Microarray analysis of gene expression in West Nile virus-infected human retinal pigment epithelium

Abstract

Purpose: To identify key genes differentially expressed in the human retinal pigment epithelium (hRPE) following low-level West Nile virus (WNV) infection.

Methods: Primary hRPE and retinal pigment epithelium cell line (ARPE-19) cells were infected with WNV (multiplicity of infection 1). RNA extracted from mock-infected and WNV-infected cells was assessed for differential expression of genes using Affymetrix microarray. Quantitative real-time PCR analysis of 23 genes was used to validate the microarray results.

Results: Functional annotation clustering of the microarray data showed that gene clusters involved in immune and antiviral responses ranked highly, involving genes such as chemokine (C-C motif) ligand 2 (CCL2), chemokine (C-C motif) ligand 5 (CCL5), chemokine (C-X-C motif) ligand 10 (CXCL10), and toll like receptor 3 (TLR3). In conjunction with the quantitative real-time PCR analysis, other novel genes regulated by WNV infection included indoleamine 2,3-dioxygenase (IDO1), genes involved in the transforming growth factor-β pathway (bone morphogenetic protein and activin membrane-bound inhibitor homolog [BAMBI] and activating transcription factor 3 [ATF3]), and genes involved in apoptosis (tumor necrosis factor receptor superfamily, member 10d [TNFRSF10D]). WNV-infected RPE did not produce any interferon-γ, suggesting that IDO1 is induced by other soluble factors, by the virus alone, or both.

Conclusions: Low-level WNV infection of hRPE cells induced expression of genes that are typically associated with the host cell response to virus infection. We also identified other genes, including IDO1 and BAMBI, that may influence the RPE and therefore outer blood-retinal barrier integrity during ocular infection and inflammation, or are associated with degeneration, as seen for example in aging.

Figure 1

Quantification of West Nile virus infection in ARPE-19 and human retinal pigment epithelial (hRPE) cells using flow cytometry. Cells were infected with West Nile virus (WNV) at a multiplicity of infection (MOI) of 0.1, 1, and 10 (n=4), and after 24 h post infection, were fixed and permeabilized with the Cytofix/Cytoperm Fixation/Permeabilization Solution Kit (BD Biosciences) and stained with fluorescein isothiocyanate (FITC)-conjugated antibodies specific for WNV nonstructural protein 1. Cells were analyzed on a BD FACSCalibur flow cytometer. Data were analyzed using FlowJo (TreeStar software).

Figure 2

Hierarchical cluster analysis of microarray results. The columns labeled hRPE1C to hRPE4C and hRPE1V to hRPE4V are data from uninfected and West Nile virus (WNV)-infected primary human retinal pigment epithelium, respectively. ARPE-19C and ARPE-19V represent mock-infected and WNV-infected ARPE-19 cells, respectively. The data were generated using the GeneSpring GX10s (Agilent) Hierarchical Clustering feature, using the Pearson’s centered algorithm for difference measurement between conditions and Ward’s method as the criterion for linkage. ARPE-19 cells are most dissimilar from all primary hRPE cells for the mock-infected group. In the WNV-infected group, ARPE-19 cells are more similar to hRPE3 and hRPE4 cells. The image presented is an arbitrarily selected segment of the whole genome signal expression and is shown to highlight the similarity between the genome profiles between patient samples and the ARPE-19 cell line. Although not shown, there were many areas of equal similarity. Red represents high expression, yellow represents moderate expression, and blue represents low expression.

Figure 3

Comparison of differential gene expression with microarray (red) and qPCR (blue). Genes are allocated to the graphs shown here, according to fold-change of expression after WNV infection, as determined by qPCR, with microarray values shown adjacent to these. A: qPCR fold change −10 to 20; (B) qPCR fold change 20 to 120, and (C) qPCR fold change >120. qPCR reactions were performed in duplicate and both qPCR and microarray data used the same RNA as the source. Samples were isolated from 4 separate donors. Genes in qPCR were amplified using Taqman probes and Taqman Universal PCR master mix (Applied Biosystems). *p<0.05 as evaluated by paired Student t-test, compared to matched, uninfected donor samples.

Figure 4

Fold changes in expression of genes not seen to change on the microarray, as shown by qPCR. All qPCR reactions were performed in duplicate on cDNA extracted from 4 separate donors. Genes were amplified using Taqman probes and Taqman Universal PCR master mix (Applied Biosystems). Genes were selected for further qPCR analysis, based on the immune and TGF-β gene groups of interest seen in the microarray analysis. Statistical analysis was undertaken using the REST program (Qiagen), which uses a pair-wise fixed reallocation randomization test to determine significance. Averaged values of duplicate samples from 4 separate donors were statistically analyzed. However, despite appreciable fold-changes in some samples, only TNF and TGF-β2 genes in WNV-infected RPE were statistically different from uninfected RPE. * represents p<0.05.

Figure 5

Simplified TGF-β pathway. Several genes in this pathway are included in our analysis (TGFβ 1/2, BAMBI, ATF3, ID1), as well as associated genes that were not analyzed (TGF-β RI/II, SMAD3). TGF-β1 or 2 binds to the TGF-β RI and RII receptor complex, and results in signal transduction. However, if the TGFβ ligand binds to a BAMBI/TGF-β RI complex, this signal is not transduced. TGF-β signaling can lead to the binding of SMAD3 with ATF3. This complex can go on to repress the transcription of ID1. Independently of the TGF-β pathway, DDIT3 protein can inhibit the transcription of ATF3, while ATF3 can also suppress the transcription of DDIT3 (insert).