BuildSOM: Build a self-organizing map

In saeyslab/FlowSOM: Using self-organizing maps for visualization and interpretation of cytometry data

Build a self-organizing map

Description

Build a SOM based on the data contained in the FlowSOM object

Usage

BuildSOM(fsom, colsToUse = NULL, silent = FALSE, outlierMAD = 4, ...)

Arguments

fsom	FlowSOM object containing the data, as constructed by the ReadInput function
colsToUse	Markers, channels or indices to use for building the SOM
silent	if TRUE, no progress updates will be printed
outlierMAD	Number of MAD when a cell is considered an outlier. See also TestOutliers
...	options to pass on to the SOM function (xdim, ydim, rlen, mst, alpha, radius, init, distf, importance)

Value

FlowSOM object containing the SOM result, which can be used as input for the BuildMST function

References

This code is strongly based on the kohonen package. R. Wehrens and L.M.C. Buydens, Self- and Super-organising Maps in R: the kohonen package J. Stat. Softw., 21(5), 2007

See Also

ReadInput, BuildMST

Examples

# Read from file
fileName <- system.file("extdata", "68983.fcs", package = "FlowSOM")
flowSOM.res <- ReadInput(fileName, compensate = TRUE, transform = TRUE,
                         scale = TRUE)

# Build the Self-Organizing Map
# E.g. with gridsize 5x5, presenting the dataset 20 times, 
# no use of MST in neighborhood calculations in between
flowSOM.res <- BuildSOM(flowSOM.res, colsToUse = c(9, 12, 14:18),
                        xdim = 5, ydim = 5, rlen = 20)

# Build the minimal spanning tree and apply metaclustering
flowSOM.res <- BuildMST(flowSOM.res)
metacl <- MetaClustering(flowSOM.res$map$codes,
                         "metaClustering_consensus", max = 10)

saeyslab/FlowSOM documentation built on July 6, 2024, 10:59 a.m.