ALS-associated genes in SCA2 mouse spinal cord transcriptomes

Abstract

The spinocerebellar ataxia type 2 (SCA2) gene ATXN2 has a prominent role in the pathogenesis and treatment of amyotrophic lateral sclerosis (ALS). In addition to cerebellar ataxia, motor neuron disease is often seen in SCA2, and ATXN2 CAG repeat expansions in the long normal range increase ALS risk. Also, lowering ATXN2 expression in TDP-43 ALS mice prolongs their survival. Here we investigated the ATXN2 relationship with motor neuron dysfunction in vivo by comparing spinal cord (SC) transcriptomes reported from TDP-43 and SOD1 ALS mice and ALS patients with those from SCA2 mice. SC transcriptomes were determined using an SCA2 bacterial artificial chromosome mouse model expressing polyglutamine expanded ATXN2. SCA2 cerebellar transcriptomes were also determined, and we also investigated the modification of gene expression following treatment of SCA2 mice with an antisense oligonucleotide (ASO) lowering ATXN2 expression. Differentially expressed genes (DEGs) defined three interconnected pathways (innate immunity, fatty acid biosynthesis and cholesterol biosynthesis) in separate modules identified by weighted gene co-expression network analysis. Other key pathways included the complement system and lysosome/phagosome pathways. Of all DEGs in SC, 12.6% were also dysregulated in the cerebellum. Treatment of mice with an ATXN2 ASO also modified innate immunity, the complement system and lysosome/phagosome pathways. This study provides new insights into the underlying molecular basis of SCA2 SC phenotypes and demonstrates annotated pathways shared with TDP-43 and SOD1 ALS mice and ALS patients. It also emphasizes the importance of ATXN2 in motor neuron degeneration and confirms ATXN2 as a therapeutic target.

Figure 1

BAC-Q72 SC expression profiles and gene co-expression modules for the pooled dataset. (A) Numbers of upregulated or downregulated DEGs in each group and in the pooled set of genes. (B) Number of shared DEGs for the untreated group (no surgery), early and late groups. Of all the DEGs in the untreated group, 64% were shared with the combined set of early and late group DEGs, and of all the early and late group DEGs, 32.7% were shared. (C) Identification of co-expression modules. Dynamic tree cut analysis gave rise to 18 modules. (D) GS per module. The lightgreen, midnightblue and yellow modules were significant (^*,P < 0.05; ^**, P < 0.01). (EG) Topological representations of the co-expression networks for the significant modules. The top 40–48 hub genes are shown. Bubble size is proportional to the number of connections. Arrows indicate the top hub gene in each module.

Figure 2

Validation of expression between BAC-Q72 mice and wild-type littermates for the top 2–4 hub genes identified in the lightgreen (A), midnightblue (B) and yellow (C) modules and selected other DEGs determined by qPCR. (D) Validation for Pcp4, an ALS-related gene, which was not assigned to a module by WGCNA. Values shown are means and SD. All individual wild-type versus BAC-Q72 comparisons were significant at P < 0.01. n = 5 and 3 mice for the wild-type and BAC-Q72 groups, respectively (A). n = 5 and 3 mice for all wild-type and BAC-Q72 groups, respectively, except for Ddx58 for which n = 6 mice per group (B). n = 6 mice per group (C and D). Probabilities were determined from unpaired two-tailed Student’s t-tests: ^**, P < 0.01; ^***, P < 0.001.

Figure 3

ASO7 uptake and reduction of ATXN2 in SCA2 mouse SC. (A and B) Validation of ASO7 inhibition of ATXN2 in SC of BAC-Q72 by qPCR for both the early (A) and late (B) groups. Values shown are means ± SD. (C and D) Anti-ASO antibody labeling in SCA2 mouse thoracic SC following ASO7 injection (C) and saline injection (D), determined by immunofluorescent labeling. Probabilities were determined from unpaired two-tailed Student’s t-tests between the BAC-Q72 saline groups and the BAC-Q72 ASO groups: ^***, P < 0.001.

Figure 4

Restoration of selected genes in SC of BAC-Q72 mice with ASO7 treatment. (A) Effect of ASO7 on Fyco1, C3 and Cyp51a1. Expression determined by qPCR relative to Gapdh. Reduced expression of C3 is significantly increased by ASO7, while increased expression of FycoI is significantly decreased by ASO7. Reduced Cyp51a1 expression was not improved by ASO7. (B) Effect of ASO7 on the expression of Eaat2 (Slc1a2), Pcp4, Ifih1, Trim30, p-Ampk, Sting, Cyp51a1, Tbk1, mTor, p62 and Lc3 determined by western blotting. (C) Densitometric quantifications of western blots (n = 3–5 mice). Bonferroni corrected Student’s t-tests. NS, not significant; ^*, P < 0.05; ^**, P < 0.01; ^***, P < 0.001.

Figure 5

Highly interconnected pathways altered in SCA2 mouse SC transcriptome converge at the ER. Regulation of the innate immunity pathway by STING and the cholesterol and fatty acid biosynthesis pathways by SREBP is dependent on INSIG1 and polyubiquitination by AMFR anchoring STING to the ER membrane. Innate immunity can be activated by dsRNAs produced by ER stress and activation of the RIDD pathway or DNAs from damaged mitochondria. STING activation can directly modify LC3 and can activate TBK1, p62 and mTOR to regulate autophagy. INSIG1 anchors SCAP and SREBP to the ER when sterols are abundant. When sterols are low, SCAP and SERBP translocate to the Golgi via COPII vesicles in a PASK-dependent manner where SREBP is processed and then its bHLH domain fragment is translocated to the nucleus to activate cholesterol and fatty acid biosynthesis genes. Among these are HMG-CoA reductase which catalyzes the rate limiting step in cholesterol biosynthesis, is the target of statins and is inhibited by AMFR polyubiquitination. We also observed genes activating LXR pathways reduced in SCA2 mouse SC transcriptomes. Finally, Ampk is activated in SCA2 mouse SC, which inhibits SREBP and activates STING. Green represents genes downregulated and red upregulated in SCA2. Asterisks indicate upregulated proteins from nonsignificant DEGs.