DeepDrug3D

 
   
standalone libraries
 

A new approach to classify drug binding sites in proteins with Deep Learning techniques. Binding sites are represented by three-dimensional interaction grids. DeepDrug3D was demonstrated to accurately distinguish between ATP and heme pockets. It is currently being extended to cover diverse drug binding sites.

  
DeepDrug3D
If you use eToxPred, please cite the following paper:
1 Pu L, Govindaraj RG, Wu HC, Brylinski M. (2019) DeepDrug3D: Classification of ligand-binding pockets in proteins with a convolutional neural network. PLoS Comput Biol 15 (2): e1006718.