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

Volume learning algorithm artificial neural networks for 3D QSAR studies.

I V Tetko1, V V Kovalishyn, D J Livingstone

  • 1Biomedical Department, Institute of Bioorganic & Petroleum Chemistry, Murmanskaya 1, Kiev-660, 253660 Ukraine. itetko@eliot.unil.ch

Journal of Medicinal Chemistry
|July 13, 2001
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

QSAR-derived affinity fingerprints (part 1): fingerprint construction and modeling performance for similarity searching, bioactivity classification and scaffold hopping.

Journal of cheminformatics·2021
Same author

QSAR studies and antimicrobial potential of 1,3-thiazolylphosphonium salts.

Ukrainian biochemical journal·2017
Same author

Computational techniques for the prediction of toxicity.

Toxicology in vitro : an international journal published in association with BIBRA·2010
Same author

Prediction of drug solubility from molecular structure using a drug-like training set.

SAR and QSAR in environmental research·2008
Same author

QSAR studies using the parashift system.

SAR and QSAR in environmental research·2008
Same author

Parvalbumin deficiency affects network properties resulting in increased susceptibility to epileptic seizures.

Molecular and cellular neurosciences·2004
Same journal

Novel Dual Soft Drug Strategy Enables Development of Topical Androgen Receptor Antagonists with Enhanced Efficacy and Optimized Safety for Androgenetic Alopecia.

Journal of medicinal chemistry·2026
Same journal

Design, Synthesis, and Biological Evaluation of Novel PAK1/HDAC10 Dual Inhibitors That Activate Antitumor Immunity for Triple-Negative Breast Cancer Treatment.

Journal of medicinal chemistry·2026
Same journal

Conformationally Tuned Cyclic RGD Peptides for Integrin-Subtype-Selective PET/CT Imaging.

Journal of medicinal chemistry·2026
Same journal

RIMTAC: A Novel Degrader Design Platform by Indirect VHL-Recruitment via RIPK1.

Journal of medicinal chemistry·2026
Same journal

Structure-Activity Relationship of Cycling Molecular Assemblies for Golgi Targeting and Disruption.

Journal of medicinal chemistry·2026
Same journal

Rational Design of Diaryl Ether-Based Dual Inhibitors Targeting Successive Essential Enzymes HadAB and InhA in <i>Mycobacterium tuberculosis</i>.

Journal of medicinal chemistry·2026
See all related articles

A new Volume Learning Algorithm (VLA) combines supervised and unsupervised neural networks for 3D quantitative structure-activity relationship (QSAR) studies. This method enhances analysis of chemical compound spatial properties and activity, offering improved or comparable results to existing techniques.

Area of Science:

  • Computational Chemistry
  • Cheminformatics
  • Drug Discovery

Background:

  • Quantitative Structure-Activity Relationship (QSAR) studies are crucial for understanding chemical compound behavior.
  • Existing methods like Comparative Molecular Field Analysis (CoMFA) and artificial neural networks have limitations.
  • There is a need for advanced computational tools to analyze complex molecular structures and activities.

Purpose of the Study:

  • To introduce a novel Volume Learning Algorithm (VLA) for 3D QSAR analysis.
  • To integrate the strengths of CoMFA and artificial neural networks into a unified approach.
  • To develop a more efficient and interpretable tool for correlating molecular properties with biological activity.

Main Methods:

  • Developed the Volume Learning Algorithm (VLA), combining supervised (feed-forward neural network with back-propagation) and unsupervised (Kohonen self-organizing map) neural networks.

Related Experiment Videos

  • Applied VLA to cluster CoMFA field variables, selecting key parameters for analysis.
  • Validated the algorithm using cannabimimetic aminoalkyl indoles, comparing results with partial least squares (PLS) analysis.

    • Main Results:

    • The VLA effectively clusters input CoMFA field variables, reducing dimensionality.
    • Statistical coefficients obtained using VLA were comparable or superior to those from PLS analysis for the test dataset.
    • The algorithm provides visualized and easily interpretable results, facilitating understanding of structure-activity relationships.

    Conclusions:

    • The Volume Learning Algorithm (VLA) is a novel and effective tool for 3D QSAR studies.
    • VLA offers advantages by integrating supervised and unsupervised learning for enhanced data analysis and interpretation.
    • This method presents a convenient and powerful approach for researchers in computational chemistry and drug discovery.