Extracellular Mitochondrial-Derived Vesicles Affect the Progression of Diabetic Foot Ulcer by Regulating Oxidative Stress and Mitochondrial Dysfunction

Abstract

Diabetic foot ulcer (DFU) is a common and severe complication of diabetes mellitus, the etiology of which remains insufficiently understood, particularly regarding the involvement of extracellular vesicles (EVs). In this study, nanoflow cytometry to detect EVs in DFU skin tissues is used and found a significant increase in the Translocase of Outer Mitochondrial Membrane 20 (TOM20)⁺ mitochondrial-derived vesicles (MDVs). The role of MDVs in DFU is yet to be reported. Using single-cell datasets, it is discovered that the increase in MDVs may be regulated by Sorting Nexin 9 (SNX9). In vitro experiments revealed that MDVs secreted by fibroblasts cultured in high glucose medium exhibited similar composition and protein enrichment results to those in DFU tissues, suggesting their potential as an ideal in vitro surrogate. These MDVs promoted apoptosis and intracellular oxidative stress, disrupted mitochondrial structure, and reduced aerobic metabolism in target cells. In vivo experiments also showed that MDV drops hindered wound healing in diabetic mice; however, this effect is rescued by SNX9 inhibitors, restoring mitochondrial dynamics and balance. Under high glucose conditions, MDVs significantly upregulated oxidative stress levels and induced mitochondrial dysfunction. This study proposes targeting MDVs as a potential therapeutic strategy for DFU.

Keywords: diabetic foot ulcers; extracellular vesicles; mitochondria; mitochondrial‐derived vesicles; oxidative stress.

Figure 1

EV isolation and typing from Healthy, Diabetes, and DFU skin tissues. A) Schematic of EV isolation protocol from human skin tissue. B) Protein level of EVs was evaluated using a BCA protein assay kit (n = 3). C) Size distribution of EV particles. D) Schematic diagram of EXO/MV, MDV, PEV, and AB biomarkers. E) Bivariate dot‐plots of EVs using nanoflow cytometry and dual immunofluorescent staining with CD63/CD41 and TOM20/Annexin V. F) Quantitative analysis of nanoflow. G) Heat map of the protein microarray, displaying the expression level of EVs biomarkers in the samples. H) Quantitative analysis of EV biomarkers (n = 3). I) Western blot analysis of EVs extracted from skin tissue. Data are presented as the mean ± SD. Statistical analysis was performed using one‐way ANOVA. *: p < 0.05, ns: p > 0.05.

Figure 2

Expression levels of MDV‐related genes in single‐cell sequencing data. A) UMAP dimensionality reduction embedding of data from Healthy individuals, those with Diabetes, and those with DFU. B) Human single‐cell RNA sequencing dot plot demonstrating gene expression within various clusters; these clusters were identified using UMAP cluster analysis, as shown in (A). C) Human single‐cell RNA sequencing dot plot demonstrating gene expression within Healthy, Diabetes, and DFU samples. D) qRT‐PCR assay results (RAB9A, PRKN, VPS35, STX17, TOLLIP, DNM1L, SNX9, and OPA1). Statistical analysis was performed using one‐way ANOVA (Healthy, n = 3; Diabetes, n = 5; DFU, n = 5). Data are presented as the mean ± SD. *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001.

Figure 3

Proteomic profiling of MDVs. A) TEM images of MDVs from Healthy, DFU, MDV, and hgMDV groups. B) Size distribution of MDV particles. C) Pearson's correlation coefficients between protein profiles of MDVs from each group. D) The Venn diagram shows the intersections of DEPs between DFU versus Healthy groups and hgMDV versus MDV groups. E) Heatmap showing DEPs in MDVs between DFU versus Healthy groups and hgMDV versus MDV groups. F) KEGG pathway enrichment analysis of 238 common DEPs. G) GO annotation analysis of 238 common DEPs.

Figure 4

Effects of MDVs and hgMDVs on fibroblasts. A) Experimental design: Fibroblasts cultured in HG medium were co‐cultured with MDVs or hgMDVs and analyzed for various cellular processes. B,C) Confocal microscopy images and quantitative analysis of fluorescence intensity for EvLINK 505‐labeled MDV internalization by CellLINK 555‐labeled fibroblasts at 12, 24, 36, and 48 h. Statistical analysis was performed using an independent Student's t‐test (n = 3). D) Representative images of the TUNEL assay. E) Semiquantitative analysis of TUNEL‐positive cells. Statistical analysis was performed using one‐way ANOVA (n = 3). F) Representative fluorescence images showing ROS formation (DCFH‐DA) in fibroblasts after exposure to MDVs and hgMDVs. G) Quantitative analysis of ROS signals in fibroblasts. Statistical analysis was performed using one‐way ANOVA (n = 3). H) MDA levels in fibroblasts were quantitatively determined using an MDA assay kit. Statistical analysis was performed using one‐way ANOVA (n = 3). I) Effect of the indicated treatments on SOD activity in fibroblasts. Statistical analysis was performed using one‐way ANOVA (n = 3). J) Effect of the indicated treatments on CAT activity in fibroblasts. K) Effects of MDVs on mitochondrial membrane potential were determined using JC‐1 staining. L) Quantitative ratio analysis of aggregated and monomeric JC‐1 is shown in panel (n = 3). M) Representative confocal images showing mitochondrial morphology in fibroblasts. Cells were stained with MitoTracker Deep Red. N) TEM images of mitochondrial structure in fibroblasts. O) Quantitative analysis of mitochondrial mean length (n = 3). Data are presented as mean ± SD. Statistical analysis was performed using one‐way ANOVA. *p < 0.05, **p < 0.01, ***p < 0.001, ns: p > 0.05.

Figure 5

hgMDV induction suppresses aerobic metabolism. A) ATP production was measured at different time points post‐treatment (n = 3). B) PFK‐1, HK, and PK activities were measured at different time points after treatment (n = 3). C) Activities of LDH and PDH and concentrations of lactic and pyruvic acids were measured (n = 3). D) Relative quantitative analysis was performed on the expressions of 𝛼‐KGDH, IDH, and CS (n = 3). E) Relative quantitative analysis was performed on expressions of NDUFB‐3, MTCO3, and SDHB (n = 3). F) Schematic diagram of the role of hgMDVs on mitochondrial OXPHOS. Data are presented as mean ± SD. Statistical analysis was performed using one‐way ANOVA. *: p < 0.05 with respect to the Control group, #: p < 0.05 with respect to the MDV group.

Figure 6

Histological analysis of diabetic wound healing modulated by hgMDVs and SNX9 inhibition. A) Schematic illustration of the operations performed on mice, arranged in chronological order. B) Representative images of wounds on days 0, 3, 7, and 14 in Control, Diabetes, hgMDV, and hgMDV+SNX9‐IN groups and diagrams of time‐evolved wound areas. C) Percentage of residual wounds at days 0, 3, 7, and 14 in each group (n = 3). *: p < 0.05 with respect to hgMDV+SNX9‐IN group; #: p < 0.05 with respect to the Diabetes group. D) Percentage of wound closure area at days 0, 3, 7, and 14 in each group (n = 3). *: p < 0.05 for hgMDV+SNX9‐IN group; #: p < 0.05 for Diabetes group. E) Hematoxylin and eosin staining of the collected skin tissue at day 14 post‐wounding. F) Quantitative analysis of wound area length (n = 3). G) Quantitative analysis of epidermal thickness (n = 3). H) Masson's trichrome staining of the collected skin tissue 14 days post‐wounding. I) Quantitative analysis of granulation tissue thickness within wound area (n = 3). J) Quantitative analysis of the collagen deposition in wound center area (n = 3). K) Collagen I and III immunohistochemical staining in each group on day 7. L,M) Quantitative data for collagen I and III in skin tissues (n = 3). (N) Immunofluorescence staining of CD31 in granulation tissues in each group. O) Quantitative analysis of CD31‐positive area (n = 3). Data are presented as the mean ± SD. Statistical analysis was performed using one‐way ANOVA. *p < 0.05, **p < 0.01.

Figure 7

Analysis of molecular pathways and protein expression in diabetic wound healing under hgMDV treatment. A) Heatmap showing differential gene expression across control, diabetes, and hgMDV groups (n = 3). B) GO term enrichment analysis: upper panel shows hgMDV versus diabetes groups, and lower panel shows hgMDV+SNX9‐IN versus hgMDV groups. C) KEGG pathway enrichment analysis: upper panel shows hgMDV versus diabetes groups, and lower panel shows hgMDV+SNX9‐IN versus hgMDV group. D) GSEA plots for key pathways in hgMDV versus diabetes group comparison: apoptosis, chemical carcinogenesis–reactive oxygen species, mitochondrial biogenesis, and mitophagy. E–H) Immunohistochemistry and quantification of Cleaved Caspase‐3 and SOD1 expression in wound tissues (n = 3). I–L) Immunofluorescence staining and quantification of NRF1 and PINK1 in wound tissues (n = 3). M) Western blot analysis of key proteins involved in apoptosis, mitochondrial function, and oxidative stress. N) Quantification of protein expression levels from western blot analysis (n = 3). Scale bars: 100 µm. Data are presented as mean ± SD. Statistical analysis was performed using one‐way ANOVA. *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001.