PGMG: A Pharmacophore-Guided Deep Learning Approach for Bioactive Molecular Generation
This work addresses the problem of accelerating drug discovery for researchers, particularly in scenarios involving novel or understudied targets, though it appears incremental as it builds on existing deep learning methods with pharmacophore guidance.
The authors tackled the challenge of designing novel bioactive molecules in drug discovery by proposing PGMG, a pharmacophore-guided deep learning approach that generates molecules matching given pharmacophore models with high validity, uniqueness, and novelty.
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.