netprioR-class: netprioR
In netprioR: A model for network-based prioritisation of genes

Description Usage Arguments Value Slots Author(s) Examples

Class that represents a netprioR model.

netprioR(networks, phenotypes, labels, ...)

## S4 method for signature 'list,matrix,factor'
netprioR(networks, phenotypes, labels,
  fit.model = FALSE, a = 0.1, b = 0.1, sigma2 = 0.1, tau2 = 100,
  eps = 1e-10, max.iter = 500, thresh = 1e-06, use.cg = FALSE,
  thresh.cg = 1e-06, nrestarts = 5, max.cores = detectCores(),
  verbose = TRUE, ...)

`networks`	List of NxN adjacency matrices of gene-gene similarities
`phenotypes`	Matrix of dimension NxP containing covariates
`labels`	Vector of Nx1 labels for all genes (NA if no label available)
`...`	Additional arguments
`fit.model`	Indicator whether to fit the model
`a`	Shape parameter of Gamma prior for W
`b`	Scale parameter of Gamma prior for W
`sigma2`	Cariance for Gaussian labels
`tau2`	Variance for Gaussian prior for beta
`eps`	Small value added to diagonal of Q in order to make it non-singular
`max.iter`	Maximum number of iterations for EM
`thresh`	Threshold for termination of EM with respect to change in parameters
`use.cg`	Flag whether to use conjugate gradient instead of exact computation of expectations
`thresh.cg`	Threshold for the termination of the conjugate gradient solver
`nrestarts`	Number of restarts for EM
`max.cores`	Maximum number of cores to use for parallel computation
`verbose`	Print verbose output

A netprioR object

networks: List of NxN adjacency matrices of gene-gene similarities
phenotypes: Matrix of dimension NxP containing covariates
labels: Vector of Nx1 labels for all genes. NA if no label available.
is.fitted: Flag indicating if model is fitted
model: List containing estimated parameters and imputed missing data

Fabian Schmich

 # runs long-ish
data(simulation)
np <- netprioR(networks = simulation$networks,
               phenotypes = simulation$phenotypes,
               labels = simulation$labels.obs,
               fit.model = TRUE)
summary(np)