Microbiota-Related Changes in Unconjugated Fecal Bile Acids Are Associated With Naturally Occurring, Insulin-Dependent Diabetes Mellitus in Dogs

Abstract

Diabetes mellitus (DM) in humans has recently been associated with altered intestinal microbiota. The consequences of intestinal dysbiosis, such as increased intestinal permeability and altered microbial metabolites, are suspected to contribute to the host inflammatory state and peripheral insulin resistance. Human diabetics have been shown to have changes in bile acid (BA) metabolism which may be detrimental to glycemic control. The purpose of this study was to examine BA metabolism in dogs with naturally-occurring, insulin-dependent DM and to relate these findings to changes in the intestinal microbiota. A prospective observational study of adult dogs with a clinical diagnosis of DM (n = 10) and healthy controls (HC, n = 10) was performed. The fecal microbiota were analyzed by 16S rRNA gene next-generation (Illumina) sequencing. Concentrations of fecal unconjugated BA (fUBA) were measured using gas chromatography and mass spectrometry. Analysis of bacterial communities showed no significant difference for any of the alpha-diversity measures between DM vs. HC dogs. Principal coordinate analysis based on unweighted Unifrac distance metric failed to show significant clustering between dog groups (ANOSIM_Unweighted: R = 0.084; p = 0.114). However, linear discriminate analysis effects size (LEfSe) detected differentially abundant bacterial taxa (α = 0.01, LDA score >2.0) on various phylogenetic levels. While Enterobacteriaceae was overrepresented in dogs with DM, the proportions of Erysipelotrichia, Mogibacteriaceae, and Anaeroplasmataceae were increased in HC dogs. Dogs with DM had increased concentration of total primary fUBA compared to HC dogs (p = 0.028). The concentrations of cholic acid and the cholic acid percentage of the total fUBA were increased (p = 0.028 and p = 0.035, respectively) in the feces of DM dogs relative to HC dogs. The levels of lithocholic acid (both absolute value and percentage of the total fUBA) were decreased (p = 0.043 and p < 0.01, respectively) in DM dogs vs. HC dogs. Results indicate that dogs with DM have both intestinal dysbiosis and associated fUBA alterations. The pattern of dysbiosis and altered BA composition is similar to that seen in humans with Type 2 DM. The dog represents a novel large animal model for advancing translational medicine research efforts (e.g., investigating pathogenesis and therapeutics) in DM affecting humans.

Keywords: T2DM; bile acids; diabetes mellitus; dog; lipopolysaccharide; microbiota.

Figure 1

Summary of alpha diversity measures.

Figure 2

Principal coordinate analysis (PCoA) plot showing clustering of microbial communities from feces of healthy and diabetic dogs (red = diabetic, blue = healthy). The microbiome (beta diversity) of healthy dogs did not differ from that of diabetic dogs (ANOSIM; p = 0.114).

Figure 3

Linear discriminant analysis effect size (LefSe) of bacterial taxa and their association with different canine groups. Only LefSe values >2 are shown.

Figure 4

Serum LPS concentrations (EU/ml) in healthy controls (HC) vs. dogs with diabetes mellitus (DM).

Figure 5

Comparison of primary and secondary fecal unconjugated bile acids in canine cohorts.