Plasma amino acids and oxylipins as potential multi-biomarkers for predicting diabetic macular edema

Abstract

To investigate the pathophysiologic characteristics of diabetic complications, we identified differences in plasma metabolites in subjects with type 2 diabetes (T2DM) with or without diabetic macular edema (DME) and a disease duration > 15 years. An cohort of older T2DM patients with prolonged disease duration was established, and clinical information and biospecimens were collected following the guidelines of the National Biobank of Korea. DME phenotypes were identified by ophthalmologic specialists. For metabolomics studies, propensity matched case and control samples were selected. To discover multi-biomarkers in plasma, non-targeted metabolite profiling and oxylipin profiling in the discovery cohort were validated in an extended cohort. From metabolomic studies, 5 amino acids (asparagine, aspartic acid, glutamic acid, cysteine, and lysine), 2 organic compounds (citric acid and uric acid) and 4 oxylipins (12-oxoETE, 15-oxoETE, 9-oxoODE, 20-carboxy leukotriene B4) were identified as candidate multi-biomarkers which can guide DME diagnosis among non-DME subjects. Receiver operating characteristic curves revealed high diagnostic value of the combined 5 amino acids and 2 organic compounds (AUC = 0.918), and of the 4 combined oxylipins (AUC = 0.957). Our study suggests that multi-biomarkers may be useful for predicting DME in older T2DM patients.

Figure 1

Schematic representation of experimental procedures used for investigating multi-biomarkers of diabetic macular edema (DME) in study subjects.

Figure 2

Principal component analysis (PCA) (A) and partial least squares discriminant analysis (PLS-DA) (B) score plots for candidate plasma markers in diabetic macular edema (DME) and non-DME subjects analyzed by GC–TOF–MS in discovery cohort. Black filled circle—non-DME group, red filled circle—DME group.

Figure 3

Receiver operating characteristic (ROC) curve of potential metabolite biomarkers distinguishing diabetic macular edema (DME) versus non-DME subjects, and combined ROC curves of those multi-biomarkers in discovery cohort. (A) 7 metabolites selected after GC–TOF–MS analysis-based metabolite profiling. (B) 4 oxylipins selected after lipid profiling analyzed by HPLC-triple-Q-MS. The ROC curves of each metabolite, and combined ROC curves, were overlain on single plots. The AUC values of each metabolite are shown inside the ROC curve.

Figure 4

Schematic diagram of a proposed metabolic pathway using plasma metabolites derived from metabolite and lipid profiling of experimental groups including diabetic macular edema (DME) and non-DME subjects. Metabolites labelled with blue characters indicate that relative metabolite levels were lower in DME cases than in non-DME subjects. Metabolites labelled with red characters indicate that relative metabolite levels were higher in DME cases than in non-DME patients. Asterisks indicate statistically significant differences in levels of metabolites distinguishing DME and non-DME individuals (p < 0.05). The metabolic pathway was modified from the reported Kyoto Encyclopedia of Genes and Genomes pathway (KEGG, http://www.genome.jp/kegg/).