MeCP2-regulated miRNAs control early human neurogenesis through differential effects on ERK and AKT signaling

Abstract

Rett syndrome (RTT) is an X-linked, neurodevelopmental disorder caused primarily by mutations in the methyl-CpG-binding protein 2 (MECP2) gene, which encodes a multifunctional epigenetic regulator with known links to a wide spectrum of neuropsychiatric disorders. Although postnatal functions of MeCP2 have been thoroughly investigated, its role in prenatal brain development remains poorly understood. Given the well-established importance of microRNAs (miRNAs) in neurogenesis, we employed isogenic human RTT patient-derived induced pluripotent stem cell (iPSC) and MeCP2 short hairpin RNA knockdown approaches to identify novel MeCP2-regulated miRNAs enriched during early human neuronal development. Focusing on the most dysregulated miRNAs, we found miR-199 and miR-214 to be increased during early brain development and to differentially regulate extracellular signal-regulated kinase (ERK)/mitogen-activated protein kinase and protein kinase B (PKB/AKT) signaling. In parallel, we characterized the effects on human neurogenesis and neuronal differentiation brought about by MeCP2 deficiency using both monolayer and three-dimensional (cerebral organoid) patient-derived and MeCP2-deficient neuronal culture models. Inhibiting miR-199 or miR-214 expression in iPSC-derived neural progenitors deficient in MeCP2 restored AKT and ERK activation, respectively, and ameliorated the observed alterations in neuronal differentiation. Moreover, overexpression of miR-199 or miR-214 in the wild-type mouse embryonic brains was sufficient to disturb neurogenesis and neuronal migration in a similar manner to Mecp2 knockdown. Taken together, our data support a novel miRNA-mediated pathway downstream of MeCP2 that influences neurogenesis via interactions with central molecular hubs linked to autism spectrum disorders.

Figure 1. Mature miRNA profiling in RTT patient-derived NPs and neurons

(a) Top: methods of NP derivation and neuronal differentiation for each of the different iPSC-derived RTT patient and control lines. Bottom: Representative examples of immunofluorescence and staining showing markers of pluripotency (Alkaline Phosphatase, Nanog, OCT4) in patient/control-acquired iPSCs, as well as NP (Nestin) and neuronal markers (TBR1, MAP2, Tuj1). Scale bars: 100 μm. (b) Top: Schematic of human MeCP2 functional domains and location of mutations for the two RTT patients examined (RTT-Mut1, RTT-Mut2). Bottom: cDNA sequencing results verifying the presence of the two different RTT-related mutations. WT1,2 controls and RTT-WT2 isogenic controls are also shown. (c) Four-way Venn diagram showing the significantly altered miRNAs in RTT-Mut1 (relative to WT1) and RTT-Mut2 (relative to RTT-WT2) NPs and immature (~3week) neurons based on NanoString miRNA profiling. The numbers of altered miRNAs for each intersection between different groups are shown inside cirlces. The 12 miRNAs that are altered in all four conditions are highlighted in yellow and are shown below (d). (d) Table showing the fold changes (ratio) and q-values (see Supplementary Materials and Methods) of the 12 miRNAs that were altered in all four conditions. Their rank based on average expression (from highest to lowest) is also shown (Levels (rank)).

Figure 2. Increased miR-199 and miR-214 levels in patient- and shRNA-mediated models of RTT

(a) Validation of NanoString miRNA profiling results for upregulated miR-199/214 miRNAs using mature miRNA-specific qRT-PCR in patient-derived mutant (RTT-Mut1 and RTT-Mut2 – red bars) and control (WT1, WT2 in blue bars and RTT-WT2 in green bars) NPs. All values are shown as mean ± SEM relative to WT control ratios. Stars depict statistical significance based on two-tailed one sample t-test (WT1, RTT-Mut1) or ANOVA (WT2, RTT-Mut2, RTT-WT2) with Sidak’s multiple comparisons test (*p < 0.05, **p < 0.01, ***p < 0.001). Number of biological replicates (N): WT1 = 6, RTT-Mut1 = 6, WT2 = 8, RTT-mut2 = 8, RTT-WT2 = 5. (b) Quantification of miR-199/214 miRNA expression using mature miRNA-specific qRT-PCR in patient-derived mutant (RTT-Mut1 and RTT-Mut2 – red bars) and control (WT1, WT2 in blue bars and RTT-WT2 in green bars) three-week differentiated neurons. All values are shown as mean ± SEM relative to WT control ratios. Stars depict statistical significance based on Mann-Whitney test (WT1, RTT-Mut1) or ANOVA (WT2, RTT-Mut2, RTT-WT2) with Sidak’s multiple comparisons test (*p < 0.05, ***p < 0.001). N: WT1 = 6, RTT-Mut1 = 8, WT2 = 9, RTT-Mut2 = 8, RTT-WT2 = 5. (c) Mean ± SEM relative to RTT-WT2 miR-199 and miR-214 levels in RTT-WT2 (green bars) and RTT-Mut2 (red bars) 14 week differentiated neurons. Stars depict statistical significance based on two-tailed one sample t-test (*p < 0.05). N: RTT-mut2 and RTT-WT2 = 6 (2 techical replicates of 3 samples). (d) Mean ± SEM relative to control MeCP2 mRNA levels (normalized to 18S rRNA) in MeCP2 shRNA (shMeCP2 – red bar) and shRNA control (shControl – blue bar) expressing NPs and differentiated neurons. Stars depict statistical significance based on two-tailed one sample t-test (***p < 0.001). N: shControl-NPs = 5, shMeCP2-NPs = 5, shControl-Neurons = 6, shMeCP2-Neurons = 6. (e) Mean ± SEM relative to control miR-199 and miR-214 levels in MeCP2 shRNA (shMeCP2 – red bar) and control (shControl – blue bar) expressing NPs. Stars depict statistical significance based on two-tailed one sample t-test (**p < 0.01). N: shControl = 7, shMeCP2 = 7. (f) Mean ± SEM relative to shControl NP stage miR-199 and miR-214 levels in MeCP2 shRNA (shMeCP2 – red bar) and control (shControl – blue bar) expressing 7 week differentiated neurons. Dotted line shows miRNA levels of shControl NPs for comparison. Stars depict statistical significance based on two-tailed Student’s t-test (*p < 0.05). N: shControl = 5, shMeCP2 = 5. (g-h) Graphs showing mean ± SEM relative miR-199a-3p (g), miR-214 (h) in embryonic brain (E12.5), perinatal (P0), and postnatal (P28) brain from WT and Mecp2 mutant (MT) mice. All data are shown as relative to E12.5 WT ratios. Stars depict statistical significance based on two-tailed Mann-Whitney test (**p < 0.01). N: E12.5 WT = 16, E12.5 MT = 5, P0 WT = 5, P0 MT = 5, P28 WT = 5, P28 MT = 5. Small RNAs RNU44 and snoRNA202 were used as normalizers in all human and mouse miRNA qRT-PCRs, respectively.

Figure 3. Alterations in neurogenesis and neuronal differentiation in RTT patient-derived and MeCP2-deficient neurons

(a) Immunofluorescence for neuronal marker MAP2 in WT2, RTT-WT2, and RTT-Mut2 three-week differentiated neurons. MeCP2 immunostaining using a C-terminus antibody shows no expression in RTT-Mut2 neurons. (b) Graphs showing mean ± SEM relative to control MAP2 and DCX mRNA levels in the same three control and RTT patient-derived three-week neuronal samples. DNM2 mRNA is also shown as an example of non-altered mRNA expression. Stars depict statistical significance based on two tailed one sample t-test (*p < 0.05, **p < 0.01). N: RTT-Mut2 = 8, RTT-WT2 = 5. (c-d) BrdU labeling and MeCP2 staining (c) and BrdU quantification (d) in WT2, RTT-WT2, and RTT-Mut2 early born three-week neurons. Stars depict statistical significance based on ANOVA with Neuman Keuls test (***p < 0.001). N: WT2 = 7, RTT-mut2 = 8, RTT-WT2 = 6. (e) Immunofluorescence for neuronal marker MAP2 in MeCP2 shRNA (shMeCP2) and control (shControl) three week neurons. MeCP2 immunostaining shows no expression in shMeCP2 neurons. (f) Quantification of the number of primary, secondary, and tertiary neurites per cell reveals significant reductions in shMeCP2 cells (**p < 0.01, ***p < 0.001). N: shControl = 13, shMeCP2 = 13. (g) Graph showing mean ± SEM MAP2 and DCX mRNA relative expression following in MeCP2-shRNA and shControl three-week neurons. DNM2 mRNA is also shown as a control. N: shControl = 10, shMeCP2 = 10. (h) Graph showing mean ± SEM average neurite length in shMeCP2 vs shControl neuronal cultures (***p < 0.001). N: shControl = 12, shMeCP2 = 13. (i-j) BrdU labeling and MeCP2 staining (i) and BrdU quantification (j) in MeCP2-shRNA and shControl three-week neurons. N: shControl = 4, shMeCP2 = 3. Stars in (f),(h),(j) depict statistical significance based on two-tailed Student’s t-test (**p < 0.01, ***p < 0.001), and in (g) based on two-tailed one sample t-test (***p < 0.001). 18S rRNA was used as a normalizer for all mRNA qRT-PCRs.

Figure 4. Patient-derived and MeCP2-deficient 3D cerebral organoids reveal deficits in neurogenesis

(a) Representative DAPI immunofluorescence reveals structural differences (i.e., expanded ventricular zones) in RTT-Mut2 vs. RTT-WT2 patient-derived organoids differentiated for 5 weeks. Scale bar = 500 μm. (b) Quantification of ventricular zones as a percentage of overall DAPI content reveals a significant increase in the percentage of ventricular zones in RTT-Mut2 organoids (n = 6 slices taken from 3 organoids (WT) and 8 slices taken from 4 organoids (Mut)); ****p < 0.0001, two-tailed Student’s t-test. (c) RTT-Mut2 organoids exhibit a reduction in mean ventricle wall thickness, defined as the distance between apical and basal surfaces of the ventricle. Graph shows mean ± SEM. (n = 60 ventricles measured across 6 slices taken from 3 organoids (WT) and 148 ventricles measured across 8 slices taken from 4 organoids (Mut); ***p < 0.001, Mann-Whitney test). (d) Assessment of the cumulative distribution of ventricle wall thickness reveals significant differences in RTT-Mut2 versus RTT-WT2 organoids. (n = 60 ventricles measured across 6 slices taken from 3 organoids (WT) and 148 ventricles measured across 8 slices taken from 4 organoids (Mut). ***p < 0.001, Kolmogorov-Smirnov test). (e) Representative immunostaining for PAX6 (early neural progenitors; green), TBR2 (intermediate neural progenitors; red), MAP2 (dendrites; magenta), TBR1 (early-born layer 6 cortical neurons; green), and Doublecortin (DCX) (immature neurons; magenta) in RTT-WT2 (top) and RTT-Mut2 (bottom) cerebral organoids. Scale bar = 500 μM. Immunostaining showing RTT-WT2 organoids expressing MeCP2 (red) and absence of MeCP2 protein in RTT-Mut2 organoids (bottom). Scale bar = 500 μm. (f) Representative thresholded images of the staining performed in (e) in RTT-WT2 (left) and RTT-Mut2 (right). Note the small percentage of TBR2- and TBR1-expressing cells in mutant organoids. Scale bar = 500 μM. (g) Quantification of the percentage of organoid expressing the aforementioned progenitor or neuronal marker, normalized to DAPI revealed: 1) significant reduction in DCX in RTT-Mut2 organoids (n = 25 sections from a total of 11 organoids (WT) and 35 sections from a total of 14 organoids (Mut), distributed across three independent organoid differentiation batches); 2) significant decrease in the expression of MAP2 in RTT-Mut2 organoids (n = 26 sections from a total of 11 organoids (WT) and 33 sections from a total of 14 organoids (Mut), distributed across three independent organoid differentiation batches); 3) significant increase in the expression of PAX6 in RTT-Mut2 organoids (n = 26 sections from a total of 11 organoids (WT) and 35 sections from a total of 14 organoids (Mut), distributed across three independent organoid differentiation batches); 4) significant decrease in the expression of Tbr2 in RTT-Mut2 organoids (n = 27 sections from a total of 12 organoids (WT) and 36 sections from a total of 14 organoids (Mut), distributed across three independent organoid differentiation batches); and 5) a significant decrease in the expression of Tbr1 in RTT-Mut2 (n = 26 sections from a total of 11 organoids (WT) and 34 sections from a total of 14 organoids (Mut), distributed across three independent organoid differentiation batches). A total of 79 sections (WT) and 103 sections (Mut) were analyzed for this experiment, which were generated from 3 independent differentiation rounds of both RTT-WT2 and RTT-Mut2 organoids. (***p < 0.001, ****p< 0.0001, two-tailed Student’s t-test). (h) Mean ± SEM relative to RTT-WT2 miR-199 and miR-214 (normalized to RNU44), pri-miR-199-a1,-a2,-b, pri-miR-214, and BMP4 mRNA levels (normalized to 18S rRNA) in RTT-WT2 (green bars) and RTT-Mut2 (red bars) 5 week 3D cerebral organoids. Stars depict statistical significance based on two-tailed Student’s t-test (*p < 0.05, ***p < 0.001, ****p < 0.0001). N for miR-199/214: RTT-Mut2 = 10, RTT-WT2 = 6, N for pri-miRNAs/BMP4: RTT-Mut2 = 4, RTT-WT2 = 5. (i) Mean ± SEM relative to RTT-WT2 DCX, PAX6, GAD1, DLX1, SST, and PVALB mRNA levels (normalized to 18S rRNA) in RTT-WT2 (green bars) and RTT-Mut2 (red bars) 5 week 3D cerebral organoids. Stars depict statistical significance based on two-tailed Student’s t-test (**p < 0.01, ****p< 0.0001). N: RTT-Mut2 = 4, RTT-WT2 = 5. (j) Human iPSC-derived cell organoids co-electroporated with GFP and control vector or MeCP2 shRNAs and examined after 7 days. MeCP2 shRNA-targeted cells exhibit increased number of PAX6+ progenitors. Scale: 100 μm. High-magnification of cells are shown in (k) and (l). The asterisks in (k) denote the PAX6- cells in the control group. Increased PAX6+ progenitors after depletion of MeCP2 are denoted by arrows in (l). (m) The percentages of PAX6+ GFP+ cells were quantified. *p < 0.05 versus control; two-tailed Student’s t-test. More than 100 GFP+ neurons from three organoids were examined in each group. Bars in all graphs represent mean ± S.E.M. (n-p) RTT-WT2 and RTT-Mut2 organoids were electroporated with GFP and fluorescence beads were used to mark the ventricles. Electroporated GFP+ cells in RTT-Mut2 organoids exhibited reduced migration distance (o) as compared to cells in RTT-WT2 organoids (n). Scale: 100 μm. (p) Graph showing significant reduction of migration distance in electroporated GFP+ cells in RTT-Mut2 vs RTT-WT2 organoids. *p < 0.05 versus control; ***p < 0.001 versus control; two-tailed Student’s t-test. More than 700 GFP+ cells from seven organoids were examined in each group. Segments such as those selected in (n,o) were divided in 9 bins. Bars in all graphs represent mean ± S.E.M.

Figure 5. Inhibition of miR-199 and miR-214 in MeCP2-deficient NPs rescues ERK and AKT activation and ameliorates alterations in neuronal differentiation

(a) Representative Western blots showing levels of phosphorylated (p) and total (t) ERK1/2 and AKT, PTEN and PAK4 protein levels together with normalizer β-actin in MeCP2 (shMeCP2) or Control shRNA (shControl)- expressing WT NPs (left), as well as in WT2, RTT-Mut2 and RTT-WT2 NPs. (b-c) Graphs based on Western blot analysis showing mean ± SEM for the same proteins mentioned above in shMeCP2 (red bar) and shControl (blue bar) (b) and WT unaffected control (WT2 – blue bar), RTT-Mut2 (red bar) and RTT-WT2 (green bar) (c) samples. Stars depict statistical significance based on two-tailed one sample t-test (shMeCP2, shControl) or ANOVA (WT2, RTT-Mut2, RTT-WT2) with Dunnett’s multiple comparisons test (right) (*p < 0.05, **p < 0.01, ***p < 0.001). N: shControl = 4, shMeCP2 = 4, WT2 = 6, RTT-mut2 = 10, RTT-WT2 = 6. (d,e) Correlation between PAK4 and p/t ERK1/2 (d) and PTEN and p/t AKT levels (e) in WT2, RTT-WT2, RTT-Mut2, as well as shControl and shMeCP2 NPs (log transformed). Each dot represents one sample (Blue dots for positive and red for negative correlations). Spearmann coefficients and p-values are shown in the graphs. (f) Schematic of the proposed molecular mechanism. (g) Representative Western blots showing levels of phosphorylated and total ERK1/2 (pERK1/2 and tERK1/2) and AKT (pAKT and tAKT), and MeCP2 protein levels together with normalizer β-actin, following nucleofection of miR-199 or miR-214 inhibitors (anti-miR-199 and anti-miR-214) in shMeCP2 expressing NPs, as well as with shMeCP2 and shControl NPs nucleofected with a negative miRNA control inhibitor (shMeCP2 anti-NC and shControl anti-NC respectively). (h) Graphs showing mean ± SEM PAK4 mRNA (upper) and phosphorylated vs total ERK1/2 protein in shControl anti-NC, shMeCP2 anti-NC, shMeCP2 anti-miR-199, and shMeCP2 anti-miR-214 NPs. (i) Graphs showing mean ± SEM PTEN mRNA (upper) and phosphorylated vs total AKT protein in the NP samples as above. For all 4 groups N = 5 for protein and N = 8 for mRNA measurements. (j) Representative immunostaining for MAP2 and MeCP2 in three-week anti-miRNA nucleofected MeCP2 shRNA neurons (same groups as above- yet different developmental stage). (k) Graphs showing mean ± SEM DCX (upper) and MAP2 mRNA in the three-week neuronal samples as above. N = 8 for for all 4 groups. Analysis in (h), (i), (k) was based on two-tailed one sample t-test, (*p < 0.05,**p < 0.01, ^#0.10< p < 0.05). 18S rRNA was used as a normalizer for all mRNA qRT-PCRs.