CellBender is a software package for eliminating technical artifacts from high-throughput single-cell RNA sequencing (scRNA-seq) data.

References:

• Stephen J Fleming, Mark D Chaffin, Alessandro Arduini, Amer-Denis Akkad, Eric Banks, John C Marioni, Anthony A Philippakis, Patrick T Ellinor, and Mehrtash Babadi
Unsupervised removal of systematic background noise from droplet-based single-cell experiments using CellBender Nature Methods, 2023. https://doi.org/10.1038/s41592-023-01943-7

• Cellbender main page

• Cellbender Github

• Module Name: cellbender (see the modules page for more information)
• Example files in : /usr/local/apps/cellbender/example-inputs

Allocate an interactive session and run the program.
Sample session (user input in bold):
Please note cellbender is compute intensive and needs sufficient memory allocation

[user@biowulf ~]$ sinteractive --gres=gpu:a100:1 --cpus-per-task=8 
salloc: Pending job allocation 13632637
salloc: job 13632637 queued and waiting for resources
salloc: job 13632637 has been allocated resources
salloc: Granted job allocation 13632637
salloc: Waiting for resource configuration
salloc: Nodes cn4308 are ready for job

[user@cn4308]$ module load cellbender
[+] Loading cellbender  0.3.1  on cn4308
[+] Loading singularity  4.0.1  on cn4308
[+] Loading python 3.10  ...

[user@cn4308]$ cellbender -h 
usage: cellbender [-h] [-v] {remove-background} ...

CellBender is a software package for eliminating technical artifacts from                                                                       
high-throughput single-cell RNA sequencing (scRNA-seq) data.

optional arguments:
  -h, --help           show this help message and exit
  -v, --version        show program's version number and exit

sub-commands:
  valid cellbender commands

  {remove-background}
    remove-background  Remove background ambient RNA and barcode-swapped reads
                       from a count matrix, producing a new count matrix and
                       determining which barcodes contain real cells.
#copy over example data                                                                                       
[user@cn4308]$  cp -a /usr/local/apps/cellbender/example-inputs . 
[user@cn4308]$  cd example-inputs 

Create a batch input file (e.g. cellbender.sh). For example:

 
#!/bin/bash

module load cellbender

cellbender remove-background \
    --cuda \
    --input tiny_raw_feature_bc_matrix.h5ad \
    --output tiny_output.h5 \
    --expected-cells 500 \
    --total-droplets-included 2000

The --cuda option is to be run when submitting to GPUs

Submit this job using the Slurm sbatch command.

sbatch -p gpu --gres=gpu:a100:1 --cpus-per-task=8 cellbender.sh