EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine learning-guided identification and simulation-based validation of potent JAK3 inhibitors for cancer therapy

Hailang Wei, Qingyun Wang iD

PLOS One · 2025

DOI: 10.1371/journal.pone.0338777 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Hailang Wei und 1 weiteren Autor:innen. Beteiligte Einrichtung: Taihe Hospital, Affiliated Hospital of Hubei University of Medicine, Shiyan, China. Hauptthemen laut MEDLINE: Janus Kinase 3, Machine Learning, Protein Kinase Inhibitors, Neoplasms. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Janus kinase 3 (JAK3) is a hematopoietic-specific kinase implicated in cytokine signaling and immune dysregulation and has recently been associated with cancer progression. However, selective and potent JAK3 inhibitors remain underdeveloped. In this study, we established a machine learning (ML)-based pipeline to identify novel JAK3 inhibitors with anti-cancer potential. A curated ChEMBL dataset of JAK3 inhibitors was used to train multiple ML classifiers, with the Random Forest model achieving the highest performance (AUC = 0.80, F1-score = 0.92). This model was applied to virtually screen 25,084 ChEMBL compounds, yielding 400 high-confidence candidates (prediction score > 0.9). Docking analysis identified ten top binders (binding affinity ≤ –8.5 kcal/mol), of which three CHEMBL49087, CHEMBL4117527, and CHEMBL50064 exhibited optimal ADMET profiles. These compounds underwent 200 ns molecular dynamics simulations, showing low RMSD (0.10–0.20 nm), stable binding conformations, and preserved protein compactness. MM/GBSA calculations revealed that CHEMBL4117527 displayed the strongest binding free energy (–29.5 kcal/mol), surpassing even the co-crystallized ligand (–17.7 kcal/mol). Our integrative approach combining machine learning, docking, pharmacokinetics, molecular dynamics, and free energy analysis presents a robust computational strategy for JAK3 inhibitor discovery. These findings support CHEMBL4117527 as promising candidates for further experimental evaluation in cancer therapeutics.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Janus Kinase 3Machine LearningProtein Kinase InhibitorsNeoplasmsAntineoplastic AgentsHumansMolecular Docking SimulationMolecular Dynamics Simulation

Substanzen

Janus Kinase 3Protein Kinase InhibitorsJAK3 protein, humanAntineoplastic Agents

Autor:innen und Institutionen

  • Taihe Hospital, Affiliated Hospital of Hubei University of Medicine, Shiyan, China.

ORCID-Profile: Qingyun Wang

Zitieren

APA

Wei, H., & Wang, Q. (2025). Machine learning-guided identification and simulation-based validation of potent JAK3 inhibitors for cancer therapy. PLOS One. https://doi.org/10.1371/journal.pone.0338777

Vancouver

Wei H, Wang Q. Machine learning-guided identification and simulation-based validation of potent JAK3 inhibitors for cancer therapy. PLOS One. 2025. doi:10.1371/journal.pone.0338777

BibTeX
@article{Wei2025,
  author = {Wei, Hailang and Wang, Qingyun},
  title = {Machine learning-guided identification and simulation-based validation of potent JAK3 inhibitors for cancer therapy},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0338777}
}
Kostenlos starten →