Deep convolutional networks for quality assessment of protein folds
- 19 June 2018
- journal article
- research article
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 34 (23) , 4046-4053
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. 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. The code and the datasets are available at https://github.com/lamoureux-lab/3DCNN_MQA. Supplementary data are available at Bioinformatics online.Keywords
All Related Versions
Funding Information
- Natural Sciences and Engineering Research Council of Canada
- NSERC (RGPIN 355789, RGPIN 1016552)
- Canada Research Chair
- Canadian Institute for Advanced Research
- CIFAR
- Calcul Quebec and Compute Canada
This publication has 42 references indexed in Scilit:
- lDDT: a local superposition-free score for comparing protein structures and models using distance difference testsBioinformatics, 2013
- The Protein Model Portal—a comprehensive resource for protein structure and model informationDatabase: The Journal of Biological Databases and Curation, 2013
- Improved model quality assessment using ProQ2BMC Bioinformatics, 2012
- Rosetta32011
- Calculation of Local Water Densities in Biological Systems: A Comparison of Molecular Dynamics Simulations and the 3D-RISM-KH Molecular Theory of SolvationThe Journal of Physical Chemistry B, 2010
- A Novel Side-Chain Orientation Dependent Potential Derived from Random-Walk Reference State for Protein Fold Selection and Structure PredictionPLOS ONE, 2010
- Improved prediction of protein side‐chain conformations with SCWRL4Proteins: Structure, Function, and Bioinformatics, 2009
- Statistical potential for assessment and prediction of protein structuresProtein Science, 2006
- Distance‐scaled, finite ideal‐gas reference state improves structure‐derived potentials of mean force for structure selection and stability predictionProtein Science, 2002
- Basic local alignment search toolJournal of Molecular Biology, 1990