Predictability and persistence of prebiotic dietary supplementation in a healthy human cohort

Abstract

Dietary interventions to manipulate the human gut microbiome for improved health have received increasing attention. However, their design has been limited by a lack of understanding of the quantitative impact of diet on a host's microbiota. We present a highly controlled diet perturbation experiment in a healthy, human cohort in which individual micronutrients are spiked in against a standardized background. We identify strong and predictable responses of specific microbes across participants consuming prebiotic spike-ins, at the level of both strains and functional genes, suggesting fine-scale resource partitioning in the human gut. No predictable responses to non-prebiotic micronutrients were found. Surprisingly, we did not observe decreases in day-to-day variability of the microbiota compared to a complex, varying diet, and instead found evidence of diet-induced stress and an associated loss of biodiversity. Our data offer insights into the effect of a low complexity diet on the gut microbiome, and suggest that effective personalized dietary interventions will rely on functional, strain-level characterization of a patient's microbiota.

Figure 1

Nutritional meal replacement and prebiotic spike-ins result in reproducible changes across participants. (a) Schematic outlining the dietary and sampling regimen for the study. (b) OTUs that showed statistically significant (DESeq. 2, FDR < 0.1) differential abundance on day 6 compared to day 3 in response to particular spike-ins. Mean relative abundances are computed across all participants and then converted to Z-scores across timepoints, to illustrate relative changes through time. (c) OTUs that showed statistically significant (Wilcoxon Rank-Sum test, FDR < 0.1; N = 39) differential abundance on day 3 compared to baseline (preB). Complete RDP taxonomies can be found in Fig. S1.

Figure 2

Inulin and pectin result in the enrichment of specific strains and specific enzymes in the metagenome across participants; in contrast, the same nutrient spike-in can also result in participant-specific responses. (a) Bacteroides uniformis blooms in response to inulin supplementation across all participants. The top plot shows mean and standard deviations of relative abundances across participants, and the bottom shows individual participant timeseries, normalized to relative abundance on day 3 for comparison purposes. (b) Same visualization for Bacteroides cellulosilyticus. (c) Average within-participant SNP heterozygosity in AMPHORA genes of B. uniformis. (d) Average between-participant SNP heterozygosity in AMPHORA genes of B. uniformis. (e) Relative abundance of pectinase enzymes in the metagenome. Statistical significance of the difference in abundance of pectinases on day 6 in the pectin arm was computed by a Wilcoxon Rank-Sum test compared to the abundance of pectinases on day 6 in the other arms (p < 10⁻⁵).

Figure 3

A diet consisting exclusively of nutritional meal replacement results in a flattening of the strain fitness landscape across the dominant genera of the gut microbiota. (a) Mean AMPHORA gene SNP heterozygosities within each participant on days 3 and 6, averaged across all bacterial species and normalized to baseline levels (preB). (b) Mean AMPHORA gene SNP heterozygosities averaged across the most abundant genera in the gut.

Figure 4

Nutritional meal replacement results in stress-like responses in the microbiota. (a) Log-transformed mean relative abundance of various bacteriophages in all participants, normalized to baseline levels (preB). (b) Mean and standard error timeseries of the relative abundance of Roseburia, Bilophila and Sutterella. (c) Relative abundance of mucinase genes on day preB, day 3 and day 6. (d) Bristol Stool Scale of all participants throughout the study.

Figure 5

Participants’ day-to-day variability in the composition of the microbiota does not decrease on identical diets, but between-participant similarity increases. (a) Weighted Unifrac values between and within participants on day preB (before) and day 6 (after). Error bars represent standard deviations. (b) Log-transformed mean relative abundance of the four distinct OTUs given a taxonomic assignment of Lachnospiracea incertae sedis at the genus level and that were found to be differentially abundant on day 3 compared to baseline (preB). Their combined relative abundance is shown in a solid line. For clarity, the denovo OTU IDs are labeled as follows: denovo6 - A; denovo84 - B; denovo65 - C; denovo155 - D.