Molecular Generative Model Based On Adversarially Regularized Autoencoder

TL;DR

This paper introduces a novel molecular generative model called ARAE, which combines autoencoder and adversarial training to improve molecule generation quality and enable conditional drug-like molecule synthesis.

Contribution

The paper proposes an adversarially regularized autoencoder (ARAE) for molecular generation, addressing limitations of VAE and GAN models, and demonstrates its effectiveness in generating valid, unique, and novel molecules.

Findings

ARAE outperforms traditional models in validity, uniqueness, and novelty.

Successful conditional generation of drug-like molecules with multiple property controls.

Generated EGFR inhibitors sharing scaffolds of known active molecules.

Abstract

Deep generative models are attracting great attention as a new promising approach for molecular design. All models reported so far are based on either variational autoencoder (VAE) or generative adversarial network (GAN). Here we propose a new type model based on an adversarially regularized autoencoder (ARAE). It basically uses latent variables like VAE, but the distribution of the latent variables is obtained by adversarial training like in GAN. The latter is intended to avoid both inappropriate approximation of posterior distribution in VAE and difficulty in handling discrete variables in GAN. Our benchmark study showed that ARAE indeed outperformed conventional models in terms of validity, uniqueness, and novelty per generated molecule. We also demonstrated successful conditional generation of drug-like molecules with ARAE for both cases of single and multiple properties control. As a potential real-world application, we could generate EGFR inhibitors sharing the scaffolds of known active molecules while satisfying drug-like conditions simultaneously.