Researchers Use Ai To Generate Novel Proteins That Meet Structural Design Targets

Researchers from MIT, the MIT-IBM Watson AI Lab, and Tufts University have developed machine-learning algorithms that can generate proteins with specific structural features. These proteins could be used to make materials that have certain mechanical properties, such as stiffness or elasticity, and could potentially replace materials made from petroleum or ceramics. The models learn biochemical relationships that control how proteins form, and can produce new proteins that could enable unique applications. The models can generate millions of proteins in a few days, quickly giving scientists a portfolio of new ideas to explore.