Metabolomics analysis of visceral leishmaniasis based on urine of golden hamsters

Abstract

Background: Leishmaniasis is one of the most neglected tropical diseases and is spread mainly in impoverished regions of the world. Although many studies have focused on the host's response to Leishmania invasion, relatively less is known about the complex processes at the metabolic level, especially the metabolic alterations in the infected hosts.

Methods: In this study, we conducted metabolomics analysis on the urine of golden hamsters in the presence or absence of visceral leishmaniasis (VL) using the ultra-performance liquid chromatography (UPLC) system tandem high-resolution mass spectrometer (HRMS). The metabolic characteristics of urine samples, along with the histopathological change and the parasite burden of liver and spleen tissues, were detected at 4 and 12 weeks post infection (WPI), respectively.

Results: Amino acid metabolism was extensively affected at both stages of VL progression. Meanwhile, there were also distinct metabolic features at different stages. At 4 WPI, the significantly affected metabolic pathways involved alanine, aspartate and glutamate metabolism, the pentose phosphate pathway (PPP), histidine metabolism, tryptophan metabolism and tyrosine metabolism. At 12 WPI, the markedly enriched metabolic pathways were almost concentrated on amino acid metabolism, including tyrosine metabolism, taurine and hypotaurine metabolism and tryptophan metabolism. The dysregulated metabolites and metabolic pathways at 12 WPI were obviously less than those at 4 WPI. In addition, seven metabolites that were dysregulated at both stages through partial least squares-discriminant analysis (PLS-DA) and receiver-operating characteristic (ROC) tests were screened to be of diagnostic potential. The combination of these metabolites as a potential biomarker panel showed satisfactory performance in distinguishing infection groups from control groups as well as among different stages of infection.

Conclusion: Our findings could provide valuable information for further understanding of the host response to Leishmania infection from the aspect of the urine metabolome. The proposed urine biomarker panel could help in the development of a novel approach for the diagnosis and prognosis of VL.

Keywords: Biomarker panel; Leishmania; Metabolomics; Visceral leishmaniasis.

Fig. 1

H&E-dyed pathological slices of liver tissues. A Observed tissue sections at 400 × magnification . B Observed tissue sections at 1000 × magnification. Graphs in each column from left to right represent groups of control, 4 and 12 WPI, respectively, as marked on the top. In contrast to the control group, the infiltration of inflammatory cells was observed at 4 WPI. Significant sporadic granulomas were observed at 12 WPI, denoted by yellow pentagons. Leishmania amastigotes were denoted by yellow arrows. Bar: (A) 60 μm; (B) 24 μm

Fig. 2

H&E-dyed pathological slices of spleen tissues. A Spleen tissue sections at 400 × magnification. B Spleen tissue sections at 1000 × magnification. Graphs in each column from left to right represent groups of control, 4 and 12 WPI, respectively, as marked on the top of the graphs. In contrast to the control group, the changes were not as obvious, yet a trend of macrophage aggregation was recognized. Leishmania amastigote-like spots were obvious in expanded white pulp at 12 WPI, denoted by yellow arrows. Bar: (A) 60 μm; (B) 24 μm

Fig. 3

Parasite load in the liver and spleen. Leishmania load in liver and spleen at 4 and 12 WPI, respectively (2 hamsters from the infection or control group were killed at each time point and each sample was in triplicate)

Fig. 4

PLS-DA plots of comparison between different groups in ESI + mode. In the PLS-DA plot, each data point represents one urine sample. The results were computed through R-based package metaX. A Control vs. infection at 4 WPI. R2 = 0.99, Q2 = 0.82. B Control vs. infection at 12 WPI. R2 = 0.99, Q2 = 0.58. C 4 WPI vs. 12 WPI of the infection group. R2 = 0.99, Q2 = 0.60

Fig. 5

Count and distribution of differential metabolites at 4 WPI and 12 WPI. The total differential metabolites at different time points were visualized as Venn diagram based online “Venny 2.1”. A Results in ESI + mode. Eleven metabolites were shared at 4 WPI and 12 WPI. B Results in ESI− mode. One metabolite was shared at 4 WPI and 12 WPI

Fig. 6

Categories and count of differential metabolites at 4 WPI and 12 WPI. The differential metabolites were categorized according to their structural features and the metabolite categories as per HMDB. Blue bars represent 4 WPI and green bars 12 WPI

Fig. 7

Heatmaps of differential metabolites at 4 WPI and 12 WPI in ESI + mode. The differential metabolites were hierarchically clustered according to their patterns of change and then visualized as heatmaps. A Results at 4 WPI in ESI + mode. B Results at 12 WPI in ESI + mode. Red bars on the top of each map indicate the control group and green bars the infection group. Metabolites are represented by rows. The colors reddish brown and blue indicate the increased and reduced metabolite intensity, respectively

Fig. 8

Dysregulated pathways at 4 WPI and 12 WPI. The pathway analysis was conducted using MetaboAnalyst 5.0. The deeper the color, the smaller the p-value. The larger the bubble size, the higher the pathway impact. A Dysregulated pathways at 4 WPI. B Dysregulated pathways at 12 WPI

Fig. 9

Heatmaps and ROC curve for assessing the diagnostic potential of the selected biomarker panel. The closer the AUC was to 1.0, the better the effectiveness of the predictive diagnosis. A ROC curve of the biomarker panel at 4 WPI. B ROC curve of biomarker panel at 12 WPI. C ROC curve of the biomarker panel for 4 WPI vs. 12 WPI. D Ionic strength changes of the seven potential biomarkers at 4 WPI and 12 WPI were visualized as heatmaps. Each row in the heatmaps at 4 WPI and 12 WPI corresponded to the same compound ID and name on the right