R/MessmerESCData.R

In LTLA/scRNAseq: Collection of Public Single-Cell RNA-Seq Datasets

#' Obtain the Messmer ESC data
#'
#' Obtain the human embryonic stem cell single-cell RNA-seq data from Messmer et al. (2019).
#'
#' @param location Logical scalar indicating whether genomic coordinates should be returned.
#' @param legacy Logical scalar indicating whether to pull data from ExperimentHub.
#' By default, we use data from the gypsum backend.
#'
#' @details
#' Row data contains a single \code{"Length"} field describing the total exonic length of each feature.
#'
#' Column metadata is provided in the same form as supplied in E-MTAB-6819.
#' This contains information such as the cell phenotype (naive or primed) and the batch of origin.
#' Note that counts for technical replicates have already been summed together.
#'
#' Count data for ERCC spike-ins are stored in the \code{"ERCC"} entry of the \code{\link{altExps}}.
#'
#' If \code{location=TRUE}, the coordinates of the Ensembl gene models are stored in the \code{\link{rowRanges}} of the output.
#'
#' All data are downloaded from ExperimentHub and cached for local re-use.
#' Specific resources can be retrieved by searching for \code{scRNAseq/messmer-esc}.
#' 
#' @return A \linkS4class{SingleCellExperiment} object with a single matrix of read counts.
#'
#' @author Aaron Lun 
#'
#' @references
#' Messmer T et al. (2019). 
#' Transcriptional heterogeneity in naive and primed human pluripotent stem cells at single-cell resolution. 
#' \emph{Cell Rep} 26(4), 815-824.e4
#'
#' @examples
#' sce <- MessmerESCData()
#' 
#' @export
#' @importFrom SingleCellExperiment splitAltExps
MessmerESCData <- function(location=TRUE, legacy=FALSE) {
    if (!legacy) {
        sce <- fetchDataset("messmer-esc-2019", "2023-12-19", realize.assays=TRUE)

    } else {
        version <- "2.0.0"
        sce <- .create_sce(file.path("messmer-esc", version))

        spike.type <- ifelse(grepl("ERCC", rownames(sce)), "ERCC", "endogenous")
        sce <- splitAltExps(sce, spike.type, ref="endogenous")
        
        spike.exp <- altExp(sce, "ERCC")
        spikedata <- ERCCSpikeInConcentrations(volume = 1, dilution = 25000000)
        spikedata <- spikedata[rownames(spike.exp), ]
        rowData(spike.exp) <- cbind(rowData(spike.exp), spikedata)
        altExp(sce, "ERCC") <- spike.exp
    }

    .define_location_from_ensembl(sce, species="Hs", location=location)
}