Document and finalise datasets

.Rbuildignore

@@ -1,2 +1,3 @@
 ^.*\.Rproj$
 ^\.Rproj\.user$
+^LICENSE\.md$

DESCRIPTION

@@ -1,15 +1,27 @@
 Package: DataTidyGelaDURT
 Type: Package
-Title: What the Package Does (Title Case)
+Title: Process and package data for Gela (2021) 
 Version: 0.1.0
-Author: Who wrote it
-Maintainer: The package maintainer <yourself@somewhere.net>
-Description: More about what it does (maybe more than one line)
-    Use four spaces when indenting paragraphs within the Description.
-License: What license is it under?
+Author: Miguel J Rodo
+Maintainer: Miguel J Rodo <rdxmig002@myuct.ac.za>
+Description: Provide data in rda and csv formats
+    that were used to obtain results in 
+    Gela (2021) - Effects of BCG vaccination
+    on donor unrestricted T cells in humans.
+License: CC BY 4.0
 Encoding: UTF-8
 LazyData: true
 Imports: 
-    magrittr
+    datautils (>= 0.1.0),
+    dplyr,
+    magrittr,
+    purrr,
+    readr,
+    stringr,
+    tidyr,
+    zip
 Depends: 
     R (>= 2.10)
+RoxygenNote: 7.1.1
+Remotes: 
+    MiguelRodo/datautils

NAMESPACE

@@ -1 +1,2 @@
-exportPattern("^[[:alpha:]]+")
+# Generated by roxygen2: do not edit by hand
+

R/data_tidy_clin.R

@@ -0,0 +1,25 @@
+#' @rdname clinical_data
+#'
+#' @title Clinical data
+#'
+#'
+#' @description Datasets containing clinical data for infants (\code{data_tidy_clin_infant})
+#' and adults (\code{data_tidy_clin_adult}). The infant dataset
+#' has one extra variable, \code{bcg}, indicating BCG status.
+#'
+#' @format Dataframes with the following variables
+#' \describe{
+#'   \item{pid}{character. Participant ID.}
+#'   \item{age}{"infant" or "adult". Age category of participant.}
+#'   \item{race}{"black" or "non_black". Race of participant.
+#'   Vast majority of non-black participants
+#'   are mixed race.}
+#'   \item{sex}{"male" or "female". Sex of participant.}
+#'   \item{bcg}{"bcg" or "no bcg". BCG status. Infants only.}
+#' }
+#'
+#' @aliases data_tidy_clin_infant,data_tidy_clin_adult,data_tidy_clin,clinical_data,data_clinical
+"data_tidy_clin_infant"
+
+#' @rdname clinical_data
+"data_tidy_clin_adult"

R/data_tidy_freq.R

@@ -0,0 +1,25 @@
+#' @rdname data_tidy_freq
+#'
+#' @title Major cell population frequencies
+#'
+#' @description Frequencies of major cell populations
+#'
+#' @format Dataframe with 720 rows and the following 5 columns:
+#' \describe{
+#'   \item{pid}{character. Participant ID.}
+#'   \item{bcg}{"bcg", "no bcg", "before" or "after".
+#'   BCG status for infants ("no bcg" -> delayed BCG; "bcg" -> BCG at birth)
+#'   and adults ("before" -> before BCG revaccination; "after" -> 35 days
+#'   after BCG revaccination).}
+#'   \item{pop}{character. Cell type. "mait" is MAIT cells,
+#'   "nkt" is NKT cells, "cd1b" is CD1b GMM T cells,
+#'   "gem" is GEM T cells, "gd" is TCRgd T cells,
+#'   "cd4" is CD4 T cells and "cd4_ifng" is
+#'   IFNg+ CD4 T cells.}
+#'   \item{freq}{numeric. Frequency of parent population, where
+#'   the parent population is all cells for all population types
+#'   except IFNg+ CD4 T cells, where the parent population is
+#'   CD4 T cells.}
+#' }
+#'
+"data_tidy_freq"

R/data_tidy_freq_ifng.R

@@ -0,0 +1,32 @@
+#' @rdname data_tidy_freq_ifng
+#'
+#' @title Frequencies of IFNg+ cells
+#'
+#' @description Background-subtracted frequencies of
+#' IFNg+ cells.
+#'
+#' @format Dataframe with 284 rows and the following 5 columns:
+#' \describe{
+#'   \item{pid}{character. Participant ID.}
+#'   \item{bcg}{"bcg", "no bcg".
+#'   BCG status for infants ("no bcg" -> delayed BCG; "bcg" -> BCG at birth).}
+#'   \item{pop}{character. Major cell type. "cd26_161" is CD26+CD161+ cells,
+#'   and "gd" is TCRgd T cells.}
+#'   \item{pop_sub}{character.
+#'   Further phenotyping of major cell type.
+#'   "-" means no further phenotyping,
+#'   "cd8[n/p]cd4[n/p]" means
+#'   CD8(-/+)CD4(-/+), and
+#'   "trav12[n/p]" means TRAV1-2(-/+).}
+#'   \item{freq_ifng}{numeric.
+#'   Frequency of parent population (). For all
+#'   populations except "trav12[n/p]", the parent population is
+#'   specified by \code{pop} and \code{pop_sub}, and
+#'   the frequency is for all cells that are IFNg}.
+#'   Where the \code{pop_sub} is "trav12[n/p]",
+#'   the parent population is
+#'   CD4+CD26+CD161+IFNg+ T cells, and the frequency is
+#'   for all cells that are TRAV1-2(-/+).}
+#' }
+#'
+"data_tidy_freq_ifng"

R/data_tidy_hladr_adult.R

@@ -0,0 +1,21 @@
+#' @rdname data_tidy_hladr_adult
+#'
+#' @title HLADR MFI by cell type for adults
+#'
+#' @description HLADR mean fluorescent intensity (MFI) by cell type
+#' for infants.
+#'
+#' @format Dataframe with 315 rows and the following 4 columns:
+#' \describe{
+#'   \item{pid}{character. Participant ID.}
+#'   \item{days}{integer. Days since BCG revaccination.
+#'   Day 0 corresponds to on the day of revaccination, but before
+#'   revaccination.}
+#'   \item{pop}{character. Cell type. "mait" is MAIT cells,
+#'   "nkt" is NKT cells, "cd1b" is CD1b GMM T cells,
+#'   "gd" is TCRgd T cells,
+#'   "cd4" is CD4 T cells.}
+#'   \item{hladr_mfi}{numeric. HLADR MFI.}
+#' }
+#'
+"data_tidy_hladr_adult"

R/data_tidy_hladr_infant.R

@@ -0,0 +1,21 @@
+#' @rdname data_tidy_hladr_infant
+#'
+#' @title HLADR MFI by cell type for infants
+#'
+#' @description HLADR mean fluorescent intensity (MFI) by cell type
+#' for infants.
+#'
+#' @format Dataframe with 315 rows and the following 4 columns:
+#' \describe{
+#'   \item{pid}{character. Participant ID.}
+#'   \item{bcg}{"bcg", "no bcg".
+#'   BCG status for infants ("no bcg" -> delayed BCG; "bcg" -> BCG at birth).}
+#'   \item{pop}{character. Cell type. "mait" is MAIT cells,
+#'   "nkt" is NKT cells, "cd1b" is CD1b GMM T cells,
+#'   "gd" is TCRgd T cells,
+#'   "cd4" is CD4 T cells and "cd4_ifng" is
+#'   IFNg+ CD4 T cells.}
+#'   \item{hladr_mfi}{numeric. HLADR MFI.}
+#' }
+#'
+"data_tidy_hladr_infant"

R/data_tidy_mem.R

@@ -0,0 +1,23 @@
+#' @rdname data_tidy_mem
+#'
+#' @title Frequencies of memory phenotypes
+#'
+#' @description Frequency of memory phenotype relative
+#' to the parent population.
+#'
+#' @format Dataframe with 284 rows and the following 5 columns:
+#' \describe{
+#'   \item{pid}{character. Participant ID.}
+#'   \item{age}{"infant" or "adult". Age category of participant.}
+#'   \item{grp}{character.
+#'   BCG status for infants ("no bcg" -> delayed BCG; "bcg" -> BCG at birth)
+#'   and adults ("0", "21", "35" and "365" days after BCG revaccination).}
+#'   \item{pop}{character.
+#'   Major cell type. "mait" is MAIT cells,
+#'   "nkt" is NKT cells, "gd" is TCRgd T cells,
+#'   "cd4" is CD4 T cells.}
+#'   \item{pop_sub}{character. Phenotype.}
+#'   \item{freq}{numeric. Frequency of parent population (specified
+#'   by \code{pop}).}
+#' }
+"data_tidy_mem"

data-raw/data_tidy_prep.Rmd

@@ -14,6 +14,12 @@ library(magrittr)
 library(stringr)
 ```
 
+```{r }
+dir_save_csv <- here::here("inst", "extdata")
+if (!dir.exists(dir_save_csv)) dir.create(dir_save_csv, 
+                                          recursive = TRUE)
+```
+
 ```{r , include = FALSE}
 unlink(here::here("data"))
 dir_data_raw <- file.path(
@@ -288,7 +294,8 @@ data_tidy_freq <- purrr::map_df(sheet_vec, function(sheet) {
   data_out
 
 }) %>%
-  tibble::as_tibble()
+  tibble::as_tibble() %>%
+  dplyr::select(-pid_sheet)
 ```
 
 ```{r }
@@ -302,6 +309,13 @@ usethis::use_data(data_tidy_freq,
                   overwrite = TRUE)
 ```
 
+```{r }
+readr::write_csv(
+  x = data_tidy_freq, 
+  file = file.path(dir_save_csv, "data_tidy_freq.csv")
+)
+```
+
 ## HLADR MFI: Infants (Figure 3)
 
 ```{r , include = FALSE}
@@ -442,6 +456,14 @@ usethis::use_data(
   )
 ```
 
+```{r }
+readr::write_csv(
+  x = data_tidy_hladr_infant, 
+  file = file.path(dir_save_csv, "data_tidy_hladr_infant.csv")
+)
+```
+
+
 ## HLADR MFI: Adults (Figure 4)
 
 ```{r , include = FALSE}
@@ -510,6 +532,13 @@ usethis::use_data(data_tidy_hladr_adult,
                   overwrite = TRUE)
 ```
 
+```{r }
+readr::write_csv(
+  x = data_tidy_hladr_adult, 
+  file = file.path(dir_save_csv, "data_tidy_hladr_adult.csv")
+)
+```
+
 ## IFN$\gamma$+ frequency: Infants (Figure 5)
 
 ```{r }
@@ -604,6 +633,14 @@ usethis::use_data(
   )
 ```
 
+```{r }
+readr::write_csv(
+  x = data_tidy_freq_ifng, 
+  file = file.path(dir_save_csv, "data_tidy_freq_ifng.csv")
+)
+```
+
+
 ## Memory profile (Figure 6)
 
 ```{r , include = FALSE}                           
@@ -734,6 +771,13 @@ usethis::use_data(
   )
 ```
 
+```{r }
+readr::write_csv(
+  x = data_tidy_mem, 
+  file = file.path(dir_save_csv, "data_tidy_mem.csv")
+)
+```
+
 ## Clinical data - Infants
 
 ### Copy of delayed BCG samples for Anele_.xlsx
@@ -1058,6 +1102,13 @@ data_tidy_clin_infant <- data_tidy_clin_infant %>%
   dplyr::mutate(age = "infant")
 ```
 
+##### Remove unused and very descriptive columns. 
+
+```{r }
+data_tidy_clin_infant <- data_tidy_clin_infant %>%
+  dplyr::select(-c(visit_age, gest_age, weight, length, head_circ))
+```
+
 ##### View
 
 ```{r }
@@ -1071,6 +1122,14 @@ usethis::use_data(data_tidy_clin_infant,
                   overwrite = TRUE)
 ```
 
+```{r }
+readr::write_csv(
+  x = data_tidy_clin_infant, 
+  file = file.path(dir_save_csv, "data_tidy_clin_infant.csv")
+)
+```
+
+
 ## Clinical data - Adults
 
 ### TBRU samples for Anele .xlsx
@@ -1380,6 +1439,13 @@ data_tidy_clin_adult <- data_tidy_clin_adult %>%
   dplyr::select(pid, age, sex, race, everything())
 ```
 
+##### Remove unused and very descriptive columns. 
+
+```{r }
+data_tidy_clin_adult <- data_tidy_clin_adult %>%
+  dplyr::select(-c(age_in_years, hgbval, height, weight, ppd))
+```
+
 #### View
 
 ```{r }
@@ -1392,3 +1458,30 @@ datautils::view_cols(
 usethis::use_data(data_tidy_clin_adult, 
                   overwrite = TRUE)
 ```
+
+```{r }
+readr::write_csv(
+  x = data_tidy_clin_adult, 
+  file = file.path(dir_save_csv, "data_tidy_clin_adult.csv")
+)
+```
+
+## Zip files together
+
+```{r }
+wd <- getwd()
+setwd(dirname(wd))
+file_vec <- list.files(dir_save_csv, full.names = FALSE, 
+                       pattern = "csv$")
+file_vec <- paste0("inst/extdata/", file_vec)
+file_zip <- file.path("inst", "extdata", 
+                      "data_tidy_gela_durt.zip")
+if (file.exists(file_zip)) unlink(file_zip, recursive = TRUE)
+
+zip::zip(
+  zipfile = file_zip, 
+  files = file_vec
+)
+
+setwd(wd)
+```

inst/extdata/data_tidy_clin_adult.csv

@@ -0,0 +1,26 @@
+pid,age,sex,race
+adult_01,adult,female,non_black
+adult_02,adult,female,non_black
+adult_03,adult,female,non_black
+adult_04,adult,male,non_black
+adult_05,adult,female,non_black
+adult_06,adult,female,non_black
+adult_07,adult,male,black
+adult_08,adult,male,non_black
+adult_09,adult,male,non_black
+adult_10,adult,female,non_black
+adult_11,adult,female,non_black
+adult_12,adult,female,black
+adult_13,adult,female,non_black
+adult_14,adult,female,black
+adult_15,adult,male,non_black
+adult_16,adult,male,non_black
+adult_17,adult,female,non_black
+adult_18,adult,male,non_black
+adult_19,adult,female,non_black
+adult_20,adult,female,black
+adult_21,adult,female,non_black
+adult_22,adult,female,non_black
+adult_23,adult,female,non_black
+adult_24,adult,female,black
+adult_25,adult,female,non_black