Distinct antimicrobial peptide expression determines host species-specific bacterial associations

Abstract

Animals are colonized by coevolved bacterial communities, which contribute to the host's health. This commensal microbiota is often highly specific to its host-species, inferring strong selective pressures on the associated microbes. Several factors, including diet, mucus composition, and the immune system have been proposed as putative determinants of host-associated bacterial communities. Here we report that species-specific antimicrobial peptides account for different bacterial communities associated with closely related species of the cnidarian Hydra. Gene family extensions for potent antimicrobial peptides, the arminins, were detected in four Hydra species, with each species possessing a unique composition and expression profile of arminins. For functional analysis, we inoculated arminin-deficient and control polyps with bacterial consortia characteristic for different Hydra species and compared their selective preferences by 454 pyrosequencing of the bacterial microbiota. In contrast to control polyps, arminin-deficient polyps displayed decreased potential to select for bacterial communities resembling their native microbiota. This finding indicates that species-specific antimicrobial peptides shape species-specific bacterial associations.

Keywords: Cnidaria; core microbiota; holobiont; host-microbe; phylosymbiotic.

Fig. 1.

Comparison of the phylogenetic tree of Hydra species and the cluster tree of the corresponding bacterial communities. (Left) Phylogenetic tree of Hydra species based on cytochrome oxidase genes [maximum likelihood, general time reversible (GTR+I)]. Bootstrap values are shown at the corresponding nodes. The branch-length indicator displays 0.02 substitutions per site. H. vulgaris (AEP) (EF059935), H. carnea (EF059940), H. magnipapillata (EF059934), H. vulgaris (EF059936), H. oligactis (EF059937), H. circumcincta (EF059938), H. viridis (EF059941). (Right) Jacknife environment cluster tree (weighted UniFrac metric, rarified to 1,300 sequences per sample) of 21 bacterial communities from seven different Hydra species. One-thousand replicates were calculated; nodes are marked with Jackknife support values. The branch-length indicator displays distance between samples in Unifrac units. Pie charts represent mean relative abundance of bacterial orders. The highly variable Burkholderiales order was separated into different families.

Fig. 2.

Host-species–specific bacterial communities remain stable in pairwise coculture. Pairwise cocultivations were conducted between the morphological distinguishable species H. vulgaris (AEP), H. oligactis, and H. viridissima. Bacterial communities were clustered using principle coordinate analysis of the weighted Unifrac distance matrix. The percent variation explained by the principle coordinates is indicated at the axes. Reads were rarified to 1,350 reads per sample. H.oli, Hydra oligactis; H.AEP, Hydra vulgaris (AEP); H.vir, Hydra viridissima; +, cocultured. For cocultivation samples, the sequenced sample in written bold. Cocultivations were conducted in biological triplicates (n = 3); n = 5 for noncocultivated polyps (H.oli, H.AEP, H.vir). Certain samples cluster strongly together such that single symbols may be overlaid.

Fig. 3.

The arminin family of antimicrobial peptides. (A) Phylogenetic analysis of the arminin AMP family from four different Hydra species. The tree was built by Bayesian interference of phylogeny. A total of 3 million generations were calculated using the general time reversible model and the invgamma rate variation and four chains with a burn-in of 25%. Posterior probabilities are shown at the corresponding nodes. Genes are colored according to species. Numbers indicate contig numbers in the species transcriptome. AEP, H. vulgaris (AEP); Hmag, H. magnipapillata; Holi, H. oligactis; Hvir, H. viridissima. (B) Relative expression of each arminin, compared with the expression of β-actin in the corresponding species. Expression data were retrieved from microarray data, conducted in three biological replicates. Bar charts represent mean + SD. Certain paralogues had no corresponding microarray probes (n.d., not detected).

Fig. 4.

Successful knockdown of arminin family members in H. vulgaris (AEP). (A) Arminin–hairpin construct for generation of transgenic Hydra (as, antisense; s, sense; TAA, stop codon; P, promoter; T, terminator). (B) Relative expression of arminins quantified by qRT-PCR with specific primers. cDNA of control polyps served as reference (dashed line). cDNA amounts were equilibrated by EF1α, the graphic shows means + SEM (n = 3). Statistic was carried out using two-tailed t test; *P < 0.05, **P < 0.01, ***P < 0.001. (C) Neighbor-joining tree of arminins from H. vulgaris (AEP). Bootstrap values are shown at the corresponding nodes (1,000 replicates).

Fig. 5.

Species-specific arminins select for species-specific bacteria. (A) Schematic representation of the experimental design. Germ-free control polyps as well as germ-free Arminin⁻ polyps [= transgenic H. vulgaris (AEP)] were cocultivated with either H. vulgaris (AEP), H. oligactis (H.oli), or H. viridissima (H.vir) polyps for 5 wk. (B–D) Bacterial communities were clustered using PCoA of the weighted Unifrac distance matrix. All three PCoA plots are based on the same distance matrix containing all 45 samples, and therefore all samples are presented relative to each other. The percent variation explained by the principle coordinates is indicated at the axes. (B) When inoculated with native bacteria retrieved from H. vulgaris (AEP), control and Arminin⁻ polyps show no differences in bacterial recolonization. (C and D) When cocultivated with H. oligactis (C) or H. viridissima (D), control and Arminin⁻ polyps cluster separately, with recolonized control polyps clustering proximate to H. vulgaris (AEP) reference polyps. (E) Comparison of the weighted Unifrac distances to the native H. vulgaris (AEP) microbiota. Control polyps infected with a H. oligactis or H. viridissima microbiota show significantly lower Unifrac distances to their bona fide wild-type status than Arminin⁻ polyps. Statistics were carried out using two-tailed t test; *P < 0.05, **P < 0.01, ***P < 0.001.

Fig. 6.

Bar charts representing the microbiota of donor and recipient polyps. Mean relative abundances (n = 5) of bacterial classes. The highly abundant Betaproteobacteria were split into different families.