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

TL;DR

PepEDiff introduces a novel zero-shot peptide binder generation method that directly creates binding sequences from protein embeddings without relying on structure prediction, enhancing diversity and outperforming existing approaches.

Contribution

It presents a structure-free, diffusion-based peptide design framework leveraging pretrained protein embeddings for zero-shot binder generation.

Findings

Outperforms state-of-the-art methods on benchmark tests

Successfully designs peptide binders for challenging targets like TIGIT

Generates diverse peptide sequences beyond known binder distributions

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