Modified deep-learning algorithms unveil features of shape-shifting proteins
Oak Ridge National LaboratoryTo function properly, proteins must morph into specific 3D shapes through a biophysical phenomenon called protein folding. Researchers at ORNL are using various deep-learning techniques to study the intermediate protein stages between the initial unfolded state and the final folded state, which are notoriously difficult to characterize. These methods could also help identify factors that cause proteins to “misfold” into dysfunctional shapes, a phenomenon often attributed as a leading factor in the development of diseases including Alzheimer’s, cardiovascular disorders, and diabetes.