Split h5mu train test

Split mudata object into training and testing (and validation) datasets based on observations into separate mudata objects.

Info

ID: split_h5mu_train_test
Namespace: dataflow

Links

Source

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/dataflow/split_h5mu_train_test/main.nf \
  --help

Run command

Example of params.yaml

# Inputs
input: # please fill in - example: "input.h5mu"
modality: "rna"

# Outputs
# output_train: "$id.$key.output_train.h5mu"
# output_test: "$id.$key.output_test.h5mu"
# output_val: "$id.$key.output_val.h5mu"
# compression: "gzip"

# Split arguments
test_size: 0.2
# val_size: 123.0
shuffle: false
# random_state: 123

# Nextflow input-output arguments
publish_dir: # please fill in - example: "output/"
# param_list: "my_params.yaml"

# Arguments

nextflow run openpipelines-bio/openpipeline \
  -r 2.1.0 -latest \
  -profile docker \
  -main-script target/nextflow/dataflow/split_h5mu_train_test/main.nf \
  -params-file params.yaml

Note

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

Argument groups

Inputs

Input dataset in mudata format.

Name	Description	Attributes
--input	The input (query) data to be labeled. Should be a .h5mu file.	file, required, example: "input.h5mu"
--modality	Which modality to process.	string, default: "rna"

Outputs

Output arguments.

Name	Description	Attributes
--output_train	The output training data in mudata format.	file, required, example: "output_train.h5mu"
--output_test	The output testing data in mudata format.	file, required, example: "output_test.h5mu"
--output_val	The output validation data in mudata format.	file, example: "output_val.h5mu"
--compression		string, example: "gzip"

Split arguments

Model arguments.

Name	Description	Attributes
--test_size	The proportion of the dataset to include in the test split.	double, default: 0.2
--val_size	The proportion of the dataset to include in the validation split.	double
--shuffle	Whether or not to shuffle the data before splitting.	boolean_true
--random_state	The seed used by the random number generator.	integer

Authors

• Jakub Majercik (author)