RunUMAP.Matrix.py: Run UMAP dimensionality reduction on a matrix using...
In eisascience/scCustFx: single-cell custom fxs Package

RunUMAP.Matrix.py

R Documentation

Run UMAP dimensionality reduction on a matrix using umap-learn which needs python

Description

Run UMAP dimensionality reduction on a matrix using umap-learn which needs python

Usage

## S3 method for class 'Matrix.py'
RunUMAP(
  DGEmat,
  assay = NULL,
  n.neighbors = 30L,
  n.components = 2L,
  metric = "correlation",
  n.epochs = NULL,
  learning.rate = 1,
  min.dist = 0.3,
  spread = 1,
  set.op.mix.ratio = 1,
  local.connectivity = 1L,
  repulsion.strength = 1,
  negative.sample.rate = 5,
  a = NULL,
  b = NULL,
  seed.use = 42,
  metric.kwds = NULL,
  angular.rp.forest = FALSE,
  reduction.key = "UMAP_",
  verbose = TRUE,
  ...
)

Arguments

`DGEmat`	matrix of gene expression data
`assay`	character name for the assay
`n.neighbors`	integer, number of neighbors to use
`n.components`	integer, number of dimensions to keep
`metric`	character, metric to use for distance calculation
`n.epochs`	integer, number of epochs for optimization
`learning.rate`	numeric, learning rate for optimization
`min.dist`	numeric, minimum distance between points
`spread`	numeric, spread of clusters
`set.op.mix.ratio`	numeric, mix ratio for set operation
`local.connectivity`	integer, controls local connectivity
`repulsion.strength`	numeric, repulsion strength
`negative.sample.rate`	integer, number of negative samples
`a`	numeric, parameter for umap
`b`	numeric, parameter for umap
`seed.use`	integer, seed for reproducibility
`metric.kwds`	list, additional arguments for metric
`angular.rp.forest`	logical, use angular random projection forest
`reduction.key`	character, prefix for reduction result names
`verbose`	logical, verbosity flag