Neutrophil Extracellular Traps Delay Diabetic Wound Healing by Inducing Endothelial-to-Mesenchymal Transition via the Hippo pathway

Abstract

Diabetic foot ulcers (DFUs) are among the most frequent complications of diabetes with significant morbidity and mortality. Diabetes can trigger neutrophils to undergo histone citrullination by protein arginine deiminase 4 (encoded by Padi4 in mice) and release neutrophil extracellular traps (NETs). The specific mechanism of NETs-mediated wound healing impairment in diabetes remains unknown. In this study, we show neutrophils are more susceptible to NETosis in diabetic wound environments. Via in vitro experiments and in vivo models of wound healing using wide-type and Padi4 ^-/- mice, we demonstrate NETs can induce the activation of PAK2 via the membrane receptor TLR-9. Then PAK2 phosphorylates the intracellular protein Merlin/NF2 to inhibit the Hippo-YAP pathway. YAP binds to transcription factor SMAD2 and translocates from the cytoplasm into the nucleus to promote endothelial-to-mesenchymal transition (EndMT), which ultimately impedes angiogenesis and delays wound healing. Suppression of the Merlin/YAP/SMAD2 pathway can attenuate NET-induced EndMT. Inhibition of NETosis accelerates wound healing by reducing EndMT and promoting angiogenesis. Cumulatively, these data suggest NETosis delays diabetic wound healing by inducing EndMT via the Hippo-YAP pathway. Increased understanding of the molecular mechanism that regulates NETosis and EndMT will be of considerable value for providing cellular targets amenable to therapeutic intervention for DFUs.

Keywords: Hippo pathway; diabetic foot ulcer; endothelial-to-mesenchymal transition; neutrophil extracellular traps; wound healing.

Figure 1

Diabetes primes NET formation, EndMT, and Hippo-YAP pathway inhibition in human and mouse wounds. (A) Western blotting analysis of typical NET marker, citrullinated histone H3 (Cit-H3), and protein arginine deiminase 4 (PAD4) protein levels in skin wounds from NDU vs DFU patients. Cit-H3 levels were normalized to histone H3 levels. PAD4 levels were normalized to β-actin levels. (B) Western blotting analysis of Cit-H3 and PAD4 in wound tissue at days 0, 3, and 7 post-ulcer formation in diabetic mice. Three independent samples from each group were analyzed. Cit-H3 levels were normalized to histone H3 levels. PAD4 levels were normalized to β-actin levels. (C-D) Immunofluorescence and immunohistochemistry images showing localization and expression of typical NET marker (CitH3, MPO) in wound tissue samples from NDU patients vs DFU patients, scale bar = 100μm in immunofluorescence images, scale bar = 1000μm in immunohistochemistry images. (E-F) High-resolution confocal immunofluorescence images (1000×, scale bar = 1μm) and transmission electron microscopy images (4000×, scale bar = 2μm; 20000×, scale bar = 0.5μm) of NETs formation in wound tissue of DFU patients. (G) Representative scan electron microscopy image of neutrophils and NETs in diabetic wound tissue. Green arrows point to extracellular meshes of NETs and white arrows point to neutrophils. (H) High-resolution confocal immunofluorescence images (1000×, scale bar = 1μm) of Sytox green and MPO dyeing in wound tissue. (I) Immunofluorescence images showing localization and expression of Snail-1 and CD31 in wound tissue samples from NDU patients vs DFU patients, scale bar = 100μm in immunofluorescence images. *P < 0.05, **P < 0.01, the variables between two groups were compared using Student's t test. For variables of more than two groups, statistical analysis was performed by one-way ANOVA followed by the SNK-q post hoc test. Data are shown as the mean ± SD, n = 6 in each group in this figure.

Figure 2

NETs regulate EC functions and induce EndMT in a TLR-9-dependent manner. (A) Western blotting analysis of the Hippo pathway (YAP, p-YAP, Last1, Mst1, MOB1, and Taz) in wound tissue from NDU vs DFU patients. β-actin is used as a loading control. (B) EC proliferation was analyzed by BrdU incorporation assays. EC migration was reported as migration speed (mm/h). Representative Matrigel assay images and quantification as total tubule length values are means ± SD. Cell membrane capacitance was also quantitatively compared. Scale bar = 500μm, (C) Morphological changes of ECs to mesenchymal phenotype were presented. (D) Relative mRNA levels of CD31, VE-cadherin, α-SMA, COL1A1, SNAIL-1, and SLUG. (E) Western blotting analysis of FSP-1, Snail-1, VE-cad, and CD31. β-actin is used as a loading control. (F-G) Immunofluorescence images showing localization and expression of Snail-1, CD31, VE-cad, and FSP-1. Scare bar = 50μm. DNase I, deoxyribonuclease I; ODN, oligonucleotide antagonist of the pattern recognition DNA receptor Toll-like receptor 9. *P < 0.05, **P < 0.01, the variables between two groups were compared using Student's t test. For variables of more than two groups, statistical analysis was performed by one-way ANOVA followed by the SNK-q post hoc test. Data are shown as the mean ± SD, n = 6 in each group in this figure.

Figure 3

NETs phosphorylate Merlin/NF2 and suppress the Hippo-YAP pathway in EC. (A) Western blotting analysis of YAP, p-YAP, Last1, Mst1, and MOB1. β-actin is used as a loading control. (B) Immunofluorescence images showing localization and expression of TLR-9, PAK2, and Merlin/NF2 by triple dyeing. Scare bar = 20μm. (C) Western blotting analysis of PAK2, Merlin/NF2, and p-Merlin (Ser518). β-actin is used as a loading control. (D) Western blotting analysis of Merlin/NF2, p-Merlin (Ser518), YAP, and p-YAP. β-actin is used as a loading control. (E) Immunoblotting of HUVECs that were infected with lentivirus expressing the indicated flagMerWT constructs and immunoprecipitated with anti-flag antibody to detect the binding of endogenous PAK2 to flagMerWT constructs. In the control group, cells were infected with lentiviruses expressing empty vector. (F) Western blotting analysis of Merlin/NF2, YAP, and p-YAP. β-actin is used as a loading control. All the cells were infected with lentiviruses expressing shRNA of NF2. At 3 days post-lentivirus infection, cells were infected with lentiviruses expressing empty mCherry vector (Empty), flagMerWT, flagMerSA, or flagMerSD. Analysis was performed at 3 days post-lentivirus infection. FRAX597 is an ATP-competitive inhibitor of PAK2. The flagMerWT expresses the wild-type form of Merlin/NF2. The flagMerSA constitutively expresses a growth-inhibitory (activated) form of Merlin/NF2 in which there is an alanine substitution at the S518 phosphorylation site. The flagMerSD expresses a phosphomimetic (inhibited) form of Merlin/NF2. *P < 0.05, **P < 0.01, the variables between two groups were compared using Student's t test. For variables of more than two groups, statistical analysis was performed by one-way ANOVA followed by the SNK-q post hoc test. Data are shown as the mean ± SD, n = 6 in each group in this figure.

Figure 4

YAP interacts with SMAD2 and promotes its translocation into the nucleus to induce EndMT. (A) Immunofluorescence images showing the translocation of YAP and SMAD2 from the cytoplasm into the nucleus. The cytoskeletal staining was presented. (B) Western blotting analysis of YAP and SMAD2 in the cytoplasmic and nuclear fraction. Scare bar = 100μm. (C) Immunoblotting of HUVECs that were infected with lentivirus expressing the indicated flag SMAD2 constructs and immunoprecipitated with anti-flag antibody to detect the binding of endogenous YAP to flag SMAD2 constructs. In the control group, cells were infected with lentiviruses expressing the empty vector. (D) Immunofluorescence images showing colocalization and expression of SMAD2 and YAP in HUVECs. Scare bar = 20μm. *P < 0.05, **P < 0.01, the variables between two groups were compared using Student's t test. For variables of more than two groups, statistical analysis was performed by one-way ANOVA followed by the SNK-q post hoc test. Data are shown as the mean ± SD, n = 6 in each group in this figure.

Figure 5

Suppression of the Merlin/YAP/SMAD2 pathway attenuates NET-induced EndMT. (A) Immunofluorescence images showing the localization and expression of Snail-1 and CD31. Scare bar = 100μm. (B) Western blotting analysis of Merlin/NF2, YAP, SMAD2, FSP-1, Snail-1, VE-cad, and CD31. β-actin is used as a loading control. (C) EC proliferation was analyzed by BrdU incorporation assay. EC migration was reported as migration speed (mm/h). Representative Matrigel assay images and quantification as total tubule length values are means ± SD. The cell membrane capacitance was also quantitatively compared. Scale bar = 500μm. (D) Western blotting analysis of YAP, p-YAP, SMAD2, FSP-1, Snail-1, VE-cad, and CD31. β-actin is used as a loading control. *P < 0.05, **P < 0.01, the variables between two groups were compared using Student's t test. For variables of more than two groups, statistical analysis was performed by one-way ANOVA followed by the SNK-q post hoc test. Data are shown as the mean ± SD, n = 6 in each group in this figure.

Figure 6

NETosis Inhibition accelerate wound healing by reducing EndMT and promoting angiogenesis in a diabetic mouse model (A) Left, representative images of treated wounds at 0, 3, 6, and 9 d post-wound injury in non-diabetic, STZ-diabetic, Padi4-/-, and STZ-diabetic + Padi4-/- groups. Right, level of wound closure is expressed as a percentage of wound area from the initial wound area. Scare bar = 500μm. (B) Epithelial gap of wound healing on histology was evaluated in non-diabetic, STZ-diabetic, Padi4-/-, and STZ-diabetic + Padi4-/- groups. The distance between the leading edges was calculated. Scare bar = 100μm. (C) Time for complete wound healing in different groups. (D) Representative color laser Doppler images taken at 5 days post-wounding in non-diabetic, STZ-diabetic, Padi4-/-, and STZ-diabetic + Padi4-/- groups. The chart shows the level of wound perfusion in mice (calculated as the ratio between treated and control blood flow). (E) Western blotting showing the upregulated expression of Snail-1 and downregulation of CD-31 in wound tissue from STZ-diabetic group compared with non-diabetic, Padi4^-/- or STZ-diabetic + Padi4^-/- groups. *P < 0.05, **P < 0.01, the variables between two groups were compared using Student's t test. For variables of more than two groups, statistical analysis was performed by one-way ANOVA followed by the SNK-q post hoc test. Data are shown as the mean ± SD, n = 6 in each group in this figure.

Figure 7

Hypothetical model of NET participation in delayed healing of diabetic wounds by inducing endothelial-to-mesenchymal transition via the Hippo-YAP pathway. Diabetic wound environment primes neutrophils to form NETs. NETs induce the activation of PAK2 via the membrane receptor TLR-9 in ECs. PAK2 phosphorylates the intracellular protein Merlin/NF2 to inhibit the Hippo-YAP signaling pathway. YAP binds to the transcription factor SMAD2. Then they translocate from the cytoplasm into the nucleus together to further induce the endothelial-to-mesenchymal transformation, which impedes angiogenesis and delays wound healing.