Merge pull request #1088 from pharmaverse/1086-create-example-pc-ex-datasets

Create example PC, EX, DM datasets

Author: Gero1999

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: aNCA
 Title: (Pre-)Clinical NCA in a Dynamic Shiny App
-Version: 0.1.0.9125
+Version: 0.1.0.9126
 Authors@R: c(
     person("Ercan", "Suekuer", email = "ercan.suekuer@roche.com", role = "aut",
            comment = c(ORCID = "0009-0001-1626-1526")),

R/data.R

@@ -114,3 +114,90 @@
 #'
 #' @source Example data created for package demonstration and testing purposes.
 "adnca_example"
+
+
+#' pc_example
+#'
+#' An SDTM PC-like pharmacokinetic concentrations dataset derived from
+#' \code{\link{adnca_example}}. Intended to support and test the PC+EX upload
+#' workflow (see GitHub issue #624).
+#'
+#' @format A data frame with the same number of rows as \code{adnca_example}
+#'   and 11 variables:
+#' \describe{
+#'   \item{DOMAIN}{Character. Domain Abbreviation.}
+#'   \item{STUDYID}{Character. Study identifier.}
+#'   \item{USUBJID}{Character. Unique subject identifier.}
+#'   \item{PCTEST}{Character. Name of the measured analyte (mapped from PARAM).}
+#'   \item{PCSPEC}{Character. Specimen type (e.g., SERUM, URINE).}
+#'   \item{PCSTRESN}{Numeric. Numeric concentration result (mapped from AVAL).}
+#'   \item{PCSTRESU}{Character. Concentration units (mapped from AVALU).}
+#'   \item{PCDTC}{Character. Sample collection datetime (ISO 8601), synthesised
+#'     from AFRLT using an arbitrary reference origin.}
+#'   \item{PCRFTDTC}{Character. Reference dose datetime (ISO 8601), synthesised
+#'     from AFRLT - ARRLT.}
+#'   \item{PCELTM}{Character. Planned elapsed time from reference dose in
+#'     ISO 8601 duration format (e.g., "PT0.5H"), derived from NFRLT.}
+#'   \item{VOLUME}{Numeric. Volume of specimen collected (mL), for urine samples.}
+#'   \item{VOLUMEU}{Character. Volume units.}
+#' }
+#' @source Derived from \code{\link{adnca_example}} and \code{\link{dm_example}}
+#'   via \code{data-raw/sdtm_example.R}.
+"pc_example"
+
+
+#' ex_example
+#'
+#' An SDTM EX-like exposure/dosing dataset derived from
+#' \code{\link{adnca_example}}. Contains one row per dosing event per subject.
+#' Intended to support and test the PC+EX upload workflow (see GitHub issue #624).
+#'
+#' @format A data frame with 11 variables:
+#' \describe{
+#'   \item{DOMAIN}{Character. Domain abbreviation.}
+#'   \item{STUDYID}{Character. Study identifier.}
+#'   \item{USUBJID}{Character. Unique subject identifier.}
+#'   \item{EXTRT}{Character. Name of the treatment (mapped from DOSETRT).}
+#'   \item{EXDOSE}{Numeric. Dose amount (mapped from DOSEA).}
+#'   \item{EXDOSU}{Character. Dose units (mapped from DOSEU).}
+#'   \item{EXROUTE}{Character. Route of administration (mapped from ROUTE).}
+#'   \item{EXSTDTC}{Character. Dosing start datetime (ISO 8601), synthesised
+#'     from AFRLT - ARRLT using the subject's RFXSTDTC as reference origin.}
+#'   \item{EXENDTC}{Character. Dosing end datetime (ISO 8601), computed as
+#'     EXSTDTC + ADOSEDUR.}
+#'   \item{EXDUR}{Character. Duration of dose in ISO 8601 duration format
+#'     (e.g., "PT2.9H"), derived from ADOSEDUR.}
+#'   \item{EXELTM}{Character. Planned elapsed time from first dose in ISO 8601
+#'     duration format (e.g., "PT0H"), derived from NFRLT - NRRLT relative to
+#'     the subject's first dose.}
+#' }
+#' @source Derived from \code{\link{adnca_example}} and \code{\link{dm_example}}
+#'   via \code{data-raw/sdtm_example.R}.
+"ex_example"
+
+
+#' dm_example
+#'
+#' An SDTM DM-like demographics dataset derived from
+#' \code{\link{adnca_example}}. Contains one row per subject with demographic
+#' variables and a synthetic treatment start date (RFXSTDTC) that serves as the
+#' reference origin for datetimes in \code{\link{pc_example}} and
+#' \code{\link{ex_example}}.
+#'
+#' @format A data frame with one row per subject and 9 variables:
+#' \describe{
+#'   \item{DOMAIN}{Character. Domain Abbreviation.}
+#'   \item{STUDYID}{Character. Study identifier.}
+#'   \item{USUBJID}{Character. Unique subject identifier.}
+#'   \item{AGE}{Numeric. Age of the subject.}
+#'   \item{AGEU}{Character. Age units (e.g., "Years").}
+#'   \item{SEX}{Character. Sex of the subject.}
+#'   \item{RACE}{Character. Race of the subject.}
+#'   \item{ARM}{Character. Planned treatment arm (mapped from TRT01A).}
+#'   \item{ACTARM}{Character. Actual treatment arm (mapped from TRT01A).}
+#'   \item{RFXSTDTC}{Character. Date/time of first study treatment (ISO 8601).
+#'     Synthetic, staggered by 3 days per subject to simulate different
+#'     enrollment dates.}
+#' }
+#' @source Derived from \code{\link{adnca_example}} via \code{data-raw/sdtm_example.R}.
+"dm_example"

data-raw/sdtm_example.R

@@ -0,0 +1,101 @@
+# Derive SDTM-like example datasets (DM, PC, EX) from adnca_example
+#
+# This script creates three datasets with SDTM-style column names from the
+# existing ADaM-style adnca_example. Intended to support and test the PC+EX
+# upload workflow (see issues #624 and #1086).
+
+adnca_example <- read.csv("data-raw/adnca_example.csv", na.strings = c("", "NA"))
+
+# --- DM (Demographics) -------------------------------------------------------
+# One row per subject with demographics and a synthetic treatment start date.
+
+subjects <- adnca_example[!duplicated(adnca_example$USUBJID), ]
+
+# Stagger treatment start dates by 3 days per subject to simulate different
+# enrollment dates.
+base_date <- as.POSIXct("2024-01-15 08:00:00", tz = "UTC")
+subject_offsets_days <- seq(0, by = 3, length.out = nrow(subjects))
+rfxstdtc <- base_date + subject_offsets_days * 86400
+
+dm_example <- data.frame(
+  DOMAIN = "DM",
+  STUDYID  = subjects$STUDYID,
+  USUBJID  = subjects$USUBJID,
+  AGE      = subjects$AGE,
+  AGEU     = subjects$AGEU,
+  SEX      = subjects$SEX,
+  RACE     = subjects$RACE,
+  ARM      = subjects$TRT01A,
+  ACTARM   = subjects$TRT01A,
+  RFXSTDTC = format(rfxstdtc, "%Y-%m-%dT%H:%M:%S"),
+  stringsAsFactors = FALSE
+)
+
+# --- Reference date lookup ----------------------------------------------------
+# Used by both PC and EX below.
+
+ref_dates <- stats::setNames(
+  as.POSIXct(dm_example$RFXSTDTC, format = "%Y-%m-%dT%H:%M:%S", tz = "UTC"),
+  dm_example$USUBJID
+)
+
+# --- PC (Pharmacokinetic Concentrations) --------------------------------------
+# One row per concentration observation, same row count as adnca_example.
+
+subject_origin_pc <- ref_dates[adnca_example$USUBJID]
+dose_time_from_first <- adnca_example$AFRLT - adnca_example$ARRLT
+
+pc_example <- data.frame(
+  DOMAIN = "PC",
+  STUDYID  = adnca_example$STUDYID,
+  USUBJID  = adnca_example$USUBJID,
+  PCTEST   = adnca_example$PARAM,
+  PCSPEC   = adnca_example$PCSPEC,
+  PCSTRESN = adnca_example$AVAL,
+  PCSTRESU = adnca_example$AVALU,
+  PCDTC    = format(subject_origin_pc + adnca_example$AFRLT * 3600,
+                    "%Y-%m-%dT%H:%M:%S"),
+  PCRFTDTC = format(subject_origin_pc + dose_time_from_first * 3600,
+                    "%Y-%m-%dT%H:%M:%S"),
+  PCELTM   = sprintf("PT%gH", adnca_example$NFRLT),
+  VOLUME   = adnca_example$VOLUME,
+  VOLUMEU  = adnca_example$VOLUMEU,
+  stringsAsFactors = FALSE
+)
+
+# --- EX (Exposure / Dosing) ---------------------------------------------------
+# One row per dosing event, deduplicated from adnca_example.
+
+ex_example <- adnca_example %>%
+  dplyr::mutate(
+    dose_time = AFRLT - ARRLT,
+    nominal_dose_time = NFRLT - NRRLT
+  ) %>%
+  dplyr::distinct(STUDYID, USUBJID, DOSETRT, ATPTREF, .keep_all = TRUE) %>%
+  dplyr::group_by(USUBJID) %>%
+  dplyr::mutate(
+    subject_origin = ref_dates[USUBJID],
+    exeltm = nominal_dose_time - min(nominal_dose_time)
+  ) %>%
+  dplyr::ungroup() %>%
+  dplyr::transmute(
+    DOMAIN   = "EX",
+    STUDYID,
+    USUBJID,
+    EXTRT    = DOSETRT,
+    EXDOSE   = DOSEA,
+    EXDOSU   = DOSEU,
+    EXROUTE  = ROUTE,
+    EXSTDTC  = format(subject_origin + dose_time * 3600, "%Y-%m-%dT%H:%M:%S"),
+    EXENDTC  = format(subject_origin + dose_time * 3600 + ADOSEDUR * 3600,
+                      "%Y-%m-%dT%H:%M:%S"),
+    EXDUR    = sprintf("PT%gH", ADOSEDUR),
+    EXELTM   = sprintf("PT%gH", exeltm)
+  ) %>%
+  as.data.frame()
+
+# --- Save all three -----------------------------------------------------------
+
+usethis::use_data(dm_example, overwrite = TRUE)
+usethis::use_data(pc_example, overwrite = TRUE)
+usethis::use_data(ex_example, overwrite = TRUE)

data/dm_example.rda

@@ -26,6 +26,7 @@ Clast
 Cmax
 Cond
 Customizable
+DM
 DOSEA
 DOSETRT
 DOSEU
@@ -38,6 +39,7 @@ ERTLST
 ERTMAX
 EV
 EVID
+EXSTDTC
 Extravascular
 Kezia
 Kobana
@@ -83,6 +85,7 @@ Pre
 QMD
 README
 RENALCL
+RFXSTDTC
 RRLTU
 RStudio
 RefGroups
@@ -132,8 +135,11 @@ customizable
 customizations
 dataformat
 dateTime
+datetime
+datetimes
 devtools
 df
+dm
 doi
 extravascular
 ggplot
@@ -154,6 +160,7 @@ nca
 ng
 oligo
 pak
+pc
 pcspec
 pharmacodynamics
 pharmacokinetic
@@ -176,6 +183,7 @@ SelectInputs
 signif
 src
 standardizations
+synthesised
 th
 tibble
 tidyverse