pwrEWAS {pwrEWAS} | R Documentation |
pwrEWAS is a computationally efficient tool to estimate power in EWAS as a function of sample and effect size for two-group comparisons of DNAm (e.g., case vs control, exposed vs non-exposed, etc.). Detailed description of in-/outputs, instructions and an example, as well as interpretations of the example results are provided in the vignette: vignette("pwrEWAS")
pwrEWAS(minTotSampleSize, maxTotSampleSize, SampleSizeSteps, NcntPer, targetDelta = NULL, deltaSD = NULL, J = 1e+05, targetDmCpGs, tissueType = c("Adult (PBMC)", "Saliva", "Sperm", "Lymphoma", "Placenta", "Liver", "Colon", "Blood adult", "Blood 5 year olds", "Blood newborns", "Cord-blood (whole blood)", "Cord-blood (PBMC)"), detectionLimit = 0.01, DMmethod = c("limma", "t-test (unequal var)", "t-test (equal var)", "Wilcox rank sum", "CPGassoc"), FDRcritVal = 0.05, core = 1, sims = 50)
minTotSampleSize |
Minimum total sample size. |
maxTotSampleSize |
Maximum total sample size. |
SampleSizeSteps |
Sample size increments. |
NcntPer |
Percentage sample group 1 (control group) (NcntPer = 0.5 indicates a balanced design). |
targetDelta |
Target maximum difference in mean DNAm. (Either 'targetDelta' or 'deltaSD' should be specified) |
deltaSD |
Standard deviation of simulated differences. (Either 'targetDelta' or 'deltaSD' should be specified) |
J |
Number of CpGs tested/simulated (default: 100000). |
targetDmCpGs |
Target number of DM CpGs. |
tissueType |
Select a tissue type from the list of most commonly used tissue types: "Adult (PBMC)" (default), "Saliva", "Sperm", "Lymphoma", "Placenta", "Liver", "Colon", "Blood adult", "Blood 5 year olds", "Blood newborns", "Cord-blood (whole blood)" or "Cord-blood (PBMC)". |
detectionLimit |
Smallest detectable difference in DNAm (default: 0.01). |
DMmethod |
Method of Differential Methylation analysis: "limma" (default), "t-test (unequal var)", "t-test (equal var)", "Wilcox rank sum", "CPGassoc". |
FDRcritVal |
FDRcritVal (default: 0.05). |
core |
Number of threads for multi-threading (default: 1). |
sims |
Number of simulated data sets (default: 50). |
pwrEWAS will return an object with the following four attributes: meanPower, powerArray, deltaArray, and metric, where metric contains marTypeI, classicalPower, FDR, and FDC
outDelta <- pwrEWAS(minTotSampleSize = 10, maxTotSampleSize = 20, SampleSizeSteps = 10, NcntPer = 0.5, targetDelta = c(0.2, 0.5), J = 1000, targetDmCpGs = 10, tissueType = "Adult (PBMC)", detectionLimit = 0.01, DMmethod = "limma", FDRcritVal = 0.05, core = 2, sims = 30) outSD <- pwrEWAS(minTotSampleSize = 10, maxTotSampleSize = 20, SampleSizeSteps = 10, NcntPer = 0.5, deltaSD = c(0.02, 0.03), J = 1000, targetDmCpGs = 10, tissueType = "Adult (PBMC)", detectionLimit = 0.01, DMmethod = "limma", FDRcritVal = 0.05, core = 2, sims = 30)