GENNUS (GENerative Approaches for NUcleotide Sequences) is a set of generative approaches designed to create synthetic nucleotide sequences.
GENNUS introduces data augmentation strategies using Generative Adversarial Networks (GANs) and Synthetic Minority Over-sampling Technique (SMOTE) to enhance nucleotide classification performance. Our findings reveal that GANs enhance model performance and provide a richer representation of minority classes, thus improving generalization capabilities across various machine learning frameworks.
This set contains MIRGAN and SMOTE_DNA.
You can download GENNUS in two different ways:
1. Direct Download
You can download the repository as a ZIP file and unpack it. This can be done via a web browser or via the command line.
wget https://github.com/chiquitto/GENNUS/archive/refs/heads/main.zip
unzip GENNUS-main.zip2. Cloning the GIT repository
Alternatively, you can clone the repository using Git:
git clone https://github.com/chiquitto/GENNUS.gitDetailed instructions on how to use each of the generative methods of GENNUS are provided below.
MIRGAN is a Generative Adversarial Networks-based approach designed to create synthetic Non-coding RNAs (ncRNAs) nucleotide sequences.
For detailed usage instructions, refer to MIRGAN.
SMOTE_DNA is a Synthetic Minority Over-sampling TEchnique (SMOTE)-based adapted to generate synthetic nucleotide sequence data.
For detailed usage instructions, refer to SMOTE_DNA.
We ask you to cite the main publication related to this software whenever you use any part of this software in any scientific publication.
Chiquitto, A. G. et al. GENNUS: Generative Approaches for Nucleotide Sequences Enhance Mirtron Classification. NAR Genomics and Bioinformatics (2025) doi:10.1093/nargab/lqaf072.
You may use the following .bibtex to cite the main publication of this software:
@article{ChiquittoGENNUSGenerative2025,
title = {{{GENNUS}}: {{Generative Approaches}} for {{Nucleotide Sequences Enhance Mirtron Classification}}},
author = {Chiquitto, Alisson Gaspar and Oliveira, Liliane Santana and Bugatti, Pedro Henrique and Saito, Priscila Tiemi Maeda and Basham, Mark and Raittz, Roberto Tadeu and Paschoal, Alexandre Rossi},
year = {2025},
journal = {NAR Genomics and Bioinformatics},
doi = {10.1093/nargab/lqaf072},
}
GNU General Public License v2.0
🐛🆘💬
To report bugs, to ask for help and to give any feedback, please contact Alisson G. Chiquitto (chiquitto@gmail.com) or Alexandre R. Paschoal (paschoal@utfpr.edu.br).
[Q1] What Operation System (OS) do I need to use GENNUS?
- We tested GENNUS in Linux Ubuntu 20.04 LTS. However, we believe that GENNUS should work on any UNIX OS able to have all dependencies installed.