binKmeans-msi.dataset-method: Return a binary mask generated applying k-means clustering on...

In SPUTNIK: Spatially Automatic Denoising for Imaging Mass Spectrometry Toolkit

Return a binary mask generated applying k-means clustering on first 10 principal components of peaks intensities.

Description

Return a binary mask generated applying k-means clustering on first 10 principal components of peaks intensities.

Usage

## S4 method for signature 'msi.dataset'
binKmeans(object, ref = "detected", invert = FALSE, npcs = 10)

Arguments

object	msi.dataset-class object
ref	string (default = "detected). Sample reference image used to align the clusters.
invert	boolean (default = FALSE). If FALSE, the clusters are inversely aligned to the sample reference image.
npcs	int (default = 10). Number of principal components to calculate.

Value

ms.image-class object representing the binary mask image.

Examples

## Load package
library("SPUTNIK")

## Create the msi.dataset-class object
sz <- c(5, 4)
x <- matrix(rnorm(sz[1] * sz[2] * 20), sz[1] * sz[2], 20)
x[x < 0] <- 0
mz <- sort(sample(100, ncol(x)))
msiX <- msiDataset(x, mz, sz[1], sz[2])

## Generate binary mask by applying k-means on the entire dataset
roiImg <- refImageBinaryKmeans(msiX, npcs = 3)

## Plot the mask
# plot(roiImg)

SPUTNIK documentation built on May 29, 2024, 11:53 a.m.