Normalisation of MSnExp, MSnSet and Spectrum objects

Description

The normalise method (also available as normalize) performs basic normalisation on spectra intensities of single spectra ("Spectrum" or "Spectrum2" objects), whole experiments ("MSnExp" objects) or quantified expression data ("MSnSet" objects).

Raw spectra and experiments are normalised using max or sum only. For MSMS spectra could be normalised to their precursor additionally. Each peak intensity is divided by the highest intensity in the spectrum, the sum of intensities or the intensity of the precursor. These methods aim at facilitating relative peaks heights between different spectra.

The method parameter for "MSnSet" can be one of sum, max, quantiles, center.mean, center.median, .median, quantiles.robust or vsn. For sum and max, each feature's reporter intensity is divided by the maximum or the sum respectively. These two methods are applied along the features (rows).

center.mean and center.median translate the respective sample (column) intensities according to the column mean or median. diff.median translates all samples (columns) so that they all match the grand median. Using quantiles or quantiles.robust applies (robust) quantile normalisation, as implemented in normalize.quantiles and normalize.quantiles.robust of the preprocessCore package. vsn uses the vsn2 function from the vsn package. Note that the latter also glog-transforms the intensities. See respective manuals for more details and function arguments.

A scale method, mimicking the base scale method exists for "MSnSet" instances. See ?base::scale for details.

Arguments

Methods

The normalise methods:

signature(object = "MSnSet", method = "character")

Normalises the object reporter ions intensities using method.

signature(object = "MSnExp", method = "character")

Normalises the object peak intensities using method.

signature(object = "Spectrum", method = "character")

Normalises the object peak intensities using method.

signature(object = "Spectrum2", method = "character", precursorIntensity)

Normalises the object peak intensities using method. If method == "precursor", precursorIntensity allows to specify the intensity of the precursor manually.

The scale method:

signature(x = "MSnSet", center = "logical", scale = "logical")

See ?base::scale.

Examples

## quantifying full experiment
data(msnset)
msnset.nrm <- normalise(msnset, "quantiles")
msnset.nrm