Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 27, 2026

Multimodal Analysis of Microplastics in Drinking Water using a Silicon Nanomembrane Analysis Pipeline
09:10

Multimodal Analysis of Microplastics in Drinking Water using a Silicon Nanomembrane Analysis Pipeline

Published on: June 13, 2025

Decoding silica nanoparticle toxicity: integrating machine learning, feature importance, rule extraction, and

Roni Romano1, Alexander Barbul1, Rafi Korenstein1

  • 1Department of Physiology and Pharmacology, Gray Faculty of Medical and Health Sciences, Tel-Aviv University, Tel-Aviv, Israel.

Nanotoxicology
|June 25, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Physician adoption patterns of AI-driven clinical decision support systems in urinary tract infection management.

Scientific reports·2026
Same author

Artificial stone dust affects oxidative stress and epithelial barrier in CALU 3 cells.

Experimental lung research·2025
Same author

AI driven decision support reduces antibiotic mismatches and inappropriate use in outpatient urinary tract infections.

NPJ digital medicine·2025
Same author

Rapid identification of in vitro cell toxicity using an electrochemical membrane screening platform.

Bioelectrochemistry (Amsterdam, Netherlands)·2023
Same author

Exploiting endocytosis for transfection of mRNA for cytoplasmatic delivery using cationic gold nanoparticles.

Frontiers in immunology·2023
Same author

Detection and estimating the blood accumulation volume of brain hemorrhage in a human anatomical skull using a RF single coil.

PeerJ·2020

Machine learning models predict silica nanoparticle (SiNP) toxicity by analyzing physicochemical properties. SiNP-OH showed higher adsorption and toxicity, suggesting adsorption contributes to nanoparticle safety concerns.

Area of Science:

  • Nanotoxicology
  • Computational Toxicology
  • Materials Science

Background:

  • Nanoparticle toxicity assessment is complex, requiring advanced methods to analyze large datasets.
  • Machine learning (ML) offers a promising approach to identify predictive features and toxicity rules for nanoparticles.
  • Silica nanoparticles (SiNPs) are widely used, necessitating a thorough understanding of their toxicological profiles.

Purpose of the Study:

  • To investigate the relationships between SiNP physicochemical properties, experimental parameters, and in vitro toxicity.
  • To develop and compare ML models for predicting SiNP toxicity.
  • To elucidate the mechanisms underlying SiNP toxicity, including adsorption and uptake.

Main Methods:

  • Data compilation from literature, databases, and in-house experiments.
Keywords:
Concentration metricsDecision Treescytotoxicitynanoparticle adsorptionsilica nanoparticles

Related Experiment Videos

Last Updated: Jun 27, 2026

Multimodal Analysis of Microplastics in Drinking Water using a Silicon Nanomembrane Analysis Pipeline
09:10

Multimodal Analysis of Microplastics in Drinking Water using a Silicon Nanomembrane Analysis Pipeline

Published on: June 13, 2025

  • Application of the Balanced Fitted Dose-Response approach for data balancing.
  • Utilizing the CatBoost algorithm and Decision Tree models for toxicity prediction.
  • Feature importance analysis using Catboost Shapley values.
  • Rule extraction from decision-tree models.
  • Experimental validation using imaging flow cytometry for adsorption and uptake studies.

    • Main Results:

    • The CatBoost algorithm demonstrated superior performance over Decision Tree models in predicting SiNP toxicity.
    • Key features influencing SiNP toxicity were identified, with Mass, Total Surface Area, and Serum concentration being most significant.
    • Surface-unmodified SiNPs-OH exhibited higher toxicity compared to surface-modified SiNPs-NH2 and SiNPs-COOH.
    • SiNPs-OH showed significantly higher adsorption to alveolar macrophages but lower uptake compared to modified SiNPs.

    Conclusions:

    • Machine learning effectively predicts SiNP toxicity based on physicochemical properties and experimental conditions.
    • Adsorption of SiNPs to cell membranes, in addition to internalization, plays a crucial role in nanoparticle toxicity.
    • This study provides valuable insights into the mechanisms of nanoparticle safety and informs future risk assessments.