PredictCellProb

Using the fit model, predict the cell abundance distributions

Usage

PredictCellProb(bulk, count, variable.features, output, k = 1)

Arguments

bulk

matrix of the query bulk data (features x samples)

count

single-cell count matrix (features x cells)

variable.features

character vector of the most variable features

output

ConDecon object with fit model

k

Number of nearest neighbor cells aggregated together when calculating rank correlation

Value

ConDecon object with inferred cell probabilities for each query bulk sample

Examples

data(counts_gps)
data(variable_genes_gps)
data(bulk_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)
ConDecon_obj = BuildModel(ConDecon_obj)

ConDecon_obj = PredictCellProb(bulk = bulk_gps, count = counts_gps,
variable.features = variable_genes_gps, output = ConDecon_obj)