Journal
FRONTIERS IN MOLECULAR BIOSCIENCES
Volume 8, Issue -, Pages -Publisher
FRONTIERS MEDIA SA
DOI: 10.3389/fmolb.2021.647915
Keywords
protein docking; docking model evaluation; graph neural networks; deep learning; protein structure prediction
Categories
Funding
- National Institutes of Health [R01GM133840, R01GM123055]
- National Science Foundation [DMS1614777, CMMI1825941, MCB1925643, DBI2003635]
Ask authors/readers for more resources
Protein-protein interactions are crucial in cellular processes, with computational methods being developed to predict complex structures, such as the deep learning-based GNN-DOVE which outperformed existing methods. GNN-DOVE extracts interface areas using a graph neural network, utilizing atom properties and inter-atomic distances as features for model evaluation.
Physical interactions of proteins play key functional roles in many important cellular processes. To understand molecular mechanisms of such functions, it is crucial to determine the structure of protein complexes. To complement experimental approaches, which usually take a considerable amount of time and resources, various computational methods have been developed for predicting the structures of protein complexes. In computational modeling, one of the challenges is to identify near-native structures from a large pool of generated models. Here, we developed a deep learning-based approach named Graph Neural Network-based DOcking decoy eValuation scorE (GNN-DOVE). To evaluate a protein docking model, GNN-DOVE extracts the interface area and represents it as a graph. The chemical properties of atoms and the inter-atom distances are used as features of nodes and edges in the graph, respectively. GNN-DOVE was trained, validated, and tested on docking models in the Dockground database and further tested on a combined dataset of Dockground and ZDOCK benchmark as well as a CAPRI scoring dataset. GNN-DOVE performed better than existing methods, including DOVE, which is our previous development that uses a convolutional neural network on voxelized structure models.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available