Skip to content

Machine Learning and Molecular Dynamics Simulations Predict Potential Compounds against Marburg Virus

License

Notifications You must be signed in to change notification settings

omicscodeathon/marvpred

Repository files navigation

marvpred

Machine Learning Prediction of Potential Inhibitors of the Marburg Virus Gene 4 Small ORF Protein using MARVpred

Overview

The Marburg virus (MARV), a member of the filovirus family, is a highly virulent pathogen responsible for causing Marburg virus disease (MVD), a hemorrhagic fever with high mortality rates. First identified in 1967, MARV has since caused sporadic outbreaks with devastating impacts on human health and socio-economic stability. The disease's primary vector is the Rousettus aegyptiacus fruit bat and facilitates its spread through direct contact with infected bodily fluids, contaminated surfaces, or the consumption of bushmeat. MVD manifests with symptoms such as fever, vomiting, diarrhea, and severe hemorrhaging, rapidly progressing to multi-organ failure in many cases. Despite its significant threat, no approved vaccines or antiviral therapies are currently available, making it an urgent target for drug discovery and therapeutic development. In this project, we aim to leverage the power of machine learning and molecular docking to accelerate the identification of potential lead compounds against Marburg virus. This approach integrates computational techniques to streamline the traditionally resource-intensive process of drug discovery, offering a rapid, cost-effective alternative to experimental methods.

Table of contents

  1. Project Objectives
  2. Graphical Abstract
  3. Results
  4. How to use
  5. Data Availability
  6. Reproducibility
  7. Credits

Project Objectives

  • Identify a suitable protein target for Marburg virus.
  • Identify a suitable database for interactions between small molecules and the protein target.
  • Preprocess and train multiple ML models.
  • Evaluate ML performance and select top models.
  • Application and Validation of Models.
  • Deployment of models for easy accessibility.

Graphical Abstract

image

Results

How to use

Data Availability

The data used for this project can be here

License

License: MIT

Citation

(Lamptey et al., 2025)

Lamptey E., Anyaele G., Arthur H., Adjadeh T., Sagoe D., Hanson G. and Awe O. I. (2025). Machine Learning Prediction of Potential Inhibitors of the Marburg Virus Gene 4 Small ORF Protein using MARVpred. Scientific Reports.

Reporting Issues

To report an issue please use the issues page (https://github.com/omicscodeathon/marburgdrug/issues). Please check existing issues before submitting a new one.

Contribute to Project

You can offer to help with the further development of this project by making pull requests on this repo. To do so, fork this repository and make the proposed changes. Once completed and tested, submit a pull request to this repo.

Reproducibility

Credits

Contributors:

First & Last Name Email address ORCID ID
1 Eugene Lamptey (Lead) lampteyeugen08@gmail.com 0009-0002-3354-1500
2 Gabriel Anyaele gabrielanyaele21@gmail.com 0009-0004-5094-5835
3 Harry Arthur harryaurthur06@gmail.com 0009-0007-5987-9143
4 George Hanson george.hanson417@gmail.com 0009-0007-2720-9102
5 Thaddeus Adjadeh thaddeusvandel@gmail.com 0009-0006-3777-3631
6 Dorothy Sagoe dorothysagoe1@gmail.com 0009-0003-2015-3282
7 Olaitan I. Awe laitanawe@gmail.com 0000-0002-4257-3611

About

Machine Learning and Molecular Dynamics Simulations Predict Potential Compounds against Marburg Virus

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •  

Languages