Extraction of protein dynamics information from cryo-EM maps using deep learning

Elucidation of both the three-dimensional structure and dynamics a protein is essential to understand its function. Technical breakthroughs in single-particle analysis based on cryo-electron microscopy (cryo-EM) have enabled structures numerous proteins be solved at atomic or near-atomic resolution. However, targets using cryo-EM often challenging because their large sizes complex structural assemblies. Here, we describe DEFMap, deep learning-based approach directly extract associated with fluctuations that are hidden density maps. Using only data, DEFMap provides correlate well data obtained from molecular simulations experimental approaches. Furthermore, successfully detects changes recognition. This strategy combines learning, simulations, may reveal new multidisciplinary for science. Cryo-electron can used determine atomic-scale It observe A deep-learning called extracts