Intraspecies warfare restricts strain coexistence in human skin microbiomes

Abstract

Determining why only a fraction of encountered or applied strains engraft in a given person's microbiome is crucial for understanding and engineering these communities. Previous work has established that metabolic competition can restrict colonization success in vivo, but the relevance of bacterial warfare in preventing commensal engraftment has been less explored. Here, we demonstrate that intraspecies warfare presents a significant barrier to strain coexistence in the human skin microbiome by profiling 14,884 pairwise interactions between Staphylococcus epidermidis isolates cultured from eighteen people from six families. We find that intraspecies antagonisms are abundant, mechanistically diverse, independent of strain relatedness, and consistent with rapid evolution via horizontal gene transfer. Critically, these antagonisms are significantly depleted among strains residing on the same person relative to random assemblages, indicating a significant in vivo role. Together, our results emphasize that accounting for intraspecies warfare may be essential to the design of long-lasting probiotic therapeutics.

Figure 1:. High-throughput assay of interbacterial warfare from skin microbiomes of related people.

(A) Antagonism between different commensal strains of the same species (circles) could theoretically prevent transmission of certain strains despite frequent contact between individuals. Ecologically-relevant warfare would result in a depletion of antagonisms on individual people relative to random assortment. (B) We built a library of 122 Staphylococcus epidermidis isolates representing the strain diversity on healthy individuals from six families, and included 23 isolates from other skin species from these people. We screened every pairwise interaction (14,884 S. epidermidis intraspecies interactions plus 6,141 including other species) using high-throughput “spot-on-lawn” assays, in which producer cells are spotted on top of a lawn of receiver cells; we identified hundreds of cases of antagonism, which appear as Zones-Of-Inhibition (ZOIs; Methods). (C) Representative photograph of spot-on-lawn assay. Several S. epidermidis spots produce antimicrobials that antagonize the S. epidermidis receiver lawn, resulting in ZOIs of a range of intensities. Some spots on the plate are blank or were excluded for poor growth (see Supplemental Table 1 for array information). (D) We developed a computer-aided image analysis pipeline to identify even subtle ZOIs that pass the inhibition threshold (red dash) and quantify the strength of antagonism, determined by the Area Under the Curve of the intensity traces (AUC, blue; Methods).

Figure 2:. Intra-species antagonism is common and does not segregate at higher phylogenetic levels.

(A) No evolutionary structure is observed in antimicrobial production (rows) or sensitivity (columns) beyond the lineage level, indicating that antimicrobial production and resistance are fast evolving and not conserved. The heatmap depicts the AUC for each ZOI calculated for pairwise interactions between skin isolates dereplicated to the lineage level (Methods). Each pair is screened twice, with each isolate serving as both spot and lawn. Inhibition of a receiver lawn by a producer spot is indicated by a lighter square, with intensity indicating the size of the ZOI. Lineages and species are sorted by phylogenetic similarity (see tree at left, not to scale beyond S. epidermidis), and dashed lines on the heatmap species boundaries. Supplementary Figure 3 depicts this data without dereplicating S. epidermidis isolates into lineages. (B-C) The likelihood of observing antagonism between two lineages does not significantly differ between members of the same or different (B) species or (C) quorum sensing variant (agr type). Significance p-values are derived from two-sided permutation tests with shuffled group labels (Methods). (D) Conversely, intra-lineage antagonism is negligible compared to inter-lineage antagonism. (E) To assess the mechanisms of antagonistic interactions, we repeated the screen using cells and filtrates from 18 S. epidermidis producers against an array of bait lawns chosen based on interaction profiles (Supplementary Figure 7). Filtrates were subjected to a variety of pre-treatments. Nine interactions that did not inhibit in the filtrate were retested on media containing excess iron to identify iron-suppressible interactions. The results suggest a large variety of interaction mechanisms which are not neatly predictable from genomic context in this screen (Supplementary Figure 8).

Figure 3:. Antagonism is depleted among lineages co-residing on individuals.

We combined the results of the antagonism screen with isolate-inferred relative abundances of each lineage on each person (Supplementary Figure 2 and Supplementary Table 3) to study the ecological relevance of these interactions. (A) The abundance-weighted Antagonism Frequency (AF) of interactions between co-resident lineages in samples (e.g. same person, same timepoint) is depleted relative to AF calculated across all subjects pooled together (red line). Each datapoint depicts the mean AF across samples from a subject. Subject codes indicate family and subject (e.g. Subject 1PA is from family 1). (B) Lineage pairs that occur in the same sample are less likely to antagonize each other than lineages from different samples, relative to permutation tests where sample origin is shuffled; this analysis maintains antagonism structure (e.g. wide distribution of percent of isolates antagonized). (C) Simulations of a null model that incorporate lineage composition on subjects (e.g. uneven relative abundances of lineages) as well as antagonism structure also support a significant depletion of antagonism in the observed AF (arrow) of coexisting lineages on individuals. In each simulation, the antagonism matrix is kept constant but lineage identities are shuffled across all subjects in our study. As each simulation has a different expected AF, we can compare the mean difference between each subject’s AF (i.e. white datapoints from A) and the expected AF (i.e. red line from A) and the mean difference from each simulation (mean ΔAF). (D) A section of the lineage-level heatmap from Figure 2A, sorted to show only lineages present on subjects in two families (see Supplementary Figure 12 for all families), highlights that lineages on a person often antagonize lineages on other family members. Intensity indicates AUC for the ZOI, and lineages are repeated if present on multiple subjects. (E) The Bray-Curtis Similarity between the lineage composition of sample pairs (purple) is negatively correlated with the AF calculated for each sample pair after dereplication (red; Spearman’s rank correlation), supporting a role for antagonism in preventing transmission. (F) Lineages that antagonize a higher proportion of other lineages (red) reach higher abundance on individuals (blue; Spearman’s rank correlation). Each lineage’s antagonism proportion was calculated by counting the other lineages it produced a ZOI on and dividing by the total number of lineages.

Figure 4:. On-person evolution drives sensitivity to multiple antimicrobials.

(A) Two lineages show significant intra-lineage variation, each containing isolates with sensitivity to the same producers, depicted using a section of the isolate-level heatmap (from Supplemental Figure 3). Isolates from the same lineage are indicated by decimals and color. Intensity indicates AUC for the ZOI. The two idiosyncratic isolates depicted (denoted by *) have different sensitivity profiles from the rest of their lineages and also have loss-of-function mutations in the vraFG pathway, as labeled. (B) The phylogeny of isolates in lineage 37 indicates that the vraF frameshift and associated sensitivity was acquired, not ancestral. Lineage 20 has a similar pattern of recently acquired sensitivity (see Supplemental Figure 16). (C) By selecting on polymyxin B, we cultivated revertant isolate 37.3-r1 which corrected the vraF frameshift and has an ancestral resistance profile. Genome sequencing confirmed this reversion (Methods). (D) Isolates with vraFG mutations, but not their ancestors or the revertant, are sensitive to cationic antimicrobials, lysostaphin, and filtered supernatant from isolate 35.1. Minimum Inhibitory Concentration (MIC) assay results were normalized to isolate 35.1 and raw values are available in Supplemental Figure 18.