Add cheese datasets

DESCRIPTION

@@ -34,4 +34,4 @@ Config/testthat/edition: 3
 Encoding: UTF-8
 LazyData: false
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.1

R/data.R

@@ -1,4 +1,4 @@
-#' Pediatric cancer gene expression
+#' Gene Expression of Pediatric Cancer
 #'
 #' Gene expression of 108 CCLE cell lines from 5 different pediatric cancers.
 #'
@@ -21,3 +21,42 @@
 #' data("pedcan_expression", package = "scimo")
 #' pedcan_expression
 "pedcan_expression"
+
+
+#' Abundance of Fungal Communities in Cheese
+#'
+#' Fungal community abundance of 74 ASVs sampled from the surface of three
+#' different French cheeses.
+#'
+#' @usage data("cheese_abundance", package = "scimo")
+#'
+#' @format For `cheese_abundance`, a [tibble][tibble::tibble-package]
+#' with columns:
+#' \describe{
+#'   \item{sample}{Sample ID.}
+#'   \item{cheese}{Appellation of the cheese. One of `Saint-Nectaire`,
+#'   `Livarot` or `Epoisses`.}
+#'   \item{rind_type}{One of `Natural` or `Washed`.}
+#'   \item{other columns}{Count of the ASV.}
+#' }
+#'
+#' @source This dataset came from \url{https://doi.org/10.24072/pcjournal.321}.
+#'
+#' @examples
+#' data("cheese_abundance", package = "scimo")
+#' cheese_abundance
+"cheese_abundance"
+
+#' @rdname cheese_abundance
+#' @format For `cheese_taxonomy`, a [tibble][tibble::tibble-package]
+#' with columns:
+#' \describe{
+#'   \item{asv}{ASV ID.}
+#'   \item{lineage}{Character corresponding to a standard concatenation of
+#'   taxonomic clades.}
+#'   \item{other columns}{Clade to which the ASV belongs.}
+#' }
+#' @examples
+#' data("cheese_taxonomy", package = "scimo")
+#' cheese_taxonomy
+"cheese_taxonomy"

_pkgdown.yml

@@ -15,6 +15,7 @@ reference:
 - title: Datasets
   contents:
   - '`pedcan_expression`'
+  - '`cheese_abundance`'
 - title: Helpers
   contents:
   - '`cv`'

data-raw/cheese_abundance.R

@@ -0,0 +1,43 @@
+## code to prepare `cheese_abundance` dataset goes here
+library(tidyverse)
+library(phyloseq)
+library(glue)
+
+phylo_cheese <- read_rds("data-raw/data/phyloseq_cheese.rds")
+
+cheese_taxonomy <-
+  phylo_cheese %>%
+  tax_table() %>%
+  as.data.frame() %>%
+  as_tibble(rownames = "sequence") %>%
+  mutate(lineage = glue("k__{Kingdom}|p__{Phylum}|c__{Class}|o__{Order}|f__{Family}|g__{Genus}|s__{Species}"),
+         lineage = str_replace_all(lineage, " ", "_")) %>%
+  arrange(lineage) %>%
+  rowid_to_column(var = "asv") %>%
+  mutate(asv = if_else(asv >= 10,
+                       paste0("asv_", asv),
+                       paste0("asv_0", asv))) %>%
+  select(asv, lineage, everything())
+
+cheese_abundance <-
+  cheese_taxonomy %>%
+  select(asv, sequence) %>%
+  left_join(otu_table(phylo_cheese)@.Data %>%
+              as_tibble(rownames = "sequence"), by = "sequence") %>%
+  select(-sequence) %>%
+  pivot_longer(-asv, names_to = "sample", values_to = "count") %>%
+  pivot_wider(names_from = asv, values_from = count) %>%
+  mutate(sample = str_remove_all(sample, "_ITS2_CURATED"),
+         sample = str_replace_all(sample, "echantillon", "sample")) %>%
+  mutate(cheese = str_remove_all(sample, "sample"),
+         cheese = str_remove_all(cheese, "-[1-3]"),
+         cheese = case_when(cheese == 1 ~ "Saint-Nectaire",
+                            cheese == 2 ~ "Livarot",
+                            cheese == 3 ~ "Epoisses"),
+         rind_type = if_else(cheese == "Saint-Nectaire", "Natural", "Washed"),
+         .after = sample)
+
+cheese_taxonomy <- select(cheese_taxonomy, -sequence)
+
+# usethis::use_data(cheese_abundance, overwrite = TRUE)
+# usethis::use_data(cheese_taxonomy, overwrite = TRUE)

dev/dev_history.R

@@ -52,6 +52,8 @@ library(testthat)
 
 # use_pkgdown()
 
+# use_data_raw("cheese_abundance")
+
 ####
 
 devtools::load_all()