Skip to contents

Run DRAGON in R.

Source: R/DRAGON.R
dragon.Rd

Description: Estimates a multi-omic Gaussian graphical model for two input layers of paired omic data.

Usage

dragon(
  layer1,
  layer2,
  pval = FALSE,
  gradient = "finite_difference",
  verbose = FALSE
)

Arguments

layer1

: first layer of omics data; rows: samples (order must match layer2), columns: variables

layer2

: second layer of omics data; rows: samples (order must match layer1), columns: variables.

pval

: calculate p-values for network edges. Not yet implemented in R; available in netZooPy.

gradient

: method for estimating parameters of p-value distribution, applies only if p-val == TRUE. default = "finite_difference"; other option = "exact"

verbose

: verbosity level (TRUE/FALSE)

Value

A list of model results. cov : the shrunken covariance matrix

  • cov the shrunken covariance matrix

  • prec the shrunken precision matrix

  • ggm the shrunken Gaussian graphical model; matrix of partial correlations. Self-edges (diagonal elements) are set to zero.

  • lambdas Vector of omics-specific tuning parameters (lambda1, lambda2) for layer1 and layer2

  • gammas Reparameterized tuning parameters; gamma = 1 - lambda^2

  • risk_grid Risk grid, for assessing optimization. Grid boundaries are in terms of gamma.