Chronic exposure to tumor necrosis factor alpha induces retinal pigment epithelium cell dedifferentiation

Abstract

Background: The retinal pigment epithelium (RPE) is a monolayer of pigmented cells with important barrier and immuno-suppressive functions in the eye. We have previously shown that acute stimulation of RPE cells by tumor necrosis factor alpha (TNFα) downregulates the expression of OTX2 (Orthodenticle homeobox 2) and dependent RPE genes. We here investigated the long-term effects of TNFα on RPE cell morphology and key functions in vitro.

Methods: Primary porcine RPE cells were exposed to TNFα (at 0.8, 4, or 20 ng/ml per day) for 10 days. RPE cell morphology, phagocytosis, barrier- and immunosuppressive-functions were assessed.

Results: Chronic (10 days) exposure of primary RPE cells to TNFα increases RPE cell size and polynucleation, decreases visual cycle gene expression, impedes RPE tight-junction organization and transepithelial resistance, and decreases the immunosuppressive capacities of the RPE. TNFα-induced morphological- and transepithelial-resistance changes were prevented by concomitant Transforming Growth Factor β inhibition.

Conclusions: Our results indicate that chronic TNFα-exposure is sufficient to alter RPE morphology and impede cardinal features that define the differentiated state of RPE cells with striking similarities to the alterations that are observed with age in neurodegenerative diseases such as age-related macular degeneration.

Keywords: Age-related macular degeneration; Neurodegenerative disease; Neuroinflammation; Retinal pigment epithelium; Transforming growth factor beta; Tumor necrosis factor alpha.

Fig. 1

Chronic exposure to activated monocyte supernatants or TNFα increases the percentage of enlarged, multinucleated RPE cells. Porcine retinal pigment epithelium (RPE) cells were cultured with or without lipopolysaccharide activated monocyte supernatants (Mo SN) or TNFα added daily at different concentrations for a total of 10 days. a Representative pictures of Zonula Occludens (ZO)1 (green) and Hoechst (blue) immunohistochemistry of control, Mo SN, and TNFα-exposed RPE. Automated quantifications by Arrayscan of b the number of RPE cells, c RPE cell size, d the number of multinucleated RPE cells (≥ 2 nuclei), and e total number of nuclei per mm² in the indicated different conditions. Representative images of 10-day TNFα-exposed RPE cell-cultures of f a co-culture of 50% RPE cells labeled with Carboxyfluorescein succinimidyl ester (CFSE) (green) and 50% RPE cells labeled with Far-red CFSE (red), and g ZO-1- (green) and Hoechst nuclear- (blue) stain of cultures maintained in the presence of EDU (5-ethynyl-2′-deoxyuridine, red). (n = 5/group, one way ANOVA or Mann-Whitney, comparison versus control: *P < 0.05, **P < 0.005*** P < 0.0005)

Fig. 2

Chronic exposure to activated monocyte supernatants or TNFα decreases visual cycle gene expression in the RPE. a Representative pictures of RPE staining with OTX2 (Orthodenticle homeobox 2, red) antibody and Arrayscan fluorescence intensity quantification of OTX-2 staining after 10 days of culture with or without lipopolysaccharide-activated monocyte supernatants (Mo SN) or TNFα added daily at different concentrations. b TTR (transthyretin) and c RPE65 (retinal pigment epithelium specific 65 kDa protein)-mRNA expression normalized with S26 expression quantified by RT-qPCR of 10-day RPE culture exposed to the indicated TNFα concentrations (n = 5/group one-way ANOVA or Mann-Whitney, comparison versus control * P < 0.05,**P < 0.005, ***P < 0.0005)

Fig. 3

Chronic exposure to TNFα disrupts RPE barrier properties. a Measurements of RPE transepithelial electric resistance (TER) measured daily in a 10-day trans-well culture with or without different concentrations of TNFα (n = 3/group, one-way ANOVA, versus control for each time point *P < 0.05, **P < 0.005, ***P < 0.0005). b Representative pictures of RPE staining with Zonula occludens(ZO) 1 (green) and F actin (Phalloidin, red). c–e Relative expression of OCLD (Occludin), CLD19 (Claudin-19), and ACTA2 (Smooth muscle alpha (a)-2 actin) mRNA expression normalized with S26 quantified by RT-qPCR of 10-day RPE culture with or without the indicated TNFα concentrations (n = 5/group one-way ANOVA, versus control *P < 0.05, **P < 0.005, ***P < 0.0005)

Fig. 4

Chronic exposure to TNFα does not alter the phagocytic and rhodopsin degradation capabilities of RPE cells. a Quantification of relative levels of photoreceptor outer segment (POS) binding and b POS internalization by RPE cells in the indicated culture conditions (n = 5/group one-way ANOVA, versus control, non-significant differences). c Western blot analysis of Rhodopsin and β-actin protein after 6 and 24 h of culture of primary porcine RPE cells (pretreated with 10-day TNF-α at 0.8, 4, and 20 ng/mL) and photoreceptor outer segments (POS)

Fig. 5

Chronic exposure to TNFα impairs the immunosuppressive function of RPE cells. a Representative pictures of human monocytes (hMos, human hematopoietic transcription factor (PU1) staining, green) and RPE nuclei (Hoechst, blue) and b automated quantification of the number of human monocytes in a 24-h co-culture with RPE cells with or without previous 10-day pre-treatment with TNFα (at 0.8, 4, and 20 ng/ml) (n = 5/group, one way ANOVA versus control ***P < 0.0005)

Fig. 6

TNFα-induced TGF-ß expression mediates the RPE polynucleation and impairment of barrier properties. a TGFβ 1-mRNA expression normalized with S26 expression quantified by RT-qPCR of 2, and 10-day RPE culture exposed to 20 ng/ml of TNFα. b Representative pictures of Zonula Occludens (ZO)1 (green) and Hoechst (blue) immunohistochemistry of control, TNFα(20 ng/ml), and TNFα(20 ng/ml) + antiTGFβ (500 nM)-exposed RPE. Quantifications of the number of multinucleated RPE cells (≥ 2 nuclei) in the indicated conditions. (a, b, n = 5/group, one-way ANOVA or Mann-Whitney versus control * P < 0.05, **P < 0.005, ***P < 0.0005). c Representative pictures of RPE staining with Zonula occludens (ZO) 1 (green) and F actin (Phalloidin, red) after 10 days of culture in the indicated conditions. d RPE transepithelial electric resistance (TER) measured daily in a 10-day trans-well culture with or without TNFα (20 ng/ml) and TNFα (20 ng/ml) + antiTGF-β (500 nM) (n = 3/group, *P < 0.05 one-way ANOVA of control versus TNFα and TNFα + antiTGF-β for each time point, ϒ P < 0.05 Mann-Whitney of TNFα + antiTGF-β versus TNFα for each time point)