Gut microbiota and fecal short chain fatty acids differ with adiposity and country of origin: the METS-microbiome study

Abstract

The relationship between microbiota, short chain fatty acids (SCFAs), and obesity remains enigmatic. We employ amplicon sequencing and targeted metabolomics in a large (n = 1904) African origin cohort from Ghana, South Africa, Jamaica, Seychelles, and the US. Microbiota diversity and fecal SCFAs are greatest in Ghanaians, and lowest in Americans, representing each end of the urbanization spectrum. Obesity is significantly associated with a reduction in SCFA concentration, microbial diversity, and SCFA synthesizing bacteria, with country of origin being the strongest explanatory factor. Diabetes, glucose state, hypertension, obesity, and sex can be accurately predicted from the global microbiota, but when analyzed at the level of country, predictive accuracy is only universally maintained for sex. Diabetes, glucose, and hypertension are only predictive in certain low-income countries. Our findings suggest that adiposity-related microbiota differences differ between low-to-middle-income compared to high-income countries. Further investigation is needed to determine the factors driving this association.

Fig. 1. Variation in gut microbiome diversity.

a Alpha diversity estimated by Shannon, Observed ASVs and Faith’s PD (phylogenetic diversity) between countries. Exact false discovery rate (FDR)-corrected q values from left to right: Shannon: 2.33e − 08, 3.55e − 41, 2.42e − 37, 1.25e − 31, 6.70e − 20, 1.03e − 16, 3.02e − 12, 0.015, 0.1089; Observed: 0.0022, 2.84e − 26, 4.77e − 51, 7.90e − 43, 7.60e − 16, 2.06e − 40, 1.61e − 32, 3.39e − 06, 5.79e − 06, 0.058; PD: 0.067, 1.51e − 11, 3.69e − 41, 3.30e − 41, 2.59e − 05, 2.04e − 30, 5.77e − 31, 3.33e − 14, 7.86e − 15. b Alpha diversity estimated by Shannon, Observed ASVs and Faith’s PD (Phylogenetic Diversity) between obese and non-obese. Exact FDR-corrected q values from left to right: Shannon: 0.014; Observed: 1.86e − 05; PD: 6.05e − 06. Alpha diversity metrics (Faith’s PD, Observed ASVs, and Shannon) are shown on the y-axis in different panels, while country or obese groups are shown on the x-axis. c Beta diversity principal coordinate analysis based on weighted UniFrac distance between countries. d Beta diversity principal coordinate analysis based on weighted UniFrac distance between obese and non-obese. e Beta diversity principal coordinate analysis based on unweighted UniFrac distance between countries. f Beta diversity principal coordinate analysis based on unweighted UniFrac distance between obese and non-obese. The proportion of variance explained by each principal coordinate axis is denoted in the corresponding axis label. g Venn diagram of shared and unique genera between the five countries detected at a relative abundance >0.001 in more than 50% of the samples. Box plots show the interquartile range (IQR), the horizontal lines show the median values and the whiskers extend from the hinge no further than 1.5*IQR. Each colored dot denotes a sample. Statistical significance adjusted for multiple comparisons using false discovery rate (FDR) correction is indicated: *, P < 0.05; **, p < 0.01; ***, p < 0.001; ****, p < 0.0001, ns, non-significant; across countries and obese groups (Kruskal–Wallis test and pairwise Wilcoxon rank sum test; two-sided) for alpha diversity or by permutational multivariate analysis of variance (PERMANOVA) for beta diversity. Source data are provided as a Source Data file. Alpha diversity analysis for country, n = 1873 samples (Ghana, n = 373; South Africa, n = 390; Jamaica, n = 401; Seychelles, n = 396; USA, n = 313) and obesity status, n = 1764 samples. For Beta diversity analysis, n = 1764 samples.

Fig. 2. Variation in gut microbiome composition.

a Differentially abundant taxa among countries with the US as the reference due to its status as the country with the highest HDI and highest obesity incidence (n = 1694). b Differentially abundant taxa between obese and non-obese groups in the entire cohort (n = 1694). Differentially abundant taxa between obese and non-obese groups within c Ghana (n = 329); d South Africa (n = 374); panel e Jamaica (n = 386); panel f US (n = 304). ANCOM-BC analyses adjusted for BMI, age, sex, and country. Data are presented by effect size (log fold change) with a 95% confidence interval (CI) calculated from the beta coefficient and standard errors estimated from the ANCOM-BC log-linear (natural log) model (two-sided; FDR-adjusted). The colored dot indicates effect size (log fold change), and the whiskers indicate 95% CI. Representative ASVs with log fold change >1.4 in at least one group are shown for the country. FDR-adjusted (q  <  0.05) effect sizes are indicated by * q < 0.05; ** q < 0.01; *** q < 0.001. The exact p-values are available in the source data file. Source data are provided as a Source Data file. FDR false discovery rate, HDI human development index, ANCOM-BC analysis of compositions of microbiomes with bias correction.

Fig. 3. Receiver operating characteristic curves showing the classification accuracy of gut microbiota in a Random Forest model.

Classification accuracy for estimating a all countries (n = 1694); b diabetes status (n = 1657); c glucose status (n = 1657); d hypertensive status (1694); e obesity status (n = 1694); f sex (n = 1694) are presented. Classification accuracy for estimating country-level obesity status in g Ghana (n = 329); h South Africa (n = 374); i Jamaica (n = 386); j Seychelles (n = 361); k USA (n = 304) are presented. Micro-averaging values are impacted by data imbalance since it averages across each sample, whereas Macro-averaging provides equal weight to the characterization of each sample. Macro-averaging values are reported in the text. AUC area under the curve.

Fig. 4. Shannon index correlates positively with fecal short-chain fatty acids.

a Correlations (Spearman’s rho, R; two-sided) between Shannon diversity and concentrations (n = 1704) of the different types of fecal short-chain fatty acids (SCFAs) among countries. b Country level correlations (Spearman’s rho, R; two-sided) between Shannon and valerate levels in Ghana (n = 331); South Africa (n = 362); Jamaica (n = 331); Seychelles (n = 374); US (n = 306). Each colored dot represents a sample of a specific country, and the horizontal line on the scatterplot denotes the line of best fit. Unadjusted p values are reported. Source data are provided as a Source Data file.

Fig. 5. Associations of gut microbiota ASVs with concentrations of short-chain fatty acids (SCFAs).

a Heatmap of Spearman’s correlation between concentrations of SCFAs and top 30 differentially abundant ASVs (identified by ANCOM-BC) among countries (n = 1694). b Heatmap of Spearman’s correlation between concentrations of SCFAs and differentially abundant ASVs (identified by ANCOM-BC) for obese (n = 1694). Heatmap of Spearman’s correlation between concentrations of SCFAs and top 30 relatively abundant features in the non-obese and obese group in c Ghana (n = 329); d South Africa (n = 374); e Jamaica (n = 386); f Seychelles (n = 361); g USA (n = 304). Correlations are identified by Spearman’s rank correlation coefficient. Brick red squares indicate positive correlation, gray squares represent negative correlation, and white squares are insignificant correlations. Exact Benjamini–Hochberg adjusted p values are shown. Source data are provided as a Source Data file.