molnet (version 0.1.0)

network_reduction_by_p_value: Reduce the the entries in an adjacency matrix by thresholding on p-values

Description

(INTERNAL) This function reduces an adjacency matrix of correlations. If computations are done non-parallel corPvalueStudent is used. If computations are done in parallel, our own parallel implementation (corPvalueStudentParallel) of this function is used. function to calculate Student asymptotic p-values taking the number of samples into account. P-values are adjusted using p.adjust function. The upper triangle without diagonal entries of the adjacency matrix is passed for faster computation. P-values can be adjusted using one of several methods. A significance threshold `alpha` can be set. All value entries below this threshold within the initial adjacency matrix will be set to NA. If a default cluster is registered with the `parallel` package the computation will happen in parallel automatically.

Usage

network_reduction_by_p_value(
  adjacency_matrix,
  number_of_samples,
  reduction_alpha = 0.05,
  p_value_adjustment_method = "BH",
  parallel_chunk_size = 10^6
)

Arguments

adjacency_matrix

An adjacency matrix of correlation values.

number_of_samples

The number of samples used to calculate the correlation matrix.

reduction_alpha

A number indicating the alpha value applied for thresholding

p_value_adjustment_method

A string of the correction method applied to p-values. Passed to stats::p.adjust().

parallel_chunk_size

Number of p-values in smallest work unit when computing in parallel.

Value

A reduced adjacency matrix with NA's at martix entries with p-values below threshold.

Examples

# NOT RUN {
adj_mat <- matrix(rnorm(36),nrow=6)
sum(is.na(adj_mat)) # before reduction
reduced_by_p_value_matrix <- network_reduction_by_p_value(adjacency_matrix=adj_mat,
                             number_of_samples=200, reduction_alpha = 0.05,
                             p_value_adjustment_method = "BH")
sum(is.na(reduced_by_p_value_matrix)) # after reduction
# }