Start with a populated object | Run the workflow | Verify preservation | Collision and realization safety | Provenance
Package: cudacellr 0.4.0
Yaoxiang Li
cudacellr: GPU-Aware Single-Cell Analysis Workflows
Provides single-cell analysis primitives for sparse count matrices, including library-size normalization, log-normalization, highly variable feature selection, principal component analysis, and nearest-neighbour construction. Integrates the 'cudaverse' numerical and sparse layers while preserving matrix identifiers and recording the computation backend for each stage. Optional adapters preserve native 'SingleCellExperiment' and 'SeuratObject' version 5 object structures.
Authors:
cudacellr_0.4.0.tar.gz
cudacellr_0.4.0.zip(r-4.7-any)cudacellr_0.4.0.zip(r-4.6-any)
cudacellr_0.4.0.tar.gz(r-4.7-any)cudacellr_0.4.0.tar.gz(r-4.6-any)
cudacellr_0.4.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
cudacellr/json (API)
| # Install 'cudacellr' in R: |
| install.packages('cudacellr', repos = c('https://cran.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/cudaverse/cudacellr/issues
Pkgdown/docs site:https://cudaverse.github.io
Last updated from:4c94e8e4aa. Checks:6 OK. Indexed: yes.
| Target | Result | Time | Files | Syslog |
|---|---|---|---|---|
| linux-devel | OK | 168 | ||
| source / vignettes | OK | 198 | ||
| linux-release | OK | 158 | ||
| windows-devel | OK | 76 | ||
| windows-release | OK | 106 | ||
| wasm-release | OK | 147 |
Exports:cuda_cell_neighborscuda_cell_pcacuda_hvgcuda_normalize_countscuda_provenancecudacell_scecudacell_seuratcudacell_workflow
A native SeuratObject v5 workflow
Last update: 2026-10-27
Started: 2026-10-27
A native SingleCellExperiment workflow
Start with a populated object | Run the workflow | Verify preservation | Normalization and size factors | Collision and memory safety | Provenance and downstream embeddings
Last update: 2026-10-27
Started: 2026-10-27
Backend provenance and CUDA diagnostics
Prepare CUDA | Prepare a count matrix | Normalize, select features, and run PCA and kNN | Read the provenance table | Native stage boundaries | Device requests and failures | Plan memory and workload size | A small CPU reference
Last update: 2026-10-27
Started: 2026-10-27
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| Construct a nearest-neighbour representation | cuda_cell_neighbors |
| Run PCA on highly variable single-cell features | cuda_cell_pca |
| Select highly variable features | cuda_hvg |
| Normalize a single-cell count matrix | cuda_normalize_counts |
| Inspect provenance stored on native single-cell containers | cuda_provenance-methods cuda_provenance.Seurat cuda_provenance.SingleCellExperiment |
| Run a cudacell workflow on a SingleCellExperiment | cudacell_sce |
| Run a cudacell workflow on a Seurat object | cudacell_seurat |
| Run the initial cudacellr workflow | cudacell_workflow |