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

Genetic Algorithm guided Selection: variable selection and subset selection.

Sung Jin Cho1, Mark A Hermsmeier

  • 1New Leads, Bristol-Myers Squibb Co., 5 Research Parkway, Wallingford, Connecticut 06492-7660, USA. scho@amgen.com

Journal of Chemical Information and Computer Sciences
|July 23, 2002
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

Highly potent and selective PPARδ agonist reverses memory deficits in mouse models of Alzheimer's disease.

Theranostics·2024
Same author

Discovery of the therapeutic potential of PPARδ agonist bearing 1,3,4- thiadiazole in inflammatory disorders.

European journal of medicinal chemistry·2024
Same author

Supraorbital Approaches for Anterior Skull Base and Parasellar Lesions: Insights From a Single-Center Experience.

Brain tumor research and treatment·2024
Same author

ERRγ-inducible FGF23 promotes alcoholic liver injury through enhancing CYP2E1 mediated hepatic oxidative stress.

Redox biology·2024
Same author

Upregulation of the ERRγ-VDAC1 axis underlies the molecular pathogenesis of pancreatitis.

Proceedings of the National Academy of Sciences of the United States of America·2023
Same author

An Inverse Agonist GSK5182 Increases Protein Stability of the Orphan Nuclear Receptor ERRγ via Inhibition of Ubiquitination.

International journal of molecular sciences·2023
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
See all related articles

A novel Genetic Algorithm guided Selection (GAS) method optimizes variables and compound subsets for QSAR/QSPR models. GAS improves model performance, especially when standard variable selection fails, by identifying relevant chemotype clusters.

Area of Science:

  • Computational Chemistry
  • Cheminformatics
  • Machine Learning

Background:

  • Quantitative Structure-Activity Relationship (QSAR) and Quantitative Structure-Property Relationship (QSPR) models are crucial in drug discovery and chemical research.
  • Traditional methods often struggle with complex datasets containing diverse chemical structures and varying descriptor relevance.
  • Optimizing both variable selection and compound subsetting simultaneously is a significant challenge.

Purpose of the Study:

  • To introduce and evaluate a novel Genetic Algorithm guided Selection (GAS) method for QSAR/QSPR model development.
  • To enable simultaneous optimization of descriptors and compound subsets.
  • To improve model accuracy and applicability by handling diverse chemotypes.

Main Methods:

Related Experiment Videos

  • Developed a GAS method with a simple encoding scheme for compounds and variables.
  • Utilized a genetic algorithm for simultaneous optimization of descriptors and compound subsets.
  • Implemented a molecular similarity procedure for assigning test compounds to specific models.
  • Tested variable selection on the Selwood dataset and subset selection on artificial and XLOGP datasets.

    • Main Results:

    • The GAS variable selection method demonstrated comparable performance to existing techniques on the Selwood dataset.
    • The GAS subset selection method successfully identified artificial data points belonging to distinct subsets.
    • Application to the XLOGP dataset revealed that subset selection can enhance QSAR/QSPR models where variable selection alone is insufficient.

    Conclusions:

    • The GAS method offers a robust approach for simultaneous variable and compound subset optimization in QSAR/QSPR modeling.
    • GAS effectively handles datasets with diverse chemotypes by generating subset-specific models.
    • The GAS method shows promise for improving predictive accuracy in complex chemical datasets.