Generative AI-Assisted Discovery of HPK1 Inhibitors
Journal of Medicinal Chemistry · 2026
DOI: 10.1021/acs.jmedchem.6c01048 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Medicinal Chemistry, 2026. Verfasst von Kathryn A Giblin und 22 weiteren Autor:innen. Beteiligte Einrichtung: Oncology R&D, AstraZeneca, 1 Francis Crick Avenue, CambridgeCB2 0AA, U.K. Hauptthemen laut MEDLINE: Protein Kinase Inhibitors, Protein Serine-Threonine Kinases, Drug Discovery. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 55 Literaturangaben.
Abstract (Originalsprache)
Generative artificial intelligence (AI) is now widely applied in medicinal chemistry, with detailed case studies emerging in the literature. Here, we describe an early application of REINVENT, AstraZeneca’s in-house generative molecular design platform, to identify new inhibitor scaffolds for hematopoietic progenitor kinase 1 (HPK1). REINVENT was deployed at two stages of the project to address distinct design objectives. For hit identification, transfer learning on kinase-active compounds, followed by reinforcement learning guided by QSAR-based scoring, led to the discovery of three active chemotypes. Subsequently, REINVENT was applied to scaffold hopping, using 3D pharmacophore and docking models as scoring functions, which enabled the identification of two additional active chemotypes. Optimization of one of these scaffolds delivered a compound with potent cellular activity, kinase selectivity, and favorable rat pharmacokinetics. These results demonstrate the value of integrating generative AI with medicinal chemistry expertise and support broader application of the approach in future discovery programs.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Oncology R&D, AstraZeneca, 1 Francis Crick Avenue, CambridgeCB2 0AA, U.K.
- Oncology R&D, AstraZeneca, 35 Gatehouse Drive, Waltham, Massachusetts02451, United States.
- Discovery Sciences, R&D, AstraZeneca, Pepparedsleden 1, SE-431 83Mölndal, Sweden.
- Pharmaron Beijing Co., Ltd., 6 Taihe Road BDA, Beijing100176, P. R. China.
- Discovery Sciences, R&D, AstraZeneca, 1 Francis Crick Avenue, CambridgeCB2 0AA, U.K.
ORCID-Profile: Kun Song, Hongming Chen, Randolph A Escobar, Neil P Grimster, Jason G Kettle, Alexander Pflug, Marianne Schimpl, Robert E Ziegler, Jason D Shields
Zitieren
APA
Giblin, K. A., Song, K., Chen, H., Chen, W., Dong, Z., Escobar, R. A., Grebe, T. P., Grimster, N. P., Hird, A. W., Hughes, S. J., Kettle, J. G., Li, C., Ma, H., Pflug, A., Richter, M., Schimpl, M., Tang, H., Wang, P., Wrigley, G., …, & Shields, J. D. (2026). Generative AI-Assisted Discovery of HPK1 Inhibitors. Journal of Medicinal Chemistry. https://doi.org/10.1021/acs.jmedchem.6c01048
Vancouver
Giblin KA, Song K, Chen H, Chen W, Dong Z, Escobar RA, et al. Generative AI-Assisted Discovery of HPK1 Inhibitors. Journal of Medicinal Chemistry. 2026. doi:10.1021/acs.jmedchem.6c01048
BibTeX
@article{Giblin2026,
author = {Giblin, Kathryn A and Song, Kun and Chen, Hongming and Chen, Weijie and Dong, Zhiqiang and Escobar, Randolph A and Grebe, Tyler P and Grimster, Neil P and Hird, Alexander W and Hughes, Samantha J and Kettle, Jason G and Li, Chengzhi and Ma, Hao and Pflug, Alexander and Richter, Magdalena and Schimpl, Marianne and Tang, Haoran and Wang, Peng and Wrigley, Gail and Wu, Ye and Yu, Haichang and Ziegler, Robert E and Shields, Jason D},
title = {Generative AI-Assisted Discovery of HPK1 Inhibitors},
journal = {Journal of Medicinal Chemistry},
year = {2026},
doi = {10.1021/acs.jmedchem.6c01048}
}
EUVIMED