EUVIMEDEUVIMED entdecken
Crossref

A two-stage stacking machine learning framework for predicting metal oxide nanoparticle toxicity and biological outcomes

Tugba Muhlise Okyay, Macit Koldas

NanoImpact · 2026-04 · 42 · 100633

DOI: 10.1016/j.impact.2026.100633 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NanoImpact, 2026-04. Verfasst von Tugba Muhlise Okyay und 1 weiteren Autor:innen. Beteiligte Einrichtung: Medical Biochemistry, University of Health Sciences, 34956 Istanbul, Turkey. Electronic address: tugba.okyay@sbu.edu.tr. Hauptthemen laut MEDLINE: Oxides, Metal Nanoparticles, Machine Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 52 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Metal oxide nanoparticles (MONPs) raise growing cytotoxicity concerns, yet experimental assessment requires multiple time-consuming biological assays. We developed a leakage-free two-stage machine learning framework predicting MONP toxicity and biological endpoints from physicochemical features. In Stage 1, a stacking ensemble (ExtraTrees + GradientBoosting + RandomForest + HistGradientBoosting → LogisticRegression meta-learner) trained on 304 KONA dataset records using out-of-fold (OOF) probability generation achieved Accuracy = 0.87 and ROC-AUC = 0.91 on held-out data, and ROC-AUC = 0.76 on an independent external validation set. A three-way ablation study revealed that IC50-derived toxicity class substantially improves Stage 2 regression (ΔR2 = +0.22 for ROS; +0.12 for Membrane Damage), while out-of-fold-predicted class provides negligible improvement with toxicity classification. In Stage 2, ordinal classification (Low/Moderate/High) with literature-based thresholds replaced continuous regression. BaggingClassifier and GradientBoostingClassifier achieved AUC = 0.82-0.86 across four endpoints. Grouped permutation importance and LIME identified nanoparticle composition, surface chemistry, core size, and surface area as dominant predictors, consistent with ion dissolution and ROS-mediated mechanisms. This framework reduces experimental burden while providing interpretable, generalizable MONP cytotoxicity predictions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

OxidesMetal NanoparticlesMachine LearningBoosting Machine Learning AlgorithmsClassification AlgorithmsPredictive Learning ModelsPrediction AlgorithmsHumansRandom ForestAnimals

Stichwörter der Autor:innen

AILIMEMachine learningMetal-oxide nanoparticlesNanotoxicitySHAPStacking meta-learner

Substanzen

Oxides

Autor:innen und Institutionen

  • Medical Biochemistry, University of Health Sciences, 34956 Istanbul, Turkey. Electronic address: tugba.okyay@sbu.edu.tr.
  • Medical Biochemistry, University of Health Sciences, 34956 Istanbul, Turkey; Department of Medical Biochemistry, Health Science University Istanbul Haseki Training and Research Hospital, Istanbul, Turkey.

Zitieren

APA

Okyay, T. M., & Koldas, M. (2026). A two-stage stacking machine learning framework for predicting metal oxide nanoparticle toxicity and biological outcomes. NanoImpact, 42, 100633. https://doi.org/10.1016/j.impact.2026.100633

Vancouver

Okyay TM, Koldas M. A two-stage stacking machine learning framework for predicting metal oxide nanoparticle toxicity and biological outcomes. NanoImpact. 2026;42:100633. doi:10.1016/j.impact.2026.100633

BibTeX
@article{Okyay2026,
  author = {Okyay, Tugba Muhlise and Koldas, Macit},
  title = {A two-stage stacking machine learning framework for predicting metal oxide nanoparticle toxicity and biological outcomes},
  journal = {NanoImpact},
  year = {2026},
  volume = {42},
  pages = {100633},
  doi = {10.1016/j.impact.2026.100633}
}
Kostenlos starten →