EUVIMEDEUVIMED entdecken
Crossref

Machine Learning‐Based QSAR, Molecular Docking, and Molecular Dynamics Simulations of Pyrazole Derivatives Targeting EGFR

Prerana Sanas, Trupti Chitre, Seemarani Pawar, Mohd Usman Mohd Siddique

ChemistrySelect · 2026-11 · 11 (42)

DOI: 10.1002/slct.75119 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ChemistrySelect, online erschienen am 10.11.2026. Verfasst von Prerana Sanas und 3 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cancer is one of the deadliest diseases worldwide, with lung cancer being a major contributor to cancer‐related mortality due to its late diagnosis, aggressive progression, and limited therapeutic outcomes. Aberrant activation of the epidermal growth factor receptor plays a central role in the progression of NSCLC by promoting uncontrolled cellular proliferation, survival, and metastasis. This study investigates the antitumor potential of the pyrazole‐based pharmacophore by using various in silico approaches. The optimal 2D QSAR model, developed using multiple linear regression, demonstrated a strong correlation coefficient ( r 2 = 0.9124) and good internal ( q 2 = 0.8738) and external (pred_ r 2 = 0.4427) predictive abilities. The 3D QSAR model, generated using the KNN molecular field analysis method, yielded a q 2 of 0.8904. Following QSAR modeling, 42 NCEs were shortlisted via ADMET screening, and 34 of these showed strong molecular docking scores with binding energies ranging from −9 to −11 kcal/mol, surpassing the standard drug erlotinib (−7.3 kcal/mol). The top four candidates underwent further toxicity and activity prediction via prediction of activity spectra of substances (PASSs) and ProTOX analyses. The two most promising compounds were subjected to molecular dynamics simulations, where M18 revealed favorable binding free energy and stable interactions over 500‐ns simulations.

Zitieren

APA

Sanas, P., Chitre, T., Pawar, S., & Siddique, M. U. M. (2026). Machine Learning‐Based QSAR, Molecular Docking, and Molecular Dynamics Simulations of Pyrazole Derivatives Targeting EGFR. ChemistrySelect, 11(42). https://doi.org/10.1002/slct.75119

Vancouver

Sanas P, Chitre T, Pawar S, Siddique MUM. Machine Learning‐Based QSAR, Molecular Docking, and Molecular Dynamics Simulations of Pyrazole Derivatives Targeting EGFR. ChemistrySelect. 2026;11(42). doi:10.1002/slct.75119

BibTeX
@article{Sanas2026,
  author = {Sanas, Prerana and Chitre, Trupti and Pawar, Seemarani and Siddique, Mohd Usman Mohd},
  title = {Machine Learning‐Based QSAR, Molecular Docking, and Molecular Dynamics Simulations of Pyrazole Derivatives Targeting EGFR},
  journal = {ChemistrySelect},
  year = {2026},
  volume = {11},
  number = {42},
  doi = {10.1002/slct.75119}
}
Kostenlos starten →