Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Drug Toxicity: Allergic Reactions

Drug Toxicity: Allergic Reactions

Drug-related allergies are immune-mediated responses triggered by the administration of pharmacological agents. These hypersensitivity reactions are classified based on the immune mechanisms involved. The four primary types—Type I, II, III, and IV—are mediated by different immunological pathways and exhibit distinct clinical manifestations.Type I Hypersensitivity/ IgE-Mediated Reactions: Immunoglobulin E (IgE) immediately mediates Type I hypersensitivity reactions. Upon initial...

You might also read

Related Articles

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

Sort by

Same author

Highlighting best practices to advance next-generation risk assessment of cosmetic ingredients.

NAM journal·2026

Same author

Validation of the Epi2SensA Method Using the EpiDerm™ Model for Skin Sensitization Testing Under OECD TG442D.

Toxics·2026

Same author

Development of a Data-Driven Prediction Model of Adverse Drug Reactions Using Large-Scale Medical Information and Machine Learning.

Biological & pharmaceutical bulletin·2026

Same author

Resonant Tunneling Oscillators Based on WSe<sub>2</sub>/<i>h</i>-BN/WSe<sub>2</sub> van der Waals Double Quantum Wells.

Nano letters·2025

Same author

CYP1B1- and CYP1A1-Template systems and their application to metabolism and inhibition.

Genes and environment : the official journal of the Japanese Environmental Mutagen Society·2025

Same author

Germline or somatic mutations in genes encoding microRNAs as biomarkers predicting the risk of adult T-cell leukemia/lymphoma.

Journal of human genetics·2025

Search research articles

Related Experiment Video

Updated: Apr 19, 2026

A Mouse Ear Model for Allergic Contact Dermatitis Evaluation

A Mouse Ear Model for Allergic Contact Dermatitis Evaluation

Published on: March 24, 2023

ExSERA: The explainable machine learning model for skin sensitization risk assessment.

Kaori Ambe¹, Kei Kinoshita², Juri Tokunaga²

¹Graduate School of Data Science, Nagoya City University, Nagoya, Japan; Department of Regulatory Science, Graduate School of Pharmaceutical Sciences, Nagoya City University, Nagoya, Japan.

Regulatory Toxicology and Pharmacology : RTP

|April 17, 2026

Summary

This study introduces ExSERA, an interpretable machine learning model for skin sensitization assessment, offering a transparent alternative to animal testing. The model accurately predicts toxicity, supporting regulatory use in chemical safety evaluations.

Keywords:

Defined approach for skin sensitization Explainable machine learning Murine local lymph node assay New approach methodologies Risk assessment Shapley additive explanations

More Related Videos

Chemical-Induced Skin Carcinogenesis Model Using Dimethylbenz[a]Anthracene and 12-O-Tetradecanoyl Phorbol-13-Acetate DMBA-TPA

Chemical-Induced Skin Carcinogenesis Model Using Dimethylbenz[a]Anthracene and 12-O-Tetradecanoyl Phorbol-13-Acetate DMBA-TPA

Published on: December 19, 2019

Cultivating a Three-dimensional Reconstructed Human Epidermis at a Large Scale

Cultivating a Three-dimensional Reconstructed Human Epidermis at a Large Scale

Published on: May 28, 2021

Related Experiment Videos

Last Updated: Apr 19, 2026

A Mouse Ear Model for Allergic Contact Dermatitis Evaluation

A Mouse Ear Model for Allergic Contact Dermatitis Evaluation

Published on: March 24, 2023

Chemical-Induced Skin Carcinogenesis Model Using Dimethylbenz[a]Anthracene and 12-O-Tetradecanoyl Phorbol-13-Acetate DMBA-TPA

Chemical-Induced Skin Carcinogenesis Model Using Dimethylbenz[a]Anthracene and 12-O-Tetradecanoyl Phorbol-13-Acetate DMBA-TPA

Published on: December 19, 2019

Cultivating a Three-dimensional Reconstructed Human Epidermis at a Large Scale

Cultivating a Three-dimensional Reconstructed Human Epidermis at a Large Scale

Published on: May 28, 2021

Area of Science:

Toxicology
Computational Chemistry
Regulatory Science

Background:

Machine learning (ML) models offer alternatives to animal testing for toxicity assessment.
Regulatory acceptance requires ML models to be transparent and interpretable.

Purpose of the Study:

Develop an explainable ML model for skin sensitization risk assessment (ExSERA).
Predict murine Local Lymph Node Assay (LLNA) EC3 values, indicating skin sensitization potency.

Main Methods:

Trained an XGBoost regression model on 154 substances (OECD TG 497).
Incorporated 21 variables: in vitro assay results (DPRA, KeratinoSens™, h-CLAT), molecular descriptors, and structural alerts.
Externally validated with 38 substances from Cosmetics Europe database.

Main Results:

80% of internal and 65% of external validation predictions were within a five-fold range of measured LLNA EC3 values.
Shapley Additive exPlanations identified in vitro assays as key predictors.
Higher toxic activity correlated with stronger predicted sensitization.

Conclusions:

ExSERA is an interpretable ML model for skin sensitization risk assessment.
The model shows potential for regulatory application as a defined approach.
It aligns with mechanistic understanding of skin sensitization.