Visceral Adipose Tissue Phospholipid Signature of Insulin Sensitivity and Obesity

Abstract

Alterations in visceral adipose tissue (VAT) are closely linked to cardiometabolic abnormalities. The aim of this work is to define a metabolic signature in VAT of insulin resistance (IR) dependent on, and independent of, obesity. An untargeted UPLC-Q-Exactive metabolomic approach was carried out on the VAT of obese insulin-sensitive (IS) and insulin-resistant subjects (N = 11 and N = 25, respectively) and nonobese IS and IR subjects (N = 25 and N = 10, respectively). The VAT metabolome in obesity was defined among other things by changes in the metabolism of lipids, nucleotides, carbohydrates, and amino acids, whereas when combined with high IR, it affected the metabolism of 18 carbon fatty acyl-containing phospholipid species. A multimetabolite model created by glycerophosphatidylinositol (18:0); glycerophosphatidylethanolamine (18:2); glycerophosphatidylserine (18:0); and glycerophosphatidylcholine (18:0/18:1), (18:2/18:2), and (18:2/18:3) exhibited a highly predictive performance to identify the metabotype of "insulin-sensitive obesity" among obese individuals [area under the curve (AUC) 96.7% (91.9-100)] and within the entire study population [AUC 87.6% (79.0-96.2)]. We demonstrated that IR has a unique and shared metabolic signature dependent on, and independent of, obesity. For it to be used in clinical practice, these findings need to be validated in a more accessible sample, such as blood.

Keywords: biomarker; diabetes; discordant phenotypes; insulin resistance; lipid remodeling; metabolomics; metabotype; obesity; phospholipids.

Figure 1

Selected metabolites from the comparison between obese and nonobese subjects by random forest. (A) Summary of the chemical classes of the selected metabolites. (B) Mean and standard error of the logarithmic transformation of the levels of the discriminant metabolites in the obese subjects (white bars) and those of normal weight (colored and sorted according to the class of the metabolites). (C) Hierarchical clustered Spearman correlation matrix of the selected metabolites and anthropometric and clinical parameters by random forest analysis of obese and nonobese subjects. Adjusted p-values with the significant threshold set at <0.05 are marked with +. Positive correlations are in blue, and negative correlations are in red.

Figure 2

VAT metabolome of the discordant phenotype of obesity. (A) Fold changes in the levels of lipid species between obese subjects with high insulin resistance and nonobese subjects with insulin sensitivity. Lipids significantly different between groups were marked in a dark color and with bold text (adjusted p-value < 0.25). (B) Spearman correlation matrix of the selected lipids with clinical variables. Adjusted p-values with a cutoff at <0.05 are marked with +. Positive correlations are in blue, and negative correlations are in red. (C) ROC curves (AUC%, CI 95%) of the multimetabolite biomarker model to identify the IS obesity metabotype among the obese population (IS and high IR) or all of the subjects of the study (normal weight and obesity and IS or high IR). The model was formed by GPE 18:2, GPI 18:0, GPS 18:0, GPC aa 36:1, GPC aa 36:4, and GPC aa 36:5, selected by the LASSO method. (D) Boxplot of the levels of the individual metabolites of the multimetabolite biomarker after logarithmic transformation and Pareto scaling. Abbreviations: AUC, area under the curve; CI, confidence interval; GPC, glycerophosphatidylcholine; GPE, glycerophosphatidylethanolamine; GPI, glycerophosphatidylinositol; PS, glycerophosphatidylserine.