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

Search research articles

Related Experiment Video

Updated: Mar 7, 2026

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

Integrating Multiview Information for Enhanced Deep Learning-Based Acute Dermal Toxicity Prediction.

Wei Lin¹, Chi Chung Alan Fung^1,2

¹Department of Neuroscience, College of Biomedicine, City University of Hong Kong, Tat Chee Avenue, Kowloon Tong, Kowloon, Hong Kong 999077, China.

Journal of Chemical Information and Modeling

|March 6, 2026

Summary

This summary is machine-generated.

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

Rethinking the Masking Strategy for Pretraining Molecular Graphs from a Data-Centric View.

ACS omega·2024

Same author

Competition on presynaptic resources enhances the discrimination of interfering memories.

PNAS nexus·2023

Same author

Orchestrated ensemble activities constitute a hippocampal memory engram.

Nature communications·2019

Same author

Transient and Persistent UP States during Slow-wave Oscillation and their Implications for Cell-Assembly Dynamics.

Scientific reports·2018

MVIToxNet enhances drug development by accurately predicting dermal toxicity using multi-view molecular data. This novel deep learning approach improves safety assessments, reducing reliance on animal testing.

Area of Science:

Computational chemistry
Toxicology
Machine learning

Background:

Accurate prediction of acute dermal toxicity is crucial for drug development.
Existing deep learning models often fail to leverage comprehensive molecular information.
Animal testing for toxicity is costly and ethically problematic.

Purpose of the Study:

To develop a novel deep learning model, MVIToxNet, for accurate acute dermal toxicity prediction.
To integrate multiview molecular features, including fingerprints and SMILES sequences, into a unified model.
To address challenges posed by small and imbalanced datasets through a weighted model averaging strategy.

Main Methods:

MVIToxNet integrates molecular fingerprints and SMILES sequences, capturing character-level, atom-level, and substructural information via byte-pair encoding.

Related Experiment Videos

Last Updated: Mar 7, 2026

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

A weighted model averaging approach combines multiple models based on validation performance to improve generalization.

The model was evaluated on acute dermal toxicity prediction tasks.

Main Results:

MVIToxNet significantly outperformed existing baseline models in acute dermal toxicity prediction.
The integration of multiview features proved effective for enhancing predictive accuracy.
The weighted model averaging strategy improved model generalization on test sets.

Conclusions:

MVIToxNet demonstrates the efficacy of utilizing multiview molecular features for toxicity prediction.
The proposed weighted model averaging strategy enhances model robustness, especially with limited data.
This data-driven approach shows promise for optimizing model design in computational toxicology.