Variational Autoencoding Molecular Graphs with Denoising Diffusion Probabilistic Model

TL;DR

This paper introduces a novel hierarchical variational autoencoder for molecular graphs using a denoising diffusion probabilistic model, improving molecular property prediction accuracy and robustness.

Contribution

It combines hierarchical latent structures with diffusion models to enhance molecular representation beyond traditional VAEs.

Findings

Superior prediction performance on small datasets

Enhanced robustness over existing models

Effective molecular property design

Abstract

In data-driven drug discovery, designing molecular descriptors is a very important task. Deep generative models such as variational autoencoders (VAEs) offer a potential solution by designing descriptors as probabilistic latent vectors derived from molecular structures. These models can be trained on large datasets, which have only molecular structures, and applied to transfer learning. Nevertheless, the approximate posterior distribution of the latent vectors of the usual VAE assumes a simple multivariate Gaussian distribution with zero covariance, which may limit the performance of representing the latent features. To overcome this limitation, we propose a novel molecular deep generative model that incorporates a hierarchical structure into the probabilistic latent vectors. We achieve this by a denoising diffusion probabilistic model (DDPM). We demonstrate that our model can design effective molecular latent vectors for molecular property prediction from some experiments by small datasets on physical properties and activity. The results highlight the superior prediction performance and robustness of our model compared to existing approaches.