Identification of serum metabolites associating with chronic kidney disease progression and anti-fibrotic effect of 5-methoxytryptophan

Abstract

Early detection and accurate monitoring of chronic kidney disease (CKD) could improve care and retard progression to end-stage renal disease. Here, using untargeted metabolomics in 2155 participants including patients with stage 1-5 CKD and healthy controls, we identify five metabolites, including 5-methoxytryptophan (5-MTP), whose levels strongly correlate with clinical markers of kidney disease. 5-MTP levels decrease with progression of CKD, and in mouse kidneys after unilateral ureteral obstruction (UUO). Treatment with 5-MTP ameliorates renal interstitial fibrosis, inhibits IκB/NF-κB signaling, and enhances Keap1/Nrf2 signaling in mice with UUO or ischemia/reperfusion injury, as well as in cultured human kidney cells. Overexpression of tryptophan hydroxylase-1 (TPH-1), an enzyme involved in 5-MTP synthesis, reduces renal injury by attenuating renal inflammation and fibrosis, whereas TPH-1 deficiency exacerbates renal injury and fibrosis by activating NF-κB and inhibiting Nrf2 pathways. Together, our results suggest that TPH-1 may serve as a target in the treatment of CKD.

Fig. 1

The five selected metabolites for the discrimination of the different CKD stages. a–e Boxplots showed the relative intensities of the five metabolites in serum (left y-axis) and urine (right y-axis) including 5-MTP, CSA, acetylcarnitine, tiglylcarnitine and taurine across all five CKD stages. f, g The levels of serum CREA and urea across all five CKD stages. h The levels of proteinuria across all five CKD stages. Dot plot and line showed the relative intensities of the five urinary metabolites including 5-MTP, CSA, acetylcarnitine, tiglylcarnitine and taurine across all five CKD stages. In the boxplot, the median is represented by the center line, 75 percentile is represented by the upper bound of the box, 25 percentile is represented by the lower bound of the box, minimum is represented by the lower whisker, and maximum is represented by the upper whisker

Fig. 2

Multivariate statistical analysis of the metabolites and clinical indexes and external validation. a Heatmap and unsupervised cluster constructed using the five metabolites and two clinical parameters. Strong cluster separation can be observed among CKD stages. All normal healthy controls were clustered together. Subjects with early CKD stages clearly separated from subjects with late CKD stages. Darker color was low abundance, light color was high abundance. b Bar plot demonstrates the accuracy and fitness of the all models tested. Three evaluation parameters were plotted: Pseudo R², random forest accuracy and support vector machine accuracy. The models with best fitness and accuracy are the models with the 98 metabolites. We further chose the model of five metabolites with two clinical parameters as our final model. c Confusion matrix of random forest evaluation on the final model. The accuracy was 95.5%. d Confusion matrix of support vector machine evaluation on the final model. The accuracy was 92.0%. e ROC curves of five metabolites and proteinuria in normal healthy controls and all patients with CKD. f Unsupervised cluster results show all 30 normal healthy controls clustered together and separated from patients with CKD. Two outliers were observed between CKD1 and CKD2. Darker color was low abundance, while light color was high abundance. g Scatter plot of PC1 vs PC2, clear separation can be observed between normal healthy controls and patients with CKD. h Random forest method was able to classify subjects to correct CKD stages. i Support vector machine method was able to classify subjects to correct CKD stages. AUC area under the curve, RF random forest, SVM support vector machine

Fig. 3

The five metabolites were further validated by a longitudinal cohort study. a Dot plots of levels of five metabolites including 5-MTP, CSA, acetylcarnitine, tiglylcarnitine and taurine in serum of normal healthy controls and CKD case. They were determined by UPLC-HDMS method. Mean values are presented by horizontal bars. Upper and lower lines indicate standard deviation values. b Dots and lines showing changes of five metabolites in each individual from normal status to CKD case status. c PCA of two components of five metabolites from normal healthy controls and CKD case. d OPLS-DA of five metabolites from normal healthy controls and CKD case. e Heatmap of five metabolites from normal healthy controls and CKD case. f Diagnostic performances of five metabolites from normal healthy controls and CKD case based on the PLS-DA model. The black dots with red squares or black circles with blue squares are for the incorrectly predicted samples in CKD case and normal controls. 27 Out of the 31 CKD case were located in CKD case area (87.1% sensitivity) and 30 out of the 31 normal healthy controls were correctly grouped (96.8% specificity). These results demonstrated that the five metabolites show high prediction class probabilities. g Analysis of PLS-DA based ROC curves of five metabolites in normal healthy controls and CKD case from 31 individuals. The associated AUC, 95% confidence interval (CI), sensitivity and specificity values were indicated. Student’s t test was used for the significance of difference between two groups. OPLS-DA orthogonal partial least squares-discriminant analysis, PCA principal component analysis

Fig. 4

Five metabolites were further validated in pre- and post-treatment by enalapril. a Box plots of levels of five metabolites including 5-MTP, CSA, acetylcarnitine, tiglylcarnitine and taurine in patients with CKD2 pre- and post-treatment by enalapril. Mean values are presented by horizontal bars. The whiskers indicate the maximum and minimum points. b Dots and lines showing changes of five metabolites in each individual from patients with CKD2 pre- and post-treatment by enalapril. c PCA of two components of proteinuria and five biomarkers. d OPLS-DA of two components of proteinuria and five biomarkers from patients with CKD2 pre- and post-treatment by enalapril. e Heatmap of two components of proteinuria and five biomarkers. f Diagnostic performances of two components of proteinuria and five biomarkers based on the PLS-DA model. The black dots with red squares or black circles with blue squares are for the incorrectly predicted samples in pre- and post-treatment. 24 Out of the 30 patients with CKD2 of pre-treatment were located in pre-treatment area (80.0% specificity) and 27 out of the 30 patients with CKD2 of post-treatment were correctly grouped (90.0% sensitivity). g PCA of two components of five biomarkers. h OPLS-DA of five biomarkers. i Heatmap of five biomarkers. j Diagnostic performances of five biomarkers based on the PLS-DA model. The black dots with red squares and or black circles with blue squares are for the incorrectly predicted samples in pre- and post-treatment. 29 Out of the 30 patients with CKD2 of pre-treatment were located in pre-treatment area (96.7% specificity) and 29 out of the 30 patients with CKD2 of post-treatment were correctly grouped (96.7% sensitivity). These results demonstrated that the five biomarkers show high prediction class probabilities. k Analysis of PLS-DA based ROC curves of proteinuria and five metabolites in patients with CKD2 pre- and post-treatment by enalapril. The associated AUC, 95% confidence interval (CI), sensitivity and specificity values were indicated. Student’s t test was used for the significance of difference between two groups

Fig. 5

Five potential biomarkers were further validated in pre- and post-treatment by Wulingsan. a Box plots of levels of five potential biomarkers including 5-MTP, CSA, acetylcarnitine, tiglylcarnitine and taurine in patients with CKD2 pre- and post-treatment by Wulingsan. Mean values are presented by horizontal bars. The whiskers indicate the maximum and minimum points. b Dots and lines showing changes of five potential biomarkers. c PCA of two components of proteinuria and five biomarkers. d OPLS-DA of two components of proteinuria and five biomarkers. e Heatmap of two components of proteinuria and five biomarkers. f Diagnostic performances of two components of proteinuria and five biomarkers based on the PLS-DA model. The black dots with red squares or black circles with blue squares are for the incorrectly predicted samples in pre- and post-treatment. 26 Out of the 30 patients with CKD2 of pre-treatment were located in pre-treatment area (86.6% specificity) and 28 out of the 30 patients with CKD2 of post-treatment were correctly grouped (93.3% sensitivity). g PCA of two components of five biomarkers. h OPLS-DA of five biomarkers. i Heatmap of five biomarkers. j Diagnostic performances of five biomarkers based on the PLS-DA model. The black dots with red squares and or black circles with blue squares are for the incorrectly predicted samples in pre- and post-treatment. 26 Out of the 30 patients with CKD2 of pre-treatment were located in pre-treatment area (86.6% specificity) and all the 30 patients with CKD2 of post-treatment were correctly grouped (100.0% sensitivity). These results demonstrated that the five biomarkers show high prediction class probabilities. k Analysis of PLS-DA based ROC curves of proteinuria and five potential biomarkers. The associated AUC, 95% confidence interval (CI), sensitivity and specificity values were indicated. Student’s t test was used for the significance of difference between two groups

Fig. 6

The anti-inflammatory and anti-fibrotic effects of 5-MTP in vivo. a The level of 5-MTP in the different tissues in UUO mice. *P < 0.05, **P < 0.01 compared with sham group (n = 6). b H&E and Masson trichrome staining of kidney tissues of UUO mice. Representative micrographs showed kidney inflammation and fibrotic lesions in indicated groups. Paraffin sections were used for H&E and Masson trichrome staining. Scale bar, 55 μm. c, d The protein expression and relative quantitative data of IκBα, p-IκBα, NF-κB, and its downstream gene products, COX-2, MCP-1, as well as Nrf2 and its downstream gene products, HO-1 and NQO-1, in indicated groups. *P < 0.05, **P < 0.01 compared with sham group (n = 6). ^#P < 0.05, ^##P < 0.01 compared with UUO group (n = 6). e, f Immunohistochemical staining of CD3 and CD68 and relative quantitative data in indicated groups. Scale bar, 50 μm. ^#P < 0.05, ^##P < 0.01 compared with UUO group (n = 6). g Immunohistochemical staining of fibronectin and vimentin in indicated groups. Scale bar, 50 μm. h, i The protein expression and relative quantitative data of collagen I, fibronectin, α-SMA and E-cadherin in different groups as indicated. *P < 0.05, **P < 0.01 compared with sham group (n = 6). ^#P < 0.05, ^##P < 0.01 compared with UUO group (n = 6). UUO, unilateral ureteral obstruction. Dot presents the single data results in bar graph. Data are presented as means ± SD. Student’s t test was used for the significance of difference between two groups; one-way ANOVA followed by Dunnett’s post hoc test for multiple comparisons was used for three or more groups

Fig. 7

The anti-inflammatory and anti-fibrotic effects of 5-MTP in vitro. a, b The protein expression and relative quantitative data of IκBα, p-IκBα, NF-κB p65, COX-2 and MCP-1 as well as Nrf2, HO-1 and NQO-1 in HK-2 cells induced by TGF-β1 as indicated. *P < 0.05, **P < 0.01 compared with CTL group (n = 6). ^#P < 0.05, ^##P < 0.01 compared with TGF-β1-induced group (n = 6). c Representative immunofluorescent staining of NF-κB p65 in HK-2 cells induced by TGF-β1 as indicated. Scale bar, 25 μm. d, e The protein expression and relative quantitative data of IκBα, p-IκBα, NF-κB p65, COX-2 and MCP-1 as well as Nrf2, HO-1 and NQO-1 in HMC induced by LPS as indicated. *P < 0.05, **P < 0.01 compared with CTL group (n = 6). ^#P < 0.05, ^##P < 0.01 compared with LPS-induced group (n = 6). f Representative immunofluorescent stainings of COX-2 and HO-1 in HMC induced by LPS as indicated. Scale bar, 25 μm. g, h The protein expression and relative quantitative data of collagen I, fibronectin, α-SMA and E-cadherin in HK-2 cells induced by TGF-β1 as indicated. *P < 0.05, **P < 0.01 compared with CTL group (n = 6). ^#P < 0.05, ^##P < 0.01 compared with TGF-β1-induced group (n = 6). i Representative immunofluorescent staining of vimentin in HK-2 cells induced by TGF-β1 as indicated. Scale bar, 25 μm. CTL, control; LPS, lipopolysaccharide; TGF, transforming growth factor-β1. Dot presents the single data result in bar graph. Data are presented as means ± SD. One-way ANOVA followed by Dunnett’s post hoc test for multiple comparisons was used for three or more groups

Fig. 8

The protective roles of TPH-1 in renal injury. a The protein expression of TPH-1 in TGF-β1-induced HK-2 cells and LPS-induced HMC, respectively. b The expression of TPH-1 in HK-2 and HMC cells after knock-down of TPH-1, respectively. HK-2 cells and HMC were transfected with TPH-1-specific siRNA or CTL siRNA. c, d The protein expression of collagen I, fibronectin, α-SMA, vimentin and E-cadherin in HK-2 cells as indicated. *P < 0.05, **P < 0.01 compared with sham group (n = 6). e The protein expression of TPH-1 in UUO and IRI mice as indicated (n = 6). f The protein expression of TPH-1 in mice after injection with lentivirus expressing full-length mouse Tph1 cDNA (TPH-1 over) or lentivirus containing empty plasmids (vector) (n = 6). g The relative intensity of 5-MTP in mice as indicated (n = 6). *P < 0.05, **P < 0.01 compared with sham group (n = 6). h, i The protein expression and relative quantitative data of collagen I, fibronectin, α-SMA, vimentin and E-cadherin in mice as indicated. j, k The protein expression and relative quantitative data of IκBα, p-IκBα, NF-κB p65, MCP-1, COX-2, Nrf2, HO-1 and NQO-1 in mice as indicated. *P < 0.05, **P < 0.01 compared with sham group (n = 6). ^#P < 0.05, ^##P < 0.01 compared with UUO group (n = 6). ^&P < 0.05, ^&&P < 0.01 compared with IRI group (n = 6). l, m The protein expression and quantitative analysis of TPH-1 in mice after injection with lentivirus carrying shRNA against Tph1 and lentivirus containing nonspecifc shRNA (scramble). **P < 0.05 compared with sham mice (n = 6). n, o The protein expression and quantitative analysis of COX-2, HO-1, α-SMA and collagen I in mice as indicated. *P < 0.05, **P < 0.01 compared with sham group (n = 6). ^#P < 0.05, ^##P < 0.01 compared with UUO group (n = 6). Dot presents the single data result in bar graph. Data are presented as means ± SD. One-way ANOVA followed by Dunnett’s post hoc test for multiple comparisons was used for three or more groups. CTL control; IRI ischemia/reperfusion injury, LPS lipopolysaccharide, TGF transforming growth factor-β1, TPH-1 tryptophan hydroxylase-1, UUO unilateral ureteral obstruction