Using Machine Learning to Find New Drugs for Dengue Virus
Author Information
Author(s): George Hanson, Joseph Adams, Daveson I. B. Kepgang, Luke S. Zondagh, Lewis Tem Bueh, Andy Asante, Soham A. Shirolkar, Maureen Kisaakye, Hem Bondarwad, Olaitan I. Awe
Primary Institution: Noguchi Memorial Institute for Medical Research, University of Ghana
Hypothesis
This study aims to identify novel potential inhibitors of the Dengue virus (DENV) using an integrative drug discovery approach encompassing machine learning and molecular docking techniques.
Conclusion
The study successfully identified new potential antiviral drugs against the Dengue virus using machine learning and molecular docking methods.
Supporting Evidence
- The Logistic Regression model achieved an accuracy of 94%.
- 18 known DENV inhibitors were predicted, with 11 identified as active.
- 2683 new compounds were explored for potential antiviral activity.
- Four lead compounds showed high binding affinities in molecular docking studies.
Takeaway
Researchers used computers to find new medicines that can help fight the Dengue virus, which makes people very sick. They found some promising candidates that could be tested in the lab.
Methodology
The study used machine learning models trained on a dataset of bioactive compounds and performed molecular docking to predict active compounds against the Dengue virus.
Potential Biases
The model may be biased due to the predominance of inactive compounds in the training dataset.
Limitations
The study faced challenges due to the imbalanced dataset, which could affect the model's generalizability.
Statistical Information
P-Value
p<0.05
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website