Apo2Mol: 3D Molecule Generation via Dynamic Pocket-Aware Diffusion Models.

Area of Science:

• Computational chemistry
• Structural biology
• Drug discovery

Background:

• Deep generative models are revolutionizing structure-based drug design for small molecule ligands.
• Current models often overlook protein binding pocket flexibility, limiting practical drug discovery applications.

Purpose of the Study:

• To introduce Apo2Mol, a diffusion-based generative framework for 3D molecule design.
• To explicitly incorporate protein binding pocket conformational flexibility into ligand generation.

Main Methods:

• Curated a dataset of over 24,000 apo-holo structure pairs from the Protein Data Bank.
• Developed a full-atom hierarchical graph-based diffusion model.
• Simultaneously generated 3D ligand molecules and corresponding holo pocket conformations from apo states.

Main Results:

• Apo2Mol achieves state-of-the-art performance in generating high-affinity ligands.
• The framework accurately captures realistic protein pocket conformational changes.
• Demonstrated effectiveness in structure-based drug design by accounting for protein flexibility.

Conclusions:

• Apo2Mol offers a significant advancement in generative models for drug design.
• Explicitly modeling protein flexibility enhances the generation of effective small molecule ligands.
• The approach holds promise for more practical and successful drug discovery pipelines.