R: List the (most relevant) genes for a decision tree.

get.genes {Pigengene}

R Documentation

List the (most relevant) genes for a decision tree.

Description

This function returns all genes that are left after shrinking (compacting ) a given tree. If enhance is set to TRUE, it makes sure that the output contains at least two genes from each used module.

Usage

get.genes(c5Tree = NULL, pigengene = NULL, queue = NULL, modules = NULL, pos=0,
  enhance = TRUE)

Arguments

`queue`	A character vector. The membership queue for a decsision tree.
`pos`	Number of genes that are considered from removal. Same interpretation as in `preds.at`
`enhance`	If `enhance` is set to `TRUE`, the function makes sure that the output contains at least two genes from each used module. Otherwise, exactly the `pos` first elements of the queue are removed from consideration.
`modules`	Named character vector listing the module assignments.
`c5Tree`	A decision tree of class `C50`.
`pigengene`	An object in `pigengene-class`, usually created by `compute.pigengene`.

Details

This function needs modules and queue, or alternatively, c5Tree and pigengene.

Value

A character vector containing the names of the genes involved in the modules whose eigengenes are used in the tree. If pos > 0, the first pos such genes with lowest absolute membership in their respective modules are filtered.

Examples

     ## Data:
     data(aml)
     data(mds)
     data(pigengene)
     d1 <- rbind(aml,mds)

     ## Fiting the trees:
     trees <- make.decision.tree(pigengene=pigengene, Data=d1,
     saveDir="trees", minPerLeaf=15, doHeat=FALSE,verbose=3,
       toCompact=FALSE)
     g1 <- get.genes(c5Tree=trees$c5Trees[["15"]],pigengene=pigengene)

[Package Pigengene version 1.14.0 Index]