Robust Regression Analysis of GCMS Data Reveals Differential Rewiring of Metabolic Networks in Hepatitis B and C Patients

Abstract

About one in 15 of the world's population is chronically infected with either hepatitis virus B (HBV) or C (HCV), with enormous public health consequences. The metabolic alterations caused by these infections have never been directly compared and contrasted. We investigated groups of HBV-positive, HCV-positive, and uninfected healthy controls using gas chromatography-mass spectrometry analyses of their plasma and urine. A robust regression analysis of the metabolite data was conducted to reveal correlations between metabolite pairs. Ten metabolite correlations appeared for HBV plasma and urine, with 18 for HCV plasma and urine, none of which were present in the controls. Metabolic perturbation networks were constructed, which permitted a differential view of the HBV- and HCV-infected liver. HBV hepatitis was consistent with enhanced glucose uptake, glycolysis, and pentose phosphate pathway metabolism, the latter using xylitol and producing threonic acid, which may also be imported by glucose transporters. HCV hepatitis was consistent with impaired glucose uptake, glycolysis, and pentose phosphate pathway metabolism, with the tricarboxylic acid pathway fueled by branched-chain amino acids feeding gluconeogenesis and the hepatocellular loss of glucose, which most probably contributed to hyperglycemia. It is concluded that robust regression analyses can uncover metabolic rewiring in disease states.

Keywords: TCA cycle; gluconeogenesis; glucose transporters; glycolysis; hepatitis B virus; hepatitis C virus; metabolic perturbation networks; metabolomics; pentose phosphate pathway; robust regression analysis.

Figure A1

Integrated perturbation and metabolic network for the HBV and HCV urine samples. Circle nodes represent metabolites, and diamonds represent enzymes. Dashed lines represent enzyme-substrate relations, and dotted lines enzyme-product relations; solid lines are appearing correlations in the metabolic perturbation network (Figure 4). The size of the node and thickness of the edge represent the relative significance.

Figure A2

Integrated perturbation and metabolic network for the HBV and HCV plasma samples. Circle nodes represent metabolites, and diamonds represent enzymes. The same legend applies as in Figure A1.

Figure 1

Principal component analysis (PCA) for the urine and plasma datasets.

Figure 2

Dot and boxplots for the metabolites with statistically significantly different intensities between the three sub-cohorts. The p values are adjusted for multiple comparisons (Benjamini-Hochberg).

Figure 3

Scatterplot of the intensities of urine ribose and urine citric acid. Only the correlation in HCV (regression line and 95% confidence interval shown) is statistically significant.

Figure 4

Metabolic perturbation networks for (a,c) HBV and (b,d) HCV in plasma (a,b) (red node borders) and urine (c,d) (yellow node borders). Solid lines denote ‘appear’ type edges and zigzag lines ‘flip’ edges. The edge color reflects the slope of the correlation in HBV/HCV patients, with green denoting positive and red negative correlations.