R/03-Kersplat.R

In duohongrui/simmethods: A collection of 40+ simulation methods for singlce-cell RNA seqencing data

#' Estimate Parameters From Real Datasets by Kersplat
#'
#' This function is used to estimate useful parameters from a real dataset by
#' using `kersplatEstimate` function in Splatter package.
#'
#' @param ref_data A count matrix. Each row represents a gene and each column
#' represents a cell.
#' @param verbose Logical.
#' @param seed An integer of a random seed.
#' @importFrom peakRAM peakRAM
#' @importFrom splatter kersplatEstimate
#'
#' @return A list contains the estimated parameters and the results of execution
#' detection.
#' @export
#' @references
#' Zappia L, Phipson B, Oshlack A. Splatter: simulation of single-cell RNA sequencing data. Genome biology, 2017, 18(1): 1-15. <https://doi.org/10.1186/s13059-017-1305-0>
#'
#' Bioconductor URL: <https://bioconductor.org/packages/release/bioc/html/splatter.html>
#'
#' Github URL: <https://github.com/Oshlack/splatter>
#' @examples
#' \dontrun{
#' ref_data <- simmethods::data
#' # Estimate parameters
#' estimate_result <- Kersplat_estimation(ref_data = ref_data,
#'                                        verbose = TRUE,
#'                                        seed = 111)
#' estimate_result <- estimate_result[["estimate_result"]]
#' ## Check the class
#' class(estimate_result) == "KersplatParams"
#' }
#'
Kersplat_estimation <- function(ref_data,
                                verbose = FALSE,
                                seed
){
  ##############################################################################
  ####                               Check                                   ###
  ##############################################################################
  if(!is.matrix(ref_data)){
    ref_data <- as.matrix(ref_data)
  }
  ##############################################################################
  ####                            Estimation                                 ###
  ##############################################################################
  if(verbose){
    message("Estimating parameters using Kersplat")
  }
  # Seed
  set.seed(seed)
  # Estimation
  estimate_detection <- peakRAM::peakRAM(
    estimate_result <- splatter::kersplatEstimate(ref_data,
                                                  verbose = FALSE)
  )
  ##############################################################################
  ####                           Ouput                                       ###
  ##############################################################################
  estimate_output <- list(estimate_result = estimate_result,
                          estimate_detection = estimate_detection)
  return(estimate_output)
}


#' Simulate Datasets by Kersplat
#'
#' This function is used to simulate datasets from learned parameters by `kersplatSimulate`
#' function in Splatter package.
#'
#' @param parameters A object generated by [splatter::kersplatEstimate()]
#' @param other_prior A list with names of certain parameters. Some methods need
#' extra parameters to execute the estimation step, so you must input them. In
#' simulation step, the number of cells, genes, groups, batches, the percent of
#' DEGs and other variables are usually customed, so before simulating a dataset
#' you must point it out. See `Details` below for more information.
#' @param return_format A character. Alternative choices: list, SingleCellExperiment,
#' Seurat, h5ad. If you select `h5ad`, you will get a path where the .h5ad file saves to.
#' @param verbose Logical. Whether to return messages or not.
#' @param seed A random seed.
#' @importFrom splatter kersplatSimulate
#'
#' @export
#' @details
#' In addtion to simulate datasets with default parameters, users can set two extra
#' parameters before executing simulation step within Simple method:
#' 1. nCells. Just only type `other_prior = list(nCells = n)` when you want to
#' simulate a dataset with n cells.
#' 2. nGenes. Like `nCells`, users just only type `other_prior = list(nGenes = m)`
#' to get the dataset with m genes.
#' @export
#' @references
#' Zappia L, Phipson B, Oshlack A. Splatter: simulation of single-cell RNA sequencing data. Genome biology, 2017, 18(1): 1-15. <https://doi.org/10.1186/s13059-017-1305-0>
#'
#' Bioconductor URL: <https://bioconductor.org/packages/release/bioc/html/splatter.html>
#'
#' Github URL: <https://github.com/Oshlack/splatter>
#' @examples
#' \dontrun{
#' ref_data <- simmethods::data
#' # Estimate parameters
#' estimate_result <- Kersplat_estimation(ref_data = ref_data,
#'                                        verbose = TRUE,
#'                                        seed = 111)
#' # (1) Simulate a dataset with default parameters
#' simulate_result <- Kersplat_simulation(parameters = estimate_result[["estimate_result"]],
#'                                        return_format = "list",
#'                                        verbose = TRUE,
#'                                        seed = 111)
#' counts <- simulate_result[["simulate_result"]][["count_data"]]
#' dim(counts)
#'
#' # (2) Simulate a dataset with customed number of cells and genes
#' simulate_result <- Kersplat_simulation(parameters = estimate_result[["estimate_result"]],
#'                                        return_format = "list",
#'                                        other_prior = list(nCells = 500,
#'                                                           nGenes = 3000),
#'                                        verbose = TRUE,
#'                                        seed = 111)
#' counts <- simulate_result[["simulate_result"]][["count_data"]]
#' dim(counts)
#' }
#'
Kersplat_simulation <- function(parameters,
                                other_prior = NULL,
                                return_format,
                                verbose = FALSE,
                                seed
){
  ##############################################################################
  ####                               Check                                   ###
  ##############################################################################
  assertthat::assert_that(class(parameters) == "KersplatParams")

  if(!is.null(other_prior)){
    parameters <- simutils::set_parameters(parameters = parameters,
                                           other_prior = other_prior,
                                           method = "Kersplat")
  }

  # Get params to check
  params_check <- splatter::getParams(parameters, c("nCells",
                                                    "nGenes"))

  # Return to users
  message(paste0("nCells: ", params_check[['nCells']]))
  message(paste0("nGenes: ", params_check[['nGenes']]))
  ##############################################################################
  ####                            Simulation                                 ###
  ##############################################################################
  if(verbose){
    message("Simulating datasets using Kersplat")
  }
  # Seed
  parameters <- splatter::setParam(parameters, name = "seed", value = seed)
  # Simulation
  simulate_detection <- peakRAM::peakRAM(
    simulate_result <- splatter::kersplatSimulate(parameters,
                                                  verbose = verbose)
  )
  ##############################################################################
  ####                        Format Conversion                              ###
  ##############################################################################
  ## counts
  counts <- as.matrix(SingleCellExperiment::counts(simulate_result))
  ## col_data
  col_data <- data.frame("cell_name" = colnames(counts))
  rownames(col_data) <- col_data$cell_name
  ## row_data
  row_data <- BiocGenerics::as.data.frame(SingleCellExperiment::rowData(simulate_result)[, 1])
  rownames(row_data) <- row_data[, 1]
  colnames(row_data) <- "gene_name"
  # Establish SingleCellExperiment
  simulate_result <- SingleCellExperiment::SingleCellExperiment(list(counts = counts),
                                                                colData = col_data,
                                                                rowData = row_data)
  simulate_result <- simutils::data_conversion(SCE_object = simulate_result,
                                               return_format = return_format)

  ##############################################################################
  ####                           Ouput                                       ###
  ##############################################################################
  simulate_output <- list(simulate_result = simulate_result,
                          simulate_detection = simulate_detection)
  return(simulate_output)
}