EUVIMEDEUVIMED entdecken
Crossref

Machine Learning‐Driven QSAR Modeling of Anticancer Activity from a Rationally Designed Synthetic Flavone Library

Natthanan Vijara, Borwornlak Toopradab, Jantana Yahuafai iD, Taweesak Gulchatchai, Rita Hairani iD, Apinya Patigo, Thanyada Rungrotmongkol iD, Sumrit Wacharasindhu iD, Warinthorn Chavasiri iD, Liyi Shi, Phornphimon Maitarad iD, Ruchuta Ardkhean iD und 1 weitere

ChemMedChem · 2025

DOI: 10.1002/cmdc.202500143 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ChemMedChem, 2025. Verfasst von Natthanan Vijara und 12 weiteren Autor:innen. Beteiligte Einrichtung: Center of Excellence in Natural Products Chemistry, Department of Chemistry, Faculty of Science, Chulalongkorn University, Bangkok, 10330, Thailand. Hauptthemen laut MEDLINE: Quantitative Structure-Activity Relationship, Flavones, Machine Learning, Antineoplastic Agents. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: National Science, Research and Innovation Fund (NSRF), Chulalongkorn University, Chulabhorn Royal Academy.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Flavones, recognized as "privileged scaffolds" in drug discovery, hold significant promise as anticancer agents. This study develops a quantitative structure–activity relationship (QSAR) model to accelerate the optimization of lead compounds. Using pharmacophore modeling against different cancer targets, 89 flavone analogs with varied substitution patterns were designed and synthesized. Biological evaluation revealed promising candidates with enhanced cytotoxicity against breast cancer (MCF‐7) and liver cancer (HepG2) cell lines, along with low toxicity toward normal Vero cells. A machine learning (ML)‐driven QSAR approach was employed, comparing random forest (RF), extreme gradient boosting, and artificial neural network (ANN) models. The RF model exhibits superior performance, achieving R 2 of 0.820 for (MCF‐7 and 0.835 for HepG2, with cross‐validation ( R 2 cv) of 0.744 and 0.770, respectively. Validation using 27 test compounds yielded root mean square error test values of 0.573 (MCF‐7) and 0.563 (HepG2). SHapley Additive exPlanations analysis highlighted key molecular descriptors influencing anticancer activity. This work presents a robust ML‐driven QSAR model that supports the rational design of flavone derivatives and advances the development of selective, potent anticancer agents.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Quantitative Structure-Activity RelationshipFlavonesMachine LearningAntineoplastic AgentsDrug DesignHumansDrug Screening Assays, AntitumorCell ProliferationMolecular StructureHep G2 CellsMCF-7 CellsAnimalsChlorocebus aethiopsDose-Response Relationship, DrugNeural Networks, ComputerVero Cells

Stichwörter der Autor:innen

anticancer activitydrug discoveryflavonesmachine learningquantitative structure–activity relationship

Substanzen

FlavonesAntineoplastic Agentsflavone

Autor:innen und Institutionen

  • Center of Excellence in Natural Products Chemistry, Department of Chemistry, Faculty of Science, Chulalongkorn University, Bangkok, 10330, Thailand.
  • Program in Bioinformatics and Computational Biology, Graduate School, Chulalongkorn University, Bangkok, 10330, Thailand.
  • Center of Excellence in Structural and Computational Biology, Department of Biochemistry, Faculty of Science, Chulalongkorn University, Bangkok, 10330, Thailand.
  • Clinical Research Section, Division of Research and Academic Support, National Cancer Institute, Bangkok, 10400, Thailand.
  • Department of Chemistry, Faculty of Science, Chulalongkorn University, Bangkok, 10330, Thailand.
  • Department of Chemistry, Faculty of Mathematics and Natural Sciences, Mulawarman University, Samarinda, 75123, East Kalimantan, Indonesia.

ORCID-Profile: Jantana Yahuafai, Rita Hairani, Thanyada Rungrotmongkol, Sumrit Wacharasindhu, Warinthorn Chavasiri, Phornphimon Maitarad, Ruchuta Ardkhean, Tanatorn Khotavivattana

Förderung

  • National Science, Research and Innovation Fund (NSRF)
  • Chulalongkorn University
  • Chulabhorn Royal Academy
  • Science and Technology Commission of Shanghai Municipality
  • Emerging Industries Research Institute, Shanghai University (Jiaxing, Zhejiang)

Zitieren

APA

Vijara, N., Toopradab, B., Yahuafai, J., Gulchatchai, T., Hairani, R., Patigo, A., Rungrotmongkol, T., Wacharasindhu, S., Chavasiri, W., Shi, L., Maitarad, P., Ardkhean, R., & Khotavivattana, T. (2025). Machine Learning‐Driven QSAR Modeling of Anticancer Activity from a Rationally Designed Synthetic Flavone Library. ChemMedChem. https://doi.org/10.1002/cmdc.202500143

Vancouver

Vijara N, Toopradab B, Yahuafai J, Gulchatchai T, Hairani R, Patigo A, et al. Machine Learning‐Driven QSAR Modeling of Anticancer Activity from a Rationally Designed Synthetic Flavone Library. ChemMedChem. 2025. doi:10.1002/cmdc.202500143

BibTeX
@article{Vijara2025,
  author = {Vijara, Natthanan and Toopradab, Borwornlak and Yahuafai, Jantana and Gulchatchai, Taweesak and Hairani, Rita and Patigo, Apinya and Rungrotmongkol, Thanyada and Wacharasindhu, Sumrit and Chavasiri, Warinthorn and Shi, Liyi and Maitarad, Phornphimon and Ardkhean, Ruchuta and Khotavivattana, Tanatorn},
  title = {Machine Learning‐Driven QSAR Modeling of Anticancer Activity from a Rationally Designed Synthetic Flavone Library},
  journal = {ChemMedChem},
  year = {2025},
  doi = {10.1002/cmdc.202500143}
}
Kostenlos starten →