TAGMol: Target-Aware Gradient-guided Molecule Generation
This work addresses the multifaceted nature of drug discovery for researchers by providing a comprehensive framework, though it is incremental as it builds on existing diffusion models with guided sampling.
The paper tackles the challenge of generating novel ligands with desired properties like drug-likeness and synthesizability in structure-based drug design, by decoupling molecular generation and property prediction to guide diffusion sampling, resulting in a 22% improvement in average Vina Score compared to state-of-the-art baselines.
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.