singleStep {rOCEAN} | R Documentation |
Single step algorithm
Description
Calculates heuristic and upper-bound for the number of true discoveries based on the Algorithm 1 introduced in paper.
Usage
singleStep(sCat, B)
Arguments
sCat |
p-categories matrix, output of getCat function. |
B |
Optional, to identify rows to be fixed (1) or removed (0) while splitting the search space. |
Value
A list of two objects, the lower bound and a heuristic for the number of true discoveries
See Also
Examples
#number of features per omic data set
n_cols<-100
n_rows<-120
#random matrix of p-values
set.seed(1258)
pvalmat<-matrix(runif(n_rows*n_cols, min=0, max=1)^5, nrow=n_rows, ncol=n_cols)
#calculate CT parameters
gCT<-simesCT(mps=pvalmat, m=nrow(pvalmat)*ncol(pvalmat))
#define the two-way feature set
subpmat<-pvalmat[61:75,81:100]
#calculate p-categories matrix for feature set by rows
rCat<-getCat(mps=subpmat, gCT, scale="row")
#get the bounds based on algorithm 1
singleStep(rCat)
#calculate p-categories matrix for feature set by columns
cCat<-getCat(mps=subpmat, gCT, scale="col")
#get the bounds based on algorithm 1 while removing column 1 and forcing column 2
singleStep(cCat, B=c(0,1))
[Package rOCEAN version 1.0 Index]