Learn R Programming

dGAselID (version 1.0)

dGAselID: dGAselID

Description

Initializes and starts the search with the genetic algorithm.

Usage

dGAselID(x, response, method = knnI(k = 3, l = 2), trainTest = "LOG",
  startGenes, populationSize, iterations, noChr = 22, elitism = NA,
  ID = "ID1", pMutationChance = NA, randomAssortment = TRUE,
  embryonicSelection = NA, EveryGeneInInitialPopulation = TRUE,
  nnetSize = NA, nnetDecay = NA, rdaAlpha = NA, rdaDelta = NA, ...)

Arguments

x
Dataset in ExpressionSet format.
response
Response variable
method
Supervised classifier for fitness evaluation. Most of the supervised classifiers in MLInterfaces are acceptable. The default is knnI(k=3, l=2).
trainTest
Cross-validation method. The default is "LOG".
startGenes
Genes in the genotypes at initialization.
populationSize
Number of genotypes in initial population.
iterations
Number of iterations.
noChr
Number of chromosomes. The default value is 22.
elitism
Elite population in percentages.
ID
Incomplete Dominance. The default value is "ID1". Use "ID2" for elitism applied to individuals.
pMutationChance
Chance for a point mutation to occur.
randomAssortment
Random Assortment of Chromosomes for recombinations. The default value is TRUE.
embryonicSelection
Remove chromosomes with fitness < specified value. The default value is NA.
EveryGeneInInitialPopulation
Request for every gene to be present in the initial population. The default value is TRUE.
nnetSize
for nnetI. The default value is NA.
nnetDecay
for nnetI. The default value is NA.
rdaAlpha
for rdaI. The default value is NA.
rdaDelta
for rdaI. The default value is NA.
...
Additional arguments.

Examples

Run this code
## Not run: ------------------------------------
#  library(genefilter)
#  library(ALL)
#  data(ALL)
#  bALL = ALL[, substr(ALL$BT,1,1) == "B"]
#  smallALL = bALL[, bALL$mol.biol %in% c("BCR/ABL", "NEG")]
#  smallALL$mol.biol = factor(smallALL$mol.biol)
#  smallALL$BT = factor(smallALL$BT)
#  f1 <- pOverA(0.25, 9)
#  f2 <- function(x) (IQR(x) > 0.75)
#  f3 <- ttest(smallALL$mol.biol, p=0.1)
#  ff <- filterfun(f1, f2, f3)
#  selectedsmallALL <- genefilter(exprs(smallALL), ff)
#  sum(selectedsmallALL)
# 
#  set.seed(1357)
#  res1<-dGAselID(smallALL, "mol.biol", method=knn.cvI(k=3, l=2), trainTest=1:79,
#    startGenes=5, populationSize=50, iterations=4, noChr=5, mutationChance=0.05,
#    elitism=10, ID="ID1")
#  
## ---------------------------------------------

Run the code above in your browser using DataLab