Horizontal gene transfer of molecular weapons can reshape bacterial competition

Abstract

Bacteria commonly use molecular weaponry to kill or inhibit competitors. Genes encoding many weapons and their associated immunity mechanisms can be transmitted horizontally. These transfer events are striking because they appear to undermine bacterial weapons when given to competing strains. Here, we develop an ecological model of bacterial warfare to understand the impacts of horizontal gene transfer. Our model predicts that weapon gene transfer from an attacker to a target strain is possible, but will typically occur at a low rate such that transfer has a negligible impact on competition outcomes. We tested the model empirically using a transmissible plasmid encoding colicin E2, a potent antibacterial toxin produced by Escherichia coli. As predicted by the model, we find that toxin plasmid transfer is feasible during warfare, but the resulting transconjugants remain rare. However, exploring the model further reveals realistic conditions where transfer is predicted to have major impacts. Specifically, the model predicts that whenever competing strains have access to unique nutrients, transconjugants can proliferate and reach high abundances. In support of these predictions, short- and long-term experiments show that transconjugants can thrive when nutrient competition is relaxed. Our work shows how horizontal gene transfer can reshape bacterial warfare in a way that benefits a weapon gene and strains that receive it. Interestingly, we also find that there is little cost to a strain that transfers a weapon gene, which is expected to further enable the horizontal gene transfer of molecular weapons.

Fig 1. Horizontal transfer of bacterial weapon genes is limited by the killing of potential recipients.

Modeling scenarios for each column are shown across the top row. (a–c) Example dynamics of the strains (attacker, target, transconjugant) during a contest using parameters that correspond to the cross (X) shown in the parameter sweeps directly below. (d–f) Transconjugant frequency at steady state (see section “Materials and methods”) in competitions as a function of conjugation rate (b) and toxin killing efficiency (E). (g–i) Final frequency of different strain types at steady state as a function of the initial frequency of target and attacker strains. Top and middle rows are conducted at an initial frequency of 1:1:0 (target:attacker:transconjugants). All other parameters are default (Table 1) unless stated. Code and data underlying these figures are available from https://doi.org/10.5281/zenodo.14910561.

Fig 2. Experiments show weapon gene transfer but with limited impact on strain frequencies.

We conducted pairwise competition assays between different E. coli strains on LB agar plates. For each genotype, cell recovery (CFU) at each time point of co-culturing is shown. Means across n = 3–6 biological replicates are shown as dots connected by lines. Shaded ribbons depict standard error across replicates. Dashed lines represent the detection limit (200 CFU). (a–c) Short competitions conducted over 4 h. CFU for each time point after t = 0 were determined via destructive sampling of replicates. (c) shows combined data from two independent experiments. (d–f) Long competitions conducted over 24 h at either low or high starting cell densities. (a+d) BZB1011-KmR pColE2-AmpR (‘Attacker’) competed against toxin-sensitive BZB1011-CmR (‘Target’). No transconjugants (BZB1011-CmR pColE2-AmpR) were detected. (b+e) BZB1011-Km^R R751-Sp^R pColE2-Amp^R (‘Attacker^D’) competed against toxin-resistant BZB1011-Cm^R ΔbtuB (‘Target ΔbtuB’). Transconjugant (BZB1011-Cm^R ΔbtuB R751-Sp^R pColE2-AmpR) CFU are shown as they emerge during the interaction (‘Transconjugant ΔbtuB’). (c+f) BZB1011-Km^R R751-Sp^R pColE2-Amp^R (‘Attacker^D’) competed against toxin-sensitive BZB1011-Cm^R (‘Target’). ‘Transconjugant’ (BZB1011-Cm^R R751-Sp^R pColE2-AmpR) CFU are shown as they emerge during the interaction. To test for differences in target survival between (d; top right) and (f; top right), we used a two-sided, two-sample t test on log-transformed CFU counts (t = −6.18, df = 4, p = 0.004). Data underlying these figures is available from https://doi.org/10.5281/zenodo.10909492.

Fig 3. Modeling predicts that metabolic diversity increases the ecological impacts of weapon gene transfer.

Modeling scenarios for each column are shown across the top row. (a–c) Example dynamics of the strains (attacker, target, transconjugant) during a contest using parameters that correspond to the cross (X) shown in the parameter sweeps directly below. (d–f) Transconjugant frequency at steady state (see section “Materials and methods”) in competitions as a function of conjugation rate (b) and toxin killing efficiency (E). (g–i) Final frequency of different strain types at steady state as a function of initial frequency of target and attacker strains. Top and middle rows are conducted at an initial frequency of 1:1:0 (target:attacker:transconjugants). All other parameters are default (Table 1) unless stated. Code and data underlying these figures are available from https://doi.org/10.5281/zenodo.14910561.

Fig 4. A private nutrient promotes the invasion of weapon plasmid recipients, but also of spontaneously resistant cells.

We conducted pairwise competition assays between different E. coli strains on LB agar plates supplemented with sorbitol. For each genotype, cell recovery (CFU) at each time point of co-culturing is shown. (a–c) Competitions conducted over 24 h at either low or high starting cell densities. Means across n = 3 replicates are shown as dots connected by lines. Shaded ribbons depict standard error across replicates. (d+e) Serial passaging competitions conducted over 7 days. CFU were determined each day before transferring to fresh nutrient plates. Means across n = 3 replicates are connected by bold lines. Individual replicates are depicted as faint lines. (a+d) BZB1011-Km^R ΔsrlAEB pColE2-Amp^R (‘Attacker ΔsrlAEB’) competed against toxin-sensitive BZB1011-Cm^R (‘Target’). (b) BZB1011-Km^R ΔsrlAEB R751-Sp^R pColE2-Amp^R (‘Attacker^D ΔsrlAEB’) competed against toxin-resistant BZB1011-Cm^R ΔbtuB (‘Target ΔbtuB’). Transconjugant (BZB1011-Cm^R ΔbtuB R751-Sp^R pColE2-AmpR) CFU are shown as they emerge during the interaction (‘Transconjugant ΔbtuB’). (c+e) BZB1011-Km^R ΔsrlAEB R751-Sp^R pColE2-Amp^R (‘Attacker^D ΔsrlAEB’) competed against toxin-sensitive BZB1011-Cm^R (‘Target’). ‘Transconjugant’ (BZB1011-Cm^R R751-Sp^R pColE2-AmpR) CFU are shown as they emerge during the interaction. To test for differences in final transconjugant abundances between Figs 2f and 4c, we used two-sided, two-sample t-tests on log-transformed CFU counts: t = 5.05, df = 4, p = 0.007 (top left); t = 20.06, df = 2.02, p = 0.002 (top right; Welch’s t test). Data underlying these figures is available from https://doi.org/10.5281/zenodo.10909492.

Fig 5. Weapon gene transfer fundamentally alters competition outcomes when resistance is costly.

We conducted pairwise competition assays between different E. coli strains on minimal medium agar plates supplemented with glucose, sorbitol, and vitamin B12. For each genotype, cell recovery (CFU) at each time point of co-culturing is shown. Dashed grey lines represent the detection limit (200 CFU). (a+b) Competitions conducted over 24 h. Means across n = 3 replicates are shown as dots connected by lines. Shaded ribbons depict standard error across replicates. To test for differences in target survival, we used two-sided, two-sample t-tests on log-transformed CFU counts. (a) WT, top left versus ∆metE, top right: t = −9.36, df = 4, p < 0.001. (b) WT, top left versus ∆metE, top right: t = −7.57, df = 4, p < 0.001. (b) WT, bottom left versus ∆metE, bottom right: t = −8.83, df = 4, p < 0.001. (a) BZB1011-Km^R ΔsrlAEB pColE2-Amp^R (‘Attacker ΔsrlAEB’) was competed against toxin-sensitive BZB1011-Cm^R or BZB1011-Cm^R ΔmetE (‘Target’). (b) BZB1011-Km^R ΔsrlAEB R751-Sp^R pColE2-Amp^R (‘Attacker^D ΔsrlAEB’) was competed against toxin-sensitive BZB1011-Cm^R or BZB1011-Cm^R ΔmetE (‘Target’). Transconjugant (BZB1011-Cm^R (ΔmetE) R751-Sp^R pColE2-AmpR) CFU are shown as they emerge during the interaction (‘Transconjugant’). (c+d) Serial passaging competitions conducted over 7 days. CFU were determined each day before transferring to fresh nutrient plates (see section “Materials and methods”). Means across n = 3 replicates are connected by bold lines. Individual replicates are depicted as faint lines. (c) BZB1011-Km^R ΔsrlAEB pColE2-Amp^R (‘Attacker ΔsrlAEB’) competed against toxin-sensitive BZB1011-Cm^R ΔmetE (‘Target ΔmetE’). (d) BZB1011-Km^R ΔsrlAEB R751-Sp^R pColE2-Amp^R (‘Attacker^D ΔsrlAEB’) competed against toxin-sensitive BZB1011-Cm^R ΔmetE (‘Target ΔmetE’). Transconjugant (BZB1011-Cm^R ΔmetE R751-Sp^R pColE2-AmpR) CFU are shown as they emerge during the interaction (‘Transconjugant ΔmetE’). Data underlying these figures is available from https://doi.org/10.5281/zenodo.10909492.