documentation

R/aa_helper_functions.R

@@ -229,7 +229,7 @@ search_type_in_df <- function(x, type, info = TRUE) {
       # take first 'mo' column
       found <- colnames(x)[vapply(FUN.VALUE = logical(1), x, is.mo)]
     } else if ("mo" %in% colnames_formatted &&
-      suppressWarnings(all(x$mo %in% c(NA, AMR::microorganisms$mo)))) {
+      suppressWarnings(all(x$mo %in% c(NA, AMR_env$MO_lookup$mo)))) {
       found <- "mo"
     } else if (any(colnames_formatted %like_case% "^(mo|microorganism|organism|bacteria|ba[ck]terie)s?$")) {
       found <- sort(colnames(x)[colnames_formatted %like_case% "^(mo|microorganism|organism|bacteria|ba[ck]terie)s?$"])

R/eucast_rules.R

@@ -1116,7 +1116,7 @@ edit_rsi <- function(x,
       error = function(e) {
         txt_error()
         stop(paste0(
-          "In row(s) ", paste(rows[1:min(length(rows), 10)], collapse = ","),
+          "In row(s) ", paste(rows[seq_len(min(length(rows), 10))], collapse = ","),
           ifelse(length(rows) > 10, "...", ""),
           " while writing value '", to,
           "' to column(s) `", paste(cols, collapse = "`, `"),

R/join_microorganisms.R

@@ -165,10 +165,11 @@ join_microorganisms <- function(type, x, by, suffix, ...) {
     # otherwise use poorman, see R/aa_helper_pm_functions.R
     join_fn <- get(paste0("pm_", type), envir = asNamespace("AMR"))
   }
+  MO_df <- AMR_env$MO_lookup[, colnames(AMR::microorganisms), drop = FALSE]
   if (type %like% "full|left|right|inner") {
-    joined <- join_fn(x = x, y = AMR::microorganisms, by = by, suffix = suffix, ...)
+    joined <- join_fn(x = x, y = MO_df, by = by, suffix = suffix, ...)
   } else {
-    joined <- join_fn(x = x, y = AMR::microorganisms, by = by, ...)
+    joined <- join_fn(x = x, y = MO_df, by = by, ...)
   }
 
   if ("join.mo" %in% colnames(joined)) {
@@ -185,5 +186,5 @@ join_microorganisms <- function(type, x, by, suffix, ...) {
     warning_("in `", type, "_microorganisms()`: the newly joined data set contains ", nrow(joined) - nrow(x), " rows more than the number of rows of `x`.")
   }
 
-  as_original_data_class(joined, class(x.bak))  # will remove tibble groups
+  as_original_data_class(joined, class(x.bak)) # will remove tibble groups
 }

R/mo_matching_score.R

@@ -30,7 +30,7 @@
 #' Calculate the Matching Score for Microorganisms
 #'
 #' This algorithm is used by [as.mo()] and all the [`mo_*`][mo_property()] functions to determine the most probable match of taxonomic records based on user input.
-#' @author Dr. Matthijs Berends
+#' @author Dr. Matthijs Berends, 2018
 #' @param x Any user input value(s)
 #' @param n A full taxonomic name, that exists in [`microorganisms$fullname`][microorganisms]
 #' @note This algorithm was originally described in: Berends MS *et al.* (2022). **AMR: An R Package for Working with Antimicrobial Resistance Data**. *Journal of Statistical Software*, 104(3), 1-31; \doi{10.18637/jss.v104.i03}.
@@ -43,7 +43,7 @@
 #'
 #' where:
 #'
-#' * \ifelse{html}{\out{<i>x</i> is the user input;}}{\eqn{x} is the user input;}
+#' * \eqn{x} is the user input;
 #' * \ifelse{html}{\out{<i>n</i> is a taxonomic name (genus, species, and subspecies);}}{\eqn{n} is a taxonomic name (genus, species, and subspecies);}
 #' * \ifelse{html}{\out{<i>l<sub>n</sub></i> is the length of <i>n</i>;}}{l_n is the length of \eqn{n};}
 #' * \ifelse{html}{\out{<i>lev</i> is the <a href="https://en.wikipedia.org/wiki/Levenshtein_distance">Levenshtein distance function</a> (counting any insertion as 1, and any deletion or substitution as 2) that is needed to change <i>x</i> into <i>n</i>;}}{lev is the Levenshtein distance function (counting any insertion as 1, and any deletion or substitution as 2) that is needed to change \eqn{x} into \eqn{n};}

R/mo_property.R

@@ -36,12 +36,13 @@
 #' @param ... other arguments passed on to [as.mo()], such as 'minimum_matching_score', 'ignore_pattern', and 'remove_from_input'
 #' @param ab any (vector of) text that can be coerced to a valid antibiotic drug code with [as.ab()]
 #' @param open browse the URL using [`browseURL()`][utils::browseURL()]
-#' @details All functions will, at default, keep old taxonomic properties. Please refer to this example, knowing that *Escherichia blattae* was renamed to *Shimwellia blattae* in 2010:
-#' - `mo_name("Escherichia blattae")` will return `"Shimwellia blattae"` (with a note about the renaming)
-#' - `mo_ref("Escherichia blattae", keep_synonyms = TRUE)` will return `"Burgess et al., 1973"` (without a note)
-#' - `mo_ref("Shimwellia blattae", keep_synonyms = FALSE)` will return `"Priest et al., 2010"` (without a note)
+#' @details All functions will, at default, **not** keep old taxonomic properties, as synonyms are automatically replaced with the current taxonomy. Take for example *Escherichia blattae*, which was renamed to *Shimwellia blattae* in 2010:
+#' - `mo_genus("Escherichia blattae")` will return `"Shemwellia"` (with a note about the renaming)
+#' - `mo_genus("Escherichia blattae", keep_synonyms = TRUE)` will return `"Escherichia"` (with a warning that the name is outdated)
+#' - `mo_ref("Escherichia blattae")` will return `"Priest et al., 2010"` (with a note)
+#' - `mo_ref("Escherichia blattae", keep_synonyms = TRUE)` will return `"Burgess et al., 1973"` (with a warning)
 #'
-#' The short name - [mo_shortname()] - almost always returns the first character of the genus and the full species, like `"E. coli"`. Exceptions are abbreviations of staphylococci (such as *"CoNS"*, Coagulase-Negative Staphylococci) and beta-haemolytic streptococci (such as *"GBS"*, Group B Streptococci). Please bear in mind that e.g. *E. coli* could mean *Escherichia coli* (kingdom of Bacteria) as well as *Entamoeba coli* (kingdom of Protozoa). Returning to the full name will be done using [as.mo()] internally, giving priority to bacteria and human pathogens, i.e. `"E. coli"` will be considered *Escherichia coli*. In other words, `mo_fullname(mo_shortname("Entamoeba coli"))` returns `"Escherichia coli"`.
+#' The short name ([mo_shortname()]) returns the first character of the genus and the full species, such as `"E. coli"`, for species and subspecies. Exceptions are abbreviations of staphylococci (such as *"CoNS"*, Coagulase-Negative Staphylococci) and beta-haemolytic streptococci (such as *"GBS"*, Group B Streptococci). Please bear in mind that e.g. *E. coli* could mean *Escherichia coli* (kingdom of Bacteria) as well as *Entamoeba coli* (kingdom of Protozoa). Returning to the full name will be done using [as.mo()] internally, giving priority to bacteria and human pathogens, i.e. `"E. coli"` will be considered *Escherichia coli*. In other words, `mo_fullname(mo_shortname("Entamoeba coli"))` returns `"Escherichia coli"`.
 #'
 #' Since the top-level of the taxonomy is sometimes referred to as 'kingdom' and sometimes as 'domain', the functions [mo_kingdom()] and [mo_domain()] return the exact same results.
 #'
@@ -60,7 +61,8 @@
 #' SNOMED codes ([mo_snomed()]) are from the version of `r documentation_date(TAXONOMY_VERSION$SNOMED$accessed_date)`. See *Source* and the [microorganisms] data set for more info.
 #'
 #' Old taxonomic names (so-called 'synonyms') can be retrieved with [mo_synonyms()], the current taxonomic name can be retrieved with [mo_current()]. Both functions return full names.
-#' @inheritSection mo_matching_score Matching Score for Microorganisms
+#' @section Matching Score for Microorganisms:
+#' This function uses [as.mo()] internally, which uses an advanced algorithm to translate arbitrary user input to valid taxonomy using a so-called matching score. You can read about this public algorithm on the [MO matching score page][mo_matching_score()].
 #' @inheritSection as.mo Source
 #' @rdname mo_property
 #' @name mo_property

R/mo_source.R

@@ -288,9 +288,9 @@ check_validity_mo_source <- function(x, refer_to_name = "`reference_df`", stop_o
       return(FALSE)
     }
   }
-  if (!all(x$mo %in% c("", AMR::microorganisms$mo, AMR::microorganisms$fullname), na.rm = TRUE)) {
+  if (!all(x$mo %in% c("", AMR_env$MO_lookup$mo, AMR_env$MO_lookup$fullname), na.rm = TRUE)) {
     if (stop_on_error == TRUE) {
-      invalid <- x[which(!x$mo %in% c("", AMR::microorganisms$mo, AMR::microorganisms$fullname)), , drop = FALSE]
+      invalid <- x[which(!x$mo %in% c("", AMR_env$MO_lookup$mo, AMR_env$MO_lookup$fullname)), , drop = FALSE]
       if (nrow(invalid) > 1) {
         plural <- "s"
       } else {