Spatial and Temporal Resolution of Global Protein Synthesis during HSV Infection Using Bioorthogonal Precursors and Click Chemistry

Abstract

We used pulse-labeling with the methionine analogue homopropargylglycine (HPG) to investigate spatiotemporal aspects of protein synthesis during herpes simplex virus (HSV) infection. In vivo incorporation of HPG enables subsequent selective coupling of fluorochrome-capture reagents to newly synthesised proteins. We demonstrate that HPG labeling had no effect on cell viability, on accumulation of test early or late viral proteins, or on overall virus yields. HPG pulse-labeling followed by SDS-PAGE analysis confirmed incorporation into newly synthesised proteins, while parallel processing by in situ cycloaddition revealed new insight into spatiotemporal aspects of protein localisation during infection. A striking feature was the rapid accumulation of newly synthesised proteins not only in a general nuclear pattern but additionally in newly forming sub-compartments represented by small discrete foci. These newly synthesised protein domains (NPDs) were similar in size and morphology to PML domains but were more numerous, and whereas PML domains were progressively disrupted, NPDs were progressively induced and persisted. Immediate-early proteins ICP4 and ICP0 were excluded from NPDs, but using an ICP0 mutant defective in PML disruption, we show a clear spatial relationship between NPDs and PML domains with NPDs frequently forming immediately adjacent and co-joining persisting PML domains. Further analysis of location of the chaperone Hsc70 demonstrated that while NPDs formed early in infection without overt Hsc70 recruitment, later in infection Hsc70 showed pronounced recruitment frequently in a coat-like fashion around NPDs. Moreover, while ICP4 and ICP0 were excluded from NPDs, ICP22 showed selective recruitment. Our data indicate that NPDs represent early recruitment of host and viral de novo translated protein to distinct structural entities which are precursors to the previously described VICE domains involved in protein quality control in the nucleus, and reveal new features from which we propose spatially linked platforms of newly synthesised protein processing after nuclear import.

Fig 1. Biochemical analysis of newly synthesised proteins using HPG and click chemistry.

(A) Schematic diagram illustrating comparative structures of methionine and HPG. The scheme indicates the in vivo incorporation of HPG into protein (solid black dots within a protein chain) and then the subsequent in vitro cycloaddition reaction to covalently cross link an azide fluorochrome-coupled capture reagent (coloured star) to HPG. (B) Mock-infected Vero cells were pulse-labeled using 1 mM HPG for 1 hr, lysed and subjected to click reactions using IRDye 800CW Azide Infrared Dye. Proteins were separated by SDS-PAGE and visualised by in-gel fluorescence using a LI-COR Odyssey Infrared Imaging System. Control experiments were carried out either in the absence of HPG (lane 5) or in the presence of 100 μg/ml of CHX (lane 4). Lanes 1–3 represent the total Coomassie blue staining protein profile and lanes 4–6 the in-gel fluorescence profile of the identical gel. (C) Cell viability of uninfected Vero cells (% live cells, in triplicate) was assessed by trypan blue exclusion. Control cultures were subject to either no methionine depletion and incubation in standard methionine-containing medium (Con; white bar) or methionine depletion with subsequent incubation in standard methionine-containing medium (Met; light grey bar); while HPG labelling was performed after methionine depletion with subsequent incubation in HPG -containing medium (30 min pulse). (D) In-gel fluorescence of newly synthesised proteins in total, cytosolic and nuclear fractions. Mock or HSV infected Vero cells (MOI 10) were pulse-labeled at the times indicated for 1 hr, lysed and fractionated prior to click reaction. Equal concentrations of proteins (20 μg, representing a 4-fold increased loading by cell equivalents for the nuclear fraction) were resolved by SDS-PAGE, and proteins visualised using a LI-COR Odyssey Infrared Imaging System scanned into the green channel. (E) The same gel was stained with Coomassie brilliant blue for total protein detection. Representative host cell proteins enriched within the cytoplasmic and nuclear fractions are labeled HC and HN respectively. (F) The same samples after separation by SDS-PAGE where transferred to a nitrocellulose membrane. Total steady-state levels of candidate viral proteins, ICP4, ICP0 and VP5 (red) were simultaneously detected using monoclonal antibodies, and newly synthesised proteins (green) were visualised on the blot.

Fig 2. HPG incorporation has no effect on the accumulation of candidate viral proteins nor on overall virus yield.

(A) Vero cells were pulse-labeled with 0.5 mM HPG for 30 min at 2, 8 or 16 hr p.i. and lysates were collected at the termination of each pulse. Control cultures were incubated as described for Fig 1 (Con and Met). Proteins were separated by SDS-PAGE and transferred to nitrocellulose membranes. Total steady-state levels of early and late viral proteins, ICP8 and VP5 (red) respectively, were simultaneously detected and γ-tubulin (green) was used as loading control. (B) Diagram illustrating the protocol for experiments in (C) and (D). Mock or infected Vero cells were pulse-labeled with 0.5 mM HPG for 30 min at 2, 4, 6, 8, 16 or 20 hr p.i. and chased in normal methionine-containing medium after removal of HPG, harvested at 20.5 hr post infection and analysed for total VP5 and ICP8 accumulation (C) and for total infectious viral yields (D).

Fig 3. Imaging newly synthesised proteins by HPG incorporation and click chemistry.

Uninfected Vero cells were pulse-labeled using 0.5 mM HPG for 30 min, fixed and subjected to click reaction using the Alexa Fluor 488-azide capture agent. Control experiments were performed either in the absence of HPG or using 100 μg/ml of CHX added prior to and during the pulse. Images were recorded as described in materials and methods.

Fig 4. Novel nuclear NPDs revealed in HSV-1 infected cells.

(A) Vero cells were mock-infected or infected (MOI 10) and pulse-labeled for 30 min at the different time points post-infection as indicated. Cells were fixed and processed as described in materials and methods. Large diagonal arrows denote nuclei containing NPDs while small vertical arrows denote the change in cytoplasmic localisation of newly synthesised proteins. (B) Higher magnification images of single cells exemplifying the spatial relationship of NPDs (green) and ICP4 (red) at 2 and 4 hr p.i. For ease of inspection separate channels are shown, with the locations of example NPDs (diagonal arrows) indicated on both channels. In the ICP4 channel, accumulation of foci of ICP4 are indicated by horizontal arrows and NPDs by diagonal arrows.

Fig 5. NPDs colocalise with phase-dense nuclear bodies induced by HSV.

Uninfected or HSV infected Vero cells were either untreated (i.e. standard media; control) or HPG pulse-labeled for 30 min at the times indicated, fixed and analysed by fluorescence (for newly synthesised proteins, green) and ICP4 (red) and by phase microscopy. Diagonal arrowheads indicate the colocalisation of NPDs with HSV-induced phase-dense nuclear domains. Identical phase dense bodies were formed in infected cells, localising to the periphery of replication compartments whether or not the cells were pulse-labeled with HPG.

Fig 6. NPDs do not generally colocalise with viral IE protein ICP0.

Vero cells were infected with HSV-1, pulse-labeled for 30 min with HPG at 1 2 or 4 hr p.i., fixed and analysed for ICP0 (red) and newly synthesised protein (green). Arrows point to the red ICP0 foci on the merged image and are superimposed on the HPG channel to show that the NPDs do not precisely colocalise with ICP0 foci, but rather are frequently juxtaposed.

Fig 7. NPDs associate with PML domains in a spatially defined manner.

Vero cells were mock-infected or infected with w/t HSV-1 (A) or ICP0 RING-finger mutated HSV-1 strain FXE (B), then pulse-labeled with HPG for 30 min at 1 or 2 hr p.i., fixed and processed for newly synthesised proteins (green) and total PML localisation (red). Arrows point to the PML domains and are superimposed on the HPG channel to illustrate the juxtaposition of PML to a population of NPDs for the w/t and mutant viruses as discussed in the text.

Fig 8. NPDs juxtapose to and overlap with PML domains in HSV-1 ICP0[FXE] infected cells.

Vero cells were infected with ICP0 RING-finger mutated HSV-1 strain FXE, pulse-labeled with HPG for 30 min at 4 hr p.i. and analysed as described in Fig 7. Several typical fields are illustrated. The clear spatial relationship between PML domains and NPDs are indicated in the white squares. While many persisting PML domains were associated with NPDs, NPDs were in excess of PML domains. Quantification data of NPD/PML association as discussed in the text are presented in S1D–S1E Fig.

Fig 9. NPDs form adjacent to ICP0/PML domains.

(A) Vero cells were infected and processed as described in Fig 8, in this case for simultaneous localisation of newly synthesised proteins (i, green), PML (ii, red) and ICP0 (iii, blue). The higher magnification insert emphasises the juxtaposition of PML and ICP0 in relation to NPDs. (B) Typical examples of merged channels showing precise colocalisation of mutant ICP0 with PML (purple) and the juxtaposition with NPDs (green).

Fig 10. Spatial relationship between NPDs with SUMO and FK2-ubiquitin accumulation.

Vero cells were infected and processed as described in Fig 8 for simultaneous detection of newly synthesised proteins (green) and total SUMO-modified (red) or ubiquitinated proteins (blue). Diagonal arrows denote example NPDs which have no obvious association with SUMO-containing foci. These latter foci do contain ubiquitinated species (horizontal arrows). For ease of inspection, the lower two fields show HPG versus SUMO alone, and HPG versus SUMO versus ubiquitin.

Fig 11. Hsc70 is recruited to NPDs at later stages of infection.

Vero cells were infected with HSV-1, pulse-labeled with HPG for 30 min at the times indicated, fixed and analysed for Hsc70 (red) and newly synthesised protein (green). NPDs are indicated by diagonal white arrow heads and early in infection show no recruitment of Hsc70. Small vertical arrows indicate formation of Hsc70 aggregates, spatially separated from NPDs but also containing a population of newly synthesised protein. Diagonal arrowhead later in infection show prominent co-localisation between NPDs and Hsc70, frequently with Hsc70 coating the exterior of the NPDs.

Fig 12. Polyubiquitinated species are recruited to NPDs at later stages of infection.

Vero cells were mock-infected or infected with HSV-1, pulse-labeled with HPG for 30 min at the times indicated, fixed and analysed for polyubiquitinated species (FK2 localisation, red) and newly synthesised protein (green). In mock infected cells HPG localised in a generally diffuse pattern with some nuclear la accumulation while polyubiquitinated species were found in a speckled diffuse nuclear pattern with variable numbers of discrete foci. NPD formation in infected cells is indicated by diagonal white arrowheads and early in infection NPDs show no colocalisation with FK2+ve foci. Conversely small vertical arrows indicate FK2+ve foci which show no obvious spatial relationship with NPDs. As described in the text (see also Fig 10) a subset of NPDs localised adjacent to, co-joining FK2+ foci (see inserts of the merged fields). Diagonal arrowheads later in infection show prominent co-localisation between NPDs and FK2+ve species, either as in example cell a, as co-joining asymmetric foci or frequently, as in example cell b, with virtually complete overlap FK2+ve species coating the exterior of the NPDs

Fig 13. ICP22 localises to NPDs and phase-dense nuclear bodies.

Infected Vero cells were either untreated (standard media; control) or HPG pulse-labeled for 30 min at 2 hr p.i. (HPG), fixed and analysed by fluorescence (for newly synthesised proteins (green) and ICP22 (red) and by phase microscopy. Diagonal arrowheads indicate the colocalisation of NPDs with ICP22 as well as phase-dense nuclear domains. The inset shows the precise co-localisation of ICP22 with NPDs. The punctate localisation of ICP22, and its recruitment into phase dense bodies was independent of HPG pulse-labeling and also observed in the control infected cultures in the absence of HPG(Control).

Fig 14. Fig Nuclear accumulation of cellular proteins synthesised prior to infection.

Uninfected Vero cells were pre-labeled with HPG (30 min pulse) followed by an infection with HSV-1 at an MOI of 10 for 4 hr (HSV-1) or mock infection (Mock). Cells were then fixed and stained for Hsc70, followed by click reactions. Cells containing Hsc70 foci were identified and the subnuclear localisation of newly synthesised proteins (green) and Hsc70 (red) are shown with diagonal arrowheads indicating the colocalisation of nuclear NPDs and Hsc70 foci as discussed in the text.

Fig 15. Schematic model of the spatial relationship between NPDs, PML domains and VICE domains and potential processing pathways of newly synthesised proteins.

The dark red shading indicates PML domains in uninfected cells and their functioning with dynamic recruitment and dissociation of target proteins (arrows in and out). The transparent lighter red shading in HSV infected cells indicates their progressive structural and functional disruption. NPDs are formed de novo only after infection (A) or in model (B), the possibility of pre-existing functional NPDs is indicated. Like PML domains, these could represent sites of dynamic protein recruitment and onward transport. As such they would not accumulate bulk newly synthesised proteins, and are thus indicated with transparent, light green shading. Their functional disruption, or overload, in infected cells is indicated by the dark green shading, firstly as smaller domains recruiting selectively ICP22, and only later in infection recruiting additional proteins including components of the host cell protein quality control machinery and in particular Hsc70, the diagnostic marker of VICE domain formation. As discussed in the text, small arrows (NPD,a) indicate impaired forward transport from NPDs and crosses (NPD,b) indicating a more complete block of transport of client proteins after continual recruitment. NPD,c, indicates a more pronounced forward transport after recruitment of certain classes of client proteins. ICP22 (magenta sphere), but not Hsc70, are recruited to NPDs during early stage of infection. As infection progresses, bulk Hsc70 (yellow diamond), and polyubiquitinated species together with ICP22, accumulates at NPDs of larger size.