Learning Disentangled Equivariant Representation for Explicitly Controllable 3D Molecule Generation

TL;DR

This paper introduces an E(3)-equivariant autoencoder that enables explicit control over molecular properties and structure in 3D molecule generation, advancing drug discovery and design.

Contribution

It proposes a novel equivariant autoencoder with disentangled latent space for property and structure control in 3D molecule generation.

Findings

Effective property-guided molecule generation demonstrated

Model maintains equivariance and invariance properties

Successful application in structure-based drug discovery

Abstract

We consider the conditional generation of 3D drug-like molecules with \textit{explicit control} over molecular properties such as drug-like properties (e.g., Quantitative Estimate of Druglikeness or Synthetic Accessibility score) and effectively binding to specific protein sites. To tackle this problem, we propose an E(3)-equivariant Wasserstein autoencoder and factorize the latent space of our generative model into two disentangled aspects: molecular properties and the remaining structural context of 3D molecules. Our model ensures explicit control over these molecular attributes while maintaining equivariance of coordinate representation and invariance of data likelihood. Furthermore, we introduce a novel alignment-based coordinate loss to adapt equivariant networks for auto-regressive de-novo 3D molecule generation from scratch. Extensive experiments validate our model's effectiveness on property-guided and context-guided molecule generation, both for de-novo 3D molecule design and structure-based drug discovery against protein targets.