Untargeted metabolomic profiling of serum from client-owned cats with early and late-stage chronic kidney disease

Abstract

Evaluation of the metabolome could discover novel biomarkers of disease. To date, characterization of the serum metabolome of client-owned cats with chronic kidney disease (CKD), which shares numerous pathophysiological similarities to human CKD, has not been reported. CKD is a leading cause of feline morbidity and mortality, which can be lessened with early detection and appropriate treatment. Consequently, there is an urgent need for early-CKD biomarkers. The goal of this cross-sectional, prospective study was to characterize the global, non-targeted serum metabolome of cats with early versus late-stage CKD compared to healthy cats. Analysis revealed distinct separation of the serum metabolome between healthy cats, early-stage and late-stage CKD. Differentially abundant lipid and amino acid metabolites were the primary contributors to these differences and included metabolites central to the metabolism of fatty acids, essential amino acids and uremic toxins. Correlation of multiple lipid and amino acid metabolites with clinical metadata important to CKD monitoring and patient treatment (e.g. creatinine, muscle condition score) further illustrates the relevance of exploring these metabolite classes further for their capacity to serve as biomarkers of early CKD detection in both feline and human populations.

Figure 1

Disease stage distinctly differentiates the serum metabolome of healthy, early-stage CKD, and late-stage CKD cats. Partial least squares discriminant analysis (PLS-DA) projections of healthy cats, cats with early-stage CKD (Stages 1 and 2), and cats with late-stage CKD (Stages 3 and 4) (a) and cats with early-stage CKD versus late-stage CKD (b). Each circle represents the serum metabolome of one cat. Shaded ellipses surrounding each patient group represent 95% confidence intervals. Unsupervised hierarchical clustering analysis and heatmap of the 50 serum metabolites with the largest PLS-DA mean decrease accuracy scores (c). Each column represents one cat and each box represents one metabolite. Class boxes refer to the disease state of each cat, where green boxes indicate healthy cats, teal boxes represent early-stage CKD cats, and navy boxes represent late-stage CKD cats. Metabolite box colors reflect the normalized, scaled relative abundance of each metabolite when scaled across the dataset, where red boxes reflect an increased normalized abundance relative to the dataset median and blue boxes show metabolites with decreased normalized abundance relative to the dataset median. Branch points were calculated using Euclidean distances where longer branches indicate larger differences between cats. CKD Chronic kidney disease, FA Fatty acid. [1] and [2] in metabolite names are used to indicate isomers and * in names indicates metabolite identities were made using in-silico annotations.

Figure 2

Lipid metabolism is a key driver of serum metabolome differences between healthy, early-stage CKD and late-stage CKD cats. Pathway enrichment scores of lipid metabolic pathways comparing healthy cats, early-stage (Stages 1 and 2) and late-stage (Stages 3 and 4) cats (a). Dotted line at 1.0 shows metabolic pathways that were defined as meaningful contributors to patient group differences (pathway enrichment score of ≥ 1.0 in at least one patient group). Differentially abundant serum lipids with the 20 largest fold differences when comparing healthy cats versus early-stage CKD cats (b), healthy cats versus late-stage CKD cats (c) and early-stage CKD versus late-stage CKD cats (d). Significance was defined as p ≤ 0.05 following Benjamini–Hochberg adjustments to a Kruskal–Wallis test comparing normalized, scaled abundances of each metabolite across the three patient groups. BCAA Branched-chain amino acid, CKD Chronic kidney disease, FA Fatty acid, GPC glycerophosphorylcholine, GPE glycerophosphorylethanolamine, GPI glycerophosphorylinositol, HODE Hydroxyoctadecadienoic acid, MCFA Medium-chain fatty acid, MUFA Mono-unsaturated fatty acid, SC Short-chain, SCFA Short-chain fatty acid. [1] and [2] in metabolite names are used to indicate isomers.

Figure 3

Cats with late-stage CKD exhibit decreased serum abundances of essential amino acids compared to healthy cats and those with early-stage CKD. Normalized, scaled abundances of 11 feline essential amino acids. Each circle represents one cat, where colors refer to patient groups: Green = Healthy cat; Teal = Early-stage CKD cat (Stages 1 and 2); Navy = Late-stage CKD cat (Stages 3 and 4). Dotted lines on each violin plot show the 25th, 50th (median) and 75th percentiles of normalized, scaled metabolite abundance distributions for each amino acid. Significance was defined as p ≤ 0.05 following Benjamini–Hochberg adjustments to a Kruskal–Wallis test comparing normalized, scaled abundances of each metabolite across the three patient groups. CKD chronic kidney disease.

Figure 4

Increased abundances of uremic toxins are present in the serum of cats with late-stage versus early-stage CKD and healthy cats. Normalized, scaled abundances of ten uremic toxins. Each circle represents one cat, where colors refer to patient groups: Green = Healthy cat; Teal = Early-stage CKD cat (Stages 1 and 2); Navy = Late-stage CKD cat (Stages 3 and 4). Dotted lines on each violin plot show the 25th, 50th (median) and 75th percentiles of normalized, scaled metabolite abundance distributions for each amino acid. Arrows between metabolites indicate their relationships to each other in uremic toxin metabolic pathways, where metabolites to the left of an arrow are upstream metabolites (precursors) to the metabolites on the right side of arrows. Significance was defined as p ≤ 0.05 following Benjamini–Hochberg adjustments to a Kruskal–Wallis test comparing normalized, scaled abundances of each metabolite across the three patient groups. Figure created with BioRender.com. CKD chronic kidney disease.