🐝 BEELINE: Benchmarking gEnE reguLatory network Inference from siNgle-cEll transcriptomic data 🐝

This fork uses Singularity instead of Docker to run the containers. Check the main repository for further details.

The documentation is available at: https://murali-group.github.io/Beeline/.

Quick setup:

• Initial creation of the Singularity images requires Docker, subsequent runs do not.
• To install docker on Ubuntu 18.04, follow the steps mentioned here
• Setup docker to run docker without sudo using sudo usermod -aG docker $USER, if you haven't already. See more details here
• To create the Singularity containers for each of the algorithms run . initialize.sh (this step will take a while). It first creates a Docker container, then converts it to a Singularity SIF image.
• We recommend using Anaconda for Python. Run the . setupAnacondaVENV.sh command to automatically create an Anaconda virtual environment named BEELINE from requirements.txt and install necessary libraries required to run BEELINE.

We provided an example dataset under inputs/example/GSD/ and a corresponding configuration file necessary for running GRN inference using 12 methods described in BEELINE.

• To compute proposed reconstructions on the example dataset, run python BLRunner.py --config config-files/config.yaml
• To compute areas under the ROC and PR curves for the proposed reconstructions, run python BLEvaluator.py --config config-files/config.yaml --auc. To display the complete list of evalutation options, run python BLEvaluator.py --help.

If you use BEELINE in your research, please cite:

Pratapa, A., Jalihal, A.P., Law, J.N., Bharadwaj, A., Murali, T. M. (2020) "Benchmarking algorithms for gene regulatory network inference from single-cell transcriptomic data." Nature Methods, 17, 147–154.

Link to the pubication: https://www.nature.com/articles/s41592-019-0690-6

The preprint version of this article is available at: https://doi.org/10.1101/642926

The repository for BoolODE is located at: https://github.com/Murali-group/BoolODE

The input datasets used in BEELINE are available at: https://doi.org/10.5281/zenodo.3378975

Twitter thread link: https://twitter.com/t_m_murali/status/1215302095601119234?s=20