deeprank-core

deeprank-core is the refactorized version of DeepRank GNN, the graph neural network of our DeepRank package. It allows to train graph neural networks to classify protein-protein interface with a greater flexibility for the user.

2
contributors
1003 commits | Last update: June 28, 2022

Cite this software

DOI:
[[ releases.length > 0 ? releases[selectedIndex].doi : conceptDOI ]]
Copy to clipboard
Choose a reference manager file format:
Download file

What deeprank-core can do for you

  • Creates graphs on protein-protein interface
  • Train graph neural network on protein-protein interface
  • Provide great flexibility to the user for implementing new classes and functions relevant for specific applications

In recent years, for the purpose of drug design or protein engineering it has become increasingly of interest to predict or classify information based on the 3D protein-protein interactome.

We have previously developed DeepRank and DeepRank-GNN, deep-learning frameworks to facilitate pattern learning from protein-protein interfaces using Convolutional Neural Network (CNN) and Graph Neural Network (GNN) approaches. deeprank-core has been redesigned to be more modular and customizable, and is wrapped into a user-friendly python3 package.

Read more
Tags
No tags available
Programming Language
  • Python
License
  • Apache-2.0
Source code

Contributors

  • Giulia Crocioni
    Netherlands eScience Center
  • Sven van der Burg
    Netherlands eScience Center

Information for page maintainers

OAI-PMH metadata:
Expected a redirect from a conceptdoi to a versioned doi, got 200 instead.
citation metadata:
doi is not a concept doi.
Show