Building and Validating Biomolecular Structure Models Using Deep Learning

Knowing 3D structure of proteins, RNA/DNA, is fundamental to understanding how the molecules carry out the function. The 3D structure is also essential for rational drug design that target proteins and RNAs. Our lab has been developing various 3D structure modeling methods using deep learning. In this seminar, I discuss recent highlights of our works.
One of our recent main projects is biomolecular structure modeling from cryo-electron microscopy (cryo-EM) data. cryo-EM has become one of the main experimental methods for determining biomolecular structures including proteins and nucleic acids. Molecular structure modeling from cryo-EM can be challenging when the resolution of maps is not high enough to specify atom positions. For maps at medium resolution, deep learning can detect characteristic local density features of amino acids and secondary structures, which can be used to guide structure modeling. Local density features can be also used for validating existing protein structure models in PDB.
Next, I will discuss our projects on RNA structure prediction and peptide docking prediction that uses an elaborated deep neural network architecture, which is inspired by Alphafold2, a recent successful protein structure prediction method.

Post Talk Link:  Click Here 

Passcode: x*9GiBG0