ProteinGCN: Protein model quality assessment using Graph Convolutional Networks

By Soumya Sanyal, Ivan V. Anishchenko, Anirudh Dagar, David Baker, Partha P. Talukdar. 2020

49 citations recorded by the source corpus.

Blind estimation of local (per-residue) and global (for the whole structure) accuracies in protein structure models is an essential step in many protein modeling applications. With the recent developments in deep-learning, single-model quality assessment methods have been also advanced, primarily through the use of 2D and 3D convolutional deep neural networks. Here we explore an alternative approach and train a graph convolutional network with nodes representing protein atoms and edges connecting spatially adjacent atom pairs on the dataset Rosetta-300k which contains a set of 300k conformations from 2,897 proteins. We show that our proposed architecture, ProteinGCN, is capable of predicting both local and global accuracies in protein models at state-of-the-art levels. Further, the number of free parameters in ProteinGCN is almost 1-2 orders of magnitude smaller compared to the 3D convolutional networks proposed earlier. We provide the source code of our work to encourage reproducible research.1

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): “685 ProteinGCN [24] 0.”
Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking (2021, background): “As a sub-task evaluated in protein folding, protein quality assessment estimates the quality of computational protein models in terms of divergence from their native structure, for which GNN architectures have also been applied (Sanyal et al., 2020; Baldassarre et al., 2021).”
ATOM3D: Tasks On Molecules in Three Dimensions (2020, methodology): “We exclude ProteinGCN [Sanyal et al., 2020], a recent GNN-based method, from comparison as they do not provide results on CASP11 dataset.”