Disentangle VAE for Molecular Generation

TL;DR

This paper introduces CJTVAE, a novel VAE-based model with an extractor module that enables controllable generation of molecules with desired properties, advancing drug discovery efforts.

Contribution

The paper proposes CJTVAE, integrating an extractor into VAE to control molecular properties during generation, addressing a key challenge in drug discovery.

Findings

Successfully generates molecules with targeted properties

Demonstrates improved control over molecular features

Encouraging experimental results validating the approach

Abstract

Automatic molecule generation plays an important role on drug discovery and has received a great deal of attention in recent years thanks to deep learning successful use. Graph-based neural network represents state of the art methods on automatic molecule generation. However, it is still challenging to generate molecule with desired properties, which is a core task in drug discovery. In this paper, we focus on this task and propose a Controllable Junction Tree Variational Autoencoder (C JTVAE), adding an extractor module into VAE framework to describe some properties of molecule. Our method is able to generate similar molecular with desired property given an input molecule. Experimental results is encouraging.