Recent independent emergence of multiple multidrug-resistant Serratia marcescens clones within the United Kingdom and Ireland

Abstract

Serratia marcescens, a member of the Enterobacteriaceae family, is a Gram-negative bacterium responsible for a wide range of nosocomial infections. The emergence of multidrug-resistant strains is an increasing danger to public health. To design effective means to control the dissemination of S. marcescens, an in-depth analysis of the population structure and variation is required. Utilizing whole-genome sequencing, we characterized the population structure and variation, as well as the antimicrobial resistance determinants, of a systematic collection of antimicrobial-resistant S. marcescens associated with bloodstream infections in hospitals across the United Kingdom and Ireland between 2001 and 2011. Our results show that S. marcescens is a diverse species with a high level of genomic variation. However, the collection was largely composed of a limited number of clones that emerged from this diverse background within the past few decades. We identified potential recent transmissions of these clones, within and between hospitals, and showed that they have acquired antimicrobial resistance determinants for different beta-lactams, ciprofloxacin, and tetracyclines on multiple occasions. The expansion of these multidrug-resistant clones suggests that the treatment of S. marcescens infections will become increasingly difficult in the future.

Figure 1.

Pan-genome analysis of Serratia marcescens whole-genome sequences. (A) Maximum likelihood tree constructed from the core genome. On the right, the presence (blue) and absence (white) of accessory genome elements is shown. Accessory elements located on the same contig are shown as colored blocks along the top of the figure. (B) Comparison between the binary tree constructed from the absence and presence pattern of genes in the accessory genome (bottom) and the maximum likelihood tree constructed from variation in the core genome (top). The lines connect identical tips of the two trees. (C) A histogram of pairwise SNP distances between all 205 isolates. The distances are based on the core genome alignment.

Figure 2.

Geographical distribution and transmission network analysis. (A) Isolation sites across the UK&I; (B) maximum likelihood tree with isolates colored according to location. (C) The transmission network constructed for potential transmission events. Only edges of <10 SNPs are displayed, and singleton nodes are not shown. Colors correspond to hospitals. Dashed circles show potential between-hospital transmissions and the locations of those hospitals on the map. The numbers next to edges denote pairwise SNP distance between isolates.

Figure 3.

Temporal, geographical and phylogenetic clustering of isolates on the tree. (A) Phylogenetic tree with isolates colored according to cluster. The nodes with bootstrap support >90 are shown in red. The pie charts show the distribution of years of isolation and the color intensity corresponds to the temporal order, namely, the older the year of isolation the darker the color. The stacked bar plot shows the distribution of hospitals across the major clades on the phylogenetic tree. Each color corresponds to one hospital. (B) The estimated substitution rate for the clusters with significant temporal signal. Error bars show the 95% confidence intervals. The mutation rate is obtained by taking the average of three independent BEAST runs. (C) The estimated age of the MRCA for each cluster. Error bars correspond to 95% confidence interval for clusters shown in B. For the clusters without significant temporal signals, i.e., clusters 1, 3, 4, 7, and 9, we calculated the mean root age by using the mean substitution rate for clusters 2, 5, 6, and 8. For error bars, we considered the substitution rates obtained for maximum and minimum of 95% confidence intervals for clusters 2, 5, 6, and 8.