Strain-Level Identification of Bacterial Tomato Pathogens Directly from Metagenomic Sequences

Abstract

Routine strain-level identification of plant pathogens directly from symptomatic tissue could significantly improve plant disease control and prevention. Here we tested the Oxford Nanopore Technologies (ONT) MinION sequencer for metagenomic sequencing of tomato plants either artificially inoculated with a known strain of the bacterial speck pathogen <i>Pseudomonas syringae</i> pv. <i>tomato</i> or collected in the field and showing bacterial spot symptoms caused by one of four <i>Xanthomonas</i> species. After species-level identification via ONT's WIMP software and the third-party tools Sourmash and MetaMaps, we used Sourmash and MetaMaps with a custom database of representative genomes of bacterial tomato pathogens to attempt strain-level identification. In parallel, each metagenome was assembled and the longest contigs were used as query with the genome-based microbial identification Web service LINbase. Both the read-based and assembly-based approaches correctly identified <i>P. syringae</i> pv. <i>tomato</i> strain T1 in the artificially inoculated samples. The pathogen strain in most field samples was identified as a member of <i>Xanthomonas perforans</i> group 2. This result was confirmed by whole genome sequencing of colonies isolated from one of the samples. Although in our case metagenome-based pathogen identification at the strain level was achieved, caution still must be exercised in interpreting strain-level results because of the challenges inherent to assigning reads to specific strains and the error rate of nanopore sequencing.