ExactFisherBC: Apply Fisher Exact Test on Biclusters of a Biclust object

In ewouddt/BiBitR: R Wrapper for Java Implementation of BiBit

Description

Accepts a Biclust Object and computes the Fisher Exact Test of the rows and columns inside the biclusters versus the rows and columns outside. This test gives some information on the fact if the rows or columns are uniquely active for this particular (or other similar) bicluster. The function will not extract the column pattern and test every row of the dataset. This functionality can be found in RowTest_Fisher.

Usage

ExactFisherBC(result, matrix, p.adjust = "BH", alpha = 0.05,
  BC = 1:result@Number)

Arguments

result	A Biclust Object.
matrix	Accompanying binary data matrix which was used to obtain result.
p.adjust	Which method to use when adjusting p-values, see p.adjust (default="BH").
alpha	Significance level (default=0.05).
BC	Numeric vector to select for which BC's the Fisher Exact Test needs to be computed. Default is all available biclusters.

Value

Returns a list with two elements:

• summary: a data frame containing the number of rows, significant rows, adjusted significant rows, columns, significant columns and adjusted significant columns for all requested biclusters.

• info: a list with an element for each requested biclusters. Each BC list element contains two data frames (row and col) which contain the index, name, pvalue, adjusted pvalue, density of 1's inside and density of 1's outside for all the row and column members of the bicluster.

Author(s)

Ewoud De Troyer

Examples

## Not run: 
data <- matrix(sample(c(0,1),100*100,replace=TRUE,prob=c(0.9,0.1)),nrow=100,ncol=100)
data[1:10,1:10] <- 1 # BC1
data[11:20,11:20] <- 1 # BC2
data[21:30,21:30] <- 1 # BC3
data <- data[sample(1:nrow(data),nrow(data)),sample(1:ncol(data),ncol(data))]

result1 <- bibit2(data,minr=5,minc=5,noise=0.1)
out_fisher <- ExactFisherBC(result1,data)
out_fisher$summary
out_fisher$info[[1]]

## End(Not run)
 

ewouddt/BiBitR documentation built on May 16, 2019, 9:41 a.m.