inferCSN: *infer*ring *C*ell-*S*pecific gene regulatory *N*etwork

In inferCSN: Inferring Cell-Specific Gene Regulatory Network

inferring Cell-Specific gene regulatory Network

Description

inferring Cell-Specific gene regulatory Network

Usage

inferCSN(
  object,
  penalty = "L0",
  cross_validation = FALSE,
  seed = 1,
  n_folds = 5,
  subsampling_method = c("sample", "meta_cells", "pseudobulk"),
  subsampling_ratio = 1,
  r_squared_threshold = 0,
  regulators = NULL,
  targets = NULL,
  cores = 1,
  verbose = TRUE,
  ...
)

## S4 method for signature 'matrix'
inferCSN(
  object,
  penalty = "L0",
  cross_validation = FALSE,
  seed = 1,
  n_folds = 5,
  subsampling_method = c("sample", "meta_cells", "pseudobulk"),
  subsampling_ratio = 1,
  r_squared_threshold = 0,
  regulators = NULL,
  targets = NULL,
  cores = 1,
  verbose = TRUE,
  ...
)

## S4 method for signature 'sparseMatrix'
inferCSN(
  object,
  penalty = "L0",
  cross_validation = FALSE,
  seed = 1,
  n_folds = 5,
  subsampling_method = c("sample", "meta_cells", "pseudobulk"),
  subsampling_ratio = 1,
  r_squared_threshold = 0,
  regulators = NULL,
  targets = NULL,
  cores = 1,
  verbose = TRUE,
  ...
)

## S4 method for signature 'data.frame'
inferCSN(
  object,
  penalty = "L0",
  cross_validation = FALSE,
  seed = 1,
  n_folds = 5,
  subsampling_method = c("sample", "meta_cells", "pseudobulk"),
  subsampling_ratio = 1,
  r_squared_threshold = 0,
  regulators = NULL,
  targets = NULL,
  cores = 1,
  verbose = TRUE,
  ...
)

Arguments

object	The input data for inferCSN.
penalty	The type of regularization, default is L0. This can take either one of the following choices: L0, L0L1, and L0L2. For high-dimensional and sparse data, L0L2 is more effective.
cross_validation	Logical value, default is FALSE, whether to use cross-validation.
seed	The random seed for cross-validation, default is 1.
n_folds	The number of folds for cross-validation, default is 5.
subsampling_method	The method to use for subsampling. Options are "sample", "pseudobulk" or "meta_cells".
subsampling_ratio	The percent of all samples used for fit_srm, default is 1.
r_squared_threshold	Threshold of R^2 coefficient, default is 0.
regulators	The regulator genes for which to infer the regulatory network.
targets	The target genes for which to infer the regulatory network. Recommend setting this to a small fraction of min(n,p) (e.g. 0.05 * min(n,p)) as L0 regularization typically selects a small portion of non-zeros.
cores	The number of cores to use for parallelization with foreach, default is 1.
verbose	Logical value, default is TRUE, whether to print progress messages.
...	Parameters for other methods.

Value

A data table of regulator-target regulatory relationships

Examples

data("example_matrix")
network_table_1 <- inferCSN(
  example_matrix
)

network_table_2 <- inferCSN(
  example_matrix,
  cores = 2
)

head(network_table_1)

identical(
  network_table_1,
  network_table_2
)

inferCSN(
  example_matrix,
  regulators = c("g1", "g2"),
  targets = c("g3", "g4")
)
inferCSN(
  example_matrix,
  regulators = c("g1", "g2"),
  targets = c("g3", "g0")
)

## Not run: 
data("example_ground_truth")
network_table_07 <- inferCSN(
  example_matrix,
  r_squared_threshold = 0.7
)
calculate_metrics(
  network_table_1,
  example_ground_truth,
  return_plot = TRUE
)
calculate_metrics(
  network_table_07,
  example_ground_truth,
  return_plot = TRUE
)

## End(Not run)
## Not run: 
data("example_matrix")
network_table <- inferCSN(example_matrix)
head(network_table)

network_table_sparse_1 <- inferCSN(
  as(example_matrix, "sparseMatrix")
)
head(network_table_sparse_1)

network_table_sparse_2 <- inferCSN(
  as(example_matrix, "sparseMatrix"),
  cores = 2
)
identical(
  network_table,
  network_table_sparse_1
)

identical(
  network_table_sparse_1,
  network_table_sparse_2
)

plot_scatter(
  data.frame(
    network_table$weight,
    network_table_sparse_1$weight
  ),
  legend_position = "none"
)

plot_weight_distribution(
  network_table
) + plot_weight_distribution(
  network_table_sparse_1
)

## End(Not run)

inferCSN documentation built on April 13, 2025, 5:11 p.m.