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 Videos

Classifying "kinase inhibitor-likeness" by using machine-learning methods.

Hans Briem1, Judith Günther

  • 1Schering AG, Research Center Europe, CDCC/Computational Chemistry, Muellerstrasse 178, 13342 Berlin, Germany. hans.briem@schering.de

Chembiochem : a European Journal of Chemical Biology
|February 8, 2005
PubMed
Summary
This summary is machine-generated.

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

[Development of a tool for structuring and reflecting data on harms with consumer health information (SCHADEN Tool)].

Zeitschrift fur Evidenz, Fortbildung und Qualitat im Gesundheitswesen·2026
Same author

CACHE Challenge #3: Targeting the Nsp3 Macrodomain of SARS-CoV-2.

Journal of chemical information and modeling·2026
Same author

CACHE Challenge #2: Targeting the RNA Site of the SARS-CoV-2 Helicase Nsp13.

Journal of chemical information and modeling·2025
Same author

The Need for Continuing Blinded Pose- and Activity Prediction Benchmarks.

Journal of chemical information and modeling·2025
Same author

Toward target 2035: EUbOPEN - a public-private partnership to enable & unlock biology in the open.

RSC medicinal chemistry·2024
Same author

Discovery of BAY-405: An Azaindole-Based MAP4K1 Inhibitor for the Enhancement of T-Cell Immunity against Cancer.

Journal of medicinal chemistry·2024
Same journal

Vancomycin-Mediated Binding of DNA Origami Nanostructures to Gram-Positive and Gram-Negative Bacteria.

Chembiochem : a European journal of chemical biology·2026
Same journal

Mutasynthesis and Antibiotic Activity of Mupirocin Analogues.

Chembiochem : a European journal of chemical biology·2026
Same journal

Pressure-Dependent Aromatic Ring Flips Reveal Variable Transition-State Volume and Compressibility Among Structural Regions of BPTI.

Chembiochem : a European journal of chemical biology·2026
Same journal

Eyes Toward the Clinic: Selective Inhibition and Degradation Approaches to Bromodomain-Containing Proteins.

Chembiochem : a European journal of chemical biology·2026
Same journal

Contrast Agents for Enhanced Bioimaging: A Comprehensive Review.

Chembiochem : a European journal of chemical biology·2026
Same journal

RNAGEN: A Generative Adversarial Network-Based Model to Generate Synthetic RNA Sequences to Target Proteins.

Chembiochem : a European journal of chemical biology·2026
See all related articles

Machine learning models effectively distinguish kinase inhibitors from inactive molecules. Ensemble methods and support-vector machines (SVMs) showed superior performance in predicting molecular activity.

Area of Science:

  • Computational chemistry
  • Cheminformatics
  • Machine learning in drug discovery

Background:

  • Kinase inhibitors are crucial in targeted cancer therapy.
  • Accurate prediction of kinase inhibition is vital for drug development.
  • Developing robust computational models is essential for screening potential inhibitors.

Purpose of the Study:

  • To evaluate and compare various machine learning techniques for identifying kinase inhibitors.
  • To assess the effectiveness of Ghose-Crippen parameters in molecular encoding.
  • To determine the optimal machine learning approach for predicting kinase inhibitor activity.

Main Methods:

  • Utilized an in-house dataset of small-molecule structures encoded by Ghose-Crippen parameters.
  • Applied four machine learning algorithms: Support-Vector Machines (SVM), Artificial Neural Networks (ANN), GA-optimized k-Nearest Neighbors (GA/kNN), and Recursive Partitioning (RP).

Related Experiment Videos

  • Employed consensus voting from multiple derived models to enhance prediction quality.

    • Main Results:

    • All tested machine learning methods demonstrated reasonable discrimination capabilities.
    • Support-vector machines (SVM) and GA/kNN showed strong individual model performance.
    • Ensemble methods, particularly consensus voting, significantly improved prediction accuracy, precision, recall, and F1 values across all techniques.
    • Artificial Neural Networks (ANN) achieved the highest F1 value using majority voting, closely followed by SVMs.

    Conclusions:

    • Machine learning, particularly SVMs and ensemble approaches, can effectively predict kinase inhibitor activity.
    • Ghose-Crippen parameters provide a useful feature set for molecular representation in predictive modeling.
    • Consensus strategies enhance the reliability and accuracy of computational drug discovery models.