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

Introducing the consensus modeling concept in genetic algorithms: application to interpretable discriminant analysis.

Milan Ganguly1, Nathan Brown, Ansgar Schuffenhauer

  • 1Novartis Institutes for BioMedical Research, Basel, CH-4002, Switzerland.

Journal of Chemical Information and Modeling
|September 26, 2006
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

Community Integration as a Key Role of the Rural Primary Care Physical Therapist: A Qualitative Case Study.

Physical therapy·2026
Same author

Once yearly cell-based therapy for sustained and dose tunable delivery of monoclonal antibodies.

bioRxiv : the preprint server for biology·2026
Same author

Clinical Handover as Craft, Not Checklist.

Emergency medicine Australasia : EMA·2026
Same author

Anticoagulation Practices Surrounding Emergency Department Cardioversion for Atrial Fibrillation and Flutter.

Emergency medicine Australasia : EMA·2026
Same author

Microbial communities in semi-mature oak trees are resilient to drought, nutrient limitation, and pathogen challenge.

Cell host & microbe·2026
Same author

Explicit Applicability Domain Calculations Can Help Determine When Uncertainty Estimates Are Less Reliable.

ACS omega·2026
Same journal

PSDTA: An Approach to Drug-Target Binding Affinity Prediction by Integrating Physicochemical and Structural Information to Reduce Feature Redundancy.

Journal of chemical information and modeling·2026
Same journal

M-JEPA: Predictive Self-Supervised Learning for Molecular Graphs with Scaffold-Shift Evaluation on Tox21.

Journal of chemical information and modeling·2026
Same journal

Advancing Biochemical Molecule Registration, Representation and Search for New Drug Modalities.

Journal of chemical information and modeling·2026
Same journal

A Unified Molecular Graph and Protein Language Model Framework for Predicting Human Drug-Hormone Receptor Interactions with Structure-Aware Validation.

Journal of chemical information and modeling·2026
Same journal

Intricate Role of Cholesterol in Membrane Fusion.

Journal of chemical information and modeling·2026
Same journal

tmGNN-XAI: An Explainable Graph Neural Network Tool for Predicting Electronic Properties of Transition Metal Complexes from SMILES.

Journal of chemical information and modeling·2026
See all related articles

This study used evolutionary statistical learning to classify drugs by biological target and oral availability. The method enhances model interpretability and identifies key drug descriptors for better classification and drug discovery.

Area of Science:

  • Computational chemistry
  • Cheminformatics
  • Machine learning in drug discovery

Background:

  • Drug classification and prediction of pharmacokinetic properties are crucial in pharmaceutical research.
  • Existing methods often lack interpretability, hindering understanding of underlying biological and chemical relationships.

Purpose of the Study:

  • To apply an evolutionary statistical learning method for drug classification based on biological targets and oral bioavailability.
  • To enhance model interpretability by analyzing model weight consistency and identifying key discriminating descriptors.
  • To improve model performance, consistency, and robustness using novel consensus and splice modeling techniques.

Main Methods:

  • Utilized an evolutionary statistical learning approach, specifically a genetic algorithm, for drug classification.

Related Experiment Videos

  • Assessed model interpretability by examining the consistency of model weights across multiple runs.
  • Employed consensus and splice modeling to reduce solution variability and enhance model robustness.
  • Compared the genetic algorithm's performance with similarity searching, Naïve Bayes, and support vector machines for different classification tasks.

    • Main Results:

    • Identified key molecular descriptors and their ranges that significantly contribute to discriminating between drug classes (biological targets, oral vs. nonoral).
    • Demonstrated that optimizing bin step size improves both interpretability and discriminatory power.
    • Consensus and splice modeling effectively enhanced model performance, consistency, and robustness.
    • The genetic algorithm showed comparable or superior performance in discriminating activity classes compared to similarity searching.

    Conclusions:

    • Evolutionary statistical learning provides interpretable models for drug classification and property prediction.
    • The developed methods offer improved accuracy, consistency, and robustness in drug analysis.
    • This approach aids in understanding structure-activity relationships and facilitates more effective drug discovery and development.