LIBRA

LIBRA is a Python toolbox for Single-Cell data integration and prediction. This project aims to lower the barrier for new users to AI state-of-the-art techniques and propose an unbalanced-AE for shared latent representation extraction between two paired-Single-Cell omics. This package provides state-of-art performance while retains good execution timing in opposite to other AI methods that require many hours to finish similar training processes. This makes possible to train hundreds of models in parallel in search of parameters that further optimize the results in moderate times using aLIBRA.

LIBRA has been designed using TensorFlow, any system that supports it is compatible with LIBRA package. It has been tested on LINUX OS.

We encourage users and developers to report problems, request features, ask for help, or leave general comments on GitHub. Please refer to our usage guide if you wish to extend LIBRA’s functionality and/or contribute to the project.

LIBRA is distributed under the open source GNU General Public License v3.0. Please cite this paper if you publish work using LIBRA:

Getting Started

• Quickstart
• Tutorial

Resources

• R scripts
• Python scripts

Notebooks

• Vignettes