Microarray-based resequencing of multiple Bacillus anthracis isolates

Abstract

We used custom-designed resequencing arrays to generate 3.1 Mb of genomic sequence from a panel of 56 Bacillus anthracis strains. Sequence quality was shown to be very high by replication (discrepancy rate of 7.4 x 10(-7)) and by comparison to independently generated shotgun sequence (discrepancy rate < 2.5 x 10(-6)). Population genomics studies of microbial pathogens using rapid resequencing technologies such as resequencing arrays are critical for recognizing newly emerging or genetically engineered strains.

Figure 1

ABACUS quality scores for base calls in B. anthracis. A quality score measures the difference, in log₁₀ units, between the likelihood support level for the best base-call model minus that for the second-best model [32]. Of the bases, 92.6% possess quality scores that exceeded the threshold (31) used for this study.

Figure 2

B. anthracis SNP frequency spectrum. An excess of rare SNPs are observed in our sample. Ninety-two percent of the SNPs that we discovered have a minor allele frequency less than or equal to 0.25. This finding (92%) is significantly different from the neutral theory expectation (60%). This excess can arise as a consequence of rapid, population expansion from a small founder population and/or the action of natural selection.

Figure 3

Radial tree showing inferred phylogenetic relationships of B. anthracis strains from this study. The 37 variable positions identified in this study were concatenated together to create artificial sequence types. Groups of strains with identical sequence types were A0488 and ASC006; A0039, ASC025, ASC031, ASC070, ASC074 and ASC394; ASC074 and ASC054; A0328, ASC061 and ASC073; A0034, ASC159, ASC165 and ASC398. A DNA distance matrix was created using DNADIST, plotted as a UPGMA tree using NEIGHBOR and the tree plotted using DRAWGRAM [56]. The B1 strain A0465 was used as an outgroup.