Dysregulation of RNA Splicing in Tauopathies

Abstract

Pathological aggregation of RNA binding proteins (RBPs) is associated with dysregulation of RNA splicing in PS19 P301S tau transgenic mice and in Alzheimer's disease brain tissues. The dysregulated splicing particularly affects genes involved in synaptic transmission. The effects of neuroprotective TIA1 reduction on PS19 mice are also examined. TIA1 reduction reduces disease-linked alternative splicing events for the major synaptic mRNA transcripts examined, suggesting that normalization of RBP functions is associated with the neuroprotection. Use of the NetDecoder informatics algorithm identifies key upstream biological targets, including MYC and EGFR, underlying the transcriptional and splicing changes in the protected compared to tauopathy mice. Pharmacological inhibition of MYC and EGFR activity in neuronal cultures tau recapitulates the neuroprotective effects of TIA1 reduction. These results demonstrate that dysfunction of RBPs and RNA splicing processes are major elements of the pathophysiology of tauopathies, as well as potential therapeutic targets for tauopathies.

Keywords: EGFR; MYC; NetDecoder; RNA metabolism; RNA splicing; RNA-seq; TIA1; neuroprotection; stress granule; tauopathy; transcriptome.

Figure 1.. Transcripts Encoding Spliceosomal Complex and mRNA Binding Proteins Are Downregulated in PS19 Brain

(A) Top 10 most statistically significant BioCarta reactome pathways enriched in the gene list of mRNA transcripts downregulated (Fisher’s adjusted p value < 0.05) in 9-month PS19 compared to WT cortex tissue, as determined by GSEA. Red asterisks denote annotation terms related to mRNA splicing or mRNA processing. (B) Heatmap of mRNA expression levels of transcripts encoding RNA binding proteins (RBPs) in the RNA-seq of PS19 compared to WT cortex. RBPs were defined by inclusion of the GO molecular function annotation ‘‘RNA-binding.’’ Note that 30 of the 37 RBPs identified were decreased in PS19 compared to the WT samples. Blue to red color scale denotes negative to positive Z scores (color key, left). (C) Volcano plot for repetitive elements in 6 months in PS19 Tia1^+/+ compared to WT mouse cortex. p values (y axis) are plotted against the log2-transformed fold change (x axis) in the level of each repetitive element transcript. No elements showed statistically significant changes.

Figure 2.. mRNA Transcripts Encoding Synaptic Proteins Are Alternatively Spliced in PS19 Brain

(A) For PS19 versus WT frontal cortex, top 10 most statistically significant Gene Ontology (GO) biological process annotation terms enriched (FDR < 0.05) in the gene list of mRNA transcripts exhibiting significant changes in splicing, as determined by OLego and Quantas splice variant analysis. (B) Top 20 most statistically significant individual splice variants in PS19 compared to WT cortex. Note that 11 of the top 20 alternatively spliced transcripts encode proteins with known functional roles at the synapse (bold). Note that some genes appear on the list multiple times because a change in mutually exclusive exons will also be recorded as a significant cassette (exon skipping) event, etc. Please refer to Tables S3 and S6 for the complete list of alternative splicing results. (C) Hierarchically clustered heatmap of exon inclusion indices for alternatively spliced cassette exons in RNA-seq of 9-month PS19 Tia1^+/+, PS19 Tia1^+/−, Tia1^+/−, and WT cortex. Inclusion indices for statistically significant (FDR < 0.1) cassette exon alternative splicing (AS) events were calculated by dividing the number of reads including a given exon where an inclusion/skip occurs by the total number of reads for that transcript. Z-transformed inclusion indices were then plotted in a heatmap to visualize changes in exon inclusion between genotypes. Genes were hierarchically clustered according to GO analysis (box inset, below). Note that Tia1 reduction in PS19 mice (P301S tau Tia1^+/−, green) returns the majority of transgenic tau-induced changes in PS19 mice (P301S Tau Tia1^+/+, red) toward WT levels, particularly in the nervous system development (light green), presynaptic process (dark red), and synaptic signaling (orange) GO clusters. Blue to red color scale denotes negative to positive Z scores (color key, right).

Figure 3.. TIA1 Reduction Rescues Dysfunctional Splicing of Synaptic mRNAs in PS19 Brain

Relative exon inclusion for statistically significant (FDR < 0.05) alternative splicing events in PS19 (P301S Tia1^+/+) compared to WT cortex was confirmed for Gria2 (A), Snap25 (B), and Camk2b (C) by real-time PCR. Left panels depict exon structure and forward (F) and reverse (R) primer design for each transcript. Ratios of exon inclusion were quantified by calculating the relative expression of each splice isoform compared to a housekeeping transcript (∆DCt Gapdh), normalizing each splice isoform to the total transcript level for each gene, and dividing the relative expression of isoform 1 to isoform 2. All ratios were then normalized to WT ratio = 1; thus, the quantification in the graphs to the right represent relative (and not absolute) changes in the ratio of splice isoforms. *p < 0.05, **p = 0.0025, and ***p < 0.0001 by two-way ANOVA with Tukey’s post hoc comparisons. Error bars denote means ± SEM (n = technical duplicates of 6 mice/group; 3 males and 3 females per genotype).

Figure 4.. TIA1 Regulates the Expression of Sexually Dimorphic Genes

(A) For human frontal cortex, top 10 most statistically significant Gene Ontology (GO) biological process annotation terms enriched (FDR < 0.05) in the gene list of mRNA transcripts exhibiting significant changes in splicing, as determined by OLego and Quantas splice variant analysis. (B) Venn diagrams highlighting the 20 genes are shared in common (at FDR < 0.05) between transcripts differentially spliced in the Alzheimer disease (AD) and PS19 mice. The right panel lists the 20 genes exhibiting overlap.

Figure 5.. Disease Phenotype in Neuroprotected PS19 Mice Is Regulated by a Prioritized Biological Network

NetDecoder analysis was performed on the RNA-seq data from 9-month PS19 Tia1^+/+ and P301S Tia1^+/− cortex in order to identify context-dependent changes inherent to the disease phenotype, as described previously (da Rocha et al., 2016). (A) Prioritized network consisting of biological pathways predicted to regulate the differences in phenotype between P301S Tia1^+/− (protected) and PS19 Tia1^+/+ (tauopathy) mice. Red and blue nodes denote proteins exhibiting either increased (red) or decreased (blue) information flow in P301S Tia1^+/− compared to PS19 Tia1^+/+ cortex. Arrows denote direction of information flow from source genes to target genes based on known protein-protein interaction (PPI) data. Network routers (diamonds) are upstream of intermediary (circles) and target (square) protein nodes. (B–D) Key genes (B), network routers (C), and key targets (D) identified by NetDecoder analysis to mediate context-dependent disease phenotype. (E) Selected protein-protein interactions (edges) showing differences in information flows between Tia1^+/− and Tia1^+/+ contexts.

Figure 6.. Inhibition of MYC and EGFR Protects against Tau-Mediated Toxicity

DIV14 cultures of hippocampal mouse neurons (C57BL/6J) transduced with AAV2 WT human 1N4R tau were treated with inhibitor for 1 h, then arsenite (125 µM) was added, and assayed for viability after 12 h. (A–C) (A) MYC inhibitor (10058-F4, 5 µM), (B) EGFR (TAG1478, 5 µM), and (C) UBE2I inhibitor (2-D08, 5 µM). **p < 0.0001, n = 4–8. (D and E) SH-SY5Y cells were pre-treated with MYC inhibitor (10058-F4, 1, 10 µM), EGFR (TAG1478, 1, 10 µM), and UBE2I inhibitor (2-D08, 1, 10 µM), then exposed to arsenite, fixed, and labeled with anti-TIA1 antibody. Representative images (D) and quantification of TIA1 immunofluorescence levels (E) are shown. Each of the inhibitors prevented arsenite-induced increases in TIA1 levels (E).