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: Aug 25, 2025

Generation of Transgenic Rats using a Lentiviral Vector Approach

Generation of Transgenic Rats using a Lentiviral Vector Approach

Published on: May 17, 2020

Machine learning models for rat multigeneration reproductive toxicity prediction.

Jie Liu¹, Wenjing Guo¹, Fan Dong¹

¹National Center for Toxicological Research, U.S. Food and Drug Administration, Jefferson, AR, United States.

Frontiers in Pharmacology

|October 14, 2022

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

Hydrogen Radical-Mediated Nitric Oxide Reduction to Ammonia Over Synergistic Pd<sup>0</sup>/Pd<sup>2+</sup> Dual Sites.

Angewandte Chemie (International ed. in English)·2026

Same author

Simultaneous CO<sub>2</sub> and NO Conversion by Spatially Locating Dual Photocatalytic Sites on a Microporous Polymer.

Environmental science & technology·2026

Same author

A Missing Source of Atmospheric NO<sub>2</sub><sup>-</sup>: Heterogeneous Dark Transformation of PAN on Industrial Mineral Dust.

Environmental science & technology·2026

Same author

Surface Energy Modulation of NiO<sub><i>x</i></sub> through In Situ Click-Cross-Linked Networks for Air-Processed Flexible Blue Perovskite Light-Emitting Diodes.

The journal of physical chemistry. A·2026

Same author

RUNX2 drives adenoma-to-carcinoma transition in colon cancer.

Cell death & disease·2026

Same author

Abnormal Activation and Connection in Middle Frontal Gyrus: A Potential Imaging Feature for Facial Synkinesis Comorbid Depression.

Depression and anxiety·2026

Machine learning models can predict chemical reproductive toxicity, offering a faster, cheaper alternative to animal testing. Consensus models improve prediction accuracy, aiding in screening chemicals before in vivo studies.

Area of Science:

Environmental Toxicology
Computational Toxicology
Risk Assessment

Background:

Assessing chemical reproductive toxicity is crucial for environmental and industrial safety.
Traditional animal testing for reproductive toxicity is time-consuming and costly.
Machine learning (ML) presents a promising alternative for efficient toxicity evaluation.

Purpose of the Study:

To develop and validate ML models for predicting rat multigeneration reproductive toxicity.
To evaluate the performance of individual and consensus ML models.
To assess the utility of ML in screening chemicals for reproductive hazards.

Main Methods:

Curated rat reproductive toxicity data for 275 chemicals from ToxRefDB.
Developed predictive models using seven ML algorithms and a consensus approach.

Keywords:

consensus model machine learning molecular descriptor multigeneration reproductive toxicity toxicity prediction

More Related Videos

A Preterm Rat Model for Pain Studies

A Preterm Rat Model for Pain Studies

Published on: February 9, 2024

Establishment of Rat Models Mimicking Gender-affirming Hormone Therapies

Establishment of Rat Models Mimicking Gender-affirming Hormone Therapies

Published on: January 10, 2025

Related Experiment Videos

Last Updated: Aug 25, 2025

Generation of Transgenic Rats using a Lentiviral Vector Approach

Generation of Transgenic Rats using a Lentiviral Vector Approach

Published on: May 17, 2020

A Preterm Rat Model for Pain Studies

A Preterm Rat Model for Pain Studies

Published on: February 9, 2024

Establishment of Rat Models Mimicking Gender-affirming Hormone Therapies

Establishment of Rat Models Mimicking Gender-affirming Hormone Therapies

Published on: January 10, 2025

Validated models using 5-fold cross-validation and an external dataset from COSMOS and literature.

Main Results:

Balanced accuracy ranged from 58%-65% in cross-validation and 45%-61% in external validation.
Consensus models demonstrated improved predictive performance.
Prediction confidence analysis provided insights for model application.

Conclusions:

ML models, particularly consensus models, show potential for assessing chemical reproductive toxicity.
These models can help prioritize chemicals for further testing, saving resources.
ML offers a viable alternative to traditional methods for reproductive toxicity screening.