Generative design and validation of therapeutic peptides for glioblastoma based on a potential target ATP5A

2025-11-19

AI Summary

Glioblastoma (GBM) urgently requires novel targeted therapeutic strategies. To address this, we target mitochondrial ATP synthase subunit ATP5A and establish an integrated “dry–wet” peptide design framework. We introduce POTFlow—the first generative model specifically designed for lead peptide optimization—innovatively integrating secondary-structure geometric constraints with optimal transport theory to drastically reduce conformational search space complexity. POTFlow generates peptides with high affinity and selectivity for ATP5A; these peptides specifically inhibit GBM cell proliferation in vitro and significantly extend survival in patient-derived xenograft (PDX) models. Critically, POTFlow outperforms five state-of-the-art generative methods in both binding efficacy and functional outcomes. This work establishes a clinically translatable peptide-based therapeutic paradigm for treatment-refractory brain tumors, bridging computational design with experimental validation.

Technology Category

• Natural Language Processing: Generation
• Search and Optimization: Combinatorial Optimization
• Machine Learning: Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

Glioblastoma (GBM) remains the most aggressive tumor, urgently requiring novel therapeutic strategies. Here, we present a dry-to-wet framework combining generative modeling and experimental validation to optimize peptides targeting ATP5A, a potential peptide-binding protein for GBM. Our framework introduces the first lead-conditioned generative model, which focuses exploration on geometrically relevant regions around lead peptides and mitigates the combinatorial complexity of de novo methods. Specifically, we propose POTFlow, a underline{P}rior and underline{O}ptimal underline{T}ransport-based underline{Flow}-matching model for peptide optimization. POTFlow employs secondary structure information (e.g., helix, sheet, loop) as geometric constraints, which are further refined by optimal transport to produce shorter flow paths. With this design, our method achieves state-of-the-art performance compared with five popular approaches. When applied to GBM, our method generates peptides that selectively inhibit cell viability and significantly prolong survival in a patient-derived xenograft (PDX) model. As the first lead peptide-conditioned flow matching model, POTFlow holds strong potential as a generalizable framework for therapeutic peptide design.

Problem

• Designs therapeutic peptides targeting ATP5A for glioblastoma treatment
• Optimizes peptides using generative modeling with geometric and structural constraints
• Validates generated peptides through experimental inhibition and survival assays

Innovation

• Generative model conditioned on lead peptides
• POTFlow uses optimal transport for peptide optimization
• Secondary structure constraints refine therapeutic peptide design