Scarches

Performs reference mapping with scArches

Info

ID: scarches
Namespace: integrate

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/integrate/scarches/main.nf \
  --help

Run command

Example of params.yaml 
# Inputs
input: # please fill in - example: "path/to/file"
# layer: "foo"
modality: "rna"
# input_obs_batch: "foo"
# input_obs_label: "foo"
# input_var_gene_names: "foo"
# input_obs_size_factor: "foo"

# Reference
reference: # please fill in - example: "path/to/file"

# Outputs
# output: "$id.$key.output"
# output_compression: "gzip"
# model_output: "model"
obsm_output: "X_integrated_scanvi"
obs_output_predictions: "scanvi_pred"
obs_output_probabilities: "scanvi_proba"

# Early stopping arguments
# early_stopping: true
early_stopping_monitor: "elbo_validation"
early_stopping_patience: 45
early_stopping_min_delta: 0.0

# Learning parameters
# max_epochs: 123
reduce_lr_on_plateau: true
lr_factor: 0.6
lr_patience: 30.0

# 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/integrate/scarches/main.nf \
  -params-file params.yaml
Note

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

Argument groups

Inputs

Arguments related to the input (query) dataset

Name Description Attributes
--input Input h5mu file to use as a query file, required
--layer Layer to be used for scArches, if .X is not to be used. string
--modality string, default: "rna"
--input_obs_batch Name of the .obs column with batch information. string
--input_obs_label Name of the .obs column with celltype information. string
--input_var_gene_names Name of the .var column with gene names, if the var .index is not to be used. string
--input_obs_size_factor Key in adata.obs for size factor information. Instead of using library size as a size factor, the provided size factor column will be used as offset in the mean of the likelihood. Assumed to be on linear scale. string

Reference

Name Description Attributes
--reference Path to the directory with reference model or a web link. file, required

Outputs

Name Description Attributes
--output Output h5mu file. file, required
--output_compression The compression format to be used on the output h5mu object. string, example: "gzip"
--model_output Output directory for model file, default: "model"
--obsm_output In which .obsm slot to store the resulting integrated embedding. string, default: "X_integrated_scanvi"
--obs_output_predictions In which .obs slot to store the resulting label predictions. Only relevant if a scANVI model was provided. string, default: "scanvi_pred"
--obs_output_probabilities In which .obs slot to store the probabilities of the label predictions. Only relevant if a scANVI model was provided. string, default: "scanvi_proba"

Early stopping arguments

Name Description Attributes
--early_stopping Whether to perform early stopping with respect to the validation set. boolean
--early_stopping_monitor Metric logged during validation set epoch. string, default: "elbo_validation"
--early_stopping_patience Number of validation epochs with no improvement after which training will be stopped. integer, default: 45
--early_stopping_min_delta Minimum change in the monitored quantity to qualify as an improvement, i.e. an absolute change of less than min_delta, will count as no improvement. double, default: 0

Learning parameters

Name Description Attributes
--max_epochs Number of passes through the dataset, defaults to (20000 / number of cells) * 400 or 400; whichever is smallest. integer
--reduce_lr_on_plateau Whether to monitor validation loss and reduce learning rate when validation set lr_scheduler_metric plateaus. boolean, default: TRUE
--lr_factor Factor to reduce learning rate. double, default: 0.6
--lr_patience Number of epochs with no improvement after which learning rate will be reduced. double, default: 30

Authors

  • Vladimir Shitov (author)

  • Dorien Roosen (maintainer)