Transgenic mice for in vivo epigenome editing with CRISPR-based systems

Abstract

CRISPR-Cas9 technologies have dramatically increased the ease of targeting DNA sequences in the genomes of living systems. The fusion of chromatin-modifying domains to nuclease-deactivated Cas9 (dCas9) has enabled targeted epigenome editing in both cultured cells and animal models. However, delivering large dCas9 fusion proteins to target cells and tissues is an obstacle to the widespread adoption of these tools for in vivo studies. Here, we describe the generation and characterization of two conditional transgenic mouse lines for epigenome editing, Rosa26:LSL-dCas9-p300 for gene activation and Rosa26:LSL-dCas9-KRAB for gene repression. By targeting the guide RNAs to transcriptional start sites or distal enhancer elements, we demonstrate regulation of target genes and corresponding changes to epigenetic states and downstream phenotypes in the brain and liver in vivo, and in T cells and fibroblasts ex vivo. These mouse lines are convenient and valuable tools for facile, temporally controlled, and tissue-restricted epigenome editing and manipulation of gene expression in vivo.

Figure 1:. AAV-based gRNA and Cre recombinase delivery to Rosa26:LSL-dCas9^p300 mice activates Pdx1 gene expression and catalyzes targeted histone acetylation.

A) Schematic of Rosa26:LSL-dCas9p300 (dCas9^p300) knock-in locus. B) Experimental design for in vivo Pdx1 activation. C) Pdx1 mRNA quantification 8 weeks post-injection in liver tissue lysates isolated from mice injected with phosphate-buffered saline (PBS), or AAV9 encoding Cre and either a control non-targeting or Pdx1-targeting gRNA (n=4 per group, Kruskal-Wallis one-way ANOVA with Dunnett’s post-hoc, *p=0.0132). D) PDX1 immunostaining of liver tissue sections at 14 days post-injection of mice treated with control and Pdx1-targeted gRNAs. Scale bar = 50 μm E) Quantification of PDX1+ nuclei in control gRNA and Pdx1 gRNA treated animals (7.0% vs 0.03%, p=0.019, students t-test, n = 3 animals, with 3 images counted per animal). F) Representative browser tracks of dCas9 and H2K27ac ChIP-Seq data from treated livers at 2 weeks post-treatment (replicates are presented in Figures S3 and S4). G) dCas9 ChIP-seq quantification of sequencing counts (CPM = counts per million) in the gRNA target region of Pdx1 in samples from mice treated with Pdx1-targeted gRNA, control gRNA, or PBS (n = 4, one-way ANOVA with Dunnett’s post-hoc, p=0.059). H) RNA-seq and Pdx1 ChIP-seq analyses showing the relationship between changes in gene expression and occupancy of Cas9 genome-wide. Log₂(fold-change) was calculated using the ratio of read counts between samples treated with the Pdx1-targeted gRNA relative to control non-targeting gRNA in dCas9^p300 cells (n = 4, FDR < 0.05). I) H3K27ac ChIP-seq quantification of sequencing counts within a 1 kb window centered on the gRNA target site near the TSS of Pdx1 in samples from mice treated with the Pdx1-targeted gRNA, control gRNA, or PBS (n = 4, two-tailed student’s t-test, p = 0.07). J) RNA-seq and H3K27ac ChIP-seq analysis showing the relationship between changes in gene expression and genome-wide H3K27 acetylation for samples from mice treated with the Pdx1-targeted gRNA and control gRNA, (n = 4, FDR < 0.05, DEG = differentially expressed gene, orange dot; Diff. ChIP = differentially enriched ChIP-seq signal, blue dot; DEG and Diff. ChIP = differentially expressed gene and ChIP-seq enrichment, red dot). All bar-plot error bars represent standard deviation, all boxplots are drawn from 25^th to 75^th percentile with the horizontal bar at the mean and whiskers extending to the minima and maxima

Figure 2:. Epigenomic enhancement of Fos in vivo increases excitability in CA1 neurons.

A) Contralateral AAV injection strategy for comparison of targeting and non-targeting control gRNAs. AAV:Syn1-Cre.gRNA was injected into in the hippocampus of dCas9^p300 mice. A gRNA targeting LacZ was used as control for the gRNA targeting Fos enh2. B) Immunoflourescence imaging of neurons in the dendate gyrus region of the hippocampus after transduction with AAV containing LacZ control-gRNA or Fos Enh2-gRNA and stimulation with novel objects. (AAV-gRNA+ neurons (green), FOS+ neurons (red). scale bar = 20 μm). C) Quantification of those FOS+ neurons in (B). The lines connect measurements from the two sides of the same mouse. Counts of FOS+ cells in tissue slices from n=6 paired ROIs per condition from 3 animals. p = 0.002 by student’s paired two-sided t-test. D) Representative current clamp traces from acute hippocampal slices. Virally-expressed GFP was used to identify CA1 neurons for recording. E) Summary of input/output. For current F(10,240) = 31.12, p < 0.0001, virus F(1,24) = 1.05, p = 0.32 and current x virus interaction F(10,240) = 4.64, p < 0.0001. For Fos Enh2 vs LacZ control at 350 pA p = 0.016, at 400 pA p = 0.031, at 450 pA p = 0.012, and at 500 pA p = 0.026 (two-way repeated measures ANOVA with post-hoc Fisher’s LSD test; * denotes p < 0.05.) F) Rheobase, minimal current to spike. G) Latency to first spike (p = 0.018). H) Input resistance (p = 0.092). I) Membrane time constant (p = 0.091). n=12 LacZ, n=14 Fos Enh2, each from 2 animals (For F-I, two-tailed students t-test; horizontal bars show mean; error bars show SEM).

Figure 3:. AAV-based gRNA and Cre recombinase delivery to Rosa26:LSL-dCas9^KRAB mice represses Pcsk9 and catalyzes targeted histone methylation.

A) Schematic of Rosa26:LSL-dCas9KRAB (dCas9^KRAB) knock-in locus. B) Schematic of the experimental design to test Pcsk9 repression in the dCas9^KRAB mice. C) Pcsk9 mRNA quantification 8 weeks post injection in liver tissue lysates isolated from mice injected with phosphate-buffered saline (PBS), or AAV9 encoding Cre and either a control non-targeting or Pcsk9-targeting gRNA (n = 4 per group, one-way ANOVA with Dunnett’s post-hoc, *p = 0.0021) D) PCSK9 serum protein levels at 4 weeks post injection of PBS or AAV9 encoding Cre and either a control non-targeting or Pcsk9-targeting gRNA (n = 4 per group, one-way ANOVA with Dunnett’s post-hoc, * p=0.0001). E) LDL cholesterol levels in the serum at 8 weeks following administration of PBS, or AAV9:Cbh.Cre containing either a control non-targeting or Pcsk9-targeting gRNA (N=4 per group, two-way ANOVA with Tukey’s, * denotes p<0.0001). F) Representative browser tracks of dCas9^KRAB (FLAG epitope) and H3K9me3 ChIP-Seq data from liver samples at 8 weeks post treatment (replicates are presented in Figures S10 and S11). Highlighted region corresponds to the area surrounding the gRNA target site in the Pcsk9 promoter. G) dCas9-FLAG ChIP-seq quantification of sequencing counts (CPM = counts per million) in the Pcsk9 promoter in samples treated with Pcsk9-targeted gRNA (n = 4), control non-targeting gRNA (n = 3), or PBS (n = 4) (one-way ANOVA with Dunnett’s post-hoc, p < 0.05.). H) Log₂(fold-change) of RNA-seq and FLAG ChIP-seq signal comparing read counts in peaks between samples treated with Pcsk9-targeted gRNA (n = 4) and control non-targeting gRNA (n = 3) showing the relationship between gene expression and genome-wide dCas9^KRAB binding. (Diff. ChIP = differentially enriched ChIP-seq signal, blue; DEG and Diff. ChIP = differentially expressed gene and ChIP-seq enrichment, red; FDR < 0.05. I) H3K9me3 ChIP-seq quantification of sequencing counts (CPM = counts per million) in the Pcsk9 promoter in samples treated with Pcsk9-targeted gRNA (n = 4), control non-targeting gRNA (n = 4), or PBS (n = 4) (one-way ANOVA with Dunnett’s post-hoc, p < 0.05.). J) Log₂(fold-change) of RNA-seq and H3K9me3 ChIP-seq signal comparing read counts in peaks for samples treated with the Pcsk9-targeting gRNA (n = 4) and control non-targeting gRNA (n = 4) (DEG = differentially expressed gene, orange; Diff. ChIP = differentially enriched ChIP-seq signal, blue; DEG and Diff. ChIP = differentially expressed gene and ChIP-seq enrichment, red; FDR < 0.05). All bar-plot error bars represent standard deviation, all boxplots are drawn from 25^th to 75^th percentile with the horizontal bar at the mean and whiskers extending to the minima and maxima

Figure 4:. Epigenome editing in T cells for activation and repression of Foxp3.

A) Flow cytometry analysis of FOXP3-eGFP expression in CD4+ T cells purified from Rosa26:LSL-dCas9^p300;CD4:Cre;Foxp3:eGFP mice cultured in vitro under Th0 polarization conditions (rIL-2) after transduction with retrovirus encoding the cell surface marker Thy1.1, for tracking transduced cells, and either the Foxp3-gRNA (green) or control-gRNA (blue). Cells cultured in iTreg polarization conditions (rIL-2, hTGFβ1) were included as a positive control for Foxp3 expression (black). B) Summary data depicting the percentage of Thy1.1+ cells that were FOXP3-EGFP+ (p<0.0001; one-way ANOVA with Dunnett’s post-hoc, iTreg n = 3, control gRNA and Foxp3-gRNA n = 4). C) qRT-PCR measurement of Foxp3 mRNA levels in Th0 cells compared to cells treated with Foxp3-targeting gRNA (green), control non-targeting gRNA (blue), or no virus (black) (p = 0.0190, one-way ANOVA with Dunnett’s post-hoc, n = 3 per condition). D) Flow cytometry histograms showing proliferation of Cell Trace Violet (CTV)-labelled CD4⁺/FOXP3-eGFP⁻ conventional T cells (Tconv) after 72 hrs of in vitro co-culture with aCD3/aCD28 dynabeads and either FOXP3-eGFP+ iTreg cells (grey, n = 3), Th0 cells (black, n = 2), FACS-purified Thy1.1+/FOXP3-eGFP+ cells treated with Foxp3-gRNA (green, n = 3), or Thy1.1+ cells treated with control non-targeting gRNA (blue, n = 3). Tconv cells with no aCD3/aCD28 and rIL-7 served as a no activation control (dashed). E) Suppressive capacity of Tregs summarized as division index of Tconv (p < 0.0001 one-way ANOVA with Tukey’s post-hoc. F) Browser track of H3K27ac ChIP-seq read counts at the Foxp3 locus in Th0 cells from a Rosa26:LSL-dCas9^p300 mouse that was either Cd4:Cre+ or Cd4:Cre−. Cells were treated with retrovirus containing Foxp3-targeting or control non-targeting gRNA and Thy1.1 reporter. ChIP-seq was performed 72hrs after transduction on sort-purified Thy1.1+ cells (red = Cd4:Cre+ Foxp3-gRNA; yellow = Cd4:Cre+ control-gRNA; blue = Cd4:Cre− Foxp3-gRNA). G) Summary of H3K27ac ChIP-seq reads counts per million within the MACS2-called peak that intersects the Foxp3-gRNA target site for each genotype and gRNA treatment (green = Foxp3-gRNA treated Cd4:Cre+ Th0, blue = control-gRNA treated Cd4:Cre+ Th0; black = Foxp3-gRNA treated Cd4:Cre− Th0, n = 3 per condition). H) Scatter plot depicting log₂(fold-change) of gene expression and H3K27ac enrichment when comparing read counts from Cd4:Cre+ Rosa26:LSL-dCas9^p300 Th0 cells treated with Foxp3-gRNA to control-gRNA (FDR < 0.01; DEG = differentially expressed gene, orange dot; Diff. ChIP = differentially enriched ChIP-seq signal, blue dot; DEG and Diff. ChIP = differentially expressed gene and ChIP-seq enrichment, red dot) I) Flow cytometry analysis of FOXP3 expression in CD4+ T cells purified from Rosa26:LSL-dCas9^KRAB mice cultured in vitro under iTreg polarization conditions and transduced with retrovirus encoding the indicated gRNAs. J) Summary data showing the percentage of Thy1.1+ cells that were FOXP3-EGFP+ for each gRNA treatment (p < 0.0001, one-way ANOVA with Dunnett’s post-hoc, n = 3 per condition). K) qRT-PCR measurement of Foxp3 mRNA levels in iTreg cells treated without virus (black), control-gRNA (blue), or Foxp3-targeting gRNA (red) (p < 0.0135, one-way ANOVA with Dunnett’s post-hoc, n = 3 per condition). All bar-plot error bars represent standard deviation, all boxplots are drawn from 25^th to 75^th percentile with the horizontal bar at the mean and whiskers extending to the minima and maxima.