TD3B: Transition-Directed Discrete Diffusion for Allosteric Binder Generation

2026/05/10 by Hanqun Cao, Aastha Pal, Sophia Tang +4 · 1 voice · 2 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #cs.LG #q-bio.BM

paper · pdf · doi:10.48550/arxiv.2605.09810

Abstract

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.

Citations

• AReUReDi: Annealed Rectified Updates for Refining Discrete Flows with Multi-Objective Guidance
• TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusion
• Multi-Objective-Guided Discrete Flow Matching for Controllable Biological Sequence Design
• PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion
• Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design
• Simple and Effective Masked Diffusion Language Models
• Simplified and Generalized Masked Diffusion for Discrete Data
• Unlocking Guidance for Discrete State-Space Diffusion and Flow Models
• Particle Denoising Diffusion Sampler
• Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
• De novo design of protein structure and function with RFdiffusion
• Evolutionary-scale prediction of atomic-level protein structure with a language model
• Diffusion Posterior Sampling for General Noisy Inverse Problems
• Classifier-Free Diffusion Guidance
• Robust deep learning–based protein sequence design using ProteinMPNN
• Structured Denoising Diffusion Models in Discrete State-Spaces
• Diffusion Models Beat GANs on Image Synthesis
• Conformational selection in protein binding and function
• Orexin Receptors: Pharmacology and Therapeutic Opportunities

Cited by

• SF-Cluster: Frustration-Guided MSA Subsampling for Alternative Protein Conformation Recovery
• AlloGen: Conformation-Selective Binder Generation with Differential State Scoring

Discussions

• Hanqun Cao, Aastha Pal, Sophia Tang, Yinuo Zhang, Jingjie Zhang, Pheng Ann Heng, Pranam Chatterjee: TD3B: Transition-Directed Discrete Diffusion for Allosteric Binder Generation https://arxiv.org/abs/ [bsky, 0 points, 0 comments]

Related

• BInD: Bond and Interaction-generating Diffusion Model for Multi-objective Structure-based Drug Design
• Binding-Adaptive Diffusion Models for Structure-Based Drug Design
• Target-conditioned diffusion generates potent TNFR superfamily antagonists and agonists
• General Binding Affinity Guidance for Diffusion Models in Structure-Based Drug Design
• PILOT: Equivariant diffusion for pocket conditioned de novo ligand generation with multi-objective guidance via importance sampling