Protein model quality assessment using rotation-equivariant, hierarchical neural networks
This work provides a significant improvement in protein model quality assessment for computational structural biologists, potentially accelerating protein structure determination.
The paper addresses the challenge of selecting the most accurate protein structural model from candidates by introducing a deep learning approach. Their method, which uses rotation-equivariant, hierarchical neural networks, achieved state-of-the-art results in the CASP blind prediction experiment without relying on physics-inspired energy terms or additional sequence alignment information.
Proteins are miniature machines whose function depends on their three-dimensional (3D) structure. Determining this structure computationally remains an unsolved grand challenge. A major bottleneck involves selecting the most accurate structural model among a large pool of candidates, a task addressed in model quality assessment. Here, we present a novel deep learning approach to assess the quality of a protein model. Our network builds on a point-based representation of the atomic structure and rotation-equivariant convolutions at different levels of structural resolution. These combined aspects allow the network to learn end-to-end from entire protein structures. Our method achieves state-of-the-art results in scoring protein models submitted to recent rounds of CASP, a blind prediction community experiment. Particularly striking is that our method does not use physics-inspired energy terms and does not rely on the availability of additional information (beyond the atomic structure of the individual protein model), such as sequence alignments of multiple proteins.