TD3B: Transition-Directed Discrete Diffusion for Allosteric Binder Generation

Hanqun Cao ,

Aastha Pal ,

Sophia Tang ,

Yinuo Zhang ,

Jingjie Zhang ,

Pheng Ann Heng ,

Pranam Chatterjee

GenAI Diffusion AI4S DSMSD

418

2026年05月10日

蛋白质的功能往往并非通过稳定单一构象来调控，而是由配体（如激动剂和拮抗剂）调控其状态转变的方向性所实现。这一机制在具有重要临床意义的G蛋白偶联受体（GPCR）中尤为关键，因为其治疗效果高度依赖于功能响应的方向性（即激动或拮抗）。目前基于结构的设计方法主要针对静态构象进行优化，既无法刻画不可逆、具有方向性的功能效应，也无法系统性地区分激动剂与拮抗剂的行为特征。为弥补这一空白，我们提出了“面向转变导向的变构结合剂设计离散扩散模型”（Transition-Directed Discrete Diffusion for Allosteric Binder Design, TD3B）——一种基于序列的生成式框架，其核心是通过一个明确的方向性转变控制目标，定向设计具备指定激动或拮抗功能的结合分子。TD3B整合了三方面关键技术：一种面向靶标的“方向判别器”（Direction Oracle）、一个兼顾结合亲和力的柔性门控机制（soft binding-affinity gate），以及对预训练离散扩散模型进行摊销式微调（amortized fine-tuning）。该框架实现了激动剂与拮抗剂的靶向生成，且其功能方向性调控与结合亲和力解耦；而现有基于平衡态建模或仅依赖推理阶段引导的方法均无法达到同等能力。相关代码与预训练模型权重已开源，地址为：https://huggingface.co/ChatterjeeLab/TD3B。

Protein function is often controlled by ligands that bias the direction of state transitions, such as agonists and antagonists, rather than stabilizing a single conformation. This is especially important for clinically relevant G protein-coupled receptors (GPCRs), where therapeutic efficacy depends on functional directionality. Structure-based design methods optimize binding to static conformations and cannot represent non-reversible, directional effects or systematically distinguish agonist from antagonist behavior. To address this gap, we introduce Transition-Directed Discrete Diffusion for Allosteric Binder Design (TD3B), a sequence-based generative framework that designs binders with specified agonist or antagonist behavior via a directional transition control objective. TD3B combines a target-aware Direction Oracle, a soft binding-affinity gate, and amortized fine-tuning of a pre-trained discrete diffusion model, enabling targeted agonist and antagonist generation decoupled from binding affinity and unattainable by equilibrium-based or inference-only guidance baselines. The code and checkpoints are available at https://huggingface.co/ChatterjeeLab/TD3B.

许愿