EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Generative AI–driven de novo design of high-affinity, epitope-specific antibodies targeting the CD93–IGFBP7 axis for cancer immunotherapy

Yixin Qian, Youxin Feng, Ming Zou, Huiyu Cai, Jintong Ye, Teng Song iD, Ping Li, Jian Tang, Mi Deng iD

Antibody Therapeutics · 29.06.2026 · 9 (3) · 323-331

DOI: 10.1093/abt/tbag019 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Antibody Therapeutics, online erschienen am 28.04.2026. Verfasst von Yixin Qian und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Immunology, School of Basic Medical Sciences, Health Science Center, Peking University, Beijing 100191, PR China. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Beijing Natural Science Foundation, National Center of Technology Innovation for Biopharmaceuticals, High Innovation Plan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

CD93 is an emerging immune checkpoint. Blocking its interaction with insulin-like growth factor-binding protein-7 (IGFBP7) restores antitumor immunity, yet discovering high-affinity antibodies against this specific functional epitope remains a formidable challenge for traditional methods.

Methods

We employed a proprietary generative artificial intelligence (AI) model, GeoFlow, to de novo design antibodies targeting the predicted binding epitope of a reference antibody 7F3. A library constructed from 105 sequences was screened via phage display, and the lead candidate, 7-4_com10, was validated through biolayer interferometry, flow cytometry, and in vivo efficacy studies.

Results

To dissect the contribution of endothelial CD93 to immunotherapy resistance, we utilized an endothelial-specific conditional knockout model in MB49 bladder cancer, where the loss of endothelial CD93 significantly sensitized tumors to PD-1 inhibition. The genetic findings identified endothelial CD93 as a fundamental driver of immunotherapy resistance and provided the rationale for our GeoFlow generative AI platform, which was employed to de novo design ~105 candidates targeting the IGFBP7-binding interface on CD93. Our lead candidate, 7-4_com10, demonstrated superior affinity and more potent functional blockade of the CD93–IGFBP7 axis compared to the reference 7F3. Crucially, 7-4_com10 sensitized H22 solid tumors to anti-PD-1 therapy in vivo, which confirmed that 7-4_com10 successfully targeted the identified immunosuppressive axis and pharmacologically phenocopied the benefits of genetic endothelial ablation.

Conclusions

This study validated generative AI for designing epitope-specific antibodies with superior potency, offering a robust candidate for next-generation immunotherapy.

Schlagwörter

Stichwörter der Autor:innen

AI-driven de novo design antibodyCD93IGFBP7endothelial cellsimmunotherapy

Autor:innen und Institutionen

  • Department of Immunology, School of Basic Medical Sciences, Health Science Center, Peking University, Beijing 100191, PR China.
  • State Key Laboratory of Molecular Oncology, Frontiers Science Center for Cancer Integrative Omics, Peking University International Cancer Institute, Peking University, Beijing 100191, PR China.
  • BioGeometry, Beijing 100083, PR China.
  • Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education), Peking University Cancer Hospital and Institute, Beijing 100142, PR China.

ORCID-Profile: Teng Song, Mi Deng

Förderung

  • Beijing Natural Science Foundation
  • National Center of Technology Innovation for Biopharmaceuticals
  • High Innovation Plan
  • National Natural Science Foundation of China

Zitieren

APA

Qian, Y., Feng, Y., Zou, M., Cai, H., Ye, J., Song, T., Li, P., Tang, J., & Deng, M. (2026). Generative AI–driven de novo design of high-affinity, epitope-specific antibodies targeting the CD93–IGFBP7 axis for cancer immunotherapy. Antibody Therapeutics, 9(3), 323-331. https://doi.org/10.1093/abt/tbag019

Vancouver

Qian Y, Feng Y, Zou M, Cai H, Ye J, Song T, et al. Generative AI–driven de novo design of high-affinity, epitope-specific antibodies targeting the CD93–IGFBP7 axis for cancer immunotherapy. Antibody Therapeutics. 2026;9(3):323-331. doi:10.1093/abt/tbag019

BibTeX
@article{Qian2026,
  author = {Qian, Yixin and Feng, Youxin and Zou, Ming and Cai, Huiyu and Ye, Jintong and Song, Teng and Li, Ping and Tang, Jian and Deng, Mi},
  title = {Generative AI–driven de novo design of high-affinity, epitope-specific antibodies targeting the CD93–IGFBP7 axis for cancer immunotherapy},
  journal = {Antibody Therapeutics},
  year = {2026},
  volume = {9},
  number = {3},
  pages = {323--331},
  doi = {10.1093/abt/tbag019}
}
Kostenlos starten →