Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension

2024-11-26

arXiv.org

AI Summary

To address key challenges in de novo peptide design—namely, uneven residue contribution, geometrically invalid conformations, and misalignment with practical drug development—this work proposes a hotspot-driven, fragment-based autoregressive generation framework. Methodologically, it innovatively integrates energy-density modeling with frame-aligned dihedral angle constraint estimation to jointly optimize hotspot residue embedding and backbone conformational synthesizability. It further incorporates multi-fragment autoregressive expansion and iterative conformational refinement to balance sequence diversity and structural validity. Evaluated on binding-site design and scaffold generation tasks, our method substantially outperforms existing baselines: generated peptides achieve high predicted binding affinity (ΔG reduced by 1.8 kcal/mol) while maintaining physically realistic, experimentally feasible 3D structures. This represents the first end-to-end generative paradigm for targeted peptide drug discovery that simultaneously ensures thermodynamic accuracy and structural feasibility.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Consent frameworks and practices on the web

Abstract

Peptides, short chains of amino acids, interact with target proteins, making them a unique class of protein-based therapeutics for treating human diseases. Recently, deep generative models have shown great promise in peptide generation. However, several challenges remain in designing effective peptide binders. First, not all residues contribute equally to peptide-target interactions. Second, the generated peptides must adopt valid geometries due to the constraints of peptide bonds. Third, realistic tasks for peptide drug development are still lacking. To address these challenges, we introduce PepHAR, a hot-spot-driven autoregressive generative model for designing peptides targeting specific proteins. Building on the observation that certain hot spot residues have higher interaction potentials, we first use an energy-based density model to fit and sample these key residues. Next, to ensure proper peptide geometry, we autoregressively extend peptide fragments by estimating dihedral angles between residue frames. Finally, we apply an optimization process to iteratively refine fragment assembly, ensuring correct peptide structures. By combining hot spot sampling with fragment-based extension, our approach enables de novo peptide design tailored to a target protein and allows the incorporation of key hot spot residues into peptide scaffolds. Extensive experiments, including peptide design and peptide scaffold generation, demonstrate the strong potential of PepHAR in computational peptide binder design. Source code will be available at https://github.com/Ced3-han/PepHAR.

Problem

• Peptide design targeting specific proteins
• Incorporating key hot spot residues
• Ensuring proper peptide geometry

Innovation

• Hot-spot-driven peptide design
• Autoregressive fragment extension
• Energy-based residue sampling