SLE-autoantibody-prediction

Author

Affiliation

Leon C. Reteig

University Medical Center Utrecht

This research project aims to predict diagnosis of Systemic Lupus Erythematosus using machine learning and microarray measurements of auto-antibodies . The (python) code is available on GitHub and belongs to the following publication:

Brunekreef TE, Reteig LC, Limper M, Haitjema S, Dias J, Mathsson-Alm L, van Laar JM, Otten HG. Microarray analysis of autoantibodies can identify future Systemic Lupus Erythematosus patients. Human Immunology. 2022 Jun 1;83(6):509-14.

The navigation bar on the left links to all the computational notebooks with the analyses and results for this project. The Main Results notebook contains all the results that are reported in the paper. The other notebooks contain all the (exploratory) analyses that we ran (for which we were able to publish the code).

There’s also a project package with a number of python modules containing supporting code that are imported in the notebooks.

The original patient data were not shared along with the publication. If you don’t have access to this data, but would still like to run the code, the notebooks offer the option to generate some simple synthetic data.

Reproducibility

You’ll need either the conda or the mamba package manager to recreate the computational environment. It might take conda a while to resolve the environment in environment.yml (see step 3), so it’s recommended to use mamba instead.

If you already have conda installed, you can install mamba as follows:
```
conda install mamba -n base -c conda-forge
```
If you don’t have conda, you can skip it and install mambaforge instead:
```
wget "https://github.com/conda-forge/miniforge/releases/latest/download/Mambaforge-$(uname)-$(uname -m).sh"
bash Mambaforge-$(uname)-$(uname -m).sh
```

Clone this repo, e.g.:

git clone https://github.com/umcu/SLE-autoantibody-prediction
cd SLE-autoantibody-prediction

Make and activate the virtual environment, e.g.:

mamba env create -f environment.yaml
conda activate SLE

Install the project package, e.g.
```
pip install -e .
```
Open and run any of the notebooks, for instance with JupyterLab:
```
jupyter lab
```

Contents

Reproducibility