dingo: Fit DINGO model

In iDINGO: Integrative Differential Network Analysis in Genomics

Description

This function fit DINGO model and calculates edge-wise differential scores for all pairwise edges among p variables.

Usage

dingo(dat,x,rhoarray=NULL,diff.score=T,B=100,verbose=T,cores=1)

Arguments

dat	nxp data with colnames as genename
x	a length n vector representing a binary covariate
rhoarray	a vector representing candidate tuning parameters of glasso for fitting global network model. If it is one value, then we use the value as the tuning parameter. It is set by NULL as default and we select 100 candidate values.
diff.score	a logical value. If TRUE, edge-wise differential scores are calculated from bootstrap standard error. Otherwise, we fit Steps 1 and 2 of DINGO model to get group specific GGMs (partial correlations)
B	the number of bootstrap samples to calculate differential scores.
verbose	if TRUE, lists the procedure
cores	the number of cores to run in parallel for bootstrapping, set to 1 as a default. If more cores are specified than the recommended maximum (the number of cores detected minus 1), this value will be replaced by the recommended value.

Value

genepair	a p(p-1)/2 x 2 matrix indicating all pairs of genes
levels.x	a length 2 vector indicating levels of the binary covariate x, the first element is for group 1 and the second element is for group 2
R1	a length p(p-1)/2 vector indicating partial correlations for group 1 and the order is corresponding to the order of genepair
R2	a length p(p-1)/2 vector indicating partial correlations for group 2 and the order is corresponding to the order of genepair
boot.diff	a p(p-1)/2 x boot.B matrix indicating bootstrapped difference, Fisher's Z transformed R1 - R2. The rows are corresponding to the order of gene pair and the columns are corresponding to the bootstrap samples
diff.score	a p(p-1)/2 vector of differential score corresponding to genepair
p.val	a p(p-1)/2 vector of corrected p-values corresponding to genepair
rho	selected tuning parameter of glasso fit
P	p by p matrix of Global component of the DINGO model
Q	p by 2 matrix of the coefficient parameter of the local group specific component L(x) of the DINGO model.
Psi	p by p diagonal matrix of the noise covariance parameter of the local group specific component L(x) of the DINGO model.
step.times	a length 3 vector containing the elapsed time for Step 1, Step 2, and Bootstrap Scoring, respectively.

Author(s)

Min Jin HA [e-mail], Caleb CLASS [e-mail]

Examples

data(gbm)
# Run DINGO (the first column, 'x', contains the group data).
# This may take 5-10 minutes.
## Not run: fit <- dingo(gbm[,-1], gbm$x, diff.score = TRUE, B = 100, cores = 2)

Example output

Loading required package: igraph

Attaching package: 'igraph'

The following objects are masked from 'package:stats':

    decompose, spectrum

The following object is masked from 'package:base':

    union

iDINGO documentation built on July 30, 2020, 5:14 p.m.