Improved protein structure refinement guided by deep learning based accuracy estimation

We develop a deep learning framework (DeepAccNet) that estimates per-residue accuracy and residue-residue distance signed error in protein models and uses these predictions to guide Rosetta protein structure refinement. The network uses 3D convolutions to evaluate local atomic environments followed by 2D convolutions to provide their global contexts and outperforms other methods that similarly predict the accuracy of protein structure models. Overall accuracy predictions for X-ray and cryoEM structures in the PDB correlate with their resolution, and the network should be broadly useful for assessing the accuracy of both predicted structure models and experimentally determined structures and identifying specific regions likely to be in error. Incorporation of the accuracy predictions at multiple stages in the Rosetta refinement protocol considerably increased the accuracy of the resulting protein structure models, illustrating how deep learning can improve search for global energy minima of biomolecules. Here the authors present DeepAccNet, a deep learning framework that estimates per-residue accuracy and residue-residue distance signed error in protein models, which are used to guide Rosetta protein structure refinement. Benchmarking suggests an improvement of accuracy prediction and refinement compared to other related state of the art methods.

Automated summary

DeepAccNet is a deep learning framework that estimates per-residue accuracy and residue-residue distance signed error in protein models, guiding Rosetta protein structure refinement and demonstrating improved accuracy prediction and refinement compared to other methods.