Model analyzes how viruses escape the immune system

MIT researchers have devised a way to computationally model viral escape, using models that were originally developed to model language. The model can predict which sections of viral surface proteins, including those of influenza, HIV, and SARS-CoV-2, are more likely to mutate in a way that allows the virus to evade the human immune system. It can also identify sections that are less likely to mutate, making them good targets for new vaccines.