Researchers at Rensselaer Polytechnic Institute (RPI) have found that today's leading artificial intelligence tools for predicting protein structures routinely generate results that are physically and chemically impossible, exposing critical blind spots in how AI is being applied across scientific research.

Ancient proteins may offer clues on how to engineer proteins that can withstand the high temperatures required in industrial applications, according to new research published in the Proceedings of the National Academy of Science. 

Research published this week in Nature Communications makes it possible to predict how volume for a given protein will change between the folded and unfolded state. 

Linking computation with experimentation, researchers at Rensselaer Polytechnic Institute (RPI) have shown that proteins can be engineered to fold more quickly and achieve greater stability by optimizing surface charges.

In 2007, Kinsley French arrived at Rensselaer as a freshman with an interest in science and research. In intervening years, she has racked up a slew of accomplishments.

Anthony Bishop, Chris Newhard, and Divya Shastry have been awarded NSF Graduate Research Fellowships, while five other students have been recognized with honorable mention.

The NSF has awarded a 1.7 million grant to George Makhatadze for research to help understand the speed at which proteins fold and unfold.