Skip to content

Latent biases present in ML methods used for protein-ligand interaction prediction tasks

Notifications You must be signed in to change notification settings

devalab/Protein-Ligand-Dataset-Bias

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

This repository contains all the models and the datasets/ methods used in this study in the following directories.

  • DAVIS_SPLITS - Contains the scripts used to create the folds for the davis dataset
  • DeepDTA - Describes the methods to reproduce the DeepDTA experiments
  • GraphDTA - Consists of the slighly modified scripts taken from the open source code provided by the authors
  • KIBA_SPLITS - Contains the scripts used to create folds for KIBA dataset.
  • SPLITS - Contains the Folds created for PDBbind dataset
  • SMINA - Contains the smina experiments
  • PLEC - Contains the Protein Ligand Extended Connectivity Fingerprint experiments
  • Pocketmatch - Contains the Pocketmatch score calculation experiments
  • pafnucy - Contains the scripts to train and test the Pafnucy model on PDBbind dataset along with ligand only and protein only experiments
  • SimCNN-DTA - Contains the Code for the SimCNN-DTA written in pytorch as explained in the work by respective authors.

About

Latent biases present in ML methods used for protein-ligand interaction prediction tasks

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published