Skip to contents

Performs DCA metric learning for single-cell data. This is the original metric learning method used in scLearn, implementing the algorithm from the dml package.

Usage

runDCA(
  high_varGenes,
  expression_profile,
  sample_information,
  strength = 0.1,
  seed = 1,
  verbose = TRUE
)

Arguments

high_varGenes

Character vector of high-variance genes

expression_profile

Numeric matrix (genes x cells)

sample_information

Named vector of cell type labels

strength

Subsampling strength (default: 0.1)

seed

Random seed (default: 1)

verbose

Print progress messages (default: TRUE)

Value

List containing:

  • expression_profile_trans: Transformed matrix (genes x cells)

  • expression_profile_origin: Original matrix

  • trans_matrix: Learned transformation matrix

  • sample_information: Input cell labels