Cell-type-specific expression of tRNAs in the brain regulates cellular homeostasis

Abstract

Defects in tRNA biogenesis are associated with multiple neurological disorders, yet our understanding of these diseases has been hampered by an inability to determine tRNA expression in individual cell types within a complex tissue. Here, we developed a mouse model in which RNA polymerase III is conditionally epitope tagged in a Cre-dependent manner, allowing us to accurately profile tRNA expression in any cell type in vivo. We investigated tRNA expression in diverse nervous system cell types, revealing dramatic heterogeneity in the expression of tRNA genes between populations. We found that while maintenance of levels of tRNA isoacceptor families is critical for cellular homeostasis, neurons are differentially vulnerable to insults to distinct tRNA isoacceptor families. Cell-type-specific translatome analysis suggests that the balance between tRNA availability and codon demand may underlie such differential resilience. Our work provides a platform for investigating the complexities of mRNA translation and tRNA biology in the brain.

Keywords: ChIP; Gtpbp2; arginine; cerebellum; isodecoder; isoleucine; neurodegeneration.

Figure 1.. Epitope-tagged POLR3A can accurately profile tRNA expression in vivo

(A) Sequences of the mouse tRNA^Ile(TAT) genes with the anticodon (blue), introns (lowercase), and the SNP in tRNA-Ile-TAT-1–1 (red) highlighted. The northern probes for pre-tRNAs and for mature tRNA sequences are indicated by orange and pink lines, respectively. (B) Northern blots of tRNA^Ile(TAT) isodecoders using pre-tRNA probes in adult mouse tissues (left) and developing mouse brain (E9.5: whole head) (right). Loading control: 5S rRNA. Exposure time is optimized to detect signal from at least one tissue/age, and the relative expression of different genes cannot be compared. (C) Western blot of Sox2-Cre-mediated incorporation of the 3x-FLAG tag in POLR3A. Loading control: vinculin. (D) POLR3A-FLAG occupancy peak score distribution in mouse liver separated by gene annotation. Each point is a detected peak. (E) Representative ChIP-seq peaks for Pol III-bound loci at tRNA^Arg(TCT) and tRNA^Ile(TAT) gene families. Biological replicates are shown. See also Figure S1 and Table S1.

Figure 2.. A comprehensive atlas reveals remarkable variation in tRNA expression across distinct cell types in the nervous system

(A) Principal-component analysis (PCA) of tRNA expression in nervous system cell types and liver. Two biological replicates for each cell type and 95% confidence ellipses for neuronal (blue) and non-neuronal (pink) cells are shown. (B) Heatmap of the Z scores of tRNA gene expression. Columns are clustered based on Euclidean distance. N1, group 1 neurons; N2, group 2 neurons; NN, non-neuronal cells. (C) Scatterplot representing the relative contribution of each tRNA gene to the global tRNA pool. (D) Frequency distribution of relative contributions of all expressed tRNA genes to the global tRNA pool in group 1 neurons (N1), group 2 neurons (N2), and non-neuronal cells (NN). One-way ANOVA with Tukey post-test. *p s≤ 0.05, **p ≤ 0.01, ***p ≤ 0.001, ****p ≤ 0.0001, mean + SEM. (E) Differentially expressed tRNA genes between group 1 and group 2 neurons. tRNA genes with significantly altered expression are highlighted in red. Genes with |log₂FoldChange| > 3 are labeled with the gene name. Horizontal line: q value = 0.05, vertical lines: log₂FoldChange = 0.5 and −0.5. (F) Frequency distribution of the relative contributions of tRNA genes to the global tRNA pool. All tRNAs (gray), upregulated (red), downregulated (blue). See also Figure S2 and Tables S2 and S3.

Figure 3.. The tRNA repertoire in neuronal cells differs from that expressed in non-neuronal cells

(A) Differentially expressed tRNA genes between neuronal and non-neuronal cells. Select tRNA genes with significantly altered expression are highlighted in the indicated colors. Horizontal line: q value = 0.05, vertical lines: log₂FoldChange = 0.5 and −0.5. (B) Heatmap of expression Z scores of tRNAs that are differentially expressed (q value ≤ 0.05 and |log₂FoldChange| ≥ 0.5) between neuronal and non-neuronal cells, but not between group 1 and group 2 neurons. Columns are clustered based on Euclidean distance. tRNA^Arg(TCT) and tRNA^Ile(TAT) genes are labeled in bold. (C) Expression of tRNA^Arg(TCT) and tRNA^Ile(TAT) genes (mean + SEM). Differentially expressed genes between neurons and non-neuronal cells are bolded and labeled with an asterisk. See also Figures S3 and S4 and Table S3.

Figure 4.. Differential expression of tRNA isoacceptor and isotype families in neuronal and non-neuronal cells in the nervous system

(A) Principal-component analysis (PCA) of tRNA isoacceptor expression. Two biological replicates for each cell type and 95% confidence ellipses for neuronal (blue) and non-neuronal (pink) cells are shown. (B) Differentially expressed tRNA isoacceptor families between neuronal (except cerebellar granule cells) and non-neuronal cells in the nervous system. Horizontal dashed line: q value = 0.05. Vertical dashed lines: log₂FoldChange = 0.5 and −0.5. tRNA families with |log₂FoldChange| > 0.5 are red, while tRNA families with |log₂FoldChange| < 0.5 are blue. (C) Heatmap of Z scores for expression of tRNA isoacceptor families that are differentially expressed (q value ≤ 0.05 and |log₂FoldChange| > 0.5) between neuronal and non-neuronal cells. (D) Heatmap of the Z scores for expression of tRNA isoacceptor families for which cerebellar granule cell expression deviates from that of non-neuronal cells. See also Figure S5.

Figure 5.. Differential isoacceptor family abundance partially correlates with cognate codon usage in cell-type-specific genes

(A) Principal-component analysis (PCA) of translatome codon usage. Three biological replicates and 95% confidence ellipses are shown for each cell type. (B) Pearson correlation of codon use in the astrocyte and layer V cortical neuron translatome (blue) and in cell-type-specific genes that are differentially expressed at least 50-fold between the two cell types (red). (C–E) Heatmaps of Z scores for codon usage in the (C) cortical neuron-specific translatome (relative to astrocytes), (D) the astrocyte-specific translatome (relative to cortical neurons), and (E) the cerebellar granule cell-specific translatome (relative to cortical neurons). Bins in which the codon usage was significantly different than expected based on random sampling of the translatome are labeled with an asterisk. The number of transcripts in each bin is indicated. See also Figure S6 and Table S4.

Figure 6.. Multigene tRNA families fail to efficiently compensate for genetic mutations

(A–D) Northern blots for expression of tRNA^Arg(TCT) isodecoders in the cerebellum of tRNA-Arg-TCT-4–1 and tRNA-Arg-TCT-1–1 knockout mice compared to congenic B6J control mice in which the wild-type tRNA-Arg-TCT-4–1 gene was transferred from B6N (B6J.N). (E–H) Northern blots for expression of tRNA^Arg(TCT) isodecoders in the cortex of transgenic mice overexpressing either tRNA-Arg-TCT-3–1 or tRNA-Arg-TCT-1–1 compared to C57BL/6J (B6J) controls. (A-H) Bands were normalized to 5S rRNA (loading control) and quantified relative to respective controls. Mean ± SEM. One-way ANOVA with Tukey post-test *p ≤ 0.05, **p ≤ 0.01, ***p ≤ 0.001, ****p ≤ 0.0001. See also Figure S7.

Figure 7.. Differences in codon use may underlie the resilience of cerebellar granule cells to depletion of the tRNA^Ile(TAT) family relative to the tRNA^Arg(TCT) family

(A) Northern blots of the expression of tRNA^Ile(TAT) genes and the tRNA^Ile(TAT) pool in the cerebellum of B6J.N mice (wild-type, +/+), tRNA-Ile-TAT-1–1^−/− mice (1–1^−/−), tRNA-Ile-TAT-2–3^−/− mice (2–3^−/−), and compound mutants homozygous for loss of one of these tRNAs and heterozygous for another (1–1^−/−, 2–3^+/− and 1–1^+/−, 2–3^−/−). Loading control: 5S rRNA. Black arrowheads indicate the precursor or immature tRNA bands, and an asterisk marks the truncated transcript produced from the mutant tRNA-Ile-TAT-1–1 locus. (B–D) tRNA levels are quantified relative to wild-type (B6J.N) mice. Data are represented as mean + SEM. (E and F) Depletion of the tRNA^Ile(TAT) pool in the context of Gtpbp2 loss causes cerebellar granule cell degeneration. (E) Hematoxylin and eosin-stained (H&E) sagittal sections of cerebella from 12-week-old mice except Gtpbp2^−/−; tRNA-Arg-TCT-4–1^B6J/B6J (Gtpbp2^−/−, n-Tr20 ^J/J), which is shown at 8 weeks. Lower panels are higher-magnification images of lobule III (black rectangle in wild-type). Scale bars, 1 mm (top panel), 50 μm (bottom panel). Cerebellar lobules are indicated by Roman numerals. (F) Quantification (mean + SEM) of cerebellar granule cells in lobule III of the indicated genotypes. (G) Ratio of the relative tRNA isoacceptor family levels to the expression-weighted usage of the cognate codon in the translatome. (B–D and F) One-way ANOVA with Tukey post-test. *p ≤ 0.05, **p ≤ 0.01, ***p ≤ 0.001, ****p ≤ 0.0001. See also Figure S8.