Description Usage Arguments Details Value Author(s) References See Also Examples
Implement limma trans. See detail for default options.
1 | limma.trans.running(count.data, cond, normalize= TRUE)
|
count.data |
A numeric matrix of the count table. |
cond |
A vector of factors or numeric of the predictor variable. |
normalize |
Logical, whether to use "TMM" normalization. |
The limma trans first transform the data with the function log(y + sqrt(y^2 + y/θ^2) + 1/(2 * θ^2)), then estimate the θ such that the regression line of variance on started log of the mean has zero slope.
For the transformed data, we use calcNormFactors in edgeR to calculate the normalization factors with method equals to "TMM". Then we rescale each column by the 10^6 divided by the product of normalization factor and library size. It is a "TMM" version of count per million. Then we call lmFit and eBayes functions in limma with default options.
An object of class MArrayLM
Yilun Zhang, David Rocke
Our first paper.
1 2 3 | data(count.data)
data(condition)
pv.trans <- limma.trans.running(count.data,condition)
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.