Run UMAP on a BANKSY embedding.
runBanksyUMAP(
se,
use_agf = FALSE,
lambda = 0.2,
use_pcs = TRUE,
npcs = 20L,
dimred = NULL,
ndims = NULL,
assay_name = NULL,
scale = TRUE,
group = NULL,
n_neighbors = 30L,
spread = 3,
min_dist = 0.1,
n_epochs = 300L,
M = NULL,
seed = NULL,
...
)
A SpatialExperiment
,
SingleCellExperiment
or SummarizedExperiment
object with computeBanksy
ran.
A logical vector specifying whether to use the AGF for computing UMAP.
A numeric vector in \(\in [0,1]\) specifying a spatial weighting parameter. Larger values (e.g. 0.8) incorporate more spatial neighborhood and find spatial domains, while smaller values (e.g. 0.2) perform spatial cell-typing.
A logical scalar specifying whether to run UMAP on PCs. If FALSE, runs on the BANKSY matrix.
An integer scalar specifying the number of principal components
to use if use_pcs
is TRUE.
A string scalar specifying the name of an existing
dimensionality reduction result to use. Will overwrite use_pcs
if
supplied.
An integer scalar specifying the number of dimensions to use if
dimred
is supplied.
A string scalar specifying the name of the assay used in
computeBanksy
.
A logical scalar specifying whether to scale features before UMAP. Only used when use_pcs is FALSE. Defaults to TRUE.
A string scalar specifying a grouping variable for samples in
se
. This is used to scale the samples in each group separately.
An integer scalar specifying the number of neighbors to use for UMAP.
A numeric scalar specifying the effective scale of embedded points.
A numeric scalar specifying the effective min. dist. between embedded points.
An integer scalar specifying the number of epochs to run UMAP optimization.
Advanced usage. An integer vector specifying the highest azimuthal
Fourier harmonic to use. If specified, overwrites the use_agf
argument.
Seed for UMAP. If not specified, no seed is set.
parameters to pass to uwot::umap
A SpatialExperiment / SingleCellExperiment / SummarizedExperiment
object with UMAP coordinates in reducedDims(se)
.
This function runs UMAP on the principal components computed on the BANKSY matrix.
data(rings)
spe <- computeBanksy(rings, assay_name = "counts", M = 1, k_geom = c(15, 30))
#> Computing neighbors...
#> Spatial mode is kNN_median
#> Parameters: k_geom=15
#> Done
#> Computing neighbors...
#> Spatial mode is kNN_median
#> Parameters: k_geom=30
#> Done
#> Computing harmonic m = 0
#> Using 15 neighbors
#> Done
#> Computing harmonic m = 1
#> Using 30 neighbors
#> Centering
#> Done
spe <- runBanksyPCA(spe, M = 1, lambda = 0.2, npcs = 20)
spe <- runBanksyUMAP(spe, M = 1, lambda = 0.2)