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

Related Concept Videos

Protein Networks

Protein Networks

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,...

Induced-fit Model

Induced-fit Model

Most chemical reactions in cells require enzymes—biological catalysts that speed up the reaction without being consumed or permanently changed. They reduce the activation energy needed to convert the reactants into products. Enzymes are proteins, that usually work by binding to a substrate—a reactant molecule that they act upon.
Enzymes exhibit substrate specificity, meaning that they can only bind to certain substrates. This is mainly determined by the shape and chemical...

Types of Chemical Bonds

Types of Chemical Bonds

Chemical bonding theories were pioneered by American chemist Gilbert N. Lewis. He developed a model called the Lewis model to explain the type and formation of different bonds. Chemical bonding is central to chemistry; it explains how atoms or ions bond together to form molecules. It explains why some bonds are strong and others are weak, or why one carbon bonds with two oxygens and not three; why water is H2O and not H4O.

Precipitation Titration: Endpoint Detection Methods

Precipitation Titration: Endpoint Detection Methods

In argentometric precipitation titrations, endpoints can be detected visually by the Mohr, Volhard, and Fajans methods. In the Mohr method, adding a soluble chromate indicator gives an initial yellow color to the analyte solution. As the titrant is added, the first excess of silver ions forms a red silver chromate precipitate, marking the endpoint. The solution pH should be maintained at about 8 by adding solid CaCO3.
In the Volhard method, a standard excess of AgNO3 is first added to the...

Predicting Molecular Geometry

Predicting Molecular Geometry

VSEPR Theory for Determination of Electron Pair Geometries

Chemical Formulas

Chemical Formulas

A chemical formula presents information about the proportions of atoms constituting a particular chemical compound or molecule, mainly using symbols of elements and numbers. At times other symbols, such as dashes, parentheses, brackets, commas, plus, and minus signs, are also used. A chemical formula can be one of three types – molecular, empirical, and structural.

You might also read

Related Articles

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

Sort by

Same author

Evaluation of deep learning architectures for predicting ligand interactions with neurologically relevant GPCRs.

Journal of cheminformatics·2026

Same author

ToxMet: a web tool for toxicogenomic data analysis using genome-scale metabolic modeling.

Toxicological sciences : an official journal of the Society of Toxicology·2026

Same author

Cross-bridge model-based quantification of muscle metabolite alterations leading to fatigue during all-out knee extension exercise.

Frontiers in physiology·2026

Same author

A reinforcement learning algorithm to optimize resource utilization in combat casualty care.

Scientific reports·2025

Same author

A model to simulate human cardio-respiratory responses to airway obstruction.

Frontiers in physiology·2025

Same author

A model to simulate human cardio-respiratory responses to ketamine analgesia.

Frontiers in physiology·2025

Search research articles

Related Experiment Video

Updated: Jan 28, 2026

Human Liver Microphysiological System for Assessing Drug-Induced Liver Toxicity In Vitro

Human Liver Microphysiological System for Assessing Drug-Induced Liver Toxicity In Vitro

Published on: January 31, 2022

Deep Neural Network Models for Predicting Chemically Induced Liver Toxicity Endpoints From Transcriptomic Responses.

Hao Wang^1,2, Ruifeng Liu^1,2, Patric Schyman^1,2

¹The Henry M. Jackson Foundation for the Advancement of Military Medicine, Inc., Bethesda, MD, United States.

Frontiers in Pharmacology

|February 27, 2019

Summary

Deep neural networks (DNNs) accurately predict chemical-induced liver injuries using gene expression data. These models show robust performance, outperforming other machine learning methods for toxicity prediction.

Keywords:

artificial neural network biliary hyperplasia classification model liver fibrosis liver necrosis machine leaning toxicity prediction

More Related Videos

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

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

Published on: January 12, 2024

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Related Experiment Videos

Last Updated: Jan 28, 2026

Human Liver Microphysiological System for Assessing Drug-Induced Liver Toxicity In Vitro

Human Liver Microphysiological System for Assessing Drug-Induced Liver Toxicity In Vitro

Published on: January 31, 2022

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

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

Published on: January 12, 2024

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Area of Science:

Toxicology
Bioinformatics
Computational Biology

Background:

Accurate toxicity prediction is crucial for drug and chemical safety assessment.
Transcriptomic data combined with machine learning offers a promising approach to enhance toxicity prediction models.
Deep neural networks (DNNs) are adept at handling high-dimensional transcriptomic data.

Purpose of the Study:

To evaluate gene- and pathway-level feature selection with DNNs for predicting chemically induced liver injuries.
To compare the performance of DNN models against Random Forest and Support Vector Machine models.
To assess the robustness of DNN models in predicting injury phenotypes across different datasets.

Main Methods:

Utilized single- and multi-task deep neural network (DNN) approaches.
Employed gene- and pathway-level feature selection schemes.
Trained and validated models using whole-genome DNA microarray data for chemically induced liver injuries (biliary hyperplasia, fibrosis, necrosis).
Compared DNN performance with Random Forest and Support Vector Machine models on cross-validation and external datasets.

Main Results:

Single-task DNN models achieved high predictive accuracy (MCC 0.56–0.89, average 0.74) and endpoint specificity.
DNN models outperformed Random Forest in cross-validation and Support Vector Machines in external validation.
Feature selection schemes had a negligible effect on model performance in cross-validation.
DNN models demonstrated robust prediction of injury phenotypes for non-chemically induced injuries.

Conclusions:

Deep neural networks effectively predict chemically induced liver injuries from transcriptomic data.
DNN models offer a robust and accurate approach for toxicity prediction, outperforming traditional machine learning methods.
The models successfully learned injury-specific features from gene expression data, highlighting their potential for safety assessment.