Exploring the ability of the MD+FoldX method to predict SARS-CoV-2 antibody escape mutations using large-scale data

Area of Science:

• Immunology
• Computational Biology
• Virology

Background:

• Antibody escape mutations challenge vaccine and therapy effectiveness.
• Predictive computational methods require large-scale experimental data for validation.

Purpose of the Study:

• Evaluate MD+FoldX's ability to predict SARS-CoV-2 receptor binding domain escape mutations.
• Assess the impact of tailored affinity cutoffs on prediction precision.

Main Methods:

• Leveraged deep mutational scanning dataset for SARS-CoV-2 receptor binding domain.
• Employed MD+FoldX molecular modeling to predict binding affinities.
• Compared predicted escape mutations with experimental data.

Main Results:

• Positive correlation observed between predicted binding affinity and experimental escape fractions.
• Tailored affinity cutoffs for four antibody classes improved precision over a general approach.
• 70% of systems exceeded 50% precision, identifying key mutations in variants of concern/interest.

Conclusions:

• MD+FoldX shows potential for predicting antibody escape mutations.
• Class-specific affinity cutoffs enhance predictive accuracy.
• Need for faster, more accurate binding affinity prediction methods is highlighted.