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

The JAK-STAT Signaling Pathway01:20

The JAK-STAT Signaling Pathway

9.0K
Several cytokine receptors have tightly bound Janus kinase or JAK proteins attached at their cytosolic tail. Small signaling molecules such as cytokines, growth hormones, or prolactins bind to the cytokine receptors and initiate their dimerization. The dimerization brings the cytosolic JAKs together that trans-phosphorylate and activates each other. The activated JAKs now phosphorylate cytosolic tails of the cytokine receptors, which serve as binding sites for adaptor proteins such as  SH2...
9.0K
Drug Discovery: Overview01:26

Drug Discovery: Overview

8.1K
Drug discovery is a multifaceted process involving extensive screening, testing, and optimization of lead compounds to identify potential new drugs for therapeutic use. It combines several approaches, including screening large numbers of natural products, chemical modification of known active molecules, identification of new drug targets, and rational design based on biological mechanisms and drug-receptor structure. These approaches are carried out in both academic research laboratories and...
8.1K
Protein-Drug Binding: Determination Methods01:22

Protein-Drug Binding: Determination Methods

250
Determining protein-drug binding can be achieved through indirect and direct methods, each providing valuable insights into the interaction between proteins and drugs.
Indirect methods involve isolating the bound drug from its free form in biological samples such as blood, serum, or plasma. These techniques aim to measure the percentage of drugs bound to proteins. Equilibrium dialysis is a commonly used method where the free drug concentration at equilibrium is measured by separating the bound...
250
Protein-Drug Binding: Mechanism and Kinetics01:16

Protein-Drug Binding: Mechanism and Kinetics

685
Protein-drug binding refers to the interaction between drugs and proteins within the body. This binding process can occur intracellularly, involving drug interactions with enzymes or receptors within cells, or extracellularly, involving plasma proteins in the blood.
Various forces drive these interactions, including hydrogen bonds, hydrophobic interactions, ionic bonds, electrostatic interactions, and van der Waals forces. These bonds enable drugs to bind to specific sites on proteins,...
685
Analysis Methods of Pharmacokinetic Data: Model and Model-Independent Approaches01:14

Analysis Methods of Pharmacokinetic Data: Model and Model-Independent Approaches

192
Drug disposition in the body is a complex process and can be studied using two major approaches: the model and the model-independent approaches.
The model approach uses mathematical models to describe changes in drug concentration over time. Pharmacokinetic models help characterize drug behavior in patients, predict drug concentration in the body fluids, calculate optimum dosage regimens, and evaluate the risk of toxicity. However, ensuring that the model fits the experimental data accurately...
192
Dipeptidyl Peptidase 4 Inhibitors01:23

Dipeptidyl Peptidase 4 Inhibitors

219
Dipeptidyl peptidase 4 (DPP-4) is a serine protease widely distributed in the body. It's involved in the inactivation of GLP-1 and GIP hormones, which are crucial for insulin regulation. DPP-4 inhibitors, such as sitagliptin (Januvia), saxagliptin (Onglyza), linagliptin (Tradjenta), alogliptin (Nesina), and vildagliptin (Galvus), help increase the proportion of active GLP-1, enhancing insulin secretion. These inhibitors work by competitively binding to DPP-4. This binding causes a...
219

You might also read

Related Articles

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

Sort by
Same author

NEP89: universal neuroevolution potential for inorganic and organic materials across 89 elements.

Nature computational science·2026
Same author

Discovery of SD-2301 as a Highly Potent and Selective PROTAC STAT3 Degrader Capable of Achieving Complete Tumor Regression with Single Administration.

Journal of medicinal chemistry·2026
Same author

Seconds-scale exfoliation of high-quality 2D crystals enabled by polycyclic aromatic hydrocarbon radical anion-mediated organoalkali intercalation.

Nature communications·2026
Same author

Enhancing Whole Slide Image Classification in Renal Cell Carcinoma via Swin Transformer-Based Multiple Instance Learning.

Bioengineering (Basel, Switzerland)·2026
Same author

Characterization of sexually acquired HIV-1 transmission networks and genetic variation in northern frontier China, 2021-2024.

Frontiers in public health·2026
Same author

Discovery of SMD-6346: A Potent, Selective, and Orally Active SMARCA2 Degrader for Targeting SMARCA4-Deficient Human Cancers.

Journal of medicinal chemistry·2026

Related Experiment Video

Updated: Aug 2, 2025

A Method for Screening and Validation of Resistant Mutations Against Kinase Inhibitors
12:40

A Method for Screening and Validation of Resistant Mutations Against Kinase Inhibitors

Published on: December 7, 2014

14.9K

CoGT: Ensemble Machine Learning Method and Its Application on JAK Inhibitor Discovery.

Yingzi Bu1, Ruoxi Gao2, Bohan Zhang3

  • 1Department of Pharmaceutical Sciences, College of Pharmacy, University of Michigan, Ann Arbor, Michigan 48109, United States.

ACS Omega
|April 17, 2023
PubMed
Summary

We developed CoGT, a novel machine learning ensemble model for predicting drug-target interactions (DTI). CoGT accelerates drug discovery by accurately identifying potential drug candidates for inhibiting targets like Janus kinases (JAKs).

More Related Videos

Kinase Inhibitor Screening In Self-assembled Human Protein Microarrays
13:22

Kinase Inhibitor Screening In Self-assembled Human Protein Microarrays

Published on: October 23, 2019

7.9K
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

8.3K

Related Experiment Videos

Last Updated: Aug 2, 2025

A Method for Screening and Validation of Resistant Mutations Against Kinase Inhibitors
12:40

A Method for Screening and Validation of Resistant Mutations Against Kinase Inhibitors

Published on: December 7, 2014

14.9K
Kinase Inhibitor Screening In Self-assembled Human Protein Microarrays
13:22

Kinase Inhibitor Screening In Self-assembled Human Protein Microarrays

Published on: October 23, 2019

7.9K
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

8.3K

Area of Science:

  • Computational chemistry
  • Drug discovery
  • Machine learning in pharmacology

Background:

  • Drug discovery is resource-intensive, with predicting drug-target interactions (DTI) being a key challenge.
  • Traditional machine learning (ML) methods for DTI prediction often lack sufficient accuracy.
  • Developing efficient computational methods is crucial for accelerating the identification of novel drug candidates.

Purpose of the Study:

  • To develop a novel ensemble machine learning model, CoGT, for enhanced prediction of drug-target interactions (DTI).
  • To integrate graph-based models and large pretrained language models for improved molecular structure representation and DTI prediction.
  • To evaluate the efficacy of CoGT in predicting compound inhibition against Janus kinases (JAKs).

Main Methods:

  • Developed CoGT, an ensemble model combining multilayer perceptron (MLP), graph neural networks (GNNs), and the pretrained chemBERTa model.
  • Utilized GNNs to extract non-Euclidean molecular structures and chemBERTa to process simplified molecular input line entry systems (SMILES).
  • Evaluated model performance using compounds targeting four Janus kinases (JAKs) and various performance metrics.

Main Results:

  • The pretrained chemBERTa model demonstrated superior DTI prediction accuracy compared to conventional ML models.
  • Graph neural networks (GNNs) proved effective for DTI prediction, especially on imbalanced datasets.
  • The ensemble model CoGT significantly outperformed individual models in predicting compound inhibition across different JAK isoforms.

Conclusions:

  • The ensemble model CoGT effectively integrates diverse ML approaches to enhance DTI prediction accuracy.
  • CoGT demonstrates significant potential to accelerate the drug discovery pipeline by improving the efficiency of identifying drug candidates.
  • This study highlights the value of combining graph-based and large pretrained models for complex DTI prediction tasks.