CreoPep: A Universal Deep Learning Framework for Target-Specific Peptide Design and Optimization

2025-05-05

AI Summary

Natural peptide variants—such as conotoxins—exhibit high sequence diversity, and conventional optimization methods are time-consuming, severely limiting the development of targeted peptide therapeutics. Method: We propose an end-to-end deep generative framework for *de novo* design and optimization of high-affinity, high-selectivity peptides. Our approach introduces progressive masked language modeling coupled with structure–function co-enhancement, breaking the canonical disulfide-bond dependency to generate peptides with non-canonical topologies and novel binding modes. It integrates FoldX-based energy filtering, temperature-controlled polynomial sampling, and multi-source data augmentation. Contribution/Results: We successfully designed sub-micromolar α7-nAChR-targeting conotoxin variants, validated experimentally via electrophysiology; cryo-EM and molecular dynamics simulations confirmed their distinct binding mechanisms. This framework substantially enhances both the efficiency and designability of therapeutic peptide discovery.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Machine Learning: Deep Neural Architectures and Foundation Models
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Target-specific peptides, such as conotoxins, exhibit exceptional binding affinity and selectivity toward ion channels and receptors. However, their therapeutic potential remains underutilized due to the limited diversity of natural variants and the labor-intensive nature of traditional optimization strategies. Here, we present CreoPep, a deep learning-based conditional generative framework that integrates masked language modeling with a progressive masking scheme to design high-affinity peptide mutants while uncovering novel structural motifs. CreoPep employs an integrative augmentation pipeline, combining FoldX-based energy screening with temperature-controlled multinomial sampling, to generate structurally and functionally diverse peptides that retain key pharmacological properties. We validate this approach by designing conotoxin inhibitors targeting the $alpha$7 nicotinic acetylcholine receptor, achieving submicromolar potency in electrophysiological assays. Structural analysis reveals that CreoPep-generated variants engage in both conserved and novel binding modes, including disulfide-deficient forms, thus expanding beyond conventional design paradigms. Overall, CreoPep offers a robust and generalizable platform that bridges computational peptide design with experimental validation, accelerating the discovery of next-generation peptide therapeutics.

Problem

• Designing high-affinity peptide mutants for target-specific applications
• Overcoming limited natural diversity in therapeutic peptides
• Integrating computational design with experimental validation efficiently

Innovation

• Deep learning-based conditional generative framework
• Integrative augmentation pipeline with energy screening
• Generates diverse peptides retaining pharmacological properties