Researchers have leveraged machine learning to create proteins that toggle between two different shapes in response to biological triggers, overcoming a limiting challenge in computational protein design and broadening the potential functionality of designed proteins. Study co-author Banumathi Sankaran, a research scientist in the Molecular Biophysics and Bioimaging Division, used the Advanced Light Source (ALS) beamlines in the Berkeley Center for Structural Biology (BCSB) to validate results with X-ray crystallography data.