In silico microarray probe design for diagnosis of multiple pathogens

Abstract

Background: With multiple strains of various pathogens being sequenced, it is necessary to develop high-throughput methods that can simultaneously process multiple bacterial or viral genomes to find common fingerprints as well as fingerprints that are unique to each individual genome. We present algorithmic enhancements to an existing single-genome pipeline that allows for efficient design of microarray probes common to groups of target genomes. The enhanced pipeline takes advantage of the similarities in the input genomes to narrow the search to short, nonredundant regions of the target genomes and, thereby, significantly reduces the computation time. The pipeline also computes a three-state hybridization matrix, which gives the expected hybridization of each probe with each target.

Results: Design of microarray probes for eight pathogenic Burkholderia genomes shows that the multiple-genome pipeline is nearly four-times faster than the single-genome pipeline for this application. The probes designed for these eight genomes were experimentally tested with one non-target and three target genomes. Hybridization experiments show that less than 10% of the designed probes cross hybridize with non-targets. Also, more than 65% of the probes designed to identify all Burkholderia mallei and B. pseudomallei strains successfully hybridize with a B. pseudomallei strain not used for probe design.

Conclusion: The savings in runtime suggest that the enhanced pipeline can be used to design fingerprints for tens or even hundreds of related genomes in a single run. Hybridization results with an unsequenced B. pseudomallei strain indicate that the designed probes might be useful in identifying unsequenced strains of B. mallei and B. pseudomallei.

Figure 1

Overview of the TOFI pipeline. Stage 1 and Stage 3 of the TOFI pipeline have been improved to handle multiple genomes. In stage 1, the target genomes are compared with each other to eliminate redundant sequences. In Stage3, an in silico hybridization matrix is computed, which indicates which probes hybridize to which targets.

Figure 2

Histograms of normalized hybridization intensities for the 382 probes that have 100% identity with the three target genomes. The X-axis shows the normalized hybridization intensities and the Y-axis shows the number of probes that have a given normalized hybridization intensity. Many of the 382 probes fail to hybridize with B. pseudomallei K96243 even though all these probes have 100% identity with this genome, whereas hybridization intensities for the other three genomes are as expected.