Rac1 selective activation improves retina ganglion cell survival and regeneration

Abstract

In adult mammals, after optic nerve injury, retinal ganglion cells (RGCs) do not regenerate their axons and most of them die by apoptosis within a few days. Recently, several strategies that activate neuronal intracellular pathways were proposed to prevent such degenerative processes. The rho-related small GTPase Rac1 is part of a complex, still not fully understood, intracellular signaling network, mediating in neurons many effects, including axon growth and cell survival. However, its role in neuronal survival and regeneration in vivo has not yet been properly investigated. To address this point we intravitreally injected selective cell-penetrating Rac1 mutants after optic nerve crush and studied the effect on RGC survival and axonal regeneration. We injected two well-characterized L61 constitutively active Tat-Rac1 fusion protein mutants, in which a second F37A or Y40C mutation confers selectivity in downstream signaling pathways. Results showed that, 15 days after crush, both mutants were able to improve survival and to prevent dendrite degeneration, while the one harboring the F37A mutation also improved axonal regeneration. The treatment with F37A mutant for one month did not improve the axonal elongation respect to 15 days. Furthermore, we found an increase of Pak1 T212 phosphorylation and ERK1/2 expression in RGCs after F37A treatment, whereas ERK1/2 was more activated in glial cells after Y40C administration. Our data suggest that the selective activation of distinct Rac1-dependent pathways could represent a therapeutic strategy to counteract neuronal degenerative processes in the retina.

Figure 1. Rac1 selective activation increased RGC survival until 15 days after optic nerve crush in YFPH mice.

Representative confocal images of flat mounted normal (A), and injured retinas after treatments with 2 injections (at day 0 and day 2 post lesion) of either vehicle (B) or Rac1WT (C), or Rac1L61F37A (D), or Rac1L61Y40C (E), or the DN Rac1-N17 (F). Retinas were excised at 15dpl and stained in order to detect RGCs (βIII tubulin, red), and YFP (anti-GFP, green). The dramatic neuronal loss observed in the vehicle-treated mice (B) was reduced in mice treated with either Rac1L61F37A (D) or Rac1L61Y40C (E). Scale bar 50 µm. Mutants were tested for different experimental protocols, whose scheme is shown in (G). YFPH mouse optic nerves were crushed at day 0 and, after one or more injections of Rac1 mutants, WT or vehicle, retinas were dissected 15 or 30 days post crush in order to investigate RGCs survival. After staining for βIII tubulin, flat mounted retinas were imaged and processed for the evaluation of survival as described in methods. (H-I) Quantification of RGC survival after optic nerve crush and Rac1 selective activation at 15 and 30 days post lesion in YFPH mice. The results at 15 dpl are shown in H, where both CA mutants were able to improve survival. Only the L61F37A exerted a dose dependent effect, whereas the DN N17 mutant decreased survival. At 30 dpl (I) the survival of Rac1 L61F37A treated mice decreased at the level of controls, even after repetitive injections, indicating that the mutant was unable to sustain survival at 30 days. Data are mean ±SEM, N is in brackets. *p<0,05; ^#p<0.01 versus the controls (one way ANOVA followed by LSD post hoc test).

Figure 2. Rac1 selective activation prevents the dendrite atrophy occurring after crush.

Representative confocal maximum projections of YFPH mouse RGCs 15 days after crush and double injection of either vehicle or CA or DN mutants. A normal RGC is shown for comparison (A). After Rac1L61F37A and Y40C treatment (D and E respectively) the dendritic atrophy is prevented, whereas the same extent of degeneration was found in control (B) and after DN treatment (C). The plots relative to the Sholl analysis for the different treatments are shown in F–G: (F) the maximum number of intersections, the ramification index and the critical value were used for statistical evaluation (10 to 20 neurons per treatment), whereas (G) the N of intersections against the distance from the soma shows the morphological changes along the whole dendritic tree. Scale bar 20 µm. # p<0,01 versus the control, the L61F37A and the L61Y40C; *p<0,05 versus the indicated group (one way ANOVA followed by LSD post hoc test).

Figure 3. Rac1 selective activation promotes axonal regeneration after optic nerve crush in Brainbow mice.

In Brainbow mice the injection of the AAV-Cre-GFP around the day of crush triggers a genetic recombination that leads to YFP expression (white false color) only in surviving neurons. We injected either the Tat-Rac1 mutants, WT or vehicle on the day of crush (day 0) and on day 2 and studied regeneration 15 days post lesion. A scheme of the treatment is in A. Nerves were acquired and studied by confocal microscopy. Single examples of whole mounted nerves after mosaic merge reconstruction are given in B to E, and are relative to vehicle (B), Rac1WT (C), L61F37A mutant (D) and L61Y40C mutant (E) double injections. The crush sites of B, C, D and E are enlarged in F, G, H and I respectively. By comparison of the panels it is clear that after treatment with L61F37A a higher number of axons is able to cross the crush site and run distally (D and H). Scale bars 100 µm.

Figure 4. Quantification of axonal regeneration after optic nerve crush and Rac1 selective activation in Brainbow mice.

Brainbow mouse optic nerves were crushed at day 0 and, after one or more injections of either Rac1 mutants, WT or vehicle, were dissected at 15 or 30 days post crush in order to investigate regeneration. A scheme of the different treatments is given in A. Nerves were studied by confocal microscopy and the results of the regeneration study are plotted in B, C and D. Only the double injection of L61F37A was able to increase the average number of axons crossing the crush site per 100 µm of nerve z-section (B) at 15 days post lesion. The number of regenerating axons is higher than control also after 2 and 5 injections of L61F37A at 30 dpl. The data at 15 days are confirmed also by the analysis of length distribution in the entire distal stump (C). The same analysis at 30 days (D) revealed that, despite after 2 and 5 L61F37A injections the total number of regenerating neurons are similar, the repetitive treatment resulted in longer axons. Since we found no differences between the various vehicle injection protocols of treatment at 15 and 30 days, we put together the data of the controls on the same column/curve (n = 6 and 8). Data are mean ±SEM. N is in brackets. ^#p<0.01, *p<0.05 by ANOVA (LSD post hoc test).

Figure 5. Long-term effects on axonal regrowth of Rac1L61F37A treatment in Brainbow mice.

Single examples of whole mounted Brainbow mouse nerves after mosaic merge reconstruction, relative to the 30 dpl treatments described in figure 4A and D. Images shows treatments with vehicle (A), 2 (B) and 5 (C) L61F37A injections. The crush sites of A, B and C are enlarged in D, E and F respectively. Longer axons were found distally from the crush site after multiple injections of the Rac1 mutant. Scale bars 100 µm.

Figure 6. Phosphorylation of Pak1 and upregulation of ERK1/2 after injections of Rac1 mutants.

Retina sections were immunostained by antibodies against the pan-specific and the phosphorylated form of Pak1 (T212), ERK1/2 and JNK. Retinas were dissected and immunostained 3 days after optic nerve crush and ivit treatment with either vehicle, or Rac1WT, or L61F37A or L61Y40C. Some representative relevant images are shown in A to J, N and O. (A–B) Colocalization of phospho-Pak1 (Pak1-p, red) and βIII tubulin (green) indicates that the L61F37A resulted in Pak1-p increase in RGCs, confirmed also by the lack of colocalization with GFAP (C–D). (E–F) Colocalization of phospho-ERK (ERK1/2-p, red) and GFAP (green) indicates that the L61Y40C mutant activated ERK1/2 in retinal glial cells. (G–H) The lack of colocalization between MAP2 (blue) and ERK1/2-p after Y40C treatment indicates that this protein is not activated in neurons. A control is also shown (I–J) where ERK1/2-p positivity is very low. (N–O) Histag staining after L61Y40C treatment showed a clear positivity in RGCs, meanwhile the ERK1/2-p positivity pattern was still glial-like. (K) Semi-quantitative expression of total and phosphorylated level of Pak1, ERK1/2, and JNK measured in correspondence of the ganglion cell layer and normalized on the signal of the normal eye (n = 9 to 15 confocal stacks from 3 to 6 animals). (L) Ratio between the normalized intensity of phosphorylated and total forms of Pak1, ERK1/2 and JNK gives an indication about the degree of kinase activity. Scale bar 30 µm. GCL: ganglion cell layer. (M) We hypothesize that L61F37A effect on survival might be related to the increased expression of ERK1/2 and increased Pak1 phosphorylation in neurons. Meanwhile, L61Y40C is most likely boosting survival through the activation of ERK1/2 in astrocytes.