Description Usage Arguments Details Value Author(s) References See Also
Estimates network using netEst.dir
or netEst.undir
for each cluster. This is a helper function in prepareAdjMat
and should not be called by the user.
1 | netEstClusts(grp, X, group, net_info, n, lambda_c, eta, net_clusters, penalize_diag)
|
grp |
Specific group to analyze e.g. condition 1, 2, etc. Same type as |
X |
p x n data matrix |
group |
Vector specifying which columns in the data matrix correspond to which condition or group |
net_info |
List with named elements "zero" and "one" corresponding to the zero and one information matrices used in |
n |
Vector of the total number of observations for |
lambda_c |
lambda constant. Used to determine |
eta |
Value of eta passed to |
net_clusters |
Named numeric vector specifying which genes correspond to which clusters. Names are genes and the values are their corresponding clusters |
penalize_diag |
TRUE/FALSE - whether or not to penalize diagonal |
This function loops through each cluster and calls netEst.undir
or netEst.dir
with the relevant parameters.
A list with components
Adj |
List of the weighted adjacency matrices (partial correlations) for each cluster. The structure is Adj[[cluster]]. If cluster = FALSE, Adj[[cluster]] only has one element. Note this is used in a lapply where we loop over the groups giving us the final Adj[[condition]][[cluster]] structure. |
invcov |
List of estimated inverse covariance matrices for each cluster. The structure is invcov[[cluster]]. If cluster = FALSE, invcov[[cluster]] only has one element |
lambda |
List of values of tuning parameters used for each cluster. |
Michael Hellstern
Ma, J., Shojaie, A. & Michailidis, G. (2016) Network-based pathway enrichment analysis with incomplete network information. Bioinformatics 32(20):165–3174.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.