wrappers/preprocessing/pca

Description

Computes PCA coordinates, loadings and variance decomposition, running either
the GPU (rapids-singlecell) or the CPU (scanpy) variant of pca, selected
with --device_type.

Inputs

Name	Type & Properties	Description
--input	file required	Input h5mu file. When running the GPU variant (`--device_type gpu`), genes with zero expression must be filtered out beforehand (e.g. with `filter_genes`), as rapids-singlecell PCA raises an error otherwise. The CPU variant tolerates zero-expression genes.
--modality	string	Which modality from the input MuData file to process.
--layer	string	Use specified layer for expression values instead of the .X object from the modality.
--var_input	string	Column name in .var matrix that will be used to select which genes to run the PCA on.

Name

Type & Properties

--input

file

required

--modality

string

--layer

string

--var_input

string

Compute

Name	Type & Properties	Description
--device_type	string	Which implementation to run: the GPU (rapids-singlecell) variant or the CPU (scanpy/squidpy) variant of the component. Selecting `gpu` requires a CUDA-capable GPU; the component errors out if none is available (there is no automatic fallback to CPU).

Name

Type & Properties

--device_type

string

Options

Name	Type & Properties	Description
--num_components	integer	Number of principal components to compute. Defaults to 50, or 1 - minimum dimension size of selected representation.
--chunked	boolean_true	If True, perform an incremental PCA on segments of a predefined size. Setting this flag automatically implies zero centering. Must be specified together with --chunk_size.
--chunk_size	integer	Number of observations to include in each chunk. Required if chunked=True was passed.
--random_state	integer	Used to set the initial states for the optimization.

Name

Type & Properties

--num_components

integer

--chunked

boolean_true

--chunk_size

integer

--random_state

integer

Outputs

Name	Type & Properties	Description
--output	file required output	Output h5mu file.
--obsm_output	string	In which .obsm slot to store the resulting embedding.
--varm_output	string	In which .varm slot to store the resulting loadings matrix.
--uns_output	string	In which .uns slot to store the resulting variance objects.
--overwrite	boolean	Allow overwriting .obsm, .varm and .uns slots.
--output_compression	string	Compression format to use for the output AnnData and/or Mudata objects. By default no compression is applied.

Name

Type & Properties

--output

file

required

output

--obsm_output

string

--varm_output

string

--uns_output

string

--overwrite

boolean

--output_compression

string

Run this component

Run the following command to execute this component with Nextflow:

cat > params.yaml <<'EOM'  
modality: [ "rna" ]  
device_type: [ "gpu" ]  
output: "$id.$key.output.h5mu"  
obsm_output: [ "X_pca" ]  
varm_output: [ "pca_loadings" ]  
uns_output: [ "pca_variance" ]  
overwrite: [ false ]  
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/wrappers/preprocessing/pca/main.nf \  
  -params-file params.yaml

wrappers/preprocessing/pca

Inputs

Compute

Options

Outputs

Run this component

Relationships

Used by

Uses