TD3B: Transition-Directed Discrete Diffusion for Allosteric Binder Generation

Hugging Face Daily Papers Papers

Summary

TD3B is a sequence-based generative framework for designing allosteric binders with specific agonist or antagonist behaviors using transition-directed discrete diffusion. The paper introduces a method to control directional transitions in protein states, addressing limitations of static structure-based design.

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.
Original Article Export to Word Export to PDF
View Cached Full Text

Cached at: 05/12/26, 07:33 AM

Paper page - TD3B: Transition-Directed Discrete Diffusion for Allosteric Binder Generation

Source: https://huggingface.co/papers/2605.09810

Abstract

A sequence-based generative framework called TD3B is introduced for designing allosteric binders with specified agonist or antagonist behavior by controlling directional transitions in protein states.

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-DirectedDiscrete DiffusionforAllosteric Binder Design(TD3B), a sequence-basedgenerative frameworkthat designs binders with specified agonist or antagonist behavior via adirectional transition controlobjective. TD3B combines atarget-aware Direction Oracle, asoft binding-affinity gate, andamortized fine-tuningof apre-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.

View arXiv pageView PDFAdd to collection

Models citing this paper1

#### ChatterjeeLab/TD3B Updatedabout 4 hours ago

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.09810 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.09810 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles