CGG repeat-associated translation mediates neurodegeneration in fragile X tremor ataxia syndrome

Abstract

Fragile X-associated tremor ataxia syndrome (FXTAS) results from a CGG repeat expansion in the 5' UTR of FMR1. This repeat is thought to elicit toxicity as RNA, yet disease brains contain ubiquitin-positive neuronal inclusions, a pathologic hallmark of protein-mediated neurodegeneration. We explain this paradox by demonstrating that CGG repeats trigger repeat-associated non-AUG-initiated (RAN) translation of a cryptic polyglycine-containing protein, FMRpolyG. FMRpolyG accumulates in ubiquitin-positive inclusions in Drosophila, cell culture, mouse disease models, and FXTAS patient brains. CGG RAN translation occurs in at least two of three possible reading frames at repeat sizes ranging from normal (25) to pathogenic (90), but inclusion formation only occurs with expanded repeats. In Drosophila, CGG repeat toxicity is suppressed by eliminating RAN translation and enhanced by increased polyglycine protein production. These studies expand the growing list of nucleotide repeat disorders in which RAN translation occurs and provide evidence that RAN translation contributes to neurodegeneration.

Figure 1. CGG RAN translation in a Drosophila model of FXTAS

A) Schematic of (CGG)₉₀ GFP fly construct. A novel polyglycine protein is produced in these flies by RAN translation proceeding through the CGG repeat. Black sequence is vector derived and red sequence is human derived. Thicker red line is CGG repeat. The black arrow shows the expected AUG translational initiation site for GFP and the expected product. The red bracket and arrow show the RAN translational initiation region for the polyglycine-GFP fusion protein identified by tandem-MS. TSS is the presumed transcription start site. B) GFP inclusions in oomatidia from (CGG)₉₀ GFP, but not GFP, expressing flies. C) Confocal micrographs of transverse retinal sections from gmr-GAL4; (CGG)₉₀ GFP flies reveal nuclear and cytoplasmic inclusions that co-localize with ubiquitin. D) (CGG)₉₀ GFP inclusions partially co-localize with HSP70. E) In situ hybridization using a Cy5(CCG)₆ RNA probe on transverse retinal sections. CGG RNA foci form in the nucleus and cytoplasm of (CGG)₉₀ GFP flies and are either distinct from (arrowhead), or overlap with(arrow), GFP inclusions. F) Quantitation of co-localization of GFP aggregates with ubiquitin, HSP70, and CGG RNA foci. G) Co-expression of proteasomal subunit mutant DTS5 with (CGG)₉₀ GFP enhances retinal degeneration at 28C. H) A HMW band is seen with anti-GFP antibody (arrow) in lysates from (CGG)₉₀-GFP expressing flies. Lane 1, gmr-GAL4 flies (negative control); lane 2, gmr-GAL4; uas GFP; lane 3, gmr-GAL4; uas (CGG)₉₀ GFP. I) tandem-MS analysis of the HMW GFP band identifies three peptides (yellow) indicating that translation initiates above the repeat. Green sequence is GFP. *Predicted peptides above the indicated AA sequence were not detected. J) The HMW GFP product is selectively digested by the polyglycine endopeptidase, lysostaphin (LS). Unless stated, error bars represent SEM in all graphs.

Figure 2. CGG repeats trigger RAN translation and inclusion formation in mammalian cells

A) Schematic of (CGG)₈₈-GFP vector and mutations introduced in various constructs. Arrowhead shows the site of additional base insertions to shift the frame of GFP relative to the repeat. Red box reflects stop codon introduced in the +1 (Gly) frame. Full sequences of all constructs are shown in Table S1B) In COS cells 72 hours after transfection with (CGG)₈₈-GFP constructs, inclusions were observed when the CGG repeat was located in the +1 (Gly) frame, but not in native CGG +0 (Arg) frame. Far right panel includes a stop codon inserted between the repeat and the GFP coding sequence. C) COS cell lysates 72 hr after transfection with indicated plasmids, probed on western blot with antibodies to GFP or Tubulin. D) Quantification of inclusion formation by (CGG)₈₈ +1GFP in COS or SY5Y neuroblastoma cells 24, 48, and 72 hrs after transfection. E) Confocal microscopy showing inclusion in a SY5Y cell expressing (CGG)₈₈ +1GFP, stained for ubiquitin (red) and co-stained for DAPI (blue). F) An ATG start site placed upstream of the repeat in the +1 (Gly) frame (ATG-(CGG)₈₈ +1GFP) increases translation of the HMW GFP product. G) ATG-(CGG)₈₈ GFP) enhances GFP inclusion formation similar to levels seen with a polyglutamine peptide fused to GFP (Q80-GFP), an aggregation-prone positive control. H) Comparison of % GFP positive cells with inclusions upon expression of ATG-(CGG)₈₈ GFP or Q₈₀-GFP 24 hours after transfection.

Figure 3. CGG RAN translation in glycine reading frame occurs at normal repeat lengths, initiates before the repeat, and does not require a specific non-AUG codon

A) RAN translation occurs even with shorter repeats in the +1 (Gly) frame. B) Representative fluorescent micrographs of cells transfected with (CGG)_n +1 GFP constructs with the indicated number of repeats. C) Percent transfected COS cells with GFP+ inclusions 72 hours after transfection of (CGG)_n +1 GFP of the indicated repeat lengths. D) (Top) Schematic of (CGG)_n +1 GFP construct with location of introduced stop codon mutations. (Bottom) Western blot of cell lysates 72 hrs after transfection with the indicated constructs. Placing a stop codon 6 or 12 bp 5’ to the repeat inhibits production of HMW GFP. E) Fluorescent micrographs of COS cells expressing (CGG)₈₈ +1 GFP or stop@-12 (CGG)₉₄ +1 GFP, 72 hrs after transfection. F) Quantitation of GFP inclusion formation in the presence or absence of a stop codon −12 bp 5’ to the CGG repeat. G) (Top) Schematic demonstrating position of specific mutations in “near AUG” codons that might serve as alternative start sites for CGG RAN translation in the +1 glycine frame. (Below) Western blot of lysates from cells expressing the indicated constructs demonstrates that eliminating any single near AUG codon is insufficient to block RAN translation. H) (Top) Schematic demonstrating position of stop codon and near AUG codon mutation introduced into (CGG)_n +1 GFP construct. (Below) The elimination of a near AUG codon at −11 (lane 2) or the presence of a stop codon at −21 (lane 3) allows HMW GFP translation, but combining these mutations (lane 4) eliminates HMW GFP production. I) (Top) Schematic demonstrating deletion mutations that remove 48 or 91 nt just 5’ proximal to the repeat. (Below) Western blot demonstrating that removal of proximal sequence partially or completely impedes RAN translation in the +1 (Gly) frame. For this and other figures, differing sizes of the HMW GFP-positive bands reflect repeat instability incurred during cloning; repeat size is shown below the GFP blot for each lane. Positions of specific mutations are defined relative to the 5’ start of the repeat. Full sequences of all constructs are in Table S1. **P < 0.001 for trend, one way ANOVA, *p < 0.001 versus GFP, †p < 0.001 vs. (CGG)₈₈ +1GFP, t-Test.

Figure 4. A RAN translation product is also produced in the alanine (GCG) frame

A) Schematic of (CGG)₈₈ +2 GFP construct. Green arrowhead indicates where an intervening stop codon was removed. Red arrowheads indicate introduced stop codons. B) Unconventional translation resulting in a discrete HMW-GFP species and aggregated protein in the stack is detected in the +2 (GCG, alanine-encoding) frame when an intervening stop codon is removed. C) No GFP inclusions are observed in +2 (Ala) constructs even when the intervening stop codon is removed. D) HMW polyalanine product is absent with shorter CGG repeats. E) In +2 frame constructs, introduction of a stop codon at −8bp (in the +2 frame) does not eliminate the RAN translation product. A stop codon at −6bp (in the +1 frame) reduces but does not eliminate HMW GFP. F) 3 hr digestion of GFP immunoprecipitates with Lysostaphin eliminates the HMW species in the +1 (Gly) frame but not in the +2 (Ala) frame.

Figure 5. The predicted polyglycine protein is present in FXTAS patient brains

A) Read coverage map of FMR1 locus derived from a published ribosomal profiling dataset in HEK-293 cells (Ingolia et al., 2012). Numbers along the X axis represent position within the genome. Y axis represents number of sequence reads at each position. Black bars represent exons, intervening sequences are introns, and blue boxed sequences represent 5’UTR (left) and 3’UTR (right). Red box indicates the region shown at higher resolution in the lower panel, which includes the FMR1 5’UTR and first exon. Green and red asterisks indicate position of possible near AUG initiation codons iGUG (12bp proximal to repeat) and iCTG (24bp proximal to repeat), respectively. Note significant reads over region 5’ proximal to the CGG repeat sequence. B) Predicted sequence of human FMRpolyG protein with 90 glycines. Underlined regions represent peptides used to generate 2J7 and 605 antibodies. Polyglycine sequence is indicated by red box. C) GST and 2J7 antibody staining of recombinant purified GST-HIS-FMRpolyG₃₀ protein. D) Expression of an FLAG (CGG)₅₅ FMRpolyG construct in COS cells stained with 2J7 and re-probed with anti-FLAG antibody and Tubulin. The protein runs higher than expected based on predicted size. NTC = no template control. E) Immunofluorescence with FLAG (green) and 2J7 (red) in COS cells expressing FLAG-FMRpolyG₅₅. F) Co-immunofluorescence of GFP and 2J7 signal in COS cells expressing FMRpolyG₁₀₀ GFP (left panels) or Q₈₀ GFP (right panels). G) Western blot with 2J7 of cerebellar lysates from 2 FXTAS patients and an age-matched control. Arrow indicates bands seen in FXTAS but not control samples. H) Representative images of 2J7 immunostaining from frontal cortex (CTX) and hippocampus (Hipp) of control and FXTAS brain. I) Co-immunofluorescence with 2J7 (green) and anti-ubiquitin (red) in FXTAS hippocampus (top two panels) or cortex (3^rd panel) from three different FXTAS subjects. In contrast, ubiquitinated inclusions in the pons of a patient with the polyglutamine disorder SCA-3 do not co-stain with 2J7. J) GST and rabbit polyclonal Ab605 staining of recombinant FMRpolyG protein. Arrow indicates band recognized by GST and Ab605. K) Representative images of Ab605 immunostaining of frontal cortex (CTX) and cerebellum from control and FXTAS brain. Unless otherwise noted, scale bars represent 50 microns.

Figure 6. Sequence differences 5’ of the repeat explain divergent inclusion formation in two murine knock-in models of FXTAS

A) Sequence differences in two established CGG knock-in models of FXTAS highlighting a stop codon 18 bp before the repeat present only in the NIH mouse. B) Placement of the NIH mouse sequence, but not the Dutch sequence, just 5’ to the repeat eliminates the HMW GFP species in the +1 (Gly) frame. C) Representative images (original magnification 400x, inset 1000x) of hypothalamus from 18 month old NIH and Dutch knock-in mice stained with antibody to ubiquitin. D) Quantification of ubiquitin-positive inclusions in 18 month old NIH and Dutch mice in the specified brain regions. E) Relative expression of fmr1 mRNA in WT, NIH, and Dutch mice at 6 months of age (n = 4/genotype). F) Representative images of hypothalamus from 18 month old NIH and Dutch knock-in mice stained with Ab605 against FMRpolyG. G) Quantification of 605-positive inclusions in 18 month old NIH and Dutch mice in the specified brain regions. H) Confocal microscopy in the Dutch knock-in mice showing co-localization of ubiquitin and Ab605 staining inclusion in frontal cortex (left images). For D, n > 300 cells/brain region and > 1000 cells/genotype, *p > 0.01 on Pearson’s chi-squared test. Error bars represent 95% CI.

Figure 7. Production of polyglycine protein from CGG repeat RNA constructs correlates with toxicity in Drosophila models

A) COS cell viability 72 hrs after transfection of (from left to right) GFP alone, (CGG)₈₈ +1 (Gly) GFP, ATG-FLAG-(CGG)₈₈ +1 (Gly) GFP, or Stop^@-12(CGG)₉₄ +1 (Gly) GFP. * p < 0.05 vs. GFP alone; † p < 0.05 vs. (CGG)₈₈ GFP. B) Schematic of pUAST constructs used to generate fly lines with differing amounts of polyglycine protein production but identical (CGG) repeat RNA expansions. Full sequences are shown in Table S2. Boxed red X = stop codon, green = GFP, Red = CGG repeat, blue = other sequence. Yellow = epitope tag (Flag or 6xHis tag). C) Placing the CGG repeat in the 3’UTR of GFP eliminates the RAN translation product. COS cells were transiently transfected with either GFP (– control), ATG-FLAG-(CGG)₈₈ +1 GFP (+ control) or GFP-STOP-(CGG)₈₈-FLAG and total lysates were harvested. Blots were serially probed with antibodies to FLAG, GFP, and actin. D) Lysates from Drosophila lines expressing the described constructs were probed with GFP or Tubulin. The higher MW of the ATG construct results from 150nt of intervening sequence between the start codon and the start of the (CGG)₁₀₀ repeat. E) GFP inclusion formation in Drosophila eye cross sections of the indicated genotypes. F) Representative images of eyes 1–2 days post eclosion with the indicated genotypes demonstrate differential toxicity across lines that is dependent on polyglycine translation. G) Quantification of the rough eye phenotypes associated with the indicated genotypes demonstrates significantly enhanced toxicity in lines with enhanced polyglycine translation and impaired toxicity in lines where CGG RAN translation is blocked. H) Ubiquitous expression of CGG GFP transgenes in the 5’UTR decreases fly viability as measured by progeny eclosion ratios. This change in viability is blocked in CGG 5’stop lines and CGG 3’UTR lines but the constructs are more toxic in ATG-CGG GFP lines where polyglycine protein production is enhanced. For G and H, * p < 0.05 vs. 3’UTR or GFP; † p < 0.05 vs. 5’UTR.

Figure 8. Model for CGG RAN translation in fragile X-associated tremor ataxia syndrome

Ribosomes assemble on the 5’ end of the FMR1 message and scan the mRNA for an appropriate initiation sequence. Near the CGG repeat hairpin, the 43S preinitiaton complex (red) stalls, triggering RAN translational initiation. Once translation initiates, the ribosome reads through the repeat to produce a polyglycine-containing protein. Normally, this peptide is readily cleared from cells, but with larger repeats the resultant expanded polyglycine protein accumulates in inclusions. The downstream AUG start site for FMRP is not in frame with the polyglycine protein, thus no N-terminal addition onto FMRP occurs with this CGG RAN translation. Trailing ribosomes (green) may not stall at the hairpin but instead initiate translation normally at the AUG for FMRP.