Detection of Beta-Barrels from Medium Resolution Cryo-electron Microscopy Density Maps

Abstract

Cryo-electron microscopy is becoming one of the most popular techniques used to determine protein structures. At medium resolutions, secondary structures can be seen from within cryo-electron microscopy density maps. The automatic isolation and detection of these secondary structures directly from density maps would be helpful to many, such as drug researchers to enable faster and better drug design for targeted proteins. One such secondary structure is the beta-barrel, a beta-sheet based secondary structure that is commonly found as in cell membranes and transport proteins. This thesis proposes a novel method combining convolutional neural networks, genetic algorithms, and ray casting to perform automatic detection for beta-barrels from within medium resolution cryo-electron density maps. This approach was tested using both experimentally produced and simulated cryo-electron microscopy density maps. This method achieved a sensitivity of 0.95 and specificity of 0.90 on simulated maps. However, this method was only able to obtain a sensitivity of 0.72 and specificity of 0.79 on experimentally produced density maps.