Metabolic and inflammatory perturbation of diabetes associated gut dysbiosis in people living with and without HIV infection

Abstract

Background: Gut dysbiosis has been linked with both HIV infection and diabetes, but its interplay with metabolic and inflammatory responses in diabetes, particularly in the context of HIV infection, remains unclear.

Methods: We first conducted a cross-sectional association analysis to characterize the gut microbial, circulating metabolite, and immune/inflammatory protein features associated with diabetes in up to 493 women (~ 146 with prevalent diabetes with 69.9% HIV +) of the Women's Interagency HIV Study. Prospective analyses were then conducted to determine associations of identified metabolites with incident diabetes over 12 years of follow-up in 694 participants (391 women from WIHS and 303 men from the Multicenter AIDS Cohort Study; 166 incident cases were recorded) with and without HIV infection. Mediation analyses were conducted to explore whether gut bacteria-diabetes associations are explained by altered metabolites and proteins.

Results: Seven gut bacterial genera were identified to be associated with diabetes (FDR-q < 0.1), with positive associations for Shigella, Escherichia, Megasphaera, and Lactobacillus, and inverse associations for Adlercreutzia, Ruminococcus, and Intestinibacter. Importantly, the associations of most species, especially Adlercreutzia and Ruminococcus, were largely independent of antidiabetic medications use. Meanwhile, 18 proteins and 76 metabolites, including 3 microbially derived metabolites (trimethylamine N-oxide, phenylacetylglutamine (PAGln), imidazolepropionic acid (IMP)), 50 lipids (e.g., diradylglycerols (DGs) and triradylglycerols (TGs)) and 23 non-lipid metabolites, were associated with diabetes (FDR-q < 0.1), with the majority showing positive associations and more than half of them (59/76) associated with incident diabetes. In mediation analyses, several proteins, especially interleukin-18 receptor 1 and osteoprotegerin, IMP and PAGln partially mediate the observed bacterial genera-diabetes associations, particularly for those of Adlercreutzia and Escherichia. Many diabetes-associated metabolites and proteins were altered in HIV, but no effect modification on their associations with diabetes was observed by HIV.

Conclusion: Among individuals with and without HIV, multiple gut bacterial genera, blood metabolites, and proinflammatory proteins were associated with diabetes. The observed mediated effects by metabolites and proteins in genera-diabetes associations highlighted the potential involvement of inflammatory and metabolic perturbations in the link between gut dysbiosis and diabetes in the context of HIV infection.

Keywords: Blood metabolome; Diabetes; Gut dysbiosis; Gut metagenome; HIV infection; Inflammatory proteome; Multi-omics integration.

Fig. 1

Gut microbiota composition and prevalent diabetes (N = 493). A Differences in alpha and beta diversities of gut microbiota at the species level between women with and without diabetes. The Wilcoxon rank test was used for the comparison of alpha diversity (observe, Chao1, Shannon, and Simpson indices). Bray–Curtis dissimilarity was used to calculate beta diversity, which was represented by the first two components of principal coordinates analysis (PCoA). Difference in beta diversity across diabetes status was tested using permutational multivariate analysis of variance (PERMANOVA with 9999 permutations). B ANCOM-II results of the 97 predominant gut bacteria genera. Genera marked as triangles were those associated with diabetes with FDR-q < 0.1 at threshold of 0.60 (i.e., the ratio of genera to at least 60% of the other taxa is detected to be significantly associated with diabetes). Color refers to phyla and sizes refer to W values in ANCOM-II. The prefixes of “g.” and “s.” refer to the taxa at genus and species levels, respectively. C Associations (odds ratio (ORs) and 95% confidential intervals (CIs)) of identified gut bacteria genera and affiliated species with diabetes (top panel) and the percentages of species within selected genera (bottom panel). Species presented in ≥5% of samples with a relative abundance ≥0.01% were included. Estimates in B and C were adjusted for age at visit, study site, race/ethnicity, household annual income, education, smoking, alcohol consumption, HIV serostatus, and antibiotics use within the 4 weeks of stool sample collections

Fig. 2

Inflammatory proteomics and prevalent diabetes (N = 428). A Associations (odds ratio (OR) and 95% confidence interval (CI)) between inflammatory proteins (n = 74) and prevalent diabetes in binary logistic regression. Significant proteins (n = 18, FDR-q < 0.1) were labeled in red. B Representations of diabetes status by the first two components of diabetes-associated proteins (n = 18) in sparse partial least squares regression for discrimination analysis (sPLS-DA). C Partial spearman correlation (Pcorr) among the 18 diabetes-associated proteins. Proteins inversely associated with diabetes were labeled in blue. Analyses of logistic regression, partial correlation, and sPLS-DA were adjusted for age at visit, study site, race/ethnicity, household annual income, education, smoking, alcohol consumption, HIV serostatus, and fasting status. CXCL11: C-X-C motif chemokine 11, CD6: T cell surface glycoprotein CD6 isoform, CSF-1: Macrophage colony-stimulating factor 1, CXCL10: C-X-C motif chemokine 10, CXCL5: C-X-C motif chemokine 5, CXCL6: C-X-C motif chemokine 6, FGF-21: fibroblast growth factor 21, GDNF: glial cell line-derived neurotrophic factor, HGF: hepatocyte growth factor, IL-17A: interleukin-17A, IL-17C: interleukin-17C, IL-18R1: interleukin-18 receptor 1, IL6: interleukin-6, LIF-R: leukemia inhibitory factor receptor, OPG: osteoprotegerin, OSM: oncostatin-M, TWEAK: tumor necrosis factor (ligand) superfamily, member 12, VEGFA: vascular endothelial growth factor A

Fig. 3

Associations between plasma metabolites and prevalent diabetes (N = 434). A An overview of analysis pipeline and study samples. B The distribution of cross-sectional associations between metabolites and diabetes in logistic regression. Metabolites in red and blue refer to those exhibiting positive and negative associations (FDR-q <0.1) with prevalent diabetes, respectively; among them, those colored in red were available in the prospective analysis of incident diabetes (N = 694, including 391 women from the Women’s Interagency HIV Study and 303 men from the Multicenter AIDS Cohort Study). C Significant associations with diabetes for metabolites selected in the cross-sectional analyses and those validated in the incident diabetes analysis. Estimates (odds ratios (ORs)/hazard ratios (HR)) were adjusted for age at visit, study site, race/ethnicity, household annual income, education, smoking, alcohol consumption status, HIV serostatus, and fasting status. Pro-Gly: dipeptide prolyl-glycine, DMGV: dimethylguanidino valerate

Fig. 4

The relationship between diabetes-associated metabolites and immune/proinflammatory proteins and the identified gut bacteria associated with diabetes. Heatmap presents the partial correlation coefficients (PCorr) of gut bacteria genera with selected metabolites and proteins while adjusting for age at visit, study sites, race/ethnicity, household annual income, education, smoking, alcohol consumption, HIV serostatus, fasting status, and antibiotics use. The top forest plot displays cross-sectional associations between identified metabolites/lipids modules (FDR-q < 0.1) and diabetes; the right forest plot displays cross-sectional associations of identified bacterial genera with prevalent diabetes. In these two panels, the color refers to the direction of association. CXCL11: C-X-C motif chemokine 11, CD6: T cell surface glycoprotein CD6 isoform, CSF-1: macrophage colony-stimulating factor 1, CXCL10: C-X-C motif chemokine 10, CXCL5: C-X-C motif chemokine 5, CXCL6: C-X-C motif chemokine 6, FGF-21: fibroblast growth factor 21, GDNF: glial cell line-derived neurotrophic factor, HGF: hepatocyte growth factor, IL-17A: interleukin-17A, IL-17C: interleukin-17C, IL-18R1: interleukin-18 receptor 1, IL6: interleukin-6, LIF-R: leukemia inhibitory factor receptor, OPG: osteoprotegerin, OSM: oncostatin-M, TWEAK: tumor necrosis factor (ligand) superfamily, member 12, VEGFA: vascular endothelial growth factor A

Fig. 5

Triangular relationship among diabetes-associated microbial genera, metabolites, proteins, and prevalent diabetes (N = 426). A Mediated association of gut bacterial genera with prevalent diabetes by selected metabolites (or lipid modules) and proteins. The left forest plot shows associations of selected genera with diabetes following consecutive adjustment for selected metabolites/proteins in logistic regression. The “base model” refers to the model adjusted for age at visit, study site, race/ethnicity, household annual income, education, smoking, alcohol consumption, HIV serostatus, fasting status, and antibiotics use. “+ metabolites/proteins” refer to the models further adjusted for specific metabolites/proteins in addition to variables in the base model, while “+ All” refer to the model further simultaneously adjusted for all selected metabolites/proteins. The right panel shows proportions mediated (calculated as the ratio of indirect effects to total effects) of examined metabolites (or lipid modules) and proteins in regression-based mediation analysis (see “ Methods”). B An alluvium plot summarizing significant mediation effects of individual proteins and metabolites in the association between bacteria and diabetes (P < 0.05). “Blue” alluvia belts refer to the potential pathway indicating the negative associations of bacteria with diabetes, while “red” ones refer to pathways exhibiting positive associations of bacteria with diabetes. Size of alluvium flow refers to the relative magnitude of mediated proportions. C A network showing the interrelationship (presented as partial correlation coefficients) among omics signatures (genera: marked as blue; metabolites: red; proteins: green) in associations with prevalent diabetes. The colors of lines refer to the direction of correlation (positive: orange; negative: blue). For interrelationship among signatures within each omics class, only |partial coefficient|> >0.25 with FDR-q < 0.1 were presented. GDNF: glial cell line-derived neurotrophic factor, HGF: hepatocyte growth factor, IL-18R1: interleukin-18 receptor 1, IL6: interleukin-6, LIF-R: leukemia inhibitory factor receptor, OPG: osteoprotegerin, OSM: oncostatin-M, CD6: T cell surface glycoprotein CD6 isoform, CSF-1: macrophage colony-stimulating factor 1, FGF-21: fibroblast growth factor 21, DMGV: dimethylguanidino valerate

Fig. 6

HIV infection-associated gut bacteria, proteins and metabolites and prevalent diabetes in WIHS women (N = 426). Data were associations and 95% confidence intervals of selected gut bacteria genera (A), proteins (B), and metabolites (C) with HIV infection (i.e., positive serostatus) and prevalent diabetes. Associations were derived via multivariable logistic regression models adjusting for age at visit, study site, race/ethnicity, annual household income, education, smoking, alcohol consumption, fasting status, antibiotics use (for gut bacterial features), and HIV serostatus (for association with prevalent diabetes). Only omics features significantly associated HIV infection at FDR-q < 0.1 were included here. Detailed numeric results were shown in Table S9. Detailed numeric results and feature annotations were shown in Table S9. CD8A: T-cell surface glycoprotein CD8 alpha chain, CXCL9: C-X-C motif chemokine 9, CXCL10: C-X-C motif chemokine 10, CCL25: C–C motif chemokine 25, SLAMF1: signaling lymphocytic activation molecule, TNF: tumor necrosis factor, CD244: natural killer cell receptor 2B4, TNFRSF9: tumor necrosis factor receptor superfamily member 9, IL-12B: interleukin-12 subunit beta, IL-15RA: interleukin-15 receptor subunit alpha, CXCL11: C-X-C motif chemokine 11, IL18: interleukin-18 (IL-18), MCP-1: monocyte chemotactic protein 1, ADA: adenosine deaminase, EN-RAGE: protein S100-A12, LAP TGF-β-1: latency-associated peptide transforming growth factor beta-1, DNER: delta and Notch-like epidermal growth factor-related receptor, TGF-α : transforming growth factor alpha