Environments that induce synthetic microbial ecosystems

Abstract

Interactions between microbial species are sometimes mediated by the exchange of small molecules, secreted by one species and metabolized by another. Both one-way (commensal) and two-way (mutualistic) interactions may contribute to complex networks of interdependencies. Understanding these interactions constitutes an open challenge in microbial ecology, with applications ranging from the human microbiome to environmental sustainability. In parallel to natural communities, it is possible to explore interactions in artificial microbial ecosystems, e.g. pairs of genetically engineered mutualistic strains. Here we computationally generate artificial microbial ecosystems without re-engineering the microbes themselves, but rather by predicting their growth on appropriately designed media. We use genome-scale stoichiometric models of metabolism to identify media that can sustain growth for a pair of species, but fail to do so for one or both individual species, thereby inducing putative symbiotic interactions. We first tested our approach on two previously studied mutualistic pairs, and on a pair of highly curated model organisms, showing that our algorithms successfully recapitulate known interactions, robustly predict new ones, and provide novel insight on exchanged molecules. We then applied our method to all possible pairs of seven microbial species, and found that it is always possible to identify putative media that induce commensalism or mutualism. Our analysis also suggests that symbiotic interactions may arise more readily through environmental fluctuations than genetic modifications. We envision that our approach will help generate microbe-microbe interaction maps useful for understanding microbial consortia dynamics and evolution, and for exploring the full potential of natural metabolic pathways for metabolic engineering applications.

Figure 1. Two known examples of metabolism-based symbiotic interactions which we use as test cases for our algorithms.

Chemical formulas represent metabolites and arrows represent possible exchange or transport reactions. A Experimental and computational setup of the methanogenic community composed of Desulfovibrio vulgaris and Methanococcus maripaludis . D. vulgaris consumes lactate and produces formate and hydrogen which are consumed by M. maripaludis. While this may seem a one-way, i.e. commensal interaction, it has been determined that D. vulgaris benefits from hydrogen consumption by M. maripaludis, as this reduces the hydrogen partial pressure, allowing D. vulgaris to continue its metabolic processes. Hence, this should be considered a case of mutualistic interaction. B Schematic representation of the yeast synthetic ecosystem experimentally constructed in . Yeast strains Ade- and Lys- where engineered to be auxotrophic for adenine and lysine respectively. It has been shown that neither yeast strain could grow on a minimal glucose medium alone. The same medium however does allow both to grow syntrophically in co-culture, demonstrating a mutualistic interaction.

Figure 2. Construction of a joint metabolic network model for two idealized microbial species meant to illustrate how a minimal metabolism-based mutualistic interaction could occur.

The networks of the two individual species are represented in panels A (red metabolites) and B (blue metabolites). The joint model, in which the two species share the same environment, is depicted in panel C, while the specific configuration of active fluxes in the mutualistic regime is shown in panel D. The two individual organisms differ only in their internal metabolic reaction (R1), while they have the same metabolites (X, Y and Z), the same uptake/secretion properties, and same usage of precursors to produce biomass. Arrows represent reactions, and encode information about reversibility (single vs. double arrow). The boxes represent distinct metabolic compartments: each organism has an extracellular (EX1, EX2) and a cytosolic (CYT1, CYT2) space. This level of compartmentalization is usually sufficient to appropriately model individual species. In this way, constraints on transporters (reactions TX, TY, TZ) can be decoupled from the constraints on environmental availability of nutrients (reactions EX, EY, EZ). In panels E and F we display each species as a stoichiometric matrix, in which columns correspond to reactions and rows to metabolites (see Methods for more details). For simplicity, we show here only the nonzero elements of each matrix. In building the joint model (see panels C, G) the two individual species (maintaining their color code) are embedded in a new environmental compartment (ENV), in which metabolite availability is controlled, as for individual models, through exchange reactions EX, EY, and EZ. The former exchange reactions EX, EY, and EZ of individual species are relabeled in the joint model as shuttle reactions SX, SY, and SZ. Being able to distinguish between shuttle reactions (which allow to artificially control the flow of a metabolite through the boundary of an organism) and transport reactions (TX, TY, TZ, associated with specific enzymes, which could possibly catalyze multiple transport reactions of different molecules) is an important subtlety of our framework, essential for a correct implementation of the SEM algorithm (see Methods). Notice that the stoichiometric matrix for the joint model (panel G) is composed of two blocks that are exactly the stoichiometric matrices for the individual species (panels E, F), with the addition of appropriate stoichiometric coefficients to encode the exchange and shuttle reactions (first three rows and first three columns). If, in the joint model, metabolite X is the only nutrient available in the medium, the two species will be forced to engage in a mutualistic interaction in order to survive (i.e. produce each its own biomass). This is illustrated in panel D, where the direction of the arrows reflects active fluxes under this specific condition. The ensuing mutualism is due to the fact that none of the two organisms can produce on its own all three biomass component, and each needs to receive a molecule from its partner.

Figure 3. Schematic representation of the pipeline used to search for interaction-inducing media (SIM).

The SIM algorithm is capable of identifying a large number of growth media predicted to induce symbiotic interaction between different microbial species. The algorithm is seeded with an initial medium (e.g. containing a specific carbon and a specific nitrogen source) that can sustain growth of a given joint pair of species. Then A the algorithm searches for all metabolites (or sets of metabolites) that can substitute the original carbon source, and subsequently all the metabolites that can substitute the original nitrogen source (black squares in corresponding arrays). These selected carbon and nitrogen sources are combined in all possible ways to give rise to a set of putative media that can sustain growth of the joint model (matrix in the figure). In the next step B the algorithm loops through each putative medium identified in A, and tests for growth of the joint pair as well as of each species individually. Finally C the different possible outcomes provide predictions of types of interactions induced by each medium. The actual algorithm, which takes into account more than two elements, is described in detail in the text and Methods.

Figure 4. Schematic representation of the metabolic network around adenine in S. cerevisiae.

This diagram illustrates why only certain metabolites are predicted to be exchanged under the syntrophy-inducing medium used in our computational implementation of the original experimental setup. Only the major metabolic steps around adenine synthesis in yeast are included for simplicity. Nodes represent metabolites, single arrows represent single biochemical reactions, and multiple arrows represent chains of biochemical reactions. Metabolites that can only be imported (but not exported, i.e. unidirectional transporters) according to the stoichiometric model have a red rectangle around them, while metabolites that can be both imported and exported (i.e. have reversible transporters) have a blue rectangle around them. Exchange metabolites are restricted to the set of metabolites the can be imported by the recipient and exported by the provider organism.

Figure 5. Metabolite usage predicted across interaction-inducing media in the pair of yeast strains from Fig. 1B .

Metabolites in all panels of this figure are clustered according to their presence in all media analyzed (see Methods). A Binary map of metabolite usage (black = not used; red = used) across all neutralism-inducing media. This emphasizes that some metabolites are used in all media, while others are never used. A large set of metabolites is used in different combination, forming a complex map of mutual capacities to compensate each other. B By looking at the overall frequency of metabolite usage across all neutralism-inducing media, one can see that lysine and adenine, or their derivatives, are always present, as expected. C The binary map (as in panel A) for all mutualism-inducing media. D Frequency of metabolites across all mutualism-inducing media. These media never contain the lysine and adenine derivatives observed above. Metabolites appearing at high frequency (positions between 20 and 30 on the x axis) correspond to carbon sources swapped between the two strains. E The atomic composition of metabolites from the above maps. This chart allows one to track the distribution and overlap of different atomic sources across metabolites.

Figure 6. Robustness analysis of the joint E. coli – S. cerevisiae model.

We evaluate the robustness of our approach by estimating the chance that a predicted interaction (e.g. mutualism) will change (e.g. to commensalism) when an organism's metabolic network is perturbed. In A, B and C this chance is displayed as a probability transition matrix, where darker shades indicate larger probability. Each row and column corresponds a different type of interaction (Sc = S. cervisiae; Ec = E. coli). Here the perturbations (100,000 for each matrix) are A individual reaction deletions, B reaction additions, and C combined instances of one addition and one deletion. The cumulative effect of multiple random addition or deletions (from one up to 10, corresponding to ∼0.25% of the organisms' reaction set) is illustrated in panel D. This graph shows the probability of not changing interaction class as a function of the number of perturbations implemented. This analysis shows that interaction classes are quite robust even when faced with multiple insults.

Figure 7. Predicted map of pairwise interactions between seven microbial species.

The size of the pie chart is representative of the number of media that allow growth of both organisms, as defined in the pie chart size legend to the right. The relative amount of each interaction type is represented by the proportion of each wedge of the pie. Details on the numbers and types of interactions for each pair of organisms can be found in Table S1. The values of n and m reported in the white boxes on the diagonal indicate respectively the number of reactions and metabolites present in each stoichiometric model.

Figure 8. Graph of transition probabilities between different types of interactions in the joint S. cerevisiae - E. coli model upon environmental and reaction perturbations.

These graphs show the chance of transition from one interaction type to another (as in Fig. 6) computed for either A environmental or B reaction network perturbations. For reaction network perturbations, the transition chances are the same ones computed for Fig. 6C. For environmental transitions, we performed perturbations to the growth media by swapping a randomly chosen environmental metabolite with a different random one. Arrows thickness and corresponding number indicate the probability of each interaction class (neutralism, mutualism, and two commensalism classes) remaining unchanged (self-arrows) or transitioning to a different interaction class. Dashed arrow represents transition probabilities of less than 0.01. See methods and text for more details.