RGCVAE: relational graph conditioned variational autoencoder for molecule design

Identifying molecules that exhibit some pre-specified properties is a difficult problem to solve. In the last few years, deep generative models have been used for molecule genera- tion. Deep Graph Variational Autoencoders are among the most powerful machine learning tools with which it is possible to address this problem. However, existing methods strug- gle to capture the true data distribution and tend to be computationally expensive. In this work, we propose RGCVAE, an efficient and effective Graph Variational Autoencoder based on: (i) an encoding network exploiting a new powerful Relational Graph Isomor- phism Network; (ii) a novel probabilistic decoding component. Compared to several State- of-the-Art VAE methods on two widely adopted datasets, RGCVAE shows State-of-the-Art molecule generation performance while being significantly faster to train. The Python code implementing RGCVAE is openly accessible for download at: https://github.com/drigoni/ RGCVAE.