Closes #217: Add microbiology related SDTM (MB, MS, BE)

.github/CODEOWNERS

@@ -35,3 +35,8 @@ data-raw/nv_neuro.R @jwang-lilly
 data-raw/suppnv_neuro.R @jwang-lilly
 data-raw/ag_neuro.R @jwang-lilly
 data-raw/lb_neuro.R @jackychen651
+
+# microbiology
+data-raw/be.R @Gero1999
+data-raw/mb.R @Gero1999
+data-raw/ms.R @Gero1999

NEWS.md

@@ -22,6 +22,8 @@
 
 - Added the Lumipulse G pTau217, β-Amyloid 1-42 Plasma and their Ratio in `lb_neuro`. (#211)
 
+- Added Microbiology (`mb`), Susceptibility (`ms`) and Biospecimen Events (`be`) SDTM linked datasets. (#217)
+
 ## Documentation
 
 - The reference page has been updated to categorize datasets by therapeutic areas. (#204)

R/be.R

@@ -0,0 +1,31 @@
+# This file is automatically generated by data-raw/create_sdtms_data.R.
+# For updating it please edit inst/extdata/sdtms-specs.json and rerun create_sdtms_data.R.
+# Manual edits are not recommended, as changes may be overwritten.
+#' Biospecimen Events
+#'
+#' A synthetic SDTM BE domain representing specimen collection, aliquoting, and culturing events, with linkage to MB and MS domains
+#'
+#' @name be
+#' @title Biospecimen Events
+#' @keywords dataset microbiology
+#' @description A synthetic SDTM BE domain representing specimen collection, aliquoting, and culturing events, with linkage to MB and MS domains
+#' @docType data
+#' @format A data frame with 13 columns:
+#'   \describe{
+#'     \item{STUDYID}{Study Identifier}
+#'     \item{DOMAIN}{Domain Abbreviation}
+#'     \item{USUBJID}{Unique Subject Identifier}
+#'     \item{BESEQ}{Sequence Number}
+#'     \item{BEREFID}{Reference ID}
+#'     \item{BELNKID}{Link Identifier}
+#'     \item{BETERM}{Reported Term for the Biospecimen Event}
+#'     \item{BECAT}{Category for Biospecimen Event}
+#'     \item{BELOC}{Anatomical Location of Event}
+#'     \item{VISITNUM}{Visit Number}
+#'     \item{BEDTC}{Date/Time of Specimen Collection}
+#'     \item{BESTDTC}{Start Date/Time of Biospecimen Event}
+#'     \item{BEENDTC}{End Date/Time of Biospecimen Event}
+#'   }
+#'
+#' @source [Access the source of the Biospecimen Events dataset.](https://github.com/pharmaverse/pharmaversesdtm/blob/main/data/be.rda)
+"be"

R/mb.R

@@ -0,0 +1,49 @@
+# This file is automatically generated by data-raw/create_sdtms_data.R.
+# For updating it please edit inst/extdata/sdtms-specs.json and rerun create_sdtms_data.R.
+# Manual edits are not recommended, as changes may be overwritten.
+#' Microbiology Specimen
+#'
+#' A synthetic SDTM MB domain representing microbiology findings and linkage to MS domain (ms)
+#'
+#' @name mb
+#' @title Microbiology Specimen
+#' @keywords dataset microbiology
+#' @description A synthetic SDTM MB domain representing microbiology findings and linkage to MS domain (ms)
+#' @docType data
+#' @format A data frame with 21 columns:
+#'   \describe{
+#'     \item{STUDYID}{Study Identifier}
+#'     \item{DOMAIN}{Domain Abbreviation}
+#'     \item{USUBJID}{Unique Subject Identifier}
+#'     \item{MBSEQ}{Sequence Number}
+#'     \item{MBGRPID}{Group ID}
+#'     \item{MBREFID}{Reference ID}
+#'     \item{MBLNKGRP}{Link Group ID}
+#'     \item{MBTESTCD}{Microbiology Test or Finding Short Name}
+#'     \item{MBTEST}{Microbiology Test or Finding Name}
+#'     \item{MBTSTDTL}{Measurement, Test or Examination Detail}
+#'     \item{MBORRES}{Result or Finding in Original Units}
+#'     \item{MBORRESU}{Original Units}
+#'     \item{MBRSLSCL}{Result Scale}
+#'     \item{MBSTRESC}{Result or Finding in Standard Format}
+#'     \item{MBSTRESN}{Numeric Result/Finding in Standard Units}
+#'     \item{MBSTRESU}{Standard Units}
+#'     \item{MBSPEC}{Specimen Material Type}
+#'     \item{MBLOC}{Specimen Collection Location}
+#'     \item{MBMETHOD}{Method of Test or Examination}
+#'     \item{VISITNUM}{Visit Number}
+#'     \item{MBDTC}{Date/Time of Collection}
+#'   }
+#'
+#' @source [Access the source of the Microbiology Specimen dataset.](https://github.com/pharmaverse/pharmaversesdtm/blob/main/data/mb.rda)
+#' @details Contains a set of 6 unique Test Short Names and Test Names: \tabular{ll}{
+#'   \strong{MBTESTCD} \tab \strong{MBTEST} \cr
+#'   GMNCOC   \tab Gram Negative Cocci               \cr
+#'   GNROD    \tab Gram Negative Rods                \cr
+#'   GPRCOC   \tab Gram Positive Cocci               \cr
+#'   MCCOLCNT \tab Colony Count                      \cr
+#'   MCORGIDN \tab Microbial Organism Identification \cr
+#'   MTBCMPLX \tab Mycobacterium tuberculosis complex
+#' }
+
+"mb"

R/ms.R

@@ -0,0 +1,48 @@
+# This file is automatically generated by data-raw/create_sdtms_data.R.
+# For updating it please edit inst/extdata/sdtms-specs.json and rerun create_sdtms_data.R.
+# Manual edits are not recommended, as changes may be overwritten.
+#' Microbiology Susceptibility
+#'
+#' A synthetic SDTM MS domain with susceptibility results and linkage to MB domain (mb)
+#'
+#' @name ms
+#' @title Microbiology Susceptibility
+#' @keywords dataset microbiology
+#' @description A synthetic SDTM MS domain with susceptibility results and linkage to MB domain (mb)
+#' @docType data
+#' @format A data frame with 23 columns:
+#'   \describe{
+#'     \item{STUDYID}{Study Identifier}
+#'     \item{DOMAIN}{Domain Abbreviation}
+#'     \item{USUBJID}{Unique Subject Identifier}
+#'     \item{MSSEQ}{Sequence Number}
+#'     \item{MSREFID}{Reference ID}
+#'     \item{NHOID}{Non-host Organism ID}
+#'     \item{MSGRPID}{Group ID}
+#'     \item{MSLNKID}{Link ID}
+#'     \item{MSTESTCD}{Short Name of Assessment}
+#'     \item{MSTEST}{Name of Assessment}
+#'     \item{MSAGENT}{Agent Name}
+#'     \item{MSCONC}{Agent Concentration}
+#'     \item{MSCONCU}{Agent Concentration Units}
+#'     \item{MSORRES}{Result or Finding in Original Units}
+#'     \item{MSORRESU}{Original Units}
+#'     \item{MSSTRESC}{Result or Finding in Standard Format}
+#'     \item{MSSTRESN}{Numeric Result/Finding in Standard Units}
+#'     \item{MSSTRESU}{Standard Units}
+#'     \item{MSSPEC}{Specimen Material Type}
+#'     \item{MSLOC}{Location Used for the Measurement}
+#'     \item{MSMETHOD}{Method of Test or Examination}
+#'     \item{VISITNUM}{Visit Number}
+#'     \item{MSDTC}{Date/Time of Collection}
+#'   }
+#'
+#' @source [Access the source of the Microbiology Susceptibility dataset.](https://github.com/pharmaverse/pharmaversesdtm/blob/main/data/ms.rda)
+#' @details Contains a set of 3 unique Test Short Names and Test Names: \tabular{ll}{
+#'   \strong{MSTESTCD} \tab \strong{MSTEST} \cr
+#'   DIAZOINH \tab Diameter of the Zone of Inhibition\cr
+#'   MIC      \tab Minimum Inhibitory Concentration  \cr
+#'   MICROSUS \tab Microbial Susceptibility
+#' }
+
+"ms"

_pkgdown.yml

@@ -49,6 +49,10 @@ reference:
     contents:
       - has_keyword("metabolic")
 
+  - title: "Microbiology Datasets"
+    contents:
+      - has_keyword("microbiology")
+
   - title: "Neurology Datasets"
     contents:
       - has_keyword("neurology")

data-raw/be.R

@@ -0,0 +1,47 @@
+# This file only processes and saves the BE domain from that shared data source.
+# Dataset: BE
+# A synthetic SDTM BE domain representing specimen collection, aliquoting
+# and culturing events with linkage to Microbiology Specimen (mb) and Microbiology Susceptibility (ms) domains
+
+# NOTE: To add or modify records in the BE domain, you must edit the data structure in 'mb.R'.
+# All synthetic microbiology data (patients, specimens, results) are defined in 'mb.R'.
+
+# Source microbiology synthetic data
+source("data-raw/mb.R")
+
+be <- be %>%
+  # Order columns
+  select(
+    STUDYID,
+    DOMAIN,
+    USUBJID,
+    BESEQ,
+    BEREFID,
+    BELNKID,
+    BETERM,
+    BECAT,
+    BELOC,
+    VISITNUM,
+    BEDTC,
+    BESTDTC,
+    BEENDTC
+  ) %>%
+  # Label columns (as per CDISC SDTM v3.4)
+  set_variable_labels(
+    STUDYID = "Study Identifier",
+    DOMAIN = "Domain Abbreviation",
+    USUBJID = "Unique Subject Identifier",
+    BESEQ = "Sequence Number",
+    BEREFID = "Reference ID",
+    BELNKID = "Link Identifier",
+    BETERM = "Reported Term for the Biospecimen Event",
+    BECAT = "Category for Biospecimen Event",
+    BELOC = "Anatomical Location of Event",
+    VISITNUM = "Visit Number",
+    BEDTC = "Date/Time of Specimen Collection",
+    BESTDTC = "Start Date/Time of Biospecimen Event",
+    BEENDTC = "End Date/Time of Biospecimen Event"
+  )
+
+# Save dataset
+usethis::use_data(be, overwrite = TRUE, internal = FALSE)