WELLINGTON: A team of international researchers has developed a hightech method to explore the possibilities of how the coronavirus could evolve to prepare for future variants using artificial intelligence (AI).

William Kelton, a researcher at the University of Waikato in the city of Hamilton in northern New Zealand, 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 into the laboratory and create artificial mutations from them. They would screen the mutations to learn which ones allow binding to cells.

A paper published in the journal

Cell on Tuesday said 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 was very accurate at predicting potential pathways by which new variants might evolve and may provide a pathway to fighting them.

“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,” he added.