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: Jul 4, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

DICTrank Is a Reliable Dataset for Cardiotoxicity Prediction Using Machine Learning Methods.

Yanyan Qu1,2, Ting Li1, Zhichao Liu3

  • 1US Food and Drug Administration, National Center for Toxicological Research, Jefferson, Arkansas 72079, United States.

Chemical Research in Toxicology
|March 27, 2025
PubMed
Summary

Related Concept Videos

Hazard Ratio01:12

Hazard Ratio

The hazard ratio (HR) is a widely used measure in clinical trials to compare the risk of events, such as death or disease recurrence, between two groups over time. It reflects the ratio of hazard rates—the instantaneous risk of the event occurring—between a treatment group and a control group. This measure provides valuable insights into the relative effectiveness of a treatment by assessing how the risk of an event differs between the two groups.
For example, in a clinical trial evaluating a...

You might also read

Related Articles

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

Sort by
Same author

Integrating AI in Medicinal Chemistry for Accelerated Drug Discovery: A Comprehensive SAR (CSAR) Optimization Strategy and Discovery of Potent ALDH3A1 Inhibitors.

Journal of medicinal chemistry·2026
Same author

SARS-CoV-2 Spike Protein's Structural Dynamics Affect the Activity of the Bebtelovimab Antibody.

Journal of chemical information and modeling·2026
Same author

Discovery of Perilloxazole Pseudo-Natural Products Yields a New Sterol Biosynthesis Inhibitor Chemotype.

Angewandte Chemie (International ed. in English)·2026
Same author

Integrating in vitro and in silico NAMs for enhanced prediction of drug-induced liver injury.

Drug discovery today·2026
Same author

Future climate scenarios drive the northward shift and habitat loss of <i>Marssonina coronaria</i> in Shaanxi Province, China's core apple-growing area.

Plant disease·2026
Same author

Pathologic complete response after neoadjuvant immunochemotherapy: Persistent recurrence risk highlights the need for stratified management.

The Journal of thoracic and cardiovascular surgery·2026

This study shows that the DICTrank dataset, combined with machine learning, effectively predicts drug-induced cardiotoxicity (DICT). Logistic Regression and XGBoost models performed best, offering insights into DICT mechanisms for safer drug development.

Area of Science:

  • Pharmacology and Toxicology
  • Computational Chemistry
  • Drug Development

Background:

  • Drug-induced cardiotoxicity (DICT) poses a significant risk in drug development and public health.
  • Current predictive models often focus on single mechanisms (e.g., hERG) due to limited datasets, hindering comprehensive DICT assessment.
  • The DICTrank dataset, derived from FDA drug labels, represents the largest collection for evaluating overall human cardiotoxicity liability.

Purpose of the Study:

  • To evaluate the utility of the DICTrank dataset for quantitative structure-activity relationship (QSAR) modeling of DICT.
  • To compare the performance of five distinct machine learning methods in predicting DICT risk.
  • To identify key drug properties contributing to DICT through feature analysis.

Main Methods:

Related Experiment Videos

Last Updated: Jul 4, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

  • Utilized DICTrank dataset comprising human cardiotoxicity data from FDA drug labels.
  • Applied five machine learning algorithms: Logistic Regression (LR), K-Nearest Neighbors, Support Vector Machines, Random Forest (RF), and XGBoost.
  • Trained models on drugs approved before 2005 to predict DICT risk for drugs approved thereafter, simulating real-world application.

Main Results:

  • Logistic Regression (LR) and XGBoost models demonstrated the highest predictive performance using the DICTrank dataset.
  • Feature analysis revealed that drug properties related to structural/topological descriptors, polarizability, and electronegativity significantly contribute to DICT.
  • Model performance varied across different therapeutic categories, indicating a need for tailored predictive approaches.

Conclusions:

  • The DICTrank dataset is robust and reliable for machine learning-based cardiotoxicity prediction in humans.
  • The study highlights the importance of comprehensive datasets and advanced machine learning for accurate DICT assessment.
  • Insights into DICT mechanisms derived from feature analysis can guide the development of safer therapeutics.