Exploring Chemical Space with Score-based Out-of-distribution Generation

TL;DR

MOOD is a score-based diffusion method that enables the generation of novel, high-quality molecules beyond the training distribution by incorporating out-of-distribution control and property-guided optimization.

Contribution

This paper introduces MOOD, a novel diffusion-based approach that controls out-of-distribution generation and guides molecule synthesis using property predictors, requiring no extra costs.

Findings

MOOD can generate molecules beyond the training distribution.

Generated molecules outperform existing methods in property scores.

MOOD finds top 0.01% molecules in the original training pool.

Abstract

A well-known limitation of existing molecular generative models is that the generated molecules highly resemble those in the training set. To generate truly novel molecules that may have even better properties for de novo drug discovery, more powerful exploration in the chemical space is necessary. To this end, we propose Molecular Out-Of-distribution Diffusion(MOOD), a score-based diffusion scheme that incorporates out-of-distribution (OOD) control in the generative stochastic differential equation (SDE) with simple control of a hyperparameter, thus requires no additional costs. Since some novel molecules may not meet the basic requirements of real-world drugs, MOOD performs conditional generation by utilizing the gradients from a property predictor that guides the reverse-time diffusion process to high-scoring regions according to target properties such as protein-ligand interactions, drug-likeness, and synthesizability. This allows MOOD to search for novel and meaningful molecules rather than generating unseen yet trivial ones. We experimentally validate that MOOD is able to explore the chemical space beyond the training distribution, generating molecules that outscore ones found with existing methods, and even the top 0.01% of the original training pool. Our code is available at https://github.com/SeulLee05/MOOD.