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

HIV-1 reverse transcriptase inhibitor design using artificial neural networks

I V Tetko1, Tanchuk VYu, N P Chentsova

  • 1Biomedical Department, Institute of Bioorganic and Petroleum Chemistry, Kiev, Ukraine.

Journal of Medicinal Chemistry
|August 5, 1994
PubMed
Summary

Artificial neural networks accurately predict human immunodeficiency virus type 1 reverse transcriptase inhibitors. This approach identified a potentially highly active molecule, later confirmed by biological testing.

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

Trends in the economic burden of mental disorders over twelve years: the Netherlands mental health survey and incidence study.

The European journal of health economics : HEPAC : health economics in prevention and care·2025
Same author

Associations of common mental disorder severity with treatment contact and treatment intensity, and its changes over twelve years.

Social psychiatry and psychiatric epidemiology·2025
Same author

DEcrease STress through RESilience training for Students (DESTRESS) Study: Protocol for a randomized controlled trial nested in a longitudinal observational cohort study.

Contemporary clinical trials·2022
Same author

Nuclear localization of BCR and cortactin indicates their potential role in regulation of actin branching in nucleus.

Experimental oncology·2021
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

Inhibition of USP1, a new partner of Bcr-Abl, results in decrease of Bcr-Abl level in K562 cells.

Experimental oncology·2020

Area of Science:

  • Computational chemistry
  • Medicinal chemistry
  • Bioinformatics

Background:

  • Human immunodeficiency virus type 1 (HIV-1) remains a significant global health challenge.
  • Developing effective reverse transcriptase inhibitors is crucial for HIV-1 treatment.
  • Predictive modeling can accelerate the discovery of novel antiviral compounds.

Purpose of the Study:

  • To develop and validate an artificial neural network model for predicting the activity of HIV-1 reverse transcriptase inhibitors.
  • To identify novel, potentially highly active inhibitor molecules using computational methods.

Main Methods:

  • Artificial neural networks (ANNs) were employed for predictive analysis.
  • Topological indices were calculated and utilized as molecular descriptors.

Related Experiment Videos

  • A network pruning algorithm and network ensembles were used to optimize the ANN classifier.
  • The model was trained and validated using a dataset of 44 known molecules.

    • Main Results:

    • The optimized ANN model demonstrated improved generalization for new data.
    • Four highly informative topological indices were identified as key predictive parameters.
    • The model successfully predicted the activity of known and novel molecules.
    • One novel molecule was identified as potentially highly active.

    Conclusions:

    • Artificial neural networks, optimized with pruning and ensemble methods, are effective tools for predicting HIV-1 reverse transcriptase inhibitor activity.
    • This computational approach can successfully identify promising drug candidates.
    • The identified molecule warrants further investigation as a potential therapeutic agent for HIV-1.