Communications of the ACM
ML Model Finds SARS-COV-2 Growing More Infectious
A novel machine-learning model developed at Michigan State University suggests SAR-CoV-2 has become more infectious due to genome mutations.
Credit: Centers for Disease Control
Researchers at Michigan State University have developed a novel machine-learning model that suggests SAR-CoV-2 has become more infectious due to genome mutations.
The model analyzed SARS-CoV-2 genotyping from more than 20,000 viral genome samples and determined that five of the six known virus subtypes are now more infectious.
Researchers focused their analysis on mutations to the spike protein, which causes infection when it interacts with a human host cell receptor.
The advanced neural network analyzed more than 8,000 protein interaction records to gauge the impact of the current known mutations on the binding affinity—the binding interaction between the spike protein and host receptor during the initial stage of infection—of the spike protein.
The researchers found that viral infectivity increases if the binding affinity strengthens. Further, the model predicts that multiple residues on the receptor-binding motif have high chances to mutate into more infectious Covid-19 strains.
From MSU Today
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found