EUVIMEDEUVIMED entdecken
Crossref

Machine learning-driven identification of pan-PI3K inhibitors: A hybrid virtual screening approach combining naïve Bayesian classification, pharmacophore modeling, and consensus scoring-based molecular docking

Li Yu, Shuo Qiu, Leyan Zhao, Haixin Sun, Jingyu Zhu

Biophysical Chemistry · 2026-10 · 337 · 107679

DOI: 10.1016/j.bpc.2026.107679 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biophysical Chemistry, 2026-10. Verfasst von Li Yu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Inspection and Testing Certification, Changzhou Vocational Institute of Engineering, Changzhou 213164, Jiangsu, China. Hauptthemen laut MEDLINE: Molecular Docking Simulation, Phosphoinositide-3 Kinase Inhibitors, Machine Learning, Phosphatidylinositol 3-Kinases. Die Arbeit nennt 96 Literaturangaben. Gefördert von: Changzhou Vocational Institute of Engineering.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The phosphatidylinositol 3-kinase (PI3K) pathway is a vital intracellular signaling cascade that plays a key role in cancer cell survival, angiogenesis, and metastasis. Consequently, PI3K has been a primary target for therapeutic inhibition in the treatment of various malignancies. Accumulating studies indicate that targeting multiple isoforms of PI3K may enhance antitumor activity. The advancement of pan-PI3K inhibitors for cancer treatment offers a promising research and development opportunity. This study introduces a machine learning-based virtual screening (VS) method that combines a Naïve Bayesian classification model employing molecular fingerprints and descriptors, alongside a pharmacophore model and consensus scoring-based molecular docking, to discover new pan-PI3K inhibitors. The VS method was validated for its strong predictive accuracy by successfully identifying the commercially available pan-PI3K inhibitor copanlisib. The hybrid VS strategy was applied to the SPECS database, leading to the discovery of several promising PI3K inhibitor compounds. The machine learning-based VS approach is expected to offer meaningful insights and a practical framework for discovering novel PI3K inhibitors.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Molecular Docking SimulationPhosphoinositide-3 Kinase InhibitorsMachine LearningPhosphatidylinositol 3-KinasesProtein Kinase InhibitorsBayes TheoremPharmacophoreHumans

Stichwörter der Autor:innen

Common feature pharmacophoreMolecular dockingNaïve Bayesian classificationPan-PI3K inhibitorVirtual screening

Substanzen

Phosphoinositide-3 Kinase InhibitorsPhosphatidylinositol 3-KinasesProtein Kinase Inhibitors

Autor:innen und Institutionen

  • School of Inspection and Testing Certification, Changzhou Vocational Institute of Engineering, Changzhou 213164, Jiangsu, China.
  • School of Life Sciences and Health Engineering, Jiangnan University, Wuxi 214122, Jiangsu, China.
  • School of Life Sciences and Health Engineering, Jiangnan University, Wuxi 214122, Jiangsu, China.. Electronic address: jingyuzhu@jiangnan.edu.cn.

Förderung

  • Changzhou Vocational Institute of Engineering

Zitieren

APA

Yu, L., Qiu, S., Zhao, L., Sun, H., & Zhu, J. (2026). Machine learning-driven identification of pan-PI3K inhibitors: A hybrid virtual screening approach combining naïve Bayesian classification, pharmacophore modeling, and consensus scoring-based molecular docking. Biophysical Chemistry, 337, 107679. https://doi.org/10.1016/j.bpc.2026.107679

Vancouver

Yu L, Qiu S, Zhao L, Sun H, Zhu J. Machine learning-driven identification of pan-PI3K inhibitors: A hybrid virtual screening approach combining naïve Bayesian classification, pharmacophore modeling, and consensus scoring-based molecular docking. Biophysical Chemistry. 2026;337:107679. doi:10.1016/j.bpc.2026.107679

BibTeX
@article{Yu2026,
  author = {Yu, Li and Qiu, Shuo and Zhao, Leyan and Sun, Haixin and Zhu, Jingyu},
  title = {Machine learning-driven identification of pan-PI3K inhibitors: A hybrid virtual screening approach combining naïve Bayesian classification, pharmacophore modeling, and consensus scoring-based molecular docking},
  journal = {Biophysical Chemistry},
  year = {2026},
  volume = {337},
  pages = {107679},
  doi = {10.1016/j.bpc.2026.107679}
}
Kostenlos starten →