Installation

Bionium-X requires Python 3.9+ and can be installed via pip. We recommend using a virtual environment (e.g., venv or conda).

Core Installation

The core library is lightweight and installs in seconds. It relies solely on standard scientific packages (numpy, scipy, astropy).

pip install bionium-x

Note: If installing from the source repository:

git clone https://github.com/bionium-x-research/Bionium-X.git
cd Bionium-X
pip install .

Bionium-X offers several optional extensions for heavy computational tasks.

To utilize the 1D Convolutional Neural Network (CNN) for rapid spectral inference, you need to install the PyTorch dependencies:

pip install bionium-x[ml]

This will download the heavy PyTorch binaries and allow bioniumx.models.fetch to download the pre-trained .pth network weights.

For Bayesian model comparison, Markov Chain Monte Carlo (MCMC) fitting, and parallelized physics modules:

pip install bionium-x[science]

To install all recommended extensions:

pip install bionium-x[full]