moscot is a scalable framework for Optimal Transport (OT) applications in single-cell genomics. It can be used for
- trajectory inference (incorporating spatial and lineage information)
- mapping cells to their spatial organisation
- aligning spatial transcriptomics slides
- translating modalities
- prototyping of new OT models in single-cell genomics
moscot is powered by OTT which is a JAX-based Optimal Transport toolkit that supports just-in-time compilation, GPU acceleration, automatic differentiation and linear memory complexity for OT problems.
You can install moscot via:
pip install moscot
In order to install moscot from in editable mode, run:
git clone https://github.com/theislab/moscot cd moscot pip install -e .
For further instructions how to install jax, please refer to https://github.com/google/jax.
Please have a look at our documentation
Our preprint "Mapping cells through time and space with moscot" can be found here.