Peptide–protein docking: from physics-based models to generative intelligence

TL;DR

This paper reviews how peptide–protein docking methods have evolved from physics-based models to modern deep learning approaches, highlighting improvements and remaining challenges.

Contribution

The paper introduces a categorization of modern deep learning-based peptide–protein docking methods and outlines future directions for improving their accuracy and applicability.

Findings

Recent deep learning methods have improved the accuracy of peptide–protein docking predictions.

AlphaFold-based protocols and generative models are transforming peptide–protein complex structure prediction.

Challenges remain in handling long, disordered, or chemically modified peptides.

Abstract

Peptide–protein interactions (PepPIs) play a pivotal role in cellular signaling and regulation, representing a significant category of therapeutic agents. However, determining peptide–protein complex structures by experiment is costly and often challenging. Computational peptide–protein complex structure prediction, therefore, plays an important role in mapping binding modes and guiding design. Classical pipelines combine template-based, local, or global docking conformational search algorithms with physics-based or empirical scoring, but they often struggle with highly flexible peptides, induced fit at shallow interfaces, and non-canonical chemistries. In this review, we describe an ongoing shift from such conventional search-and-score workflows to deep learning-based pipelines. We categorize the modern methods into three modules: (i) approaches that predict likely peptide-binding regions on the protein surface and use these predictions to guide or filter docking models; (ii) AlphaFold-based protocols that use general structure prediction methods for peptide–protein co-folding and refinement; and (iii) deep generative models that sample peptide conformations given a target protein structure. We highlight that recent methods have substantially improved the accuracy and applicability of peptide–protein docking, while also identifying shared remaining challenges, including limited avaiability of training data and weak performance on long, disordered, or chemically modified peptides. We conclude by outlining directions for integrating richer biophysical constraints, better-curated peptide–protein datasets, and large-scale generative models to move toward robust, design-ready peptide docking.

We review the evolution of peptide–protein docking methods from traditional physics-based approaches to modern AlphaFold-inspired and diffusion-based frameworks. Their impact, remaining limitations, and open challenges are discussed.

Figures