In LTLA/CellTypeReferences: Index of Reference Cell Type Datasets

From ExperimentHub to gypsum

knitr::opts_chunk$set(error=FALSE, message=FALSE)

Pulling assets from ExperimentHub.

library(ExperimentHub)
hub <- ExperimentHub()
prefix <- "celldex/monaco_immune/"
norm.hub <- hub[hub$rdatapath==paste0(prefix, "1.0.0/logcounts.rds")]
stopifnot(nrow(norm.hub) == 1L)
norm <- norm.hub[[1]]
str(norm)
coldata.hub <- hub[hub$rdatapath==paste0(prefix, "1.0.0/coldata.rds")]
stopifnot(nrow(coldata.hub) == 1L)
coldata <- coldata.hub[[1]]
coldata

Attaching ontology mappings.

path <- system.file("mapping", "monaco.tsv", package="celldex", mustWork=TRUE)
src <- read.delim(path, header=FALSE, stringsAsFactors=FALSE)

m <- match(coldata$label.fine, src[,1])
stopifnot(all(!is.na(m))) # sanity check

matched <- src[m, 2]
matched[matched==""] <- NA_character_
coldata$label.ont <- matched
coldata

Assembling some metadata.

meta <- list(
    title="Human bulk RNA-seq data from Monaco et al.",
    description=paste(c(
        "Normalized expression values of 114 human RNA-seq samples for Monaco et al. (2019).",
        "Expression values obtained from GEO (GSE107011) were already TPM normalized.",
        "Additional processing was performed to remove unsorted samples, remove non-expressed genes, collapse duplicate genes, and log~2~-normalize the expression values.",
        "Samples were annotated to 10 main cell types (`label.main`):",
        "- CD8+ T cells",
        "- T cells",
        "- CD4+ T cells",
        "- Progenitors",
        "- B cells",
        "- Monocytes",
        "- NK cells",
        "- Dendritic cells",
        "- Neutrophils",
        "- Basophils",
        "",
        "Samples were additionally annotated to 29 fine cell types (`label.fine`):",
        "- Naive CD8 T cells",
        "- Central memory CD8 T cells",
        "- Effector memory CD8 T cells",
        "- Terminal effector CD8 T cells",
        "- MAIT cells",
        "- Vd2 gd T cells",
        "- Non-Vd2 gd T cells",
        "- Follicular helper T cells",
        "- T regulatory cells",
        "- Th1 cells",
        "- Th1/Th17 cells",
        "- Th17 cells",
        "- Th2 cells",
        "- Naive CD4 T cells",
        "- Terminal effector CD4 T cells",
        "- Progenitor cells",
        "- Naive B cells",
        "- Non-switched memory B cells",
        "- Exhausted B cells",
        "- Switched memory B cells",
        "- Plasmablasts",
        "- Classical monocytes",
        "- Intermediate monocytes",
        "- Non classical monocytes",
        "- Natural killer cells",
        "- Plasmacytoid dendritic cells",
        "- Myeloid dendritic cells",
        "- Low-density neutrophils",
        "- Low-density basophils",
        "",
        "The subtypes have also been mapped to the Cell Ontology (`label.ont`)."
    ), collapse="\n"),
    taxonomy_id="9606",
    genome="GRCh38",
    sources=list(
        list(provider="PubMed", id="30726743"),
        list(provider="GEO", id="GSE107011"),
        list(provider="ExperimentHub", id=norm.hub$ah_id),
        list(provider="ExperimentHub", id=coldata.hub$ah_id)
    ),
    maintainer_name="Jared Andrews",
    maintainer_email="[e-mail]"
)

Saving it to disk.

library(celldex)
path <- "2024-02-26_output"
saveReference(norm, coldata, path, meta)

LTLA/CellTypeReferences documentation built on June 1, 2024, 12:12 p.m.