[GDR-3409] Add prism data - first phase

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: gDRtestData
 Title: gDRtestData - R data package with testing dose response data
-Version: 1.11.3
-Date: 2026-06-01
+Version: 1.11.4
+Date: 2026-06-02
 Description: R package with internal dose-response test data. Package provides functions to generate
   input testing data that can be used as the input for gDR pipeline. It also contains qs2 files
   with MAE data processed by gDR.

NEWS.md

@@ -1,3 +1,6 @@
+## gDRtestData 1.11.4 - 2026-06-02
+* add PRISM public dataset
+
 ## gDRtestData 1.11.3 - 2026-06-01
 * add public data from DepMap Portal
 

R/dataset.R

@@ -2,7 +2,17 @@
 #'
 #' Cell line information from DepMap Public 24Q4.
 #'
+#' @section Loading:
+#' \code{data.table::fread(system.file("depmap_data/Model.csv.gz", package = "gDRtestData"))}
+#'
 #' @format Table
+#'
+#' @section Description:
+#' - Rows: Cell line identifiers
+#' - Columns: Metadata columns (see below)
+#' - Values: Cell line annotations and patient information
+#'
+#' Columns:
 #' \describe{
 #'   \item{ModelID}{Unique cell line identifier (ACH-XXXXX format)}
 #'   \item{CCLEName}{Cell line name from Cancer Cell Line Encyclopedia (CCLE)}
@@ -25,35 +35,44 @@
 #'   \item{PatientRace}{Patient/clinical indicated race (not derived)}
 #' }
 #'
-#' @source \url{https://depmap.org/portal/data_page/?tab=allData}
+#' @section Source:
+#' [DepMap Portal - Data](https://depmap.org/portal/data_page/?tab=allData)
+#'
+#' @section Details:
+#' Downloaded May 26, 2026 from DepMap Portal (version 24Q4).
 #'
-#' @details
-#' Downloaded May 26, 2024 from DepMap Portal (version 24Q4).
+#' Citation: 24Q4 DepMap Release, including CRISPR Screens, PRISM Drug Screens, Copy Number,
+#' Mutation, Expression, and Fusions
+#' DepMap, Broad (2024). DepMap 24Q4 Public. Figshare+. Dataset.
+#' \url{https://doi.org/10.25452/figshare.plus.27993248.v1}
 #'
-#' Citation: DepMap, Broad (2024). DepMap 24Q4 Public. Figshare+.
-#' https://doi.org/10.25452/figshare.plus.27993248.v1
 #'
 #' @docType data
-#' @keywords internal
+#' @keywords real_data
 #' @name DepMap_Model
 NULL
 
 #' CRISPR Gene Effect Scores
 #'
 #' Genome-wide CRISPR/Cas9 knockout dependency scores.
 #'
-#' @format Matrix with cell lines as rows and genes as columns
+#' @section Loading:
+#' \code{data.table::fread(system.file("depmap_data/CRISPRGeneEffect.csv.gz",
+#' package = "gDRtestData"))}
 #'
-#' @source \url{https://depmap.org/portal/data_page/?tab=allData}
+#' @format Matrix with cell lines as rows and genes as columns
 #'
-#' @details
+#' @section Description:
 #' - Rows: Cell line identifiers
 #' - Columns: NCBI gene IDs (Entrez format)
 #' - Values: Dependency scores (-1 to +1); lower = more essential
 #' - NA indicates insufficient screen coverage
 #'
+#' @inheritSection DepMap_Model Source
+#' @inheritSection DepMap_Model Details
+#'
 #' @docType data
-#' @keywords internal
+#' @keywords real_data
 #' @name DepMap_CRISPRGeneEffect
 NULL
 
@@ -62,18 +81,25 @@ NULL
 #'
 #' RNA-seq based gene expression for protein-coding genes.
 #'
-#' @format Matrix with ~1000 rows (cell lines) and ~19,000 columns (genes)
+#' @section Loading:
+#' \code{data.table::fread(
+#' system.file("depmap_data/OmicsExpressionProteinCodingGenesTPMLogp1.csv.gz",
+#' package = "gDRtestData"))}
 #'
-#' @source \url{https://depmap.org/portal/data_page/?tab=allData}
+#' @format Matrix with cell lines as rows and genes as columns
 #'
-#' @details
+#' @section Description:
 #' - Rows: Cell line identifiers
 #' - Columns: NCBI gene IDs (Entrez format)
 #' - Values: Log2(TPM + 1) transformed expression
 #' - Only protein-coding genes included
 #'
+#' @inheritSection DepMap_Model Source
+#' @inheritSection DepMap_Model Details
+#'
+#'
 #' @docType data
-#' @keywords internal
+#' @keywords real_data
 #' @name DepMap_OmicsExpressionProteinCodingGenesTPMLogp1
 NULL
 
@@ -82,18 +108,24 @@ NULL
 #'
 #' Binary matrix of known hotspot mutations from whole exome sequencing.
 #'
-#' @format Matrix with cell lines as rows and genes as columns
+#' @section Loading:
+#' \code{data.table::fread(system.file("depmap_data/OmicsSomaticMutationsMatrixHotspot.csv.gz",
+#' package = "gDRtestData"))}
 #'
-#' @source \url{https://depmap.org/portal/data_page/?tab=allData}
+#' @format Matrix with cell lines as rows and genes as columns
 #'
-#' @details
+#' @section Description:
 #' - Rows: Cell line identifiers
 #' - Columns: NCBI gene IDs
 #' - Values: Binary (0 = no mutation, 1 = hotspot mutation)
 #' - Hotspots defined by COSMIC and OncoKB
 #'
+#' @inheritSection DepMap_Model Source
+#' @inheritSection DepMap_Model Details
+#'
+#'
 #' @docType data
-#' @keywords internal
+#' @keywords real_data
 #' @name DepMap_OmicsSomaticMutationsMatrixHotspot
 NULL
 
@@ -102,18 +134,24 @@ NULL
 #'
 #' Binary matrix of damaging mutations (frame-shift, stop-gain, splice-site).
 #'
-#' @format Matrix with cell lines as rows and genes as columns
+#' @section Loading:
+#' \code{data.table::fread(system.file("depmap_data/OmicsSomaticMutationsMatrixDamaging.csv.gz",
+#' package = "gDRtestData"))}
 #'
-#' @source \url{https://depmap.org/portal/data_page/?tab=allData}
+#' @format Matrix with cell lines as rows and genes as columns
 #'
-#' @details
+#' @section Description:
 #' - Rows: Cell line identifiers
 #' - Columns: NCBI gene IDs
 #' - Values: Binary (0 = no mutation, 1 = damaging mutation)
 #' - High-confidence loss-of-function mutations
 #'
+#' @inheritSection DepMap_Model Source
+#' @inheritSection DepMap_Model Details
+#'
+#'
 #' @docType data
-#' @keywords internal
+#' @keywords real_data
 #' @name DepMap_OmicsSomaticMutationsMatrixDamaging
 NULL
 
@@ -122,18 +160,73 @@ NULL
 #'
 #' Gene-level copy number estimates from SNP microarray or WES.
 #'
-#' @format Matrix with cell lines as rows and genes as columns
+#' @section Loading:
+#' \code{data.table::fread(system.file("depmap_data/OmicsCNGene.csv.gz", package = "gDRtestData"))}
 #'
-#' @source \url{https://depmap.org/portal/data_page/?tab=allData}
+#' @format Matrix with cell lines as rows and genes as columns
 #'
-#' @details
+#' @section Description:
 #' - Rows: Cell line identifiers
 #' - Columns: NCBI gene IDs
 #' - Values: Log2 ratio relative to diploid reference
 #' - Typical range: -2 (deletion) to +3 (amplification)
 #' - 0 = diploid (2 copies)
 #'
+#' @inheritSection DepMap_Model Source
+#' @inheritSection DepMap_Model Details
+#'
+#'
 #' @docType data
-#' @keywords internal
+#' @keywords real_data
 #' @name DepMap_OmicsCNGene
 NULL
+
+#' PRISM Broad Screen Cancer Cell Line Viability Dataset
+#'
+#' The single-agent screening data from the PRISM platform -
+#' with one drug and 774 cell lines.
+#'
+#' @section Loading:
+#' \code{gDRutils::get_synthetic_data("prism")}
+#'
+#' @format A \code{\link[MultiAssayExperiment]{MultiAssayExperiment}} object
+#' containing a single-agent experiment with 5 assays.
+#'
+#' @section Description:
+#' ### Assays
+#' Experimental data matrices tracking cell line viability across processing stages:
+#' \describe{
+#'   \item{RawTreated}{Raw intensity values for treated cell line pools.}
+#'   \item{Controls}{Raw intensity values for DMSO and killing controls.}
+#'   \item{Normalized}{Viability scores relative to controls.}
+#'   \item{Averaged}{Replicate-averaged viability scores.}
+#'   \item{Metrics}{Dose-response curve parameters (e.g., IC50, AUC).}
+#' }
+#'
+#' ### Column Metadata (colData)
+#' Feature metadata describing the cell lines (models) across assays:
+#' \describe{
+#'   \item{clid}{Unique Broad Institute cell line identifier.}
+#'   \item{CellLineName}{Publicly recognized cancer cell line name.}
+#'   \item{Tissue}{Primary tissue of origin.}
+#'   \item{parental_identifier}{Identifier for parental strain/patient source.}
+#'   \item{subtype}{Histological or molecular subtype.}
+#'   \item{ReferenceDivisionTime}{Estimated doubling time in hours.}
+#' }
+#'
+#' ### Row Metadata (rowData)
+#' Feature metadata describing the treatment compounds across assays:
+#' \describe{
+#'   \item{Gnumber}{Broad Institute global substance identifier (Genentech/Broad ID).}
+#'   \item{DrugName}{Public or commercial name of the tested compound.}
+#'   \item{drug_moa}{Mechanism of action / biological target of the drug.}
+#'   \item{Duration}{Exposure time of the cell lines to the compound (e.g., 72h).}
+#' }
+#'
+#' @source Hagenbeek et al, Nat Comm 2026, Accepted
+#'
+#'
+#' @docType data
+#' @keywords real_data
+#' @name PRISMBroadScreen_Hagenbeek_NatComm_2026
+NULL

_pkgdown.yml

@@ -12,3 +12,6 @@ reference:
 - title: Generate test data
 - contents:
   - has_keyword("generate_test_data")
+- title: Examples of real data
+- contents:
+  - has_keyword("real_data")