scverse/rapids-singlecell

rapids-singlecell: GPU-accelerated framework for scRNA analysis

What it solves

It addresses the performance bottlenecks of analyzing large single-cell datasets by moving common analysis workflows from the CPU to the GPU, significantly speeding up computation.

How it works

The library uses an AnnData-first API and leverages CuPy and NVIDIA RAPIDS to perform computations on the GPU. It is designed to be largely compatible with the Scanpy API, allowing users to transition their workflows to GPU acceleration without significant code changes.

Who it’s for

Researchers and data scientists working with single-cell analysis who need to process large datasets more efficiently.

Highlights

  • GPU Acceleration: Speeds up common single-cell workflows using AnnData.
  • Ecosystem Compatibility: Integrates with and maintains compatibility with Scanpy, Squidpy, decoupler, and pertpy.
  • Easy Installation: Can be installed via PyPI and Conda.

Related

  • Project
    scverse/scanpy

    A scalable Python toolkit for analyzing single-cell gene expression data, supporting preprocessing, clustering, and trajectory inference for datasets with over a million cells.

  • Project
    NVIDIA/cuml

    A GPU-accelerated machine learning library that provides scikit-learn-style APIs and a transparent acceleration module to speed up ML workloads on NVIDIA GPUs.

  • Project
    NVIDIA/cudf

    A GPU-accelerated DataFrame library for tabular data processing that mirrors the pandas API and integrates with Polars and Dask.

  • Project
    rapidsai/cugraph

    A collection of GPU-accelerated graph analytics packages that enable the creation and manipulation of graphs and the execution of scalable graph algorithms.

  • Project
    graphistry/pygraphistry

    A Python library for high-performance graph visualization and analytics that leverages GPU acceleration and columnar data to handle millions of edges.