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 Video

Updated: May 11, 2026

Vector Competence Analyses on Aedes aegypti Mosquitoes using Zika Virus
10:35

Vector Competence Analyses on Aedes aegypti Mosquitoes using Zika Virus

Published on: May 31, 2020

Exploring anti-dengue activity with atomic-weighted vectors, class balancing and machine learning.

Yoan Martínez-López1,2,3, Ansel Y Rodríguez-Gonzalez4, Paulina Phoobane5

  • 1Department of Computer Sciences, Faculty of Informatics, Camagüey University, 74650, Camagüey City, Cuba. ymlopez2022@gmail.com.

Molecular Diversity
|May 9, 2026
PubMed

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

Machine Learning-Based QSAR Models for Discovery of Inhibitors Targeting <i>Leishmania infantum</i> Amastigotes.

Pharmaceuticals (Basel, Switzerland)·2026
Same author

Protozoan Neglected Tropical Diseases (NTDs) Target Inhibition of Alkaloids from <i>Croton linearis</i> Jacq Leaves: A Molecular Docking and ADMET Approach.

Pharmaceuticals (Basel, Switzerland)·2025
Same author

Exploring antimalarial activity of drugs using weighted atomic vectors and artificial intelligence.

Journal of vector borne diseases·2025
Same author

Discovery of Diphenylsilane Compounds as Potential Inhibitors of Zn-Metalloproteinase Thermolysin Using Artificial Neural Networks.

Current topics in medicinal chemistry·2025
Same author

Edge Computing System for Automatic Detection of Chronic Respiratory Diseases Using Audio Analysis.

Journal of medical systems·2025
Same author

Natriuretic effect of 4',5-dihydroxy-6,7-methylenedioxyflavonol-3-<i>O</i>-α-L-rhamnopyranosyl-(1→2)-β-D-xylopyranoside from <i>Boldoa purpurascens: in silico</i> and <i>in vivo</i> studies.

Journal of biomolecular structure & dynamics·2024
Summary

Machine learning predicts anti-dengue activity in molecules using Atomic-Weighted Vector (AWV) descriptors. Data balancing improved model robustness, with tree-based classifiers showing best performance for drug discovery.

Area of Science:

  • Computational chemistry
  • Machine learning
  • Drug discovery

Background:

  • Dengue is a significant mosquito-borne viral disease.
  • No effective antiviral treatments are currently available.

Purpose of the Study:

  • To develop a machine-learning framework for predicting anti-dengue activity in small molecules.
  • To utilize Atomic-Weighted Vector (AWV) descriptors and data-balancing techniques for enhanced prediction accuracy.

Main Methods:

  • Generated 16 datasets (2118 molecules each) using MD-LOVIs.
  • Preprocessed data with IMMAN and Shannon entropy for feature selection.
  • Employed ADASYN algorithm to address class imbalance (ratio=6.66).
  • Evaluated 30 classifiers (six families) using tenfold cross-validation and percentage split.
Keywords:
AWVAnti-dengue activityClass balancingMD-LOVIsMachine learning

More Related Videos

Flying Insect Detection and Classification with Inexpensive Sensors
05:16

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

Related Experiment Videos

Last Updated: May 11, 2026

Vector Competence Analyses on Aedes aegypti Mosquitoes using Zika Virus
10:35

Vector Competence Analyses on Aedes aegypti Mosquitoes using Zika Virus

Published on: May 31, 2020

Flying Insect Detection and Classification with Inexpensive Sensors
05:16

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

  • Assessed performance via accuracy (ACC) and nonparametric statistical tests.

    • Main Results:

    • Data balancing significantly improved model robustness.
    • Tree-based and function-based classifiers demonstrated superior predictive performance.
    • The proposed workflow provides a reproducible, data-driven approach for virtual screening.

    Conclusions:

    • The developed machine-learning framework effectively predicts anti-dengue activity.
    • Data balancing is crucial for robust antiviral drug discovery models.
    • The methodology is adaptable for other antiviral drug discovery tasks.