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 29, 2025

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

1.2K

A QSAR study for predicting malformation in zebrafish embryo.

Mahsa Daneshmand1, Jamileh SalarAmoli1, Negin BaghbanZadeh2

  • 1Department of Comparative Bioscience, Faculty of Veterinary Medicine, University of Tehran, Tehran, Iran.

Toxicology Mechanisms and Methods
|April 8, 2024
PubMed
Summary

This study developed a quantitative structure-activity relationship (QSAR) model to predict developmental malformations using computational methods. Gradient boosting achieved 78% accuracy, identifying key physicochemical properties influencing malformations.

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

Potential for near-term AI risks to evolve into existential threats in healthcare.

BMJ health & care informatics·2025
Same author

Fully robotic social environment for teaching and practicing affective interaction: Case of teaching emotion recognition skills to children with autism spectrum disorder, a pilot study.

Frontiers in robotics and AI·2023
See all related articles

Area of Science:

  • Computational toxicology
  • cheminformatics
  • Predictive modeling

Background:

  • Developmental toxicity tests are costly, time-consuming, and animal-intensive.
  • Simplifying the analysis of developmental endpoints, like malformations, is crucial.
  • In silico models offer a promising alternative for assessing developmental toxicity.

Purpose of the Study:

  • To develop a quantitative structure-activity relationship (QSAR) model for predicting developmental malformations.
  • To identify the optimal machine learning algorithm for malformation prediction.
  • To determine the most influential physicochemical properties associated with malformations.

Main Methods:

  • A dataset from the COMPTOX database was utilized.
  • Physicochemical properties (descriptors) were computed using Mordred and RDKit.
Keywords:
Malformationdevelopmental toxicitygradient boostingin silico testpredictive toxicology

More Related Videos

Zebrafish Larvae as a Model to Evaluate Potential Radiosensitizers or Protectors
04:53

Zebrafish Larvae as a Model to Evaluate Potential Radiosensitizers or Protectors

Published on: August 25, 2022

1.5K
Assessing Teratogenic Changes in a Zebrafish Model of Fetal Alcohol Exposure
10:07

Assessing Teratogenic Changes in a Zebrafish Model of Fetal Alcohol Exposure

Published on: March 20, 2012

26.3K

Related Experiment Videos

Last Updated: Jun 29, 2025

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

1.2K
Zebrafish Larvae as a Model to Evaluate Potential Radiosensitizers or Protectors
04:53

Zebrafish Larvae as a Model to Evaluate Potential Radiosensitizers or Protectors

Published on: August 25, 2022

1.5K
Assessing Teratogenic Changes in a Zebrafish Model of Fetal Alcohol Exposure
10:07

Assessing Teratogenic Changes in a Zebrafish Model of Fetal Alcohol Exposure

Published on: March 20, 2012

26.3K
  • Gradient boosting (GBM) and logistic regression (LR), alongside deep learning models (MLP, NNs), were trained and validated.

    • Main Results:

    • A set of descriptors yielding 78% area under the curve (AUC) was identified as optimal.
    • The gradient boosting model (GBM) demonstrated the highest predictive power at 78%.
    • Key descriptors directly implicated in the mechanism of malformation were identified.

    Conclusions:

    • Gradient boosting (GBM) emerged as the superior algorithm for predicting malformations, based on Matthew's correlation coefficient (MCC) and balanced accuracy (BAC).
    • The identified physicochemical properties provide insights into the underlying mechanisms of developmental malformations.
    • This QSAR model offers a more efficient and potentially reduced-animal testing approach for developmental toxicity assessment.