Whole-Genome Sequencing Reveals the High Nosocomial Transmission and Antimicrobial Resistance of Clostridioides difficile in a Single Center in China, a Four-Year Retrospective Study

Abstract

Clostridioides difficile, which causes life-threatening diarrheal disease, presents an urgent threat to health care systems. In this study, we present a retrospective genomic and epidemiological analysis of C. difficile in a large teaching hospital. First, we collected 894 nonduplicate fecal samples from patients during a whole year to elucidate the C. difficile molecular epidemiology. We then presented a detailed description of the population structure of C. difficile based on 270 isolates separated between 2015 and 2020 and clarified the genetic and phenotypic features by MIC and whole-genome sequencing. We observed a high carriage rate (19.4%, 173/894) of C. difficile among patients in this hospital. The population structure of C. difficile was diverse with a total of 36 distinct STs assigned. In total, 64.8% (175/270) of the isolates were toxigenic, including four CDT-positive (C. difficile transferase) isolates, and 50.4% (135/268) of the isolates were multidrug-resistant. Statistically, the rates of resistance to erythromycin, moxifloxacin, and rifaximin were higher for nontoxigenic isolates. Although no vancomycin-resistant isolates were detected, the MIC for vancomycin was higher for toxigenic isolates (P < 0.01). The in-hospital transmission was observed, with 43.8% (110/251) of isolates being genetically linked to a prior case. However, no strong correlation was detected between the genetic linkage and epidemiological linkage. Asymptomatic colonized patients play the same role in nosocomial transmission as infected patients, raising the issue of routine screening of C. difficile on admission. This work provides an in-depth description of C. difficile in a hospital setting and paves the way for better surveillance and effective prevention of related diseases in China. IMPORTANCE Clostridioides difficile infections (CDI) are the leading cause of healthcare-associated diarrhea and are known to be resistant to multiple antibiotics. In the past decade, C. difficile has emerged rapidly and has spread globally, causing great concern among American and European countries. However, research on CDI remains limited in China. Here, we characterized the comprehensive spectrum of C. difficile by whole-genome sequencing (WGS) in a Chinese hospital, showing a high detection rate among patients, diverse genome characteristics, a high level of antibiotic resistance, and an unknown nosocomial transmission risk of C. difficile. During the study period, two C. difficile transferase (CDT)-positive isolates belonging to a new multilocus sequence type (ST820) were detected, which have caused serious clinical symptoms. This work describes C. difficile integrally and provides new insight into C. difficile surveillance based on WGS in China.

Keywords: Clostridioides difficile; antibiotic-resistant; infection and colonization; nosocomial transmission; virulence gene variants; whole-genome sequencing.

FIG 1

Genomic structure of the C. difficile population. (A) A maximum likelihood phylogenetic tree of 283 C. difficile isolates (270 sequenced in this study and 13 reference genomes) was generated using 20057 cgSNPs from a 5.5 Mb alignment of 1529 core genes. The background shading represents the MLST clades. The internal (first) circle is colored based on sequence clusters (SCs) by hierBAPs analysis. The second circle is colored MLST data. The outside circle is the collected dates. Colored stars at the start of the branches represent different toxin profiles. (B) The correlation between three genotyping methods: clade, MLST, and SCs. The height of the bars indicates the number of isolates. Each bar represents a single SC, and the STs are labeled in the blank. The colors of the bars represent different clades. (C) MLST distribution in different toxin profiles. The height of the bars indicates the number of isolates. Each bar represents a single ST, except for the far-right bar containing all the singleton STs. The colors of the bars represent different toxin profiles.

FIG 2

The relationship between TcdA, TcdB variants, and MLST. (A) The genomic structure of PaLoc in the reference strain C. difficile CD630. (B) Riverplot graph showing the relationship between TcdA, TcdB variants, and MLST. The flows are colored according to MLST. (C) Amino acid sequence identity between the 11 types of TcdA variants. (D) Amino acid sequence identity between the 16 types of TcdB variants. Because the TcdA CROP domain contained many repeat sequences, the complete amino acid sequence was unable to be assembled, so only the first 6330 nucleotide sites (1 to 2110 aa) were included in the analysis.

FIG 3

Distribution of antimicrobial resistance elements. The phylogenetic tree was structured as in Fig. 1A. The branches and the color strip next to the tree are colored according to SCs. From left to right, the red heatmap represents the ARGs identified by the Resfinder and CARD databases, the green heatmap represents the amino acid substitutions, and the blue heatmap represents the resistant phenotype. The dark color indicates presence (resistance), and the light color indicates absence (susceptibility).

FIG 4

The relationship between genetic linkages and epidemiological linkages. (A) SNVs between each case and the most genetically closed previous case. (B) The percentages of the epidemiological-linked case pairs in genetically linked case pairs according to the different SNV thresholds (from SNV = 0 to SNV ≤ 10). CD630 was used as the reference genome.

FIG 5

Transmission networks of C. difficile positive inpatients based on SNVs, wards, and sampling time. Only 30 multiple case clusters are shown. Filled colors indicate the ward information. (A) The x-axis indicates the collection date. Each plot represents an isolate. Isolates sharing more than three SNVs with any prior isolates were defined as a distinct cluster and were plotted on a separate horizontal line. (B) The shape of arrows represents the sample interval: solid line (in 28 d), dashed line (28 d to 365 d), and vertical slash (>365). The arrowhead points to the isolates collected later.

FIG 6

Samples isolated from the same patient at different times. Each plot represents an isolate, and each line represents a patient. Genetically related isolates are shown in the same color. TCD isolates are represented by circles and NTCD isolates by triangles. Isolates connected with solid lines indicate 0 to 3 pairwise SNVs, while isolates connected with dashed lines indicate 4 to 10 pairwise SNVs.