Map2Latent

Use the latent space to expand the distributions of cell abundances and correlations on a basis of functions

Usage

Map2Latent(TrainingSet, latent, count, bulk, variable.features, k = 1)

Arguments

TrainingSet

Training set data (output from BuildTrainingSet)

latent

matrix of single-cell latent space (cells x dims)

count

single-cell count matrix (features x cells)

bulk

matrix of query bulk data (features x samples)

variable.features

character vector of variable features

k

Number of nearest neighbor cells aggregated together when calculating rank correlation

Value

ConDecon object with low dimensional embedding of the space of cell abundances and correlations

Examples

data(counts_gps)
data(latent_gps)
data(bulk_gps)
data(variable_genes_gps)

# For this example, we will reduce the training size to max.iter = 50 to reduce run time
TrainingSet = BuildTrainingSet(count = counts_gps, latent = latent_gps, max.iter = 50)

ConDecon_obj = Map2Latent(TrainingSet = TrainingSet, latent = latent_gps, count = counts_gps,
bulk = bulk_gps, variable.features = variable_genes_gps)