EmbedSOM (version 1.9)

EmbedSOM: Process the cells with SOM into a nice embedding

Description

Process the cells with SOM into a nice embedding

Usage

EmbedSOM(fsom = NULL, smooth = NULL, k = NULL, adjust = NULL,
  data = NULL, map = NULL, importance = NULL, emcoords = "flat",
  emcoords.pow = 1)

Arguments

fsom

FlowSOM object with a built SOM (used if data or map are missing)

smooth

Produce smoother (positive values) or more rough approximation (negative values).

k

How many SOM neighbors to take into the whole computation

adjust

How much non-local information to remove (parameter a)

data

Data matrix with points that optionally overrides the one from `fsom$data`

map

Map object in FlowSOM format, to optionally override `fsom$map`

importance

Importance of dimensions that was used to train the SOM

emcoords

Either a matrix of embedded coordinates (same number of rows as map$coords, and either 2 or 3 columns depending on the SOM grid dimension), or one of 'flat' (default behavior), 'som' (adjust the SOM coords according to U-matrix distances), 'mst' (embed to MST-like structure), 'fsom-mst' (embed to MST that should look exactly like that of FlowSOM), 'tsne' (embed using tSNE from package Rtsne), 'umap' (embed using UMAP from package umap) or 'uwot::umap' (embed using UMAP from package uwot)

emcoords.pow

Exaggeration factor (power) of the distances in U-matrix used for some methods of auto-generating emcoords; default 1.

Value

matrix with 2D or 3D coordinates of the embedded cels, depending on the map

Examples

# NOT RUN {
d <- cbind(rnorm(10000), 3*runif(10000), rexp(10000))
colnames(d) <- paste0("col",1:3)
map <- EmbedSOM::SOM(d, xdim=10, ydim=10)
e <- EmbedSOM::EmbedSOM(data=d, map=map)
EmbedSOM::PlotEmbed(e, data=d, 'col1', pch=16)
# }