Frank DiMaio
Associate Professor, Institute for Protein Design, University of Washington
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.
Machine learning structure prediction and cryoEM map interpretation
The machine-learning structure prediction tools AlphaFold and RoseTTAfold have dramatically simplified low-resolution cryoEM map interpretation. Following this, we describe three tools our lab has developed in conjunction with these approaches. First, we describe novel machine-learning methodology for detecting errors in models built against low-resolution cryoEM density. Next, we describe tools for modelling ligands into low-resolution cryoEM density. Finally, we describe our efforts at adding to RoseTTAFold the ability to predict the structure of protein/nucleic-acid complexes.