The interact package provide an implementation of INtERAcT (Interaction networks from vector representation of words) together with a selection of different metrics. Additionally, it exposes various utilities parse data from STRING DB, UniProt and files in gmt format.

For details check the paper.

If you use INtERAcT in your research, please consider citing:

@article{manica2019context,
  title={Context-specific interaction networks from vector representation of words},
  author={Manica, Matteo and Mathis, Roland and Cadow, Joris and Mart{\'\i}nez, Mar{\'\i}a Rodr{\'\i}guez},
  journal={Nature Machine Intelligence},
  volume={1},
  number={4},
  pages={181--190},
  year={2019},
  publisher={Nature Publishing Group}
}

We strongly recommend to work inside a virtual environment (venv).

Create the environment:

python3 -m venv venv

Activate it:

source venv/bin/activate

pip3 install -r requirements.txt

The module can be installed either in editable mode:

pip3 install -e .

Or as a normal package:

pip3 install .

Check the folder examples for a quick start on inferring interaction from an embedding using interact.

The INtERAcT web-service has been deprecated in favour of the python package hosted in this repository. Please check the examples to use INtERAcT in your research.