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

Induction of decision trees via evolutionary programming.

Robert Kirk DeLisle1, Steven L Dixon

  • 1Department of Molecular Modeling, Pharmacopeia, P.O. Box 5350, Princeton, New Jersey 08543-5350, USA. kdelisle@pharmacop.com

Journal of Chemical Information and Computer Sciences
|May 25, 2004
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

Crossing the Halfway Point: Aptamer-Based, Highly Multiplexed Assay for the Assessment of the Proteome.

Journal of proteome research·2024
Same author

A Dual, Systematic Approach to Malaria Diagnostic Biomarker Discovery.

Clinical infectious diseases : an official publication of the Infectious Diseases Society of America·2021
Same author

Reliable and Accurate Solution to the Induced Fit Docking Problem for Protein-Ligand Binding.

Journal of chemical theory and computation·2021
Same author

Plasma protein patterns as comprehensive indicators of health.

Nature medicine·2019
Same author

Erratum: Connecting genetic risk to disease end points through the human blood plasma proteome.

Nature communications·2017
Same author

Connecting genetic risk to disease end points through the human blood plasma proteome.

Nature communications·2017
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

Evolutionary programming creates more accurate decision trees for cheminformatics modeling than traditional recursive partitioning. This advanced method improves predictions for biochemical endpoints like toxicity and biodegradability.

Area of Science:

  • Cheminformatics
  • Computational Chemistry
  • Biochemical Modeling

Background:

  • Decision trees are widely used in cheminformatics for modeling biochemical endpoints.
  • Traditional recursive partitioning uses a greedy approach, which may miss underlying data relationships.
  • This method offers interpretability and models nonlinear relationships.

Purpose of the Study:

  • To develop a more accurate method for inducing decision trees in cheminformatics.
  • To compare the performance of evolutionary programming with traditional recursive partitioning.
  • To assess the predictive accuracy on unseen data.

Main Methods:

  • Utilizing evolutionary programming to induce decision trees.
  • Comparing evolutionary programming with single-tree and multiple-tree recursive partitioning.

Related Experiment Videos

  • Employing 10-fold cross-validation for performance assessment.

    • Main Results:

    • Evolutionary programming induced decision trees showed significantly higher accuracy.
    • The method produced less complex classifiers.
    • Average predictive accuracy increased by 5-10% over traditional methods.

    Conclusions:

    • Evolutionary programming offers a superior approach for decision tree induction in cheminformatics.
    • This method enhances predictive accuracy for biochemical endpoints.
    • The approach is effective for modeling toxicity and biodegradability.