pcorfdrci.inv {GeneNT} | R Documentation |
The inverse screening procedure is presented in our the paper below. It allows the FDR p-value of a gene pair's strength of association measured using partial correlation coefficient to be computed
pcorfdrci.inv(pcormin)
pcormin |
partial correlation threshold |
Please refer to Zhu et al. below for detail.
This function returns a list of fdr adjusted p-values.
Dongxiao Zhu (http://www-personal.umich.edu/~zhud)
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.
# 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" #Subset data to run faster dat <- dat[1:10,] #Set MAS level pcormin = 0.8, calculate fdr adjusted p-values. #fdrp8 <- pcorfdrci.inv(0.8)