MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning

TL;DR

MF-LAL is a novel generative framework that combines multi-fidelity surrogate models with active learning to generate more accurate and effective drug compounds, significantly improving binding free energy scores over existing methods.

Contribution

It introduces a unified framework integrating generative and multi-fidelity surrogate models for drug discovery, enhancing activity prediction accuracy.

Findings

MF-LAL produces compounds with ~50% better binding free energy scores.

The framework outperforms single and multi-fidelity approaches.

It effectively guides compound generation using active learning.

Abstract

Current generative models for drug discovery primarily use molecular docking as an oracle to guide the generation of active compounds. However, such models are often not useful in practice because even compounds with high docking scores do not consistently show real-world experimental activity. More accurate methods for activity prediction exist, such as molecular dynamics based binding free energy calculations, but they are too computationally expensive to use in a generative model. To address this challenge, we propose Multi-Fidelity Latent space Active Learning (MF-LAL), a generative modeling framework that integrates a set of oracles with varying cost-accuracy tradeoffs. Using active learning, we train a surrogate model for each oracle and use these surrogates to guide generation of compounds with high predicted activity. Unlike previous approaches that separately learn the surrogate model and generative model, MF-LAL combines the generative and multi-fidelity surrogate models into a single framework, allowing for more accurate activity prediction and higher quality samples. Our experiments on two disease-relevant proteins show that MF-LAL produces compounds with significantly better binding free energy scores than other single and multi-fidelity approaches (~50% improvement in mean binding free energy score). The code is available at https://github.com/Rose-STL-Lab/MF-LAL.