General Binding Affinity Guidance for Diffusion Models in Structure-Based Drug Design

TL;DR

This paper introduces BADGER, a guidance framework for diffusion models in structure-based drug design that improves binding affinity control and enables multi-constraint optimization, leading to more effective and realistic drug candidate generation.

Contribution

BADGER provides a novel, flexible guidance framework that enhances diffusion models with binding affinity control and multi-constraint optimization in drug design.

Findings

Up to 60% improvement in binding affinity of generated molecules.

Effective integration of affinity guidance into diffusion models.

Successful multi-constraint optimization for drug-likeness and synthesizability.

Abstract

Structure-based drug design (SBDD) aims to generate ligands that bind strongly and specifically to target protein pockets. Recent diffusion models have advanced SBDD by capturing the distributions of atomic positions and types, yet they often underemphasize binding affinity control during generation. To address this limitation, we introduce \textbf{\textnormal{\textbf{BADGER}}}, a general \textbf{binding-affinity guidance framework for diffusion models in SBDD}. \textnormal{\textbf{BADGER} }incorporates binding affinity awareness through two complementary strategies: (1) \textit{classifier guidance}, which applies gradient-based affinity signals during sampling in a plug-and-play fashion, and (2) \textit{classifier-free guidance}, which integrates affinity conditioning directly into diffusion model training. Together, these approaches enable controllable ligand generation guided by binding affinity. \textnormal{\textbf{BADGER} } can be added to any diffusion model and achieves up to a \textbf{60\% improvement in ligand--protein binding affinity} of sampled molecules over prior methods. Furthermore, we extend the framework to \textbf{multi-constraint diffusion guidance}, jointly optimizing for binding affinity, drug-likeness (QED), and synthetic accessibility (SA) to design realistic and synthesizable drug candidates.