Skip to content

qaiserfatmi/Drug-Discovery

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

21 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Drug-Discovery

Majority of the codes and works are inspired by https://projects.volkamerlab.org/teachopencadd/talktorials and https://github.com/Ash100.

Tut001_Compound_Data_Acquisition_(ChEMBL).ipynb used V5TFZ2 (Uniprot ID; https://www.uniprot.org/uniprotkb/V5TFZ2/entry) which is infact Dengue Type-2 NS5 protein.

Tut002_Dataset_Filteration_and_Analysis.ipynb uses the file "NS5_compounds.csv" produced in Tut001. This file (NS5_compounds.csv) is also present in this folder.

Key Notes

•	Tut001–Tut003: Build a clean training dataset from ChEMBL (known Dengue NS3 inhibitors).

•	Tut004–Tut006: Feature engineering + scaffold analysis for both datasets.

•	Tut007: Entry point for unlabeled ZINC ligands → predict activity using ML.

•	Tut008–Tut012: Dock both known and predicted unknowns into Dengue NS3 for structure-based refinement.

•	Tut013: Output = ranked hit list of reference actives (ChEMBL) and novel hits (ZINC).

About

This repo contains ML tutorials for Drug Discovery

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors