleles is indicated below. (E and F). G) Chromosomal deletion in family 10NCE is defined by genotyping common SNPs between CRX and SULT2A1 genes in the affected probands. Heterozygous SNPs are indicated by △, whereas SNPs where mother and child were homozygous for different alleles are indicated by ∇. Adjacent breakpoint regions with high sequence similarity are boxed in orange and green and preserved sequences in the rearranged allele are indicated with orange and green lines. H) Sequence chromatogram of the rearranged allele is shown below. Alignment of the highly similar sequences of CRX intron 2 (CRX IVS2) and the intragenic region involved in the rearrangement is also indicated. Again, orange and green lines are the adjacent sequences to the breakpoint, which is indicated by a red square.

Fig 3. Identification of independent PRPF31 deletion and duplication segregating in pedigree E4.

Exome data indicated significant coverage differences of PRPF31 exons in the E4 family, pointing to chromosomal rearrangements. Some patients (A) showed higher coverage in exons 2–5 compared to a control sample (C) whereas patients from another family branch showed a significant decrease of exons 1–13 (B). CRX, located a few Mb away from PRPF31 gene, was used as a control gene (D-F). MLPA analysis confirmed a nearly full deletion of PRPF31 (exons 1 to 13) in some patients of the family (G) and an internal duplication involving exons 2 to 5 in other affected members (H) (shown in grey in Fig 1). I) Chromosomal region of PRPF31 involved in the duplication, where the duplicated exons are coloured in orange. Green and red lines below indicate the extent of the duplication. Chromatogram of the rearranged allele is shown below. Alignment of the flanking sequences (boxed in orange and green) involved in the rearrangement shows no clear homology. Orange and green lines are the adjacent sequences to the breakpoint, which is indicated by a red square.

Fig 4. Immunodetection of endogenous CEP250 in mouse retinal cryosections.

Immunostaining of CEP250 with rod photoreceptor marker rhodopsin (A) and acetylated α-tubulin (B). CEP250 stained mainly the outer segment of photoreceptors (CEP250 is in red, Rhodopsin and acetylated-α-tubulin in green, nuclear counterstaining by DAPI in blue). Cells expressing A609V CEP250-IT6 show longer cilia. (C) Wild-type (Wt) and mutant (Mt) CEP250-IT6 (green) co-localize with acetylated α-tubulin (red) to primary cilia in serum-starved ARPE-19 cells. Immunolabelling of CEP250 and acetylated α-tubulin show longer cilia in cells transfected with the mutant A609V CEP250-IT6 compared to Wt-CEP250-IT6. (D) Cilia length quantification in Wt- and Mt- CEP250-IT6 transfected cells. Graph shows that cilia from cells expressing mutant CEP250 were one third longer than cilia from cells expressing Wt-CEP250 (n>30). Mean and error are shown. *** indicates high statistical significance by the t-Student test, p<0.001. (E) Distribution of cilium length represented as a cumulative frequency chart of the percentage of total cilia. OS—photoreceptor outer segments; CC—connecting cilium; IS—photoreceptor inner segments; ONL—outer nuclear layer; INL—inner nuclear layer; GCL—ganglion cell layer.