Richer gut microbiota with distinct metabolic profile in HIV infected Elite Controllers

Abstract

Gut microbiota dysbiosis features progressive HIV infection and is a potential target for intervention. Herein, we explored the microbiome of 16 elite controllers (EC), 32 antiretroviral therapy naive progressors and 16 HIV negative controls. We found that the number of observed genera and richness indices in fecal microbiota were significantly higher in EC versus naive. Genera Succinivibrio, Sutterella, Rhizobium, Delftia, Anaerofilum and Oscillospira were more abundant in EC, whereas Blautia and Anaerostipes were depleted. Additionally, carbohydrate metabolism and secondary bile acid synthesis pathway related genes were less represented in EC. Conversely, fatty acid metabolism, PPAR-signalling and lipid biosynthesis proteins pathways were enriched in EC vs naive. The kynurenine pathway of tryptophan metabolism was altered during progressive HIV infection, and inversely associated with microbiota richness. In conclusion, EC have richer gut microbiota than untreated HIV patients, with unique bacterial signatures and a distinct metabolic profile which may contribute to control of HIV.

Figure 1

Similar richness and diversity of fecal microbiota in EC and negative controls. Number of observed bacterial genera was significantly lower in naive patients as compared to the other groups (a). Richness indices Chao-1 (b) and ACE (c) were reduced in naive, but no significant differences were observed between EC and negative. Alpha-diversity, assessed by Shannon index was lower in naive as compared to negative (d), whereas Simpson index was similar in all groups (e). Comparisons between groups were obtained via Kruskal-Wallis rank based test including Dunn’s post-hoc pairwise analyses. Benjamini-Hochberg method was used for correction of multiple testing. A p-value < 0.05 was considered significant. Box plots represent median (black horizontal line), 25th and 75th quartiles (edge of boxes), upper and lower extremes (whiskers). Outliers are represented by a single data point.

Figure 2

Separation between EC and naive patients in inter-individual (ß-diversity) analyses. Non-metric multidimensional scaling (NMDS) analysis was performed to characterize inter-individual differences between groups, revealing clustering of EC at NMDS axis 1 and naive at axis 2. The separations between groups at each axis are presented in respective box-plot. Box plots represent median (black horizontal line), 25th and 75th quartiles (edge of boxes), upper and lower extremes (whiskers). Outliers are represented by a single data point (a). LASSO regression analysis with AUROC (ROC curves; AUC used for estimation of model accuracy) curve was used for classification of gut microbiota composition between groups, and lowest accuracy was found between EC and negative patients (AUC 0.77, suggesting that the similarity of microbiota composition was highest between these groups) (b).

Figure 3

Compositional differences in fecal microbiota between groups. Several differences in bacterial abundance were observed between the groups at genus level. Comparisons of taxa abundances were performed via Kruskal -Wallis rank based test and Benjamini-Hochberg method was used for correction of multiple testing. Adjusted p-value < 0.01 was considered significant for Kruskal-Wallis. Dunn’s post-hoc pairwise analyses: *p < 0.05, **p < 0.01, ***p < 0.001. Box plots represent median (black horizontal line), 25th and 75th quartiles (edge of boxes), upper and lower extremes (whiskers). Outliers are represented by a single data point.

Figure 4

Inferred functional content of gut microbiota. The metagenomic functional content of gut microbiota was predicted by inferred PICRUSt analysis. Abundance of pathways involved in carbohydrate metabolism, cardiovascular diseases and circulatory system at KEGG level II (a), or level III (b–d). Pathways involved in carbohydrate metabolism, galactose metabolism, pentose and glucoranate interconversions, pentose-phosphate pathway and pyrovate metabolism (b). Pathways related to metabolism of lipids and fatty acids and biosynthesis of secondary bile acids (c). Bacterial tryptophan metabolism, PPAR signaling, phenylalanine, tyrosine and tryptophan biosynthesis and synthesis and degradation of ketone bodies pathways (d). Kruskal – Wallis rank-based test was applied, and Benjamini – Hochberg method was used to correct for multiple testing. Adjusted p-value < 0.01 was considered significant for Kruskal-Wallis. Dunn’s post-hoc pairwaise analyses: *p < 0.05, **p < 0.01, ***p < 0.001. Box plots represent median (black horizontal line), 25th and 75th quartiles (edge of boxes), upper and lower extremes (whiskers). Outliers are represented by a single data point.

Figure 5

Correlations between tryptophan catabolism metabolites and NMDS 2 axis reveal clustering of naive patients. Significant correlations between NMDS 2 axis and tryptophan (a), xanthurenic acid (b) and K/T ratio (c) were observed, separating naive patients from EC and negative controls. The gray area defines the 95% confidence interval for the linear regression coefficients. The different groups are represented by different colors (EC-red, naive-blue, negative-yellow). Spearman’s correlation was applied for testing correlations between metabolites and NMDS plot axis coordinates.

Figure 6

The composition and functionality of gut microbiota correlate with markers of immune activation and inflammation. Most cellular and some soluble markers of immune activation correlated to specific genera and functional pathways of gut microbiota. Correlations are presented by genus (a) and functional pathways (b). Spearman’s correlation was used. Associations with a Benjamini – Hochberg adjusted p-value lower than 0.01 were considered relevant. Immune activation and inflammatory parameters associated with less than two bacteria were discarded when plotting the heatmap.