The neural network is looking for the most dangerous mutations of COVID-19

A new tool can prevent potentially dangerous variants of the virus that will

bind to human cells even more actively. If biologists know in advance about possible mutations, this will make it easier to combat them. 

It is important to be able to assess in advance howamino acid changes can increase the infectivity of the virus. Our structure is a powerful tool for understanding how amino acids influence changes in the SARS-CoV-2 spike protein.

Research text

The authors of the new paper used a two-step computational procedure to create a model to predict changes in amino acids, the building blocks of all proteins in the body.

Changes can occur in the receptor binding (RBD) process of the SARS-CoV-2 spike protein. This will affect the ability of the virus to bind to the ACE2 receptors in human and other animal cells.

During the work, the researchers trained the neural networkon experimental data on the activity of a new type of coronavirus depending on changes in one amino acid. They found that they could predict with about 80% accuracy whether certain amino acid changes would improve or worsen the ability of SARS-CoV-2 to infect humans and animals. 

The model also predicted how changes in SARS-CoV-2 amino acids affected the activity of the alpha, beta, gamma, and delta variants.

Read more:

Archaeologists have found a hidden area in the ancient Mayan city. It turned out to be a special citadel

Forensic scientists have recovered the faces of three Egyptian mummies

It wasn't an explosion: the three main myths about how the universe began