Sulforaphane's Nuclear Factor Erythroid 2-Related Factor 2 (Nrf2)-Dependent and -Independent Mechanism of Anti-SARS-CoV-2 Activity

Abstract

It is well established that Nrf2 plays a crucial role in anti-oxidant and anti-inflammatory functions. However, its antiviral capabilities remain less explored. Despite this, several Nrf2 activators have demonstrated anti-SARS-CoV-2 properties, though the mechanisms behind these effects are not fully understood. In this study, using two mouse models of SARS-CoV-2 infection, we observed that the absence of Nrf2 significantly increased viral load and altered inflammatory responses. Additionally, we evaluated five Nrf2 modulators. Notably, epigallocatechin gallate (EGCG), sulforaphane (SFN), and dimethyl fumarate (DMF) exhibited significant antiviral effects, with SFN being the most effective. SFN did not impact viral entry but appeared to inhibit the main protease (M^Pro) of SARS-CoV-2, encoded by the Nsp5 gene, as indicated by two protease inhibition assays. Moreover, using two Nrf2 knockout cell lines, we confirmed that SFN's antiviral activity occurs independently of Nrf2 activation in vitro. Paradoxically, in vivo tests using the MA30 model showed that SFN's antiviral function was completely lost in Nrf2 knockout mice. Thus, although SFN and potentially other Nrf2 modulators can inhibit SARS-CoV-2 independently of Nrf2 activation in cell models, their Nrf2-dependent activities might be crucial for antiviral defense under physiological conditions.

Keywords: Lung; MA30; MPro; Nrf2; SARS-CoV-2; Sulforaphane.

Figure 1.

Effects of Nrf2 deficiency on survival, body weight and viral production. WT: wild-type mice. Nrf2 KO: Nrf2 Knockout mice. (A–D) Mice were intranasally infected with 10⁵ PFU/mouse MA30 and samples were collected at dpi as designated in the figures. (A) Survival, (B) body weight, (C) lung viral titer, (D) viral N1 gene expression by qPCR. Actin: control. (E–H) Mice were intranasally infected with 10⁵ PFU/mouse Omicron BA.4.6 and samples were collected at dpi as designated in the figures. (E) Survival, (F) body weight, (G) lung viral titer, (H) viral N1 gene expression by qPCR. Actin: control. *: p < 0.05. **: p < 0.01. ****: p < 0.0001. (n = 8–10 for survival and body weight, n = 4–6 for other analyses).

Figure 2.

Effects of Nrf2 deficiency on cytokine gene expression. WT: wild-type mice. Nrf2 KO: Nrf2 Knockout mice. (A–E) Mice were intranasally infected with 10⁵ PFU/mouse MA30 and samples were collected at dpi as designated in the figures. Cytokine expressions were measured by qPCR. Actin was used as a control and data are presented as fold induction. (F–J) Mice were intranasally infected with 10⁵ PFU/mouse Omicron BA.4.6 and samples were collected at dpi as designated in the figures. *: p < 0.05. **: p < 0.01. ns: not significant. n = 4–6.

Figure 3.

Screening of Nrf2 modulators for their anti-SARS-CoV-2 activities. Vero-E6 cells were pretreated with GC376, EGCG, SFN, DMF, 4-OI, CDDO-ME at different doses as designated in the figure for 1 h, then cells were incubated with 50 PFU SARS-CoV-2 for 1 h followed by continuous treatment of the compounds. Viral production was assayed 72 h later. IC₅₀ was calculated as described in Materials and Methods.

Figure 4.

SFN did not affect viral entry but inhibited M^Pro activity. (A) A549-hACE2 cells were pre-treated with the indicated concentrations of SFN for 1 h, followed by infection with the SARS-CoV-2 at MOI = 1 for 48 h and proteins were collected for the analysis of ACE2, HO-1 and Actin was used as a loading control. HO-1 was tested to show the activation of the NRF2 pathway by SFN. (B) A549-hACE2 cells were pre-treated with the indicated concentrations of SFN for 1 h, followed by infection with the SARS-CoV-2 Spike-pseudotyped lentivirus at an MOI of 1. Forty-eight hours later, the cells were lysed and subjected to luciferase activity measurement. (C) Autodocking was performed using ADT tools as described in the Materials and Methods. (D) FRET analysis using the specific M^Pro substrate and purified M^Pro. (E) M^Pro protease activity assay. 2 μM M^Pro was incubated for 1 h with SFN (1, 10, 100 μM), GC376 (10 μM), Nirmatrelvir (10 μM). DMSO was used as a negative control. Subsequently, the His-tagged substrate was added at a concentration of 5 μM and further incubated for 1 h, followed by Western blot analyses of M^Pro, intact (full length) and cleaved substrate (Sub).

Figure 5.

Nrf2-dependent and -independent activity of SFN in inhibiting SARS-CoV-2. Due to the low availability of ACE2 in A549 and BEAS2B cells, all WT and KO cell lines were transduced with adenoviral hACE2 at forty-eight hours before SARS-CoV-2 infections. (A,B) BEAS2B-WT and BEAS2B-NRF2 KO cells were pretreated with SFN at different doses for 1 h followed by infections with SARS-CoV-2 for 48 h. Total cellular proteins were collected followed by western blot analyses for viral NP and cellular NRF2. ACTIN was used as a loading control. Percentage (%) of inhibition was calculated as following: (1-viral titer (PFU) under SFN treatment/viral tier (PFU) under DMSO treatment) × 100 (%). (C,D) A549-WT and A549-NRF2 KO cells. The protocols were the same as (A,B). (E) WT and Nrf2 KO mice were pretreated with SFN (10 mg/kg) or the vehicle DMSO one day prior to MA30 infection following by daily treatment of SFN or DMSO. The lung viral titer was collected at 5 dpi. (n = 6–8). *: p < 0.05.