diffMeanVar (version 0.0.6)

POTestWrapper: Wrapper function to test for equality of variance by using Phipson and Oshlack's (2014) methods

Description

Wrapper function to test for equality of variance by using Phipson and Oshlack's (2014) methods

Usage

POTestWrapper(
  es, 
  grpVar = "group", 
  type = "AD",
  esFlag = "es", 
  pvalAdjMethod = "fdr", 
  alpha = 0.05, 
  nTop = 20, 
  probeID.var = "ProbeID", 
  gene.var = "Symbol", 
  chr.var = "Chromosome", 
  applier = lapply, 
  verbose = FALSE)

Arguments

es

An ExpressionSet object storing gene expression/DNA methylation data, phenotype data, and feature annotation.

grpVar

character string. The name of the phenotype variable indicating arrays' group membership. 0 means control and 1 means case.

type

character string indicating if AD method or SQ method would be used.

esFlag

character string. Indicating if es is an ExpressionSet object or MethylSet object. The program will use exprs function to extract gene expression data or use betas function to extract methylation data.

pvalAdjMethod

character string. Indicating which p-value adjustment will be used to control for multiple testing.

alpha

numeric. Cutoff for p-value or adjusted p-value to determine if a probe is diferentially variable.

nTop

integer. Specifying the number of top probes to be displayed if verbose=TRUE

probeID.var

character string. Feature annotation variable indicating probe ID.

gene.var

character string. Feature annotation variable indicating gene symbol.

chr.var

character string. Feature annotation variable indicating chromosome number.

applier

function name to do apply operation.

verbose

logical. indicating if intermediate results should be output to screen.

Value

A list of 2 elements. The first element frame is unsorted data frame; the second element frame.s is a sorted data frame object storing the analysis results and containing the following columns: probe (probe id), stat (test statistic), pval (raw p-value), p.adj (adjusted p-value), gene (gene symbol), chr (chromosome number), and pos (position of a probe in unsorted data frame).

The data frame is sorted based on the descending order of the absolute value of the test statistic.

References

Phipson B, Oshlack A. DiffVar: a new method for detecting differential variability with application to methylation in cancer and aging. Genome Biology 2014, 15:465.

Examples

# NOT RUN {
    # generate simulated data set from t distribution
    set.seed(1234567)
    es.sim = genSimData.tDistr(nCpGs = 100, nCases = 20, nControls = 20,
      df0 = 10, ncp0 = 0, df1 = 6, ncp1 = 2.393, testPara = "var",
      eps = 1.0e-3, applier = lapply) 
    print(es.sim)
    
    res.POTestWrapper = POTestWrapper(
      es = es.sim,
      grpVar = "memSubj",
      type = "SQ",
      esFlag = "es", 
      pvalAdjMethod = "fdr",
      alpha = 0.05,
      nTop = 20,
      probeID.var = "probe",
      gene.var = "gene",
      chr.var = "chr",
      applier=lapply,
      verbose=TRUE)

# }