wrappers/preprocessing/harmony_integrate

Description

Integrate observations over one or more batch/covariate columns using Harmony,
running either the GPU (rapids-singlecell) or the CPU (harmonypy) variant of
harmony_integrate, selected with --device_type.

Inputs

Name	Type & Properties	Description
--input	file required	Input h5mu file.
--modality	string	Which modality from the input MuData file to process.
--obsm_input	string	Which .obsm slot to use as the PCA embedding to integrate (basis).
--obs_covariates	string required multiple	The .obs columns to integrate over (the batch/covariate keys passed to Harmony). Provide one or more comma-separated column names. When multiple keys are provided, a combined batch variable is created from all columns.

Name

Type & Properties

--input

file

required

--modality

string

--obsm_input

string

--obs_covariates

string

required

multiple

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

Outputs

Name	Type & Properties	Description
--output	file required output	Output h5mu file containing the integrated embedding.
--obsm_output	string	In which .obsm slot to store the Harmony-corrected embedding.
--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

--output_compression

string

Options

Name	Type & Properties	Description
--theta	double multiple	Diversity clustering penalty parameter. theta=0 does not encourage any diversity; larger values result in more aggressive diversity-encouraging correction over the covariates. Provide a single value for all covariates, or one value per --obs_covariates entry.

Name

Type & Properties

--theta

double

multiple

rapids-singlecell options

Name	Type & Properties	Description
--overwrite	boolean	Allow overwriting the .obsm output slot if it already exists.
--flavor	string	Which Harmony implementation to use. 'harmony2' is the faster reimplementation; 'harmony1' reproduces the original algorithm.
--n_clusters	integer	Number of clusters used by Harmony. If not set, the value is chosen automatically.
--max_iter_harmony	integer	Maximum number of rounds to run Harmony.
--random_state	integer	A random seed.

Name

Type & Properties

--overwrite

boolean

--flavor

string

--n_clusters

integer

--max_iter_harmony

integer

--random_state

integer

Run this component

Run the following command to execute this component with Nextflow:

cat > params.yaml <<'EOM'  
modality: [ "rna" ]  
obsm_input: [ "X_pca" ]  
device_type: [ "gpu" ]  
output: "$id.$key.output.h5mu"  
obsm_output: [ "X_pca_integrated" ]  
theta: [ 2 ]  
overwrite: [ false ]  
flavor: [ "harmony2" ]  
max_iter_harmony: [ 10 ]  
random_state: [ 0 ]  
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/harmony_integrate/main.nf \  
  -params-file params.yaml

wrappers/preprocessing/harmony_integrate

Inputs

Compute

Outputs

Options

rapids-singlecell options

Run this component

Relationships

Used by

Uses