Tensorflow implementation of MolGAN: An implicit generative model for small molecular graphs (https://arxiv.org/abs/1805.11973)

This library contains a Tensorflow implementation of MolGAN: An implicit generative model for small molecular graphs as presented in [1](https://arxiv.org/abs/1805.11973).

• python>=3.6
• tensorflow>=1.7.0: https://tensorflow.org
• rdkit: https://www.rdkit.org
• numpy
• scikit-learn

• data: should contain your datasets. If you run download_dataset.sh the script will download the dataset used for the paper (then you should run utils/sparse_molecular_dataset.py to convert the dataset in a graph format used by MolGAN models).
• example: Example code for using the library within a Tensorflow project. NOTE: these are NOT the experiments on the paper!
• models: Class for Models. Both VAE and (W)GAN are implemented.
• optimizers: Class for Optimizers for both VAE, (W)GAN and RL.

Please have a look at the example.

Please cite [1] in your work when using this library in your experiments.

For questions and comments, feel free to contact Nicola De Cao.

MIT

[1] De Cao, N., and Kipf, T. (2018).MolGAN: An implicit generative 
model for small molecular graphs. ICML 2018 workshop on Theoretical
Foundations and Applications of Deep Generative Models.

BibTeX format:

@article{de2018molgan,
  title={{MolGAN: An implicit generative model for small
  molecular graphs}},
  author={De Cao, Nicola and Kipf, Thomas},
  journal={ICML 2018 workshop on Theoretical Foundations 
  and Applications of Deep Generative Models},
  year={2018}
}