https://github.com/csiro/emmai
Computational pipeline to enhance Genome-Scale Modelling prediction accuracy
https://github.com/csiro/emmai
Last synced: 3 months ago
JSON representation
Computational pipeline to enhance Genome-Scale Modelling prediction accuracy
- Host: GitHub
- URL: https://github.com/csiro/emmai
- Owner: csiro
- License: gpl-3.0
- Created: 2025-09-11T05:46:40.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2026-02-19T06:08:40.000Z (4 months ago)
- Last Synced: 2026-02-19T12:20:23.499Z (4 months ago)
- Language: Jupyter Notebook
- Size: 33.5 MB
- Stars: 1
- Watchers: 0
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
README
# EMMAi pipeline
## Description
The `EMMAi` repository contains a collection of IPython notebooks,
Python scripts, and SLURM batch files designed to facilitate the EMMAi
computational workflow.
## Contents
- **IPython Notebooks**: Interactive notebooks for data analysis and visualization.
- **Python Scripts**: Standalone scripts for various computational tasks. These
for the most part duplicate the code in the IPython notebooks.
- **SLURM Batch Files**: Scripts to manage and execute jobs on SLURM-based
high-performance computing clusters. These execute the Python scripts after
activating a CONDA environment.
## Requirements
To use the contents of this repository, you will need the following:
- Python 3.9
- Jupyter Notebook
- SLURM workload manager (for batch files)
- MAMBA (or CONDA if you prefer)
## Installation
1. Clone the repository:
```bash
git clone --recurse-submodules git@github.com:csiro-internal/emmai.git
```
2. There are two installation scripts provided in the setup_scripts directory. 1
One for HPC systems with GPU and CPU clusters - [see the detailed README](setup_scripts/README_HPC.md) and
one for standalone systems - [see the detailed README](setup_scripts/README_standalone.md)
## Executing the pipeline
1. After following the installation guidelines you can choose to execute the
pipeline in 1 of three ways, or a combination of the three - if you know what
you are doing.
i. By running the Jupyter notebooks sequentially starting with:
notebooks/1_data_retrieval.ipynb
ii. By executing the python scripts sequentially starting with:
source env.sh
python_scripts/1_data_retrieval.py
iii. Or by running a combination of the batch scripts in hpc_scripts. See
[See the HPC README](hpc_scripts/README.md) for details.
## License
This software is licensed under the GNU General Public License, version 3 (GPLv3).
Copyright (C) 2025, CSIRO
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or any later version.