Professor of Biological Sciences, Computer Science, Purdue University
Date and time: September 7th, 2022
Wednesday, at 8am PT / 11am ET / 4pm BST / 5pm CEST / 11pm China
For the zoom and gather.town links, please join the One World Cryo-EM mailing list.
Validating and Building Protein Structure Models for cryo-EM Maps Using Deep Learning
Cryo-electron microscopy (cryo-EM) has become one of the main experimental methods for determining protein structures. Protein structure modeling from cryo-EM is in general more difficult than X-ray crystallography since the resolution of maps is often not high enough to specify atom positions. We have been developing a series of computational methods for modeling protein structures from cryo-EM maps. For maps at medium resolution, deep learning can provide useful structure information for structure validation and modeling. Particularly, we have recently developed a protein model quality assessment score, DAQ, which compares local density patterns captured by deep learning with amino acid positions in a model, and detect potential errors in the model. In a large-scale analysis of protein models from cryo-EM, we found that not a small number of models may have some errors. All the tools we developed are available at https://kiharalab.org/emsuites/.