TAGMol: Target-Aware Gradient-guided Molecule Generation

Vineeth Dorna, D. Subhalingam, Keshav Kolluru, Shreshth Tuli, Mrityunjay Singh, Saurabh Singal, N M Anoop Krishnan, Sayan Ranu

Keywords: Structure-Based Drug Design, Drug-Target Binding, Property prediction, Conditional Diffusion, Property guidance.

TL;DR: Introducing TAGMol: A novel approach to structure-based drug design that generates target-specific, drug-like molecules with optimal properties (QED, SA) through gradient-guided, diffusion-based molecule generation.

Abstract:

3D generative models have shown significant promise in *structure-based drug design (SBDD)*, particularly in discovering ligands tailored to specific target binding sites. Existing algorithms often focus primarily on ligand-target binding, characterized by binding affinity. Moreover, models trained solely on target-ligand distribution may fall short in addressing the broader objectives of drug discovery, such as the development of novel ligands with desired properties like drug-likeness, and synthesizability, underscoring the multifaceted nature of the drug design process.
To overcome these challenges, we decouple the problem into molecular generation and property prediction. The latter synergistically *guides* the diffusion sampling process, facilitating guided diffusion and resulting in the creation of meaningful molecules with the desired properties. We call this guided molecular generation process as TAGMol.
Through experiments on benchmark datasets, TAGMol demonstrates superior performance compared to state-of-the-art baselines, achieving a 22% improvement in average Vina Score and yielding favorable outcomes in essential auxiliary properties. This establishes TAGMol as a comprehensive framework for drug generation. The code is available at https://github.com/moleculeai/TAGMol.

Submission Number: 42