A Graph Neural Network Approach to Automated Model Building in Cryo-EM Maps
This addresses the problem of time-consuming manual model building in structural biology for researchers using cryo-EM, representing a strong domain-specific advancement rather than a foundational breakthrough.
The authors tackled the laborious manual process of atomic modeling in cryo-EM maps by proposing a graph neural network approach for automated protein model building, achieving performance that outperforms state-of-the-art methods and approximates manual building for maps with resolutions better than 3.5 Å, as demonstrated on 28 test cases.
Electron cryo-microscopy (cryo-EM) produces three-dimensional (3D) maps of the electrostatic potential of biological macromolecules, including proteins. Along with knowledge about the imaged molecules, cryo-EM maps allow de novo atomic modelling, which is typically done through a laborious manual process. Taking inspiration from recent advances in machine learning applications to protein structure prediction, we propose a graph neural network (GNN) approach for automated model building of proteins in cryo-EM maps. The GNN acts on a graph with nodes assigned to individual amino acids and edges representing the protein chain. Combining information from the voxel-based cryo-EM data, the amino acid sequence data and prior knowledge about protein geometries, the GNN refines the geometry of the protein chain and classifies the amino acids for each of its nodes. Application to 28 test cases shows that our approach outperforms the state-of-the-art and approximates manual building for cryo-EM maps with resolutions better than 3.5 Å.