EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

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

Hao Qian iD, Pu You, Lin Zeng, Jingyuan Zhou iD, Dengdeng Huang, Kaicheng Li, Shikui Tu iD, Lei Xu

Briefings in Bioinformatics · 2026

DOI: 10.1093/bib/bbag188 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Hao Qian und 7 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Cognitive Machines and Computational Health (CMaCH), School of Computer Science, Shanghai Jiao Tong University, No. 800 Dongchuan Road, Mi…. Hauptthemen laut MEDLINE: Glioblastoma, Peptides, Drug Design, Brain Neoplasms. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Science and Technology Commission of Shanghai Municipality, National Natural Science Foundation of China, Shanghai Municipal Science and Technology Major Project, China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 Prior and Optimal Transport-based Flow-matching model for peptide optimization. POTFlow employs secondary structure information (e.g. helix, sheet, and 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 model. As the first lead peptide-conditioned flow matching model, POTFlow holds strong potential as a generalizable framework for therapeutic peptide design.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GlioblastomaPeptidesDrug DesignBrain NeoplasmsHumansAnimalsMiceGenerative Artificial IntelligenceCell Line, Tumor

Stichwörter der Autor:innen

flow matchinggenerative modelsglioblastomapeptide design

Substanzen

Peptides

Autor:innen und Institutionen

  • Centre for Cognitive Machines and Computational Health (CMaCH), School of Computer Science, Shanghai Jiao Tong University, No. 800 Dongchuan Road, Minhang District, Shanghai 200240, China.
  • QuietD Bio Co., Ltd., No. 333 Haike Road, Pudong New District, Shanghai 201210, China.

ORCID-Profile: Hao Qian, Jingyuan Zhou, Shikui Tu

Förderung

  • Science and Technology Commission of Shanghai Municipality
  • National Natural Science Foundation of China
  • Shanghai Municipal Science and Technology Major Project, China

Zitieren

APA

Qian, H., You, P., Zeng, L., Zhou, J., Huang, D., Li, K., Tu, S., & Xu, L. (2026). Generative design and validation of therapeutic peptides for glioblastoma based on a potential target ATP5A. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag188

Vancouver

Qian H, You P, Zeng L, Zhou J, Huang D, Li K, et al. Generative design and validation of therapeutic peptides for glioblastoma based on a potential target ATP5A. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag188

BibTeX
@article{Qian2026,
  author = {Qian, Hao and You, Pu and Zeng, Lin and Zhou, Jingyuan and Huang, Dengdeng and Li, Kaicheng and Tu, Shikui and Xu, Lei},
  title = {Generative design and validation of therapeutic peptides for glioblastoma based on a potential target ATP5A},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  doi = {10.1093/bib/bbag188}
}
Kostenlos starten →