Rapids-singlecell offers enhanced single-cell data analysis as a near drop-in replacement predominantly for scanpy, while also incorporating select functionalities from squidpy and decoupler. Utilizing GPU computing with cupy and Nvidia’s RAPIDS, it emphasizes high computational efficiency.

References:

• if you use the code, cite this

• rapids-singlecell Main Site

• rapids-singlecell module currently can only run on V100,V100x, and A100 GPU.
• Important environment variables: $RSC_TEST_DATA

Allocate an interactive session and run the program.
Sample session (user input in bold):

[user@biowulf]$ sinteractive --gres=gpu:1,lscratch:10 --constraint="gpuv100|gpuv100x|gpua100" -c 8 --mem=32g 
salloc.exe: Pending job allocation 46116226
salloc.exe: job 46116226 queued and waiting for resources
salloc.exe: job 46116226 has been allocated resources
salloc.exe: Granted job allocation 46116226
salloc.exe: Waiting for resource configuration
salloc.exe: Nodes cn3144 are ready for job

[user@cn3144 ~]$ module load rapids-singlecell

[user@cn3144 ~]$ cd /data/$USER/

[user@cn3144 ~]$ cp $RSC_TEST_DATA .

[user@cn3144 ~]$ python3-rsc
Python 3.11.9 | packaged by conda-forge | (main, Apr 19 2024, 18:36:13) [GCC 12.3.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import scanpy as sc
>>> import rapids_singlecell as rsc
>>> adata = sc.read("krasnow_hlca_10x.sparse.h5ad")
>>> rsc.get.anndata_to_GPU(adata)

[user@biowulf ~]$

[user@biowulf]$ sinteractive --gres=gpu:1,lscratch:10 --constraint="gpuv100|gpuv100x|gpua100" -c 8 --mem=32g -T
salloc.exe: Pending job allocation 46116226
salloc.exe: job 46116226 queued and waiting for resources
salloc.exe: job 46116226 has been allocated resources
salloc.exe: Granted job allocation 46116226
salloc.exe: Waiting for resource configuration
salloc.exe: Nodes cn3144 are ready for job

[user@cn3144]$ module load rapids-singlecell
[user@cn3144]$ jupyter-rsc lab --ip localhost --port $PORT1 --no-browser

Create a batch input file (e.g. rapids-singlecell.sh). For example:

#!/bin/bash
set -e
module load rapids-singlecell
cd /data/$USER
python3-rsc run-rsc.py 

Submit this job using the Slurm sbatch command.

sbatch [--cpus-per-task=#] [--mem=#] rapids-singlecell.sh