Deep Learning for Resolution Validation of Three Dimensional Cryo-Electron Microscopy Density Maps

Abstract

Cryo-electron microscopy (cryo-EM) is becoming the imaging method of choice for determining protein structures. Many atomic structures have been resolved based on an exponentially growing number of published three-dimensional (3D) high resolution cryo-EM density maps. The resolution value claimed for the reconstructed 3D density map has been the topic of scientific debate for many years. The Fourier Shell Correlation (FSC) is the currently accepted cryo-EM resolution measure, but it can be subjective and has its own limitations. The FSC indicates the quality of the experimental maps but no the amount of geometric and volumetric feature details present in the 3D map. In this study, we propose supervised deep learning methods to extract representative 3D features at high, medium and low resolutions from simulated protein density maps and build classification models that objectively validate resolutions of experimental 3D cryo-EM maps. Specifically, we build classification models based on dense artificial neural network (DNN) and 3D convolutional neural network (3D CNN) architectures. The trained models can classify a given 3D cryo-EM density map into one of three resolution levels: high, medium, low. The DNN model achieved 92.73% accuracy and the 3D CNN model achieved 99.75% accuracy on simulated test maps. Applying the DNN and 3D CNN models to thirty experimental cryo-EM maps achieved an agreement of 60.0% and 56.7%, respectively, with the author published resolution value of the density maps. The results suggest that deep learning can be utilized to potentially improve the resolution validation process of experimental cryo-EM maps.