ClassifyReference: Use a reference dataset to classify itself. A good reference...

In CHETAH: Fast and accurate scRNA-seq cell type identification

Description

Use a reference dataset to classify itself. A good reference should have almost no mixture between reference cells.

Usage

ClassifyReference(ref_cells, ref_ct = "celltypes", ref_c = "counts",
  return = FALSE, ...)

Arguments

ref_cells	the reference, similar to CHETAHclassifier's ref_cells
ref_ct	the colData of ref_cells where the cell types are stored.
ref_c	same as input_c, but for the reference.
return	return the matrix that was used to produce the plot
...	Other variables to pass to CHETAHclassifier

Value

A square plot. The rows are the original cell types, the columns the classifion labels. The colors and sizes of the squares indicate which part of the cells of the rowname type are classified to the type of the column name. On the left of the plot, the percentage of cells that is classified to an intermediate type is plotted. A good reference would classify nearly 100

Examples

ClassifyReference(ref_cells = headneck_ref)

CHETAH documentation built on Nov. 8, 2020, 8:02 p.m.