Genotyping of Bacillus cereus strains by microarray-based resequencing

Abstract

The ability to distinguish microbial pathogens from closely related but nonpathogenic strains is key to understanding the population biology of these organisms. In this regard, Bacillus anthracis, the bacterium that causes inhalational anthrax, is of interest because it is closely related and often difficult to distinguish from other members of the B. cereus group that can cause diverse diseases. We employed custom-designed resequencing arrays (RAs) based on the genome sequence of Bacillus anthracis to generate 422 kb of genomic sequence from a panel of 41 Bacillus cereus sensu lato strains. Here we show that RAs represent a "one reaction" genotyping technology with the ability to discriminate between highly similar B. anthracis isolates and more divergent strains of the B. cereus s.l. Clade 1. Our data show that RAs can be an efficient genotyping technology for pre-screening the genetic diversity of large strain collections to selected the best candidates for whole genome sequencing.

Figure 1. Graph shows the relationship between basecalling frequency and estimated phred score at various ABACUS total quality score thresholds.

For both the replication and accuracy experiments in Zwick et al. (2005), note that as the ABACUS total quality score threshold is increased, the number of bases called is decreased, with a concomitant increase in data quality (phred score).

Figure 2. Graphs showing resequencing array (RA) percent basecalling at different ABACUS quality score (QS) thresholds.

The black line in each plot shows the basecalling rate for the B. anthracis Ames strain that acted as the reference sequence for the design of the RA. The raw data for this figure is contained in Table S5.

Figure 3. Graph shows relationship between multilocus sequence typing (MLST)/Resequencing Array(RA) tree distance and ABACUS quality score.

Figure 4. Neighbor-joining phylogenetic tree inferred using multilocus sequence typing (MLST) data for a subsample of 19 Bacillus strains.

Bootstrap values for nodes with greater than 99% support (1000 replicates total) are shown.

Figure 5. Neighbor-joining phylogenetic tree inferred using resequencing array (RA) data with a quality score threshold of 30 for a subsample of 19 Bacillus strains.

Bootstrap values for nodes with greater than 99% support (1000 replicates total) are shown.

Figure 6. Neighbor-joining phylogenetic tree inferred using resequencing array (RA) data with a quality score threshold of 60 for a subsample of 19 Bacillus strains.

Bootstrap values for nodes with greater than 99% support (1000 replicates total) are shown.