MFG-E8 released by apoptotic endothelial cells triggers anti-inflammatory macrophage reprogramming

Abstract

Apoptotic endothelial cells are an important component of the "response to injury" process. Several atherosclerosis risk factors such as hyperglycemia and oxidized low-density lipoproteins, and immune injuries, such as antibodies and complement, induce endothelial cell apoptosis. While endothelial cell apoptosis is known to affect neighboring vascular wall cell biology, its consequences on macrophage reprogramming are ill defined. In this study, we report that apoptosis of human and mouse endothelial cells triggers the release of milk fat globule-epidermal growth factor 8 (MFG-E8) and reprograms macrophages into an anti-inflammatory cells. We demonstrated that MFG-E8 is released by apoptotic endothelial cells in a caspase-3-dependent manner. When macrophages were exposed to conditioned media from serum-starved apoptotic endothelial cells, they adopt a high anti-inflammatory, low pro-inflammatory cytokine/chemokine secreting phenotype that is lost if MFG-E8 is absent from the media. Macrophage treatment with recombinant MFG-E8 recapitulates the effect of conditioned media. Finally, we showed that MFG-E8-mediated reprogramming of macrophages occurs through increased phosphorylation of signal transducer and activator of transcription-3 (STAT-3). Taken together, our study suggests a key role of MFG-E8 release from apoptotic endothelial cells in macrophage reprogramming and demonstrates the importance of the apoptotic microenvironment in anti-inflammatory macrophage responses.

Figure 1. Apoptotic EC-conditioned media contain MFG-E8 and reprogram macrophages.

A Percentage of cells with increased chromatin condensation and cell membrane permeabilization (as evaluated with HO and PI staining) in HUVEC exposed to normal medium with growth factors without serum (normal serum-starved, NSS) or serum starvation (SS) for 1 h to 4 h (*p<0.001 versus Normal, n = 3). Example of HO/PI staining on serum starved HUVEC for 4 h showing chromatin condensation, right panel. B MEC and HUVEC were serum-starved for 1 h to 4 h. Supernatants (upper panels) and cells (lower panels) were harvested. Immunoblotting of MEC protein extracts showed that MFG-E8 levels decreased over time in parallel with increased active caspase-3 levels (lower left panel). HUVEC also exhibited reduced intracellular MFG-E8 levels over time (lower right panel). MFG-E8 levels increased over time in serum-starved conditioned medium (SSC) from EC (upper panels). β-Actin and Ponceau red staining were loading controls. Representative of 3 experiments. C Percentage of cells with increased chromatin condensation and cell membrane permeabilization (as evaluated with HO and PI staining) in HUVEC exposed to MMC 0.01 mg/mL or vehicle in normal medium and serum starvation (as positive control) for 15 h (left panel), *p<0.0001 versus vehicle, n = 3. Immunoblot for hMFG-E8 in supernatant of EC treated with MMC (right panel). Ponceau red staining is shown as loading control. Representative of 2 experiments. D Immunoblot for hMFG-E8 in supernatants conditioned by necrotic HUVEC (3 freeze-thaw cycles) and serum-starved HUVEC as positive control. Ponceau red staining included as loading control. Representative of 2 experiments. E Immunoblot for mMFG-E8 from total medium conditioned by apoptotic EC (Total SSC), supernatant after removal of apoptotic blebs by centrifugation at 50 000 g (SSC without (W/O) blebs) and apoptotic blebs (Blebs) purified from total SSC by centrifugation, supernatant obtained from the supernatant after 50 000 g and 200 000 g centrifugation (SSC W/O exo.) and exosome-like nanovesicle fraction pelleted after the 200 000 g centrifugation (Exo.). Proteins from equal initial volumes were precipitated by TCA. Ponceau red staining is shown as loading control of samples. Representative of 2 experiments. F MEC were serum-starved for 4 h, the SSC were harvested, centrifuged to remove apoptotic cells. Murine macrophages were exposed to SSC or serum starvation (SS) for 24 h. ELISA were performed for TGF-β₁, VEGF, IL-10, (left panel) MCP-1 and MIP-2 (right panel), *p<0.05, representative of n = 14, 12, 4, 7 and 9 separate experiments respectively.

Figure 2. Caspase-3 activation is necessary for MFG-E8 release and subsequent macrophage reprogramming.

MEC were pre-treated with an irreversible caspase-3 inhibitor, DEVD-FMK (SSC-DEVD, 100 µM) to prevent apoptosis, and then serum-starved for 4 h. Control MEC were pre-treated with vehicle (DMSO) for 2 h, washed and serum-starved for 4 h A Murine MFG-E8 was immunoblotted in SSC and cell extracts. DEVD-FMK-treated murine EC released less MFG-E8 compared to the vehicle (DMSO) (left panel), whereas their intra-cellular content remained higher than DMSO-treated EC (right panel). Ponceau red and β-Actin were loading controls. Representative of 3 experiments. B Immunoblot for murine MFG-E8 of SSC from caspase-3 KO EC compared to EC from WT mice. Representative of 2 experiments. C Murine macrophages produced more TGF-β₁, VEGF, IL-10 (left panel) and less pro-inflammatory chemokines MCP-1 and MIP-2 (right panel) when exposed to media where apoptosis was not inhibited. *p<0.05, representative of n = 11, 9, 3, 5 and 8 separate experiments respectively.

Figure 3. MFG-E8 immunoprecipitation from SSC alters macrophage reprogramming.

Serum-Starved Conditioned medium (SSC) from MEC were treated with an anti-MFG-E8 antibody (or isotype control) to deplete the MFG-E8 content. Immunoblotting of MFG-E8 protein in SSC is shown for MEC (top panel). BMDM treated with SSC depleted of MFG-E8 produced less TGF-β₁, VEGF, IL-10 (lower left panel), and more MCP-1 and MIP-2 (lower right panel). *p<0.05, representative of n = 2, 2, 3, 5 and 3 separate experiments respectively.

Figure 4. SSC from MFG-E8 KO mice do not reprogram macrophages into anti-inflammatory macrophages.

A MFG-E8 KO or WT MEC were serum-starved for 4 h. Supernatants and cell extracts were immunoblotted for mMFG-E8 confirming KO status. Caspase-3 activation was similar between the 2 groups. B Murine macrophages were stimulated with Serum-Starved Conditioned medium (SSC) from MFG-E8 KO or WT EC. Supernatant were analyzed by ELISA. The results indicate that MFG-E8 in SSC is necessary to induce an anti-inflammatory macrophage phenotype. *p<0.05, representative of n = 5 separate experiments.

Figure 5. Recombinant murine MFG-E8 recapitulates SSC-induced macrophage reprogramming.

Murine macrophages were stimulated with rmMFG-E8 (1 ng/mL) resuspended in RPMI (SS), vehicle (PBS), SS or SSC for 48 h and supernatant were harvested. rmMFG-E8 induced an anti-inflammatory macrophage phenotype with an increased production of TGF-β₁, VEGF and IL-10 and reduced MCP-1 and MIP-2 compared to the vehicle control (PBS resuspended in SS). *p<0.05 vs respective controls, mean ± SD , representative of n = 3 separate experiments.

Figure 6. STAT-3 activation in macrophage reprogramming by apoptosis-conditioned media.

A BMDM were stimulated with Serum-Starved Conditioned medium (SSC) or serum starvation (SS) for 30 minutes to 1 h. Total protein extracts were harvested and immunoblotted for phospho-STAT-3, STAT-3 and β-actin as loading control. Phosphorylated STAT-3 levels are higher after SSC stimulation compared to SS. Representative of 4 experiments. B C57BL/6 mice were pre-conditioned with SSC-DEVD or SSC-DMSO intraperitoneally for 3 h. Experimental peritonitis was induced with thioglycollate for 2 h and followed by peritoneal lavage to harvest peritoneal cellular exudates and supernatants. Protein extracts from the cellular exudates showed increased STAT-3 phosphorylation in mice pre-conditioned with SSC-DMSO compared to SSC-DEVD (B, left panel). ELISA of the supernatants revealed that SSC-DMSO pre-treatment increased TGF-β₁ and IL-10 production compared to SSC-DEVD (B, right panel). *p<0.05, representative of n = 3 separate experiments. C MFG-E8 pre-conditioning increased STAT-3 phosphorylation compared to PBS pre-conditioned or control immunomagnetically-isolated peritoneal macrophages prior to Brewer thioglycollate (BTG) administration (W/O BTG). STAT-3 activation persisted and increased further 2 h following the induction of BTG peritonitis (BTG) in pre-conditioned macrophages. Total STAT-3 levels are depicted. β-Actin were loading controls. Representative of 2 experiments.