A secreted WY-domain-containing protein present in European isolates of the oomycete Plasmopara viticola induces cell death in grapevine and tobacco species

Abstract

Plasmopara viticola is a biotrophic oomycete pathogen causing grapevine downy mildew. We characterized the repertoire of P. viticola effector proteins which may be translocated into plants to support the disease. We found several secreted proteins that contain canonical dEER motifs and conserved WY-domains but lack the characteristic RXLR motif reported previously from oomycete effectors. We cloned four candidates and showed that one of them, Pv33, induces plant cell death in grapevine and Nicotiana species. This activity is dependent on the nuclear localization of the protein. Sequence similar effectors were present in seven European, but in none of the tested American isolates. Together our work contributes a new type of conserved P. viticola effector candidates.

Fig 1. Identification of WY-domain proteins from P. viticola.

(A) Venn-diagram showing the distribution of candidate RXLR effectors based on the method leading to their identification and their structural homology to known RXLR effectors. (B) Alignment of the N-terminal protein sequences of candidate effector genes showing structural homology to RXLR effectors but lacking the eponymous motif. Signal peptide (SP) and dEER motifs are highlighted.

Fig 2. Characterization of P. viticola WY-domain proteins.

(A) Phylogenetic tree obtained with the WY-domain proteins from P. viticola. Branch support values show 100 bootstraps. The three clades referred to in the text are highlighted in pink (I), blue (II) and green (III). Genes selected for further analysis are indicated (B) Expression level of WY-domain proteins in germinated spores (Sp) and infected tissues (hpi) at 48- and 72-hours post-infection. White colour shows absence of expression. Detailed expression data is shown in S3 Dataset.

Fig 3. Pv33 induces cell death in V. vinifera cv Syrah.

Agrobacterium-mediated transient expression of Pv18, Pv31, Pv33, Pv82 without their signal peptide (Δsp) and full-length Pv33, including its signal peptide (FL) in V. vinifera Syrah leaf disks. (A) Macroscopic results. Pictures were taken 6 days after agroinfiltration and are representative of the phenotype of each effector. (B) Semi-quantitative RT-PCR showing VvHSR and effector expression. Actin expression is used as reference. Agrobacterium-mediated transient expression of GFP was used to confirm that the induction of VvHSR expression is specific to Pv33. Each effector-expressing Agrobacterium strain was infiltrated into 4 leaf discs and the experiment was repeated twice. The macroscopic effect of 33Δsp was not visible in all infiltrated discs but could be observed in both repetitions. RNA extractions for RT-PCRs were done by pooling the 4 disks for each effector.

Fig 4. Expression of Pv33 in P. viticola developmental stages.

Semi-quantitative RT-PCR of Pv33 expression in sporangia (Sp), germinated spores (Sg) and infected tissues at 0, 24, 48 and 72 hours after inoculation (hpi). Expression of V. vinifera Actin (VvActin) is shown as loading of samples corresponding to infected tissues. Expression of P. viticola Actin (PvActin) reflects pathogen biomass and shows progression of infection.

Fig 5. Pv33 induces cell death in Nicotiana spp.

Agrobacterium-mediated transient expression of Pv18, Pv31, Pv33, Pv82 without their signal peptide (Δsp) (A) and full-length Pv33, including its signal peptide (FL) (B) in N. benthamiana, N. tabacum and N. occidentalis leaves. All pictures were taken 5 days after agroinfiltration. (C) Constructs used in experiments shown in D and E. PR1SP: signal peptide of PR1. Pv33SP: signal peptide of Pv33. (D and E) Confocal images following infiltration of N. benthamiana leaves with the constructs described in C, without (D) and with (E) BFA treatment. Red arrows show nucleus. Bars show 10 Δm. In A and B, for each species, 6 leaves were infiltrated with all the effectors. Experiments were repeated twice with the same results.

Fig 6. Pv33-triggered cell death requires SGT1.

(A) Representative pictures of cell death assays on TRV-silenced leaves. Pictures were taken 5 days after agroinfiltreation with A. tumefaciens cells carrying a construct for constitutive expression of uidA (GUS), 33 full length (33FL) or without signal peptide (33Δsp), or a 1:1 combination of Xanthomonas effector AvrBs3 and the resistance gene Bs4, used as positive control. The experiment was performed in quadruplicate (N = 32). (B) Validation of virus-induced gene silencing by quantitative RT-PCR. Accumulation of transcripts from N. benthamiana genes EDS1 and SGT1 in 6 individual plants, 3 weeks after agroinfiltration with A. tumefaciens cells carrying a construct for TRV-induced gene silencing of uidA, EDS1 and SGT1. Data are shown relative to L23 and F-BOX reference genes. Circles represent ratios, lines represent means. Statistical significance was assessed using one-way ANOVA and Tukey’s HSD test (P < 0.05).

Fig 7. Pv33 localizes to the nucleus.

(A) Confocal microscopy images following infiltration of N. benthamiana leaves with Agrobacterium carrying GFP translational fusions of Pv33 either lacking (33Δsp-GFP) or including (33FL-GFP) the signal peptide. GFP alone was used as control. (B) Low magnification epifluorescence microscopy images of 33ΔSP-GFP and 33FL-GFP infiltrations. (C) Epifluorescence microscopy images following infiltration of V. vinifera cv Syrah leaf discs with Agrobacterium carrying 33ΔSP-GFP and 33FL-GFP. Pictures were taken 2 days after agroinfiltration. Experiments were repeated 5 times for N. benthamiana and twice for V. vinifera, with the same results. Bar shows 25 µm.

Fig 8. Pv33-triggered cell death depends on its nuclear localisation.

(A) Agrobacterium-mediated transient expression of N. benthamiana leaves with 33Δsp-GFP fused to either an active (33Δsp-GFP-NES) or inactive (33Δsp-GFP-nes) nuclear exclusion sequence. Pictures were taken 5 days after agroinfiltration under white and blue light. (B) Subcellular localisation of 33Δsp-GFP-NES and 33Δsp-GFP-nes as observed by confocal microscopy 2 days after agroinfiltration. (C) Western blot with anti-GFP of the different GFP-tagged Pv33 versions. GFP is used as positive control. Ponceau red staining of the nitrocellulose membrane is shown as loading marker. Results shown in A and B are representative of 3 independent experiments, each consisting of at least 6 N. benthamiana leaves infiltrated as shown in A.