R: Estimate Power Under Increasing Sample Sizes

predictPower {PowerExplorer}

R Documentation

Estimate Power Under Increasing Sample Sizes

Description

Simlilar to estimatePower, power estimations are performed under multiple increasing sample sizes

Usage

predictPower(inputObject, groupVec, isLogTransformed = FALSE,
  dataType = c("RNASeq", "Proteomics"), enableROTS = FALSE,
  paraROTS = list(B = 1000, K = NULL, paired = FALSE, a1 = NULL, a2 =
  NULL, progress = FALSE), minLFC = 0.5, rangeSimNumRep = NA,
  alpha = 0.05, ST = 100, seed = 123, parallel = FALSE,
  BPPARAM = bpparam(), showProcess = FALSE, saveResultData = FALSE)

Arguments

`inputObject`	a numeric raw Proteomics abundance data matrix, in which rows correspond to proteins and columns correspond to samples.
`groupVec`	a vector indicating the grouping of samples
`isLogTransformed`	logical; logical; set to `TRUE`, if the input data is log transformed.
`dataType`	"RNASeq" or "Proteomics" indictes the data type of the input data matrix.
`enableROTS`	logical; if `TRUE`, Reproducibility-Optimized Test Statistic (ROTS) will be used as the statistical model.
`paraROTS`	a `list` object containing addtional parameters passed to ROTS (if enabled), see `ROTS`.
`minLFC`	LFC threshold
`rangeSimNumRep`	a vector of sample sizes under which power will be estimated
`alpha`	controlled false positive rate.
`ST`	the number of simulations of abundance data generation and repeated times of statistical test for each protein (>=100 recommended).
`seed`	an integer seed for the random number generator.
`parallel`	logical; if `FALSE` parallelization is disabled; if `TRUE`, parallelize calculations using `BiocParallel`.
`BPPARAM`	an optional argument object passed `bplapply` to indicate the registered cores, if `parallel=TRUE`.
`showProcess`	logical; if `TRUE`, show the detailed information of each simulation, used for debugging only.
`saveResultData`	logical; if `TRUE`, save the simulated data into RData with name pattern "simulated_Data_numRep_X_numSim_XXX_XXXXX.RData".

Value

a list of power predictions for each sample size, grouped in comparisons between each two groups

Examples

# Example 1: a random generated Proteomics dataset (10 DE, 100 non-DE)
data(exampleProteomicsData)
dataMatrix <- exampleProteomicsData$dataMatrix
groupVec <- exampleProteomicsData$groupVec

# Run estimation
# Note: Simulation times(ST) is specified as 5 for shorter example runtime
#       For better performence, ST > 50 is recommended
predictedPower <- predictPower(dataMatrix, groupVec,
                               isLogTransformed=FALSE,
                               dataType="Proteomics",
                               minLFC=0,
                               rangeSimNumRep=c(5, 10, 15),
                               alpha=0.05, ST=5, seed=123)