directDblClassification {scDblFinder} | R Documentation |
Trains a classifier directly on the expression matrix to distinguish artificial doublets from real cells.
directDblClassification( sce, dbr = NULL, processing = "default", iter = 2, dims = 20, nrounds = 0.25, max_depth = 6, ... )
sce |
A |
dbr |
The expected doublet rate. By default this is assumed to be 1% per thousand cells captured (so 4% among 4000 thousand cells), which is appropriate for 10x datasets. Corrections for homeotypic doublets will be performed on the given rate. |
processing |
Counts (real and artificial) processing. Either
'default' (normal |
iter |
A positive integer indicating the number of scoring iterations. At each iteration, real cells that would be called as doublets are excluding from the training, and new scores are calculated. |
dims |
The number of dimensions used. |
nrounds |
Maximum rounds of boosting. If NULL, will be determined through cross-validation. |
max_depth |
Maximum depths of each tree. |
... |
Any doublet generation or pre-processing argument passed to 'scDblFinder'. |
A SummarizedExperiment-class
with the additional 'colData' column 'directDoubletScore'.
sce <- directDblClassification(mockDoubletSCE(), artificialDoublets=1) boxplot(sce$directDoubletScore~sce$type)