Metagenomic Approaches Reveal Strain Profiling and Genotyping of Klebsiella pneumoniae from Hospitalized Patients in China

Abstract

Klebsiella pneumoniae is a leading cause of highly drug-resistant infections in hospitals worldwide. Strain-level bacterial identification on the genetic determinants of multidrug resistance and high pathogenicity is critical for the surveillance and treatment of this clinically relevant pathogen. In this study, metagenomic next-generation sequencing was performed for specimens collected from August 2020 to May 2021 in Ruijin Hospital, Ningbo Women and Children's Hospital, and the Second Affiliated Hospital of Harbin Medical University. Genome biology of K. pneumoniae prevalent in China was characterized based on metagenomic data. Thirty K. pneumoniae strains derived from 14 sequence types were identified by multilocus sequence typing. The hypervirulent ST11 K. pneumoniae strains carrying the KL64 capsular locus were the most prevalent in the hospital population. The phylogenomic analyses revealed that the metagenome-reconstructed strains and public isolate genomes belonging to the same STs were closely related in the phylogenetic tree. Furthermore, the pangenome structure of the detected K. pneumoniae strains was analyzed, particularly focusing on the distribution of antimicrobial resistance genes and virulence genes across the strains. The genes encoding carbapenemases and extended-spectrum beta-lactamases were frequently detected in the strains of ST11 and ST15. The highest numbers of virulence genes were identified in the well-known hypervirulent strains affiliated to ST23 bearing the K1 capsule. In comparison to traditional cultivation and identification, strain-level metagenomics is advantageous to understand the mechanisms underlying resistance and virulence of K. pneumoniae directly from clinical specimens. Our findings should provide novel clues for future research into culture-independent metagenomic surveillance for bacterial pathogens. IMPORTANCE Routine culture and PCR-based molecular testing in the clinical microbiology laboratory are unable to recognize pathogens at the strain level and to detect strain-specific genetic determinants involved in virulence and resistance. To address this issue, we explored the strain-level profiling of K. pneumoniae prevalent in China based on metagenome-sequenced patient materials. Genome biology of the targeted bacterium can be well characterized through decoding sequence signatures and functional gene profiles at the single-strain resolution. The in-depth metagenomic analysis on strain profiling presented here shall provide a promising perspective for culture-free pathogen surveillance and molecular epidemiology of nosocomial infections.

Keywords: K. pneumoniae; MLST; antimicrobial resistance genes; capsule typing; metagenome-reconstructed strains; phylogeny; strain profiling; virulence genes.

FIG 1

Phylogenomic and pangenomic structure of K. pneumoniae. (A) Maximum likelihood phylogeny of K. pneumoniae. The phylogenetic tree was built using the 38 K. pneumoniae-specific marker genes detected in the 30 metagenomic samples and 100 reference genomes from three major members of the K. pneumoniae species complex. (B) Gene family profiles of K. pneumoniae strains from metagenomes as well as isolate genomes. The heatmap displays the presence/absence patterns of the accessory genes across data sets.

FIG 2

Comparison of COG functional categories between core and accessory gene families in the pangenome of K. pneumoniae MRSs. The asterisk denotes a significant difference in the corresponding category between two genic groups (FDR < 0.001; chi-square test).

FIG 3

Distribution of antimicrobial resistance (AMR) genes across the metagenome-reconstructed strains of K. pneumoniae. The prediction of AMR genes was performed using RGI searching against CARD. The heatmap shows the presence/absence patterns of the genes conferring resistance to β-lactams, fluoroquinolones, aminoglycosides, and tetracyclines. The list of all detected AMR genes is summarized in Table S5.

FIG 4

Distribution of virulence genes across the metagenome-reconstructed strains of K. pneumoniae. The prediction of virulence genes was performed using BLAST searching against VARD. The heatmap shows the presence/absence patterns of the genes associated with the biosynthesis of polysaccharide capsule and three siderophores aerobactin (Aer), yersiniabactin (Ybt), and salmochelin (Sal). The list of all detected virulence genes is summarized in Table S6.