Wnt signaling activates MFSD2A to suppress vascular endothelial transcytosis and maintain blood-retinal barrier

Abstract

Breakdown of the blood-retinal barrier (BRB) causes retinal edema and vision loss. We investigated the role of Wnt signaling in maintaining the BRB by limiting transcytosis. Mice lacking either the Wnt co-receptor low-density lipoprotein receptor-related protein 5 (Lrp5^-/- ) or the Wnt ligand Norrin (Ndp^y/- ) exhibit increased retinal vascular leakage and enhanced endothelial transcytosis. Wnt signaling directly controls the transcription of an endothelium-specific transcytosis inhibitor, major facilitator superfamily domain-containing protein 2a (MFSD2A), in a β-catenin-dependent manner. MFSD2A overexpression reverses Wnt deficiency-induced transcytosis in endothelial cells and in retinas. Moreover, Wnt signaling mediates MFSD2A-dependent vascular endothelium transcytosis through a caveolin-1 (CAV-1)-positive caveolae pathway. In addition, levels of omega-3 fatty acids are also decreased in Wnt signaling-deficient retinas, reflecting the basic function of MFSD2A as a lipid transporter. Our findings uncovered the Wnt/β-catenin/MFSD2A/CAV-1 axis as a key pathway governing endothelium transcytosis and inner BRB integrity.

Fig. 1. Lrp5^−/− and Ndp^y/− mice have impaired BRB and increased number of transcytotic vesicles within their retinal vascular endothelium.

(A) One-month-old Lrp5^−/− and Ndp^y/− and their control mice (WT and Ndp^y/+) were intraperitoneally injected with sodium fluorescein followed by fluorescent fundus imaging after 2, 4, 6, and 8 min. Green: Fluorescein within retinal blood vessels and extravasated fluorescein. (B) FITC-conjugated 70-kDa dextran (green) was injected retro-orbitally into Lrp5^−/−, Ndp^y/−, and control mice at P17. Isolated retinas were stained with IB₄ (magenta), with Lrp5^−/− and Ndp^y/− retinas showing pathological glomeruloid vascular structures. Vascular leakage was quantified by leakage intensity of extravasated FITC-conjugated dextran. (C) TEM images show transcytotic vesicles in the retinal vessel endothelium of 3-month-old Lrp5^−/− and Ndp^y/− mice and their controls. Left: Transcytotic vesicles are categorized into three types: luminal (arrows) or abluminal (arrowheads) membrane-connected and cytoplasmic vesicles (asterisks). E, endothelial cell; L, lumen; P, pericyte. (D) Quantification of transcytotic vesicular density in EM images, normalized by EC area. (E and F) HRP was retro-orbitally injected to Lrp5^−/− (2 months old) and Ndp^y/− mice (3 months old) and their age-matched controls, followed by TEM. The blood vessel lumen in HRP-injected mice was filled with electron-dense DAB reaction (black). HRP-filled vesicles (white arrowheads) were observed in retinal ECs and quantified (normalized by EC area). Scale bars, 500 μm (A), 100 μm (B), and 500 nm (C and D). Data are expressed as individual values plus means ± SD. n = 3 to 6 mice per group. Statistical differences between groups were analyzed using two-tailed unpaired t tests. **P < 0.01, ***P < 0.001.

Fig. 2. MFSD2A levels are down-regulated in the retinas of Wnt signaling–deficient mice.

(A) mRNA levels of Mfsd2a were measured by RT-qPCR in Lrp5^−/− and Ndp^y/− retinas and their respective controls at P5, P8, P12, and P17. (B and C) Laser-captured microdissection (LCM) was used to isolate retinal blood vessels (red), outlined by the white dashed lines in (C) illustrating retinal cross-sections (left). Cell nuclei were stained with 4′,6-diamidino-2-phenylindole (DAPI) (blue). RGC, retinal ganglion cells; INL, inner nuclear layer; ONL, outer nuclear layer. (B) Enrichment of Mfsd2a mRNA levels in LCM isolated blood vessels compared with the whole retina. (C) Comparisons of Mfsd2a mRNA levels in the retinal vessels of Lrp5^−/−/Ndp^y/− mice with their controls. (D) Protein levels of MFSD2A in Lrp5^−/− and Ndp^y/− retinas were quantified and normalized by glyceraldehyde-3-phosphate dehydrogenase (GAPDH) levels. (E) Retinas were costained with MFSD2A and CD31, which colocalize in the WT eyes. MFSD2A staining is barely visible in Lrp5^−/− and Ndp^y/− retinas. Scale bars, 50 μm (B) and 100 μm (E). Data are expressed as individual values plus means ± SD. n = 3 to 6 per group. Statistical differences between groups were analyzed using two-tailed unpaired t tests. *P < 0.05, **P < 0.01.

Fig. 3. Wnt signaling modulates endothelial transcytosis through its direct target gene MFSD2A.

(A and B) Mfsd2a mRNA levels were increased in HRMEC treated with lithium chloride (LiCl), using control sodium chloride (NaCl). (C and D) Mfsd2a mRNA and protein levels were induced by Wnt3a-conditioned medium (Wnt3a-CM) and suppressed by the Wnt inhibitor XAV939. n-p-β-catenin, nonphosphorylated β-catenin. (E) Three promoter regions upstream of MFSD2A gene were identified containing putative Wnt-responsive TCF-binding motifs (TTCAAAG): P1 (−2841 to −2211 bp), P2 (−1900 to −1099 bp), and P3 (−1145 to −168 bp), followed by cloning and ligation with a luciferase reporter, and transfected with an active β-catenin plasmid in HEK293 cells. Luciferase activity was measured. (F) Mutation of TCF-binding site #1 (Mut-P1) (mutated to CCTGGGT) partially abolished the Wnt/β-catenin–responsive luciferase reporter activity compared with native P1. (G) Scheme of in vitro HRP transcytosis assay in ECs. (H and I) Transferred HRP in the lower chambers was measured to indicate the transcytosis levels through the EC monolayer. Activation of Wnt signaling activation was achieved by treatment with Wnt3a-CM (H) or human recombinant Norrin (I), and inhibition by XAV939 treatment. (J and K) siRNA targeting MFSD2A (si-M2A) suppressed MFSD2A mRNA (J) and protein levels (K) in HRMEC compared with si-control (si-Ctrl). (L) HRP-based in vitro transcytosis was used to detect transcytosis levels in HRMEC with Wnt3a-CM in combination with si-M2A or si-control (si-Ctrl) treatment (K). Data are expressed as individual values plus means ± SD. n = 3 to 4 per group. Statistical differences between groups were analyzed using a one-way analysis of variance (ANOVA) statistical test with Dunnett’s multiple comparisons tests or two-tailed unpaired t tests. *P < 0.05, **P < 0.01.

Fig. 4. CAV-1 levels and CAV-1–associated transcytosis are increased in Wnt-deficient retinas.

(A) mRNA levels of Cav-1 and Clathrin were measured in the retinas of Lrp5^−/− and Ndp^y/− mice and compared with their respective controls. (B) The protein levels of CAV-1 were detected by Western blot in the retinas of Lrp5^−/− and Ndp^y/− mice compared with their respective controls. (C) CAV-1) and IB₄ costaining in Lrp5^−/− and Ndp^y/− and their respective control retinas at P17. CAV-1 (green) and IB₄ (magenta) staining colocalize in the retina. Scale bar, 50 μm. GCL, ganglion cell layer. (D and E) CAV-1 was labeled with immunogold and imaged with electron microscopy (black dots, D). Scale bar, 200 nm. The numbers of Cav-1 associated vesicles were counted and normalized by EC area (E). Data are expressed as individual values plus means ± SD. n = 3 to 6 per group. Statistical differences between groups were analyzed using two-tailed unpaired t tests. *P < 0.05, **P < 0.01.

Fig. 5. Lentivirus overexpressing MFSD2A inhibits Wnt deficiency–induced up-regulation of caveolar transcytosis.

(A to C) HRMECs were treated with XAV939 to inhibit Wnt signaling and infected with Lenti-M2A to detect the effect of MFSD2A overexpression on Wnt signaling–induced up-regulation of CAV-1. (A) Protein levels were shown with Western blot. (B) Relative protein levels of nonphosphorylated β-catenin (n-p-β-catenin), MFSD2A, and CAV-1 were normalized by GAPDH. (C) Inhibition of Wnt signaling by XAV939 induced an increase of transferred HRP, while overexpression of MFSD2A reversed the changes. (D to G) Lenti-M2A and its control were injected intravitreally into Lrp5^−/− mice at P10. Mice were euthanized at P30. (D) Retinas were used to detect protein levels with Western blot. (E) Quantification of relative protein levels of MFSD2A and Cav-1 in lenti-M2A– and lenti-control–treated Lrp5^−/− retinas, normalized by GAPDH. (F) Fixed Lrp5^−/− retinas with lenti-M2A and lenti-control treatment were prepared for electron microscopy analysis. Transcytotic vesicles in the retinal vessel endothelia of Lrp5^−/− mice were categorized into three groups (representative images of three groups were shown in Fig. 1). Overexpression of MFSD2A by lentivirus decreased the transcytotic vesicles of type I (arrows) and type II (asterisks), but not type III (arrowheads). (G) CAV-1 was labeled with immunogold in Lrp5^−/− retinas treated with lenti-M2A and lenti-control, and immunogold was detected with electron microscopy (black dots). The numbers of CAV-1–associated vesicles were counted and normalized by EC area. Scale bars, 500 nm (F) and 200 nm (G). Data are expressed as individual values plus means ± SD. n = 3 per group. Statistical differences between groups were analyzed using an ANOVA statistical test with Dunnett’s multiple comparisons tests or two-tailed unpaired t tests. *P < 0.05, **P < 0.01.

Fig. 6. Fatty acid DHA and EPA levels are decreased in the retinas of Wnt signaling–deficient mice.

(A and B) Long-chain polyunsaturated fatty acids in the retina or brain were measured. Both DHA and EPA were down-regulated in the retinas of Lrp5^−/− and Ndp^y/− mice compared with their respective controls (A), but remained unchanged in the brains of the same mice (B). Data are expressed as individual values plus means ± SD. n = 4 per group. Statistical differences between groups were analyzed using two-tailed unpaired t tests. *P < 0.05, **P < 0.01. n.s., not significant. (C) Scheme illustration on the role of Wnt signaling in controlling inner BRB integrity by limiting MFSD2A-mediated EC caveolar transcytosis. Canonical Wnt signaling is activated by binding of the ligand (Norrin or Wnts) to the receptor complex containing Frizzed4 (FZD4) and co-receptors (LRP5 or LRP6), leading to the prevention of β-catenin ubiquitination and degradation. Stabilized β-catenin then translocates to the nucleus and works with TCF to bind the TCF-responsive motif in the promoter region of MFSD2A, directly regulating its gene transcription. MFSD2A protein is located on cellular plasma membrane to suppress CAV-1 protein levels and block the formation of CAV-1–positive caveolae, thereby limiting EC transcytosis and maintaining inner BRB integrity.