NEBULA: Neural Empirical Bayes Under Latent Representations for Efficient and Controllable Design of Molecular Libraries

TL;DR

NEBULA is a novel latent 3D generative model that efficiently produces large, high-quality molecular libraries around a seed compound, significantly faster than previous methods, and generalizes well to unseen drug-like molecules.

Contribution

It introduces a scalable, fast, and high-quality 3D molecular library generation method using neural empirical Bayes in a learned latent space, outperforming existing voxel-based approaches.

Findings

NEBULA generates molecular libraries nearly ten times faster than prior methods.

It maintains high sample quality comparable to voxel-based models.

The model generalizes effectively to unseen drug-like molecules across multiple datasets.

Abstract

We present NEBULA, the first latent 3D generative model for scalable generation of large molecular libraries around a seed compound of interest. Such libraries are crucial for scientific discovery, but it remains challenging to generate large numbers of high quality samples efficiently. 3D-voxel-based methods have recently shown great promise for generating high quality samples de novo from random noise (Pinheiro et al., 2023). However, sampling in 3D-voxel space is computationally expensive and use in library generation is prohibitively slow. Here, we instead perform neural empirical Bayes sampling (Saremi & Hyvarinen, 2019) in the learned latent space of a vector-quantized variational autoencoder. NEBULA generates large molecular libraries nearly an order of magnitude faster than existing methods without sacrificing sample quality. Moreover, NEBULA generalizes better to unseen drug-like molecules, as demonstrated on two public datasets and multiple recently released drugs. We expect the approach herein to be highly enabling for machine learning-based drug discovery. The code is available at https://github.com/prescient-design/nebula