Fine-tuning Pocket-Aware Diffusion Models via Denoising Policy Optimization

2026-05-17

AI Summary

Existing pocket-aware 3D molecular generation methods struggle to simultaneously optimize multiple objectives, including binding affinity, drug-likeness, synthesizability, and diversity. This work addresses this challenge by formulating the denoising diffusion process as a multi-step Markov decision process and integrating reinforcement learning with a multi-objective reward mechanism. The authors propose a coarse-grained denoising scheduling strategy that enables fine-grained control over molecular properties while preserving generation efficiency. Evaluated on the CrossDocked2020 benchmark, the proposed method significantly outperforms current baselines, achieving a Vina docking score of −8.5 kcal/mol and demonstrating superior performance in drug-likeness, molecular diversity, and synthesizability.

Abstract

Structure-based drug design has been accelerated by pocket-aware 3D generative models, yet most methods primarily fit the training distribution and may fall short of satisfying multiple properties required in real-world therapeutic drug discovery. Recently, increasing attention has focused on structure-based molecule optimization (SBMO), which targets fine-grained control over multiple specified molecular properties. In this paper, we present DEPPA, a novel SBMO approach building upon Denoising Diffusion Policy Optimization for fine-tuning a pre-trained pocket-aware diffusion model via reinforcement learning. DEPPA enables optimization over multiple properties, including binding affinity, drug-likeness, synthesizability and diversity. We formulate the reverse denoising process of the pretrained pocket-aware diffusion model as a multi-step Markov Decision Process, where the desired properties that serve as reward signals are evaluated on the final generated ligand molecules. DEPPA incorporates a coarse denoising scheduler during the RL fine-tuning to achieve efficient and effective molecule optimization. Experimental results on the CrossDocked2020 benchmark demonstrate that DEPPA outperforms baselines in binding affinity (Vina Score -8.5 kcal/mol), drug-likeness and diversity while exhibiting competitive performance in synthesizability. The source code is available at https://github.com/xy9485/DePPA .

Problem

• structure-based drug design
• pocket-aware generation
• molecule optimization
• multi-property optimization
• binding affinity

Innovation

• pocket-aware diffusion
• reinforcement learning
• structure-based molecule optimization
• denoising policy optimization
• multi-property optimization