Temporal interplay between efflux pumps and target mutations in development of antibiotic resistance in Escherichia coli

Abstract

The emergence of resistance presents a debilitating change in the management of infectious diseases. Currently, the temporal relationship and interplay between various mechanisms of drug resistance are not well understood. A thorough understanding of the resistance development process is needed to facilitate rational design of countermeasure strategies. Using an in vitro hollow-fiber infection model that simulates human drug treatment, we examined the appearance of efflux pump (acrAB) overexpression and target topoisomerase gene (gyrA and parC) mutations over time in the emergence of quinolone resistance in Escherichia coli. Drug-resistant isolates recovered early (24 h) had 2- to 8-fold elevation in the MIC due to acrAB overexpression, but no point mutations were noted. In contrast, high-level (≥ 64× MIC) resistant isolates with target site mutations (gyrA S83L with or without parC E84K) were selected more readily after 120 h, and regression of acrAB overexpression was observed at 240 h. Using a similar dosing selection pressure, the emergence of levofloxacin resistance was delayed in a strain with acrAB deleted compared to the isogenic parent. The role of efflux pumps in bacterial resistance development may have been underappreciated. Our data revealed the interplay between two mechanisms of quinolone resistance and provided a new mechanistic framework in the development of high-level resistance. Early low-level levofloxacin resistance conferred by acrAB overexpression preceded and facilitated high-level resistance development mediated by target site mutation(s). If this interpretation is correct, then these findings represent a paradigm shift in the way quinolone resistance is thought to develop.

Fig 1

Bacterial response to sequentially escalating levofloxacin exposures in HFIM (starting with the parent E. coli strain). The data are shown as means ± standard deviations.

Fig 2

Relative expression of acrAB in resistant isolates recovered from HFIM studies (starting with the parent E. coli strain) at various time points (n = 6). The data are shown as means and standard deviations.

Fig 3

Bacterial responses to similar levofloxacin exposures (AUC, approximately 0.6 mg · h/liter) in parent (A) and ΔacrAB mutant (B) strains. The data are shown as means ± standard deviations.

Fig 4

Bacterial responses to levofloxacin exposure (adjusted for MIC) in the parent strain (A) and the ΔacrAB mutant (B). The data are shown as means ± standard deviations.