DeepRank GNN

DeepRank-GNN is the graph neural network of our DeepRank package. DeepRank GNN allows to train graph neural networks to classify protein-protein interface

1
mention
2
contributors

What DeepRank GNN can do for you

  • Creates graphs on protein-protein interface
  • Train graph neural network on protein-protein interface

Gaining structural insights into the protein-protein interactome is essential to understand biological phenomena and extract knowledge for rational drug design or protein engineering. We have previously developed DeepRank, a deep-learning framework to facilitate pattern learning from protein-protein interfaces using Convolutional Neural Network (CNN) approaches. However, CNN is not rotation invariant and data augmentation is required to desensitize the network to the input data orientation which dramatically impairs the computation performance. Representing protein-protein complexes as atomic- or residue-scale rotation invariant graphs instead enables using graph neural networks (GNN) approaches, bypassing those limitations.

We have developed DeepRank-GNN, a framework that converts protein-protein interfaces from PDB 3D coordinates files into graphs that are further provided to a pre-defined or user-defined GNN architecture to learn problem-specific interaction patterns. DeepRank-GNN is designed to be highly modularizable, easily customized, and is wrapped into a user-friendly python3 package. Here, we showcase DeepRank-GNN’s performance for scoring docking models using a dedicated graph interaction neural network (GINet). We show that this graph-based model performs better than DeepRank, DOVE and HADDOCK scores and competes with iScore on the CAPRI score set. We show a significant gain in speed and storage requirement using DeepRank-GNN as compared to DeepRank.

https://www.biorxiv.org/content/10.1101/2021.12.08.471762v1

Keywords
No keywords avaliable
Programming language
  • Python 100%
License
  • Apache-2.0
</>Source code

Participating organisations

Netherlands eScience Center

Mentions

Flavour your linked data with garlic

Author(s): Carlos Martinez-Ortiz
Published in 2018

Contributors

Contact person

Nicolas Renaud

Nicolas Renaud

Netherlands eScience Center
MR
Manon Réau
Utrecht University
Nicolas Renaud
Nicolas Renaud
Netherlands eScience Center

Related projects

3D-Vac

Personalized cancer vaccine design through 3D modelling boosted geometric learning

Updated 11 months ago
In progress

DeepRank

Scoring 3D protein-protein interaction models using deep learning

Updated 11 months ago
Finished

Related software

DeepRank

DE

Deep learning framework for data mining protein-protein interactions using CNN

Updated 4 months ago
56 8

iScore

IS

A framework and predictor based on support vector machine and random walk graph kernel for scoring protein-protein interfaces.

Updated 4 months ago
3 4

pdb2sql

PD

Fast and versatile Python package that leverages SQL queries to parse, manipulate and process biomolecular structure files. The structure files should be in the PDB format and are available on www.rcsb.org.

Updated 20 months ago
3 2