A Graph Based Method for the Prediction of Backbone Trace from Cryo-EM Density Maps

Abstract

Cryo-electron microscopy (Cryo-EM) is able to achieve high resolution density maps. These density maps are near atomic resolution and individual atoms can be seen as well as large secondary structure elements. However, it is challenging to extract the backbone structure information automatically and efficiently. This paper presents a novel method for creating a backbone trace and predicting locations of Cα atoms for high resolution density maps. It is a graph based method utilizing density along a backbone trace and features of secondary structure elements to find the optimal backbone trace and Cα atom locations. The method is mostly automatic requiring an initial user determined threshold value and primary secondary structure type. We tested our method on fifteen simulated maps at 3A resolution and four experimental cryo-EM density maps between 2.6-3.1A resolution. The result shows that our method is able to generate a complete Cα backbone trace when the density map is not missing data at near atomic resolution.