Inherent structural disorder and dimerisation of murine norovirus NS1-2 protein

Abstract

Human noroviruses are highly infectious viruses that cause the majority of acute, non-bacterial epidemic gastroenteritis cases worldwide. The first open reading frame of the norovirus RNA genome encodes for a polyprotein that is cleaved by the viral protease into six non-structural proteins. The first non-structural protein, NS1-2, lacks any significant sequence similarity to other viral or cellular proteins and limited information is available about the function and biophysical characteristics of this protein. Bioinformatic analyses identified an inherently disordered region (residues 1-142) in the highly divergent N-terminal region of the norovirus NS1-2 protein. Expression and purification of the NS1-2 protein of Murine norovirus confirmed these predictions by identifying several features typical of an inherently disordered protein. These were a biased amino acid composition with enrichment in the disorder promoting residues serine and proline, a lack of predicted secondary structure, a hydrophilic nature, an aberrant electrophoretic migration, an increased Stokes radius similar to that predicted for a protein from the pre-molten globule family, a high sensitivity to thermolysin proteolysis and a circular dichroism spectrum typical of an inherently disordered protein. The purification of the NS1-2 protein also identified the presence of an NS1-2 dimer in Escherichia coli and transfected HEK293T cells. Inherent disorder provides significant advantages including structural flexibility and the ability to bind to numerous targets allowing a single protein to have multiple functions. These advantages combined with the potential functional advantages of multimerisation suggest a multi-functional role for the NS1-2 protein.

Figure 1. Secondary structure and disorder predictions of the MNV NS1-2 protein.

(A) MeDor output showing five different disorder predictors with regions of disorder indicated by bi-directional arrows (IUPred – red, GlobPlot2 – black, DisEMBL – green, FoldIndex – brown, RONN – purple). CASP¹¹⁹, caspase 3 cleavage site. (B) PONDR® graph showing predicted disordered and ordered segments. The strength of the prediction is indicated by the PONDR® score on the y-axis. Regions above 0.5 are considered disordered and are indicated by a solid black line through the central x-axis, with the corresponding average strength shown in the attached box. (C) PSIPRED secondary structure prediction. Pink barrels indicate helices, yellow arrows indicate strands, and the strength of the prediction is shown as the blue graph above the structural prediction (D) Kyte-Doolittle hydropathy plot. Hydrophobic regions are indicated above the x-axis. TM, putative transmembrane domain (residues 266–318) predicted by PSIPRED.

Figure 2. FoldIndex disorder predictions of the NS1-2 protein from norovirus genogroups.

GI.1 (Norwalk), GI.2 (Southampton), GII.1 (Hawaii), GII.4 (Lordsdale), GIII (Jena) and GV (MNV-1). Ordered regions are indicated in green above 0, while disordered regions are indicated in red below 0.

Figure 3. Multiple sequence alignment of the NS1-2 protein representative of different norovirus genogroups.

GI.1 (Norwalk), GI.2 (Southampton), GII.1 (Hawaii), GII.4 (Lordsdale), GIII (Jena) and GV (MNV-1). Completely conserved residues are shown in white on a red background. Identical residues with >50% conservation are shaded in yellow. Similar residues with >50% conservation are shaded in grey. Residue numbers correspond to the MNV-1 NS1-2 sequence.

Figure 4. Amino acid composition analysis of the NS1-2 protein.

Composition profiler analyses of NS1-2 regions showing the deviations in amino acid composition from the SWISS-PROT51 database. (A) N-terminal caspase cleavage product, (B) Middle ordered region. The relative levels of disorder promoting residues are shown as red bars, order-promoting residues are shown as blue bars and disorder neutral residues are shown as grey bars. Residues with significant enrichment (P<0.05) compared to the SWISS-PROT51 database are indicated with *.

Figure 5. Charge-hydropathy plot of the NS1-2 protein regions and other MNV-1 proteins.

The mean net charge (R) is plotted against the mean hydrophobicity (H). The boundary line is described by the equation . Proteins (or regions of proteins) shown to the left of the boundary line are predicted to be intrinsically disordered. Proteins to the right of the boundary line are predicted to be structured. NS1-2 regions (•); N-terminal caspase cleavage product (casp), truncated NS1-2 protein (trunc), full-length NS1-2 (full), middle ordered region (ord). The other MNV-1 non-structural proteins (∇) are numbered 2–7. Structural proteins are indicated by □.

Figure 6. Protein design and expression of the MNV-1 NS1-2 protein in Escherichia coli.

(A) Schematic diagram of the MNV genome and the NS1-2 protein. TM, predicted transmembrane domain. DIS, disordered region. The expressed regions (truncated, caspase cleavage product and middle ordered region) are indicated by amino acid number (a.a.) and the molecular masses (in kDa) are indicated below or beside each protein. (B) SDS-PAGE analysis of the expression and purification of the NS1-2trunc region. The CBD-Intein-NS1-2trunc fusion protein is visible at three hours post-induction and in the soluble fraction. The NS1-2trunc protein is shown in the elution fraction collected after cleavage of the intein. Marker, NEB Broad Range. 0, Pre-induction. 3, three hours post-induction. S, soluble. F, flow through from the chitin bead column. E, elution. The vertical line indicates that two sections of the same gel have been combined in this figure. (C) SDS-PAGE analysis of the eluted fraction collected from the chitin bead columns for NS1-2casp. (D) SDS-PAGE analysis of the fraction collected after stripping the chitin column of NS1-2ord. (E) SDS PAGE analysis showing thermolysin digestion of each of the NS1-2 protein fragments. Lysozyme was used as globular protein control, showing resistance to proteolysis even at 24 hours. 0, sample collected before adding thermolysin. 0.5, 30 minutes digest. 1, one-hour digest. 24, 24-hour digest. (F) Western blot analysis of MNV-infected RAW264.7 cells using a 1 in 2500 dilution of the rabbit polyclonal NS1-2 antibody stock. The antibody detects the NS1-2 full-length protein (actual size of 38.3 kDa, observed at ∼44 kDa) and caspase 3 cleavage products of 24.7 kDa (observed at ∼30 kDa) and 13.6 kDa (observed at ∼18 kDa). Marker, Invitrogen BenchMark™ Pre-stained Protein Ladder. 12, RAW264.7 cells harvested at 12 hours post-infection with MNV-1. Un, RAW264.7 cells only (negative control).

Figure 7. Dimerisation of the NS1-2 protein.

(A) Chromatogram showing the two peaks (1 and 2) obtained during purification of the NS1-2trunc protein through a Superose12 column. (B) Bacterial two-hybrid analyses show a positive interaction between both full-length NS1-2 and truncated NS1-2 clones. full, pBT-NS1-2full + pTRG-NS1-2full. trunc, pBT-NS1-2trunc + pTRG-NS1-2trunc. +ve, positive control, pBT-LGF2 + pTRG-Gal11^P. 1, negative control for medium quality (pTRG- Gal11^P + pBT). 2, pBT-NS1-2full + pTRG. 3, pTRG-NS1-2full + pBT. 4, pBT-NS1-2trunc + pTRG. 5, pTRG-NS1-2trunc + pBT. (C) 10% SDS-PAGE (left) and western blot (right) of GA cross-linking of NS1-2trunc from peak 1 of the size exclusion column. (D) 10% SDS-PAGE (left) and western blot (right) of GA cross-linking of NS1-2trunc from peak 2 of the size exclusion column. The NS1-2 monoclonal antibody was used for western blot analysis in Fig. C and D. (E) Western blot analysis of HEK293T cells harvested 24 hours post-transfection with the NS1-2 protein constructs. Arrows indicate the NS1-2 dimer band for each construct. The NS1-2 polyclonal antibody was used at a 1 in 5000 dilution for the detection by western blot. Legend for Fig. C, D and E: Markers, NEB Broad Range (SDS-PAGE gels), Invitrogen Novex® Sharp Protein Standard (western blots). Un, untreated protein. 1, cross-linked with 0.005% GA. 2, cross-linked with 0.01% GA. DSS, cross-linked with 5 mM DSS.

Figure 8. Analysis of the NS1-2 protein by far-UV circular dichroism.

(A) Far-UV CD spectra of NS1-2trunc and NS1-2casp in 20 mM citrate-phosphate pH 6.1, 150 mM NaCl. The CD spectra are the average of five independent acquisitions. (B) Double wavelength plot, [θ]₂₂₂ versus [θ]₂₀₀, of a set of ‘natively unfolded’ proteins (from [32]) and the NS1-2trunc and NS1-2casp proteins.