Biallelic expansion of an intronic repeat in RFC1 is a common cause of late-onset ataxia

Abstract

Late-onset ataxia is common, often idiopathic, and can result from cerebellar, proprioceptive, or vestibular impairment; when in combination, it is also termed cerebellar ataxia, neuropathy, vestibular areflexia syndrome (CANVAS). We used non-parametric linkage analysis and genome sequencing to identify a biallelic intronic AAGGG repeat expansion in the replication factor C subunit 1 (RFC1) gene as the cause of familial CANVAS and a frequent cause of late-onset ataxia, particularly if sensory neuronopathy and bilateral vestibular areflexia coexist. The expansion, which occurs in the poly(A) tail of an AluSx3 element and differs in both size and nucleotide sequence from the reference (AAAAG)₁₁ allele, does not affect RFC1 expression in patient peripheral and brain tissue, suggesting no overt loss of function. These data, along with an expansion carrier frequency of 0.7% in Europeans, implies that biallelic AAGGG expansion in RFC1 is a frequent cause of late-onset ataxia.

Fig. 1 |. Clinical spectrum and pedigrees of late-onset ataxia.

a, Clinical spectrum of idiopathic late-onset ataxia from isolated cerebellar, vestibular, and sensory variants to full-blown CANVAS. b, Pedigrees of CANVAS families. The squares indicate males and the circles females. The diagonal lines are used for deceased individuals. CANVAS patients are indicated with filled shapes. The black dots indicate genotyped individuals. The red dots indicate patients enrolled for WGS study.

Fig. 2 |. Identification of CANVAS locus.

a, Non-parametric multipoint linkage analysis identifies a unique locus associated with the disease in chromosomal region 4p14 with a maximal HLOD score of 5.8. b, Schematic representation of shared haplotypes within single families. The light blue bars indicate a genomic region shared by affected siblings in a family and for which unaffected siblings are discordant. Two red dashed lines define a 1.7-Mb region common to the different families. SNPs defining the haplotypes are represented on the top line. c, Fine mapping inside the 1.7-Mb region identifies a recessive haplotype shared by all distinct families (highlighted in green), except for individual Fam 5b-2, who probably shares only one allele (highlighted in light green). d, Schematic representation of the candidate region encompassing all 24 exons and flanking regions of RFC1 and the last exon and flanking intron of WDR19.

Fig. 3 |. Recessive expansion of a mutated AAGGG repeated unit in intron 2 of RFC1 causes CANVAS and late-onset ataxia in familial and sporadic cases.

a, A reduced read depth of WGS is observed in CANVAS patients (n = 6) in a region corresponding to a short tandem AAAAG repeat in intron 2 of RFC1. b, Visualization on IGV of reads aligned to the short repeat and flanking region shows in patients (n = 6) the presence of a mutated AAGGG repeat unit (representative image). Reads from both sides are interrupted and are unable to cover the entire length of the microsatellite region. Note that, per IGV default setting, AAGGG repeated units that do not map to the (AAAAG)₁₁ reference sequence are soft-clipped and do not contribute to the coverage of the STR in a, which is virtually absent. However, ≥20 reads containing the AAGGG repeated unit could be observed in each patient if soft-clipped reads were shown. c, RP-PCR targeting the mutated AAGGG repeated unit. Fluorescein amidite-labeled PCR products were separated on an ABI 3730 DNA Analyzer. Electropherograms were visualized on GeneMapper at 2,000 relative fluorescence units. The representative plots from a patient carrying the AAGGG repeat expansion and one non-carrier are shown. RP-PCR experiments were repeated independently twice with similar results. d, Sanger sequencing of long-range PCR reactions confirms the AAAAG to AAGGG nucleotide change of the repeated unit in patients.

Fig. 4 |. Polymorphic configurations of the repeat expansion locus and allelic distribution in healthy controls.

a, Schematic representation of the repeat expansion locus in intron 2 of RFC1 and its main allelic variants. b, Estimated allelic frequencies in 608 chromosomes from 304 healthy controls. c, Average size and s.d. of (AAAAG)_exp (n = 24) and (AAAGG)_exp (n = 30) expansions in healthy controls and (AAGGG)_exp (n = 72) in controls and CANVAS patients.

Fig. 5 |. Pathology of cerebellar degeneration in a patient with CANVAS carrying the recessive AAGGG repeat expansion.

a-j, Hematoxylin and eosin (H&E)-stained sections (a-e) and sections immunostained for p62 (f-j). In a control brain (a), age-matched for the patient with CANVAS syndrome, there is well preserved density of Purkinje cells (yellow arrowhead); the granule cell layer is densely populated with small neurocytes (green asterisk). b, In CANVAS syndrome, there is severe, widespread depletion of Purkinje cells with associated prominent Bergmann gliosis (blue arrowhead), while cell density in the granule cell layer is well preserved. c, In a patient with genetically confirmed FRDA, there is patchy depletion of Purkinje cells associated with Bergmann gliosis and unremarkable appearance of the granule cell layer. d, In a patient with genetically confirmed SCA17, there is widespread Purkinje cell loss with only occasional Purkinje cells remaining; also, in this patient, the granule cell layer is densely populated with small neurocytes. e, In a patient with FTD due to C9orf72 expansion, Purkinje cell loss is patchy and the granule cell layer is unremarkable. f-h, Immunostaining for p62 shows no pathological cytoplasmic or intranuclear inclusions in the cerebellar cortex in the control patient (f), the patient with CANVAS syndrome (g), and also in the patient with FRDA (h). i, In the SCA17 patient, there are scattered discrete intranuclear p62 immunoreactive inclusions in the small neurons within the granule cell layer (high-power view of a representative intranuclear inclusion is demonstrated in the inset within i). j, In the patient with the C9orf72 expansion, there are frequent characteristic perinuclear p62 positive inclusions in the granule cell layer (high-power view of a representative inclusion is shown in the inset within j). Scale bar, 100 μm in a-e, 30 μm in f-j, and 5μm in the insets in f-j. Staining was carried out once on patient samples with appropriate controls according to standard practice and histopathology procedures in an ISO 15189-accredited laboratory.

Fig. 6 |. RFC1 expression is not affected by the AAGGG repeat expansion.

a, Plots showing the expression levels of RFC1 and FXN in controls (n = 3), patients with FRDA (n = 2), and one CANVAS patient in postmortem cerebellum and frontal cortex. b, Mapping on RFC1 transcript 1 of the primers used for assessment by qRT-PCR of RFC1 mRNA (cF1-cR1 and cF2-cR2) and pre-mRNA (cF1/iR1) expression. The blue arrows indicate the primers mapping to the exonic and intronic regions of the canonical RFC1 transcript. Primers spanning across exonic junctions are connected by dotted lines. A red triangle indicates the site of the AAGGG repeat expansion. c, Expression levels of the canonical coding RFC1 mRNA as measured by qRT-PCR using two separate sets of primers, cF1-cR1 and cF2-cR2, in control (n = 3) and CANVAS (n = 2) lymphoblasts, control (n = 5) and CANVAS (n = 5) fibroblasts, control (n = 3), FRDA (n = 3), and CANVAS (n = 1) cerebellum and frontal cortex, and control (n = 5) and CANVAS muscles (n = 7). d, RFC1-encoded protein levels as measured by western blotting using the polyclonal antibody GTX129291 and normalized to β-actin in control (n = 5) and CANVAS (n = 5) fibroblasts, control (n = 3) and CANVAS (n = 4) lymphoblasts, and control (n = 3), FRDA (n = 3), and CANVAS (n = 1) postmortem cerebellum and frontal cortex. The bar graphs show the mean±s.d. and data distribution (black dots). A two-tailed t-test was performed to compare RFC1 transcript and encoded protein expression in patients versus healthy or disease controls. All experiments were repeated independently twice with similar results.