Direct activation of RhoA by reactive oxygen species requires a redox-sensitive motif

Abstract

Background: Rho family GTPases are critical regulators of the cytoskeleton and affect cell migration, cell-cell adhesion, and cell-matrix adhesion. As with all GTPases, their activity is determined by their guanine nucleotide-bound state. Understanding how Rho proteins are activated and inactivated has largely focused on regulatory proteins such as guanine nucleotide exchange factors (GEFs) and GTPase activating proteins (GAPs). However, recent in vitro studies have indicated that GTPases may also be directly regulated by redox agents. We hypothesized that this redox-based mechanism occurs in cells and affects cytoskeletal dynamics, and in this report we conclude this is indeed a novel mechanism of regulating the GTPase RhoA.

Methodology/principal findings: In this report, we show that RhoA can be directly activated by reactive oxygen species (ROS) in cells, and that this requires two critical cysteine residues located in a unique redox-sensitive motif within the phosphoryl binding loop. First, we show that ROS can reversibly activate RhoA and induce stress fiber formation, a well characterized readout of RhoA activity. To determine the role of cysteine residues in this mechanism of regulation, we generated cysteine to alanine RhoA mutants. Mutation of these cysteines abolishes ROS-mediated activation and stress fiber formation, indicating that these residues are critical for redox-regulation of RhoA. Importantly, these mutants maintain the ability to be activated by GEFs.

Conclusions/significance: Our findings identify a novel mechanism for the regulation of RhoA in cells by ROS, which is independent of classical regulatory proteins. This mechanism of regulation may be particularly relevant in pathological conditions where ROS are generated and the cellular redox-balance altered, such as in asthma and ischemia-reperfusion injury.

Figure 1. RhoA is reversibly activated upon exposure to ROS.

(A) REF-52 fibroblasts were serum-starved followed by treatment with the indicated concentrations of t-butyl hydroperoxide (peroxide) in serum-free DMEM for 10 min. RhoA activity assays show that peroxide treatment results in the activation of endogenous RhoA. A representative blot of active RhoA sedimented by GST-RBD versus total RhoA from whole cell lysates is shown. ImageJ software was used to quantify RhoA activation. Relative RhoA activity is the ratio of active RhoA divided by total RhoA normalized to the untreated control. Graph represents the average +/− SEM of 5 independent experiments. * p<0.05. (B) REF-52 fibroblasts were serum-starved and treated as above with 100 nM peroxide for 10 min. Following peroxide treatment, the medium was either left unchanged (0′) or replaced with serum-free DMEM for 15 or 30 min (15′, 30′). The RhoA activity assay shows that peroxide-induced RhoA activation is reversible after washout. (C) REF-52 fibroblasts were serum-starved with or without 0.5 µM NAC followed by treatment with 10 µM antimycin A (AA) for 30 min. RhoA activity assays show that treatment with antimycin A results in the activation of endogenous RhoA. However, this activation is inhibited in cells pre-treated with NAC. Representative blots of active RhoA sedimented by GST-RBD versus total RhoA from whole cell lysates are shown. ImageJ software was used to quantify RhoA activation. Relative RhoA activity is the ratio of active RhoA divided by total RhoA normalized to the untreated control. Graph represents the average +/− SD of 3 independent experiments. * p<0.05, not signficiant (NS).

Figure 2. ROS treatment induces stress fiber formation.

(A) Rat2 fibroblasts were grown on fibronectin-coated coverslips and either untreated, serum-starved for 1 h, or serum-starved followed by 15 min treatment with 5% FBS or 1 µM peroxide. F-actin staining was detected with Texas-Red labeled phalloidin. Serum-starvation results in loss of actin stress fibers; treatment with either FBS or peroxide induces prominent stress fibers. (B) Cells treated as above were scored for the presence of stress fibers and graphed as an index of stress fiber induction (normalized to serum-starved). Both FBS and peroxide result in an equally significant induction of stress fibers. Graph represents the mean of 3 independent experiments±SD, with >300 cells counted for each condition. Actual percent cells with stress fibers for each condition is 75.3±7.5% (untreated), 42.3 ± 4.6% (starved), 64.3±6.1% (serum-starved and peroxide treated), and 73±6.4% (serum-starved and FBS treated). * p<0.05. (C) Rat2 fibroblasts were serum-starved for 1 hr, followed by treatment with either 1 µM peroxide or 5% FBS for 15 min. RhoA activity assays show that both peroxide and FBS activate RhoA. A representative blot of active RhoA sedimented by GST-RBD versus total RhoA from whole cell lysates is shown. ImageJ software was used to quantify RhoA activation. Relative RhoA activity is the ratio of active RhoA divided by total RhoA normalized to the untreated control. Graph represents the average +/− SD of 2 independent experiments. * p<0.05. (D) Rat2 cells were grown as in panel A, serum-starved for 1 hr ±5 µM Y27632, and then treated for 15 min with 1 µM peroxide or 5% FBS. F-actin staining was detected with Texas-Red labeled phalloidin. Pre-treatment with Y27632 significantly reduces the percent of cells with prominent stress fibers after both peroxide and FBS treatment. Graph represents the mean of 3 independent experiments ± SD with >300 cells counted for each condition.

Figure 3. Characterization of RhoA miRNA and re-expression of non-targetable (NT) redox-resistant RhoA mutant constructs.

(A) RhoA protein sequence (amino acids 1–25) showing conserved putative redox-sensitive cysteines C16 and C20 (shaded residues). (B) Nucleotide sequence (bp 43–87) of rat, mouse, and human RhoA showing the region targeted by the RhoA miRNA used in this study (shaded area). To re-express non-targeted RhoA constructs five silent mutations were introduced in the miRNA targeting region (black boxes). Nucleotides corresponding to C16 and C20 are underlined. (C) Knockdown of endogenous RhoA and simultaneous re-expression of non-targeted (NT) mutant constructs. REF-52 cells were infected with negative control or RhoA miRNA-encoding adenovirus together with virus encoding wt or C16/20A myc-RhoA where indicated. After 72 hours, total cell lysates were analyzed by western blot with a RhoA and B-actin antibody (loading control). Arrowhead indicates endogenous RhoA; arrow indicates the slower migrating non-targeting, myc-RhoA constructs. (D) Activity assay of wt and C16/20A myc-RhoA constructs. REF-52 cells were infected with negative control or RhoA miRNA-encoding adenovirus together with virus encoding wt or C16/20A myc-RhoA. After 72 hours, cells were processed for RhoA activity assays (in the presence of serum) and analyzed by western blot with a myc antibody.

Figure 4. C16/20A myc-RhoA is not activated by ROS but responds normally to other physiological stimuli.

(A) REF-52 cells expressing wt or C16/20A myc-RhoA were serum-starved and treated with the indicated concentrations of peroxide for 10 min. RhoA activity assays show that the activity of wt myc-RhoA increases in response to peroxide, however, the C16/20A mutant is resistant to activation by peroxide. (B) ImageJ software was used to quantify RhoA activation. Peroxide treated conditions are normalized to the corresponding untreated controls. Graph represents the average +/− SEM of 2 independent experiments. * p<0.05 compared to untreated control. (C) REF-52 cells in which endogenous RhoA had been knocked down and re-expressing wt or C16/20A myc-RhoA were serum starved and treated with 1 U/mL thrombin to test their responsiveness to GEF-mediated activation. RhoA activity assays show that both wt and C16/20A myc-RhoA are activated by thrombin at 1 and 5 min. (D) REF-52 cells in which endogenous RhoA had been knocked down and expressing wt or C16/20A myc-RhoA were treated with either GST alone or GST-C3, as described in the methods. F-actin staining was detected with Texas-Red labeled phalloidin. C3 treatment results in a characteristic dendritic morphology due to RhoA inactivation. Cells expressing either wt or C16/20A myc-RhoA develop the C3 phenotype.

Figure 5. ROS induction of stress fibers is dependent on redox-regulation of RhoA.

Rat2 fibroblasts were infected with adenoviruses to knockdown endogenous RhoA and re-express wt or C16/20A myc-RhoA. These cells were seeded on fibronectin-coated coverslips, and either left unstarved (DMEM +5% FBS), or serum-starved for 1 h followed by treatment with DMEM alone, or 1 µM peroxide in DMEM for 15 min. Quantitation of stress fiber induction shows that compared with the starved condition, peroxide treatment induces a statistically significant increase in stress fibers in cells expressing wt myc-RhoA but not in cells expressing redox-resistant C16/20A myc-RhoA. Graph represents the mean of 3 independent experiments, with >300 cells counted for each condition (error bars equal SD). * p<0.05; NS, not significant. Actual percent cells with stress fibers for each condition is: (unstarved) wt myc-RhoA 76.7±5.0%, C16/20A myc-RhoA 78.1±5.2%; (starved) wt myc-RhoA 48.3±5.7%, C16/20A myc-RhoA 49.6±5.0%; (peroxide) wt myc-RhoA 68.5±4.9%, C16/20A myc-RhoA 46.3±7.4%.