A genomic portrait of the emergence, evolution, and global spread of a methicillin-resistant Staphylococcus aureus pandemic

Abstract

The widespread use of antibiotics in association with high-density clinical care has driven the emergence of drug-resistant bacteria that are adapted to thrive in hospitalized patients. Of particular concern are globally disseminated methicillin-resistant Staphylococcus aureus (MRSA) clones that cause outbreaks and epidemics associated with health care. The most rapidly spreading and tenacious health-care-associated clone in Europe currently is EMRSA-15, which was first detected in the UK in the early 1990s and subsequently spread throughout Europe and beyond. Using phylogenomic methods to analyze the genome sequences for 193 S. aureus isolates, we were able to show that the current pandemic population of EMRSA-15 descends from a health-care-associated MRSA epidemic that spread throughout England in the 1980s, which had itself previously emerged from a primarily community-associated methicillin-sensitive population. The emergence of fluoroquinolone resistance in this EMRSA-15 subclone in the English Midlands during the mid-1980s appears to have played a key role in triggering pandemic spread, and occurred shortly after the first clinical trials of this drug. Genome-based coalescence analysis estimated that the population of this subclone over the last 20 yr has grown four times faster than its progenitor. Using comparative genomic analysis we identified the molecular genetic basis of 99.8% of the antimicrobial resistance phenotypes of the isolates, highlighting the potential of pathogen genome sequencing as a diagnostic tool. We document the genetic changes associated with adaptation to the hospital environment and with increasing drug resistance over time, and how MRSA evolution likely has been influenced by country-specific drug use regimens.

Figure 1.

Phylogeny of ST22 and the emergence of MRSA clones. (A) Maximum likelihood phylogenetic tree of ST22 isolates. The tree was rooted by using the distantly related S. aureus isolate MSSA476 as an outgroup. Colors indicate the isolates' countries of origin. Roman numerals indicate acquisitions of structurally different SCCmec elements, which cause methicillin resistance. (B) Maximum clade credibility tree of the ST22-A clade based on BEAST analysis using a variable clock rate (uncorrelated lognormal) model. Tips of the tree are constrained by isolation dates, the time scale is shown at the bottom. Gains and losses (Δ) of genetic determinants for resistance to methicillin (SCCmec IVh), fluoroquinolones (point mutations in grlA and gyrA), erythromycin (plasmid-encoded ermC), and clindamycin (mutations in ermC leader peptide region, c-ermC) have been mapped on the tree by applying the parsimony criterion.

Figure 2.

Accessory genome diversity in ST22. CDSs in the accessory genome of each isolate were clustered and assigned to homology groups (HGs). (A) Conservation of accessory genome HGs across the ST22 population. The isolates are ordered according to the phylogeny displayed along the left and top of the figure. The conserved HGs in the pairwise comparison are displayed as a heat map matrix and colored according to the number of conserved HGs (range 64 to 235 HGs) per pair; see figure for scale. (B) Size and composition of each isolate's accessory genome based on the number of HG CDSs. The HGs have been subdivided into different mobile genetic element types based on matches to an annotated MGE reference set included in the clustering (see legend to figure).

Figure 3.

Exponential growth rates (λ) of ST22-A and other ST22 isolates (posterior probability density functions from Bayesian analysis). ST22-A is estimated to have grown significantly faster than non-ST22-A. The population size N at time t was modeled by N(t) = N(0) × e^{(λ × t)}, where λ is the exponential growth rate and t is measured in years. Accordingly, the population size change per year is e^λ.

Figure 4.

Bayesian reconstruction of the spread of ST22-A2 in the UK. A continuous spatial diffusion model was used to reconstruct the finer-scale geographical dispersal of ST22-A2 within the UK and to predict the origin of fluoroquinolone resistance. Lines indicate the inferred routes of spread with confidence displayed as green ovals representing 80% of the highest posterior density (HPD) for latitude and longitude. The timing of transmission events are represented by red (old) to black (recent) lines and light- to dark-green oval shading (for the animation of the reconstruction of the spread, see Supplemental File S2). The maps are based on satellite pictures made available at Google Earth (http://earth.google.com).

Figure 5.

Increase in antibiotic resistance traits within ST22-A population over time. Number of genotypic resistance determinants per ST22-A isolate (red, no. 162) and non-ST22-A isolates (blue, no. 31) from all countries, 1990–2008, including regression lines with 95% confidence interval for each group. Size of circle corresponds to number of isolates.