Description

Module to use scAR to remove ambient RNA from single-cell RNA-seq data

Input

Name
Description
Pattern

0 ()

1 ()

2 ()

input_layer (string)

Layer to use as input. Defaults to X.

output_layer (string)

Layer to save the denoised counts to. Defaults to scar.

max_epochs (integer)

Maximum number of epochs to train the model. Defaults to the heuristic default.

n_batch (integer)

Number of batches to use for generating the ambient profile. Defaults to 1. This can be increased to prevent out-of-memory errors.

Output

Name
Description
Pattern

0 ()

0 ()

Tools

scvitools Documentation

scvi-tools (single-cell variational inference tools) is a package for end-to-end analysis of single-cell omics data

https://github.com/scverse/scvi-toolsLicense: BSD-3-clause

scar Documentation

scAR (single-cell Ambient Remover) is a deep learning model for removal of the ambient signals in droplet-based single cell omics.

https://github.com/Novartis/scarLicense: Novartis Terms of License
Authors