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 18, 2025

Author Spotlight: High-Throughput Toxicity Screening Using Zebrafish Embryo Startle Response Assay
06:25

Author Spotlight: High-Throughput Toxicity Screening Using Zebrafish Embryo Startle Response Assay

Published on: January 12, 2024

1.4K

A novel multitask learning algorithm for tasks with distinct chemical space: zebrafish toxicity prediction as an

Run-Hsin Lin1,2, Pinpin Lin3, Chia-Chi Wang4

  • 1Institute of Biotechnology and Pharmaceutical Research, National Health Research Institutes, Miaoli County, 35053, Taiwan.

Journal of Cheminformatics
|August 2, 2024
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

Structural Modification and Development of <i>N</i>-(1,2,3,4-Tetrahydro-3-isoquinolinylmethyl)benzamide, BPR1M492, as a Potent and Rapid-Onset Opioid Analgesic with Reduced Withdrawal Symptoms.

Journal of medicinal chemistry·2026
Same author

Evaluating Thiram-Induced Embryotoxicity Using Integrated In Silico, In Vitro, and Transcriptomic Approaches.

Environmental toxicology·2026
Same author

Integrating machine learning and protein-ligand interaction profiling for the discovery of METTL3 inhibitors.

Scientific reports·2025
Same author

Population Cohort-Validated PM<sub>2.5</sub>-Induced Gene Signatures: A Machine Learning Approach to Individual Exposure Prediction.

Toxics·2025
Same author

Fipronil Triggers Immunotoxicity Through Reactive Oxygen Species-Driven Mitochondrial Apoptosis in Thymocytes.

Toxics·2025
Same author

Orally Bioavailable and Site-Selective Covalent STING Inhibitor Derived from a Macrocyclic Marine Diterpenoid.

Journal of medicinal chemistry·2025

A new multitask learning method, MTForestNet, effectively predicts chemical effects despite data scarcity and distinct chemical spaces. This approach improves zebrafish toxicity predictions and can reduce animal testing.

Area of Science:

  • Cheminformatics
  • Computational Toxicology
  • Machine Learning

Background:

  • Data scarcity hinders chemical effect prediction model development.
  • Existing multitask learning methods struggle with datasets from distinct chemical spaces.
  • Conventional methods require extensive labeled data, which is often unavailable.

Purpose of the Study:

  • To introduce MTForestNet, a novel multitask learning algorithm designed for data scarcity and distinct chemical spaces.
  • To develop accurate zebrafish toxicity prediction models using MTForestNet.
  • To demonstrate the method's ability to improve predictions and reduce animal testing.

Main Methods:

  • Developed MTForestNet, a progressive network of random forest classifiers.
  • Utilized 48 zebrafish toxicity datasets, including tasks with unique chemical spaces.
Keywords:
Chemical spaceChemical toxicityDevelopmental toxicityMultitask learningZebrafish

More Related Videos

Automated High-throughput Behavioral Analyses in Zebrafish Larvae
09:28

Automated High-throughput Behavioral Analyses in Zebrafish Larvae

Published on: July 4, 2013

15.2K
Small Molecule Screening and Toxicity Testing in Early-stage Zebrafish Larvae
02:52

Small Molecule Screening and Toxicity Testing in Early-stage Zebrafish Larvae

Published on: March 7, 2025

1.1K

Related Experiment Videos

Last Updated: Jun 18, 2025

Author Spotlight: High-Throughput Toxicity Screening Using Zebrafish Embryo Startle Response Assay
06:25

Author Spotlight: High-Throughput Toxicity Screening Using Zebrafish Embryo Startle Response Assay

Published on: January 12, 2024

1.4K
Automated High-throughput Behavioral Analyses in Zebrafish Larvae
09:28

Automated High-throughput Behavioral Analyses in Zebrafish Larvae

Published on: July 4, 2013

15.2K
Small Molecule Screening and Toxicity Testing in Early-stage Zebrafish Larvae
02:52

Small Molecule Screening and Toxicity Testing in Early-stage Zebrafish Larvae

Published on: March 7, 2025

1.1K
  • Evaluated MTForestNet against single-task and conventional multitask learning methods.

    • Main Results:

    • MTForestNet achieved a high area under the receiver operating characteristic curve (AUC) of 0.911 in independent tests.
    • The model outperformed existing single-task and multitask approaches.
    • Predicted toxicity strongly correlated with experimental data and improved developmental toxicity predictions.

    Conclusions:

    • MTForestNet effectively addresses data scarcity and distinct chemical space challenges in multitask learning.
    • The developed zebrafish toxicity models offer a promising alternative to animal testing.
    • MTForestNet is applicable to various cheminformatics tasks with heterogeneous datasets.