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 Concept Videos

Pharmacovigilance01:19

Pharmacovigilance

1.8K
Post-marketing surveillance is a critical component of pharmaceutical regulation, often uncovering unanticipated adverse drug reactions (ADRs) once a drug is widely used over an extended period.
This process, termed pharmacovigilance, aims to detect, evaluate, and minimize harmful effects related to medication use. The data collection for pharmacovigilance depends on spontaneous reporting systems, where healthcare professionals or patients voluntarily report suspected ADRs.
In some cases, there...
1.8K
Protein Networks02:26

Protein Networks

4.6K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.6K
Predicting Molecular Geometry02:27

Predicting Molecular Geometry

46.0K
VSEPR Theory for Determination of Electron Pair Geometries
46.0K
Model Approaches for Pharmacokinetic Data: Compartment Models01:14

Model Approaches for Pharmacokinetic Data: Compartment Models

570
Compartmental analysis is a widely adopted approach to characterizing drug pharmacokinetics. It uses compartment models that conceptualize the body as a collection of reversibly communicating compartments, each representing a group of tissues exhibiting similar drug distribution characteristics. The movement rate of the drug between these compartments is typically described by first-order kinetics.
Two primary types of compartment models are recognized: mammillary and catenary. The more...
570
Model Approaches for Pharmacokinetic Data: Physiological Models01:15

Model Approaches for Pharmacokinetic Data: Physiological Models

279
Physiological models in pharmacokinetics are instrumental in understanding the distribution and elimination of drugs within the body. These models describe the drug concentration within target organs, influenced by factors such as drug uptake, tissue volume, and blood flow. Drug uptake is governed by the partition coefficient, which signifies the drug concentration ratio in tissue to that in the blood. The blood flow rate to a specific tissue is expressed as Qt, and the rate of change in tissue...
279
Ogive Graph01:07

Ogive Graph

6.8K
An ogive graph is sometimes called a cumulative frequency polygon. It is one type of frequency polygon that shows cumulative frequency. In other words, the cumulative percentages are added to the graph from left to right. An ogive graph plots cumulative frequency on the vertical y-axis and class boundaries along the horizontal x-axis. It’s very similar to a histogram; only instead of rectangles, an ogive displays a single point where the top right of the rectangle would be. Creating this...
6.8K

You might also read

Related Articles

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

Sort by
Same author

Structure-based prediction of muscarinic M1/M3 receptor antagonist activity: Curated dataset and scaffold-aware evaluation.

The Journal of pharmacology and experimental therapeutics·2026
Same author

Cluster-Validated Graph Neural Network for P-gp Substrate Prediction from Public Data.

Journal of chemical information and modeling·2026
Same author

Effects of microcurrent electrical neuromuscular stimulation on recovery of muscle performance after high-intensity sprint and resistance combined training sessions.

Journal of exercise science and fitness·2026
Same author

Meroterpenoids with BACE1-inhibitory activity from the fruiting bodies of Suillus bovinus and Boletinus cavipes.

Journal of natural medicines·2024
Same author

Developing an AI-based prediction model for anaphylactic shock from injection drugs using Japanese real-world data and chemical structure-based analysis.

Daru : journal of Faculty of Pharmacy, Tehran University of Medical Sciences·2024
Same author

Photoreaction products of extract from the fruiting bodies of Polyozellus multiplex.

Journal of natural medicines·2024

Related Experiment Video

Updated: Feb 8, 2026

A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

69.8K

Structure-Based Prediction of QT Prolongation Risk Using Graph Neural Networks: An Integrative Approach Combining In

Tomoyuki Enokiya1,2, Ryosuke Kunitomo1, Takamasa Yamaguchi2

  • 1Laboratory of Pharmacoinformatics, Department of Pharmaceutical Sciences, Faculty of Pharmaceutical Sciences, Suzuka University of Medical Science, Suzuka, Japan.

Clinical Pharmacology and Therapeutics
|February 7, 2026
PubMed
Summary

We developed a graph neural network (GNN) to predict drug-induced QT-interval prolongation risk by integrating molecular structure, in vitro data, and safety signals. This interpretable model enhances drug safety assessment.

More Related Videos

A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes
10:04

A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes

Published on: March 3, 2018

7.1K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.0K

Related Experiment Videos

Last Updated: Feb 8, 2026

A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

69.8K
A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes
10:04

A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes

Published on: March 3, 2018

7.1K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.0K

Area of Science:

  • Pharmacology
  • Computational Chemistry
  • Drug Safety

Background:

  • Drug-induced QT-interval prolongation is a major safety concern in drug development, increasing the risk of Torsades de Pointes (TdP).
  • In vitro hERG inhibition assays are standard for early screening, but pharmacovigilance data offer complementary insights into proarrhythmic risk.
  • Integrating molecular structure with diverse data sources presents an underutilized approach for predicting drug cardiotoxicity.

Purpose of the Study:

  • To develop an interpretable graph neural network (GNN) framework for predicting QT liability.
  • To integrate in vitro hERG inhibition data, FDA Adverse Event Reporting System (FAERS) signals, and molecular structure information.
  • To identify structural features contributing to QT liability using model interpretability techniques.

Main Methods:

  • Developed a GNN framework using RDKit to convert Canonical SMILES into molecular graphs with encoded atom- and bond-level features.
  • Compared four GNN architectures (GINE, GCN, GraphSAGE, GATv2) using stratified five-fold cross-validation on 4,808 small molecules with binary QT-risk labels.
  • Utilized Integrated Gradients for interpreting the best-performing GATv2 model and validated performance on an independent hERG assay dataset.

Main Results:

  • The GATv2 model achieved a cross-validated ROC-AUC of 0.838, PR-AUC of 0.830, and F1-score of 0.756.
  • Retraining on the full dataset improved performance to ROC-AUC 0.918, PR-AUC 0.908, and F1-score 0.847.
  • External validation demonstrated strong performance with ROC-AUC 0.859, sensitivity 0.80, and specificity 0.82; atomic degree and hydrogen count were key predictors.

Conclusions:

  • The developed GNN framework effectively integrates structural and pharmacological data to predict QT risk.
  • The interpretable nature of the model provides a transparent, structure-based decision-support tool for drug development.
  • This approach aligns with regulatory guidelines (ICH S7B/E14) and initiatives like CiPA for enhanced drug safety assessment.