test_dPDUI {InPAS} | R Documentation |
do test for dPDUI
test_dPDUI( eset, method = c("limma", "fisher.exact", "singleSample", "singleGroup"), normalize = c("none", "quantiles", "quantiles.robust", "mean", "median"), design, contrast.matrix, coef = 1, robust = FALSE, ..., sqlite_db )
eset |
An object of UTR3eSet. It is an output of
|
method |
A character(1), indicating the method for testing dPDUI. It can be "limma", "fisher.exact", "singleSample", or "singleGroup" |
normalize |
A character(1), indicating the normalization method. It can be "none", "quantiles", "quantiles.robust", "mean", or "median" |
design |
a design matrix of the experiment, with rows corresponding to
samples and columns to coefficients to be estimated. Defaults to the unit
vector meaning that the samples are treated as replicates. see
|
contrast.matrix |
a numeric matrix with rows corresponding to
coefficients in fit and columns containing contrasts. May be a vector if
there is only one contrast. see |
coef |
column number or column name specifying which coefficient or
contrast of the linear model is of interest. see more |
robust |
logical, should the estimation of the empirical Bayes prior parameters be robustified against outlier sample variances? |
... |
other arguments are passed to lmFit |
sqlite_db |
A path to the SQLite database for InPAS, i.e. the output of setup_sqlitedb(). |
if method is "limma", design matrix and contrast is required. if method is "fisher.exact", gp1 and gp2 is required.
An object of UTR3eSet, with the last element testRes
containing the test results in a matrix.
Jianhong Ou, Haibo Liu
run_singleSampleAnalysis()
, run_singleGroupAnalysis()
,
run_fisherExactTest()
, run_limmaAnalysis()
library(limma) path <- system.file("extdata", package = "InPAS") load(file.path(path, "eset.MAQC.rda")) tags <- colnames(eset@PDUI) g <- factor(gsub("\\..*$", "", tags)) design <- model.matrix(~ -1 + g) colnames(design) <- c("Brain", "UHR") contrast.matrix <- makeContrasts(contrasts = "Brain-UHR", levels = design) res <- test_dPDUI(eset = eset, method = "limma", normalize = "none", design = design, contrast.matrix = contrast.matrix)