Hierarchical, rotation-equivariant neural networks to select structural models of protein complexes

TL;DR

This paper presents a novel hierarchical, rotation-equivariant neural network that directly learns from atomic coordinates to identify accurate protein complex models, improving structure prediction without relying on pre-defined features.

Contribution

The authors introduce a new neural network architecture that learns directly from 3D atomic positions, combining equivariance, local convolutions, and hierarchical sampling for protein structure prediction.

Findings

Significantly improves identification of accurate models

Can predict absolute accuracy of structural models

Applicable to other 3D atomic learning tasks

Abstract

Predicting the structure of multi-protein complexes is a grand challenge in biochemistry, with major implications for basic science and drug discovery. Computational structure prediction methods generally leverage pre-defined structural features to distinguish accurate structural models from less accurate ones. This raises the question of whether it is possible to learn characteristics of accurate models directly from atomic coordinates of protein complexes, with no prior assumptions. Here we introduce a machine learning method that learns directly from the 3D positions of all atoms to identify accurate models of protein complexes, without using any pre-computed physics-inspired or statistical terms. Our neural network architecture combines multiple ingredients that together enable end-to-end learning from molecular structures containing tens of thousands of atoms: a point-based representation of atoms, equivariance with respect to rotation and translation, local convolutions, and hierarchical subsampling operations. When used in combination with previously developed scoring functions, our network substantially improves the identification of accurate structural models among a large set of possible models. Our network can also be used to predict the accuracy of a given structural model in absolute terms. The architecture we present is readily applicable to other tasks involving learning on 3D structures of large atomic systems.