DrugDesign

Code for the paper :

Conditional Reduction of the Loss Value Versus Reinforcement Learning for Biassing a de-novo Drug Design Generator

paper link: https://jcheminf.biomedcentral.com/articles/10.1186/s13321-022-00643-2

Requirements

MatPlotLib
seaborn
numpy
pandas
PyTorch
RDKit
umap

files: (1 - 4: objective 1 to objective 4)

1_training_G.ipynb
2_CRLV_biased_G__1.ipynb
2_CRLV_biased_G__2.ipynb
2_CRLV_biased_G__3.ipynb
2_CRLV_biased_G__4.ipynb
2_RL_biased_G__1.ipynb
2_RL_biased_G__2.ipynb
2_RL_biased_G__3.ipynb
2_RL_biased_G__4.ipynb
Data_exploration&analysis.ipynb
utils.py

folders:

all_data
gen_smis
models and models/pretrained