Skip to contents

Pipeline step: Harmony batch correction

step_harmony_sc.Rd

Wraps harmony_sc() as an ScStep.

Usage

step_harmony_sc(
  batch_column,
  additional_batch_columns = NULL,
  modality = c("rna", "adt"),
  harmony_params = params_sc_harmony(),
  seed = 42L,
  .verbose = TRUE
)

Arguments

batch_column

String. Column name in the object containing the primary batch labels.

additional_batch_columns

Optional character vector. Additional batch columns to regress out. If NULL, only the primary batch column is used.

modality

String. One of c("rna", "adt"). You can only use "adt" on SingleCellsMultiModal class.

harmony_params

List. Output of params_sc_harmony().

seed

Integer. For reproducibility.

.verbose

Boolean or integer. Controls verbosity and returns run times. FALSE -> quiet, TRUE or 1L -> normal verbosity, 2L -> detailed verbosity.

Value

An ScStep.

Examples

# correct the PCA, then build the graph on the corrected embedding
step_harmony_sc(batch_column = "batch_index") %>>%
  step_neighbours_sc(embd_to_use = "harmony")
#> <ScPipeline> 2 steps
#>   1. harmony     batch_column = "batch_index", additional_batch_columns = NULL, modality = c("rna", "adt"), harmony_params = <params_sc_harmony>, seed = 42L, .verbose = TRUE
#>   2. neighbours  embd_to_use = "harmony", no_embd_to_use = NULL, modality = c("rna", "adt"), neighbours_params = <list>, seed = 42L, .verbose = TRUE