Limits to compensatory adaptation and the persistence of antibiotic resistance in pathogenic bacteria

Abstract

Antibiotic resistance carries a fitness cost that could potentially limit the spread of resistance in bacterial pathogens. In spite of this cost, a large number of experimental evolution studies have found that resistance is stably maintained in the absence of antibiotics as a result of compensatory evolution. Clinical studies, on the other hand, have found that resistance in pathogen populations usually declines after antibiotic use is stopped, suggesting that compensatory adaptation is not effective in vivo. In this article, we argue that this disagreement arises because there are limits to compensatory adaptation in nature that are not captured by the design of current laboratory selection experiments. First, clinical treatment fails to eradicate antibiotic-sensitive strains, and competition between sensitive and resistant strains leads to the rapid loss of resistance following treatment. Second, laboratory studies overestimate the efficacy of compensatory adaptation in nature by failing to capture costs associated with compensatory mutations. Taken together, these ideas can potentially reconcile evolutionary theory with the clinical dynamics of antibiotic resistance and guide the development of strategies for containing resistance in clinical pathogens.

Keywords: antibiotic resistance, fitness cost; clinical microbiology; compensatory adaptation; experimental evolution.

Figure 1.

Half-life of resistance following antibiotic treatment This figure shows the expected half-life (measured in number of generations) of an antibiotic resistant strain (R) in competition with a higher fitness antibiotic sensitive strain (S) following antibiotic treatment. The key prediction of the model is that resistance should be rapidly eliminated in the absence of antibiotics, provided that sensitive strains make up a small fraction of the population that survives treatment. Half-life was calculated from log (S_t/R_t) = log (S₀/R₀) + t log (w) where t is time and w is the relative fitness of the resistant strain. We assume that half-life is the time taken for the resistant strain to decline to a frequency of 0.5.