pcorfdrci {GeneNT}R Documentation

Two-stage screening procedure based on partial correlation coefficient in Graphic Gaussian Model framework

Description

This function implement the two-stage screening procedure based on partial correlation coefficient in the framework of Gaussian Graphic Model. Specifying a pair of FDR and MAS criteria, the algorithm provides an initial co-expression discovery that controls only FDR, which is then followed by a second stage co-expression discovery which controls both FDR and MAS.

Usage

pcorfdrci(Q, pcormin)

Arguments

Q The significant level
pcormin The specified minimum acceptable strength of association measured using partial correlation coefficient

Details

The data matrix file must be in the right format. The first row (header) must be one shorter than the rest rows. The first column must be gene names.

Value

The function returns a list of gene pairs that satisfies the FDR and MAS criteria simultaneously measured by partial correlation coefficient.

pG1 The gene pairs that passes Stage I (FDR only) screening
pG2 The gene pairs that passed both Stage I (FDR) and II (MAS) screenings

Author(s)

Dongxiao Zhu (http://www-personal.umich.edu/~zhud)

References

Fisher, R.A. (1921). On the 'probable error' of a coefficient of correlation deduced from a small sample. Metron, 1, 1–32.

Zhu, D., Hero, A.O., Qin, Z.S. and Swaroop, A. High throughput screening of co-expressed gene pairs with controlled False Discovery Rate (FDR) and Minimum Acceptable Strength (MAS). Submitted.

Schäfer, J., and K. Strimmer. (2004) An empirical Bayes approach to inferring large-scale gene association networks. Bioinformatics, 1, 1-13.

See Also

corfdrci

Examples

# load GeneNT and GeneTS library
library(GeneTS)
library(GeneNT)

#EITHER use the example dataset
data(dat) 
#OR use the following if you want to import external data 
#dat <- read.table("gal.txt", h = T, row.names = 1) 
#Note, data matrix name has to be "dat"

#use (FDR, MAS) criteria (0.2, 0.2) as example to screen gene pairs 
#g3 <- pcorfdrci(0.2, 0.2) 
#G1 <- g3$G1.all
#G2 is the dataset containing gene pairs that passed two-stage screening
#G2 <- g3$G2  

[Package GeneNT version 1.2 Index]