The expeditious spread of coronavirus disease 2019 (COVID-19) pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has led to tens of millions of confirmed cases and millions of fatalities. Vaccines are among our last resort to end the raging COVID-19 pandemic. They, however, are prone to near 30,000 mutations uncovered by a Mutation Tracker:  https://users.math.msu.edu/users/weig/SARS-CoV-2_Mutation_Tracker.html. It is imperative to understand how these mutations are impacting SARS-CoV-2 infectivity and COVID-19 vaccines. We develop new algorithms based on artificial intelligence (AI) and algebraic topology to predict the impacts of SARS-CoV-2 mutations on SARS-CoV-2 infectivity and COVID-19 vaccines. Specifically, we consider the mutation-induced binding free energy (BFE) changes for the complexes of SARS-CoV-2 spike (S) protein and the host receptor angiotensin-converting enzyme 2 (ACE2) or host antibodies. We build a library of antibody structures and analyze their 2D and 3D characteristics. Moreover, we construct multitask, deep-learning predictors to reconcile different training datasets. By integrating genetics, biophysics, deep learning, and algebraic topology, we deduce that some mutations may weaken the binding of S protein and antibodies, and potentially disrupt the efficacy and reliability of antibody therapies and vaccines, while other mutations may make COVID-19 more infectious. We provide a strategy to prioritize the selection of mutations for designing vaccines or antibody cocktails.

Impact of mutations to COVID-19 vaccines and infectivity

ACS Spring Meeting 2021

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.