Professor Samy Missoum is leading the development of a surrogate aerodynamic database, which aims to help researchers choose which experiments and computations are the most efficient and cost effective to run.

With the help of an advanced machine learning technique, researchers from Brown University suggest strategies for improving the performance of epidemiological models used to predict the course of pandemics.

Using artificial intelligence and deep learning, researchers have developed a neural network that "hallucinates" the structures of new protein molecules. The scientists made up completely random protein sequences and introduced mutations into them until the neural network predicted they would fold into stable structures. The software was not guided toward a particular outcome; the proteins were just what the computer dreams up. Next step: using deep learning to try to design proteins with particular functions, such as enzymes or drugs.

For the first time, computer scientists and mathematicians have used artificial intelligence to help prove or suggest new mathematical theorems in the complex fields of knot theory and representation theory.

Researchers at Intermountain Healthcare in Salt Lake City have received a $4.6 million grant from the National Institutes of Health to study the best ways to implement recognized standards of care to determine when ICU patients on mechanical ventilators, including those being treated for severe COVID illness, should be taken off the ventilators to resume breathing on their own.