The chemical interactome space between the human host and the genetically defined gut metabotypes

Abstract

The bacteria that colonize the gastrointestinal tracts of mammals represent a highly selected microbiome that has a profound influence on human physiology by shaping the host's metabolic and immune system activity. Despite the recent advances on the biological principles that underlie microbial symbiosis in the gut of mammals, mechanistic understanding of the contributions of the gut microbiome and how variations in the metabotypes are linked to the host health are obscure. Here, we mapped the entire metabolic potential of the gut microbiome based solely on metagenomics sequencing data derived from fecal samples of 124 Europeans (healthy, obese and with inflammatory bowel disease). Interestingly, three distinct clusters of individuals with high, medium and low metabolic potential were observed. By illustrating these results in the context of bacterial population, we concluded that the abundance of the Prevotella genera is a key factor indicating a low metabolic potential. These metagenome-based metabolic signatures were used to study the interaction networks between bacteria-specific metabolites and human proteins. We found that thirty-three such metabolites interact with disease-relevant protein complexes several of which are highly expressed in cells and tissues involved in the signaling and shaping of the adaptive immune system and associated with squamous cell carcinoma and bladder cancer. From this set of metabolites, eighteen are present in DrugBank providing evidence that we carry a natural pharmacy in our guts. Furthermore, we established connections between the systemic effects of non-antibiotic drugs and the gut microbiome of relevance to drug side effects and health-care solutions.

Figure 1

The genetically defined metabotypes of the bacterial communities in the gut of healthy individuals. (a) The present study focuses on the evaluation of: (1) the interactions between small molecules (metabolites) produced by the microbiome and human proteins, and (2) the interactions between drug molecules and bacterial proteins. (b) The frequency of each of the 1490 metabolic reactions (red: essential reactions, blue: non-essential) that were assigned to the microbiome of the healthy individuals. The frequencies are given as both: (1) total number of reactions for a given frequency, represented by the bar width, and (2) density for essential and non-essential reactions for a given frequency. (c) Visualization of the most common (present in >70% of the samples) metabolic reactions (59 reactions) of the group of healthy individuals. Glycolysis, pyruvate metabolism, fatty acid metabolism, amino acid and nitrogen metabolism were the most conserved parts of the metabolic network. (d) The three distinct groups formed by clustering the healthy individuals based on a binary representation of their microbiome metabolic profile. The three clusters are characterized by high (736–1395), medium (254–758) and low (34–195) number of metabolic reactions. (e) Distribution of reaction counts in healthy samples dominated by the Bacteroides, Prevotella, and Ruminococcus genera (Arumugam et al., 2011).

Figure 2

The interactome space of the 33 ‘non-human' metabolites with the human proteome. (a) A total of 195 MetaHit sequences (non-redundant) are involved in reactions in which these 33 metabolites participate. (1) Taxonomy distribution (top 20 species) for the MetaHit sequences (1091 non-redundant) involved in all metabolic reactions, (2) available taxonomy distribution for 56 of the 195 MetaHit sequences. (b) Heat map showing the disease space (given as OMIM IDs) targeted by the 33 metabolites that can be synthesized or degraded only by the gut microbiome. Information in parenthesis shows whether a metabolite participates in an irreversible reaction (as substrate (S) or a product (P)) or in a reversible reaction (S and P). When available, the Anatomical Therapeutically Classification code was retrieved from DrugBank. (c) The tissue specificity (given as a z-value) of the disease protein complexes that interact with metabolites with high binding affinity (K_i⩽1 μℳ). Hierarchical clustering was performed using Euclidean distances according to Ward's method. Detailed information for the protein complex IDs is provided in Supplementary Table S4.

Figure 3

Drug–metagenome interactions. (a) A network of interactions between drug molecules (circles) and metabolic reactions (squares) in healthy individuals. A drug is connected with a metabolic reaction if (i) it is chemically similar with a metabolite that appears as reactant and (ii) the drug and the metabolite share at least one protein interactor in ChEMBLdb. Red font indicates essential reactions and green font indicates antibiotics. (b) A network of interactions between drug molecules (circles) and non-metabolic proteins (squares) in healthy individuals. A drug is connected with a protein if the drug target and the metagenome protein are homologs (90% similarity and 80% coverage). Red font indicates essential reactions and green font indicates antibiotics.