PGMG: A Pharmacophore-Guided Deep Learning Approach for Bioactive Molecular Generation

TL;DR

PGMG is a novel deep learning method that uses pharmacophore guidance to generate diverse, valid, and bioactive molecules, aiding drug discovery especially for understudied targets.

Contribution

It introduces a flexible pharmacophore-guided deep learning framework for bioactive molecule generation using a variational autoencoder, applicable to various drug design scenarios.

Findings

Successfully generates molecules matching pharmacophore models.

Maintains high validity, uniqueness, and novelty in generated molecules.

Effective in ligand-based, structure-based, and lead optimization tasks.

Abstract

The rational design of novel molecules with desired bioactivity is a critical but challenging task in drug discovery, especially when treating a novel target family or understudied targets. Here, we propose PGMG, a pharmacophore-guided deep learning approach for bioactivate molecule generation. Through the guidance of pharmacophore, PGMG provides a flexible strategy to generate bioactive molecules with structural diversity in various scenarios using a trained variational autoencoder. We show that PGMG can generate molecules matching given pharmacophore models while maintaining a high level of validity, uniqueness, and novelty. In the case studies, we demonstrate the application of PGMG to generate bioactive molecules in ligand-based and structure-based drug de novo design, as well as in lead optimization scenarios. Overall, the flexibility and effectiveness of PGMG make it a useful tool for accelerating the drug discovery process.