DeepRank

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

60
mentions
8
contributors

Cite this software

What DeepRank can do for you

  • Predefined atom-level and residue-level PPI feature types, e.g. atomic density, vdw energy, residue contacts, PSSM, etc.
  • Predefined target types, e.g. binary class, CAPRI categories, DockQ, RMSD, FNAT, etc.
  • Flexible definition of both new features and targets
  • 3D grid feature mapping
  • Efficient data storage in HDF5 format
  • Support both classification and regression (based on PyTorch)

DeepRank is a general, configurable deep learning framework for data mining protein-protein interactions (PPIs) using 3D convolutional neural networks (CNNs).

DeepRank contains useful APIs for pre-processing PPIs data, computing features and targets, as well as training and testing CNN models.

Features:

  • Predefined atom-level and residue-level PPI feature types, e.g. atomic density, vdw energy, residue contacts, PSSM, etc.
  • Predefined target types, e.g. binary class, CAPRI categories, DockQ, RMSD, FNAT, etc.
  • Flexible definition of both new features and targets
  • 3D grid feature mapping
  • Efficient data storage in HDF5 format
  • Support both classification and regression (based on PyTorch)
Logo of DeepRank
Keywords
Programming languages
  • Python 99%
  • R 1%
License
  • Apache-2.0
</>Source code

Participating organisations

Life Sciences
Life Sciences
Netherlands eScience Center
Radboud University Medical Center
Utrecht University

Reference papers

Mentions

Contributors

Contact person

Nicolas Renaud

Nicolas Renaud

Netherlands eScience Center
AB
Alexandre M.J.J. Bonvin
Utrecht University
Cunliang Geng
Cunliang Geng
Netherlands eScience Center
DM
Dario Marzella
Radboud University Medical Center
FA
Francesco Ambrosetti
Utrecht University
Lars Ridder
Lars Ridder
Netherlands eScience Center
LX
Li Xue
Radboud University Medical Center
Nicolas Renaud
Nicolas Renaud
Netherlands eScience Center
Sonja Georgievska
Sonja Georgievska
Netherlands eScience Center

Related projects

3D-Vac

Personalized cancer vaccine design through 3D modelling boosted geometric learning

Updated 12 months ago
In progress

DeepRank

Scoring 3D protein-protein interaction models using deep learning

Updated 12 months ago
Finished

Related software

DeepRank GNN

DE

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

Updated 21 months ago
1 2

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 21 months ago
3 2

PSSMGen

PS

Generates consistent PSSM and PDB files for protein-protein complexes

Updated 21 months ago
2 2