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

Granular kernel trees with parallel genetic algorithms for drug activity comparisons.

Bo Jin1, Yan-Qing Zhang, Binghe Wang

  • 1Department of Computer Science, Georgia State University, Atlanta, GA 30302, USA. cscbxjx@cs.gsu.edu

International Journal of Data Mining and Bioinformatics
|April 11, 2008
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

Inhibitors of the Machupo Virus L Endonuclease for Bolivian Hemorrhagic Fever Treatments.

Microorganisms·2026
Same author

A Metal-Free Carbon Monoxide Prodrug Suppresses Metastasis of Pancreatic and Breast Cancer.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Targeting Highly Reactive Oxygen Species (hROS) for Prodrug Activation through a Cascade Reaction with Kinetic Tunability (CReKT) to Effect Linker Cleavage.

Journal of medicinal chemistry·2026
Same author

Reactive oxygen species (ROS) research in drug discovery and drug delivery: Can the medium Be a Trojan Horse disguised as something benign?

Journal of enzyme inhibition and medicinal chemistry·2026
Same author

A Cu(II)-Based Fluorescent Probe for Carbon Monoxide, Nap-BC-Cu(II), Does Not Selectively Detect Carbon Monoxide.

Molecules (Basel, Switzerland)·2026
Same author

Pd(0)-Mediated Deallylation Chemistry: A Reassessment of Its Application in Sensing CO.

The Journal of organic chemistry·2025
Same journal

DiffGRN: differential gene regulatory network analysis.

International journal of data mining and bioinformatics·2019
Same journal

Integration of multi-omics data for integrative gene regulatory network inference.

International journal of data mining and bioinformatics·2018
Same journal

The development of non-coding RNA ontology.

International journal of data mining and bioinformatics·2016
Same journal

Learning multiple distributed prototypes of semantic categories for named entity recognition.

International journal of data mining and bioinformatics·2015
Same journal

Weighted fusion regularisation and predicting microbial interactions with vector autoregressive model.

International journal of data mining and bioinformatics·2015
Same journal

Application of consensus string matching in the diagnosis of allelic heterogeneity involving transposition mutation.

International journal of data mining and bioinformatics·2015
See all related articles

Granular Kernel Trees (GKTs) offer improved biological and chemical data prediction by effectively incorporating prior knowledge. Optimized using Genetic Algorithms (GAs), GKTs outperform traditional RBF kernels in drug activity prediction accuracy.

Area of Science:

  • Bioinformatics
  • Cheminformatics
  • Machine Learning

Background:

  • Increasing demand for accurate biological and chemical data prediction.
  • Need for advanced kernel functions to capture complex data relationships.
  • Limitations of existing methods in expressing prior knowledge effectively.

Purpose of the Study:

  • Introduce Granular Kernel Trees (GKTs) as a novel kernel function.
  • Utilize parallel Genetic Algorithms (GAs) for optimizing GKT parameters.
  • Evaluate the performance of GKTs in biological and chemical data prediction tasks.

Main Methods:

  • Development of the Granular Kernel Tree (GKT) model.
  • Application of parallel Genetic Algorithms (GAs) for hyperparameter optimization.

Related Experiment Videos

  • Implementation of Support Vector Machines (SVMs) with GKTs for drug activity prediction.

    • Main Results:

    • GKTs demonstrated superior performance compared to traditional RBF kernels.
    • Evolutionary GKTs (optimized via GAs) showed enhanced prediction accuracy.
    • Effective application of GKTs in drug activity comparison tasks.

    Conclusions:

    • Granular Kernel Trees (GKTs) provide a powerful and flexible approach for biological and chemical data prediction.
    • Genetic Algorithm optimization significantly improves GKT performance.
    • GKTs represent a promising advancement over traditional kernels for predictive modeling in drug discovery.