Skip to contents

Pipeline step: BBKNN batch correction

step_bbknn_sc.Rd

Wraps bbknn_sc() as an ScStep.

Usage

step_bbknn_sc(
  batch_column,
  no_neighbours_to_keep = 5L,
  embd_to_use = "pca",
  no_embd_to_use = NULL,
  bbknn_params = params_sc_bbknn(),
  seed = 42L,
  .verbose = TRUE
)

Arguments

batch_column

String. The column with the batch information in the obs data of the class.

no_neighbours_to_keep

Integer. Maximum number of neighbours to keep from the BBKNN algorithm. Due to generating neighbours for each batch, there might be a large number of generated neighbours. This will only keep the top no_neighbours_to_keep neighbours. Defaults to 5L.

embd_to_use

String. The embedding to use. Atm, the only option is "pca".

no_embd_to_use

Optional integer. Number of embedding dimensions to use. If NULL all will be used.

bbknn_params

A list, please see params_sc_bbknn(). The list has the following parameters:

  • neighbours_within_batch - Integer. Number of neighbours to consider per batch.

  • set_op_mix_ratio - Numeric. Mixing ratio between union (1.0) and intersection (0.0).

  • local_connectivity - Numeric. UMAP connectivity computation parameter, how many nearest neighbours of each cell are assumed to be fully connected.

  • trim - Optional integer. Trim the neighbours of each cell to these many top connectivities. May help with population independence and improve the tidiness of clustering. If NULL, it defaults to 10 * neighbours_within_batch.

  • knn - List of kNN parameters. See params_knn_defaults() for available parameters and their defaults.

seed

Integer. Random seed.

.verbose

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

Value

An ScStep.

Examples

# BBKNN replaces the graph outright, so nothing follows it
step_pca_sc(no_pcs = 10L) %>>%
  step_bbknn_sc(batch_column = "batch_index")
#> <ScPipeline> 2 steps
#>   1. pca    no_pcs = 10L, pca_params = <list>, sparse_svd = FALSE, hvg = NULL, seed = 42L, .verbose = TRUE
#>   2. bbknn  batch_column = "batch_index", no_neighbours_to_keep = 5L, embd_to_use = "pca", no_embd_to_use = NULL, bbknn_params = <list>, seed = 42L, .verbose = TRUE