Comparison of gene expression profile of epiretinal membranes obtained from eyes with proliferative vitreoretinopathy to that of secondary epiretinal membranes

Abstract

Background: Proliferative vitreoretinopathy (PVR) is a destructive complication of retinal detachment and vitreoretinal surgery which can lead to severe vision reduction by tractional retinal detachments. The purpose of this study was to determine the gene expression profile of epiretinal membranes (ERMs) associated with a PVR (PVR-ERM) and to compare it to the expression profile of less-aggressive secondary ERMs.

Methodology/principal findings: A PCR-amplified complementary DNA (cDNA) library was constructed using the RNAs isolated from ERMs obtained during vitrectomy. The sequence from the 5' end was obtained for randomly selected clones and used to generate expressed sequence tags (ESTs). We obtained 1116 nonredundant clusters representing individual genes expressed in PVR-ERMs, and 799 clusters representing the genes expressed in secondary ERMs. The transcriptome of the PVR-ERMs was subdivided by functional subsets of genes related to metabolism, cell adhesion, cytoskeleton, signaling, and other functions, by FatiGo analysis. The genes highly expressed in PVR-ERMs were compared to those expressed in the secondary ERMs, and these were subdivided by cell adhesion, proliferation, and other functions. Querying 10 cell adhesion-related genes against the STRING database yielded 70 possible physical relationships to other genes/proteins, which included an additional 60 genes that were not detected in the PVR-ERM library. Of these, soluble CD44 and soluble vascular cellular adhesion molecule-1 were significantly increased in the vitreous of patients with PVR.

Conclusions/significance: Our results support an earlier hypothesis that a PVR-ERM, even from genomic points of view, is an aberrant form of wound healing response. Genes preferentially expressed in PVR-ERMs may play an important role in the progression of PVR and could be served as therapeutic targets.

Figure 1. Known human genes identified in the human epiretinal membrane (ERM) associated with PVR (A) and secondary ERM (B) are grouped according to the KEGG functional categories.

Figure 2. Molecular networks associated with the genes expressed in ERMs associated with PVR (PVR-ERM) are shown.

Gene symbols of 10 cell adhesion-related genes (FN1, COL1A2, COL1A1, COL3A1, TIMP3, LGALS1, THBS1, DCN, POSTN, SPARC) from the PVR-ERM cDNA library were queried against the STRING database, and the predicted interactions for genes/proteins were obtained. Filled black circles represent the submitted 10 genes/proteins from the PVR-ERM cDNA library, and the white circles represent potentially expressed 60 genes in PVR-ERMs that are extracted in Silico. Of these, CD44 and VCAM-1 were examine by ELISA and are shown by arrows. The gene names are shown next to the circles. The edges connecting two circles represent the predicted functional associations. An edge is drawn with up to 7 differently colored lines. These lines represent the presence of the seven types of evidence used in predicting the associations. A red line indicates the presence of fusion evidence; a green line-neighborhood evidence; a blue line–co-occurrence evidence; a purple line-experimental evidence; a yellow line-textmining evidence; a light blue line-database evidence; and a black line–co-expression evidence.

Figure 3. sCD44 (A) and sVCAM-1 (B) concentrations in the vitreous fluid of patients with secondary ERM and proliferative vitreoretinopathy patients (PVR-ERM).

The levels of both sCD44 and sVCAM-1 were significantly higher in the patients with PVR than in the eyes with secondary ERM (*P<0.001).

Figure 4. Correlations of vitreous sCD44 and sVCAM-1 levels in patients with PVR.

There was a strong statistically significant correlation between the vitreous concentration of sCD44 and sVCAM-1 (r = 0.971;P<0.0001).