more MOs

NEWS

@@ -1,10 +1,11 @@
 ## 0.1.2
-- Added full support for Windows, Linux and macOS; this package now works everywhere :)
+- Added full support for Windows, Linux and macOS
-- New function `guess_bactid` to determine the ID of a microorganism based on genus/species
+- New function `guess_bactid` to determine the ID of a microorganism based on genus/species or known abbreviations like MRSA
 - New functions `clipboard_import` and `clipboard_export` as helper functions to quickly copy and paste from/to software like Excel and SPSS
 - New algorithm to determine weighted isolates, can now be `"points"` or `"keyantibiotics"`, see `?first_isolate`
 - Renamed dataset `ablist` to `antibiotics`
 - Renamed dataset `bactlist` to `microorganisms`
+- Added more microorganisms to `bactlist`
 - Added analysis examples on help page of dataset `septic_patients`
 - Added support for character vector in join functions
 - Added warnings when applying a join results in more rows after than before the join

R/atc.R

@@ -237,3 +237,133 @@ abname <- function(abcode, from = c("guess", "atc", "molis", "umcg"), to = 'offi
 
   abcode
 }
+
+#' Find bacteria ID based on genus/species
+#'
+#' Use this function to determine a valid ID based on a genus (and species). This input could be a full name (like \code{"Staphylococcus aureus"}), an abbreviated name (like \code{"S. aureus"}), or just a genus. You could also use a \code{\link{paste}} of a genus and species column to use the full name as input: \code{x = paste(df$genus, df$species)}, where \code{df} is your dataframe.
+#' @param x character vector to determine \code{bactid}
+#' @export
+#' @importFrom dplyr %>% filter slice pull
+#' @return Character (vector).
+#' @seealso \code{\link{microorganisms}} for the dataframe that is being used to determine ID's.
+#' @examples
+#' # These examples all return "STAAUR", the ID of S. aureus:
+#' guess_bactid("stau")
+#' guess_bactid("STAU")
+#' guess_bactid("staaur")
+#' guess_bactid("S. aureus")
+#' guess_bactid("S aureus")
+#' guess_bactid("Staphylococcus aureus")
+#' guess_bactid("MRSA") # Methicillin-resistant S. aureus
+#' guess_bactid("VISA") # Vancomycin Intermediate S. aureus
+guess_bactid <- function(x) {
+  # remove dots and other non-text in case of "E. coli" except spaces
+  x <- gsub("[^a-zA-Z ]+", "", x)
+  # but spaces before and after should be omitted
+  x <- trimws(x, which = "both")
+  x.bak <- x
+  # replace space by regex sign
+  x <- gsub(" ", ".*", x, fixed = TRUE)
+  # add start and stop
+  x_species <- paste(x, 'species')
+  x <- paste0('^', x, '$')
+
+  for (i in 1:length(x)) {
+    if (tolower(x[i]) == '^e.*coli$') {
+      # avoid detection of Entamoeba coli in case of E. coli
+      x[i] <- 'Escherichia coli'
+    }
+    if (tolower(x[i]) == '^h.*influenzae$') {
+      # avoid detection of Haematobacter influenzae in case of H. influenzae
+      x[i] <- 'Haemophilus influenzae'
+    }
+    if (tolower(x[i]) == '^st.*au$'
+        | tolower(x[i]) == '^stau$'
+        | tolower(x[i]) == '^staaur$') {
+      # avoid detection of Staphylococcus auricularis in case of S. aureus
+      x[i] <- 'Staphylococcus aureus'
+    }
+    if (tolower(x[i]) == '^p.*aer$') {
+      # avoid detection of Pasteurella aerogenes in case of Pseudomonas aeruginosa
+      x[i] <- 'Pseudomonas aeruginosa'
+    }
+
+    # translate known trivial names to genus+species
+    if (toupper(x.bak[i]) == 'MRSA'
+        | toupper(x.bak[i]) == 'VISA'
+        | toupper(x.bak[i]) == 'VRSA') {
+      x[i] <- 'Staphylococcus aureus'
+    }
+    if (toupper(x.bak[i]) == 'MRSE') {
+      x[i] <- 'Staphylococcus epidermidis'
+    }
+    if (toupper(x.bak[i]) == 'VRE') {
+      x[i] <- 'Enterococcus'
+    }
+    if (toupper(x.bak[i]) == 'MRPA') {
+      # multi resistant P. aeruginosa
+      x[i] <- 'Pseudomonas aeruginosa'
+    }
+    if (toupper(x.bak[i]) == 'PISP'
+        | toupper(x.bak[i]) == 'PRSP') {
+      # peni resistant S. pneumoniae
+      x[i] <- 'Streptococcus pneumoniae'
+    }
+    if (toupper(x.bak[i]) == 'VISP'
+        | toupper(x.bak[i]) == 'VRSP') {
+      # vanco resistant S. pneumoniae
+      x[i] <- 'Streptococcus pneumoniae'
+    }
+
+    # let's try the ID's first
+    found <- AMR::microorganisms %>% filter(bactid == x.bak[i])
+
+    if (nrow(found) == 0) {
+      # now try exact match
+      found <- AMR::microorganisms %>% filter(fullname == x[i])
+    }
+    if (nrow(found) == 0) {
+      # try any match
+      found <- AMR::microorganisms %>% filter(fullname %like% x[i])
+    }
+    if (nrow(found) == 0) {
+      # try only genus, with 'species' attached
+      found <- AMR::microorganisms %>% filter(fullname %like% x_species[i])
+    }
+    if (nrow(found) == 0) {
+      # search for GLIMS code
+      if (toupper(x.bak[i]) %in% toupper(AMR::microorganisms.umcg$mocode)) {
+        found <- AMR::microorganisms.umcg %>% filter(toupper(mocode) == toupper(x.bak[i]))
+      }
+    }
+    if (nrow(found) == 0) {
+      # try splitting of characters and then find ID
+      # like esco = E. coli, klpn = K. pneumoniae, stau = S. aureus
+      x_split <- x
+      x_length <- nchar(x.bak[i])
+      x_split[i] <- paste0(x.bak[i] %>% substr(1, x_length / 2) %>% trimws(),
+                     '.* ',
+                     x.bak[i] %>% substr((x_length / 2) + 1, x_length) %>% trimws())
+      found <- AMR::microorganisms %>% filter(fullname %like% paste0('^', x_split[i]))
+    }
+    if (nrow(found) == 0) {
+      # try any match with text before and after original search string
+      # so "negative rods" will be "GNR"
+      if (x.bak[i] %like% "^Gram") {
+        x.bak[i] <- gsub("^Gram", "", x.bak[i], ignore.case = TRUE)
+        # remove leading and trailing spaces again
+        x.bak[i] <- trimws(x.bak[i], which = "both")
+      }
+      found <- AMR::microorganisms %>% filter(fullname %like% x.bak[i])
+    }
+
+    if (nrow(found) != 0) {
+      x[i] <- found %>%
+        slice(1) %>%
+        pull(bactid)
+    } else {
+      x[i] <- ""
+    }
+  }
+  x
+}

R/classes.R

@@ -361,26 +361,19 @@ print.mic <- function(x, ...) {
 
 #' @exportMethod summary.mic
 #' @export
-#' @importFrom dplyr %>% tibble group_by summarise pull
+#' @importFrom dplyr %>%
 #' @noRd
 summary.mic <- function(object, ...) {
   x <- object
   n_total <- x %>% length()
   x <- x[!is.na(x)]
   n <- x %>% length()
-  return(c("Mode" = 'mic',
+  lst <- c('mic',
-           "<NA>" = n_total - n,
+           n_total - n,
-           "Min." = sort(x)[1] %>% as.character(),
+           sort(x)[1] %>% as.character(),
-           "Max." = sort(x)[n] %>% as.character()
+           sort(x)[n] %>% as.character())
-  ))
+  names(lst) <- c("Mode", "<NA>", "Min.", "Max.")
-  cat("Class 'mic': ", n, " isolates\n", sep = '')
+  lst
-  cat('\n')
-  cat('<NA> ', n_total - n, '\n')
-  cat('\n')
-  tbl <- tibble(x = x, y = 1) %>% group_by(x) %>% summarise(y = sum(y))
-  cnt <- tbl %>% pull(y)
-  names(cnt) <- tbl %>% pull(x)
-  print(cnt)
 }
 
 #' @exportMethod plot.mic

R/clipboard.R

@@ -1,17 +1,35 @@
 #' Import/export from clipboard
 #'
-#' These are helper functions around \code{\link{read.table}} and \code{\link{write.table}} to import from and export to clipboard, with support for Windows, Linux and macOS. The data will be read and written as tab-separated by default, which makes it possible to copy and paste from other software like Excel and SPSS without further transformation.
+#' These are helper functions around \code{\link{read.table}} and \code{\link{write.table}} to import from and export to clipboard with support for Windows, Linux and macOS. The data will be read and written as tab-separated by default, which makes it possible to copy and paste from other software like Excel and SPSS without further transformation. See Details for an example.
 #' @rdname clipboard
 #' @name clipboard
 #' @inheritParams utils::read.table
 #' @inheritParams utils::write.table
-#' @param startrow \emph{n}th row to start importing from. For \code{clipboard_import}, when \code{header = TRUE} the import will start on row \code{startrow} \emph{below} the header.
+#' @param startrow \emph{n}th row to start importing from. When \code{header = TRUE}, the import will start on row \code{startrow} \emph{below} the header.
 #' @param as_vector a logical value indicating whether data consisting of only one column should be imported as vector using \code{\link[dplyr]{pull}}. This will strip off the header.
 #' @param info print info about copying
 #' @keywords clipboard clipboard_import clipboard_export import export
 #' @importFrom dplyr %>% pull as_tibble
 #' @importFrom utils read.delim write.table object.size
-#' @details For \code{clipboard_export}, the reserved clipboard size for exporting will be set automatically to 125\% of the object size of \code{x}. This way, it is possible to export data with thousands of rows as the only limit will be your systems RAM.
+#' @details For \code{clipboard_export()}, the reserved clipboard size for exporting will be set to 125\% of the object size of \code{x}. This way, it is possible to export data with thousands of rows as the only limit will be your systems RAM.
+#'
+#'   Example for copying from Excel:
+#'   \if{html}{
+#'     \out{<div style="text-align: left">}\figure{Excel_copy.png}\out{</div>}
+#'   }
+#'   \if{latex}{
+#'     \out{\begin{left}}\figure{Excel_copy.png}\out{\end{left}}
+#'   }
+#'   \cr
+#'   And pasting in R: \cr \cr
+#'   \code{> data <- clipboard_import()} \cr
+#'   \code{> data} \cr
+#'   \if{html}{
+#'     \out{<div style="text-align: left">}\figure{Excel_paste.png}\out{</div>}
+#'   }
+#'   \if{latex}{
+#'     \out{\begin{left}}\figure{Excel_paste.png}\out{\end{left}}
+#'   }
 #' @export
 #' @return data.frame
 clipboard_import <- function(sep = '\t',

R/first_isolates.R

@@ -610,105 +610,3 @@ key_antibiotics_equal <- function(x,
   }
   result
 }
-
-#' Find bacteria ID based on genus/species
-#'
-#' Use this function to determine a valid ID based on a genus (and species). This input could be a full name (like \code{"Staphylococcus aureus"}), an abbreviated name (like \code{"S. aureus"}), or just a genus. You could also use a \code{\link{paste}} of a genus and species column to use the full name as input: \code{x = paste(df$genus, df$species)}, where \code{df} is your dataframe.
-#' @param x character vector to determine \code{bactid}
-#' @export
-#' @importFrom dplyr %>% filter slice pull
-#' @return Character (vector).
-#' @seealso \code{\link{microorganisms}} for the dataframe that is being used to determine ID's.
-#' @examples
-#' # These examples all return "STAAUR", the ID of S. aureus:
-#' guess_bactid("stau")
-#' guess_bactid("STAU")
-#' guess_bactid("staaur")
-#' guess_bactid("S. aureus")
-#' guess_bactid("S aureus")
-#' guess_bactid("Staphylococcus aureus")
-#' guess_bactid("MRSA") # Methicillin-resistant S. aureus
-#' guess_bactid("VISA") # Vancomycin Intermediate S. aureus
-guess_bactid <- function(x) {
-  # remove dots and other non-text in case of "E. coli" except spaces
-  x <- gsub("[^a-zA-Z ]+", "", x)
-  x.bak <- x
-  # replace space by regex sign
-  x <- gsub(" ", ".*", x, fixed = TRUE)
-  # add start and stop
-  x_species <- paste(x, 'species')
-  x <- paste0('^', x, '$')
-
-  for (i in 1:length(x)) {
-    if (tolower(x[i]) == '^e.*coli$') {
-      # avoid detection of Entamoeba coli in case of E. coli
-      x[i] <- 'Escherichia coli'
-    }
-    if (tolower(x[i]) == '^h.*influenzae$') {
-      # avoid detection of Haematobacter influenzae in case of H. influenzae
-      x[i] <- 'Haemophilus influenzae'
-    }
-    if (tolower(x[i]) == '^st.*au$'
-        | tolower(x[i]) == '^stau$'
-        | tolower(x[i]) == '^staaur$') {
-      # avoid detection of Staphylococcus auricularis in case of S. aureus
-      x[i] <- 'Staphylococcus aureus'
-    }
-    if (tolower(x[i]) == '^p.*aer$') {
-      # avoid detection of Pasteurella aerogenes in case of Pseudomonas aeruginosa
-      x[i] <- 'Pseudomonas aeruginosa'
-    }
-    # translate known trivial names to genus+species
-    if (toupper(x.bak[i]) == 'MRSA'
-        | toupper(x.bak[i]) == 'VISA'
-        | toupper(x.bak[i]) == 'VRSA') {
-      x[i] <- 'Staphylococcus aureus'
-    }
-    if (toupper(x.bak[i]) == 'MRSE') {
-      x[i] <- 'Staphylococcus epidermidis'
-    }
-    if (toupper(x.bak[i]) == 'VRE') {
-      x[i] <- 'Enterococcus'
-    }
-
-    # let's try the ID's first
-    found <- AMR::microorganisms %>% filter(bactid == x.bak[i])
-
-    if (nrow(found) == 0) {
-      # now try exact match
-      found <- AMR::microorganisms %>% filter(fullname == x[i])
-    }
-    if (nrow(found) == 0) {
-      # try any match
-      found <- AMR::microorganisms %>% filter(fullname %like% x[i])
-    }
-    if (nrow(found) == 0) {
-      # try only genus, with 'species' attached
-      found <- AMR::microorganisms %>% filter(fullname %like% x_species[i])
-    }
-    if (nrow(found) == 0) {
-      # search for GLIMS code
-      if (toupper(x.bak[i]) %in% toupper(AMR::microorganisms.umcg$mocode)) {
-        found <- AMR::microorganisms.umcg %>% filter(toupper(mocode) == toupper(x.bak[i]))
-      }
-    }
-    if (nrow(found) == 0) {
-      # try splitting of characters and then find ID
-      # like esco = E. coli, klpn = K. pneumoniae, stau = S. aureus
-      x_length <- nchar(x.bak[i])
-      x[i] <- paste0(x.bak[i] %>% substr(1, x_length / 2) %>% trimws(),
-                     '.* ',
-                     x.bak[i] %>% substr((x_length / 2) + 1, x_length) %>% trimws())
-      found <- AMR::microorganisms %>% filter(fullname %like% paste0('^', x[i]))
-    }
-
-    if (nrow(found) != 0) {
-      x[i] <- found %>%
-        slice(1) %>%
-        pull(bactid)
-    } else {
-      x[i] <- ""
-    }
-  }
-  x
-}

man/clipboard.Rd

@@ -28,7 +28,7 @@ clipboard_export(x, sep = "\\t", dec = ".", na = "", header = TRUE,
 
 \item{na}{the string to use for missing values in the data.}
 
-\item{startrow}{\emph{n}th row to start importing from. For \code{clipboard_import}, when \code{header = TRUE} the import will start on row \code{startrow} \emph{below} the header.}
+\item{startrow}{\emph{n}th row to start importing from. When \code{header = TRUE}, the import will start on row \code{startrow} \emph{below} the header.}
 
 \item{as_vector}{a logical value indicating whether data consisting of only one column should be imported as vector using \code{\link[dplyr]{pull}}. This will strip off the header.}
 
@@ -41,10 +41,28 @@ clipboard_export(x, sep = "\\t", dec = ".", na = "", header = TRUE,
 data.frame
 }
 \description{
-These are helper functions around \code{\link{read.table}} and \code{\link{write.table}} to import from and export to clipboard, with support for Windows, Linux and macOS. The data will be read and written as tab-separated by default, which makes it possible to copy and paste from other software like Excel and SPSS without further transformation.
+These are helper functions around \code{\link{read.table}} and \code{\link{write.table}} to import from and export to clipboard with support for Windows, Linux and macOS. The data will be read and written as tab-separated by default, which makes it possible to copy and paste from other software like Excel and SPSS without further transformation. See Details for an example.
 }
 \details{
-For \code{clipboard_export}, the reserved clipboard size for exporting will be set automatically to 125\% of the object size of \code{x}. This way, it is possible to export data with thousands of rows as the only limit will be your systems RAM.
+For \code{clipboard_export()}, the reserved clipboard size for exporting will be set to 125\% of the object size of \code{x}. This way, it is possible to export data with thousands of rows as the only limit will be your systems RAM.
+
+  Example for copying from Excel:
+  \if{html}{
+    \out{<div style="text-align: left">}\figure{Excel_copy.png}\out{</div>}
+  }
+  \if{latex}{
+    \out{\begin{left}}\figure{Excel_copy.png}\out{\end{left}}
+  }
+  \cr
+  And pasting in R: \cr \cr
+  \code{> data <- clipboard_import()} \cr
+  \code{> data} \cr
+  \if{html}{
+    \out{<div style="text-align: left">}\figure{Excel_paste.png}\out{</div>}
+  }
+  \if{latex}{
+    \out{\begin{left}}\figure{Excel_paste.png}\out{\end{left}}
+  }
 }
 \keyword{clipboard}
 \keyword{clipboard_export}

man/guess_bactid.Rd

@@ -1,5 +1,5 @@
 % Generated by roxygen2: do not edit by hand
-% Please edit documentation in R/first_isolates.R
+% Please edit documentation in R/atc.R
 \name{guess_bactid}
 \alias{guess_bactid}
 \title{Find bacteria ID based on genus/species}

tests/testthat/test-atc.R

@@ -14,3 +14,18 @@ test_that("abname works", {
   expect_equal(abname("amox", from = 'molis'), "Amoxicillin")
   expect_equal(abname("J01CA04", from = 'atc'), "Amoxicillin")
 })
+
+test_that("guess_bactid works", {
+  expect_identical(guess_bactid(c("E. coli", "H. influenzae")), c("ESCCOL", "HAEINF"))
+  expect_equal(guess_bactid("Escherichia coli"), "ESCCOL")
+  expect_equal(guess_bactid("Negative rods"), "GNR")
+  expect_equal(guess_bactid(c("stau",
+                              "STAU",
+                              "staaur",
+                              "S. aureus",
+                              "S aureus",
+                              "Staphylococcus aureus",
+                              "MRSA",
+                              "VISA")),
+               rep("STAAUR", 8))
+})

tests/testthat/test-first_isolates.R

@@ -7,11 +7,6 @@ test_that("keyantibiotics work", {
   expect_false(key_antibiotics_equal("SSS", "SIS", ignore_I = FALSE))
 })
 
-test_that("guess_bactid works", {
-  expect_equal(guess_bactid("E. coli"), "ESCCOL")
-  expect_equal(guess_bactid("Escherichia coli"), "ESCCOL")
-})
-
 test_that("first isolates work", {
   # septic_patients contains 1960 out of 2000 first isolates
   #septic_ptns <- septic_patients