preprocessing/scale
Description
Scale data to unit variance and (optionally) zero mean.
Standardizes the expression matrix gene-wise so that each feature has unit
variance, optionally centering it to zero mean first. Values can be clipped
after scaling via max_value. Wraps the rapids-singlecell
rapids_singlecell.pp.scale function.
Inputs
Name | Type & Properties | Description |
|---|---|---|
--input -i | file required | Input h5mu file. |
--modality | string | Which modality from the input MuData file to process. |
--input_layer | string | Input layer to use. By default, X is scaled. |
Outputs
Name | Type & Properties | Description |
|---|---|---|
--output -o | file required output | Output h5mu file. |
--output_layer | string | Output layer to use. By default, use X. |
--output_compression | string | Compression format to use for the output AnnData and/or Mudata objects. By default no compression is applied. |
Options
Name | Type & Properties | Description |
|---|---|---|
--zero_center | boolean | If True, center the data to zero mean before scaling. If False, omit zero-centering, which preserves sparsity. |
--max_value | double | Clip (truncate) values to this maximum after scaling. By default, values are not clipped. |
Run this component
Run the following command to execute this component with Nextflow:
cat > params.yaml <<'EOM'
modality: [ "rna" ]
output: "$id.$key.output"
zero_center: [ true ]
id: "run"
publish_dir: "output/"
EOM
nextflow run https://packages.viash-hub.com/vsh/openpipeline_rapids.git \
-revision v0.1.3 \
-main-script target/nextflow/preprocessing/scale/main.nf \
-params-file params.yaml Relationships
Used by
1 relationships
Current component
preprocessing/scaleopenpipeline_rapids v0.1.3
Uses
0 relationships
No component dependencies found.