optimize_k: Optimization of k value

In emosca-cnr/mND: Gene relevance based on multiple evidences in complex networks

Optimization of k value

Description

Optimization of the 'k' value by selecting a value that yields connected networks enriched in initial scores.

Usage

optimize_k(
  Xs = NULL,
  X0 = NULL,
  k = NULL,
  ind_adj = NULL,
  W = NULL,
  top = 200,
  BPPARAM = NULL
)

Arguments

Xs	a matrix or list of matrices (if X0 was permuted, where the first element of the list is the one obtained with real data) with network diffusion scores, see 'ND' function
X0	matrix; initial score matrix X0, in which each column (layer) represents a score vector over all vertices of G
k	array; array with k values
ind_adj	list; index of neighbours obtained from adjacency matrix, see 'neighbour_index' function
W	matrix; symmetrically normalized adjacency matrix W = D^-1 A D^-1, see 'normalize_adj_mat' function
top	numeric; number of genes to be considered at the top of the list of genes ranked by mND
BPPARAM	optional BiocParallelParam instance determining the parallel back-end to be used during evaluation. If NULL, parallel evaluation is disabled using SerialParam(). See ?bplapply.

Value

list with calculation of w at varying k and plot with results.

emosca-cnr/mND documentation built on April 11, 2024, 12:49 p.m.