The composition of the gut microbiome (GM) is characterized by a strong host-specific dominance of particular taxa, but with substantial variability over time within one host individual (Dabrowska and Witkiewicz, 2016; Adair and Douglas, 2017; Zhang et al., 2017). A key challenge is to decipher the factors shaping the host’s microbiome community and the relative contribution of different deterministic and stochastic processes to variation in its community structure (Alberdi et al., 2016; Adair and Douglas, 2017). So far, most studies on GM assembly have focused on within-host processes (Macke et al., 2017b; De Meester et al., 2019). Host-mediated control over the GM composition has been shown to occur in several taxa, most often due to antimicrobial defenses mounted by the host (Tasiemski et al., 2015) or developmentally regulated anatomical barriers to colonization (Ohbayashi et al., 2015; Lanan et al., 2016; Norman and Koskella, 2017). Behavioral traits such as selective feeding or sociality also contribute to shaping the GM by modifying the pool of potential colonizing microbes (Grossart et al., 2010; Koch and Schmid-Hempel, 2011; Mushegian et al., 2019). These deterministic processes partly depend on the host’s genetic background, suggesting an association between host genotype and GM composition (Macke et al., 2017a; Mushegian et al., 2019). On the other hand, microbe-microbe interactions, including competition and syntrophic interactions, have also been shown to affect the persistence of microbes within the gut (Adair and Douglas, 2017; Foster et al., 2017; Macke et al., 2017a). These interactions are strongly mediated by the host’s diet, which determines the available resources in the gut and, accordingly, what microbial species and types of metabolism can become dominant (Carmody et al., 2015; Foster et al., 2017).

The GM does not exist in isolation, but can contribute to a wider metacommunity maintained by the transmission between individual hosts and dispersal between host-associated and free-living microbial communities (Eckert et al., 2016; Murall et al., 2017). Dispersal of microbes is likely to be key in maintaining microbiome diversity and reducing variation in microbiome composition between individual hosts (Alberdi et al., 2016; Adair and Douglas, 2017; Macke et al., 2017b). Hence, processes involved in structuring the GM might often involve multiple spatial scales (Penczykowski et al., 2016; Norman and Koskella, 2017; Laine et al., 2019). In this way, the GM could be regarded as a local community colonized from a regional species pool, i.e., the microbial pool present in the environment (Shapira, 2016; Foster et al., 2017). The composition of this regional pool depends on environmental conditions, but might also be directly affected by hosts and their microbiomes (Wong et al., 2015; Callens et al., 2018). The interaction between hosts, their microbiomes and free-living communities is expected to play a crucial role in microbiome assembly. This metacommunity perspective on microbiome assembly might be particularly relevant for aquatic organisms and bacterioplankton (BPK), which are in close and continuous contact and are therefore expected to have strong reciprocal effects. If these interactions prove to be host genotype-dependent to a certain extent, then they may also be an important missing link in eco-evolutionary theory (Macke et al., 2017b; De Meester et al., 2019).

Combining metabarcoding with a GM transplant approach, we investigated the interplay between host genotype, GM, and BPK in the freshwater crustacean Daphnia magna. In a first experiment, we examined the effects of Daphnia genotype and diet on both the GM and BPK composition. Nine Daphnia genotypes were exposed to an environmental microbial source and were submitted to either a green algal or a cyanobacterial diet for approximately 58 generations. GM and BPK compositions were subsequently determined through next-generation sequencing and were found to be affected by host genotype and diet. In a second experiment, we examined the relative contribution of the microbial source versus Daphnia genotype-dependent sorting processes to GM and BPK assembly by performing a GM transplant. Germ-free Daphnia of two genotypes were exposed to different GM inocula. Two weeks after the transplant, GM and BPK compositions were assessed through next-generation sequencing, revealing a combined effect of microbial source and host genotype on the structuring of both communities.

Our results show that Daphnia GM is not assembled randomly. There were strong differences between microbial communities in the Daphnia gut (GM) and in the surrounding water (BPK). In both experiments, the taxonomic composition of microbial communities (Figures 1, 2) differed between GM and BPK (Figures 3A, 4A and Tables 1a, 2a), mainly due to an overrepresentation of Actinobacteria (mostly Microbacteriaceae) and Flavobacteriia (Flavobacterium sp.) in BPK compared to GM (all p < 0.001 by Wald test; Supplementary Table S1). This suggests that these bacteria do not preferentially colonize the Daphnia gut environment. In Experiment 1, in which the cultures were regularly seeded with a diverse environmental sample of BPK, OTU richness was lower in GM than in BPK (p < 0.0001, GLM; Figure 3D and Supplementary Table S2a), suggesting a selection of particular BPK strains in the GM. β-proteobacteria (mostly Comamonadaceae) were over-represented in GM in Experiment 1 (p < 0.05 by Wald test; Supplementary Table S1a). The Comamonadaceae family is a major constituent of the microbiome and induces positive fitness effects in Daphnia (Eckert and Pernthaler, 2014; Peerakietkhajorn et al., 2015; Macke et al., 2017a; Callens et al., 2018; Mushegian et al., 2019). In Experiment 2, in which Daphnia were transferred into sterile water following the transplant so that BPK could only come from the leakage of Daphnia gut-associated microbes, OTU richness was higher in GM than in BPK (p < 0.0001, GLM; Figure 4D and Supplementary Table S3). This indicates that not all bacteria growing in Daphnia GM can thrive in an open environment. Important to note is that the GM is not the only potential host-derived source of microbiota. Daphnia contain microbiota on other structures as well, such as the carapace, the filter apparatus, etc. (Qi et al., 2009; Eckert and Pernthaler, 2014; Freese and Schink, 2011; Callens et al., 2016), which may explain the difference between GM and BPK. Taken together, our results suggest that under natural conditions with a diverse environmental microbial community, the gut microbiota will be a subset of the taxa occurring in the environment, while the taxa that leak from the GMs into the environment show differential capacities to contribute to the environmental microbial communities. Similar results were observed when considering the Shannon diversity index (Supplementary Tables S4, S5). Figures 3D, 4D suggest that α-diversity values were similar in both experiments for the GM, but not for the BPK, which was more diverse in the non-sterile medium of Experiment 1 than in the sterile medium of Experiment 2.

Another conclusion of our study is that the host genotype influences the composition of both the GM and BPK community. In Experiment 1, after ±58 generations of exposure of Daphnia to a shared environmental microbial pool, both GM and BPK compositions were influenced by Daphnia genotype. In Experiment 2, 2 weeks after a GM transplant, the two recipient genotypes differed in terms of both GM and BPK compositions. Host-mediated structuring of the external microbial environment has already been reported in Drosophila (Wong et al., 2015) and in Daphnia (Degans et al., 2002). Our study reveals that this impact can be genotype-dependent. In this way, our results indicate that the composition of the environmental microbial community is affected by the evolution of the host species (see also terhorst et al., 2014), providing a potentially important avenue for future research in the field of eco-evolutionary dynamics (Hendry, 2017; De Meester et al., 2019). Daphnia-mediated modification of the BPK might further influence the success of species in the freshwater community and induce ecosystem-level effects. In Experiment 1, the overall β-diversity of microbial communities was affected by host diet and genotype as well as by the interaction of these two factors (Table 1a). However, diet and genotype effects on BPK were different from those on GM (i.e., significant interactions with the community type; Table 1a). A Mantel test (R = −0.025, p = 0.68) and Procrustes analysis (Pr: m² = 0.96, r = 0.19, p = 0.32; Figures 3B,C) revealed no association between community composition in GM and BPK. Focusing on BPK separately, both diet and host genotype had a substantial effect on the taxonomic composition, and as these two factors interacted (Figure 3B and Table 1b), this suggests that the effect of diet varied among genotypes. Figure 3B indicates that the genotype effect was stronger with the Microcystis than with the Scenedesmus diet. Overall, diet had the strongest impact on the proportion of Flavobacteriia and Sphingobacteriia, which were overrepresented in Daphnia on the Microcystis diet compared to those on the Scenedesmus diet (both p < 0.01, by Wald test; Supplementary Table S6). In GM, the taxonomic composition was mainly affected by the genotype, while the diet had a smaller effect (Figure 3C and Table 1c). Flavobacteriia, Cytophagia, Actinobacteria, and Bacilli were all more strongly associated with the Microcystis diet, whereas α- and γ-proteobacteria were more strongly associated with the Scenedesmus diet (all p < 0.05 by Wald test; Supplementary Table S6). The effects of genotype and diet on OTU richness were dependent on the community type (p < 0.0002 for all interactions involving the community type, GLM; Figure 3D and Supplementary Tables S2a, S7). In BPK, OTU richness differed among genotypes (p < 0.0001, GLM; Figure 3D and Supplementary Table S3b), and the diet had a genotype-dependent impact (Diet: p = 0.0042, diet × genotype: p < 0.0001, GLM; Figure 3D and Supplementary Table S2b). In GM, OTU richness was affected by genotype (p < 0.0001, GLM; Figure 3D and Supplementary Table S2c), diet (p = 0.048, GLM; Figure 3D and Supplementary Table S2c) and their interaction (p < 0.0001, GLM; Figure 3D and Supplementary Table S2c). The Shannon diversity index was influenced by host genotype in both BPK and GM (p = 0.005, GLM; Supplementary Tables S4, S8), but it was not influenced by the diet (p = 0.45, GLM; Supplementary Tables S4, S8).

The external microbial source interacts with the Daphnia genotype to shape GM and BPK. In addition to host-dependent processes, our results revealed that GM and BPK are affected by external factors including the diet (Experiment 1) and the external microbial source (Experiment 2). Both factors interacted with host genotype to shape the microbial communities. Overall, the diet effect was stronger in BPK, while GM composition was mostly affected by host genotype, suggesting that genotype-dependent sorting processes are more important in GM than in BPK. Exposure to Microcystis tended to decrease α-diversity in both types of communities and was associated with particular taxonomic groups, mainly Flavobacteria. Flavobacteria contribute to the lysis and degradation of Microcystis cells during cyanobacterial blooms (Maruyama et al., 2003; Kolmonen et al., 2004; Eiler and Bertilsson, 2007; Manage and Premetilake, 2011) and were found to be associated with Microcystis tolerance in Daphnia (Macke et al., 2017a). Interestingly, our results suggest that the structuring effect of host genotype on BPK is stronger with the Microcystis diet. Overall, the taxonomic composition of microbial communities was affected by both recipient genotype and microbiome inoculum (Figures 2, 4B,C and Table 2a). Differences among recipient genotypes and among microbiome inocula, however, varied depending on the community type (p < 0.03 for all interactions involving the community type, PERMANOVA; Table 2a). In both BPK and GM, both recipient genotype and microbiome inoculum affected the community structure, and both factors interacted (Figures 4B,C,5 and Tables 2b,c). The results of a Mantel test (R = 0.38, p = 0.002) and a Procrustes analysis (m² = 0.59, r = 0.64, p = 0.001; Figures 4B,C) showed that variation in community composition among experimental treatments covaried between BPK and GM. OTU richness differed between the two recipient genotypes, clone G2 having a higher OTU richness than clone G6 for both BPK and GM (p = 0.003, GLM; Figure 4D and Supplementary Table S3). OTU richness was also affected by the microbiome inoculum (p = 0.009, GLM; Figure 4D and Supplementary Table S3), and this effect differed among community types (p = 0.002; Supplementary Table S3). The Shannon diversity index, however, was not affected by these factors (all p > 0.1, GLM; Supplementary Table S5).

Daphnia feeding behavior can play a role in structuring Daphnia-associated microbial communities (Degans et al., 2002; Mushegian et al., 2019). More specifically, by mediating the intake of microbes from the environment, Daphnia grazing activity might directly affect the relative abundance of certain bacterial strains both within the gut and in the BPK. Differential grazing might also influence microbial community composition indirectly, through its effect on phytoplankton. Algae produce exopolysaccharides and metabolites that are used by BPK and may influence their relative abundance (Taylor et al., 2014). By feeding on algae, Daphnia might affect the resources available for bacteria both in the BPK and in the GM and thus affect the community structure. Second, by shaping the intestinal environment, host metabolism and immunity, might contribute to drive GM assembly and favor the growth of specific microbes within the gut (Macke et al., 2017b). These effects may further extend to influence the external environment of Daphnia, for instance through the shedding of immune effectors (Otti et al., 2014), thus affecting the BPK community structure. Third, GM communities might influence environmental microbial communities by leakage of dominant taxa. If hosts are common in the environment, such leakage might be an important force in structuring free-living microbial communities. In Experiment 2, we found a positive correlation between variation in GM composition and variation in BPK composition. This either reflects a shared structuring effect of Daphnia on both GM and BPK, or a direct interaction between GM and BPK. This association was not present in Experiment 1, likely because it was masked in the presence of a more diverse environmental microbial community. Given the low congruence of GM and BPK community structure at the OTU level, it is, however, unlikely that GM contributed strongly to the structuring of BPK via the leakage of microbes, although some seeding cannot be excluded. Another explanation that does not discount the role of leakage of bacterial strains from the gut into the environment could be the different growth rate of bacteria in the gut versus the water. If some microbes have a higher growth rate in the gut than in the environment, this could lead to differences between GM and BPK, suggesting that some microbes, which are rare in the environment but common in the gut, may only be maintained by leakage from the host. Alternatively, GM may have contributed to structuring BPK indirectly via the expression of particular metabolites. Microbe–microbe interactions are indeed central in structuring microbial communities, more specifically through the production of antimicrobial molecules (Tasiemski et al., 2015; Adair and Douglas, 2017).

We can conclude by stating that host-dependent processes interact with external factors to shape both the GM and wider bacterial environment, suggesting that these two communities influence each other. Interactions between host genotypes, their GMs and free-living microbial communities might have important ecosystem level effects. This structuring effect is an essential prerequisite for the important role of the microbiome in eco-evolutionary processes and generates adaptive flexibility. An important avenue for future studies will be to determine how the microbiome can affect interactions among host species, e.g., by measuring the impact of microbial dispersal on the GMs, as well as on their fitness and competitive strength.

The datasets generated for this study can be found in the NCBI, under accession numbers PRJNA498431 and PRJNA498417.

EM, MC, ED, and LD conceived the ideas and designed the experiment approach. EM, MC, IV, and ED performed the experiments, did the sequencing and collected the data. EM, MC, and FM analyzed the data, with input from ED and LD. EM and ED then led the writing of the manuscript. All authors contributed to the revised versions.

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.