estimatePower {PowerExplorer} | R Documentation |
Estimate power of comparison between each two groups based on the data simulated from estimated normal distributions of entrys in the entire dataset
estimatePower(inputObject, groupVec, isLogTransformed = FALSE, dataType = c("RNASeq", "Proteomics"), minLFC = 0.5, alpha = 0.05, ST = 100, seed = 123, enableROTS = FALSE, paraROTS = list(B = 1000, K = NULL, paired = FALSE, a1 = NULL, a2 = NULL, progress = FALSE), showProcess = FALSE, saveResultData = FALSE, parallel = FALSE, BPPARAM = bpparam())
inputObject |
a numeric raw data matrix or SummarizedExperiment object |
groupVec |
a vector indicating the grouping of samples |
isLogTransformed |
logical; set to |
dataType |
"RNASeq" or "Proteomics" indictes the data type of the input data matrix. |
minLFC |
the threshold for log2 fold change, entrys with lower LFC are not included in the power calculation, set to 0 if no threshold is needed. |
alpha |
controlled false positive rate. |
ST |
the number of simulations of abundance data generation and repeated times of statistical test for each entry (>=100 recommended). |
seed |
an integer seed for the random number generator. |
enableROTS |
logical; if |
paraROTS |
a |
showProcess |
logical; if |
saveResultData |
logical; if |
parallel |
logical; if |
BPPARAM |
an optional argument object passed |
a list of power estimates grouped in comparisons between each two groups
predictPower
predict power with incresing sample sizes
# Example 1: a random generated Proteomics dataset (10 DE, 100 non-DE) # Note: Simulation times(ST) is specified as 10 for shorter example runtime, # ST > 50 is recommended data(exampleProteomicsData) dataMatrix <- exampleProteomicsData$dataMatrix groupVec <- exampleProteomicsData$groupVec # Run estimation without LFC filtration resObject <- estimatePower(dataMatrix, groupVec, dataType="Proteomics", isLogTransformed=FALSE, minLFC=0, alpha=0.05, ST=10, seed=123)