The main steps of this procedure are outlined below. For a more detailed description of the methodology, please see Hao, et al Biorxiv 2022: tools:::Rd_expr_doi("10.1101/2022.02.24.481684")
ProjectIntegration(
object,
sketched.assay = "sketch",
assay = "RNA",
reduction = "integrated_dr",
features = NULL,
layers = "data",
reduction.name = NULL,
reduction.key = NULL,
method = c("sketch", "data"),
ratio = 0.8,
sketched.layers = NULL,
seed = 123,
verbose = TRUE
)Returns a Seurat object with an integrated dimensional reduction
A Seurat object with all cells for one dataset
Assay name for sketched-cell expression (default is 'sketch')
Assay name for original expression (default is 'RNA')
Dimensional reduction name for batch-corrected embeddings in the sketched object (default is 'integrated_dr')
Features used for atomic sketch integration
Names of layers for correction.
Name to save new reduction as; defaults to
paste0(reduction, '.orig')
Key for new dimensional reduction; defaults to creating
one from reduction.name
Methods to construct sketch-cell representation for all cells (default is 'sketch'). Can be one of:
“sketch”: Use random sketched data slot
“data”: Use data slot
Sketch ratio of data slot when dictionary.method is set
to “sketch”; defaults to 0.8
Names of sketched layers, defaults to all
layers of “object[[assay]]”
A positive integer. The seed for the random number generator, defaults to 123.
Print progress and message
First learn a atom dictionary representation to reconstruct each cell. Then, using this dictionary representation, reconstruct the embeddings of each cell from the integrated atoms.