The vast majority of living biomass consists of single-celled organisms, but the existence of higher organisms demonstrates that interacting networks of cell populations can thrive despite competition between them [1], [2]. How nascent communities gain a growth advantage over unassociated individuals is an open question [2]–[9], but cell–cell interactions [10]–[14] and the formation of specific multi-cellular structures [15]–[18] are thought to contribute. Evaluating the role of physical structure in the initiation and persistence of natural consortia poses a causality dilemma [2], and de novo design of synthetic consortia that self-organize into specific structures is difficult. Thus, experimental studies of the formation and benefits of specific physical structures in mixed microbial communities are few.

We describe a synthetic symbiotic microbial consortium that allows us to address some of these questions. An advantage of using synthetic, or engineered, consortia for studies of this nature is that complex communal behaviors such as symbiosis can be implemented under defined and tunable experimental control [9], [19]–[21]. Although very simple relative to naturally-occurring microbial consortia, engineered ecosystems can nonetheless exhibit behaviors that mimic those found in nature and, because the interactions of engineered consortia can be controlled and more fully characterized, can provide insight into the development and persistence of natural communities.

It is useful to study the relationship between microbial community structure and persistence in biofilm communities for three primary reasons. First, biofilm spatial structure and productivity (total biomass accumulation) can be observed and quantified as a function of time using confocal laser scanning microscopy (CLSM) [22]. Second, stable micro-communities with very different properties and behaviors can form and persist within biofilms [23]–[26]. Finally, cells and sub-communities that detach from a biofilm subjected to fluid flow will flow downstream and may colonize downstream environments, where composition, spatial structure, and productivity can be observed. Thus, the effects of composition and spatial structure on the productivity of a consortium can be easily quantified when it grows as a biofilm. A structure that is beneficial should increase productivity in the local environment; it might also improve colonization or productivity when the consortium moves to downstream environments. The synthetic microbial consortium was engineered to rely on biofilm formation so that these effects could be measured.

The synthetic symbiotic consortium consists of two engineered populations of Escherichia coli which are not viable alone, but can grow and form biofilms when grown together (Fig 1A). The first population, which is identified by constitutive expression of cyan fluorescent protein (CFP, the “blue population”), can form initially healthy biofilms. However, it cannot synthesize a set of metabolites critical for cell growth and division and therefore quickly dies. To engineer this strain we interrupted a critical pathway responsible for synthesis of diaminopimelate and lysine by deleting a key gene, DapD (E. coli MG1655ΔDapD) [27]. We then restored DapD under the control of a RhlR-dependent promoter. The transcription factor RhlR is activated by a small-molecule autoinducer, butanoyl-homoserine lactone (C4HSL) [28], which is provided by a second population. This “yellow population,” identified by constitutive expression of yellow fluorescent protein (YFP), cannot form biofilms alone but is otherwise healthy. To engineer this strain we identified genetic loci implicated in E. coli biofilm formation and, by trial-and-error, found a subset of these loci which when deleted significantly reduce biofilm formation without compromising growth rate. This set of deletions, removing genes involved in expression of type I pili, curli, colanic acid, and capsular polysaccharides, was concurrently identified elsewhere (E. coli MG1655Δfim, ΔwcaL–wza, ΔcsgC-csgG) [29]. Finally, strong constitutive production of RhlI, and thus of C4HSL, in this yellow population means that its presence up-regulates expression of DapD in biofilms formed by the blue population. Only when the yellow population becomes entangled within biofilms initially formed by the blue population can either population form enduring biofilms (Fig 1B). A 50/50 mixture of these two populations inoculated into biofilm flow chambers generates symbiotic biofilms that persist for at least 288 hours given a constant flow of fresh sterile nutrients; the timing of biomass growth and sloughing in these biofilms is repeatable over at least 120 hours (see Supporting Information S1 for more information regarding construction of the consortium and Supporting Information S2 for information regarding repeatability).

After 80 hours of growth, the synthetic symbiotic biofilms always form a defined, layered physical structure. Yellow cells, initially randomly interspersed within a porous blue biofilm, grow away from the substrate to form clumps that are attached to the blue biomass. Pores previously present in the nascent, thin biofilm, which might have been filled by clonal expansion of either population, are filled entirely by blue cells which form a dense basement layer in the biofilm (Fig. 2A, B). The biomass medians—quantitative indicators of the locations of individual populations with respect to the substrate in mixed biofilms, as measured by CLSM—confirm this change (Fig. 2B). As this layered structure matures, the yellow clumps expand laterally to cover the blue biomass. Yellow cells are no longer found buried within the blue biomass; at steady state, the populations are vertically stratified, and the blue biomass forms a dense and uniform mat over the substrate, while the yellow biomass forms an uneven layer attached to this blue mat.

There is precedent for this type of self-organization in microbial consortia: after Acinetobacter and Pseudomonas putida are co-cultured in laboratory biofilms for several days, P. putida forms clumps on Acinetobacter. This structure provides a growth advantage for P. putida when carbon is scarce [30]. A growth advantage is associated with the structure of the synthetic symbiotic biofilm consortium as well. Samples of symbiotic biofilm effluent (containing the same numbers of viable cells) taken immediately before and after the layered structure emerges were transferred into fresh, downstream environments (experimental schematics can be found in Supporting Information S3). Effluent taken from the symbiotic consortium just prior to emergence of structure is unable to productively colonize a downstream environment. The resulting biofilm accumulates less biomass than the blue control monoculture biofilm shown in Fig. 2B. Effluent taken before the structure forms may contain primarily sessile or unhealthy cells. In contrast, effluent from the symbiotic consortium already exhibiting layered structure successfully colonizes a downstream flow chamber. This successful downstream biofilm recapitulates its predecessor's structure, but assumes the structure more quickly and accumulates more total biomass (Fig. 2C). In particular, the maximal total biomass in the successful downstream biofilm is always at least double the highest amount observed in the predecessor (Fig. 2B, C). Thus, the layered structure provides two clear growth advantages for this consortium. First, the structured consortium can colonize downstream environments, and second, when the structure forms in new environments the consortium accumulates more total biomass than it did in the initial environment. The most significant measurable benefits of this structure are observed in the downstream communities.

We find the layered structure and growth advantage in downstream biofilms only when aggregates containing blue and yellow cells are preserved during effluent transfer. When we treat the effluent to disrupt aggregates prior to transfer, leaving yellow and blue viable cell counts constant, this treated effluent can form biofilms, but they never exhibit the layered structure or growth advantage (Fig. 2D, Supporting Information S3). However, we can sort effluent from these unproductive biofilms and collect two fractions, aggregates containing both blue and yellow cells and single, unassociated cells (Supporting Information S3, information regarding sorting can be found in Supporting Information S4). The layered structure is recovered when the blue-and-yellow aggregate fraction forms biofilms downstream, and biomass accumulation is double the highest amount observed in the predecessor, suggesting recovery of the growth advantage (compare Figs. 2D, E). The single-cell fraction consists of more than 99% yellow cells, and thus neither the blue population nor structure nor any growth advantage is evident in the downstream biofilm it forms (Fig. 2F). Furthermore, although the blue-and-yellow aggregates are sorted from the effluent of unproductive biofilms, that same effluent—left untreated and unsorted—forms unusual downstream biofilms that are never otherwise observed (Supporting Information S3). These are initially dense, monomorphic, and primarily yellow. They do not exhibit defined structure and, after starting with significant amounts of biomass, these biofilms consistently lose biomass rather than accumulate it (Fig. 2G). We conclude that blue-and-yellow aggregates are necessary to preserve and convey the beneficial layered structure and growth advantage into downstream environments, but their abilities can be modulated or destroyed by other constituents in the effluent.

Biofilms can propagate when single cells dissociate from the outer regions of mature biofilms and adhere downstream, and this is considered the primary mode by which biofilms spread [31], [32]. Our results suggest this as one mechanism of proliferation. The regions of the symbiotic biofilm that are exposed to flow are predominantly populated by yellow cells, and more than 99% of cells in the single-cell fraction are yellow (Supporting Information S4). This fraction can form biofilms downstream, indicating that the yellow population adapts to adhere better, but these biofilms are weak and monomorphic (Fig. 2F). However, when effluent is never treated or sorted, the whole consortium colonizes downstream environments through multiple transfers and these biofilms accumulate more biomass than the initial biofilm. Therefore, aggregates that dissociate from upstream biofilms and colonize downstream environments enhance overall growth and proliferation of this consortium. These results indicate that a critical mechanism by which microbial communities propagate is the movement of aggregated members into downstream environments.

What are these aggregates, and how do they work? Aggregates preserve the physical relationship between the blue and yellow populations, and enhance yellow adhesion in downstream biofilms. Aggregates are distinct but conjoined clusters of blue and yellow biomass (Supporting Information S4, information regarding aggregate composition can be found in Supporting Information S5). When aggregates are transferred, average downstream biofilms contain five times more yellow biomass, after initial adhesion, than when aggregates are disrupted, even though both inocula contain the same numbers of blue and yellow cells (Supporting Information S3, S4, S5). Aggregates appear to be pre-organized pieces of the layered structure that quickly grow to recapitulate it in new environments. Additionally, it is possible that the proximity of blue and yellow cells in the aggregates enhances collaboration and therefore productivity (this is difficult to assess and remains untested).

We have used an engineered symbiotic microbial consortium to explore spatial self-organization and its benefits to a microbial community. Here, two symbiotic populations of E. coli grow to form a defined, layered structure which provides a growth advantage to both. This engineered consortium allowed us to observe the critical roles of self-organization, layering, and aggregation in the growth, movement, and ability of a microbial consortium to colonize new environments. The persistence assured by aggregates allows evolution and adaptation of interacting microbial communities despite environmental disruptions. It may eventually be possible to use engineered consortia like this one to determine how relationships between interacting, co-evolving populations are enhanced and preserved by particular physical structures.