inferCSN {inferCSN}

Inferring Cell-Specific Gene Regulatory Network

Description

Inferring Cell-Specific Gene Regulatory Network

Usage

inferCSN(object, ...)

## S4 method for signature 'matrix'
inferCSN(
  object,
  penalty = "L0",
  algorithm = "CD",
  cross_validation = FALSE,
  seed = 1,
  n_folds = 10,
  k_folds = NULL,
  r_threshold = 0,
  regulators = NULL,
  targets = NULL,
  regulators_num = NULL,
  verbose = FALSE,
  cores = 1,
  ...
)

## S4 method for signature 'data.frame'
inferCSN(
  object,
  penalty = "L0",
  algorithm = "CD",
  cross_validation = FALSE,
  seed = 1,
  n_folds = 10,
  k_folds = NULL,
  r_threshold = 0,
  regulators = NULL,
  targets = NULL,
  regulators_num = NULL,
  verbose = FALSE,
  cores = 1,
  ...
)

Arguments

object

Input object

...

Arguments for other methods

penalty

The type of regularization. This can take either one of the following choices: "L0" and "L0L2". For high-dimensional and sparse data, such as single-cell sequencing data, "L0L2" is more effective.

algorithm

The type of algorithm used to minimize the objective function. Currently "CD" and "CDPSI" are supported. The CDPSI algorithm may yield better results, but it also increases running time.

cross_validation

Check whether cross validation is used.

seed

The seed used in randomly shuffling the data for cross-validation.

n_folds

The number of folds for cross-validation.

k_folds

The number of folds for sample split.

r_threshold

Threshold of R^2.

regulators

Regulator genes.

targets

Target genes.

regulators_num

The number of non-zore coef, this value will affect the final performance. The maximum support size at which to terminate the regularization path. 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.

verbose

Print detailed information.

cores

CPU cores.

Value

A data table of gene-gene regulatory relationship

Examples

library(inferCSN)
data("example_matrix")
weight_table <- inferCSN(example_matrix, verbose = TRUE)
head(weight_table)

weight_table <- inferCSN(example_matrix, verbose = TRUE, cores = 2)
head(weight_table)