Full-length de novo protein structure determination from cryo-EM maps using deep learning

Motivation: Advances in microscopy instruments and image processing algorithms have led to an increasing number of Cryo-electron microscopy (cryo-EM) maps. However, building accurate models for the EM maps at 3-5 angstrom resolution remains a challenging and time-consuming process. With the rapid growth of deposited EM maps, there is an increasing gap between the maps and reconstructed/modeled three-dimensional (3D) structures. Therefore, automatic reconstruction of atomic-accuracy full-atom structures from EM maps is pressingly needed. Results: We present a semi-automatic de novo structure determination method using a deep learning-based framework, named as DeepMM, which builds atomic-accuracy all-atom models from cryo-EM maps at near-atomic resolution. In our method, the main-chain and Ca positions as well as their amino acid and secondary structure types are predicted in the EM map using Densely Connected Convolutional Networks. DeepMM was extensively validated on 40 simulated maps at 5 angstrom resolution and 30 experimental maps at 2.6-4.8 angstrom. resolution as well as an Electron Microscopy Data Bank-wide dataset of 2931 experimental maps at 2.6-4.9 angstrom resolution, and compared with state-of-the-art algorithms including RosettaES, MAINMAST and Phenix. Overall, our DeepMM algorithm obtained a significant improvement over existing methods in terms of both accuracy and coverage in building full-length protein structures on all test sets, demonstrating the efficacy and general applicability of DeepMM.

Automated summary

The study presents a semi-automatic de novo structure determination method named DeepMM that can build atomic-accuracy all-atom models from cryo-EM maps at near-atomic resolution. It uses Densely Connected Convolutional Networks to predict main-chain, Ca positions, amino acid, and secondary structure types in the EM map. DeepMM showed significant improvement in accuracy and coverage in building full-length protein structures on various test sets compared to existing methods like RosettaES, MAINMAST, and Phenix.