Establishment of a Publicly Available Core Genome Multilocus Sequence Typing Scheme for Clostridium perfringens

Abstract

Clostridium perfringens is a spore-forming anaerobic pathogen responsible for a variety of histotoxic and intestinal infections in humans and animals. High-resolution genotyping aiming to identify bacteria at strain level has become increasingly important in modern microbiology to understand pathogen transmission pathways and to tackle infection sources. This study aimed at establishing a publicly available genome-wide multilocus sequence-typing (MLST) scheme for C. perfringens. A total of 1,431 highly conserved core genes (1.34 megabases; 50% of the reference genome genes) were indexed for a core genome-based MLST (cgMLST) scheme for C. perfringens. The scheme was applied to 282 ecologically and geographically diverse genomes, showing that the genotyping results of cgMLST were highly congruent with the core genome-based single-nucleotide-polymorphism typing in terms of resolution and tree topology. In addition, the cgMLST provided a greater discrimination than classical MLST methods for C. perfringens. The usability of the scheme for outbreak analysis was confirmed by reinvestigating published outbreaks of C. perfringens-associated infections in the United States and the United Kingdom. In summary, a publicly available scheme and an allele nomenclature database for genomic typing of C. perfringens have been established and can be used for broad-based and standardized epidemiological studies. IMPORTANCE Global epidemiological surveillance of bacterial pathogens is enhanced by the availability of standard tools and sharing of typing data. The use of whole-genome sequencing has opened the possibility for high-resolution characterization of bacterial strains down to the clonal and subclonal levels. Core genome multilocus sequence typing is a robust system that uses highly conserved core genes for deep genotyping. The method has been successfully and widely used to describe the epidemiology of various bacterial species. Nevertheless, a cgMLST typing scheme for Clostridium perfringens is currently not publicly available. In this study, we (i) developed a cgMLST typing scheme for C. perfringens, (ii) evaluated the performance of the scheme on different sets of C. perfringens genomes from different hosts and geographic regions as well as from different outbreak situations, and, finally, (iii) made this scheme publicly available supported by an allele nomenclature database for global and standard genomic typing.

Keywords: Clostridium perfringens; SNP; cgMLST; genome typing.

FIG 1

Schematic of the workflow to define the Clostridium perfringens core genome MLST targets.

FIG 2

Comparison between typing results of allele- and nucleotide-based analysis of core genome MLST target genes. (A) Topological correspondence between the cgMLST neighbor-joining tree (left) and the SNP-based maximum-likelihood tree (right) is shown as a tanglegram. The branches of the tree were color-coded based on the species phylogroups indicated on the branches. The tanglegram was generated using Dendroscope v3.2.1027. (B) Phylogenetic maximum-likelihood tree based on nonrecombinant SNPs identified in the 282 Clostridium perfringens genomes. It shows the population structure of the species with the five phylogroups highlighted next to the ML tree, followed by the predicted toxin types of the strains and the origin and country of isolation as in the legend. The phylogenetic tree was visualized using iTOL v5 (49).

FIG 3

Minimum spanning tree based on the core genome MLST genes of 52 Clostridium perfringens strains from foodborne outbreaks in the United States. Nodes represent core genome MLST sequence types and were labeled according to the outbreak. Classical MLST types of the outbreak strains are also indicated where applicable. Red boxes mark monoclonal clusters detected in the outbreak. Connected blue boxes indicate more than one cluster identified in the outbreak. Clusters were identified based on fewer than seven allelic mismatches (gray shading). Numbers on the connecting lines illustrate the number of target genes with different alleles, represented by solid lines for allele differences below 40 and dotted lines for allele differences above 40. The minimum spanning trees was generated using Ridom SeqSphere v07 (https://www.ridom.de/).

FIG 4

Minimum spanning tree based on the core genome MLST genes of 71 Clostridium perfringens strains from foodborne outbreaks in the United Kingdom. Classical MLST types of the outbreak strains are indicated where applicable. Nodes represent core genome MLST sequence types. Red boxes mark monoclonal clusters detected in the outbreak. Connected blue boxes indicate more than one cluster identified in the outbreak. Clusters were identified based on fewer than seven allelic mismatches (gray shading). Numbers on the connecting lines illustrate the number of target genes with different alleles, represented by solid lines for allele differences below 40 and dotted lines for allele differences above 40. The minimum spanning tree was generated using Ridom SeqSphere v07 (https://www.ridom.de/).

FIG 5

Investigation of 32 Clostridium perfringens strains from outbreaks in care homes in the United Kingdom. (A) Neighbor-joining tree of the 32 C. perfringens strains using the cgMLST allele typing system, with lineages identified based on SNP analysis highlighted as in the original study (17). (B) Minimum spanning tree using cgMLST of the same genomes. Lineages are indicated with boxes, and outbreaks are color-coded as in the legend. Clusters were identified based on fewer than seven allelic mismatches (gray shading). Numbers on the connecting lines illustrate the number of target genes with different alleles, represented by solid lines for allele differences below 40 and dotted lines for allele differences above 40. The minimum spanning tree was generated using Ridom SeqSphere v07 (https://www.ridom.de/).