eNOS-induced vascular barrier disruption in retinopathy by c-Src activation and tyrosine phosphorylation of VE-cadherin

Abstract

Background: Hypoxia and consequent production of vascular endothelial growth factor A (VEGFA) promote blood vessel leakiness and edema in ocular diseases. Anti-VEGFA therapeutics may aggravate hypoxia; therefore, therapy development is needed.

Methods: Oxygen-induced retinopathy was used as a model to test the role of nitric oxide (NO) in pathological neovascularization and vessel permeability. Suppression of NO formation was achieved chemically using L-NMMA, or genetically, in endothelial NO synthase serine to alanine (S1176A) mutant mice.

Results: Suppression of NO formation resulted in reduced retinal neoangiogenesis. Remaining vascular tufts exhibited reduced vascular leakage through stabilized endothelial adherens junctions, manifested as reduced phosphorylation of vascular endothelial (VE)-cadherin Y685 in a c-Src-dependent manner. Treatment with a single dose of L-NMMA in established retinopathy restored the vascular barrier and prevented leakage.

Conclusions: We conclude that NO destabilizes adheren junctions, resulting in vascular hyperpermeability, by converging with the VEGFA/VEGFR2/c-Src/VE-cadherin pathway.

Funding: This study was supported by the Swedish Cancer foundation (19 0119 Pj ), the Swedish Research Council (2020-01349), the Knut and Alice Wallenberg foundation (KAW 2020.0057) and a Fondation Leducq Transatlantic Network of Excellence Grant in Neurovascular Disease (17 CVD 03). KAW also supported LCW with a Wallenberg Scholar grant (2015.0275). WCS was supported by Grants R35 HL139945, P01 HL1070205, AHA MERIT Award. DV was supported by grants from the Deutsche Forschungsgemeinschaft, SFB1450, B03, and CRU342, P2.

Keywords: Src; VE-cadherin; cell biology; medicine; mouse; nitric oxide; retinal vasculature; retinopathy of prematurity; vascular barrier.

Figure 1.. Suppressed tuft formation in the Nos3^{S1176A/S1176A} retina after OIR-challenge.

(A) Outline of OIR-challenge protocol; pups were placed in 75% O₂ (hyperoxia) between P7 and P12, followed by return to normal atmosphere (relative hypoxia) until P17. (B) Schematic representation of vascular abnormalities after OIR in P17 retinas. (C) Nitric oxide formation determined using a Griess assay, expressed as the combined concentration of nitrite and nitrate, the end products of NO, reacting with molecules in biological fluids. Mean ± S.E.M. n = 3 mice/genotype. ****p<0.0001; t-test. (D) Representative images of whole mount retinas from Nos3^+/+ and Nos3^{S1176A/S1176A} mice, collected at P17 after OIR-challenge, stained with isolectin B4 (IB4). Avascular area is marked in magenta and tufts in blue. Scale bar = 500 µm. (E, F) Tuft area (E) and avascular area (F) expressed as percentage of total vascular area at P17. (G, H) Tuft size in µm2 (G) and total number/FOV in P17 mice (H). For (E–H): mean ± S.E.M. n = 7 (Nos3^+/+) and 5 (Nos3^{S1176A/S1176A}) mice. *p<0.05; t-test.

Figure 1—figure supplement 1.. Postnatal development of Nos3^+/+ and Nos3^{S1176A/S1176A} retinal vasculature.

(A) Representative images of Nos3^+/+ and Nos3^{S1176A/S1176A} retinas collected at P7, stained with isolectin B4 (IB4). (B, C) Quantification of vascular area (B) and outgrowth from the optic nerve (C) at P7 in Nos3^+/+ and Nos3^{S1176A/S1176A} pups. (D) Representative images of the vessel front from whole mount retinas collected at P7 stained with Isolectin-B4 (IB4, red, upper), ERG (yellow, upper), and CD34 (green, lower), to visualize vessel outgrowth and tip cells in Nos3^+/+ and Nos3^{S1176A/S1176A} retinal vasculature. Scale bar = 50 µm. (E–G) Filopodia length (E), tip cell number (F), branch points (G) in Nos3^+/+ and Nos3^{S1176A/S1176A} retinas at P7. Mean ± S.E.M. n = 3 (Nos3^+/+) and 4 (Nos3^{S1176A/S1176A}) mice, five to six images per mouse; t-test.

Figure 1—figure supplement 2.. Retina characteristics in Nos3^+/+ and Nos3^{S1176A/S1176A} P12 pups.

(A) Representative images of whole mount Nos3^+/+ and Nos3^{S1176A/S1176A} retinas collected at P12 after the vessel destruction phase of OIR and before vessel regrowth, stained with isolectin B4 (IB4). Scale bar = 500 µm. (B) Avascular area in Nos3^+/+ and Nos3^{S1176A/S1176A} retinas at P12 after OIR. n = 4 (Nos3^+/+) and 5 (Nos3^{S1176A/S1176A}) mice, three independent experiments; t-test.

Figure 1—figure supplement 3.. Pericytes, macrophage influx, and vascular perfusion in OIR-challenged Nos3^+/+ and Nos3^{S1176A/S1176A} retinas.

(A) Representative images of tufts visualized by IB4 binding and co-stained for NG2 (red) to mark pericytes in Nos3^+/+ and Nos3^{S1176A/S1176A} retinas collected at P17. Scale bar = 100 μm. (B) Pericyte coverage expressed as the NG2-positive area normalized to the IB4 area. Mean ± S.E.M. n = 4 (Nos3^+/+) and 4 (Nos3^{S1176A/S1176A}) mice. t-test. (C) Representative images of one leaf of the retina (IB4) co-stained for CD68 (yellow) to mark circulatory/tissue macrophages in Nos3^+/+ and Nos3^{S1176A/S1176A} retinas collected at P17. Scale bar = 200 μm. (D) The number of CD68-positive macrophages in the entire retina represented by particle number, normalized to the retina area. Mean ± S.E.M. n = 4 (Nos3^+/+) and 4 (Nos3^{S1176A/S1176A}) mice. t-test. (E) Representative images of tufts with circulating tomato lectin (green), co-stained with IB4 in Nos3^+/+ and Nos3^{S1176A/S1176A} retinas collected at P17. Scale bar = 100 μm. (F) Tuft perfusion, expressed as the area of tomato lectin normalized to the IB4 area. Mean ± S.E.M. n = 4 (Nos3^+/+) and 4 (Nos3^{S1176A/S1176A}) mice. *p<0.05; t-test.

Figure 1—figure supplement 4.. Expression of Nos2, Nos3, and Vegfa in Nos3^+/+ and Nos3^{S1176A/S1176A} retinas.

(A–C) qPCR of Nos3 (A), Nos2 (B), and Vegfa (C) expression in P17 normoxic and OIR-challenged Nos3^+/+ and Nos3^{S1176A/S1176A} mouse retinas. (D, E) Relative levels of Nos2 and Nos3 compared against standard curves of TBP and UBC in Nos3^+/+ (D) and Nos3^{S1176A/S1176A} (E) retinas. Mean ± S.E.M. n = 5 (Nos3^+/+) and 5 (Nos3^{S1176A/S1176A}) mice. Three independent experiments. *, **, ***p<0.05, 0.01, 0.001; two-way ANOVA, Sidak’s multiple comparison test.

Figure 2.. Suppressed c-Src Y418 and VE-cadherin Y685 phosphorylation in Nos3^{S1176A/S1176A} retinas and isolated endothelial cells.

(A) Representative maximum intensity projections of similar sized tufts from Nos3^+/+ and Nos3^{S1176A/S1176A} retinas showing VE-cadherin (green), pY685 VE-cadherin (red), and isolectin B4 (IB4; cyan). Scale bar = 50 μm. (B) Ratio of pY685 positive area/total VE-cadherin positive area. Mean ± S.E.M n = 3–6 images per group from 5 (Nos3^+/+) and 5 (Nos3^{S1176A/S1176A}) mice, three independent experiments, *p<0.05; t-test. (C) Representative images of VE-cadherin staining (green) and proximity ligation assay (PLA) to detect c-Src pY418 (magenta) in isolated mouse lung endothelial cells (iEC) from Nos3^+/+ and Nos3^{S1176A/S1176A} mice. Scale bar = 20 µM. (D) c-Src pY418 PLA dots detected in PBS and VEGFA (50 ng/mL)-treated iECs from Nos3^+/+ and Nos3^{S1176A/S1176A} mouse lungs. Data expressed as the number of dots per field of view. (E) c-Src pY418 PLA dots co-localized with VE-cadherin (green), normalized against total VE-cadherin area in the field of view. Mean ± S.E.M. Cells isolated from n = 4 (Nos3^+/+) and 4 (Nos3^{S1176A/S1176A}) mice, from three separate experiments. *, **p<0.05, 0.01; two-way ANOVA, Sidak’s multiple comparisons test.

Figure 2—figure supplement 1.. VEGFA induced eNOS phosphorylation and activity in vitro.

(A) Effect of VEGFA (V; 50 ng/mL; 1, 5, 10 min), histamine (H; 10 µM, 1, 5, 10 min), or medium (C, control) on eNOS phosphorylation at S1177 in cultured Human Retinal Microvascular Endothelial Cells (HRMEC). (B) Quantification of eNOS pS1177/total eNOS normalized to tubulin. Mean ± S.E.M. n = 3 independent experiments. *p<0.05; two-way ANOVA, Sidak’s multiple comparison test. (C) Antibody validation by immunoblotting for eNOS on HRMECs transfected with a control siRNA or Nos3-specific siRNA followed by treatment with VEGFA (50 ng/mL; 5 min). (D) Antibody validation by immunoblotting for eNOS pS1177 on HRMECs transfected with a control siRNA or Nos3-specific siRNA followed by treatment with VEGFA (50 ng/mL; 5 min). (E) Quantification of NO production in HRMECs treated with PBS or VEGFA (50 ng/mL, for 1, 5, or 10 min) using the cell-permeable fluorescent probe DAF-FM DA. (F) Quantification of NO production in HRMECs pre-treated with PBS or L-NMMA (1 mM) before VEGFA stimulation (50 ng/mL, 5 min). Mean ± S.E.M. n = 12, three independent experiments. *, **, ****p<0.05, 0.01, 0.0001; two-way ANOVA, Sidak’s multiple comparison test.

Figure 2—figure supplement 2.. VEGFA induced phosphorylation of eNOS, AKT, VE-cadherin, and c-Src in vitro.

(A) Representative immunoblots and the effect of VEGFA (50 ng/mL; 1, 5, 10, 30 min) on eNOS, eNOS pS1177, AKT, AKT pS473, VE-cadherin, VE-cadherin pY685, c-Src, SFK pY418, and tubulin in cultured Human Retinal Microvascular Endothelial Cells (HRMEC) treated with a PBS vehicle or 1 mM L-NMMA for 1 hr. (B) Quantification of eNOS pS1177/total eNOS (normalized to tubulin). (C) Quantification of AKT pS473/total AKT (normalized to tubulin). (D) Quantification of VE-cadherin pY685/total VE-cadherin (normalized to tubulin). (E) Quantification of SFK pY418/total c-Src (normalized to tubulin) Mean ± S.E.M. n = 3 independent experiments. *, ***p<0.05, 0.001 (indicates significance between vehicle and L-NMMA-treated samples, stimulated with VEGFA as indicated). Two-way ANOVA, Sidak’s multiple comparison test.

Figure 2—figure supplement 3.. c-Src pY418 immunostaining and PLA controls.

(A) Representative maximum intensity projections of tufts from Nos3^+/+ and Nos3^{S1176A/S1176A} retinas immunostained for VE-cadherin (green), c-Src pY418 (red), and IB4 (cyan). (B) Quantification of pY418-positive area/total VE-cadherin area. n = 3 images per group from 3 (Nos3^+/+) and 4 (Nos3^{S1176A/S1176A}) mice from two separate experiments; t-test. (C) Representative images of VE-cadherin staining (green) and negative controls for proximity ligation in isolated mouse lung endothelial cells (iEC) from Nos3^+/+ mice. Controls were performed by incubation with only one of the necessary antibodies or, one of the PLUS or MINUS PLA probes (mouse and rabbit secondary antibodies), which should inhibit rolling circle DNA synthesis. This allows for the detection of non-specific ligation or uncontrolled rolling circle DNA synthesis. Scale bar = 20 µm.

Figure 3.. Suppressed microsphere leakage in Nos3^{S1176A/S1176A} retinas.

(A) Representative images of similar sized tufts from Nos3^+/+ and Nos3^{S1176A/S1176A} mice showing isolectin B4 (IB4; red), and leakage of tail-vein injected FITC-conjugated 25 nm microspheres (cyan) around the tufts. Scale bar = 100 µM. Lower panels show leakage maps. Dots that do not overlap with vessels (beige) are considered extravascular. (B) Quantification of the average area of extravascular microspheres normalized to IB4 area. Mean ± S.E.M. n = 4 (Nos3^+/+) and 4 (Nos3^{S1176A/S1176A}) mice, 6–15 images per mouse. *p<0.05, t-test.

Figure 4.. OIR-challenged mice treated with NO inhibitor L-NMMA.

(A) Representative images of whole mount retinas from PBS- and L-NMMA-treated (P12–P16) wild-type C57Bl/6 mice, collected on P17 after OIR-challenge, and stained with isolectin B4 (IB4). Avascular area as a result of OIR is marked in magenta and tufts in blue. Scale bar = 500 µm. (B, C) Tuft area and avascular area expressed as percentage of total vascular area at P17. (D, E) Tuft size in µm² and total number of tufts/field of vision at P17. Mean ± S.E.M. n = 8 (PBS) and 9 (L-NMMA) treated mice. *, **p<0.05, 0.01; t-test. (F) Representative images of whole mount IB4-stained P17 retinas from OIR-challenged VEC-WT and VEC-Y685F mice injected with PBS or L-NMMA during P12-P16. Avascular area is marked in magenta and tufts in blue. Scale bar = 500 µm. (G) Tuft area normalized to total vascular area in PBS or L-NMMA-treated VEC-WT and VEC-Y685F retinas. (H) Avascular area normalized to total vascular area. Mean ± S.E.M. n = 8 (VEC-WT) and 8 (VEC-Y685F) mice. **, ***p<0.01, 0.001; two-way ANOVA, Sidak’s multiple comparison test.

Figure 4—figure supplement 1.. Pericytes, macrophage influx, and vascular perfusion in OIR-challenged WT retinas treated with PBS or L-NMMA.

(A) Representative images of tufts visualized by IB4 binding and co-stained for NG2 (red) to mark pericytes in PBS and L-NMMA-treated retinas collected at P17. Scale bar = 100 μm. (B) Pericyte coverage expressed as the NG2-positive area normalized to the IB4 area. Mean ± S.E.M. n = 4 (PBS) and 4 (L-NMMA) mice. t-test. (C) Representative images of one leaf of the retina (IB4) co-stained for CD68 (yellow) to mark circulatory/tissue macrophages in PBS and L-NMMA treated retinas collected at P17. Scale bar = 200 μm. (D) The number of CD68-positive macrophages in the entire retina represented by particle number, normalized to the retina area. Mean ± S.E.M. n = 4 (Nos3^+/+) and 4 (Nos3^{S1176A/S1176A}) mice. t-test. (E) Representative images tufts with circulating tomato lectin (green) co-stained with IB4 in PBS- and L-NMMA-treated retinas collected at P17. Scale bar = 100 μm. (F) Tuft perfusion, expressed as the tomato lectin area normalized to the IB4 area Mean ± S.E.M. n = 4 (PBS) and 4 (L-NMMA) mice. t-test.

Figure 5.. Decreased leakage from retinal vascular tufts after single-dose L-NMMA treatment.

(A) Representative images of tufts from Nos3^+/+ (wild type) mice treated with PBS or L-NMMA (60 µg/g body weight) 24 hr before tail-vein injection of 25 nm microspheres. Retinas were stained using isolectin B4 (IB4; cyan), microspheres (red) appear in and around the tufts. Scale bar = 100 µM. Lower panels show leakage maps. Dots that do not overlap with vessels (beige) are considered extravascular. (B) Quantification of the average area of extravascular microspheres normalized to IB4 area. (C) Quantification of the average area of extravascular microspheres normalized to total microsphere area. (D) Quantification of average total microsphere area in PBS- or L-NMMA-treated wild-type mouse retinas. (E) Quantification of tuft area normalized to total vascular area. Mean ± S.E.M. n = 5 (PBS) and 5 (L-NMMA) treated mice. *p<0.05; t-test.

Figure 5—figure supplement 1.. Pericytes, macrophage influx, and vascular perfusion in OIR-challenged WT retinas treated with a single injection of PBS or L-NMMA.

(A) Representative images of tufts visualized by IB4 binding and co-stained for NG2 (red) to mark pericytes in single-dose-treated PBS and L-NMMA retinas collected at P17. Scale bar = 100 μm. (B) Pericyte coverage expressed as the NG2-positive area normalized to the IB4 area. Mean ± S.E.M. n = 4 (PBS) and 4 (L-NMMA) mice. t-test. (C) Representative images of one leaf of the retina (IB4) co-stained for CD68 (yellow) to mark circulatory/tissue macrophages in single-dose-treated PBS and L-NMMA retinas collected at P17. Scale bar = 200 μm. (D) The number of CD68-positive macrophages in the entire retina represented by particle number, normalized to the retina area. Mean ± S.E.M. n = 4 (Nos3^+/+) and 4 (Nos3^{S1176A/S1176A}) mice. t-test. (E) Representative images tufts with circulating tomato lectin (green) co-stained with IB4 in single-dose-treated PBS and L-NMMA retinas collected at P17. Scale bar = 100 μm. (F) Tuft perfusion, expressed as the area of tomato lectin normalized to the IB4 area. Mean ± S.E.M. n = 4 (PBS) and 4 (L-NMMA) mice. t-test.

Figure 6.. eNOS/NO modulates VE-cadherin Y685 phosphorylation via c-Src in a VEGFA/VEGFR2-dependent manner.

VEGFA through VEGFR2 and its phosphosite Y1212 induces a chain of consecutive reactions in endothelial cells: phosphorylation of AKT at S473 and eNOS at S1176. The VEGFR2 phosphosite Y949 mediates phosphorylation of c-Src at Y418 and of VE-cadherin at Y685. Combined, these activating phosphorylation reactions disrupt the vascular barrier by dissociating VE-cadherin’s homophilic interactions, resulting in macromolecular leakage. eNOS/NO regulates activation of c-Src to enhance VE-cadherin Y685 phosphorylation and internalization.