rapids_singlecell
rapids_singlecell copied to clipboard
scverse
Rapids_singlecell: A GPU-accelerated tool for scRNA analysis. Offers seamless scverse compatibility for efficient single-cell data processing and analysis.
This adds dask support Functions to add: * [x] `calculate_qc_metrics` * [x] `normalize_total` * [x] `log1p` * [x] `highly_variable_genes` with `seurat` and `cell_ranger` * [x] `scale` * [x] `PCA` *...
I added a separate file here containing the refactor. It drops the number of lines by 50, and that's only first pass (second would be more). To reproduce my benchmark,...
Hi, rapids_singlecell raised an error when running rsc.pp.highly_variable_genes. Could you please take a look at it？Below are the error information. Thanks in advance! Traceback (most recent call last): File "",...
**Describe the bug** While running the leiden algorithm `rsc.tl.leiden(adata, key_added="leiden_res0_25", resolution=0.25` , I got a "CUDA error encountered 101 cudaErrorInvalidDevice invalid device ordinal" Just setting `rmm.reinitialize` `managed_memory` to `False` resolved...
Hello, I try to perform CNV detection with infercnvpy with rapids_singlecell integrated 1 M cells. It still work slow. Any suggestion to speed up the process of CNV detection? Could...
I bring my initial implementation of `read_mtx_gpu` from gpu branch of scanpy, now available at `rsc.read_mtx`! Here are some infos: - I added an option to keep the loaded matrix...
Please don't use cuml-23.08 with cuda 12. PCA will fail for larger datasets https://github.com/rapidsai/cuml/issues/5555
We’ve been thinking about checking if Scanpy’s neighbors backends can benefit from the shortcut, but it seems like PyNNDescent behaves differently (`(n_neighbors - 1) * n_obs` instead of `n_neighbors *...
