Regress out

Regress out (mostly) unwanted sources of variation.

Info

ID: regress_out
Namespace: transform

Uses simple linear regression. This is inspired by Seurat’s regressOut function in R [Satija15]. Note that this function tends to overcorrect in certain circumstances as described in issue theislab/scanpy#526. See https://github.com/theislab/scanpy/issues/526

Example commands

You can run the pipeline using nextflow run.

View help

You can use --help as a parameter to get an overview of the possible parameters.

nextflow run openpipelines-bio/openpipeline \
  -r 2.1.0 -latest \
  -main-script target/nextflow/transform/regress_out/main.nf \
  --help

Run command

Example of params.yaml 
# Arguments
input: # please fill in - example: "input.h5mu"
# output: "output.h5mu"
# output_compression: "gzip"
modality: "rna"
# obs_keys: ["foo"]
# input_layer: "X_normalized"
# output_layer: "X_regressed"

# Nextflow input-output arguments
publish_dir: # please fill in - example: "output/"
# param_list: "my_params.yaml"
nextflow run openpipelines-bio/openpipeline \
  -r 2.1.0 -latest \
  -profile docker \
  -main-script target/nextflow/transform/regress_out/main.nf \
  -params-file params.yaml
Note

Replace -profile docker with -profile podman or -profile singularity depending on the desired backend.

Argument group

Arguments

Name Description Attributes
--input Input h5mu file file, required, example: "input.h5mu"
--output Output h5mu file. file, required, default: "output.h5mu"
--output_compression The compression format to be used on the output h5mu object. string, example: "gzip"
--modality Which modality (one or more) to run this component on. string, default: "rna"
--obs_keys Which .obs keys to regress on. List of string, multiple_sep: ";"
--input_layer The layer of the adata object to regress on. If not provided, the X attribute of the adata object will be used. string, example: "X_normalized"
--output_layer The layer of the adata object containing the regressed count data. If not provided, the X attribute of the adata object will be used. string, example: "X_regressed"

Authors

  • Robrecht Cannoodt (maintainer, contributor)