Scientists using AI to see how COVID-19 might evolve to prepare for future variants

WELLINGTON, Sept. 20 (Xinhua) -- A team of international researchers has developed a high-tech method to explore the possibilities of how the COVID-19 virus could evolve to prepare for future coronavirus variants using Artificial Intelligence (AI).

University of Waikato researcher William Kelton has been working with international partners from Switzerland's ETH Zurich and the University of Geneva, among others, to take proteins from the coronavirus surface (not the live virus) into the lab and creat lots of artificial mutations to the protein, screening those mutations to discover which ones allow binding to cells.

In a paper published in the journal Cell on Tuesday, the team added antibodies to the process later on to mimic the selection pressures a virus might undergo in the human body. This protein engineering information was used to train machine learning models to predict how well a new variant might bind to cells and escape antibody binding from tens of billions of possibilities.

Kelton said this model is very accurate at predicting potential pathways by which new variants might evolve and may provide a pathway to fighting future variants.

"If we can get ahead of COVID, we can make drugs and antibodies before these variants emerge and design solutions to combat them. We can also test to see how existing drugs work against panels of potential variants," Kelton said.