PepEDiff: Zero-Shot Peptide Binder Design via Protein Embedding Diffusion

2026-01-19

AI Summary

This work proposes a novel paradigm for de novo peptide binder design that circumvents the need for intermediate structural prediction, thereby overcoming limitations in sequence diversity and added complexity inherent in conventional approaches. By leveraging pretrained protein embeddings to construct a continuous latent space and integrating a diffusion probabilistic model with guidance from target pocket residues, the method directly generates peptide sequences in a zero-shot setting. It eschews explicit structural intermediates, instead utilizing the protein embedding manifold as a semantic prior to effectively explore out-of-distribution sequence space. Evaluated on challenging, traditionally undruggable targets such as TIGIT, the framework demonstrates markedly enhanced sequence diversity and binding potential, underscoring its generality and superiority over existing strategies.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

We present PepEDiff, a novel peptide binder generator that designs binding sequences given a target receptor protein sequence and its pocket residues. Peptide binder generation is critical in therapeutic and biochemical applications, yet many existing methods rely heavily on intermediate structure prediction, adding complexity and limiting sequence diversity. Our approach departs from this paradigm by generating binder sequences directly in a continuous latent space derived from a pretrained protein embedding model, without relying on predicted structures, thereby improving structural and sequence diversity. To encourage the model to capture binding-relevant features rather than memorizing known sequences, we perform latent-space exploration and diffusion-based sampling, enabling the generation of peptides beyond the limited distribution of known binders. This zero-shot generative strategy leverages the global protein embedding manifold as a semantic prior, allowing the model to propose novel peptide sequences in previously unseen regions of the protein space. We evaluate PepEDiff on TIGIT, a challenging target with a large, flat protein-protein interaction interface that lacks a druggable pocket. Despite its simplicity, our method outperforms state-of-the-art approaches across benchmark tests and in the TIGIT case study, demonstrating its potential as a general, structure-free framework for zero-shot peptide binder design. The code for this research is available at GitHub: https://github.com/LabJunBMI/PepEDiff-An-Peptide-binder-Embedding-Diffusion-Model

Problem

• peptide binder design
• zero-shot generation
• protein embedding
• structure-free design
• sequence diversity

Innovation

• zero-shot generation
• protein embedding
• diffusion model
• peptide binder design
• structure-free