Uniform Manifold Approximation and Projection(UMAP) algorithm for dimension reduction.
getUMAP( inSCE, useAssay = "counts", useAltExp = NULL, sample = NULL, reducedDimName = "UMAP", logNorm = TRUE, nNeighbors = 30, nIterations = 200, alpha = 1, minDist = 0.01, spread = 1, pca = TRUE, initialDims = 50 )
Input SingleCellExperiment object.
Assay to use for UMAP computation. If
The subset to use for UMAP computation, usually for the
selected.variable features. Default
Character vector. Indicates which sample each cell belongs to.
If given a single character, will take the annotation from
A name to store the results of the dimension reduction
coordinates obtained from this method. Default
Whether the counts will need to be log-normalized prior to
generating the UMAP via
The size of local neighborhood used for manifold
approximation. Larger values result in more global views of the manifold,
while smaller values result in more local data being preserved. Default
The number of iterations performed during layout
optimization. Default is
The initial value of "learning rate" of layout optimization.
The effective minimum distance between embedded points.
Smaller values will result in a more clustered/clumped embedding where nearby
points on the manifold are drawn closer together, while larger values will
result on a more even dispersal of points. Default
The effective scale of embedded points. In combination with
minDist, this determines how clustered/clumped the embedded points are.
Logical. Whether to perform dimension reduction with PCA before
Number of dimensions from PCA to use as input in UMAP.
A SingleCellExperiment object with UMAP computation
data(scExample, package = "singleCellTK") sce <- subsetSCECols(sce, colData = "type != 'EmptyDroplet'") umap_res <- getUMAP(inSCE = sce, useAssay = "counts", reducedDimName = "UMAP", logNorm = TRUE, nNeighbors = 30, alpha = 1, nIterations = 200, spread = 1, pca = TRUE, initialDims = 50)#>#>#>#>#>#>reducedDims(umap_res)#> List of length 1 #> names(1): UMAP