https://github.com/gicsaw/ARAE_torch
python3
numpy
tensorflow <=1.13
RDKit
SA_Score for RDKit
https://github.com/rdkit/rdkit/tree/master/Contrib/SA_Score
git clone https://github.com/gicsaw/ARAE_SMILES
cd ARAE_SMILES
python data_char_ZINC.py train
python data_char_ZINC.py test
python data_char_QM9.py train
python data_char_QM9.py test
python train_ARAE_QM9.py
python train_ARAE_ZINC.py
python train_CARAE_logP_SAS_TPSA.py
python test_n_ARAE_QM9.py
python test_n_ARAE_ZINC.py
python test_n_CARAE_con_logP_SAS_TPSA.py $logP $SAS $TPSA
python test_n_CARAE_uncon_logP_SAS_TPSA.py
python gen_ARAE_QM9.py
python del_end_code.py out_ARAE_QM9/79
generated smiles: out_ARAE_QM9/79/smiles_gen.txt
python gen_ARAE_ZINC.py
python del_end_code.py out_ARAE_ZINC/39
generated smiles: out_ARAE_ZINC/39/smiles_gen.txt
python gen_CARAE_con_logP_SAS_TPSA.py $logP $SAS $TPSA
Hong, S. H., Ryu, S., Lim, J., & Kim, W. Y. (2019). Molecular Generative Model Based On Adversarially Regularized Autoencoder. Journal of Chemical Information and Modeling.