arXiv 2603.024022026-03-02q-bio.GN

大规模GPU加速单细胞分析的rapids-singlecell

GPU-accelerated single-cell analysis at scale with rapids-singlecell

Institute of Computational Biology, Helmholtz Center Munich（亥姆霍兹慕尼黑中心计算生物学研究所）；NVIDIA Corporation（英伟达公司）；TUM School of Life Sciences Weihenstephan, Technical University of Munich（慕尼黑工业大学魏森施泰芬生命科学学院）；Department of Experimental Psychology, University of Oxford（牛津大学实验心理学系）；TUM School of Computing, Information and Technology, Technical University of Munich（慕尼黑工业大学计算、信息与技术学院）；Institute of Medical Bioinformatics and Systems Medicine, Medical Center - University of Freiburg, Faculty of Medicine, University of Freiburg（弗赖堡大学医学院弗赖堡大学医学中心医学生物信息与系统医学研究所）

Severin Dicks, Lukas Heumos, Lilly May, Sara Jimenez, Philipp Angerer, Ilan Gold, Isaac Virshup, Felix Fischer, Michelle Gill, Melanie Boerries, Corey J Nolet, … 展开作者

Severin Dicks, Lukas Heumos, Lilly May, Sara Jimenez, Philipp Angerer, Ilan Gold, Isaac Virshup, Felix Fischer, Michelle Gill, Melanie Boerries, Corey J Nolet, Tiffany J. Chen, Fabian J. Theis

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

rapids-singlecell通过GPU加速实现大规模单细胞分析，显著提升处理速度，使大规模数据实时分析成为可能。

摘要：

单细胞测序技术揭示了高分辨率的细胞异质性，推动了我们对生物复杂性的理解。随着数据集开始扩展到数百万个细胞，计算工作流面临显著的瓶颈，基于CPU的分析流程需要数小时或数天才能完成常规处理步骤，如过滤、标准化和聚类。这些可扩展性限制从根本上限制了常见的交互数据探索和迭代假设检验。在这里，我们介绍了rapids-singlecell，这是一个GPU加速的框架，原生集成了scverse生态系统，并直接操作AnnData数据结构，为单细胞工作流程提供了数量级的速度提升。基于CuPy数组和NVIDIA CUDA-X Data Science（RAPIDS）生态系统，rapids-singlecell为基于scanpy的核心分析步骤提供了接近即插即用的GPU替代方案。在标准的单细胞工作流程中，如预处理、降维、邻近图构建、聚类和批次校正，rapids-singlecell相比优化的CPU基线，实现了高达数百倍的速度提升。这将分析时间从几小时减少到几分钟，同时保持一致的生物解释。这些性能改进使在不需要数据分割的情况下分析大数据集成为可能。结合实时参数调优和迭代工作流，rapids-singlecell使大规模单细胞分析成为可能。

英文摘要：

Single-cell sequencing technologies reveal cellular heterogeneity at high resolution, advancing our understanding of biological complexity. As datasets start to scale to tens of millions of cells, computational workflows face substantial bottlenecks, with CPU-based analytical pipelines requiring hours or days for routine processing steps like filtering, normalization, and clustering. These scalability limitations fundamentally restrict common interactive data exploration and iterative hypothesis testing. Here we introduce rapids-singlecell, a GPU-accelerated framework that integrates natively with the scverse ecosystem and operates directly on the AnnData data structure, which delivers orders-of-magnitude speedups for single-cell workflows. Built on CuPy arrays and the NVIDIA CUDA-X Data Science (RAPIDS) ecosystem, rapids-singlecell provides near drop-in GPU replacements for core scanpy-based analysis steps. Across standard single-cell workflows such as preprocessing, dimensionality reduction, neighborhood graph construction, clustering, and batch correction, rapids-singlecell achieves speedups of up to several hundred-fold compared to optimized CPU baselines. This reduces analysis time from hours to minutes on standard hardware, while maintaining consistent biological interpretations. These performance improvements make it possible to analyze large data sets in close to real time, without the need for data splitting. Together with real-time parameter tuning and iterative workflows, rapids-singlecell makes interactive large-scale single-cell analysis possible.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。