Proteomics Evidence of a Systemic Response to Desiccation in the Resurrection Plant Haberlea rhodopensis

Abstract

Global warming and drought stress are expected to have a negative impact on agricultural productivity. Desiccation-tolerant species, which are able to tolerate the almost complete desiccation of their vegetative tissues, are appropriate models to study extreme drought tolerance and identify novel approaches to improve the resistance of crops to drought stress. In the present study, to better understand what makes resurrection plants extremely tolerant to drought, we performed transmission electron microscopy and integrative large-scale proteomics, including organellar and phosphorylation proteomics, and combined these investigations with previously published transcriptomic and metabolomics data from the resurrection plant Haberlea rhodopensis. The results revealed new evidence about organelle and cell preservation, posttranscriptional and posttranslational regulation, photosynthesis, primary metabolism, autophagy, and cell death in response to desiccation in H. rhodopensis. Different protective intrinsically disordered proteins, such as late embryogenesis abundant (LEA) proteins, thaumatin-like proteins (TLPs), and heat shock proteins (HSPs), were detected. We also found a constitutively abundant dehydrin in H. rhodopensis whose phosphorylation levels increased under stress in the chloroplast fraction. This integrative multi-omics analysis revealed a systemic response to desiccation in H. rhodopensis and certain targets for further genomic and evolutionary studies on DT mechanisms and genetic engineering towards the improvement of drought tolerance in crops.

Keywords: dehydrin; drought stress; proteomics; resurrection plant; subcellular fractionation; systems biology.

Figure 1

Impacts of desiccation on the cellular ultrastructure of H. rhodopensis leaf cells. Transmission electron microscopy leaf micrographs from fresh (A) and dry (B) plants. (A) Peripheral chloroplasts within the cell are shown in the left panel, and the internal organization of the cell can be observed in the right panel. c—chloroplast; g—granal thylakoid; s—starch granule; m—mitochondrion; cw—cell wall. (B) Chloroplast localization in the center of dry cells and fragmented vacuoles (v) is shown in the left panel. The internal chloroplast organization with granal thylakoids and bubble-like loculi (b), as well as mitochondria, can be observed in the middle panel, and the degradation of the chloroplast envelope in parallel to an accumulation of plastoglobules (pg) and features of phagocytosis (ph) in the chloroplast are shown in the right panel. Note the presence of a mitochondrion close to the chloroplast in the desiccated state.

Figure 2

Shotgun proteomics. (A) Principal component analysis biplot showing the distribution of proteins (blue dots) from fresh and dry samples (colored circles) along with the first three principal components. (B) GO annotation of the subcellular localization of the identified proteins. Statistically significant enriched localization of identified proteins is given by asterisks (C) Heat map showing the mean log2 fold change (log2 FC) for the abundance of each identified protein in response to drought stress. Gene annotations are provided for significantly (|log2 FC| > 1) more (red) or less abundant (blue) proteins in dry plants.

Figure 3

Extraction of intact organelles and their subcompartments from H. rhodopensis and gel-based proteomic analyses. (A) Purification of organelles and chloroplast subcompartments from H. rhodopensis. (Left) Percoll gradient allowing the separation of intact (bottom) and broken (top) chloroplasts (chl). (Middle) Percoll-purified chloroplasts fractionated into stromal (S), envelope (E), and thylakoid (T) subfractions using a sucrose gradient. (Right) Purification of the mitochondrial (M) fraction using a Percoll gradient. (B) SDS-PAGE analysis of organelle (upper panel) and suborganelle fractions and immunoblotting for the evaluation of cross-contamination (lower panel). MW—molecular weight marker; C—crude cell extract; Chl—chloroplasts; S—stroma; T—thylakoids; E,—envelopes; M—mitochondria. TOM40—translocator of the outer mitochondrial membrane 40; E21—chloroplast envelope protein 21; RbcL—RuBisCO large subunit; LHC—light-harvesting complex proteins. (C) Representative 2D-DIGE gels of the total protein extract (Total), low-abundance protein-enriched extract (Low abundance), phosphoprotein-enriched extract (Phospho), stromal fraction (Stroma), thylakoid fraction (Thylakoids), and mitochondria fraction (Mitochondria). Numbers represent the spots identified using matrix-assisted laser desorption/ionization time-of-flight/time-of-flight MS.

Figure 4

Immunoblot detection and analysis of dehydrins in H. rhodopensis. (A) Representative results from the 2D electrophoresis and immunoblotting of dehydrins. Proteins from a crude protein extract (mixture of internal standards for fresh and dry plants) were labeled with Cy5 (blue) and resolved using 2D electrophoresis with an isoelectric point (pI)/MW marker labeled with Cy2 (red). Subsequently, immunoblotting signals were detected with Cy3 (green). (B) Results of the 2D electrophoresis and quantitative analysis of proteins from fully hydrated and dry plants. (Upper panel) Representative gels. (Lower panel) 3D “landscape representation” of Dhn1 and Dhn2 from fully hydrated and dry plants with their corresponding relative abundances. (C) Immunoblot analysis of dehydrin expression at selected states of desiccation stress. C—watered plants; D1—moderate desiccation; D2—severe desiccation; D3—dry plants. (Upper panel) Resolved leaf protein extracts were stained with MemCode as a protein loading control. (Middle panel) Using anti-dehydrin serum, one 20 kDa protein band was detected (arrow). (Bottom panel) The mean area of each dehydrin band was normalized to the mean area of the total protein stain. Error bars were calculated from triplicate samples. (D) (Upper panel) Immunoblot detection of dehydrins in crude protein extracts and chloroplasts. C—watered plants; D3—dry plants; Chl—chloroplasts from watered plants; T-C—thylakoids from watered plants; T-D3—thylakoids from dry plants. (Lower panel) Colored numbers in each lane correspond to colors defining immunosignal areas.

Figure 5

Pathway analysis and co-expression changes in the proteome and transcriptome of H. rhodopensis. (A) Scatter plot of averaged log2 transformed fold changes of abundances of RNA contigs (x-axis) and the corresponding proteins (y-axis). Colored bar represents significant expression changes above log2 of 0.5 for contigs and proteins (n.c.—no change; arrow up—upregulation; arrow down—downregulation). (B) RNA contigs and peptides annotated in the CLUE GO network were searched against the KEGG database and visualized together with available metabolomic data to clarify their involvement in cellular metabolism. Squares represent assigned proteins, rectangles represent transcripts, and circles represent metabolites. The colored bar represents changes in log₂ FC between plants in the fresh and dry states. P—phosphorylation event. (C) Pathway signal flow analysis. The pathway was constructed by condensing and enriching a subset of reactions from several primary metabolism pathways of A. thaliana downloaded from KEGG. Unidirectional edges were used for reactions. Nodes are colored from blue to red, corresponding to low to high signals, respectively. The median was regarded as one because it represented the normal state.