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

You might also read

Related Articles

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

Sort by
Same author

From dual norepinephrine-dopamine reuptake inhibition to selective dopamine reuptake inhibitors: a case of aromatically substituted <i>N</i>,2-cyclopentylamines.

RSC medicinal chemistry·2026
Same author

Automated Parallel Synthesis Accelerates Virtual Screening Hit Discovery.

Journal of the American Chemical Society·2026
Same author

Scaffold-based evaluation metrics for fair comparison of molecular generators.

Journal of cheminformatics·2026
Same author

Artificial Intelligence for Regulatory Evidence: A Systematic Document Analysis of European Medicines Agency Regulatory Advice and Public Reports.

Clinical pharmacology and therapeutics·2026
Same author

A Structure-Based Platform for Predicting Chemical-Induced Parkinson's Disease.

Chemical research in toxicology·2026
Same author

Doing More with Less: Accurate and Scalable Ligand Free Energy Calculations by Focusing on the Binding Site.

Journal of chemical information and modeling·2026

Related Experiment Video

Updated: Mar 16, 2026

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

8.4K

Unprecedently Large-Scale Kinase Inhibitor Set Enabling the Accurate Prediction of Compound-Kinase Activities: A Way

Serge Christmann-Franck1, Gerard J P van Westen2, George Papadatos2

  • 1Merck Serono , Chemin des Mines 9, 1202 Genève, Switzerland.

Journal of Chemical Information and Modeling
|August 3, 2016
PubMed
Summary

Researchers created predictive models for protein kinase inhibitors using extensive literature data. These models accurately predict kinase activity and selectivity, aiding in rational drug design for cancer and other diseases.

More Related Videos

Characterization at the Molecular Level using Robust Biochemical Approaches of a New Kinase Protein
11:23

Characterization at the Molecular Level using Robust Biochemical Approaches of a New Kinase Protein

Published on: June 30, 2019

6.8K
Identification of Kinase-substrate Pairs Using High Throughput Screening
11:13

Identification of Kinase-substrate Pairs Using High Throughput Screening

Published on: August 29, 2015

8.7K

Related Experiment Videos

Last Updated: Mar 16, 2026

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

8.4K
Characterization at the Molecular Level using Robust Biochemical Approaches of a New Kinase Protein
11:23

Characterization at the Molecular Level using Robust Biochemical Approaches of a New Kinase Protein

Published on: June 30, 2019

6.8K
Identification of Kinase-substrate Pairs Using High Throughput Screening
11:13

Identification of Kinase-substrate Pairs Using High Throughput Screening

Published on: August 29, 2015

8.7K

Area of Science:

  • Medicinal Chemistry
  • Computational Biology
  • Drug Discovery

Background:

  • Drug discovery programs often target the human kinome, seeking small molecule protein kinase inhibitors for cancer and other diseases.
  • A key challenge is controlling inhibitor selectivity, typically assessed via in vitro profiling against kinase panels.
  • Existing data on kinase inhibitor profiles are dispersed across scientific literature and patents.

Purpose of the Study:

  • To create robust proteochemometric models for predicting kinase activity and inhibitor selectivity.
  • To analyze existing kinase inhibitor data for kinome coverage, reproducibility, and selectivity trends.
  • To facilitate the rational design of kinase inhibitors with specific selectivity profiles.

Main Methods:

  • Manual extraction, compilation, and standardization of 356,908 data points from 661 patents and literature.
  • Analysis of data for kinome coverage, reproducibility, popularity, and selectivity.
  • Development of proteochemometric models with external validation (RMSE of 0.41 ± 0.02 log units, R02 of 0.74 ± 0.03).
  • Assessment of factors influencing prediction quality (e.g., data volume, Murcko scaffold frequency).

Main Results:

  • A comprehensive dataset of 482 protein kinases and 2106 inhibitors was compiled.
  • Proteochemometric models demonstrated high predictive power for kinase activity.
  • Model interpretation identified properties correlating with higher kinase-inhibitor affinities.
  • Analysis highlighted structural features influencing selectivity.

Conclusions:

  • The developed models accurately predict kinase-inhibitor activities and enable structural interpretation.
  • These models support the rational design of novel small molecule kinase inhibitors with tailored selectivity.
  • This approach aids in advancing drug discovery programs targeting the human kinome.