Conditional Constrained Graph Variational Autoencoders for Molecule Design
This work addresses challenges in molecule design for drug discovery, but it is incremental as it builds on existing state-of-the-art models.
The paper tackled the problem of generating molecules with deep generative models by using the histogram of atom valences to guide generation, resulting in improved performance on evaluation metrics across two datasets.
In recent years, deep generative models for graphs have been used to generate new molecules. These models have produced good results, leading to several proposals in the literature. However, these models may have troubles learning some of the complex laws governing the chemical world. In this work, we explore the usage of the histogram of atom valences to drive the generation of molecules in such models. We present Conditional Constrained Graph Variational Autoencoder (CCGVAE), a model that implements this key-idea in a state-of-the-art model, and shows improved results on several evaluation metrics on two commonly adopted datasets for molecule generation.