Deep convolutional networks for quality assessment of protein folds

By Georgy Derevyanko, Sergei Grudinin, Yoshua Bengio, Guillaume Lamoureux. 2018

119 citations recorded by the source corpus.

Motivation 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. Results 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. Availability and implementation The code and the datasets are available at https://github.com/lamoureux-lab/3DCNN_MQA. Supplementary information Supplementary data are available at Bioinformatics online.

Subfields: Materials Chemistry, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Materials Chemistry

In Molecular Biology

Citations in the corpus

Learning from Protein Structure with Geometric Vector Perceptrons (2020, methodology): “6 These include the CNN methods 3DCNN (Derevyanko et al., 2018) and Ornate (Pagès et al.”
Multi-Scale Representation Learning on Proteins (2022, methodology): “Previous methods typically only consider an individual subset within these scales, focusing on either sequence [Öztürk et al., 2018, Hou et al., 2018], three-dimensional structure [Hermosilla et al., 2021, Derevyanko et al., 2018] or surface [Gainza et al., 2020].”
GraphQA: protein model quality assessment using graph convolutional networks (2020, unknown): “By forming an edge between all pairs of residues that are within a chemically reasonable distance of each other, the graph becomes a rich representation of both the sequential and geometric structure of the protein (Fig.”
Intrinsic-Extrinsic Convolution and Pooling for Learning on 3D Protein Structures (2021, methodology): “Other methods have solely used 3D atomic coordinates as an input, and applied 3D convolutional neural networks (3DCNN) (Amidi et al., 2017; Derevyanko et al., 2018) or graph convolutional neural networks (GCNN) (Kipf & Welling, 2017).”
Deep Learning in Protein Structural Modeling and Design (2020, background): “A score function may contain knowledge-based terms that do not necessarily have a valid physical meaning, and they are designed to distinguish near-native conformations from non-native ones (for example, learning the GDT_TS).(119) A molecular dynamics (MD) or Monte Carlo (MC) simulation with a state”
Protein Representation Learning by Geometric Structure Pretraining (2022, methodology): “3DCNN_MQA (Derevyanko et al., 2018).”
Protein model quality assessment using 3D oriented convolutional neural networks (2018, methodology): “For example, to circumvent this problem, (17) had to significantly augment the training set with random orientation of the input structures in 3D.”
End-to-End Learning on 3D Protein Structure for Interface Prediction (2018, methodology): “3D convolutional networks have been used for protein-ligand binding affinity [14], [15], [16], as well as for protein fold quality assessment [17], protein structure classication [18], fingerprint prediction [19], and filling in missing amino acids [20].”
ProteinGCN: Protein model quality assessment using Graph Convolutional Networks (2020, methodology): “To tackle the problem of model quality estimation from deep learning perspective, one approach is to project the structure onto a 3D grid and use 3D convolutions (convolutions are local by definition) to convert this voxelized representation in the quality score (3DCNN [5]).”