corneto 1.0.0rc3

CORNETO: Unified knowledge-driven network inference from omics data.

Paper | Documentation | Notebooks

CORNETO is a Python framework for inferring biological networks from omics data by framing them as optimisation problems. It provides a unified, flexible, and extensible API to solve a wide range of network inference problems, including signalling pathway and metabolic model reconstruction.

Why CORNETO?

🚀 Installation

Recommended Installation

For most users, we recommend creating a conda environment and installing the research flavor:

conda create -n corneto python>=3.11
conda activate corneto
conda install python-graphviz
pip install corneto[research]

This installs CORNETO with all research dependencies including Gurobi, PICOS, and visualization libraries.

Standard Installation

The minimal installation via pip provides core functionalities:

pip install corneto

Optional dependencies

CORNETO provides several optional dependency groups:

• plot: Graphviz, NetworkX, and Matplotlib visualization support
• research: Full research stack with Gurobi, PICOS, visualization, and network tools
• os: Open-source solvers (SCIP, HiGHS) with visualization and network tools
• ml: Machine learning dependencies (JAX, Keras, scikit-learn)

Install any combination with:

pip install corneto[plot]         # Visualization without the full research stack
pip install corneto[research,ml]  # Multiple extras

Gurobi Installation

For research problems, we strongly recommend using the Gurobi solver. Gurobi is a commercial solver that offers free academic licences. To install and configure Gurobi, please refer to the official Gurobi documentation. After installation, you can verify that Gurobi is correctly set up by running:

from corneto.utils import check_gurobi
check_gurobi()

Development Installation

If you plan to contribute to CORNETO, we recommend using Poetry for dependency management.

git clone https://github.com/saezlab/corneto.git
cd corneto
poetry install --with dev

Legacy Compatibility

The stable version used by LIANA+ and NetworkCommons remains available. However, we recommend using the latest version for new projects to access the latest features and improvements described in our manuscript.

🧪 Experiments

Notebooks with the experiments presented in the manuscript are available here: https://github.com/saezlab/corneto-manuscript-experiments

🎓 How to cite

@article{Rodriguez-Mier2025,
	author = {Rodriguez-Mier, Pablo and Garrido-Rodriguez, Martin and Gabor, Attila and Saez-Rodriguez, Julio},
	title = {Unifying multi-sample network inference from prior knowledge and omics data with CORNETO},
	journal = {Nature Machine Intelligence},
	year = {2025},
	doi = {10.1038/s42256-025-01069-9},
	url = {https://www.nature.com/articles/s42256-025-01069-9}
}

🙏 Acknowledgements

CORNETO is developed at the Institute for Computational Biomedicine (Heidelberg University). We acknowledge funding from the European Unions Horizon 2020 Programme under the grant agreement No 951773 (PerMedCoE https://permedcoe.eu/) and under grant agreement No 965193 (DECIDER https://www.deciderproject.eu/)