SimulateData: Simulate Data This function first generates a random network...

In HamdaBinteAjmal/DBN4GRN: An R Package for Learning Sparse DBN Structures to Reverse Engineer Gene Regulatory Networks

Description

Simulate Data This function first generates a random network and then simulates the multi variate time series data according to the following first order Auto-Regressive process, X(t) = AX(t-1) + B + E(t), where E(t) follows a zero-centered multivariate gaussian distribution whose variance matrix S is diagonal. It uses different functions from the G1DBN package.

Usage

SimulateData(
  genes,
  timepoints,
  seed = 1,
  prop = 0.05,
  range = c(-0.95, -0.05, 0.05, 0.95),
  errors = c(0.03, 0.08)
)

Arguments

genes	Number of genes or variables
timepoints	Number of samples
seed	Random seed, is a number used to initialize a pseudorandom number generator.
prop	The proportion of edges in the entire network
range	vector with 4 elements specifying range values for the adjacency matrix generation (minimum negative value, maximum negative value, minimum positive value, maximum positive value)
errors	vector of 2 elements specifying min and max value of the uniform distribution from which the error variances are drawn

Value

A list comprising of dataset generated (data) and the network (RealNet) from which the data is generated.

Examples

sim <- SimulateData(genes = 50, timepoints = 20, seed = 1, prop = 0.25)
head(sim$data)

HamdaBinteAjmal/DBN4GRN documentation built on Dec. 27, 2021, 2:08 p.m.