AI-guided identification of natural CTSL inhibitors with therapeutic potential for renal injury
PLOS Computational Biology · 10.07.2026 · 22 (7) · e1014464
DOI: 10.1371/journal.pcbi.1014464 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 10.07.2026. Verfasst von Feier Ma und 4 weiteren Autor:innen. Beteiligte Einrichtung: Beijing Key Laboratory of Diabetes Research and Care, Beijing Diabetes Institute, Beijing Tongren Hospital, Capital Medical University, Beijing, Chin…. Hauptthemen laut MEDLINE: Biological Products, Artificial Intelligence, Drug Discovery. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, the Scientific Project of Beijing’s Municipal Science & Technology Commission, Beijing Municipal Administration of Hospitals Clinical Medicine Development of Special Funding Support Programme.
Abstract (Originalsprache)
Cathepsin L (CTSL) is a prominent therapeutic target for kidney injury, yet clinically available CTSL inhibitors remain limited. Here, we developed an artificial intelligence (AI)-assisted discovery strategy to identify novel CTSL inhibitors from a natural products library. Through a robust deep learning model and molecular docking, we screened 200 molecules from natural products library for experimental validation. Active candidates were further analyzed by molecular dynamics simulations to characterize binding modes and key CTSL-ligand interaction networks, followed by evaluation of therapeutic efficacy in kidney injury-relevant models. At a concentration of 100 µM, we found that 43 of them exhibited more than 50% inhibition of CTSL. Notably, nine molecules displayed over 90% inhibition and exhibited concentration-dependent effects. Molecular dynamics simulations indicated that Kuwanon G (KG), Iberverin, and Wighteone stably bind within the CTSL active site. In human renal cells, KG attenuated high glucose and high lipid induced inflammatory and injury responses. Collectively, these findings identify new CTSL inhibitors with therapeutic potential for renal injury and underscore the utility of AI-assisted strategies in accelerating drug discovery.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Beijing Key Laboratory of Diabetes Research and Care, Beijing Diabetes Institute, Beijing Tongren Hospital, Capital Medical University, Beijing, China.
- Laboratory for Clinical Medicine, Capital Medical University, Beijing, China.
ORCID-Profile: Jin-Kui Yang
Förderung
- National Natural Science Foundation of China
- the Scientific Project of Beijing’s Municipal Science & Technology Commission
- Beijing Municipal Administration of Hospitals Clinical Medicine Development of Special Funding Support Programme
- Training Fund for Open Projects at Clinical Institutes and Departments of Capital Medical University
Zitieren
APA
Ma, F., Li, Q., Zhou, S., Li, X., & Yang, J. K. (2026). AI-guided identification of natural CTSL inhibitors with therapeutic potential for renal injury. PLOS Computational Biology, 22(7), e1014464. https://doi.org/10.1371/journal.pcbi.1014464
Vancouver
Ma F, Li Q, Zhou S, Li X, Yang JK. AI-guided identification of natural CTSL inhibitors with therapeutic potential for renal injury. PLOS Computational Biology. 2026;22(7):e1014464. doi:10.1371/journal.pcbi.1014464
BibTeX
@article{Ma2026,
author = {Ma, Feier and Li, Qi and Zhou, Sirui and Li, Xiaoya and Yang, Jin-Kui},
title = {AI-guided identification of natural CTSL inhibitors with therapeutic potential for renal injury},
journal = {PLOS Computational Biology},
year = {2026},
volume = {22},
number = {7},
pages = {e1014464},
doi = {10.1371/journal.pcbi.1014464}
}
EUVIMED