Prefusion spike protein stabilization through computational mutagenesis

Abstract

A novel severe acute respiratory syndrome (SARS)-like coronavirus (SARS-CoV-2) has emerged as a human pathogen, causing global pandemic and resulting in over 400 000 deaths worldwide. The surface spike protein of SARS-CoV-2 mediates the process of coronavirus entry into human cells by binding angiotensin-converting enzyme 2 (ACE2). Due to the critical role in viral-host interaction and the exposure of spike protein, it has been a focus of most vaccines' developments. However, the structural and biochemical studies of the spike protein are challenging because it is thermodynamically metastable. Here, we develop a new pipeline that automatically identifies mutants that thermodynamically stabilize the spike protein. Our pipeline integrates bioinformatics analysis of conserved residues, motion dynamics from molecular dynamics simulations, and other structural analysis to identify residues that significantly contribute to the thermodynamic stability of the spike protein. We then utilize our previously developed protein design tool, Eris, to predict thermodynamically stabilizing mutations in proteins. We validate the ability of our pipeline to identify protein stabilization mutants through known prefusion spike protein mutants. We finally utilize the pipeline to identify new prefusion spike protein stabilization mutants.

Keywords: computational mutagenesis; coronavirus; protein stabilization; spike protein.

FIGURE 1

The pipeline of the stabilization of spike protein. The pipeline is roughly divided into two stages. In the first stage, users designate the protein of interest through either the 3D structure of the PDB ID. The pipeline will then analyze the conversation score, solvent accessible surface area (SASA), and root mean square fluctuation (RMSF) of each residue in the protein. In the second stage, users designate the mutation sites for stabilization mutagenesis. The pipeline then utilizes Eris to identify the stabilizing mutantions. Finally, the stabilization capability of these mutants is validated by discrete molecular dynamics (DMD) simulations [Color figure can be viewed at wileyonlinelibrary.com]

FIGURE 2

Remodeling results of the spike protein structure. A, Comparison of the crystal structure and the remodeled structure of the spike protein. B, The surface representation of the spike protein. The extra blue loops are the completed loops. C, The Discrete Optimized Protein ENergy (DOPE) score of each residue in the structure remodeled by MODELER. D, The remodeled structure of the spike protein with three receptor‐binding domain (RBD) in up conformations. E, The remodeled structure of the spike protein with three RBDs in down conformations [Color figure can be viewed at wileyonlinelibrary.com]

FIGURE 3

Evaluation of the stabilization mutation identification ability of the pipeline. A, The ΔΔG predicted by Eris vs experimental ΔΔG for all mutations in the dataset. B, The solvent accessible surface area (SASA) vs experimental ΔΔG for all mutations in the dataset. C, The root mean square fluctuation (RMSF) vs experimental ΔΔG for all mutations in the dataset. D, The conservation score vs experimental ΔΔG for all mutations in the dataset. E, The receiver operator characteristic (ROC) curve of Eris ΔΔG, SASA, RMSF, conservation score, and the combination of the four metrics, respectively [Color figure can be viewed at wileyonlinelibrary.com]

FIGURE 4

Conservation score, solvent accessible surface area (SASA), and root mean square fluctuation (RMSF) of the spike protein. A, The conservation score of residues in the spike protein. Conservation score of 9 means highly conserved, while conservation score of 1 means a highly variable position. B, SASA of residues in the spike protein. C, The RMSF of residues in the spike protein. D, The 3D structures of the spike protein colored by the conservation score. The red/blue colors indicate highly conserved/highly variable residues. E, The 3D structure of the spike protein colored SASA. The red/blue colors indicate exposed/buried residues. F, The 3D structure of the spike protein colored by RMSF. Red means flexible and blue means frozen [Color figure can be viewed at wileyonlinelibrary.com]

FIGURE 5

Stabilization results of the spike protein. A, The free energy change (ΔΔG) of all mutations on the selected residues in N‐terminal domain (NTD) of the spike protein. B, The correlation between free energy change and the conservation score for all mutants of the four domains. The blue dots refer to the average free energy change of all 19 mutants of each residue. The bottom end of each gray line refers to the minimum free energy change of all 19 mutants of the residue. C, The correlation between free energy change and solvent accessible surface area (SASA) for all mutants of residues in the four domains. D, The correlation between free energy change and root mean square fluctuation (RMSF) for all mutants of residues in the four domains [Color figure can be viewed at wileyonlinelibrary.com]