Marker Ranking by Boruta — marker_ranking

Function to run Boruta on the stimulation - cell population combinations that passed the Fisher's exact test to rank the markers according to their contribution to the response.

Usage

marker_ranking_boruta(
  mapped_data,
  path = NULL,
  n_cells = NULL,
  max_runs = 100,
  seed_val = 123,
  verbose = 0
)

Arguments

mapped_data: Returned list from the HDStIM function.
path: Path to the folder to save figures generated by this function.
n_cells: Number of cells to down sample the data. Default is NULL to include all the cells.
max_runs: Maximum number of runs for the random forest algorithm. Default is 100.
seed_val: Seed value for Boruta. Default is 123.
verbose: 0, 1, or 2. Default is 0.

Value

A list with a tibble containing attribute statistics calculated by Boruta and ggplot objects. If the path is not NULL, plots are also rendered and saved in the specified folder in PNG format.

Examples

# \donttest{
mapped_data <- HDStIM(chi11$expr_data, chi11$state_markers,
                      chi11$cluster_col, chi11$stim_label,
                      chi11$unstim_label, seed_val = 123, umap = FALSE, umap_cells = NULL,
                      verbose = FALSE)

marker_ranking <- marker_ranking_boruta(mapped_data, path = NULL, n_cells = NULL,
                                        max_runs = 1000, seed_val = 123,
                                        verbose = 0)
# }