Next generation sequencing provides rapid access to the genome of Puccinia striiformis f. sp. tritici, the causal agent of wheat stripe rust

Abstract

Background: The wheat stripe rust fungus (Puccinia striiformis f. sp. tritici, PST) is responsible for significant yield losses in wheat production worldwide. In spite of its economic importance, the PST genomic sequence is not currently available. Fortunately Next Generation Sequencing (NGS) has radically improved sequencing speed and efficiency with a great reduction in costs compared to traditional sequencing technologies. We used Illumina sequencing to rapidly access the genomic sequence of the highly virulent PST race 130 (PST-130).

Methodology/principal findings: We obtained nearly 80 million high quality paired-end reads (>50x coverage) that were assembled into 29,178 contigs (64.8 Mb), which provide an estimated coverage of at least 88% of the PST genes and are available through GenBank. Extensive micro-synteny with the Puccinia graminis f. sp. tritici (PGTG) genome and high sequence similarity with annotated PGTG genes support the quality of the PST-130 contigs. We characterized the transposable elements present in the PST-130 contigs and using an ab initio gene prediction program we identified and tentatively annotated 22,815 putative coding sequences. We provide examples on the use of comparative approaches to improve gene annotation for both PST and PGTG and to identify candidate effectors. Finally, the assembled contigs provided an inventory of PST repetitive elements, which were annotated and deposited in Repbase.

Conclusions/significance: The assembly of the PST-130 genome and the predicted proteins provide useful resources to rapidly identify and clone PST genes and their regulatory regions. Although the automatic gene prediction has limitations, we show that a comparative genomics approach using multiple rust species can greatly improve the quality of gene annotation in these species. The PST-130 sequence will also be useful for comparative studies within PST as more races are sequenced. This study illustrates the power of NGS for rapid and efficient access to genomic sequence in non-model organisms.

Figure 1. Coverage distribution by contig (log₁₀ scale).

Contigs are ordered by coverage (calculated using Bowtie [10]). Some repetitive regions are assembled into single contigs resulting in higher coverage and an underestimation of the genome size. The horizontal line indicates the median coverage (60.4x) and the dotted line the 2-fold coverage (120.8x) used as the threshold to calculate the proportion of the genome represented by contigs assembled from duplicated regions.

Figure 2. Microsynteny between PST-130 and PGTG contigs.

Microsynteny between PGTG [AAWC01001263 (A), AAWC01003253 (B), AAWC01000559 (C) [5]] and PST-130 (PST130_8308, PST130_8617, PST130_7101) contigs. Contig alignment and similarity visualization was done using ACT-Artemis Comparison Tool (http://www.sanger.ac.uk/resources/software/act/). Red and blue lines indicate similar regions between PST-130 and PGTG contigs (% identity ≥60). Blue lines indicate inversions. Arrows correspond to putative genes predicted by geneid in PST-130 contigs and annotated genes in PGTG contigs .

Figure 3. Genes identified in the PST-130 contigs that encode proteins involved in the ergosterol biosynthetic pathway.

In red the IDs of the PST-130 manually curated genes. ERG1: squalene epoxidase (HQ698552); ERG2: C-8 sterol isomerase (HQ698553); ERG3: C-5 sterol desaturase (JN033203); ERG4: C-24 sterol reductase (partial clone, not submitted to GenBank); ERG5: C-22 sterol desaturase (JN033204); ERG6: C-24 sterol methyl-transferase (JN033205); ERG7: lanosterol synthase (JN033206); ERG11: lanosterol 14α-demethylase (HQ698554); ERG24: C-14 sterol reductase (HQ698555); ERG25: C-4 sterol methyloxidase (JN033207); ERG26: C-4 sterol decarboxylase (JN033208); ERG27: C-3 sterol ketoreductase (JN033209).