Transcriptomic analysis of sweet potato under dehydration stress identifies candidate genes for drought tolerance

Abstract

Sweet potato (Ipomoea batatas [L.] Lam.) is an important subsistence crop in Sub-Saharan Africa, yet as for many crops, yield can be severely impacted by drought stress. Understanding the genetic mechanisms that control drought tolerance can facilitate the development of drought-tolerant sweet potato cultivars. Here, we report an expression profiling study using the US-bred cultivar, Beauregard, and a Ugandan landrace, Tanzania, treated with polyethylene glycol (PEG) to simulate drought and sampled at 24 and 48 hr after stress. At each time-point, between 4,000 to 6,000 genes in leaf tissue were differentially expressed in each cultivar. Approximately half of these differentially expressed genes were common between the two cultivars and were enriched for Gene Ontology terms associated with drought response. Three hundred orthologs of drought tolerance genes reported in model species were identified in the Ipomoea trifida reference genome, of which 122 were differentially expressed under at least one experimental condition, constituting a list of drought tolerance candidate genes. A subset of genes was differentially regulated between Beauregard and Tanzania, representing genotype-specific responses to drought stress. The data analyzed and reported here provide a resource for geneticists and breeders toward identifying and utilizing drought tolerance genes in sweet potato.

Keywords: Ipomoea batatas; RNA‐Seq; drought; expression; polyethylene glycol; sweet potato.

Figure 1

Phenotypic and genetic response of Beauregard and Tanzania sweetpotato varieties to the application of polyethylene glycol (PEG). (a) Plantlets incubated in untreated media or 25% PEG media at 24 and 48 hr after stress (HAS). (b) Principal component analysis of individual biological replicates using variance stabilizing transformed read counts. Each point represents a biological replicate

Figure 2

Conserved expression responses to polyethylene glycol in Beauregard and Tanzania. (a) Log2 fold change (LFC) of gene expression abundances in Beauregard and Tanzania at 24 and 48 hr after stress (HAS). “DE B” and “DE T” indicate genes differentially expressed in only Beauregard or Tanzania, respectively. (b) The most significantly enriched biological process gene ontology terms among genes differentially expressed in both Beauregard and Tanzania at 24 and 48 HAS

Figure 3

Time‐point specific differentially expressed genes (a) Differentially expressed genes at 24 and 48 hr after stress (HAS) in Beauregard and Tanzania. Genes labeled “up” or “down” were significantly upregulated or downregulated, respectively. (b) Overlap between genes significantly downregulated or upregulated in each variety (B: Beauregard, T: Tanzania) and at each time‐point. Red rectangles indicate genes tested for GO term enrichment and dashed outlines indicate weak or insignificant enrichment. (c) The most significant GO terms for genes downregulated in both Beauregard and Tanzania at 24 HAS but not 48 HAS (solid red rectangle in panel b)

Figure 4

Ipomoea trifida orthologs of drought tolerance candidate genes identified in Arabidopsis, rice, and tomato. (a) Species representation of orthogroups containing DroughtDB genes. (b) Log2 fold changes (left; polyethylene glycol/control) and differential expression state (right; grey: not differentially expressed; red: differentially expressed). The arrow indicates itf03g07310 (TAS14). (c) Counts of I. trifida genes in orthogroups containing drought tolerance candidate genes significantly downregulated in all four variety‐time point combinations

Figure 5

Genes differentially regulated between Beauregard and Tanzania in response to polyethylene glycol (PEG). (a) Representative K‐means clusters for mean‐centered (per gene) log2 fold changes (PEG/control) for Beauregard and Tanzania at 24 and 48 hr after stress. The number of genes in each cluster is indicated in parentheses. (b) Top three most significant biological processes gene ontology terms for each K‐means cluster