Acceleration of age-associated methylation patterns in HIV-1-infected adults

Abstract

Patients with treated HIV-1-infection experience earlier occurrence of aging-associated diseases, raising speculation that HIV-1-infection, or antiretroviral treatment, may accelerate aging. We recently described an age-related co-methylation module comprised of hundreds of CpGs; however, it is unknown whether aging and HIV-1-infection exert negative health effects through similar, or disparate, mechanisms. We investigated whether HIV-1-infection would induce age-associated methylation changes. We evaluated DNA methylation levels at >450,000 CpG sites in peripheral blood mononuclear cells (PBMC) of young (20-35) and older (36-56) adults in two separate groups of participants. Each age group for each data set consisted of 12 HIV-1-infected and 12 age-matched HIV-1-uninfected samples for a total of 96 samples. The effects of age and HIV-1 infection on methylation at each CpG revealed a strong correlation of 0.49, p<1 x 10(-200) and 0.47, p<1 x 10(-200). Weighted gene correlation network analysis (WGCNA) identified 17 co-methylation modules; module 3 (ME3) was significantly correlated with age (cor=0.70) and HIV-1 status (cor=0.31). Older HIV-1+ individuals had a greater number of hypermethylated CpGs across ME3 (p=0.015). In a multivariate model, ME3 was significantly associated with age and HIV status (Data set 1: βage=0.007088, p=2.08 x 10(-9); βHIV=0.099574, p=0.0011; Data set 2: βage=0.008762, p=1.27 x 10(-5); βHIV=0.128649, p=0.0001). Using this model, we estimate that HIV-1 infection accelerates age-related methylation by approximately 13.7 years in data set 1 and 14.7 years in data set 2. The genes related to CpGs in ME3 are enriched for polycomb group target genes known to be involved in cell renewal and aging. The overlap between ME3 and an aging methylation module found in solid tissues is also highly significant (Fisher-exact p=5.6 x 10(-6), odds ratio=1.91). These data demonstrate that HIV-1 infection is associated with methylation patterns that are similar to age-associated patterns and suggest that general aging and HIV-1 related aging work through some common cellular and molecular mechanisms. These results are an important first step for finding potential therapeutic targets and novel clinical approaches to mitigate the detrimental effects of both HIV-1-infection and aging.

Fig 1. Age effects versus HIV-1 effects on methylation status.

Methylation differences for each of the 24 pairs of samples were calculated and a paired t-test was performed for each of the CpG sites on the 450K array. The HIV-1 effect (X-axis) was measured as the signed logarithm of the Student t-test p-value. Age effects (Y-axis) were measured by the Pearson correlation coefficient with age. Each dot is colored according to its module membership (See Fig. 2). This is a representative figure for both data sets.

Fig 2. Relating modules to HIV-status and age.

Co-methylation modules for HIV-1 status and aging (A) were identified using the blockwise modules function in WCGNA R package. The significant p values for the modules are indicated as follows: * = p≤0.05, ** = p≤0.01, *** = p≤0.001 (B) A box plot depicting module 3 versus age and HIV status.

Fig 3. Heat map of module-trait relationships.

This heat map shows correlations between HIV status, chronological age, and the co-methylation module (represented by their eigenvectors) for data set one (A) and data set two (B). Included are cell subsets whose absolute numbers have an absolute correlation with module 3 that was ≥0.4. Red depicts a positive correlation, blue depicts a negative correlation, as indicated by the color band on the right.