The serum resistome of a globally disseminated multidrug resistant uropathogenic Escherichia coli clone

Abstract

Escherichia coli ST131 is a globally disseminated, multidrug resistant clone responsible for a high proportion of urinary tract and bloodstream infections. The rapid emergence and successful spread of E. coli ST131 is strongly associated with antibiotic resistance; however, this phenotype alone is unlikely to explain its dominance amongst multidrug resistant uropathogens circulating worldwide in hospitals and the community. Thus, a greater understanding of the molecular mechanisms that underpin the fitness of E. coli ST131 is required. In this study, we employed hyper-saturated transposon mutagenesis in combination with multiplexed transposon directed insertion-site sequencing to define the essential genes required for in vitro growth and the serum resistome (i.e. genes required for resistance to human serum) of E. coli EC958, a representative of the predominant E. coli ST131 clonal lineage. We identified 315 essential genes in E. coli EC958, 231 (73%) of which were also essential in E. coli K-12. The serum resistome comprised 56 genes, the majority of which encode membrane proteins or factors involved in lipopolysaccharide (LPS) biosynthesis. Targeted mutagenesis confirmed a role in serum resistance for 46 (82%) of these genes. The murein lipoprotein Lpp, along with two lipid A-core biosynthesis enzymes WaaP and WaaG, were most strongly associated with serum resistance. While LPS was the main resistance mechanism defined for E. coli EC958 in serum, the enterobacterial common antigen and colanic acid also impacted on this phenotype. Our analysis also identified a novel function for two genes, hyxA and hyxR, as minor regulators of O-antigen chain length. This study offers novel insight into the genetic make-up of E. coli ST131, and provides a framework for future research on E. coli and other Gram-negative pathogens to define their essential gene repertoire and to dissect the molecular mechanisms that enable them to survive in the bloodstream and cause disease.

Figure 1. Summary of sequence read data from multiplexed TraDIS.

(A) Number of tagged reads obtained in each lane of TruSeq version 2 and version 3 flowcells. (B) Correlation between the two biological replicates. The number of insertions in each gene from Test A was plotted against that from Test B; the correlation coefficient R² indicates very low variation between the two replicates.

Figure 2. Number of essential genes in each COG functional category.

Figure 3. Experimental design to identify serum resistance genes in EC958.

(A) Selection steps employed using fresh serum as test and inactivated serum as control. (B) Schematic illustration of the Illumina sequencing procedure including the use of a custom oligo for indexing and enrichment of insert sites.

Figure 4. Overview of the E. coli EC958 serum resistance genes.

The circular diagram depicts the location of 56 serum resistance genes on the E. coli EC958 genome. The two outer rings containing blue and red arrows illustrate the CDS and serum resistance genes, respectively, on the forward and reverse strand of the genome. The inner red ring represents the logFC between the control and the test samples for each CDS. The three insets represent a close-up look at three regions on the genome with the graphs showing the location and relative number of each mutant found in the control (blue) and test (red) samples.

Figure 5. Characterization of O25b antigen genes in EC958.

(A) Comparison of the O-antigen cluster in EC958 with MG1655 (NC_000913) and E47a (GU014554); genes in green are involved in sugar biosynthesis, genes in purple are involved in O-antigen processing and genes in orange encode glycosyl transferase enzymes; genes with a black outline were shown to be required for serum resistance and genes with a red outline were defined as essential. (B) Predicted function of the four glycosyl transferases in the biosynthesis of the O25b repeat unit , . (C) LPS gels showing changes in O-antigen structures corresponding to mutations in each gene.

Figure 6. Genetic context of the hyxA and hyxR genes and their role in O-antigen synthesis.

(A) The conserved location of PAI-X containing hyxAR genes in E. coli genomes of various pathotypes. (B) The LPS pattern of the hyxA and hyxR mutants and their complemented strains, demonstrating a role for the hyxA and hyxR genes in O-antigen chain length regulation. Red boxes highlight differences in LPS patterns compared with that of the wild-type.

Figure 7. In trans complementation of wild-type EC958 protects ompA mutants from serum killing.

Wild-type EC958 and an EC958 ompA mutant were mixed at different ratios, exposed to human serum for 90 minutes, and the EC958 ompA mutant was examined for its sensitivity to human serum (expressed as the −log₁₀ CFU difference between time 90 and time 0). The red line indicates the threshold below which a strain was considered resistant to serum killing. The EC958 ompA mutant was protected from killing when present at a percentage of 15% or less in the mixed bacterial suspension.