Genome-wide analysis of DNA methylation in subjects with type 1 diabetes identifies epigenetic modifications associated with proliferative diabetic retinopathy

Abstract

Background: Epigenetic variation has been linked to several human diseases. Proliferative diabetic retinopathy (PDR) is a major cause of vision loss in subjects with diabetes. However, studies examining the association between PDR and the genome-wide DNA methylation pattern are lacking. Our aim was to identify epigenetic modifications that associate with and predict PDR in subjects with type 1 diabetes (T1D).

Methods: DNA methylation was analyzed genome-wide in 485,577 sites in blood from cases with PDR (n = 28), controls (n = 30), and in a prospective cohort (n = 7). False discovery rate analysis was used to correct the data for multiple testing. Study participants with T1D diagnosed before 30 years of age and insulin treatment within 1 year from diagnosis were selected based on 1) subjects classified as having PDR (cases) and 2) subjects with T1D who had had diabetes for at least 10 years when blood DNA was sampled and classified as having no/mild diabetic retinopathy also after an 8.7-year follow-up (controls). DNA methylation was also analyzed in a prospective cohort including seven subjects with T1D who had no/mild diabetic retinopathy when blood samples were taken, but who developed PDR within 6.3 years (converters). The retinopathy level was classified by fundus photography.

Results: We identified differential DNA methylation of 349 CpG sites representing 233 unique genes including TNF, CHI3L1 (also known as YKL-40), CHN2, GIPR, GLRA1, GPX1, AHRR, and BCOR in cases with PDR compared with controls. The majority of these sites (79 %) showed decreased DNA methylation in cases with PDR. The Natural Killer cell-mediated cytotoxicity pathway was found to be significantly (P = 0.006) enriched among differentially methylated genes in cases with PDR. We also identified differential DNA methylation of 28 CpG sites representing 17 genes (e.g. AHRR, GIPR, GLRA1, and BCOR) with P <0.05 in the prospective cohort, which is more than expected by chance (P = 0.0096).

Conclusions: Subjects with T1D and PDR exhibit altered DNA methylation patterns in blood. Some of these epigenetic changes may predict the development of PDR, suggesting that DNA methylation may be used as a prospective marker of PDR.

Fig. 1

Number of CpG sites with significantly higher (a) or lower (b) DNA methylation in cases with PDR versus controls. Genes involved in retina and eye development (c), inflammation (d), diabetic complications (e), and oxidative stress (f) were among the ones with one or more CpG sites differentially methylated between cases with PDR and controls (q <0.05); data are presented as mean ± SD. Global DNA methylation is calculated as average DNA methylation based on all CpG sites in each region on the chip and shows no differences between cases with PDR compared with controls in mean methylation value based on gene regions (g) or regions in relation to nearest CpG island (h)