Deep convolutional networks for quality assessment of protein folds

Abstract

The computational prediction of a protein structure from its sequence generally relies on a method to assess the quality of protein models. Most assessment methods rank candidate models using heavily engineered structural features, defined as complex functions of the atomic coordinates. However, very few methods have attempted to learn these features directly from the data. We show that deep convolutional networks can be used to predict the ranking of model structures solely on the basis of their raw three-dimensional atomic densities, without any feature tuning. We develop a deep neural network that performs on par with state-of-the-art algorithms from the literature. The network is trained on decoys from the CASP7 to CASP10 datasets and its performance is tested on the CASP11 dataset. On the CASP11 stage 2 dataset, it achieves a loss of 0.064, whereas the best performing method achieves a loss of 0.063. Additional testing on decoys from the CASP12, CAMEO, and 3DRobot datasets confirms that the network performs consistently well across a variety of protein structures. While the network learns to assess structural decoys globally and does not rely on any predefined features, it can be analyzed to show that it implicitly identifies regions that deviate from the native structure.

arXiv comment8 pages

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Protein-Ligand Scoring with Convolutional Neural Networks
• AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• Deep Convolutional Ranking for Multilabel Image Annotation
• Harmonic Networks: Deep Translation and Rotation Equivariance

Cited by in corpus (5)

• Learning from Protein Structure with Geometric Vector Perceptrons
• Hierarchical, rotation-equivariant neural networks to select structural models of protein complexes
• KekuleScope: prediction of cancer cell line sensitivity and compound potency using convolutional neural networks trained on compound images
• Energy-based Graph Convolutional Networks for Scoring Protein Docking Models
• Deep Learning in Protein Structural Modeling and Design