maSelectGnames: Select genes according to the values of a few different statistics

Description

Select genes by considering the union or intersect of multiple statistics.

Usage

maSelectGnames(statdata, crit1 = 50, crit2 = crit1, sub = TRUE, selectstat, operate = c("intersect", "union"))

Arguments

statdata

A numerical matrix where the rows corresponds to genes and the columns corresponds to various statistics corresponding to a particular gene.

crit1

The number of points to be selected. If crit1 < 1, the crit1*100% spots with the smallest M values will be selected. If crit1 >= 1, the crit spots with the smallest M values are selected.

crit2

Similar to "crit1". If crit2 < 1, the crit2*100% spots with the largest M values will be selected. If crit2 >= 1, the crit2 spots with the largest M values are selected.

sub

A "logical" or "numeric" vector indicating the subset of genes to be consider.

selectstat

A integer value indicating the statistics where the final ranking is based on.

operate

The operation used to combined different rankings

Value

A vector of numeric values.

Details

This functions calls stat.gnames to select say the 100 most extreme genes from various statistics and combined the different gene lists by either union or intersection.

Examples

Run this code

X <- matrix(rnorm(1000), 100,10)
Xstat <- cbind(mean=apply(X, 1, mean, na.rm=TRUE),
               var=apply(X, 1, var, na.rm=TRUE))
maSelectGnames(Xstat, crit1=50)