R/scanpyFunctions.R
runScanpyUMAP.Rd
runScanpyUMAP Computes UMAP from the given sce object and stores the UMAP computations back into the sce object
runScanpyUMAP(
inSCE,
useAssay = NULL,
useReducedDim = "scanpyPCA",
reducedDimName = "scanpyUMAP",
dims = 40,
minDist = 0.5,
nNeighbors = 10,
spread = 1,
alpha = 1,
gamma = 1,
externalReduction = NULL,
seed = 12345
)
(sce) object on which to compute the UMAP
Specify name of assay to use. Default is NULL
, so
useReducedDim
param will be used instead.
Reduction to use for computing UMAP.
Default is "scanpyPCA"
.
Name of new reducedDims object containing Scanpy UMAP
Default scanpyUMAP
.
Numerical value of how many reduction components to use for UMAP
computation. Default 40
.
Sets the "min_dist"
parameter to the underlying UMAP
call. Default 0.5
.
Sets the "n_neighbors"
parameter to the underlying
UMAP call. Default 10
.
Sets the "spread"
parameter to the underlying UMAP call.
Default 1
.
Sets the "alpha"
parameter to the underlying UMAP call.
Default 1
.
Sets the "gamma"
parameter to the underlying UMAP call.
Default 1
.
Pass DimReduce object if PCA computed through
other libraries. Default NULL
.
Specify numeric value to set as a seed. Default 12345
.
Updated sce object with UMAP computations stored
data(scExample, package = "singleCellTK")
if (FALSE) {
sce <- runScanpyNormalizeData(sce, useAssay = "counts")
sce <- runScanpyFindHVG(sce, useAssay = "scanpyNormData", method = "seurat")
sce <- runScanpyScaleData(sce, useAssay = "scanpyNormData")
sce <- runScanpyPCA(sce, useAssay = "scanpyScaledData")
sce <- runScanpyFindClusters(sce, useReducedDim = "scanpyPCA")
sce <- runScanpyUMAP(sce, useReducedDim = "scanpyPCA")
}