Environmental and genetic determinants of plasmid mobility in pathogenic Escherichia coli

Abstract

Plasmids are key vehicles of horizontal gene transfer (HGT), mobilizing antibiotic resistance, virulence, and other traits among bacterial populations. The environmental and genetic forces that drive plasmid transfer are poorly understood, however, due to the lack of definitive quantification coupled with genomic analysis. Here, we integrate conjugative phenotype with plasmid genotype to provide quantitative analysis of HGT in clinical Escherichia coli pathogens. We find a substantial proportion of these pathogens (>25%) able to readily spread resistance to the most common classes of antibiotics. Antibiotics of varied modes of action had less than a 5-fold effect on conjugation efficiency in general, with one exception displaying 31-fold promotion upon exposure to macrolides and chloramphenicol. In contrast, genome sequencing reveals plasmid incompatibility group strongly correlates with transfer efficiency. Our findings offer new insights into the determinants of plasmid mobility and have implications for the development of treatments that target HGT.

Fig. 1. The environmental and genetic determinants of plasmid mobility.

(A) The influence of environmental and genetic factors on conjugation is confounded by growth dynamics between donor (red), recipient (blue), and transconjugant (purple) populations. By decoupling conjugation modulation from growth dynamics, we can identify and use the determinants of plasmid mobility to fight antibiotic resistance. (B) Assembling a library of natural isolates with quantifiable rates of conjugation is a substantial undertaking. Starting from a library of 219 clinical E. coli pathogens from patient bloodstream infections, we screened for the ability to transfer β-lactam resistance commonly found on plasmids native to the Enterobacteriaceae family. Approximately 25% of the carbenicillin-resistant (CarbR) isolates exhibited detectable transfer to chromosomally kanamycin (KanR)– or chloramphenicol (CmR)–resistant recipients. These and seven extended spectrum β-lactamase (ESBL) donors were subsequently used to examine environmental and genetic determinants of plasmid mobility. (C) The diversity present in the E. coli pathogen library is maintained through conjugation screening. A phylogenetic tree of the library was constructed from 200 genome assemblies (BioProject accession nos. PRJNA290784 and PRJNA551684) to reveal the breadth of our analysis throughout each phase of screening. Genome assemblies for the remaining 19 isolates were either unavailable or of insufficient quality. E. coli strain EC958 (GenBank accession no. HG941718.1) was used as a reference genome for alignment. Isolates are color labeled by their final phase. Major multilocus sequence types (≥5 isolates in common) present in the library are highlighted in gray.

Fig. 2. A time to threshold method for conjugation quantification.

(A) The principle of time to threshold quantification. Consider the exponential growth of the transconjugant from an initial density T₀ (top panel). The time (τ) required for the population to reach a set threshold (T_C) is uniquely determined by T₀ and the specific growth rate (μ). This defines a log-linear relationship between T₀ and τ: lnT₀ = ln T_C − μτ (bottom panel). (B) Quantification of T₀ is complicated by the presence of donor and recipient cells. Top panel: Although strong antibiotic selection is applied against donor and recipient cells during transconjugant outgrowth, death is not instantaneous (i.e., conjugation may still occur). Bottom panel: Modeling reveals conjugation of variable efficiency (η) during outgrowth causes a deviation from the log-linear relationship. This effect is amplified with smaller T₀, where transconjugants produced from outgrowth conjugation—not outgrowth alone—may comprise a sizeable proportion of the total transconjugant population. (C) Correcting for outgrowth conjugation. Top panel: The growth contribution from the transconjugant alone can be approximated by the difference (ΔN) between the growth curves originating from the conjugation mixture (T₀ > 0) and conjugation control (T₀ = 0). Darker curves represent higher T₀. Bottom panel: Using ΔN, the log-linear relationship between T₀ and τ is maintained even in the presence of conjugation during outgrowth. (D) Applying the time to threshold method to experimental data. T₀, spanning six orders of magnitude, maintains a strong correlation (R² > 0.99) with τ from a ΔOD threshold. Darker curves represent higher T₀.

Fig. 3. Antibiotic modulation of conjugation is rare in pathogenic E. coli.

The effect of five antibiotics on conjugation in clinical E. coli pathogens was assessed via the time to threshold method. Antibiotics of differing therapeutic mechanism were dosed in three concentrations (0.5×, 1×, and 2×) based on 50% inhibitory concentrations for a MG1655 E. coli recipient standard. IC₅₀ values for Carb, Cm, Kan, erythromycin (Ery), and Norf were as follows: 1.91, 1.92, 2.13, 20.20, and 0.05 μg/ml. Displayed Δτ are averages of triplicate measurements ±SE, and normalized by subtracting the no-antibiotic control τ. Promotion of conjugation is indicated by Δτ < 0, while Δτ > 0 indicates inhibition. Only GN02766 displayed major modulation of conjugation when exposed to Ery (all concentrations, P < 0.01, Tukey post hoc test) and Cm (2× concentration, P < 0.05). Results from two separate GN02766 experiments are shown.

Fig. 4. Identification of plasmid features unique to strain GN02766.

Plasmid sequences from strains displaying no antibiotic modulation were aligned to p2766-1 via BLASTn and BLAST Ring Image Generator (BRIG) (47). Nucleotide identity ≥70% is indicated by a band colored according to the Inc group, with darker shading corresponding to higher sequence match. Blank regions indicate <70% nucleotide identity. Inner GC content plots, size map, and outer coding sequences (CDSs) are for p2766-1. Antibiotic resistance genes are highlighted in red, and transposon repeat region in gray. Notable features include five-plasmid maintenance systems (pemKI, relBE, hok-sok, srnBC, and parAB), a mobilized enterotoxin and colicin J receptor operon (cjrABC-senB), and five consecutive tnpA transposon repeats carrying blaSHV.

Fig. 5. Conjugation efficiency groups by plasmid incompatibility.

Plasmids carrying β-lactamases from clinical E. coli pathogens were classified by Inc grouping and MOB relaxase families. To eliminate host effects, conjugation efficiencies were only measured using DA28102 transconjugants and the fAYC002 recipient. There is no significant difference among conjugation efficiencies when grouped by MOB relaxase (P = 0.291, ANOVA), whereas grouping by Inc is highly significant (P < 0.0001). Individual Inc groups that could not be distinguished from one another at P ≤ 0.05 are bracketed. Data were log transformed to normalize variation across orders of magnitude. Error bars represent ±SD from at least three replicates.