3D molecule generation by denoising voxel grids

TL;DR

VoxMol introduces a novel score-based method for 3D molecule generation using denoising voxel grids, outperforming existing approaches in capturing drug-like molecules efficiently.

Contribution

The paper presents a new voxel grid-based generative model for 3D molecules, differing from diffusion models on atom clouds, with improved speed and accuracy.

Findings

VoxMol better captures drug-like molecule distribution.

Faster molecule generation compared to state-of-the-art.

Effective denoising of 3D molecular voxel grids.

Abstract

We propose a new score-based approach to generate 3D molecules represented as atomic densities on regular grids. First, we train a denoising neural network that learns to map from a smooth distribution of noisy molecules to the distribution of real molecules. Then, we follow the neural empirical Bayes framework (Saremi and Hyvarinen, 19) and generate molecules in two steps: (i) sample noisy density grids from a smooth distribution via underdamped Langevin Markov chain Monte Carlo, and (ii) recover the "clean" molecule by denoising the noisy grid with a single step. Our method, VoxMol, generates molecules in a fundamentally different way than the current state of the art (ie, diffusion models applied to atom point clouds). It differs in terms of the data representation, the noise model, the network architecture and the generative modeling algorithm. Our experiments show that VoxMol captures the distribution of drug-like molecules better than state of the art, while being faster to generate samples.