Bacterial Transformation Buffers Environmental Fluctuations through the Reversible Integration of Mobile Genetic Elements

Abstract

Horizontal gene transfer (HGT) promotes the spread of genes within bacterial communities. Among the HGT mechanisms, natural transformation stands out as being encoded by the bacterial core genome. Natural transformation is often viewed as a way to acquire new genes and to generate genetic mixing within bacterial populations. Another recently proposed function is the curing of bacterial genomes of their infectious parasitic mobile genetic elements (MGEs). Here, we propose that these seemingly opposing theoretical points of view can be unified. Although costly for bacterial cells, MGEs can carry functions that are at points in time beneficial to bacteria under stressful conditions (e.g., antibiotic resistance genes). Using computational modeling, we show that, in stochastic environments, an intermediate transformation rate maximizes bacterial fitness by allowing the reversible integration of MGEs carrying resistance genes, although these MGEs are costly for host cell replication. Based on this dual function (MGE acquisition and removal), transformation would be a key mechanism for stabilizing the bacterial genome in the long term, and this would explain its striking conservation.IMPORTANCE Natural transformation is the acquisition, controlled by bacteria, of extracellular DNA and is one of the most common mechanisms of horizontal gene transfer, promoting the spread of resistance genes. However, its evolutionary function remains elusive, and two main roles have been proposed: (i) the new gene acquisition and genetic mixing within bacterial populations and (ii) the removal of infectious parasitic mobile genetic elements (MGEs). While the first one promotes genetic diversification, the other one promotes the removal of foreign DNA and thus genome stability, making these two functions apparently antagonistic. Using a computational model, we show that intermediate transformation rates, commonly observed in bacteria, allow the acquisition then removal of MGEs. The transient acquisition of costly MGEs with resistance genes maximizes bacterial fitness in environments with stochastic stress exposure. Thus, transformation would ensure both a strong dynamic of the bacterial genome in the short term and its long-term stabilization.

Keywords: horizontal gene transfer; mobile genetic elements; natural transformation; resistance genes; stochastic environment.

FIG 1

Schematic representation of the computational model. Bacterial cell growth follows a logistic growth model. The bacterial cells have an insertion site in their chromosome at which two types of alleles from the eDNA compartment can be integrated from transformation and replace their current DNA: wild-type (WT) allele and MGE. The integration of a WT allele is costless for cells, whereas the integration of MGEs causes a cost in terms of cell replication. Bacterial populations are faced with stochastic stresses of random duration and intensity. In the absence of stress, cells are lysed at a basal rate. Under stress exposure, the lysis rate of WT cells increases but remains unchanged for cells with an MGE carrying resistance. Each lysed cell releases its DNA and fuels the extracellular compartment with eDNA. MGEs are constantly added to the extracellular environment at a marginal rate (MGE input) simulating residual arrival from neighboring populations. The WT alleles and MGEs are degraded at a constant rate in the extracellular compartment.

FIG 2

Relative success of genotypes according to their transformation strategies. (A) Proportions of the competing genotypes at t = 5,000: nontransformable resistant (NTR), nontransformable susceptible (NTS), and 21 genotypes with transformation rates ranging from 10⁻⁵ to 10⁻¹ per time unit (t⁻¹). (B) Proportions of extinction of the genotypes at t = 5,000, among the 500 simulations. (C) Stochastic growth rate, as proxy of the fitness of the genotypes in stochastic environments (see Materials and Methods). (D) Composition of the extracellular compartment at t = 5,000. Represented data are the means and standard errors calculated from 500 simulations. Population dynamics are simulated in four distinct environments: one stress-free constant environment (F = 0) and three environments with stochastic stress exposure, differentiated by stress frequency of F = 5 × 10⁻⁴, F = 10⁻³, and F = 2 × 10⁻³ t⁻¹ (see Fig. S2 in the supplemental material).

FIG 3

Maintenance of wild-type alleles in transformable genotypes. (A) Percentages of wild-type (WT) cells at the end of the simulations for each genotype. Extinct genotypes are not accounted for the calculus. (B) Percentages of WT cells from cure, i.e., WT cells with past MGE integration.

FIG 4

Types of transformation events (infection or cure) for the predominant genotype (with transformation rate 10^−2.4 t⁻¹). (A) Box plot of the percentages of cure events (MGE infected cell→WT cell) among all transformation events depending on the number of stresses. (B) Box plot of the percentage events of infection by MGE (WT cell→MGE infected cell) among all transformation events depending on the number of stresses. Results group simulations with all stress frequencies. (C) Composition of the extracellular compartment at t = 5,000 (box plot of the percentage of WT alleles).