Methylation vs. Protein Inflammatory Biomarkers and Their Associations With Cardiovascular Function

Abstract

DNA methylation data can be used to estimate proportions of leukocyte subsets retrospectively, when directly measured cell counts are unavailable. The methylation-derived neutrophil-to-lymphocyte and lymphocyte-to-monocyte ratios (mdNLRs and mdLMRs) have proven to be particularly useful as indicators of systemic inflammation. As with directly measured NLRs and LMRs, these methylation-derived ratios have been used as prognostic markers for cancer, although little is known about them in relation to other disorders with inflammatory components, such as cardiovascular disease (CVD). Recently, methylation of five genomic cytosine-phosphate-guanine sites (CpGs) was suggested as proxies for mdNLRs, potentially providing a cost-effective alternative when whole-genome methylation data are not available. This study compares seven methylation-derived inflammatory markers (mdNLR, mdLMR, and individual CpG sites) with five conventionally used protein-based inflammatory markers (C-reactive protein, interleukins 6 and 10, tumor-necrosis factor alpha, and interferon-gamma) and a protein-based inflammation score, in their associations with cardiovascular function (CVF) and risk. We found that markers of CVF were more strongly associated with methylation-derived than protein-based markers. In addition, the protein-based and methylation-derived inflammatory markers complemented rather than proxied one another in their contribution to the variance in CVF. There were no strong correlations between the methylation and protein markers either. Therefore, the methylation markers could offer unique information on the inflammatory process and are not just surrogate markers for inflammatory proteins. Although the five CpGs mirrored the mdNLR well in their capacity as proxies, they contributed to CVF above and beyond the mdNLR, suggesting possible added functional relevance. We conclude that methylation-derived indicators of inflammation enable individuals with increased CVD risk to be identified without measurement of protein-based inflammatory markers. In addition, the five CpGs investigated here could be useful surrogates for the NLR when the cost of array data cannot be met. Used in tandem, methylation-derived and protein-based inflammatory markers explain more variance than protein-based inflammatory markers alone.

Keywords: cell counts; epidemiology; epigenetics; inflammation; lymphocyte-to-monocyte; neutrophil-to-lymphocyte.

Figure 1

Heat map of the partial Spearman correlations among protein-based and methylation-derived biomarkers of inflammation. Numeric values indicate Spearman's rho values while controlling for age and smoking status. The presence of color indicates p < 0.003 (α = 0.05/16, calculated as 4 × 4 independent inflammatory marker comparisons). The shades of color represent the strength and direction of the correlation. “Score” represents the average of the IL-6, IL-10, TNA-α, IFN-γ, and CRP z-scores. CRP, C-reactive protein; IFN-γ, interferon-gamma; IL-6, interleukin-6; IL-10, interleukin-10; mdLMR, methylation-derived lymphocyte-to-monocyte ratio; mdNLR, methylation-derived neutrophil-to-lymphocyte ratio; TNF-α, tumor necrosis factor-alpha.