08/03/2023
Excited to share our team and collaborators’ latest research which delves into crucial host-pathogen interactions and viral evolution. Using an AI enable protein-protein interaction affinity prediction system called UnBind, we effectively predicted the impact of SARS-CoV-2 on infectivity, antibody escape and viral evolution. This in silico approach shows promise as an early warning system for emerging coronavirus variants and aids research on protein interactions.
Based on a newly developed deep-learning model for predicting the binding affinities of protein–protein interactions, the effects of SARS-CoV-2 spike protein variants on binding to the ACE2 receptor and neutralizing antibodies were analyzed and used to predict immune escape and viral evolution.