This library is designed to accelerate single cell data analysis by utilizing the capabilities of GPU computing. Drawing inspiration from both the scanpy library by Theis lab and the rapids-single-cell-examples library from Nvidia's RAPIDS team, it introduces GPU-optimized versions of their functions. While aiming to remain compatible with the original codes, the library's primary objective is to blend the computational strength of GPUs with the user-friendly nature of the scverse ecosystem.
The easiest way to install rapids-singlecell is to use one of the yaml file provided in the conda folder. These yaml files install everything needed to run the example notbooks and get you started.
conda env create -f conda/rsc_rapids_23.04.yml
# or
mamba env create -f conda/rsc_rapids_23.08.yml
As of version 0.4.0 rapids-singlecell is now on PyPI.
pip install rapids-singlecell
The default installer doesn't cover RAPIDS nor cupy. Information on how to install RAPIDS & cupy can be found here.
If you want to use RAPIDS new PyPI packages, the whole library with all dependencies can be install with:
pip install 'rapids-singlecell[rapids11]' --extra-index-url=https://pypi.nvidia.com #CUDA11.X
pip install 'rapids-singlecell[rapids12]' --extra-index-url=https://pypi.nvidia.com #CUDA12
It is important to ensure that the CUDA environment is set up correctly so that RAPIDS and Cupy can locate the necessary libraries.
To view a full guide how to set up a fully functioned single cell GPU accelerated conda environment visit GPU_SingleCell_Setup
Please have a look through the documentation
If you use this code, please cite:
Please also consider citing: rapids-single-cell-examples and scanpy
In addition to that please cite the methods' original research articles in the scanpy documentation
If you use the accelerated decoupler functions please cite decoupler