Integrative Analyses of Circulating Proteins and Metabolites Reveal Sex Differences in the Associations with Cardiac Function among DCM Patients

Abstract

Dilated cardiomyopathy (DCM) is characterized by reduced left ventricular ejection fraction (LVEF) and left or biventricular dilatation. We evaluated sex-specific associations of circulating proteins and metabolites with structural and functional heart parameters in DCM. Plasma samples (297 men, 71 women) were analyzed for proteins using Olink assays (targeted analysis) or LC-MS/MS (untargeted analysis), and for metabolites using LC MS/MS (Biocrates AbsoluteIDQ p180 Kit). Associations of proteins (n = 571) or metabolites (n = 163) with LVEF, measured left ventricular end diastolic diameter (LVEDD^measured), and the dilation percentage of LVEDD from the norm (LVEDD^{acc. to HENRY}) were examined in combined and sex-specific regression models. To disclose protein-metabolite relations, correlation analyses were performed. Associations between proteins, metabolites and LVEF were restricted to men, while associations with LVEDD were absent in both sexes. Significant metabolites were validated in a second independent DCM cohort (93 men). Integrative analyses demonstrated close relations between altered proteins and metabolites involved in lipid metabolism, inflammation, and endothelial dysfunction with declining LVEF, with kynurenine as the most prominent finding. In DCM, the loss of cardiac function was reflected by circulating proteins and metabolites with sex-specific differences. Our integrative approach demonstrated that concurrently assessing specific proteins and metabolites might help us to gain insights into the alterations associated with DCM.

Keywords: Biocrates; DCM; LC MS/MS; OLINK; correlation; metabolomics; phenotype association; proteomics.

Figure 1

(A) Heatmap illustrating the significant associations of left ventricular ejection fraction (LVEF) and the plasma proteins in male DCM patients. Results from regression models were adjusted for age and BMI. The color gradient illustrates the false discovery rate (FDR) obtained after correction for multiple testing. A blue-to-orange color gradient highlights a linear association, with blue color indicating an inverse and orange color a positive association. A white-to-black color gradient highlights a non-linear association using restricted cubic splines. A black line within a box implies that the association is no longer significant after additional adjustment for aspartate amino transferase (ASAT) activity. An asterisk within a box implies that the FDR was truncated at a value of 5. In the targeted analyses, ten proteins were present on the inflammation and CVD II or III panel. To reduce redundancies, the results from the inflammation panel are not illustrated. (B) Categorization of 115 unique proteins by Gene Ontology terms. (C) Illustration of an exemplary non-linear, positive, and inverse association between selected proteins (MMP12, FCN3, GDF15) and LVEF.

Figure 2

(A) Heatmap illustrating the significant associations of left ventricular ejection fraction (LVEF) and the plasma metabolites with their respective substance classes in male DCM patients. Results from regression models were adjusted for age and BMI. The color gradient illustrates the false discovery rate (FDR) obtained after correction for multiple testing. A blue-to-orange color gradient highlights a linear association, with blue color indicating an inverse and orange color a positive association. A white-to-black color gradient highlights a non-linear association using restricted cubic splines. A black line within a box implies that the association is no longer significant after additional adjustment for aspartate amino transferase (ASAT) activity. (B) Illustration of an exemplary non-linear, positive, and inverse association between selected metabolites (C14:2, PC ae C38:0, kynurenine) and LVEF. PC = phosphatidylcholine.

Figure 3

Heatmap illustrating the correlation between proteins and metabolites that were significantly associated with LVEF. Spearman correlation coefficients are illustrated for those proteins and metabolites that had at least one correlation coefficient above |0.3|. The clustering was based on the average linkage method. Positive correlation coefficients are illustrated in green; negative correlation coefficients in purple. * In addition to the correlation coefficients, the effect estimates (ß) from the associations between the proteins and metabolites with LVEF are presented next to the protein and metabolite names. Positive associations are colored in orange; inverse associations in blue. Note that effects for non-linear associations are not displayed. In the targeted protein analyses, ten proteins were present on the inflammation and CVD II or III panel. To reduce redundancies, the results from the inflammation panel are not illustrated.