Run Supervised Latent Semantic Indexing

Run a supervised LSI (SLSI) dimensionality reduction supervised by a cell-cell kernel. SLSI is used to capture a linear transformation of peaks that maximizes its dependency to the given cell-cell kernel.

RunSLSI(object, ...)

# Default S3 method
RunSLSI(
  object,
  assay = NULL,
  n = 50,
  reduction.key = "SLSI_",
  graph = NULL,
  verbose = TRUE,
  seed.use = 42,
  ...
)

# S3 method for class 'Assay'
RunSLSI(
  object,
  assay = NULL,
  features = NULL,
  n = 50,
  reduction.key = "SLSI_",
  graph = NULL,
  verbose = TRUE,
  seed.use = 42,
  ...
)

# S3 method for class 'StdAssay'
RunSLSI(
  object,
  assay = NULL,
  features = NULL,
  n = 50,
  reduction.key = "SLSI_",
  graph = NULL,
  layer = "data",
  verbose = TRUE,
  seed.use = 42,
  ...
)

# S3 method for class 'Seurat'
RunSLSI(
  object,
  assay = NULL,
  features = NULL,
  n = 50,
  reduction.name = "slsi",
  reduction.key = "SLSI_",
  graph = NULL,
  verbose = TRUE,
  seed.use = 42,
  ...
)

Arguments

object: An object
...: Arguments passed to IRLBA irlba
assay: Name of Assay SLSI is being run on
n: Total Number of SLSI components to compute and store
reduction.key: dimensional reduction key, specifies the string before the number for the dimension names
graph: Graph used supervised by SLSI
verbose: Display messages
seed.use: Set a random seed. Setting NULL will not set a seed.
features: Features to compute SLSI on. If features=NULL, SLSI will be run using the variable features for the Assay5.
layer: Layer to run SLSI on
reduction.name: dimensional reduction name

Value

Returns Seurat object with the SLSI calculation stored in the reductions slot