Pathogenicity Locus, Core Genome, and Accessory Gene Contributions to Clostridium difficile Virulence

Abstract

Clostridium difficile is a spore-forming anaerobic bacterium that causes colitis in patients with disrupted colonic microbiota. While some individuals are asymptomatic C. difficile carriers, symptomatic disease ranges from mild diarrhea to potentially lethal toxic megacolon. The wide disease spectrum has been attributed to the infected host's age, underlying diseases, immune status, and microbiome composition. However, strain-specific differences in C. difficile virulence have also been implicated in determining colitis severity. Because patients infected with C. difficile are unique in terms of medical history, microbiome composition, and immune competence, determining the relative contribution of C. difficile virulence to disease severity has been challenging, and conclusions regarding the virulence of specific strains have been inconsistent. To address this, we used a mouse model to test 33 clinical C. difficile strains isolated from patients with disease severities ranging from asymptomatic carriage to severe colitis, and we determined their relative in vivo virulence in genetically identical, antibiotic-pretreated mice. We found that murine infections with C. difficile clade 2 strains (including multilocus sequence type 1/ribotype 027) were associated with higher lethality and that C. difficile strains associated with greater human disease severity caused more severe disease in mice. While toxin production was not strongly correlated with in vivo colonic pathology, the ability of C. difficile strains to grow in the presence of secondary bile acids was associated with greater disease severity. Whole-genome sequencing and identification of core and accessory genes identified a subset of accessory genes that distinguish high-virulence from lower-virulence C. difficile strains.IMPORTANCEClostridium difficile is an important cause of hospital-associated intestinal infections, and recent years have seen an increase in the number and severity of cases in the United States. A patient's antibiotic history, immune status, and medical comorbidities determine, in part, the severity of C. difficile infection. The relative virulence of different clinical C. difficile strains, although postulated to determine disease severity in patients, has been more difficult to consistently associate with mild versus severe colitis. We tested 33 distinct clinical C. difficile isolates for their ability to cause disease in genetically identical mice and found that C. difficile strains belonging to clade 2 were associated with higher mortality. Differences in survival were not attributed to differences in toxin production but likely resulted from the distinct gene content in the various clinical isolates.

Keywords: Clostridium difficile; accessory genome; bile salt; genome analysis; pathogenicity locus; toxin.

FIG 1

In vivo disease burden of C. difficile clinical isolates in the mouse model. (A) Summary of the experimental protocol. (B) Average acute disease scores taken 3 days postinfection for each of the clinical isolates (n = 5 to 10 mice per isolate). (C) Survival rates in the 2 weeks following infection. Clinical isolates are labeled by their unique strain identifier (in boldface) followed by their MLST type (in parentheses). Error bars indicate standard errors. (D) Disease scores following infection. Disease scores for each clinical isolate were averaged by clade.

FIG 2

Comparison of C. difficile clinical isolate disease severity in humans and mice. Clinical isolates are ranked by their average acute disease score. The bar fill color indicates if the clinical isolate was identified as severe or nonsevere in humans. The bar outlines indicates if the clinical isolate was identified as lethal or nonlethal in mice. Clinical isolates are labeled by their unique strain identifier (shown in boldface) followed by their MLST type (in parentheses).

FIG 3

Ex vivo and in vitro assessments of putative virulence factors of C. difficile clinical isolates. (A) C. difficile burden in the feces of mice 2 days after infection (n = 5 to 10 mice per isolate). (B) Toxin titers in the feces of mice 2 days after infection (n = 5 to 10 mice per isolate). (C) Tolerance of each clinical isolate to administration of 0.01% lithocholic acid (n = 3 experimental trials per isolate). (A to C) Clinical isolates are ranked by their average acute disease score. They are labeled by their unique strain identifier (in bold) followed by their MLST type (in parentheses). Error bars indicate standard errors. (D to F) Comparison of ex vivo and in vitro data to disease score, 2 or 3 days postinfection. Solid lines represent the linear regression, with 95% confidence intervals in the corresponding shaded regions.

FIG 4

Comparative analysis of C. difficile pathogenicity loci. (A) Phylogenetic tree of pathogenicity locus sequences with each clinical isolate. Tree leaves are colored by the relative acute disease score (from blue to red). Clinical isolates are labeled by their unique strain identifier (in bold) followed by the MLST type (in parentheses), and clade 2 isolates are labeled in red text. (B) Single nucleotide variant differences of pathogenicity locus sequences, in relation to the reference strain 217B (MLST 2). Each variant is indicated by a small vertical line, and variants are assigned colors based on the isolate’s clade. Clinical isolates are arranged by their acute disease score.

FIG 5

Core genome phylogeny of C. difficile clinical isolates. Phylogenetic tree of core genome sequences with each clinical isolate. Tree leaves are colored by acute disease score (left) or survival rate (right). Clinical isolates are labeled by their unique strain identifier (in bold) followed by MLST type (in parentheses), and clade 2 isolates are labeled in red text.

FIG 6

Top discriminant features in the accessory genome, based on multiple regression analysis. (A to C) Presence (red) or absence (gray) of the indicated ORF group for each C. difficile clinical isolate. Clinical isolates are labeled by their unique strain identifier (in boldface) followed by the MLST type (in parentheses). (A) Overall multiple regression results. (B) Comparison of low-virulence (186A) and high-virulence MLST 1 strains. (C) Comparison of intermediate-virulence (WUp42) and high-virulence (BBL2) MLST 2 strains.