Metabolite profiling in identifying metabolic biomarkers in older people with late-onset type 2 diabetes mellitus

Abstract

Regulation of blood glucose requires precise coordination between different endocrine systems and multiple organs. Type 2 diabetes mellitus (T2D) arises from a dysregulated response to elevated glucose levels in the circulation. Globally, the prevalence of T2D has increased dramatically in all age groups. T2D in older adults is associated with higher mortality and reduced functional status, leading to higher rate of institutionalization. Despite the potential healthcare challenges associated with the presence of T2D in the elderly, the pathogenesis and phenotype of late-onset T2D is not well studied. Here we applied untargeted metabolite profiling of urine samples from people with and without late-onset T2D using ultra-performance liquid-chromatography mass-spectrometry (UPLC-MS) to identify urinary biomarkers for late-onset T2D in the elderly. Statistical modeling of measurements and thorough validation of structural assignment using liquid chromatography tandem mass-spectrometry (LC-MS/MS) have led to the identification of metabolite biomarkers associated with late-onset T2D. Lower levels of phenylalanine, acetylhistidine, and cyclic adenosine monophosphate (cAMP) were found in urine samples of T2D subjects validated with commercial standards. Elevated levels of 5'-methylthioadenosine (MTA), which previously has only been implicated in animal model of diabetes, was found in urine of older people with T2D.

Figure 1

Workflow for untargeted metabolomics. Samples collected from nested case control cohort were prepared before being analyzed on UPLC-MS machines. After data preprocessing and data analysis, the metabolite biomarkers were validated using standards. The results are then compared to published biomarkers of diabetes.

Figure 2

BPI chromatogram of urine samples. (A) Representative BPI chromatogram of urine samples from subjects with and without type 2 diabetes (T2D). (B) Overlap of QC samples BPI chromatogram shows that the retention time for major peaks were found to be stable throughout the whole analysis.

Figure 3

PCA was applied to features after preprocessing of LCMS measurements. The quality control (QC) samples were found to be well clustered near the center of the scores plot in both (A) positive and (B) negative ionization mode. Control and type 2 diabetes (T2D) samples, however, do not exhibit any meaningful separations. Quality of the dataset is first assessed using principle component analysis (PCA). Visual inspection of the clustering of the QC samples and drift of the run order QCs in the PCA scored plots were performed to assess the data integrity by tight clustering of the QC samples on the PCA score plots. The percentage variance explained by each principle components is shown beside the axis legend.

Figure 4

Multivariate data analysis of urine metabolomics data. (A) Scores plot of ESI+ measurements. The urine samples from diabetes subjects (T2D) and controls were found to be well separated along the predictive component axis with an explained variance (R ² Y) of 0.84 and predictability (Q ² Y) of 0.36. (B) Scores plot of ESI− experiment, with a R ² Y of 0.77 and Q ² Y of 0.46.

Figure 5

The relative abundance of biomarkers is shown as a heatmap. The color bar shows the abundance z-scores. Hierarchical clustering was applied to the validated biomarkers and cohort samples. The set of biomarkers are clustered into groups that are more or less abundant in the type 2 diabetes (T2D) group. The compounds at the top were found to be less abundant in T2D urine samples, while the compounds at the bottom are enriched in T2D urine samples.