v1.6.0

.Rbuildignore

@@ -22,7 +22,6 @@
 ^data-raw$
 ^\.lintr$
 ^tests/testthat/_snaps$
-^vignettes/AMR.Rmd$
 ^vignettes/benchmarks.Rmd$
 ^vignettes/EUCAST.Rmd$
 ^vignettes/PCA.Rmd$

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: AMR
-Version: 1.5.0.9024
-Date: 2021-02-22
+Version: 1.6.0
+Date: 2021-03-14
 Title: Antimicrobial Resistance Data Analysis
 Authors@R: c(
     person(role = c("aut", "cre"), 
@@ -38,8 +38,8 @@ Authors@R: c(
 Description: Functions to simplify the analysis and prediction of Antimicrobial 
     Resistance (AMR) and to work with microbial and antimicrobial properties by
     using evidence-based methods, like those defined by Leclercq et al. (2013) 
-    <doi:10.1111/j.1469-0691.2011.03703.x> and the Clinical and Laboratory 
-    Standards Institute (2014) <isbn: 1-56238-899-1>.
+    <doi:10.1111/j.1469-0691.2011.03703.x> and containing reference data such as 
+    LPSN <doi:10.1099/ijsem.0.004332>.
 Depends:
     R (>= 3.0.0)
 Suggests:

NAMESPACE

@@ -1,51 +1,95 @@
 # Generated by roxygen2: do not edit by hand
 
+S3method("!",mic)
+S3method("!=",mic)
+S3method("%%",mic)
+S3method("%/%",mic)
+S3method("&",mic)
+S3method("*",mic)
+S3method("+",mic)
+S3method("-",mic)
+S3method("/",mic)
+S3method("<",mic)
+S3method("<=",mic)
+S3method("==",mic)
+S3method(">",mic)
+S3method(">=",mic)
 S3method("[",ab)
 S3method("[",disk)
-S3method("[",isolate_identifier)
 S3method("[",mic)
 S3method("[",mo)
 S3method("[<-",ab)
 S3method("[<-",disk)
-S3method("[<-",isolate_identifier)
 S3method("[<-",mic)
 S3method("[<-",mo)
 S3method("[<-",rsi)
 S3method("[[",ab)
 S3method("[[",disk)
-S3method("[[",isolate_identifier)
 S3method("[[",mic)
 S3method("[[",mo)
 S3method("[[<-",ab)
 S3method("[[<-",disk)
-S3method("[[<-",isolate_identifier)
 S3method("[[<-",mic)
 S3method("[[<-",mo)
 S3method("[[<-",rsi)
-S3method(all.equal,isolate_identifier)
+S3method("^",mic)
+S3method("|",mic)
+S3method(abs,mic)
+S3method(acos,mic)
+S3method(acosh,mic)
+S3method(all,mic)
+S3method(any,mic)
 S3method(as.data.frame,ab)
 S3method(as.data.frame,mo)
 S3method(as.double,mic)
 S3method(as.integer,mic)
+S3method(as.matrix,mic)
 S3method(as.numeric,mic)
 S3method(as.rsi,data.frame)
 S3method(as.rsi,default)
 S3method(as.rsi,disk)
 S3method(as.rsi,mic)
+S3method(asin,mic)
+S3method(asinh,mic)
+S3method(atan,mic)
+S3method(atanh,mic)
+S3method(barplot,disk)
 S3method(barplot,mic)
 S3method(barplot,rsi)
 S3method(c,ab)
 S3method(c,disk)
-S3method(c,isolate_identifier)
 S3method(c,mic)
 S3method(c,mo)
 S3method(c,rsi)
+S3method(ceiling,mic)
+S3method(cos,mic)
+S3method(cosh,mic)
+S3method(cospi,mic)
+S3method(cummax,mic)
+S3method(cummin,mic)
+S3method(cumprod,mic)
+S3method(cumsum,mic)
+S3method(digamma,mic)
 S3method(droplevels,mic)
 S3method(droplevels,rsi)
+S3method(exp,mic)
+S3method(expm1,mic)
+S3method(floor,mic)
 S3method(format,bug_drug_combinations)
+S3method(gamma,mic)
+S3method(hist,mic)
 S3method(kurtosis,data.frame)
 S3method(kurtosis,default)
 S3method(kurtosis,matrix)
+S3method(lgamma,mic)
+S3method(log,mic)
+S3method(log10,mic)
+S3method(log1p,mic)
+S3method(log2,mic)
+S3method(max,mic)
+S3method(mean,mic)
+S3method(median,mic)
+S3method(min,mic)
 S3method(plot,disk)
 S3method(plot,mic)
 S3method(plot,resistance_predict)
@@ -55,24 +99,39 @@ S3method(print,bug_drug_combinations)
 S3method(print,catalogue_of_life_version)
 S3method(print,custom_mdro_guideline)
 S3method(print,disk)
-S3method(print,isolate_identifier)
 S3method(print,mic)
 S3method(print,mo)
 S3method(print,mo_renamed)
 S3method(print,mo_uncertainties)
 S3method(print,pca)
 S3method(print,rsi)
+S3method(prod,mic)
+S3method(quantile,mic)
+S3method(range,mic)
 S3method(rep,mo)
+S3method(round,mic)
+S3method(sign,mic)
+S3method(signif,mic)
+S3method(sin,mic)
+S3method(sinh,mic)
+S3method(sinpi,mic)
 S3method(skewness,data.frame)
 S3method(skewness,default)
 S3method(skewness,matrix)
+S3method(sort,mic)
+S3method(sqrt,mic)
+S3method(sum,mic)
 S3method(summary,mic)
 S3method(summary,mo)
 S3method(summary,pca)
 S3method(summary,rsi)
+S3method(tan,mic)
+S3method(tanh,mic)
+S3method(tanpi,mic)
+S3method(trigamma,mic)
+S3method(trunc,mic)
 S3method(unique,ab)
 S3method(unique,disk)
-S3method(unique,isolate_identifier)
 S3method(unique,mic)
 S3method(unique,mo)
 S3method(unique,rsi)
@@ -168,7 +227,6 @@ export(is.mo)
 export(is.rsi)
 export(is.rsi.eligible)
 export(is_new_episode)
-export(isolate_identifier)
 export(key_antibiotics)
 export(key_antibiotics_equal)
 export(kurtosis)
@@ -242,15 +300,19 @@ export(theme_rsi)
 importFrom(graphics,arrows)
 importFrom(graphics,axis)
 importFrom(graphics,barplot)
-importFrom(graphics,par)
+importFrom(graphics,hist)
+importFrom(graphics,legend)
+importFrom(graphics,mtext)
 importFrom(graphics,plot)
 importFrom(graphics,points)
 importFrom(graphics,text)
 importFrom(stats,complete.cases)
 importFrom(stats,glm)
 importFrom(stats,lm)
+importFrom(stats,median)
 importFrom(stats,pchisq)
 importFrom(stats,prcomp)
 importFrom(stats,predict)
 importFrom(stats,qchisq)
+importFrom(stats,quantile)
 importFrom(stats,var)

NEWS.md

@@ -1,5 +1,5 @@
-# AMR 1.5.0.9024
-## <small>Last updated: 22 February 2021</small>
+# AMR 1.6.0
+
 
 ### New
 * Support for EUCAST Clinical Breakpoints v11.0 (2021), effective in the `eucast_rules()` function and in `as.rsi()` to interpret MIC and disk diffusion values. This is now the default guideline in this package.
@@ -22,7 +22,7 @@
   #> Filtering on oxazolidinones: value in column `LNZ` (linezolid) is either "R", "S" or "I"
    ```
 * Support for custom MDRO guidelines, using the new `custom_mdro_guideline()` function, please see `mdro()` for additional info
-* Function `isolate_identifier()`, which will paste a microorganism code with all antimicrobial results of a data set into one string for each row. This is useful to compare isolates, e.g. between institutions or regions, when there is no genotyping available.
+* `ggplot()` generics for classes `<mic>` and `<disk>`
 * Function `mo_is_yeast()`, which determines whether a microorganism is a member of the taxonomic class Saccharomycetes or the taxonomic order Saccharomycetales:
   ```r
   mo_kingdom(c("Aspergillus", "Candida"))
@@ -42,24 +42,51 @@
   mo_type(c("Aspergillus", "Candida"), language = "es") # also supported: de, nl, fr, it, pt
   #> [1] "Hongos"    "Levaduras"
   ```
+* Added Pretomanid (PMD, J04AK08) to the `antibiotics` data set
+* MIC values (see `as.mic()`) can now be used in any mathematical processing, such as usage inside functions `min()`, `max()`, `range()`, and with binary operators (`+`, `-`, etc.). This allows for easy distribution analysis and fast filtering on MIC values:
+  ```r
+  x <- random_mic(10)
+  x
+  #> Class <mic>
+  #>  [1] 128   0.5   2     0.125 64    0.25  >=256 8     16    4
+  x[x > 4]
+  #> Class <mic>
+  #> [1] 128   64    >=256 8     16
+  range(x)
+  #> [1]   0.125 256.000
+  range(log2(x))
+  #> [1] -3  8
+  ```
 
 ### Changed
+* Updated the bacterial taxonomy to 3 March 2021 (using [LSPN](https://lpsn.dsmz.de))
+  * Added 3,372 new species and 1,523 existing species became synomyms
+  * The URL of a bacterial species (`mo_url()`) will now lead to https://lpsn.dsmz.de
+* Big update for plotting classes `rsi`, `<mic>`, and `<disk>`:
+  * Plotting of MIC and disk diffusion values now support interpretation colouring if you supply the microorganism and antimicrobial agent
+  * All colours were updated to colour-blind friendly versions for values R, S and I for all plot methods (also applies to tibble printing)
+  * Interpretation of MIC and disk diffusion values to R/SI will now be translated if the system language is German, Dutch or Spanish (see `translate`)
+  * Plotting is now possible with base R using `plot()` and with ggplot2 using `ggplot()` on any vector of MIC and disk diffusion values
+* Updated SNOMED codes to US Edition of SNOMED CT from 1 September 2020 and added the source to the help page of the `microorganisms` data set
 * `is.rsi()` and `is.rsi.eligible()` now return a vector of `TRUE`/`FALSE` when the input is a data set, by iterating over all columns
 * Using functions without setting a data set (e.g., `mo_is_gram_negative()`, `mo_is_gram_positive()`, `mo_is_intrinsic_resistant()`, `first_isolate()`, `mdro()`) now work with `dplyr`s `group_by()` again
 * `first_isolate()` can be used with `group_by()` (also when using a dot `.` as input for the data) and now returns the names of the groups
 * Updated the data set `microorganisms.codes` (which contains popular LIS and WHONET codes for microorganisms) for some species of *Mycobacterium* that previously incorrectly returned *M. africanum*
-* Added Pretomanid (PMD, J04AK08) to the `antibiotics` data set
 * WHONET code `"PNV"` will now correctly be interpreted as `PHN`, the antibiotic code for phenoxymethylpenicillin ('peni V')
 * Fix for verbose output of `mdro(..., verbose = TRUE)` for German guideline (3MGRN and 4MGRN) and Dutch guideline (BRMO, only *P. aeruginosa*)
 * `is.rsi.eligible()` now detects if the column name resembles an antibiotic name or code and now returns `TRUE` immediately if the input contains any of the values "R", "S" or "I". This drastically improves speed, also for a lot of other functions that rely on automatic determination of antibiotic columns.
 * Functions `get_episode()` and `is_new_episode()` now support less than a day as value for argument `episode_days` (e.g., to include one patient/test per hour)
 * Argument `ampc_cephalosporin_resistance` in `eucast_rules()` now also applies to value "I" (not only "S")
-* Updated colours of values R, S and I in tibble printing
 * Functions `print()` and `summary()` on a Principal Components Analysis object (`pca()`) now print additional group info if the original data was grouped using `dplyr::group_by()`
 * Improved speed and reliability of `guess_ab_col()`. As this also internally improves the reliability of `first_isolate()` and `mdro()`, this might have a slight impact on the results of those functions.
 * Fix for `mo_name()` when used in other languages than English
 * The `like()` function (and its fast alias `%like%`) now always use Perl compatibility, improving speed for many functions in this package (e.g., `as.mo()` is now up to 4 times faster)
 * *Staphylococcus cornubiensis* is now correctly categorised as coagulase-positive
+* `random_disk()` and `random_mic()` now have an expanded range in their randomisation
+* Support for GISA (glycopeptide-intermediate *S. aureus*), so e.g. `mo_genus("GISA")` will return `"Staphylococcus"` 
+* Added translations of German and Spanish for more than 200 antimicrobial drugs
+* Speed improvement for `as.ab()` when the input is an official name or ATC code
+* Added argument `include_untested_rsi` to the `first_isolate()` functions (defaults to `TRUE` to keep existing behaviour), to be able to exclude rows where all R/SI values (class `<rsi>`, see `as.rsi()`) are empty
 
 ### Other
 * Big documentation updates
@@ -380,7 +407,7 @@ This software is now out of beta and considered stable. Nonetheless, this packag
   * Speed improvements, especially for the *G. species* format (G for genus), like *E. coli* and *K pneumoniae*
   * Support for more common codes used in laboratory information systems
 * Input values for `as.disk()` limited to a maximum of 50 millimeters
-* Added a lifecycle state to every function, following [the lifecycle circle of the `tidyverse`](https://www.tidyverse.org/lifecycle)
+* Added a lifecycle state to every function, following the lifecycle circle of the `tidyverse`
 * For in `as.ab()`: support for drugs starting with "co-" like co-amoxiclav, co-trimoxazole, co-trimazine and co-trimazole (thanks to Peter Dutey)
 * Changes to the `antibiotics` data set (thanks to Peter Dutey):
   * Added more synonyms to colistin, imipenem and piperacillin/tazobactam
@@ -666,7 +693,7 @@ This software is now out of beta and considered stable. Nonetheless, this packag
   * Based on the Compound ID, almost 5,000 official brand names have been added from many different countries
   * All references to antibiotics in our package now use EARS-Net codes, like `AMX` for amoxicillin
   * Functions `atc_certe`, `ab_umcg` and `atc_trivial_nl` have been removed
-  * All `atc_*` functions are superceded by `ab_*` functions
+  * All `atc_*` functions are superseded by `ab_*` functions
   * All output will be translated by using an included translation file which [can be viewed here](https://github.com/msberends/AMR/blob/master/data-raw/translations.tsv)
 * Improvements to plotting AMR results with `ggplot_rsi()`:
   * New argument `colours` to set the bar colours

R/aa_helper_functions.R

@@ -507,12 +507,12 @@ format_class <- function(class, plural) {
   if ("isolate_identifier" %in% class) {
     class <- "created with isolate_identifier()"
   }
-  if (any(c("mo", "ab", "rsi", "disk", "mic") %in% class)) {
+  if (any(c("mo", "ab", "rsi") %in% class)) {
     class <- paste0("of class <", class[1L], ">")
   }
   class[class == class.bak] <- paste0("of class <", class[class == class.bak], ">")
   # output
-  vector_or(class, quotes = FALSE)
+  vector_or(class, quotes = FALSE, sort = FALSE)
 }
 
 # a check for every single argument in all functions
@@ -879,13 +879,16 @@ font_green_bg <- function(..., collapse = " ") {
   try_colour(..., before = "\033[42m", after = "\033[49m", collapse = collapse)
 }
 font_rsi_R_bg <- function(..., collapse = " ") {
-  try_colour(..., before = "\033[48;5;210m", after = "\033[49m", collapse = collapse)
+  #ED553B
+  try_colour(..., before = "\033[48;5;203m", after = "\033[49m", collapse = collapse)
 }
 font_rsi_S_bg <- function(..., collapse = " ") {
-  try_colour(..., before = "\033[48;5;113m", after = "\033[49m", collapse = collapse)
+  #3CAEA3
+  try_colour(..., before = "\033[48;5;79m", after = "\033[49m", collapse = collapse)
 }
 font_rsi_I_bg <- function(..., collapse = " ") {
-  try_colour(..., before = "\033[48;5;185m", after = "\033[49m", collapse = collapse)
+  #F6D55C
+  try_colour(..., before = "\033[48;5;222m", after = "\033[49m", collapse = collapse)
 }
 font_red_bg <- function(..., collapse = " ") {
   try_colour(..., before = "\033[41m", after = "\033[49m", collapse = collapse)
@@ -958,15 +961,8 @@ formatted_filesize <- function(...) {
 }
 
 create_pillar_column <- function(x, ...) {
-  new_pillar_shaft_simple <- import_fn("new_pillar_shaft_simple", "pillar", error_on_fail = FALSE)
-  if (!is.null(new_pillar_shaft_simple)) {
-    new_pillar_shaft_simple(x, ...)
-  } else {
-    # does not exist in package 'pillar' anymore
-    structure(list(x),
-              class = "pillar_shaft_simple",
-              ...)
-  }
+  new_pillar_shaft_simple <- import_fn("new_pillar_shaft_simple", "pillar")
+  new_pillar_shaft_simple(x, ...)
 }
 
 # copied from vctrs::s3_register by their permission:

R/ab.R

@@ -105,14 +105,28 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = TRUE, ...) {
   already_regex <- isTRUE(list(...)$already_regex)
   fast_mode <- isTRUE(list(...)$fast_mode)
   
-  if (all(toupper(x) %in% antibiotics$ab)) {
-    # valid AB code, but not yet right class
-    return(set_clean_class(toupper(x),
-                           new_class = c("ab", "character")))
-  }
-
   x_bak <- x
   x <- toupper(x)
+  x_nonNA <- x[!is.na(x)]
+  
+  if (all(x_nonNA %in% antibiotics$ab, na.rm = TRUE)) {
+    # all valid AB codes, but not yet right class
+    return(set_clean_class(x,
+                           new_class = c("ab", "character")))
+  }
+  if (all(x_nonNA %in% toupper(antibiotics$name), na.rm = TRUE)) {
+    # all valid AB names
+    out <- antibiotics$ab[match(x, toupper(antibiotics$name))]
+    out[is.na(x)] <- NA_character_
+    return(out)
+  }
+  if (all(x_nonNA %in% antibiotics$atc, na.rm = TRUE)) {
+    # all valid ATC codes
+    out <- antibiotics$ab[match(x, antibiotics$atc)]
+    out[is.na(x)] <- NA_character_
+    return(out)
+  }
+  
   # remove diacritics
   x <- iconv(x, from = "UTF-8", to = "ASCII//TRANSLIT")
   x <- gsub('"', "", x, fixed = TRUE)
@@ -310,10 +324,12 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = TRUE, ...) {
       x_translated <- paste(lapply(strsplit(x[i], "[^A-Z0-9]"),
                                    function(y) {
                                      for (i in seq_len(length(y))) {
-                                       y[i] <- ifelse(tolower(y[i]) %in% tolower(translations_file$replacement),
-                                                      translations_file[which(tolower(translations_file$replacement) == tolower(y[i]) &
-                                                                                !isFALSE(translations_file$fixed)), "pattern"],
-                                                      y[i])
+                                       for (lang in LANGUAGES_SUPPORTED[LANGUAGES_SUPPORTED != "en"]) {
+                                         y[i] <- ifelse(tolower(y[i]) %in% tolower(translations_file[, lang, drop = TRUE]),
+                                                        translations_file[which(tolower(translations_file[, lang, drop = TRUE]) == tolower(y[i]) &
+                                                                                  !isFALSE(translations_file$fixed)), "pattern"],
+                                                        y[i])
+                                       }
                                      }
                                      generalise_antibiotic_name(y)
                                    })[[1]],

R/ab_class_selectors.R

@@ -27,7 +27,7 @@
 #' 
 #' These functions help to select the columns of antibiotics that are of a specific antibiotic class, without the need to define the columns or antibiotic abbreviations. \strong{\Sexpr{ifelse(as.double(R.Version()$major) + (as.double(R.Version()$minor) / 10) < 3.2, paste0("NOTE: THESE FUNCTIONS DO NOT WORK ON YOUR CURRENT R VERSION. These functions require R version 3.2 or later - you have ", R.version.string, "."), "")}}
 #' @inheritSection lifecycle Stable Lifecycle
-#' @param only_rsi_columns a logical to indicate whether only columns of class [`<rsi>`]([rsi]) must be selected (defaults to `FALSE`)
+#' @param only_rsi_columns a logical to indicate whether only columns of class `<rsi>` must be selected (defaults to `FALSE`), see [as.rsi()]
 #' @inheritParams filter_ab_class 
 #' @details \strong{\Sexpr{ifelse(as.double(R.Version()$major) + (as.double(R.Version()$minor) / 10) < 3.2, paste0("NOTE: THESE FUNCTIONS DO NOT WORK ON YOUR CURRENT R VERSION. These functions require R version 3.2 or later - you have ", R.version.string, "."), "")}}
 #' 

R/ab_from_text.R

@@ -26,7 +26,7 @@
 #' Retrieve Antimicrobial Drug Names and Doses from Clinical Text
 #' 
 #' Use this function on e.g. clinical texts from health care records. It returns a [list] with all antimicrobial drugs, doses and forms of administration found in the texts.
-#' @inheritSection lifecycle Maturing Lifecycle
+#' @inheritSection lifecycle Stable Lifecycle
 #' @param text text to analyse
 #' @param type type of property to search for, either `"drug"`, `"dose"` or `"administration"`, see *Examples*
 #' @param collapse character to pass on to `paste(, collapse = ...)` to only return one character per element of `text`, see *Examples*

R/amr.R

@@ -29,7 +29,7 @@
 #' @details
 #' `AMR` is a free, open-source and independent \R package to simplify the analysis and prediction of Antimicrobial Resistance (AMR) and to work with microbial and antimicrobial data and properties, by using evidence-based methods. Our aim is to provide a standard for clean and reproducible antimicrobial resistance data analysis, that can therefore empower epidemiological analyses to continuously enable surveillance and treatment evaluation in any setting.
 #' 
-#' After installing this package, \R knows ~70,000 distinct microbial species and all ~550 antibiotic, antimycotic and antiviral drugs by name and code (including ATC, EARS-NET, LOINC and SNOMED CT), and knows all about valid R/SI and MIC values. It supports any data format, including WHONET/EARS-Net data.
+#' After installing this package, \R knows `r format_included_data_number(microorganisms)` distinct microbial species and all `r format_included_data_number(rbind(antibiotics[, "atc", drop = FALSE], antivirals[, "atc", drop = FALSE]))` antibiotic, antimycotic and antiviral drugs by name and code (including ATC, EARS-NET, LOINC and SNOMED CT), and knows all about valid R/SI and MIC values. It supports any data format, including WHONET/EARS-Net data.
 #' 
 #' This package is fully independent of any other \R package and works on Windows, macOS and Linux with all versions of \R since R-3.0.0 (April 2013). It was designed to work in any setting, including those with very limited resources. It was created for both routine data analysis and academic research at the Faculty of Medical Sciences of the University of Groningen, in collaboration with non-profit organisations Certe Medical Diagnostics and Advice and University Medical Center Groningen. This \R package is actively maintained and free software; you can freely use and distribute it for both personal and commercial (but not patent) purposes under the terms of the GNU General Public License version 2.0 (GPL-2), as published by the Free Software Foundation.
 #'
@@ -73,16 +73,3 @@
 #' @name AMR
 #' @rdname AMR
 NULL
-
-#' Plotting for Classes `rsi`, `mic` and `disk`
-#' 
-#' Functions to print classes of the `AMR` package.
-#' @inheritSection lifecycle Stable Lifecycle
-#' @inheritSection AMR Read more on Our Website!
-#' @param ... Arguments passed on to functions
-#' @inheritParams base::plot
-#' @inheritParams graphics::barplot
-#' @name plot
-#' @rdname plot
-#' @keywords internal
-NULL

R/catalogue_of_life.R

@@ -44,9 +44,9 @@ format_included_data_number <- function(data) {
 #' This package contains the complete taxonomic tree of almost all microorganisms from the authoritative and comprehensive Catalogue of Life.
 #' @section Catalogue of Life:
 #' \if{html}{\figure{logo_col.png}{options: height=40px style=margin-bottom:5px} \cr}
-#' This package contains the complete taxonomic tree of almost all microorganisms (~70,000 species) from the authoritative and comprehensive Catalogue of Life (CoL, <http://www.catalogueoflife.org>). The CoL is the most comprehensive and authoritative global index of species currently available. Nonetheless, we supplemented the CoL data with data from the List of Prokaryotic names with Standing in Nomenclature (LPSN, [lpsn.dsmz.de](https://lpsn.dsmz.de)). This supplementation is needed until the [CoL+ project](https://github.com/CatalogueOfLife/general) is finished, which we await.
+#' This package contains the complete taxonomic tree of almost all microorganisms (`r format_included_data_number(microorganisms)` species) from the authoritative and comprehensive Catalogue of Life (CoL, <http://www.catalogueoflife.org>). The CoL is the most comprehensive and authoritative global index of species currently available. Nonetheless, we supplemented the CoL data with data from the List of Prokaryotic names with Standing in Nomenclature (LPSN, [lpsn.dsmz.de](https://lpsn.dsmz.de)). This supplementation is needed until the [CoL+ project](https://github.com/CatalogueOfLife/general) is finished, which we await.
 #'
-#' [Click here][catalogue_of_life] for more information about the included taxa. Check which versions of the CoL and LSPN were included in this package with [catalogue_of_life_version()].
+#' [Click here][catalogue_of_life] for more information about the included taxa. Check which versions of the CoL and LPSN were included in this package with [catalogue_of_life_version()].
 #' @section Included Taxa:
 #' Included are:
 #' - All `r format_included_data_number(microorganisms[which(microorganisms$kingdom %in% c("Archeae", "Bacteria", "Chromista", "Protozoa")), ])` (sub)species from the kingdoms of Archaea, Bacteria, Chromista and Protozoa
@@ -99,7 +99,7 @@ NULL
 #'
 #' This function returns information about the included data from the Catalogue of Life.
 #' @seealso [microorganisms]
-#' @details For DSMZ, see [microorganisms].
+#' @details For LPSN, see [microorganisms].
 #' @return a [list], which prints in pretty format
 #' @inheritSection catalogue_of_life Catalogue of Life
 #' @inheritSection AMR Read more on Our Website!
@@ -108,16 +108,16 @@ catalogue_of_life_version <- function() {
   
   check_dataset_integrity()
   
-  # see the `catalogue_of_life` list in R/data.R
-  lst <- list(catalogue_of_life =
-                list(version = gsub("{year}", catalogue_of_life$year, catalogue_of_life$version, fixed = TRUE),
-                     url = gsub("{year}", catalogue_of_life$year, catalogue_of_life$url_CoL, fixed = TRUE),
+  # see the `CATALOGUE_OF_LIFE` list in R/globals.R
+  lst <- list(CoL =
+                list(version = gsub("{year}", CATALOGUE_OF_LIFE$year, CATALOGUE_OF_LIFE$version, fixed = TRUE),
+                     url = gsub("{year}", CATALOGUE_OF_LIFE$year, CATALOGUE_OF_LIFE$url_CoL, fixed = TRUE),
                      n = nrow(pm_filter(microorganisms, source == "CoL"))),
-              deutsche_sammlung_von_mikroorganismen_und_zellkulturen =
-                list(version = "Prokaryotic Nomenclature Up-to-Date from DSMZ",
-                     url = catalogue_of_life$url_DSMZ,
-                     yearmonth = catalogue_of_life$yearmonth_DSMZ,
-                     n = nrow(pm_filter(microorganisms, source == "DSMZ"))),
+              LPSN =
+                list(version = "List of Prokaryotic names with Standing in Nomenclature",
+                     url = CATALOGUE_OF_LIFE$url_LPSN,
+                     yearmonth = CATALOGUE_OF_LIFE$yearmonth_LPSN,
+                     n = nrow(pm_filter(microorganisms, source == "LPSN"))),
               total_included =
                 list(
                   n_total_species = nrow(microorganisms),
@@ -131,16 +131,15 @@ catalogue_of_life_version <- function() {
 #' @export
 #' @noRd
 print.catalogue_of_life_version <- function(x, ...) {
-  lst <- x
-  cat(paste0(font_bold("Included in this AMR package are:\n\n"),
-             font_underline(lst$catalogue_of_life$version), "\n",
-             "  Available at: ", lst$catalogue_of_life$url, "\n",
-             "  Number of included species: ", format(lst$catalogue_of_life$n, big.mark = ","), "\n",
-             font_underline(paste0(lst$deutsche_sammlung_von_mikroorganismen_und_zellkulturen$version, " (",
-                                   lst$deutsche_sammlung_von_mikroorganismen_und_zellkulturen$yearmonth, ")")), "\n",
-             "  Available at: ", lst$deutsche_sammlung_von_mikroorganismen_und_zellkulturen$url, "\n",
-             "  Number of included species: ", format(lst$deutsche_sammlung_von_mikroorganismen_und_zellkulturen$n, big.mark = ","), "\n\n",
-             "=> Total number of species included:  ", format(lst$total_included$n_total_species, big.mark = ","), "\n",
-             "=> Total number of synonyms included: ", format(lst$total_included$n_total_synonyms, big.mark = ","), "\n\n",
+  cat(paste0(font_bold("Included in this AMR package (v", utils::packageDescription("AMR")$Version, ") are:\n\n", collapse = ""),
+             font_underline(x$CoL$version), "\n",
+             "  Available at: ", font_blue(x$CoL$url), "\n",
+             "  Number of included microbial species: ", format(x$CoL$n, big.mark = ","), "\n",
+             font_underline(paste0(x$LPSN$version, " (",
+                                   x$LPSN$yearmonth, ")")), "\n",
+             "  Available at: ", font_blue(x$LPSN$url), "\n",
+             "  Number of included bacterial species: ", format(x$LPSN$n, big.mark = ","), "\n\n",
+             "=> Total number of species included:  ", format(x$total_included$n_total_species, big.mark = ","), "\n",
+             "=> Total number of synonyms included: ", format(x$total_included$n_total_synonyms, big.mark = ","), "\n\n",
              "See for more info ?microorganisms and ?catalogue_of_life.\n"))
 }

R/data.R

@@ -83,7 +83,7 @@
 
 #' Data Set with `r format(nrow(microorganisms), big.mark = ",")` Microorganisms
 #'
-#' A data set containing the microbial taxonomy of six kingdoms from the Catalogue of Life. MO codes can be looked up using [as.mo()].
+#' A data set containing the microbial taxonomy, last updated in `r CATALOGUE_OF_LIFE$yearmonth_LPSN`, of six kingdoms from the Catalogue of Life (CoL) and the List of Prokaryotic names with Standing in Nomenclature (LPSN). MO codes can be looked up using [as.mo()].
 #' @inheritSection catalogue_of_life Catalogue of Life
 #' @format A [data.frame] with `r format(nrow(microorganisms), big.mark = ",")` observations and `r ncol(microorganisms)` variables:
 #' - `mo`\cr ID of microorganism as used by this package
@@ -92,15 +92,15 @@
 #' - `rank`\cr Text of the taxonomic rank of the microorganism, like `"species"` or `"genus"`
 #' - `ref`\cr Author(s) and year of concerning scientific publication
 #' - `species_id`\cr ID of the species as used by the Catalogue of Life
-#' - `source`\cr Either "CoL", "DSMZ" (see *Source*) or "manually added"
+#' - `source`\cr Either `r vector_or(microorganisms$source)` (see *Source*)
 #' - `prevalence`\cr Prevalence of the microorganism, see [as.mo()]
-#' - `snomed`\cr SNOMED code of the microorganism. Use [mo_snomed()] to retrieve it quickly, see [mo_property()].
+#' - `snomed`\cr Systematized Nomenclature of Medicine (SNOMED) code of the microorganism, according to the `r SNOMED_VERSION$current_source` (see *Source*). Use [mo_snomed()] to retrieve it quickly, see [mo_property()].
 #' @details 
 #' Please note that entries are only based on the Catalogue of Life and the LPSN (see below). Since these sources incorporate entries based on (recent) publications in the International Journal of Systematic and Evolutionary Microbiology (IJSEM), it can happen that the year of publication is sometimes later than one might expect.
 #' 
-#' For example, *Staphylococcus pettenkoferi* was newly named in Diagnostic Microbiology and Infectious Disease in 2002 (PMID 12106949), but it was not before 2007 that a publication in IJSEM followed (PMID 17625191). Consequently, the AMR package returns 2007 for `mo_year("S. pettenkoferi")`.
+#' For example, *Staphylococcus pettenkoferi* was described for the first time in Diagnostic Microbiology and Infectious Disease in 2002 (\doi{10.1016/s0732-8893(02)00399-1}), but it was not before 2007 that a publication in IJSEM followed (\doi{10.1099/ijs.0.64381-0}). Consequently, the AMR package returns 2007 for `mo_year("S. pettenkoferi")`.
 #' 
-#' ## Manually additions
+#' ## Manual additions
 #' For convenience, some entries were added manually:
 #' 
 #' - 11 entries of *Streptococcus* (beta-haemolytic: groups A, B, C, D, F, G, H, K and unspecified; other: viridans, milleri)
@@ -110,7 +110,6 @@
 #' - 1 entry of *Blastocystis* (*Blastocystis hominis*), although it officially does not exist (Noel *et al.* 2005, PMID 15634993)
 #' - 5 other 'undefined' entries (unknown, unknown Gram negatives, unknown Gram positives, unknown yeast and unknown fungus)
 #' - 6 families under the Enterobacterales order, according to Adeolu *et al.* (2016, PMID 27620848), that are not (yet) in the Catalogue of Life
-#' - `r format(nrow(subset(microorganisms, source == "DSMZ")), big.mark = ",")` species from the DSMZ (Deutsche Sammlung von Mikroorganismen und Zellkulturen) since the DSMZ contain the latest taxonomic information based on recent publications
 #' 
 #' ## Direct download
 #' This data set is available as 'flat file' for use even without \R - you can find the file here:
@@ -120,29 +119,30 @@
 #' The file in \R format (with preserved data structure) can be found here:
 #' 
 #' * <https://github.com/msberends/AMR/raw/master/data/microorganisms.rda>
-#' @section About the Records from DSMZ (see *Source*):
-#' Names of prokaryotes are defined as being validly published by the International Code of Nomenclature of Bacteria. Validly published are all names which are included in the Approved Lists of Bacterial Names and the names subsequently published in the International Journal of Systematic Bacteriology (IJSB) and, from January 2000, in the International Journal of Systematic and Evolutionary Microbiology (IJSEM) as original articles or in the validation lists.
-#' *(from <https://www.dsmz.de/services/online-tools/prokaryotic-nomenclature-up-to-date>)*
+#' @section About the Records from LPSN (see *Source*):
+#' The List of Prokaryotic names with Standing in Nomenclature (LPSN) provides comprehensive information on the nomenclature of prokaryotes. LPSN is a free to use service founded by Jean P. Euzeby in 1997 and later on maintained by Aidan C. Parte.
 #' 
-#' In February 2020, the DSMZ records were merged with the List of Prokaryotic names with Standing in Nomenclature (LPSN).
-#' @source Catalogue of Life: Annual Checklist (public online taxonomic database), <http://www.catalogueoflife.org> (check included annual version with [catalogue_of_life_version()]).
+#' As of February 2020, the regularly augmented LPSN database at DSMZ is the basis of the new LPSN service. The new database was implemented for the Type-Strain Genome Server and augmented in 2018 to store all kinds of nomenclatural information. Data from the previous version of LPSN and from the Prokaryotic Nomenclature Up-to-date (PNU) service were imported into the new system. PNU had been established in 1993 as a service of the Leibniz Institute DSMZ, and was curated by Norbert Weiss, Manfred Kracht and Dorothea Gleim.
+#' @source 
+#' `r gsub("{year}", CATALOGUE_OF_LIFE$year, CATALOGUE_OF_LIFE$version, fixed = TRUE)` as currently implemented in this `AMR` package:
 #' 
-#' Parte, A.C. (2018). LPSN — List of Prokaryotic names with Standing in Nomenclature (bacterio.net), 20 years on. International Journal of Systematic and Evolutionary Microbiology, 68, 1825-1829; \doi{10.1099/ijsem.0.002786}
-#'
-#' Leibniz Institute DSMZ-German Collection of Microorganisms and Cell Cultures, Germany, Prokaryotic Nomenclature Up-to-Date, <https://www.dsmz.de/services/online-tools/prokaryotic-nomenclature-up-to-date> and <https://lpsn.dsmz.de> (check included version with [catalogue_of_life_version()]).
+#' * Annual Checklist (public online taxonomic database), <http://www.catalogueoflife.org>
+#' 
+#' List of Prokaryotic names with Standing in Nomenclature (`r CATALOGUE_OF_LIFE$yearmonth_LPSN`) as currently implemented in this `AMR` package:
+#' 
+#' * Parte, A.C., Sarda Carbasse, J., Meier-Kolthoff, J.P., Reimer, L.C. and Goker, M. (2020). List of Prokaryotic names with Standing in Nomenclature (LPSN) moves to the DSMZ. International Journal of Systematic and Evolutionary Microbiology, 70, 5607-5612; \doi{10.1099/ijsem.0.004332}
+#' * Parte, A.C. (2018). LPSN — List of Prokaryotic names with Standing in Nomenclature (bacterio.net), 20 years on. International Journal of Systematic and Evolutionary Microbiology, 68, 1825-1829; \doi{10.1099/ijsem.0.002786}
+#' * Parte, A.C. (2014). LPSN — List of Prokaryotic names with Standing in Nomenclature. Nucleic Acids Research, 42, Issue D1, D613–D616; \doi{10.1093/nar/gkt1111}
+#' * Euzeby, J.P. (1997). List of Bacterial Names with Standing in Nomenclature: a Folder Available on the Internet. International Journal of Systematic Bacteriology, 47, 590-592; \doi{10.1099/00207713-47-2-590}
+#' 
+#' `r SNOMED_VERSION$current_source` as currently implemented in this `AMR` package:
+#' 
+#' * Retrieved from the `r SNOMED_VERSION$title`, OID `r SNOMED_VERSION$current_oid`, version `r SNOMED_VERSION$current_version`; url: <`r SNOMED_VERSION$url`>
 #' @inheritSection AMR Reference Data Publicly Available
 #' @inheritSection AMR Read more on Our Website!
 #' @seealso [as.mo()], [mo_property()], [microorganisms.codes], [intrinsic_resistant]
 "microorganisms"
 
-catalogue_of_life <- list(
-  year = 2019,
-  version = "Catalogue of Life: {year} Annual Checklist",
-  url_CoL = "http://www.catalogueoflife.org/col/",
-  url_DSMZ = "https://lpsn.dsmz.de",
-  yearmonth_DSMZ = "May 2020"
-)
-
 #' Data Set with Previously Accepted Taxonomic Names
 #'
 #' A data set containing old (previously valid or accepted) taxonomic names according to the Catalogue of Life. This data set is used internally by [as.mo()].
@@ -242,7 +242,7 @@ catalogue_of_life <- list(
 #' Data set to interpret MIC and disk diffusion to R/SI values. Included guidelines are CLSI (`r min(as.integer(gsub("[^0-9]", "", subset(rsi_translation, guideline %like% "CLSI")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(rsi_translation, guideline %like% "CLSI")$guideline)))`) and EUCAST (`r min(as.integer(gsub("[^0-9]", "", subset(rsi_translation, guideline %like% "EUCAST")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(rsi_translation, guideline %like% "EUCAST")$guideline)))`). Use [as.rsi()] to transform MICs or disks measurements to R/SI values.
 #' @format A [data.frame] with `r format(nrow(rsi_translation), big.mark = ",")` observations and `r ncol(rsi_translation)` variables:
 #' - `guideline`\cr Name of the guideline
-#' - `method`\cr Either "MIC" or "DISK"
+#' - `method`\cr Either `r vector_or(rsi_translation$method)`
 #' - `site`\cr Body site, e.g. "Oral" or "Respiratory"
 #' - `mo`\cr Microbial ID, see [as.mo()]
 #' - `ab`\cr Antibiotic ID, see [as.ab()]

R/disk.R

@@ -145,30 +145,6 @@ print.disk <- function(x, ...) {
   print(as.integer(x), quote = FALSE)
 }
 
-#' @method plot disk
-#' @export
-#' @importFrom graphics barplot axis
-#' @rdname plot
-plot.disk <- function(x,
-                      main = paste("Disk zones values of", deparse(substitute(x))),
-                      ylab = "Frequency",
-                      xlab = "Disk diffusion (mm)",
-                      axes = FALSE,
-                      ...) {
-  meet_criteria(main, allow_class = "character", has_length = 1)
-  meet_criteria(ylab, allow_class = "character", has_length = 1)
-  meet_criteria(xlab, allow_class = "character", has_length = 1)
-  meet_criteria(axes, allow_class = "logical", has_length = 1)
-  
-  barplot(table(x),
-          ylab = ylab,
-          xlab = xlab,
-          axes = axes,
-          main = main,
-          ...)
-  axis(2, seq(0, max(table(x))))
-}
-
 #' @method [ disk
 #' @export
 #' @noRd

R/eucast_rules.R

@@ -23,25 +23,6 @@
 # how to conduct AMR data analysis: https://msberends.github.io/AMR/   #
 # ==================================================================== #
 
-# add new version numbers here, and add the rules themselves to "data-raw/eucast_rules.tsv" and rsi_translation
-# (sourcing "data-raw/_internals.R" will process the TSV file)
-EUCAST_VERSION_BREAKPOINTS <- list("11.0" = list(version_txt = "v11.0",
-                                                 year = 2021, 
-                                                 title = "'EUCAST Clinical Breakpoint Tables'",
-                                                 url = "https://www.eucast.org/clinical_breakpoints/"),
-                                   "10.0" = list(version_txt = "v10.0",
-                                                 year = 2020, 
-                                                 title = "'EUCAST Clinical Breakpoint Tables'",
-                                                 url = "https://www.eucast.org/ast_of_bacteria/previous_versions_of_documents/"))
-EUCAST_VERSION_EXPERT_RULES <- list("3.1" = list(version_txt = "v3.1",
-                                                 year = 2016, 
-                                                 title = "'EUCAST Expert Rules, Intrinsic Resistance and Exceptional Phenotypes'",
-                                                 url = "https://www.eucast.org/expert_rules_and_intrinsic_resistance/"),
-                                    "3.2" = list(version_txt = "v3.2",
-                                                 year = 2020, 
-                                                 title = "'EUCAST Expert Rules' and 'EUCAST Intrinsic Resistance and Unusual Phenotypes'",
-                                                 url = "https://www.eucast.org/expert_rules_and_intrinsic_resistance/"))
-
 format_eucast_version_nr <- function(version, markdown = TRUE) {
   # for documentation - adds title, version number, year and url in markdown language
   lst <- c(EUCAST_VERSION_BREAKPOINTS, EUCAST_VERSION_EXPERT_RULES)
@@ -74,11 +55,11 @@ format_eucast_version_nr <- function(version, markdown = TRUE) {
 #' @param verbose a [logical] to turn Verbose mode on and off (default is off). In Verbose mode, the function does not apply rules to the data, but instead returns a data set in logbook form with extensive info about which rows and columns would be effected and in which way. Using Verbose mode takes a lot more time.
 #' @param version_breakpoints the version number to use for the EUCAST Clinical Breakpoints guideline. Can be either `r vector_or(names(EUCAST_VERSION_BREAKPOINTS), reverse = TRUE)`.
 #' @param version_expertrules the version number to use for the EUCAST Expert Rules and Intrinsic Resistance guideline. Can be either `r vector_or(names(EUCAST_VERSION_EXPERT_RULES), reverse = TRUE)`.
-#' @param ampc_cephalosporin_resistance a character value that should be applied for AmpC de-repressed cephalosporin-resistant mutants, defaults to `NA`. Currently only works when `version_expertrules` is `3.2`; '*EUCAST Expert Rules v3.2 on Enterobacterales*' states that results of cefotaxime, ceftriaxone and ceftazidime should be reported with a note, or results should be suppressed (emptied) for these agents. A value of `NA` for this argument will remove results for these agents, while e.g. a value of `"R"` will make the results for these agents resistant. Use `NULL` to not alter the results for AmpC de-repressed cephalosporin-resistant mutants. \cr For *EUCAST Expert Rules* v3.2, this rule applies to: `r vector_and(gsub("[^a-zA-Z ]+", "", unlist(strsplit(eucast_rules_file[which(eucast_rules_file$reference.version == 3.2 & eucast_rules_file$reference.rule %like% "ampc"), "this_value"][1], "|", fixed = TRUE))), quotes = "*")`.
+#' @param ampc_cephalosporin_resistance a character value that should be applied to cefotaxime, ceftriaxone and ceftazidime for AmpC de-repressed cephalosporin-resistant mutants, defaults to `NA`. Currently only works when `version_expertrules` is `3.2`; '*EUCAST Expert Rules v3.2 on Enterobacterales*' states that results of cefotaxime, ceftriaxone and ceftazidime should be reported with a note, or results should be suppressed (emptied) for these three agents. A value of `NA` (the default) for this argument will remove results for these three agents, while e.g. a value of `"R"` will make the results for these agents resistant. Use `NULL` or `FALSE` to not alter results for these three agents of AmpC de-repressed cephalosporin-resistant mutants. Using `TRUE` is equal to using `"R"`. \cr For *EUCAST Expert Rules* v3.2, this rule applies to: `r vector_and(gsub("[^a-zA-Z ]+", "", unlist(strsplit(eucast_rules_file[which(eucast_rules_file$reference.version == 3.2 & eucast_rules_file$reference.rule %like% "ampc"), "this_value"][1], "|", fixed = TRUE))), quotes = "*")`.
 #' @param ... column name of an antibiotic, see section *Antibiotics* below
 #' @param ab any (vector of) text that can be coerced to a valid antibiotic code with [as.ab()]
 #' @param administration route of administration, either `r vector_or(dosage$administration)`
-#' @param only_rsi_columns a logical to indicate whether only antibiotic columns must be detected that were [transformed to class `<rsi>`]([rsi]) on beforehand (defaults to `FALSE`)
+#' @param only_rsi_columns a logical to indicate whether only antibiotic columns must be detected that were transformed to class `<rsi>` (see [as.rsi()]) on beforehand (defaults to `FALSE`)
 #' @inheritParams first_isolate
 #' @details
 #' **Note:** This function does not translate MIC values to RSI values. Use [as.rsi()] for that. \cr
@@ -101,7 +82,7 @@ format_eucast_version_nr <- function(version, markdown = TRUE) {
 #'
 #' The following antibiotics are used for the functions [eucast_rules()] and [mdro()]. These are shown below in the format 'name (`antimicrobial ID`, [ATC code](https://www.whocc.no/atc/structure_and_principles/))', sorted alphabetically:
 #'
-#' `r create_ab_documentation(c("AMC", "AMK", "AMP", "AMX", "ATM", "AVO", "AZL", "AZM", "BAM", "BPR", "CAC", "CAT", "CAZ", "CCP", "CCV", "CCX", "CDC", "CDR", "CDZ", "CEC", "CED", "CEI", "CEM", "CEP", "CFM", "CFM1", "CFP", "CFR", "CFS", "CFZ", "CHE", "CHL", "CID", "CIP", "CLI", "CLR", "CMX", "CMZ", "CND", "COL", "CPD", "CPI", "CPL", "CPM", "CPO", "CPR", "CPT", "CPX", "CRB", "CRD", "CRN", "CRO", "CSL", "CTB", "CTC", "CTF", "CTL", "CTS", "CTT", "CTX", "CTZ", "CXM", "CYC", "CZA", "CZD", "CZO", "CZP", "CZX", "DAL", "DAP", "DIR", "DIT", "DIX", "DIZ", "DKB", "DOR", "DOX", "ENX", "EPC", "ERY", "ETP", "FEP", "FLC", "FLE", "FLR1", "FOS", "FOV", "FOX", "FOX1", "FUS", "GAT", "GEM", "GEN", "GRX", "HAP", "HET", "IPM", "ISE", "JOS", "KAN", "LEX", "LIN", "LNZ", "LOM", "LOR", "LTM", "LVX", "MAN", "MCM", "MEC", "MEM", "MEV", "MEZ", "MFX", "MID", "MNO", "MTM", "NAL", "NEO", "NET", "NIT", "NOR", "NOV", "NVA", "OFX", "OLE", "ORI", "OXA", "PAZ", "PEF", "PEN", "PHN", "PIP", "PLB", "PME", "PRI", "PRL", "PRU", "PVM", "QDA", "RAM", "RFL", "RID", "RIF", "ROK", "RST", "RXT", "SAM", "SBC", "SDI", "SDM", "SIS", "SLF", "SLF1", "SLF10", "SLF11", "SLF12", "SLF13", "SLF2", "SLF3", "SLF4", "SLF5", "SLF6", "SLF7", "SLF8", "SLF9", "SLT1", "SLT2", "SLT3", "SLT4", "SLT5", "SMX", "SPI", "SPX", "STR", "STR1", "SUD", "SUT", "SXT", "SZO", "TAL", "TCC", "TCM", "TCY", "TEC", "TEM", "TGC", "THA", "TIC", "TIO", "TLT", "TLV", "TMP", "TMX", "TOB", "TRL", "TVA", "TZD", "TZP", "VAN"))`
+#' `r create_ab_documentation(c("AMC", "AMK", "AMP", "AMX", "APL", "APX", "ATM", "AVB", "AVO", "AZD", "AZL", "AZM", "BAM", "BPR", "CAC", "CAT", "CAZ", "CCP", "CCV", "CCX", "CDC", "CDR", "CDZ", "CEC", "CED", "CEI", "CEM", "CEP", "CFM", "CFM1", "CFP", "CFR", "CFS", "CFZ", "CHE", "CHL", "CIC", "CID", "CIP", "CLI", "CLM", "CLO", "CLR", "CMX", "CMZ", "CND", "COL", "CPD", "CPI", "CPL", "CPM", "CPO", "CPR", "CPT", "CPX", "CRB", "CRD", "CRN", "CRO", "CSL", "CTB", "CTC", "CTF", "CTL", "CTS", "CTT", "CTX", "CTZ", "CXM", "CYC", "CZA", "CZD", "CZO", "CZP", "CZX", "DAL", "DAP", "DIC", "DIR", "DIT", "DIX", "DIZ", "DKB", "DOR", "DOX", "ENX", "EPC", "ERY", "ETP", "FEP", "FLC", "FLE", "FLR1", "FOS", "FOV", "FOX", "FOX1", "FUS", "GAT", "GEM", "GEN", "GRX", "HAP", "HET", "IPM", "ISE", "JOS", "KAN", "LEN", "LEX", "LIN", "LNZ", "LOM", "LOR", "LTM", "LVX", "MAN", "MCM", "MEC", "MEM", "MET", "MEV", "MEZ", "MFX", "MID", "MNO", "MTM", "NAC", "NAF", "NAL", "NEO", "NET", "NIT", "NOR", "NOV", "NVA", "OFX", "OLE", "ORI", "OXA", "PAZ", "PEF", "PEN", "PHE", "PHN", "PIP", "PLB", "PME", "PNM", "PRC", "PRI", "PRL", "PRP", "PRU", "PVM", "QDA", "RAM", "RFL", "RID", "RIF", "ROK", "RST", "RXT", "SAM", "SBC", "SDI", "SDM", "SIS", "SLF", "SLF1", "SLF10", "SLF11", "SLF12", "SLF13", "SLF2", "SLF3", "SLF4", "SLF5", "SLF6", "SLF7", "SLF8", "SLF9", "SLT1", "SLT2", "SLT3", "SLT4", "SLT5", "SLT6", "SMX", "SPI", "SPX", "SRX", "STR", "STR1", "SUD", "SUL", "SUT", "SXT", "SZO", "TAL", "TAZ", "TCC", "TCM", "TCY", "TEC", "TEM", "TGC", "THA", "TIC", "TIO", "TLT", "TLV", "TMP", "TMX", "TOB", "TRL", "TVA", "TZD", "TZP", "VAN"))`
 #' @aliases EUCAST
 #' @rdname eucast_rules
 #' @export
@@ -176,7 +157,7 @@ eucast_rules <- function(x,
   meet_criteria(verbose, allow_class = "logical", has_length = 1)
   meet_criteria(version_breakpoints, allow_class = c("numeric", "integer"), has_length = 1, is_in = as.double(names(EUCAST_VERSION_BREAKPOINTS)))
   meet_criteria(version_expertrules, allow_class = c("numeric", "integer"), has_length = 1, is_in = as.double(names(EUCAST_VERSION_EXPERT_RULES)))
-  meet_criteria(ampc_cephalosporin_resistance, has_length = 1, allow_NA = TRUE, allow_NULL = TRUE, is_in = c("R", "S", "I"))
+  meet_criteria(ampc_cephalosporin_resistance, allow_class = c("logical", "character", "rsi"), has_length = 1, allow_NA = TRUE, allow_NULL = TRUE)
   meet_criteria(only_rsi_columns, allow_class = "logical", has_length = 1)
   
   x_deparsed <- deparse(substitute(x))
@@ -287,8 +268,12 @@ eucast_rules <- function(x,
   AMK <- cols_ab["AMK"]
   AMP <- cols_ab["AMP"]
   AMX <- cols_ab["AMX"]
+  APL <- cols_ab["APL"]
+  APX <- cols_ab["APX"]
   ATM <- cols_ab["ATM"]
+  AVB <- cols_ab["AVB"]
   AVO <- cols_ab["AVO"]
+  AZD <- cols_ab["AZD"]
   AZL <- cols_ab["AZL"]
   AZM <- cols_ab["AZM"]
   BAM <- cols_ab["BAM"]
@@ -315,9 +300,12 @@ eucast_rules <- function(x,
   CFZ <- cols_ab["CFZ"]
   CHE <- cols_ab["CHE"]
   CHL <- cols_ab["CHL"]
+  CIC <- cols_ab["CIC"]
   CID <- cols_ab["CID"]
   CIP <- cols_ab["CIP"]
   CLI <- cols_ab["CLI"]
+  CLM <- cols_ab["CLM"]
+  CLO <- cols_ab["CLO"]
   CLR <- cols_ab["CLR"]
   CMX <- cols_ab["CMX"]
   CMZ <- cols_ab["CMZ"]
@@ -353,6 +341,7 @@ eucast_rules <- function(x,
   CZX <- cols_ab["CZX"]
   DAL <- cols_ab["DAL"]
   DAP <- cols_ab["DAP"]
+  DIC <- cols_ab["DIC"]
   DIR <- cols_ab["DIR"]
   DIT <- cols_ab["DIT"]
   DIX <- cols_ab["DIX"]
@@ -383,6 +372,7 @@ eucast_rules <- function(x,
   ISE <- cols_ab["ISE"]
   JOS <- cols_ab["JOS"]
   KAN <- cols_ab["KAN"]
+  LEN <- cols_ab["LEN"]
   LEX <- cols_ab["LEX"]
   LIN <- cols_ab["LIN"]
   LNZ <- cols_ab["LNZ"]
@@ -394,12 +384,15 @@ eucast_rules <- function(x,
   MCM <- cols_ab["MCM"]
   MEC <- cols_ab["MEC"]
   MEM <- cols_ab["MEM"]
+  MET <- cols_ab["MET"]
   MEV <- cols_ab["MEV"]
   MEZ <- cols_ab["MEZ"]
   MFX <- cols_ab["MFX"]
   MID <- cols_ab["MID"]
   MNO <- cols_ab["MNO"]
   MTM <- cols_ab["MTM"]
+  NAC <- cols_ab["NAC"]
+  NAF <- cols_ab["NAF"]
   NAL <- cols_ab["NAL"]
   NEO <- cols_ab["NEO"]
   NET <- cols_ab["NET"]
@@ -414,12 +407,16 @@ eucast_rules <- function(x,
   PAZ <- cols_ab["PAZ"]
   PEF <- cols_ab["PEF"]
   PEN <- cols_ab["PEN"]
+  PHE <- cols_ab["PHE"]
   PHN <- cols_ab["PHN"]
   PIP <- cols_ab["PIP"]
   PLB <- cols_ab["PLB"]
   PME <- cols_ab["PME"]
+  PNM <- cols_ab["PNM"]
+  PRC <- cols_ab["PRC"]
   PRI <- cols_ab["PRI"]
   PRL <- cols_ab["PRL"]
+  PRP <- cols_ab["PRP"]
   PRU <- cols_ab["PRU"]
   PVM <- cols_ab["PVM"]
   QDA <- cols_ab["QDA"]
@@ -454,16 +451,20 @@ eucast_rules <- function(x,
   SLT3 <- cols_ab["SLT3"]
   SLT4 <- cols_ab["SLT4"]
   SLT5 <- cols_ab["SLT5"]
+  SLT6 <- cols_ab["SLT6"]
   SMX <- cols_ab["SMX"]
   SPI <- cols_ab["SPI"]
   SPX <- cols_ab["SPX"]
+  SRX <- cols_ab["SRX"]
   STR <- cols_ab["STR"]
   STR1 <- cols_ab["STR1"]
   SUD <- cols_ab["SUD"]
+  SUL <- cols_ab["SUL"]
   SUT <- cols_ab["SUT"]
   SXT <- cols_ab["SXT"]
   SZO <- cols_ab["SZO"]
   TAL <- cols_ab["TAL"]
+  TAZ <- cols_ab["TAZ"]
   TCC <- cols_ab["TCC"]
   TCM <- cols_ab["TCM"]
   TCY <- cols_ab["TCY"]
@@ -765,10 +766,14 @@ eucast_rules <- function(x,
                                 (reference.rule_group %like% "expert" & reference.version == version_expertrules))
   }
   # filter out AmpC de-repressed cephalosporin-resistant mutants ----
-  if (is.null(ampc_cephalosporin_resistance)) {
+  # cefotaxime, ceftriaxone, ceftazidime
+  if (is.null(ampc_cephalosporin_resistance) || isFALSE(ampc_cephalosporin_resistance)) {
     eucast_rules_df <- subset(eucast_rules_df,
                               !reference.rule %like% "ampc")
   } else {
+    if (isTRUE(ampc_cephalosporin_resistance)) {
+      ampc_cephalosporin_resistance <- "R"
+    }
     eucast_rules_df[which(eucast_rules_df$reference.rule %like% "ampc"), "to_value"] <- as.character(ampc_cephalosporin_resistance)
   }
   

R/filter_ab_class.R

@@ -31,7 +31,7 @@
 #' @param ab_class an antimicrobial class, like `"carbapenems"`. The columns `group`, `atc_group1` and `atc_group2` of the [antibiotics] data set will be searched (case-insensitive) for this value.
 #' @param result an antibiotic result: S, I or R (or a combination of more of them)
 #' @param scope the scope to check which variables to check, can be `"any"` (default) or `"all"`
-#' @param only_rsi_columns a logical to indicate whether only columns must be included that were [transformed to class `<rsi>`]([rsi]) on beforehand (defaults to `FALSE`)
+#' @param only_rsi_columns a logical to indicate whether only columns must be included that were transformed to class `<rsi>` (see [as.rsi()]) on beforehand (defaults to `FALSE`)
 #' @param ... arguments passed on to [filter_ab_class()]
 #' @details All columns of `x` will be searched for known antibiotic names, abbreviations, brand names and codes (ATC, EARS-Net, WHO, etc.). This means that a filter function like e.g. [filter_aminoglycosides()] will include column names like 'gen', 'genta', 'J01GB03', 'tobra', 'Tobracin', etc.
 #' @rdname filter_ab_class

R/first_isolate.R

@@ -37,13 +37,14 @@
 #' @param col_keyantibiotics column name of the key antibiotics to determine first (weighted) isolates, see [key_antibiotics()]. Defaults to the first column that starts with 'key' followed by 'ab' or 'antibiotics' (case insensitive). Use `col_keyantibiotics = FALSE` to prevent this.
 #' @param episode_days episode in days after which a genus/species combination will be determined as 'first isolate' again. The default of 365 days is based on the guideline by CLSI, see *Source*. 
 #' @param testcodes_exclude character vector with test codes that should be excluded (case-insensitive)
-#' @param icu_exclude logical whether ICU isolates should be excluded (rows with value `TRUE` in the column set with `col_icu`)
+#' @param icu_exclude logical to indicate whether ICU isolates should be excluded (rows with value `TRUE` in the column set with `col_icu`)
 #' @param specimen_group value in the column set with `col_specimen` to filter on
 #' @param type type to determine weighed isolates; can be `"keyantibiotics"` or `"points"`, see *Details*
-#' @param ignore_I logical to determine whether antibiotic interpretations with `"I"` will be ignored when `type = "keyantibiotics"`, see *Details*
+#' @param ignore_I logical to indicate whether antibiotic interpretations with `"I"` will be ignored when `type = "keyantibiotics"`, see *Details*
 #' @param points_threshold points until the comparison of key antibiotics will lead to inclusion of an isolate when `type = "points"`, see *Details*
 #' @param info print progress
-#' @param include_unknown logical to determine whether 'unknown' microorganisms should be included too, i.e. microbial code `"UNKNOWN"`, which defaults to `FALSE`. For WHONET users, this means that all records with organism code `"con"` (*contamination*) will be excluded at default. Isolates with a microbial ID of `NA` will always be excluded as first isolate.
+#' @param include_unknown logical to indicate whether 'unknown' microorganisms should be included too, i.e. microbial code `"UNKNOWN"`, which defaults to `FALSE`. For WHONET users, this means that all records with organism code `"con"` (*contamination*) will be excluded at default. Isolates with a microbial ID of `NA` will always be excluded as first isolate.
+#' @param include_untested_rsi logical to indicate whether also rows without antibiotic results are still eligible for becoming a first isolate. Use `include_untested_rsi = FALSE` to always return `FALSE` for such rows. This checks the data set for columns of class `<rsi>` and consequently requires transforming columns with antibiotic results using [as.rsi()] first.
 #' @param ... arguments passed on to [first_isolate()] when using [filter_first_isolate()], or arguments passed on to [key_antibiotics()] when using [filter_first_weighted_isolate()]
 #' @details 
 #' These functions are context-aware. This means that then the `x` argument can be left blank, see *Examples*.
@@ -159,6 +160,7 @@ first_isolate <- function(x = NULL,
                           points_threshold = 2,
                           info = interactive(),
                           include_unknown = FALSE,
+                          include_untested_rsi = TRUE,
                           ...) {
   if (is_null_or_grouped_tbl(x)) {
     # when `x` is left blank, auto determine it (get_current_data() also contains dplyr::cur_data_all())
@@ -188,6 +190,7 @@ first_isolate <- function(x = NULL,
   meet_criteria(points_threshold, allow_class = c("numeric", "integer"), has_length = 1, is_positive = TRUE, is_finite = TRUE)
   meet_criteria(info, allow_class = "logical", has_length = 1)
   meet_criteria(include_unknown, allow_class = "logical", has_length = 1)
+  meet_criteria(include_untested_rsi, allow_class = "logical", has_length = 1)
   
   # remove data.table, grouping from tibbles, etc.
   x <- as.data.frame(x, stringsAsFactors = FALSE)
@@ -472,6 +475,14 @@ first_isolate <- function(x = NULL,
   }
   x[which(is.na(x$newvar_mo)), "newvar_first_isolate"] <- FALSE
   
+  # handle isolates without antibiogram
+  if (include_untested_rsi == FALSE && any(is.rsi(x))) {
+    rsi_all_NA <- which(unname(vapply(FUN.VALUE = logical(1), 
+                                      as.data.frame(t(x[, is.rsi(x), drop = FALSE])),
+                                      function(rsi_values) all(is.na(rsi_values)))))
+    x[rsi_all_NA, "newvar_first_isolate"] <- FALSE
+  }
+  
   # arrange back according to original sorting again
   x <- x[order(x$newvar_row_index), ]
   rownames(x) <- NULL

R/ggplot_pca.R

@@ -26,7 +26,7 @@
 #' PCA Biplot with `ggplot2`
 #'
 #' Produces a `ggplot2` variant of a so-called [biplot](https://en.wikipedia.org/wiki/Biplot) for PCA (principal component analysis), but is more flexible and more appealing than the base \R [biplot()] function.
-#' @inheritSection lifecycle Maturing Lifecycle
+#' @inheritSection lifecycle Stable Lifecycle
 #' @param x an object returned by [pca()], [prcomp()] or [princomp()]
 #' @inheritParams stats::biplot.prcomp
 #' @param labels an optional vector of labels for the observations. If set, the labels will be placed below their respective points. When using the [pca()] function as input for `x`, this will be determined automatically based on the attribute `non_numeric_cols`, see [pca()].
@@ -57,7 +57,7 @@
 #' 4. Added total amount of explained variance as a caption in the plot
 #' 5. Cleaned all syntax based on the `lintr` package, fixed grammatical errors and added integrity checks
 #' 6. Updated documentation
-#' @details The colours for labels and points can be changed by adding another scale layer for colour, like `scale_colour_viridis_d()` or `scale_colour_brewer()`.
+#' @details The colours for labels and points can be changed by adding another scale layer for colour, such as `scale_colour_viridis_d()` and `scale_colour_brewer()`.
 #' @rdname ggplot_pca
 #' @export
 #' @examples 

R/ggplot_rsi.R

@@ -26,7 +26,7 @@
 #' AMR Plots with `ggplot2`
 #'
 #' Use these functions to create bar plots for AMR data analysis. All functions rely on [ggplot2][ggplot2::ggplot()] functions.
-#' @inheritSection lifecycle Maturing Lifecycle
+#' @inheritSection lifecycle Stable Lifecycle
 #' @param data a [data.frame] with column(s) of class [`rsi`] (see [as.rsi()])
 #' @param position position adjustment of bars, either `"fill"`, `"stack"` or `"dodge"`
 #' @param x variable to show on x axis, either `"antibiotic"` (default) or `"interpretation"` or a grouping variable
@@ -36,7 +36,8 @@
 #' @param facet variable to split plots by, either `"interpretation"` (default) or `"antibiotic"` or a grouping variable
 #' @inheritParams proportion
 #' @param nrow (when using `facet`) number of rows
-#' @param colours a named vector with colours for the bars. The names must be one or more of: S, SI, I, IR, R or be `FALSE` to use default [ggplot2][ggplot2::ggplot()] colours.
+#' @param colours a named vactor with colour to be used for filling. The default colours are colour-blind friendly.
+#' @param aesthetics aesthetics to apply the colours to, defaults to "fill" but can also be (a combination of) "alpha", "colour", "fill", "linetype", "shape" or "size"
 #' @param datalabels show datalabels using [labels_rsi_count()]
 #' @param datalabels.size size of the datalabels
 #' @param datalabels.colour colour of the datalabels
@@ -45,7 +46,7 @@
 #' @param caption text to show as caption of the plot
 #' @param x.title text to show as x axis description
 #' @param y.title text to show as y axis description
-#' @param ... other arguments passed on to [geom_rsi()]
+#' @param ... other arguments passed on to [geom_rsi()] or, in case of [scale_rsi_colours()], named values to set colours. The default colours are colour-blind friendly, while maintaining the convention that e.g. 'susceptible' should be green and 'resistant' should be red. See *Examples*.
 #' @details At default, the names of antibiotics will be shown on the plots using [ab_name()]. This can be set with the `translate_ab` argument. See [count_df()].
 #'
 #' ## The Functions
@@ -55,7 +56,7 @@
 #'
 #' [scale_y_percent()] transforms the y axis to a 0 to 100% range using [ggplot2::scale_y_continuous()].
 #'
-#' [scale_rsi_colours()] sets colours to the bars: pastel blue for S, pastel turquoise for I and pastel red for R, using [ggplot2::scale_fill_manual()].
+#' [scale_rsi_colours()] sets colours to the bars (green for S, yellow for I, and red for R). with multilingual support. The default colours are colour-blind friendly, while maintaining the convention that e.g. 'susceptible' should be green and 'resistant' should be red.
 #'
 #' [theme_rsi()] is a [ggplot2 theme][[ggplot2::theme()] with minimal distraction.
 #'
@@ -99,11 +100,20 @@
 #'                size = 1,
 #'                linetype = 2,
 #'                alpha = 0.25)
-#'  
+#'
+#'   # you can alter the colours with colour names:
 #'   example_isolates %>%
 #'     select(AMX) %>%
 #'     ggplot_rsi(colours = c(SI = "yellow"))
-#'   
+#'
+#'   # but you can also use the built-in colour-blind friendly colours for
+#'   # your plots, where "S" is green, "I" is yellow and "R" is red:
+#'   data.frame(x = c("Value1", "Value2", "Value3"),
+#'              y = c(1, 2, 3),
+#'              z = c("Value4", "Value5", "Value6")) %>%
+#'     ggplot() +
+#'     geom_col(aes(x = x, y = y, fill = z)) +
+#'     scale_rsi_colours(Value4 = "S", Value5 = "I", Value6 = "R")
 #' }
 #'   
 #' \donttest{
@@ -118,11 +128,6 @@
 #'          CIP) %>%
 #'   ggplot_rsi(x = "age_group")
 #'   
-#' # for colourblind mode, use divergent colours from the viridis package:
-#' example_isolates %>%
-#'   select(AMX, NIT, FOS, TMP, CIP) %>%
-#'   ggplot_rsi() + 
-#'   scale_fill_viridis_d()
 #' # a shorter version which also adjusts data label colours:
 #' example_isolates %>%
 #'   select(AMX, NIT, FOS, TMP, CIP) %>%
@@ -154,11 +159,11 @@ ggplot_rsi <- function(data,
                        minimum = 30,
                        language = get_locale(),
                        nrow = NULL,
-                       colours = c(S = "#61a8ff",
-                                   SI = "#61a8ff",
-                                   I = "#61f7ff",
-                                   IR = "#ff6961",
-                                   R = "#ff6961"),
+                       colours = c(S = "#3CAEA3",
+                                   SI = "#3CAEA3",
+                                   I = "#F6D55C",
+                                   IR = "#ED553B",
+                                   R = "#ED553B"),
                        datalabels = TRUE,
                        datalabels.size = 2.5,
                        datalabels.colour = "grey15",
@@ -223,11 +228,6 @@ ggplot_rsi <- function(data,
     theme_rsi()
   
   if (fill == "interpretation") {
-    # set RSI colours
-    if (isFALSE(colours) & missing(datalabels.colour)) {
-      # set datalabel colour to middle grey
-      datalabels.colour <- "grey50"
-    }
     p <- p + scale_rsi_colours(colours = colours)
   }
   
@@ -308,17 +308,19 @@ geom_rsi <- function(position = NULL,
     x <- "interpretation"
   }
   
-  ggplot2::layer(geom = "bar", stat = "identity", position = position,
-                 mapping = ggplot2::aes_string(x = x, y = y, fill = fill),
-                 params = list(...), data = function(x) {
-                   rsi_df(data = x,
-                          translate_ab = translate_ab,
-                          language = language,
-                          minimum = minimum,
-                          combine_SI = combine_SI,
-                          combine_IR = combine_IR)
-                 })
-  
+  ggplot2::geom_col(
+    data = function(x) {
+      rsi_df(data = x,
+             translate_ab = translate_ab,
+             language = language,
+             minimum = minimum,
+             combine_SI = combine_SI,
+             combine_IR = combine_IR)
+    },
+    mapping = ggplot2::aes_string(x = x, y = y, fill = fill),
+    position = position,
+    ...
+  )
 }
 
 #' @rdname ggplot_rsi
@@ -364,26 +366,52 @@ scale_y_percent <- function(breaks = seq(0, 1, 0.1), limits = NULL) {
 
 #' @rdname ggplot_rsi
 #' @export
-scale_rsi_colours <- function(colours = c(S = "#61a8ff",
-                                          SI = "#61a8ff",
-                                          I = "#61f7ff",
-                                          IR = "#ff6961",
-                                          R = "#ff6961")) {
+scale_rsi_colours <- function(...,
+                              aesthetics = "fill") {
   stop_ifnot_installed("ggplot2")
-  meet_criteria(colours, allow_class = c("character", "logical"))
+  meet_criteria(aesthetics, allow_class = "character", is_in = c("alpha", "colour", "color", "fill", "linetype", "shape", "size"))
   
-  # previous colour: palette = "RdYlGn"
-  # previous colours: values = c("#b22222", "#ae9c20", "#7cfc00")
-  
-  if (!identical(colours, FALSE)) {
-    original_cols <- c(S = "#61a8ff",
-                       SI = "#61a8ff",
-                       I = "#61f7ff",
-                       IR = "#ff6961",
-                       R = "#ff6961")
-    colours <- replace(original_cols, names(colours), colours)
-    ggplot2::scale_fill_manual(values = colours)
+  # behaviour until AMR pkg v1.5.0 and also when coming from ggplot_rsi()
+  if ("colours" %in% names(list(...))) {
+    original_cols <- c(S = "#3CAEA3",
+                       SI = "#3CAEA3",
+                       I = "#F6D55C",
+                       IR = "#ED553B",
+                       R = "#ED553B")
+    colours <- replace(original_cols, names(list(...)$colours), list(...)$colours)
+    return(ggplot2::scale_fill_manual(values = colours))
   }
+  if (identical(unlist(list(...)), FALSE)) {
+    return(invisible())
+  }
+  
+  names_susceptible <- c("S", "SI", "IS", "S+I", "I+S", "susceptible", "Susceptible",
+                         unique(translations_file[which(translations_file$pattern == "Susceptible"),
+                                                  "replacement", drop = TRUE]))
+  names_incr_exposure <- c("I", "intermediate", "increased exposure", "incr. exposure", "Increased exposure", "Incr. exposure",
+                           unique(translations_file[which(translations_file$pattern == "Intermediate"),
+                                                    "replacement", drop = TRUE]),
+                           unique(translations_file[which(translations_file$pattern == "Incr. exposure"),
+                                                    "replacement", drop = TRUE]))
+  names_resistant <- c("R", "IR", "RI", "R+I", "I+R", "resistant", "Resistant",
+                       unique(translations_file[which(translations_file$pattern == "Resistant"), 
+                                                "replacement", drop = TRUE]))
+  
+  susceptible <- rep("#3CAEA3", length(names_susceptible))
+  names(susceptible) <- names_susceptible
+  incr_exposure <- rep("#F6D55C", length(names_incr_exposure))
+  names(incr_exposure) <- names_incr_exposure
+  resistant <- rep("#ED553B", length(names_resistant))
+  names(resistant) <- names_resistant
+  
+  original_cols = c(susceptible, incr_exposure, resistant)
+  dots <- c(...)
+  # replace S, I, R as colours: scale_rsi_colours(mydatavalue = "S")
+  dots[dots == "S"] <- "#3CAEA3"
+  dots[dots == "I"] <- "#F6D55C"
+  dots[dots == "R"] <- "#ED553B"
+  cols <- replace(original_cols, names(dots), dots)
+  ggplot2::scale_discrete_manual(aesthetics = aesthetics, values = cols)
 }
 
 #' @rdname ggplot_rsi

R/globals.R

@@ -23,6 +23,40 @@
 # how to conduct AMR data analysis: https://msberends.github.io/AMR/   #
 # ==================================================================== #
 
+# add new version numbers here, and add the rules themselves to "data-raw/eucast_rules.tsv" and rsi_translation
+# (sourcing "data-raw/_internals.R" will process the TSV file)
+EUCAST_VERSION_BREAKPOINTS <- list("11.0" = list(version_txt = "v11.0",
+                                                 year = 2021, 
+                                                 title = "'EUCAST Clinical Breakpoint Tables'",
+                                                 url = "https://www.eucast.org/clinical_breakpoints/"),
+                                   "10.0" = list(version_txt = "v10.0",
+                                                 year = 2020, 
+                                                 title = "'EUCAST Clinical Breakpoint Tables'",
+                                                 url = "https://www.eucast.org/ast_of_bacteria/previous_versions_of_documents/"))
+EUCAST_VERSION_EXPERT_RULES <- list("3.1" = list(version_txt = "v3.1",
+                                                 year = 2016, 
+                                                 title = "'EUCAST Expert Rules, Intrinsic Resistance and Exceptional Phenotypes'",
+                                                 url = "https://www.eucast.org/expert_rules_and_intrinsic_resistance/"),
+                                    "3.2" = list(version_txt = "v3.2",
+                                                 year = 2020, 
+                                                 title = "'EUCAST Expert Rules' and 'EUCAST Intrinsic Resistance and Unusual Phenotypes'",
+                                                 url = "https://www.eucast.org/expert_rules_and_intrinsic_resistance/"))
+
+SNOMED_VERSION <- list(title = "Public Health Information Network Vocabulary Access and Distribution System (PHIN VADS)",
+                       current_source = "US Edition of SNOMED CT from 1 September 2020",
+                       current_version = 12,
+                       current_oid = "2.16.840.1.114222.4.11.1009",
+                       value_set_name = "Microorganism",
+                       url = "https://phinvads.cdc.gov/vads/ViewValueSet.action?oid=2.16.840.1.114222.4.11.1009")
+
+CATALOGUE_OF_LIFE <- list(
+  year = 2019,
+  version = "Catalogue of Life: {year} Annual Checklist",
+  url_CoL = "http://www.catalogueoflife.org/col/",
+  url_LPSN = "https://lpsn.dsmz.de",
+  yearmonth_LPSN = "March 2021"
+)
+
 globalVariables(c(".rowid",
                   "ab",
                   "ab_txt",
@@ -33,7 +67,10 @@ globalVariables(c(".rowid",
                   "atc_group1",
                   "atc_group2",
                   "code",
+                  "cols",
+                  "count",
                   "data",
+                  "disk",
                   "dosage",
                   "dose",
                   "dose_times",
@@ -52,6 +89,8 @@ globalVariables(c(".rowid",
                   "language",
                   "lookup",
                   "method",
+                  "mic",
+                  "mic ",
                   "microorganism",
                   "microorganisms",
                   "microorganisms.codes",
@@ -67,8 +106,9 @@ globalVariables(c(".rowid",
                   "reference.rule",
                   "reference.rule_group",
                   "reference.version",
-                  "rsi_translation",
                   "rowid",
+                  "rsi",
+                  "rsi_translation",
                   "rule_group",
                   "rule_name",
                   "se_max",

R/guess_ab_col.R

@@ -30,7 +30,7 @@
 #' @param x a [data.frame]
 #' @param search_string a text to search `x` for, will be checked with [as.ab()] if this value is not a column in `x`
 #' @param verbose a logical to indicate whether additional info should be printed
-#' @param only_rsi_columns a logical to indicate whether only antibiotic columns must be detected that were [transformed to class `<rsi>`]([rsi]) on beforehand (defaults to `FALSE`)
+#' @param only_rsi_columns a logical to indicate whether only antibiotic columns must be detected that were transformed to class `<rsi>` (see [as.rsi()]) on beforehand (defaults to `FALSE`)
 #' @details You can look for an antibiotic (trade) name or abbreviation and it will search `x` and the [antibiotics] data set for any column containing a name or code of that antibiotic. **Longer columns names take precedence over shorter column names.**
 #' @return A column name of `x`, or `NULL` when no result is found.
 #' @export

R/isolate_identifier.R

@@ -1,203 +0,0 @@
-# ==================================================================== #
-# TITLE                                                                #
-# Antimicrobial Resistance (AMR) Data Analysis for R                   #
-#                                                                      #
-# SOURCE                                                               #
-# https://github.com/msberends/AMR                                     #
-#                                                                      #
-# LICENCE                                                              #
-# (c) 2018-2021 Berends MS, Luz CF et al.                              #
-# Developed at the University of Groningen, the Netherlands, in        #
-# collaboration with non-profit organisations Certe Medical            #
-# Diagnostics & Advice, and University Medical Center Groningen.       # 
-#                                                                      #
-# This R package is free software; you can freely use and distribute   #
-# it for both personal and commercial purposes under the terms of the  #
-# GNU General Public License version 2.0 (GNU GPL-2), as published by  #
-# the Free Software Foundation.                                        #
-# We created this package for both routine data analysis and academic  #
-# research and it was publicly released in the hope that it will be    #
-# useful, but it comes WITHOUT ANY WARRANTY OR LIABILITY.              #
-#                                                                      #
-# Visit our website for the full manual and a complete tutorial about  #
-# how to conduct AMR data analysis: https://msberends.github.io/AMR/   #
-# ==================================================================== #
-
-#' Create Identifier of an Isolate
-#' 
-#' This function will paste the microorganism code with all antimicrobial results into one string for each row in a data set. This is useful to compare isolates, e.g. between institutions or regions, when there is no genotyping available.
-#' @inheritSection lifecycle Experimental Lifecycle
-#' @inheritParams eucast_rules
-#' @param cols_ab a character vector of column names of `x`, or (a combination with) an [antibiotic selector function]([ab_class()]), such as [carbapenems()] and [aminoglycosides()]
-#' @rdname isolate_identifier
-#' @export
-#' @inheritSection AMR Read more on Our Website!
-#' @examples 
-#' # automatic selection of microorganism and antibiotics (i.e., all <rsi> columns, see ?as.rsi)
-#' x <- isolate_identifier(example_isolates)
-#' 
-#' # ignore microorganism codes, only use antimicrobial results
-#' x <- isolate_identifier(example_isolates, col_mo = FALSE, cols_ab = c("AMX", "TZP", "GEN", "TOB"))
-#' 
-#' # select antibiotics from certain antibiotic classes
-#' x <- isolate_identifier(example_isolates, cols_ab = c(carbapenems(), aminoglycosides()))
-isolate_identifier <- function(x, col_mo = NULL, cols_ab = NULL) {
-  if (is.null(col_mo)) {
-    col_mo <- search_type_in_df(x, "mo")
-    if (is.null(col_mo)) {
-      # no column found, then ignore the argument
-      col_mo <- FALSE
-    }
-  }
-  
-  if (isFALSE(col_mo)) {
-    # is FALSE then ignore mo column
-    x$col_mo <- ""
-    col_mo <- "col_mo"
-  } else if (!is.null(col_mo)) {
-    x[, col_mo] <- paste0(as.mo(x[, col_mo, drop = TRUE]), "|")
-  }
-  
-  cols_ab <- deparse(substitute(cols_ab)) # support ab class selectors: isolate_identifier(x, cols_ab = carbapenems())
-  if (identical(cols_ab, "NULL")) {
-    cols_ab <- colnames(x)[vapply(FUN.VALUE = logical(1), x, is.rsi)]
-  } else {
-    cols_ab <- tryCatch(colnames(x[, eval(parse(text = cols_ab), envir = parent.frame())]),
-                        # tryCatch adds 4 calls, so total is -5
-                        error = function(e) stop_(e$message, call = -5))
-  }
-  
-  # cope with empty values
-  if (length(cols_ab) == 0 && all(x[, col_mo, drop = TRUE] == "", na.rm = TRUE)) {
-    warning_("in isolate_identifier(): no column with microorganisms and no columns with antimicrobial agents found", call = FALSE)
-  } else if (length(cols_ab) == 0) {
-    warning_("in isolate_identifier(): no columns with antimicrobial agents found", call = FALSE)
-  }
-  
-  out <- x[, c(col_mo, cols_ab), drop = FALSE]
-  out <- do.call(paste, c(out, sep = ""))
-  out <- gsub("NA", ".", out, fixed = TRUE)
-  out <- set_clean_class(out, new_class = c("isolate_identifier", "character"))
-  attr(out, "ab") <- cols_ab
-  out
-}
-
-#' @method all.equal isolate_identifier
-#' @inheritParams base::all.equal
-#' @param ignore_empty_results a logical to indicate whether empty results must be ignored, so that only values R, S and I will be compared
-#' @rdname isolate_identifier
-#' @export
-all.equal.isolate_identifier <- function(target, current, ignore_empty_results = TRUE, ...) {
-  meet_criteria(target, allow_class = "isolate_identifier")
-  meet_criteria(current, allow_class = "isolate_identifier")
-  meet_criteria(ignore_empty_results, allow_class = "logical", has_length = 1)
-  
-  if (isTRUE(all.equal.character(target, current))) {
-    return(TRUE)
-  }
-  # vectorise over both target and current
-  if (length(target) > 1 && length(current) == 1) {
-    current <- rep(current, length(target))
-  } else if (length(current) > 1 && length(target) == 1) {
-    target <- rep(target, length(current))
-  }
-  stop_if(length(target) != length(current),
-          "length of `target` and `current` must be the same, or one must be 1")
-  
-  get_vector <- function(x) {
-    if (grepl("|", x, fixed = TRUE)) {
-      mo <- gsub("(.*)\\|.*", "\\1", x)
-    } else {
-      mo <- NULL
-    }
-    if (grepl("|", x, fixed = TRUE)) {
-      ab <- gsub(".*\\|(.*)", "\\1", x)
-    } else {
-      ab <- x
-    }
-    ab <- strsplit(ab, "")[[1L]]
-    if (is.null(mo)) {
-      out <- as.character(ab)
-      names(out) <- attributes(x)$ab
-    } else {
-      out <- as.character(c(mo, ab))
-      names(out) <- c("mo", attributes(x)$ab)
-    }
-    out
-  }
-  
-  # run it
-  for (i in seq_len(length(target))) {
-    if (i == 1) {
-      df <- data.frame(object = paste0(c("target[", "current["), i, "]"))
-    }
-    trgt <- get_vector(target[i])
-    crnt <- get_vector(current[i])
-    if (ignore_empty_results == TRUE) {
-      diff <- names(trgt[trgt != crnt & trgt != "." & crnt != "."])  
-    } else {
-      diff <- names(trgt[trgt != crnt])
-    }
-    
-  }
-  
-  stop("THIS FUNCTION IS WORK IN PROGRESS AND NOT AVAILABLE IN THIS BETA VERSION")
-  
-}
-
-#' @method print isolate_identifier
-#' @export
-#' @noRd
-print.isolate_identifier <- function(x, ...) {
-  print(as.character(x), ...)
-}
-
-#' @method [ isolate_identifier
-#' @export
-#' @noRd
-"[.isolate_identifier" <- function(x, ...) {
-  y <- NextMethod()
-  attributes(y) <- attributes(x)
-  y
-}
-#' @method [[ isolate_identifier
-#' @export
-#' @noRd
-"[[.isolate_identifier" <- function(x, ...) {
-  y <- NextMethod()
-  attributes(y) <- attributes(x)
-  y
-}
-#' @method [<- isolate_identifier
-#' @export
-#' @noRd
-"[<-.isolate_identifier" <- function(i, j, ..., value) {
-  y <- NextMethod()
-  attributes(y) <- attributes(i)
-  y
-}
-#' @method [[<- isolate_identifier
-#' @export
-#' @noRd
-"[[<-.isolate_identifier" <- function(i, j, ..., value) {
-  y <- NextMethod()
-  attributes(y) <- attributes(i)
-  y
-}
-#' @method c isolate_identifier
-#' @export
-#' @noRd
-c.isolate_identifier <- function(x, ...) {
-  y <- NextMethod()
-  attributes(y) <- attributes(x)
-  y
-}
-
-#' @method unique isolate_identifier
-#' @export
-#' @noRd
-unique.isolate_identifier <- function(x, incomparables = FALSE, ...) {
-  y <- NextMethod()
-  attributes(y) <- attributes(x)
-  y
-}

R/lifecycle.R

@@ -27,10 +27,10 @@
 # NOTE TO SELF: could also have done this with the 'lifecycle' package, but why add a package dependency for such an easy job??
 ###############
 
-#' Lifecycles of Functions in the `amr` Package
+#' Lifecycles of Functions in the `AMR` Package
 #' @name lifecycle
 #' @rdname lifecycle
-#' @description Functions in this `AMR` package are categorised using [the lifecycle circle of the Tidyverse as found on www.tidyverse.org/lifecycle](https://www.Tidyverse.org/lifecycle).
+#' @description Functions in this `AMR` package are categorised using [the lifecycle circle of the Tidyverse as found on www.tidyverse.org/lifecycle](https://lifecycle.r-lib.org/articles/stages.html).
 #' 
 #' \if{html}{\figure{lifecycle_tidyverse.svg}{options: height=200px style=margin-bottom:5px} \cr}
 #' This page contains a section for every lifecycle (with text borrowed from the aforementioned Tidyverse website), so they can be used in the manual pages of the functions. 

R/like.R

@@ -25,7 +25,7 @@
 
 #' Pattern Matching with Keyboard Shortcut
 #'
-#' Convenient wrapper around [grep()] to match a pattern: `x %like% pattern`. It always returns a [`logical`] vector and is always case-insensitive (use `x %like_case% pattern` for case-sensitive matching). Also, `pattern` can be as long as `x` to compare items of each index in both vectors, or they both can have the same length to iterate over all cases.
+#' Convenient wrapper around [grepl()] to match a pattern: `x %like% pattern`. It always returns a [`logical`] vector and is always case-insensitive (use `x %like_case% pattern` for case-sensitive matching). Also, `pattern` can be as long as `x` to compare items of each index in both vectors, or they both can have the same length to iterate over all cases.
 #' @inheritSection lifecycle Stable Lifecycle
 #' @param x a character vector where matches are sought, or an object which can be coerced by [as.character()] to a character vector.
 #' @param pattern a character string containing a regular expression (or [character] string for `fixed = TRUE`) to be matched in the given character vector. Coerced by [as.character()] to a character string if possible.  If a [character] vector of length 2 or more is supplied, the first element is used with a warning.
@@ -43,7 +43,7 @@
 #' 
 #' Using RStudio? The text `%like%` can also be directly inserted in your code from the Addins menu and can have its own Keyboard Shortcut like `Ctrl+Shift+L` or `Cmd+Shift+L` (see `Tools` > `Modify Keyboard Shortcuts...`).
 #' @source Idea from the [`like` function from the `data.table` package](https://github.com/Rdatatable/data.table/blob/master/R/like.R)
-#' @seealso [grep()]
+#' @seealso [grepl()]
 #' @inheritSection AMR Read more on Our Website!
 #' @examples
 #' # simple test
@@ -53,13 +53,17 @@
 #' #> TRUE
 #' b %like% a
 #' #> FALSE
-#'
-#' # also supports multiple patterns, length must be equal to x
+#' 
+#' # also supports multiple patterns
 #' a <- c("Test case", "Something different", "Yet another thing")
 #' b <- c(     "case",           "diff",      "yet")
 #' a %like% b
 #' #> TRUE TRUE TRUE
-#'
+#' a[1] %like% b
+#' #> TRUE FALSE FALSE
+#' a %like% b[1]
+#' #> TRUE FALSE FALSE
+#' 
 #' # get isolates whose name start with 'Ent' or 'ent'
 #' \donttest{
 #' if (require("dplyr")) {
@@ -71,7 +75,11 @@ like <- function(x, pattern, ignore.case = TRUE) {
   meet_criteria(x, allow_NA = TRUE)
   meet_criteria(pattern, allow_NA = FALSE)
   meet_criteria(ignore.case, allow_class = "logical", has_length = 1)
-
+  
+  if (all(is.na(x))) {
+    return(rep(FALSE, length(x)))
+  }
+  
   # set to fixed if no regex found
   fixed <- !any(is_possibly_regex(pattern))
   if (ignore.case == TRUE) {
@@ -79,53 +87,25 @@ like <- function(x, pattern, ignore.case = TRUE) {
     x <- tolower(x)
     pattern <- tolower(pattern)
   }
-  
-  if (length(pattern) > 1 & length(x) == 1) {
-    x <- rep(x, length(pattern))
-  }
-  
-  if (all(is.na(x))) {
-    return(rep(FALSE, length(x)))
-  }
-    
-  if (length(pattern) > 1) {
-    res <- vector(length = length(pattern))
-    if (length(x) != length(pattern)) {
-      if (length(x) == 1) {
-        x <- rep(x, length(pattern))
-      }
-      # return TRUE for every 'x' that matches any 'pattern', FALSE otherwise
-      for (i in seq_len(length(res))) {
-        if (is.factor(x[i])) {
-          res[i] <- as.integer(x[i]) %in% grep(pattern[i], levels(x[i]), ignore.case = FALSE, fixed = fixed)
-        } else {
-          res[i] <- grepl(pattern[i], x[i], ignore.case = FALSE, fixed = fixed, perl = !fixed)
-        }
-      }
-      res <- vapply(FUN.VALUE = logical(1), pattern, function(pttrn) grepl(pttrn, x, ignore.case = FALSE, fixed = fixed))
-      res2 <- as.logical(rowSums(res))
-      # get only first item of every hit in pattern
-      res2[duplicated(res)] <- FALSE
-      res2[rowSums(res) == 0] <- NA
-      return(res2)
-    } else {
-      # x and pattern are of same length, so items with each other
-      for (i in seq_len(length(res))) {
-        if (is.factor(x[i])) {
-          res[i] <- as.integer(x[i]) %in% grep(pattern[i], levels(x[i]), ignore.case = FALSE, fixed = fixed, perl = !fixed)
-        } else {
-          res[i] <- grepl(pattern[i], x[i], ignore.case = FALSE, fixed = fixed, perl = !fixed)
-        }
-      }
-      return(res)
-    }
-  }
-  
-  # the regular way how grepl works; just one pattern against one or more x
+
   if (is.factor(x)) {
-    as.integer(x) %in% grep(pattern, levels(x), ignore.case = FALSE, fixed = fixed, perl = !fixed)
-  } else {
+    x <- as.character(x)
+  }
+  
+  if (length(pattern) == 1) {
     grepl(pattern, x, ignore.case = FALSE, fixed = fixed, perl = !fixed)
+  } else {
+    if (length(x) == 1) {
+      x <- rep(x, length(pattern))
+    } else if (length(pattern) != length(x)) {
+      stop_("arguments `x` and `pattern` must be of same length, or either one must be 1")
+    }
+    unlist(
+      Map(f = grepl,
+          pattern,
+          x,
+          MoreArgs = list(ignore.case = FALSE, fixed = fixed, perl = !fixed)),
+      use.names = FALSE)
   }
 }
 

R/mic.R

@@ -25,13 +25,51 @@
 
 #' Transform Input to Minimum Inhibitory Concentrations (MIC)
 #'
-#' This transforms a vector to a new class [`mic`], which is an ordered [factor] with valid minimum inhibitory concentrations (MIC) as levels. Invalid MIC values will be translated as `NA` with a warning.
+#' This ransforms vectors to a new class [`mic`], which treats the input as decimal numbers, while maintaining operators (such as ">=") and only allowing valid MIC values known to the field of (medical) microbiology.
 #' @inheritSection lifecycle Stable Lifecycle
 #' @rdname as.mic
-#' @param x vector
+#' @param x character or numeric vector
 #' @param na.rm a logical indicating whether missing values should be removed
 #' @details To interpret MIC values as RSI values, use [as.rsi()] on MIC values. It supports guidelines from EUCAST and CLSI.
-#' @return Ordered [factor] with additional class [`mic`]
+#' 
+#' This class for MIC values is a quite a special data type: formally it is an ordered factor with valid MIC values as factor levels (to make sure only valid MIC values are retained), but for any mathematical operation it acts as decimal numbers:
+#' 
+#' ```
+#' x <- random_mic(10)
+#' x
+#' #> Class <mic>
+#' #>  [1] 16     1      8      8      64     >=128  0.0625 32     32     16
+#' 
+#' is.factor(x)
+#' #> [1] TRUE
+#' 
+#' x[1] * 2
+#' #> [1] 32
+#' 
+#' median(x)
+#' #> [1] 26
+#' ```
+#' 
+#' This makes it possible to maintain operators that often come with MIC values, such ">=" and "<=", even when filtering using numeric values in data analysis, e.g.:
+#' 
+#' ```
+#' x[x > 4]
+#' #> Class <mic>
+#' #> [1] 16    8     8     64    >=128 32    32    16
+#' 
+#' df <- data.frame(x, hospital = "A")
+#' subset(df, x > 4) # or with dplyr: df %>% filter(x > 4)
+#' #>        x hospital
+#' #> 1     16        A
+#' #> 5     64        A
+#' #> 6  >=128        A
+#' #> 8     32        A
+#' #> 9     32        A
+#' #> 10    16        A
+#' ```
+#' 
+#' The following [generic functions][groupGeneric()] are implemented for the MIC class: `!`, `!=`, `%%`, `%/%`, `&`, `*`, `+`, `-`, `/`, `<`, `<=`, `==`, `>`, `>=`, `^`, `|`, [abs()], [acos()], [acosh()], [all()], [any()], [asin()], [asinh()], [atan()], [atanh()], [ceiling()], [cos()], [cosh()], [cospi()], [cummax()], [cummin()], [cumprod()], [cumsum()], [digamma()], [exp()], [expm1()], [floor()], [gamma()], [lgamma()], [log()], [log1p()], [log2()], [log10()], [max()], [mean()], [min()], [prod()], [range()], [round()], [sign()], [signif()], [sin()], [sinh()], [sinpi()], [sqrt()], [sum()], [tan()], [tanh()], [tanpi()], [trigamma()] and [trunc()]. Some functions of the `stats` package are also implemented: [median()], [quantile()], [mad()], [IQR()], [fivenum()]. Also, [boxplot.stats()] is supported. Since [sd()] and [var()] are non-generic functions, these could not be extended. Use [mad()] as an alternative, or use e.g. `sd(as.numeric(x))` where `x` is your vector of MIC values.
+#' @return Ordered [factor] with additional class [`mic`], that in mathematical operations acts as decimal numbers. Bare in mind that the outcome of any mathematical operation on MICs will return a numeric value.
 #' @aliases mic
 #' @export
 #' @seealso [as.rsi()]
@@ -42,6 +80,11 @@
 #'
 #' # this can also coerce combined MIC/RSI values:
 #' as.mic("<=0.002; S") # will return <=0.002
+#' 
+#' # mathematical processing treats MICs as numeric values
+#' fivenum(mic_data)
+#' quantile(mic_data)
+#' all(mic_data < 512)
 #'
 #' # interpret MIC values
 #' as.rsi(x = as.mic(2),
@@ -53,16 +96,17 @@
 #'        ab = "AMX",
 #'        guideline = "EUCAST")
 #'
+#' # plot MIC values, see ?plot
 #' plot(mic_data)
-#' barplot(mic_data)
+#' plot(mic_data, mo = "E. coli", ab = "cipro")
 as.mic <- function(x, na.rm = FALSE) {
-  meet_criteria(x, allow_class = c("mic", "character", "numeric", "integer"), allow_NA = TRUE)
+  meet_criteria(x, allow_class = c("mic", "character", "numeric", "integer", "factor"), allow_NA = TRUE)
   meet_criteria(na.rm, allow_class = "logical", has_length = 1)
   
   if (is.mic(x)) {
     x
   } else {
-    x <- unlist(x)
+    x <- as.character(unlist(x))
     if (na.rm == TRUE) {
       x <- x[!is.na(x)]
     }
@@ -74,29 +118,29 @@ as.mic <- function(x, na.rm = FALSE) {
     x <- gsub("\u2264", "<=", x, fixed = TRUE)
     x <- gsub("\u2265", ">=", x, fixed = TRUE)
     # remove space between operator and number ("<= 0.002" -> "<=0.002")
-    x <- gsub("(<|=|>) +", "\\1", x)
+    x <- gsub("(<|=|>) +", "\\1", x, perl = TRUE)
     # transform => to >= and =< to <=
     x <- gsub("=<", "<=", x, fixed = TRUE)
     x <- gsub("=>", ">=", x, fixed = TRUE)
     # dots without a leading zero must start with 0
-    x <- gsub("([^0-9]|^)[.]", "\\10.", x)
+    x <- gsub("([^0-9]|^)[.]", "\\10.", x, perl = TRUE)
     # values like "<=0.2560.512" should be 0.512
-    x <- gsub(".*[.].*[.]", "0.", x)
+    x <- gsub(".*[.].*[.]", "0.", x, perl = TRUE)
     # remove ending .0
-    x <- gsub("[.]+0$", "", x)
+    x <- gsub("[.]+0$", "", x, perl = TRUE)
     # remove all after last digit
-    x <- gsub("[^0-9]+$", "", x)
+    x <- gsub("[^0-9]+$", "", x, perl = TRUE)
     # keep only one zero before dot
-    x <- gsub("0+[.]", "0.", x)
+    x <- gsub("0+[.]", "0.", x, perl = TRUE)
     # starting 00 is probably 0.0 if there's no dot yet
     x[!x %like% "[.]"] <- gsub("^00", "0.0", x[!x %like% "[.]"])
     # remove last zeroes
-    x <- gsub("([.].?)0+$", "\\1", x)
-    x <- gsub("(.*[.])0+$", "\\10", x)
+    x <- gsub("([.].?)0+$", "\\1", x, perl = TRUE)
+    x <- gsub("(.*[.])0+$", "\\10", x, perl = TRUE)
     # remove ending .0 again
     x[x %like% "[.]"] <- gsub("0+$", "", x[x %like% "[.]"])
     # never end with dot
-    x <- gsub("[.]$", "", x)
+    x <- gsub("[.]$", "", x, perl = TRUE)
     # force to be character
     x <- as.character(x)
     # trim it
@@ -155,29 +199,31 @@ is.mic <- function(x) {
 #' @export
 #' @noRd
 as.double.mic <- function(x, ...) {
-  as.double(gsub("[<=>]+", "", as.character(x)))
+  as.double(gsub("[<=>]+", "", as.character(x), perl = TRUE))
 }
 
 #' @method as.integer mic
 #' @export
 #' @noRd
 as.integer.mic <- function(x, ...) {
-  as.integer(gsub("[<=>]+", "", as.character(x)))
+  as.integer(gsub("[<=>]+", "", as.character(x), perl = TRUE))
 }
 
 #' @method as.numeric mic
 #' @export
 #' @noRd
 as.numeric.mic <- function(x, ...) {
-  as.numeric(gsub("[<=>]+", "", as.character(x)))
+  as.numeric(gsub("[<=>]+", "", as.character(x), perl = TRUE))
 }
 
 #' @method droplevels mic
 #' @export
 #' @noRd
-droplevels.mic <- function(x, exclude = if (any(is.na(levels(x)))) NULL else NA, ...) {
+droplevels.mic <- function(x, exclude = if (any(is.na(levels(x)))) NULL else NA, as.mic = TRUE, ...) {
   x <- droplevels.factor(x, exclude = exclude, ...)
-  class(x) <- c("mic", "ordered", "factor")
+  if (as.mic == TRUE) {
+    class(x) <- c("mic", "ordered", "factor")
+  }
   x
 }
 
@@ -189,6 +235,7 @@ pillar_shaft.mic <- function(x, ...) {
   out <- pasted
   out[is.na(x)] <- font_na(NA)
   out <- gsub("(<|=|>)", font_silver("\\1"), out)
+  out <- gsub("([.]?0+)$", font_white("\\1"), out)
   create_pillar_column(out, align = "right", width = max(nchar(pasted)))
 }
 
@@ -203,70 +250,24 @@ type_sum.mic <- function(x, ...) {
 print.mic <- function(x, ...) {
   cat("Class <mic>\n")
   print(as.character(x), quote = FALSE)
+  att <- attributes(x)
+  if ("na.action" %in% names(att)) {
+    cat(font_silver(paste0("(NA ", class(att$na.action), ": ", paste0(att$na.action, collapse = ", "), ")\n")))
+  }
 }
 
 #' @method summary mic
 #' @export
 #' @noRd
 summary.mic <- function(object, ...) {
-  x <- object
-  n_total <- length(x)
-  x <- x[!is.na(x)]
-  n <- length(x)
-  value <- c("Class" = "mic",
-             "<NA>" = n_total - n,
-             "Min." = as.character(sort(x)[1]),
-             "Max." = as.character(sort(x)[n]))
-  class(value) <- c("summaryDefault", "table")
-  value
+  summary(as.double(object), ...)
 }
 
-#' @method plot mic
+#' @method as.matrix mic
 #' @export
-#' @importFrom graphics barplot axis
-#' @rdname plot
-plot.mic <- function(x,
-                     main = paste("MIC values of", deparse(substitute(x))),
-                     ylab = "Frequency",
-                     xlab = "MIC value",
-                     axes = FALSE,
-                     ...) {
-  meet_criteria(main, allow_class = "character", has_length = 1)
-  meet_criteria(ylab, allow_class = "character", has_length = 1)
-  meet_criteria(xlab, allow_class = "character", has_length = 1)
-  meet_criteria(axes, allow_class = "logical", has_length = 1)
-  
-  barplot(table(as.double(x)),
-          ylab = ylab,
-          xlab = xlab,
-          axes = axes,
-          main = main,
-          ...)
-  axis(2, seq(0, max(table(as.double(x)))))
-}
-
-#' @method barplot mic
-#' @export
-#' @importFrom graphics barplot axis
-#' @rdname plot
-barplot.mic <- function(height,
-                        main = paste("MIC values of", deparse(substitute(height))),
-                        ylab = "Frequency",
-                        xlab = "MIC value",
-                        axes = FALSE,
-                        ...) {
-  meet_criteria(main, allow_class = "character", has_length = 1)
-  meet_criteria(ylab, allow_class = "character", has_length = 1)
-  meet_criteria(xlab, allow_class = "character", has_length = 1)
-  meet_criteria(axes, allow_class = "logical", has_length = 1)
-  
-  barplot(table(as.double(height)),
-          ylab = ylab,
-          xlab = xlab,
-          axes = axes,
-          main = main,
-          ...)
-  axis(2, seq(0, max(table(as.double(height)))))
+#' @noRd
+as.matrix.mic <- function(x, ...) {
+  as.matrix(as.double(x), ...)
 }
 
 #' @method [ mic
@@ -321,14 +322,446 @@ unique.mic <- function(x, incomparables = FALSE, ...) {
   y
 }
 
+#' @method sort mic
+#' @export
+#' @noRd
+sort.mic <- function(x, decreasing = FALSE, ...) {
+  if (decreasing == TRUE) {
+    ord <- order(-as.double(x))
+  } else {
+    ord <- order(as.double(x))
+  }
+  x[ord]
+}
+
+#' @method hist mic
+#' @importFrom graphics hist
+#' @export
+#' @noRd
+hist.mic <- function(x, ...) {
+  warning_("Use `plot()` or `ggplot()` for optimal plotting of MIC values", call = FALSE)
+  hist(log2(x))
+}
+
 # will be exported using s3_register() in R/zzz.R
 get_skimmers.mic <- function(column) {
   skimr::sfl(
     skim_type = "mic",
-    min = ~as.character(sort(stats::na.omit(.))[1]),
-    max = ~as.character(sort(stats::na.omit(.))[length(stats::na.omit(.))]),
-    median = ~as.character(stats::na.omit(.)[as.double(stats::na.omit(.)) == median(as.double(stats::na.omit(.)))])[1],
+    min = ~min(., na.rm = TRUE),
+    max = ~max(., na.rm = TRUE),
+    median = ~stats::median(., na.rm = TRUE),
     n_unique = ~pm_n_distinct(., na.rm = TRUE),
-    hist_log2 = ~skimr::inline_hist(log2(as.double(stats::na.omit(.))))
+    hist_log2 = ~skimr::inline_hist(log2(stats::na.omit(.)))
   )
 }
+
+# Miscellaneous mathematical functions ------------------------------------
+
+#' @method mean mic
+#' @export
+#' @noRd
+mean.mic <- function(x, trim = 0, na.rm = FALSE, ...) {
+  mean(as.double(x), trim = trim, na.rm = na.rm, ...)
+}
+
+#' @method median mic
+#' @importFrom stats median
+#' @export
+#' @noRd
+median.mic <- function(x, na.rm = FALSE, ...) {
+  median(as.double(x), na.rm = na.rm, ...)
+}
+
+#' @method quantile mic
+#' @importFrom stats quantile
+#' @export
+#' @noRd
+quantile.mic <- function(x, probs = seq(0, 1, 0.25), na.rm = FALSE,
+                         names = TRUE, type = 7, ...) {
+  quantile(as.double(x), probs = probs, na.rm = na.rm, names = names, type = type, ...)
+}
+
+# Math (see ?groupGeneric) ----------------------------------------------
+
+#' @method abs mic
+#' @export
+#' @noRd
+abs.mic <- function(x) {
+  abs(as.double(x))
+}
+#' @method sign mic
+#' @export
+#' @noRd
+sign.mic <- function(x) {
+  sign(as.double(x))
+}
+#' @method sqrt mic
+#' @export
+#' @noRd
+sqrt.mic <- function(x) {
+  sqrt(as.double(x))
+}
+#' @method floor mic
+#' @export
+#' @noRd
+floor.mic <- function(x) {
+  floor(as.double(x))
+}
+#' @method ceiling mic
+#' @export
+#' @noRd
+ceiling.mic <- function(x) {
+  ceiling(as.double(x))
+}
+#' @method trunc mic
+#' @export
+#' @noRd
+trunc.mic <- function(x, ...) {
+  trunc(as.double(x), ...)
+}
+#' @method round mic
+#' @export
+#' @noRd
+round.mic <- function(x, digits = 0) {
+  round(as.double(x), digits = digits)
+}
+#' @method signif mic
+#' @export
+#' @noRd
+signif.mic <- function(x, digits = 6) {
+  signif(as.double(x), digits = digits)
+}
+#' @method exp mic
+#' @export
+#' @noRd
+exp.mic <- function(x) {
+  exp(as.double(x))
+}
+#' @method log mic
+#' @export
+#' @noRd
+log.mic <- function(x, base = exp(1)) {
+  log(as.double(x), base = base)
+}
+#' @method log10 mic
+#' @export
+#' @noRd
+log10.mic <- function(x) {
+  log10(as.double(x))
+}
+#' @method log2 mic
+#' @export
+#' @noRd
+log2.mic <- function(x) {
+  log2(as.double(x))
+}
+#' @method expm1 mic
+#' @export
+#' @noRd
+expm1.mic <- function(x) {
+  expm1(as.double(x))
+}
+#' @method log1p mic
+#' @export
+#' @noRd
+log1p.mic <- function(x) {
+  log1p(as.double(x))
+}
+#' @method cos mic
+#' @export
+#' @noRd
+cos.mic <- function(x) {
+  cos(as.double(x))
+}
+#' @method sin mic
+#' @export
+#' @noRd
+sin.mic <- function(x) {
+  sin(as.double(x))
+}
+#' @method tan mic
+#' @export
+#' @noRd
+tan.mic <- function(x) {
+  tan(as.double(x))
+}
+#' @method cospi mic
+#' @export
+#' @noRd
+cospi.mic <- function(x) {
+  cospi(as.double(x))
+}
+#' @method sinpi mic
+#' @export
+#' @noRd
+sinpi.mic <- function(x) {
+  sinpi(as.double(x))
+}
+#' @method tanpi mic
+#' @export
+#' @noRd
+tanpi.mic <- function(x) {
+  tanpi(as.double(x))
+}
+#' @method acos mic
+#' @export
+#' @noRd
+acos.mic <- function(x) {
+  acos(as.double(x))
+}
+#' @method asin mic
+#' @export
+#' @noRd
+asin.mic <- function(x) {
+  asin(as.double(x))
+}
+#' @method atan mic
+#' @export
+#' @noRd
+atan.mic <- function(x) {
+  atan(as.double(x))
+}
+#' @method cosh mic
+#' @export
+#' @noRd
+cosh.mic <- function(x) {
+  cosh(as.double(x))
+}
+#' @method sinh mic
+#' @export
+#' @noRd
+sinh.mic <- function(x) {
+  sinh(as.double(x))
+}
+#' @method tanh mic
+#' @export
+#' @noRd
+tanh.mic <- function(x) {
+  tanh(as.double(x))
+}
+#' @method acosh mic
+#' @export
+#' @noRd
+acosh.mic <- function(x) {
+  acosh(as.double(x))
+}
+#' @method asinh mic
+#' @export
+#' @noRd
+asinh.mic <- function(x) {
+  asinh(as.double(x))
+}
+#' @method atanh mic
+#' @export
+#' @noRd
+atanh.mic <- function(x) {
+  atanh(as.double(x))
+}
+#' @method lgamma mic
+#' @export
+#' @noRd
+lgamma.mic <- function(x) {
+  lgamma(as.double(x))
+}
+#' @method gamma mic
+#' @export
+#' @noRd
+gamma.mic <- function(x) {
+  gamma(as.double(x))
+}
+#' @method digamma mic
+#' @export
+#' @noRd
+digamma.mic <- function(x) {
+  digamma(as.double(x))
+}
+#' @method trigamma mic
+#' @export
+#' @noRd
+trigamma.mic <- function(x) {
+  trigamma(as.double(x))
+}
+#' @method cumsum mic
+#' @export
+#' @noRd
+cumsum.mic <- function(x) {
+  cumsum(as.double(x))
+}
+#' @method cumprod mic
+#' @export
+#' @noRd
+cumprod.mic <- function(x) {
+  cumprod(as.double(x))
+}
+#' @method cummax mic
+#' @export
+#' @noRd
+cummax.mic <- function(x) {
+  cummax(as.double(x))
+}
+#' @method cummin mic
+#' @export
+#' @noRd
+cummin.mic <- function(x) {
+  cummin(as.double(x))
+}
+
+# Ops (see ?groupGeneric) -----------------------------------------------
+
+
+#' @method + mic
+#' @export
+#' @noRd
+`+.mic` <- function(e1, e2) {
+  as.double(e1) + as.double(e2)
+}
+
+#' @method - mic
+#' @export
+#' @noRd
+`-.mic` <- function(e1, e2) {
+  as.double(e1) - as.double(e2)
+}
+
+#' @method * mic
+#' @export
+#' @noRd
+`*.mic` <- function(e1, e2) {
+  as.double(e1) * as.double(e2)
+}
+
+#' @method / mic
+#' @export
+#' @noRd
+`/.mic` <- function(e1, e2) {
+  as.double(e1) / as.double(e2)
+}
+
+#' @method ^ mic
+#' @export
+#' @noRd
+`^.mic` <- function(e1, e2) {
+  as.double(e1) ^ as.double(e2)
+}
+
+#' @method %% mic
+#' @export
+#' @noRd
+`%%.mic` <- function(e1, e2) {
+  as.double(e1) %% as.double(e2)
+}
+
+#' @method %/% mic
+#' @export
+#' @noRd
+`%/%.mic` <- function(e1, e2) {
+  as.double(e1) %/% as.double(e2)
+}
+
+#' @method & mic
+#' @export
+#' @noRd
+`&.mic` <- function(e1, e2) {
+  as.double(e1) & as.double(e2)
+}
+
+#' @method | mic
+#' @export
+#' @noRd
+`|.mic` <- function(e1, e2) {
+  as.double(e1) | as.double(e2)
+}
+
+#' @method ! mic
+#' @export
+#' @noRd
+`!.mic` <- function(x) {
+  !as.double(x)
+}
+
+#' @method == mic
+#' @export
+#' @noRd
+`==.mic` <- function(e1, e2) {
+  as.double(e1) == as.double(e2)
+}
+
+#' @method != mic
+#' @export
+#' @noRd
+`!=.mic` <- function(e1, e2) {
+  as.double(e1) != as.double(e2)
+}
+
+#' @method < mic
+#' @export
+#' @noRd
+`<.mic` <- function(e1, e2) {
+  as.double(e1) < as.double(e2)
+}
+
+#' @method <= mic
+#' @export
+#' @noRd
+`<=.mic` <- function(e1, e2) {
+  as.double(e1) <= as.double(e2)
+}
+
+#' @method >= mic
+#' @export
+#' @noRd
+`>=.mic` <- function(e1, e2) {
+  as.double(e1) >= as.double(e2)
+}
+
+#' @method > mic
+#' @export
+#' @noRd
+`>.mic` <- function(e1, e2) {
+  as.double(e1) > as.double(e2)
+}
+
+# Summary (see ?groupGeneric) -------------------------------------------
+
+#' @method all mic
+#' @export
+#' @noRd
+all.mic <- function(..., na.rm = FALSE) {
+  all(as.double(c(...)), na.rm = na.rm)
+}
+#' @method any mic
+#' @export
+#' @noRd
+any.mic <- function(..., na.rm = FALSE) {
+  any(as.double(c(...)), na.rm = na.rm)
+}
+#' @method sum mic
+#' @export
+#' @noRd
+sum.mic <- function(..., na.rm = FALSE) {
+  sum(as.double(c(...)), na.rm = na.rm)
+}
+#' @method prod mic
+#' @export
+#' @noRd
+prod.mic <- function(..., na.rm = FALSE) {
+  prod(as.double(c(...)), na.rm = na.rm)
+}
+#' @method min mic
+#' @export
+#' @noRd
+min.mic <- function(..., na.rm = FALSE) {
+  min(as.double(c(...)), na.rm = na.rm)
+}
+#' @method max mic
+#' @export
+#' @noRd
+max.mic <- function(..., na.rm = FALSE) {
+  max(as.double(c(...)), na.rm = na.rm)
+}
+#' @method range mic
+#' @export
+#' @noRd
+range.mic <- function(..., na.rm = FALSE) {
+  range(as.double(c(...)), na.rm = na.rm)
+}

R/mo.R

@@ -106,7 +106,9 @@
 #' 2. Becker K *et al.* **Implications of identifying the recently defined members of the *S. aureus* complex, *S. argenteus* and *S. schweitzeri*: A position paper of members of the ESCMID Study Group for staphylococci and Staphylococcal Diseases (ESGS).** 2019. Clin Microbiol Infect; \doi{10.1016/j.cmi.2019.02.028}
 #' 3. Becker K *et al.* **Emergence of coagulase-negative staphylococci** 2020. Expert Rev Anti Infect Ther. 18(4):349-366; \doi{10.1080/14787210.2020.1730813}
 #' 4. Lancefield RC **A serological differentiation of human and other groups of hemolytic streptococci**. 1933. J Exp Med. 57(4): 571–95; \doi{10.1084/jem.57.4.571}
-#' 5. Catalogue of Life: Annual Checklist (public online taxonomic database), <http://www.catalogueoflife.org> (check included annual version with [catalogue_of_life_version()]).
+#' 5. `r gsub("{year}", CATALOGUE_OF_LIFE$year, CATALOGUE_OF_LIFE$version, fixed = TRUE)`, <http://www.catalogueoflife.org>
+#' 6. List of Prokaryotic names with Standing in Nomenclature (`r CATALOGUE_OF_LIFE$yearmonth_LPSN`), \doi{10.1099/ijsem.0.004332}
+#' 7. `r SNOMED_VERSION$current_source`, retrieved from the `r SNOMED_VERSION$title`, OID `r SNOMED_VERSION$current_oid`, version `r SNOMED_VERSION$current_version`; url: <`r SNOMED_VERSION$url`>
 #' @export
 #' @return A [character] [vector] with additional class [`mo`]
 #' @seealso [microorganisms] for the [data.frame] that is being used to determine ID's.
@@ -463,16 +465,22 @@ exec_as.mo <- function(x,
     # translate 'unknown' names back to English
     if (any(x %like% "unbekannt|onbekend|desconocid|sconosciut|iconnu|desconhecid", na.rm = TRUE)) {
       trns <- subset(translations_file, pattern %like% "unknown" | affect_mo_name == TRUE)
-      lapply(seq_len(nrow(trns)),
-             function(i) x <<- gsub(pattern = trns$replacement[i],
-                                    replacement = trns$pattern[i],
-                                    x = x,
-                                    ignore.case = TRUE,
-                                    perl = TRUE))
+      langs <- LANGUAGES_SUPPORTED[LANGUAGES_SUPPORTED != "en"]
+      for (l in langs) {
+        for (i in seq_len(nrow(trns))) {
+          if (!is.na(trns[i, l, drop = TRUE])) {
+            x <- gsub(pattern = trns[i, l, drop = TRUE],
+                      replacement = trns$pattern[i],
+                      x = x,
+                      ignore.case = TRUE,
+                      perl = TRUE)
+          }
+        }
+      }
     }
     
     x_backup <- x
-
+    
     # from here on case-insensitive
     x <- tolower(x)
     
@@ -711,8 +719,8 @@ exec_as.mo <- function(x,
         }
         
         # translate known trivial abbreviations to genus + species ----
-        if (toupper(x_backup_without_spp[i]) %in% c("MRSA", "MSSA", "VISA", "VRSA", "BORSA")
-            | x_backup_without_spp[i] %like_case% "(^| )(mrsa|mssa|visa|vrsa|borsa|la-?mrsa|ca-?mrsa)( |$)") {
+        if (toupper(x_backup_without_spp[i]) %in% c("MRSA", "MSSA", "VISA", "VRSA", "BORSA", "GISA")
+            | x_backup_without_spp[i] %like_case% "(^| )(mrsa|mssa|visa|vrsa|borsa|gisa|la-?mrsa|ca-?mrsa)( |$)") {
           x[i] <- lookup(fullname == "Staphylococcus aureus", uncertainty = -1)
           next
         }
@@ -1468,8 +1476,8 @@ exec_as.mo <- function(x,
         if (length(uncertainties$input) > 1) {
           plural <- c("s", "them", "were")
         }
-        msg <- paste0("Translation to ", nr2char(length(uncertainties$input)), " microorganism", plural[1],
-                      " was guessed with uncertainty. Use `mo_uncertainties()` to review ", plural[2], ".")
+        msg <- paste0("Translation is uncertain of ", nr2char(length(uncertainties$input)), " microorganism", plural[1],
+                      ". Use `mo_uncertainties()` to review ", plural[2], ".")
         message_(msg)
       }
       x[already_known] <- x_known
@@ -1551,6 +1559,9 @@ exec_as.mo <- function(x,
   if (property == "mo") {
     x <- set_clean_class(x, new_class = c("mo", "character"))
   }
+  
+  # keep track of time
+  end_time <- Sys.time()
 
   if (length(mo_renamed()) > 0) {
     print(mo_renamed())
@@ -1571,10 +1582,9 @@ exec_as.mo <- function(x,
     x <- structure(x, uncertainties = uncertainties)
   } else {
     # keep track of time - give some hints to improve speed if it takes a long time
-    end_time <- Sys.time()
     delta_time <- difftime(end_time, start_time, units = "secs")
     if (delta_time >= 30) {
-      message_("Using `as.mo()` took ", delta_time, " seconds, which is a long time. Some suggestions to improve speed include:")
+      message_("Using `as.mo()` took ", round(delta_time), " seconds, which is a long time. Some suggestions to improve speed include:")
       message_(word_wrap("- Try to use as many valid taxonomic names as possible for your input.",
                          extra_indent = 2),
                as_note = FALSE)
@@ -1922,7 +1932,7 @@ print.mo_renamed <- function(x, ...) {
                     "",
                     paste0(" (",  gsub("et al.", font_italic("et al."), x$old_ref[i]), ")")),
              " was renamed ",
-             ifelse(as.integer(gsub("[^0-9]", "", x$new_ref[i])) < as.integer(gsub("[^0-9]", "", x$old_ref[i])),
+             ifelse(!x$new_ref[i] %in% c("", NA) && as.integer(gsub("[^0-9]", "", x$new_ref[i])) < as.integer(gsub("[^0-9]", "", x$old_ref[i])),
                     font_bold("back to "),
                     ""),
              font_italic(x$new_name[i]),

R/mo_matching_score.R

@@ -44,7 +44,7 @@
 #' * \ifelse{html}{\out{<i>p<sub>n</sub></i> is the human pathogenic prevalence group of <i>n</i>, as described below;}}{p_n is the human pathogenic prevalence group of \eqn{n}, as described below;}
 #' * \ifelse{html}{\out{<i>k<sub>n</sub></i> is the taxonomic kingdom of <i>n</i>, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.}}{l_n is the taxonomic kingdom of \eqn{n}, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.}
 #' 
-#' The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. **Group 1** (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is *Enterococcus*, *Staphylococcus* or *Streptococcus*. This group consequently contains all common Gram-negative bacteria, such as *Pseudomonas* and *Legionella* and all species within the order Enterobacterales. **Group 2** consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is *Absidia*, *Acremonium*, *Actinotignum*, *Alternaria*, *Anaerosalibacter*, *Apophysomyces*, *Arachnia*, *Aspergillus*, *Aureobacterium*, *Aureobasidium*, *Bacteroides*, *Basidiobolus*, *Beauveria*, *Blastocystis*, *Branhamella*, *Calymmatobacterium*, *Candida*, *Capnocytophaga*, *Catabacter*, *Chaetomium*, *Chryseobacterium*, *Chryseomonas*, *Chrysonilia*, *Cladophialophora*, *Cladosporium*, *Conidiobolus*, *Cryptococcus*, *Curvularia*, *Exophiala*, *Exserohilum*, *Flavobacterium*, *Fonsecaea*, *Fusarium*, *Fusobacterium*, *Hendersonula*, *Hypomyces*, *Koserella*, *Lelliottia*, *Leptosphaeria*, *Leptotrichia*, *Malassezia*, *Malbranchea*, *Mortierella*, *Mucor*, *Mycocentrospora*, *Mycoplasma*, *Nectria*, *Ochroconis*, *Oidiodendron*, *Phoma*, *Piedraia*, *Pithomyces*, *Pityrosporum*, *Prevotella*,\\*Pseudallescheria*, *Rhizomucor*, *Rhizopus*, *Rhodotorula*, *Scolecobasidium*, *Scopulariopsis*, *Scytalidium*,*Sporobolomyces*, *Stachybotrys*, *Stomatococcus*, *Treponema*, *Trichoderma*, *Trichophyton*, *Trichosporon*, *Tritirachium* or *Ureaplasma*. **Group 3** consists of all other microorganisms.
+#' The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. **Group 1** (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is *Enterococcus*, *Staphylococcus* or *Streptococcus*. This group consequently contains all common Gram-negative bacteria, such as *Pseudomonas* and *Legionella* and all species within the order Enterobacterales. **Group 2** consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is *Absidia*, *Acremonium*, *Actinotignum*, *Alternaria*, *Anaerosalibacter*, *Apophysomyces*, *Arachnia*, *Aspergillus*, *Aureobacterium*, *Aureobasidium*, *Bacteroides*, *Basidiobolus*, *Beauveria*, *Blastocystis*, *Branhamella*, *Calymmatobacterium*, *Candida*, *Capnocytophaga*, *Catabacter*, *Chaetomium*, *Chryseobacterium*, *Chryseomonas*, *Chrysonilia*, *Cladophialophora*, *Cladosporium*, *Conidiobolus*, *Cryptococcus*, *Curvularia*, *Exophiala*, *Exserohilum*, *Flavobacterium*, *Fonsecaea*, *Fusarium*, *Fusobacterium*, *Hendersonula*, *Hypomyces*, *Koserella*, *Lelliottia*, *Leptosphaeria*, *Leptotrichia*, *Malassezia*, *Malbranchea*, *Mortierella*, *Mucor*, *Mycocentrospora*, *Mycoplasma*, *Nectria*, *Ochroconis*, *Oidiodendron*, *Phoma*, *Piedraia*, *Pithomyces*, *Pityrosporum*, *Prevotella*, *Pseudallescheria*, *Rhizomucor*, *Rhizopus*, *Rhodotorula*, *Scolecobasidium*, *Scopulariopsis*, *Scytalidium*,*Sporobolomyces*, *Stachybotrys*, *Stomatococcus*, *Treponema*, *Trichoderma*, *Trichophyton*, *Trichosporon*, *Tritirachium* or *Ureaplasma*. **Group 3** consists of all other microorganisms.
 #' 
 #' All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., `"E. coli"` will return the microbial ID of *Escherichia coli* (\eqn{m = `r round(mo_matching_score("E. coli", "Escherichia coli"), 3)`}, a highly prevalent microorganism found in humans) and not *Entamoeba coli* (\eqn{m = `r round(mo_matching_score("E. coli", "Entamoeba coli"), 3)`}, a less prevalent microorganism in humans), although the latter would alphabetically come first. 
 #' @export

R/mo_property.R

@@ -51,6 +51,8 @@
 #' All output [will be translated][translate] where possible.
 #'
 #' The function [mo_url()] will return the direct URL to the online database entry, which also shows the scientific reference of the concerned species.
+#' 
+#' SNOMED codes - [mo_snomed()] - are from the `r SNOMED_VERSION$current_source`. See the [microorganisms] data set for more info.
 #' @inheritSection mo_matching_score Matching Score for Microorganisms
 #' @inheritSection catalogue_of_life Catalogue of Life
 #' @inheritSection as.mo Source
@@ -60,7 +62,7 @@
 #' - An [integer] in case of [mo_year()]
 #' - A [list] in case of [mo_taxonomy()] and [mo_info()]
 #' - A named [character] in case of [mo_url()]
-#' - A [double] in case of [mo_snomed()]
+#' - A [numeric] in case of [mo_snomed()]
 #' - A [character] in all other cases
 #' @export
 #' @seealso [microorganisms]
@@ -161,7 +163,8 @@
 #' 
 #' # get a list with the complete taxonomy (from kingdom to subspecies)
 #' mo_taxonomy("E. coli")
-#' # get a list with the taxonomy, the authors, Gram-stain and URL to the online database
+#' # get a list with the taxonomy, the authors, Gram-stain,
+#' #   SNOMED codes, and URL to the online database
 #' mo_info("E. coli")
 #' }
 mo_name <- function(x, language = get_locale(), ...) {
@@ -629,7 +632,8 @@ mo_info <- function(x, language = get_locale(),  ...) {
       list(synonyms = mo_synonyms(y),
            gramstain = mo_gramstain(y, language = language),
            url = unname(mo_url(y, open = FALSE)),
-           ref = mo_ref(y))))
+           ref = mo_ref(y),
+           snomed = unlist(mo_snomed(y)))))
   if (length(info) > 1) {
     names(info) <- mo_name(x)
     result <- info
@@ -659,11 +663,21 @@ mo_url <- function(x, open = FALSE, language = get_locale(), ...) {
   df <- data.frame(mo, stringsAsFactors = FALSE) %pm>%
     pm_left_join(pm_select(microorganisms, mo, source, species_id), by = "mo")
   df$url <- ifelse(df$source == "CoL",
-                   paste0(catalogue_of_life$url_CoL, "details/species/id/", df$species_id, "/"),
-                   ifelse(df$source == "DSMZ",
-                          paste0(catalogue_of_life$url_DSMZ, "/advanced_search?adv[taxon-name]=", gsub(" ", "+", mo_names), "/"),
-                          NA_character_))
+                   paste0(CATALOGUE_OF_LIFE$url_CoL, "details/species/id/", df$species_id, "/"),
+                   NA_character_)
   u <- df$url
+  u[mo_kingdom(mo) == "Bacteria"] <- paste0(CATALOGUE_OF_LIFE$url_LPSN, "/species/", gsub(" ", "-", tolower(mo_names), fixed = TRUE))
+  u[mo_kingdom(mo) == "Bacteria" & mo_rank(mo) == "genus"] <- gsub("/species/",
+                                                                   "/genus/",
+                                                                   u[mo_kingdom(mo) == "Bacteria" & mo_rank(mo) == "genus"],
+                                                                   fixed = TRUE)
+  u[mo_kingdom(mo) == "Bacteria" &
+      mo_rank(mo) %in% c("subsp.", "infraspecies")] <- gsub("/species/",
+                                                            "/subspecies/",
+                                                            u[mo_kingdom(mo) == "Bacteria" &
+                                                                mo_rank(mo) %in% c("subsp.", "infraspecies")],
+                                                            fixed = TRUE)
+  
   names(u) <- mo_names
   
   if (open == TRUE) {

R/pca.R

@@ -26,7 +26,7 @@
 #' Principal Component Analysis (for AMR)
 #' 
 #' Performs a principal component analysis (PCA) based on a data set with automatic determination for afterwards plotting the groups and labels, and automatic filtering on only suitable (i.e. non-empty and numeric) variables.
-#' @inheritSection lifecycle Maturing Lifecycle
+#' @inheritSection lifecycle Stable Lifecycle
 #' @param x a [data.frame] containing numeric columns
 #' @param ... columns of `x` to be selected for PCA, can be unquoted since it supports quasiquotation.
 #' @inheritParams stats::prcomp

R/plot.R

@@ -0,0 +1,660 @@
+# ==================================================================== #
+# TITLE                                                                #
+# Antimicrobial Resistance (AMR) Data Analysis for R                   #
+#                                                                      #
+# SOURCE                                                               #
+# https://github.com/msberends/AMR                                     #
+#                                                                      #
+# LICENCE                                                              #
+# (c) 2018-2021 Berends MS, Luz CF et al.                              #
+# Developed at the University of Groningen, the Netherlands, in        #
+# collaboration with non-profit organisations Certe Medical            #
+# Diagnostics & Advice, and University Medical Center Groningen.       # 
+#                                                                      #
+# This R package is free software; you can freely use and distribute   #
+# it for both personal and commercial purposes under the terms of the  #
+# GNU General Public License version 2.0 (GNU GPL-2), as published by  #
+# the Free Software Foundation.                                        #
+# We created this package for both routine data analysis and academic  #
+# research and it was publicly released in the hope that it will be    #
+# useful, but it comes WITHOUT ANY WARRANTY OR LIABILITY.              #
+#                                                                      #
+# Visit our website for the full manual and a complete tutorial about  #
+# how to conduct AMR data analysis: https://msberends.github.io/AMR/   #
+# ==================================================================== #
+
+#' Plotting for Classes `rsi`, `mic` and `disk`
+#' 
+#' Functions to plot classes `rsi`, `mic` and `disk`, with support for base R and `ggplot2`.
+#' @inheritSection lifecycle Stable Lifecycle
+#' @inheritSection AMR Read more on Our Website!
+#' @param x,data MIC values created with [as.mic()] or disk diffusion values created with [as.disk()]
+#' @param mapping aesthetic mappings to use for [`ggplot()`][ggplot2::ggplot()]
+#' @param main,title title of the plot
+#' @param xlab,ylab axis title
+#' @param mo any (vector of) text that can be coerced to a valid microorganism code with [as.mo()]
+#' @param ab any (vector of) text that can be coerced to a valid antimicrobial code with [as.ab()]
+#' @param guideline interpretation guideline to use, defaults to the latest included EUCAST guideline, see *Details*
+#' @param colours_RSI colours to use for filling in the bars, must be a vector of three values (in the order R, S and I). The default colours are colour-blind friendly.
+#' @param language language to be used to translate 'Susceptible', 'Increased exposure'/'Intermediate' and 'Resistant', defaults to system language (see [get_locale()]) and can be overwritten by setting the option `AMR_locale`, e.g. `options(AMR_locale = "de")`, see [translate]. Use `language = NULL` or `language = ""` to prevent translation.
+#' @param expand logical to indicate whether the range on the x axis should be expanded between the lowest and highest value. For MIC values, intermediate values will be factors of 2 starting from the highest MIC value. For disk diameters, the whole diameter range will be filled.
+#' @details
+#' The interpretation of "I" will be named "Increased exposure" for all EUCAST guidelines since 2019, and will be named "Intermediate" in all other cases.
+#' 
+#' For interpreting MIC values as well as disk diffusion diameters, supported guidelines to be used as input for the `guideline` argument are: `r vector_and(AMR::rsi_translation$guideline, quotes = TRUE, reverse = TRUE)`.
+#' 
+#' Simply using `"CLSI"` or `"EUCAST"` as input will automatically select the latest version of that guideline.
+#' @name plot
+#' @rdname plot
+#' @return The `ggplot` functions return a [`ggplot`][ggplot2::ggplot()] model that is extendible with any `ggplot2` function.
+#' @param ... arguments passed on to [as.rsi()]
+#' @examples 
+#' some_mic_values <- random_mic(size = 100)
+#' some_disk_values <- random_disk(size = 100, mo = "Escherichia coli", ab = "cipro")
+#' some_rsi_values <- random_rsi(50, prob_RSI = c(0.30, 0.55, 0.05))
+#' 
+#' plot(some_mic_values)
+#' plot(some_disk_values)
+#' plot(some_rsi_values)
+#' 
+#' # when providing the microorganism and antibiotic, colours will show interpretations:
+#' plot(some_mic_values, mo = "S. aureus", ab = "ampicillin")
+#' plot(some_disk_values, mo = "Escherichia coli", ab = "cipro")
+#' 
+#' if (require("ggplot2")) {
+#'   ggplot(some_mic_values)
+#'   ggplot(some_disk_values, mo = "Escherichia coli", ab = "cipro")
+#'   ggplot(some_rsi_values)
+#' }
+NULL
+
+#' @method plot mic
+#' @importFrom graphics barplot axis mtext legend
+#' @export
+#' @rdname plot
+plot.mic <- function(x,
+                     main = paste("MIC values of", deparse(substitute(x))),
+                     ylab = "Frequency",
+                     xlab = "Minimum Inhibitory Concentration (mg/L)",
+                     mo = NULL,
+                     ab = NULL,
+                     guideline = "EUCAST",
+                     colours_RSI = c("#ED553B", "#3CAEA3", "#F6D55C"),
+                     language = get_locale(),
+                     expand = TRUE,
+                     ...) {
+  meet_criteria(main, allow_class = "character", has_length = 1, allow_NULL = TRUE)
+  meet_criteria(ylab, allow_class = "character", has_length = 1)
+  meet_criteria(xlab, allow_class = "character", has_length = 1)
+  meet_criteria(mo, allow_class = c("mo", "character"), allow_NULL = TRUE)
+  meet_criteria(ab, allow_class = c("ab", "character"), allow_NULL = TRUE)
+  meet_criteria(guideline, allow_class = "character", has_length = 1)
+  meet_criteria(colours_RSI, allow_class = "character", has_length = c(1, 3))
+  meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
+  meet_criteria(expand, allow_class = "logical", has_length = 1)
+  
+  if (length(colours_RSI) == 1) {
+    colours_RSI <- rep(colours_RSI, 3)
+  }
+  main <- gsub(" +", " ", paste0(main, collapse = " "))
+  
+  x <- plot_prepare_table(x, expand = expand)
+  
+  cols_sub <- plot_colours_subtitle_guideline(x = x, 
+                                              mo = mo, 
+                                              ab = ab,
+                                              guideline = guideline,
+                                              colours_RSI = colours_RSI, 
+                                              fn = as.mic,
+                                              language = language,
+                                              ...)
+  barplot(x,
+          col = cols_sub$cols,
+          main = main,
+          ylim = c(0, max(x) * ifelse(any(colours_RSI %in% cols_sub$cols), 1.1, 1)),
+          ylab = ylab,
+          xlab = xlab,
+          axes = FALSE)
+  axis(2, seq(0, max(x)))
+  if (!is.null(cols_sub$sub)) {
+    mtext(side = 3, line = 0.5, adj = 0.5, cex = 0.75, cols_sub$sub)
+  }
+  
+  if (any(colours_RSI %in% cols_sub$cols)) {
+    legend_txt <- character(0)
+    legend_col <- character(0)
+    if (any(cols_sub$cols == colours_RSI[2] & cols_sub$count > 0)) {
+      legend_txt <- "Susceptible"
+      legend_col <- colours_RSI[2]
+    }
+    if (any(cols_sub$cols == colours_RSI[3] & cols_sub$count > 0)) {
+      legend_txt <- c(legend_txt, plot_name_of_I(cols_sub$guideline))
+      legend_col <- c(legend_col, colours_RSI[3])
+    }
+    if (any(cols_sub$cols == colours_RSI[1] & cols_sub$count > 0)) {
+      legend_txt <- c(legend_txt, "Resistant")
+      legend_col <- c(legend_col, colours_RSI[1])
+    }
+    legend("top", 
+           x.intersp = 0.5,
+           legend = translate_AMR(legend_txt, language = language),
+           fill = legend_col,
+           horiz = TRUE,
+           cex = 0.75, 
+           box.lwd = 0, 
+           bg = "#FFFFFF55")
+  }
+}
+
+#' @method barplot mic
+#' @export
+#' @noRd
+barplot.mic <- function(height,
+                        main = paste("MIC values of", deparse(substitute(height))),
+                        ylab = "Frequency",
+                        xlab = "Minimum Inhibitory Concentration (mg/L)",
+                        mo = NULL,
+                        ab = NULL,
+                        guideline = "EUCAST",
+                        colours_RSI = c("#ED553B", "#3CAEA3", "#F6D55C"),
+                        language = get_locale(),
+                        expand = TRUE,
+                        ...) {
+  meet_criteria(main, allow_class = "character", has_length = 1, allow_NULL = TRUE)
+  meet_criteria(ylab, allow_class = "character", has_length = 1)
+  meet_criteria(xlab, allow_class = "character", has_length = 1)
+  meet_criteria(mo, allow_class = c("mo", "character"), allow_NULL = TRUE)
+  meet_criteria(ab, allow_class = c("ab", "character"), allow_NULL = TRUE)
+  meet_criteria(guideline, allow_class = "character", has_length = 1)
+  meet_criteria(colours_RSI, allow_class = "character", has_length = c(1, 3))
+  meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
+  meet_criteria(expand, allow_class = "logical", has_length = 1)
+  
+  main <- gsub(" +", " ", paste0(main, collapse = " "))
+  
+  plot(x = height,
+       main = main,
+       ylab = ylab,
+       xlab = xlab,
+       mo = mo,
+       ab = ab,
+       guideline = guideline,
+       colours_RSI = colours_RSI,
+       ...)
+}
+
+#' @method ggplot mic
+#' @rdname plot
+# will be exported using s3_register() in R/zzz.R
+ggplot.mic <- function(data,
+                       mapping = NULL,
+                       title = paste("MIC values of", deparse(substitute(data))),
+                       ylab = "Frequency",
+                       xlab = "Minimum Inhibitory Concentration (mg/L)",
+                       mo = NULL,
+                       ab = NULL,
+                       guideline = "EUCAST",
+                       colours_RSI = c("#ED553B", "#3CAEA3", "#F6D55C"),
+                       language = get_locale(),
+                       expand = TRUE,
+                       ...) {
+  stop_ifnot_installed("ggplot2")
+  meet_criteria(title, allow_class = "character", allow_NULL = TRUE)
+  meet_criteria(ylab, allow_class = "character", has_length = 1)
+  meet_criteria(xlab, allow_class = "character", has_length = 1)
+  meet_criteria(mo, allow_class = c("mo", "character"), allow_NULL = TRUE)
+  meet_criteria(ab, allow_class = c("ab", "character"), allow_NULL = TRUE)
+  meet_criteria(guideline, allow_class = "character", has_length = 1)
+  meet_criteria(colours_RSI, allow_class = "character", has_length = c(1, 3))
+  meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
+  meet_criteria(expand, allow_class = "logical", has_length = 1)
+  
+  if ("main" %in% names(list(...))) {
+    title <- list(...)$main
+  }
+  if (!is.null(title)) {
+    title <- gsub(" +", " ", paste0(title, collapse = " "))
+  }
+  
+  x <- plot_prepare_table(data, expand = expand)
+  cols_sub <- plot_colours_subtitle_guideline(x = x, 
+                                              mo = mo, 
+                                              ab = ab,
+                                              guideline = guideline,
+                                              colours_RSI = colours_RSI, 
+                                              fn = as.mic,
+                                              language = language,
+                                              ...)
+  df <- as.data.frame(x, stringsAsFactors = TRUE)
+  colnames(df) <- c("mic", "count")
+  df$cols <- cols_sub$cols
+  df$cols[df$cols == colours_RSI[1]] <- "Resistant"
+  df$cols[df$cols == colours_RSI[2]] <- "Susceptible"
+  df$cols[df$cols == colours_RSI[3]] <- plot_name_of_I(cols_sub$guideline)
+  df$cols <- factor(translate_AMR(df$cols, language = language),
+                    levels = translate_AMR(c("Susceptible", plot_name_of_I(cols_sub$guideline), "Resistant"),
+                                           language = language),
+                    ordered = TRUE)
+  if (!is.null(mapping)) {
+    p <- ggplot2::ggplot(df, mapping = mapping)
+  } else {
+    p <- ggplot2::ggplot(df)
+  }
+  
+  if (any(colours_RSI %in% cols_sub$cols)) {
+    vals <- c("Resistant" = colours_RSI[1],
+              "Susceptible" = colours_RSI[2],
+              "Incr. exposure" = colours_RSI[3],
+              "Intermediate" = colours_RSI[3])
+    names(vals) <- translate_AMR(names(vals), language = language)
+    p <- p +
+      ggplot2::geom_col(ggplot2::aes(x = mic, y = count, fill = cols)) + 
+      ggplot2::scale_fill_manual(values = vals,
+                                 name = NULL)
+  } else {
+    p <- p +
+      ggplot2::geom_col(ggplot2::aes(x = mic, y = count))
+  }
+  
+  p +
+    ggplot2::labs(title = title, x = xlab, y = ylab, subtitle = cols_sub$sub)
+}
+
+#' @method plot disk
+#' @export
+#' @importFrom graphics barplot axis mtext legend
+#' @rdname plot
+plot.disk <- function(x,
+                      main = paste("Disk zones of", deparse(substitute(x))),
+                      ylab = "Frequency",
+                      xlab = "Disk diffusion diameter (mm)",
+                      mo = NULL,
+                      ab = NULL,
+                      guideline = "EUCAST",
+                      colours_RSI = c("#ED553B", "#3CAEA3", "#F6D55C"),
+                      language = get_locale(),
+                      expand = TRUE,
+                      ...) {
+  meet_criteria(main, allow_class = "character", has_length = 1, allow_NULL = TRUE)
+  meet_criteria(ylab, allow_class = "character", has_length = 1)
+  meet_criteria(xlab, allow_class = "character", has_length = 1)
+  meet_criteria(mo, allow_class = c("mo", "character"), allow_NULL = TRUE)
+  meet_criteria(ab, allow_class = c("ab", "character"), allow_NULL = TRUE)
+  meet_criteria(guideline, allow_class = "character", has_length = 1)
+  meet_criteria(colours_RSI, allow_class = "character", has_length = c(1, 3))
+  meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
+  meet_criteria(expand, allow_class = "logical", has_length = 1)
+  
+  if (length(colours_RSI) == 1) {
+    colours_RSI <- rep(colours_RSI, 3)
+  }
+  main <- gsub(" +", " ", paste0(main, collapse = " "))
+  
+  x <- plot_prepare_table(x, expand = expand)
+  
+  cols_sub <- plot_colours_subtitle_guideline(x = x, 
+                                              mo = mo, 
+                                              ab = ab,
+                                              guideline = guideline,
+                                              colours_RSI = colours_RSI, 
+                                              fn = as.disk,
+                                              language = language,
+                                              ...)
+  
+  barplot(x,
+          col = cols_sub$cols,
+          main = main,
+          ylim = c(0, max(x) * ifelse(any(colours_RSI %in% cols_sub$cols), 1.1, 1)),
+          ylab = ylab,
+          xlab = xlab,
+          axes = FALSE)
+  axis(2, seq(0, max(x)))
+  if (!is.null(cols_sub$sub)) {
+    mtext(side = 3, line = 0.5, adj = 0.5, cex = 0.75, cols_sub$sub)
+  }
+  
+  if (any(colours_RSI %in% cols_sub$cols)) {
+    legend_txt <- character(0)
+    legend_col <- character(0)
+    if (any(cols_sub$cols == colours_RSI[1] & cols_sub$count > 0)) {
+      legend_txt <- "Resistant"
+      legend_col <- colours_RSI[1]
+    }
+    if (any(cols_sub$cols == colours_RSI[3] & cols_sub$count > 0)) {
+      legend_txt <- c(legend_txt, plot_name_of_I(cols_sub$guideline))
+      legend_col <- c(legend_col, colours_RSI[3])
+    }
+    if (any(cols_sub$cols == colours_RSI[2] & cols_sub$count > 0)) {
+      legend_txt <- c(legend_txt, "Susceptible")
+      legend_col <- c(legend_col, colours_RSI[2])
+    }
+    legend("top", 
+           x.intersp = 0.5,
+           legend = translate_AMR(legend_txt, language = language),
+           fill = legend_col,
+           horiz = TRUE,
+           cex = 0.75, 
+           box.lwd = 0, 
+           bg = "#FFFFFF55")
+  }
+}
+
+#' @method barplot disk
+#' @export
+#' @noRd
+barplot.disk <- function(height,
+                         main = paste("Disk zones of", deparse(substitute(height))),
+                         ylab = "Frequency",
+                         xlab = "Disk diffusion diameter (mm)",
+                         mo = NULL,
+                         ab = NULL,
+                         guideline = "EUCAST",
+                         colours_RSI = c("#ED553B", "#3CAEA3", "#F6D55C"),
+                         language = get_locale(),
+                         expand = TRUE,
+                         ...) {
+  meet_criteria(main, allow_class = "character", has_length = 1, allow_NULL = TRUE)
+  meet_criteria(ylab, allow_class = "character", has_length = 1)
+  meet_criteria(xlab, allow_class = "character", has_length = 1)
+  meet_criteria(mo, allow_class = c("mo", "character"), allow_NULL = TRUE)
+  meet_criteria(ab, allow_class = c("ab", "character"), allow_NULL = TRUE)
+  meet_criteria(guideline, allow_class = "character", has_length = 1)
+  meet_criteria(colours_RSI, allow_class = "character", has_length = c(1, 3))
+  meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
+  meet_criteria(expand, allow_class = "logical", has_length = 1)
+  
+  main <- gsub(" +", " ", paste0(main, collapse = " "))
+  
+  plot(x = height,
+       main = main,
+       ylab = ylab,
+       xlab = xlab,
+       mo = mo,
+       ab = ab,
+       guideline = guideline,
+       colours_RSI = colours_RSI,
+       ...)
+}
+
+#' @method ggplot disk
+#' @rdname plot
+# will be exported using s3_register() in R/zzz.R
+ggplot.disk <- function(data,
+                        mapping = NULL,
+                        title = paste("Disk zones of", deparse(substitute(data))),
+                        ylab = "Frequency",
+                        xlab = "Disk diffusion diameter (mm)",
+                        mo = NULL,
+                        ab = NULL,
+                        guideline = "EUCAST",
+                        colours_RSI = c("#ED553B", "#3CAEA3", "#F6D55C"),
+                        language = get_locale(),
+                        expand = TRUE,
+                        ...) {
+  stop_ifnot_installed("ggplot2")
+  meet_criteria(title, allow_class = "character", allow_NULL = TRUE)
+  meet_criteria(ylab, allow_class = "character", has_length = 1)
+  meet_criteria(xlab, allow_class = "character", has_length = 1)
+  meet_criteria(mo, allow_class = c("mo", "character"), allow_NULL = TRUE)
+  meet_criteria(ab, allow_class = c("ab", "character"), allow_NULL = TRUE)
+  meet_criteria(guideline, allow_class = "character", has_length = 1)
+  meet_criteria(colours_RSI, allow_class = "character", has_length = c(1, 3))
+  meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
+  meet_criteria(expand, allow_class = "logical", has_length = 1)
+  
+  if ("main" %in% names(list(...))) {
+    title <- list(...)$main
+  }
+  if (!is.null(title)) {
+    title <- gsub(" +", " ", paste0(title, collapse = " "))
+  }
+  
+  x <- plot_prepare_table(data, expand = expand)
+  cols_sub <- plot_colours_subtitle_guideline(x = x,
+                                              mo = mo,
+                                              ab = ab,
+                                              guideline = guideline,
+                                              colours_RSI = colours_RSI,
+                                              fn = as.disk,
+                                              language = language,
+                                              ...)
+  df <- as.data.frame(x, stringsAsFactors = TRUE)
+  colnames(df) <- c("disk", "count")
+  df$cols <- cols_sub$cols
+  
+  df$cols[df$cols == colours_RSI[1]] <- "Resistant"
+  df$cols[df$cols == colours_RSI[2]] <- "Susceptible"
+  df$cols[df$cols == colours_RSI[3]] <- plot_name_of_I(cols_sub$guideline)
+  df$cols <- factor(translate_AMR(df$cols, language = language),
+                    levels = translate_AMR(c("Susceptible", plot_name_of_I(cols_sub$guideline), "Resistant"),
+                                           language = language),
+                    ordered = TRUE)
+  if (!is.null(mapping)) {
+    p <- ggplot2::ggplot(df, mapping = mapping)
+  } else {
+    p <- ggplot2::ggplot(df)
+  }
+  
+  if (any(colours_RSI %in% cols_sub$cols)) {
+    vals <- c("Resistant" = colours_RSI[1],
+              "Susceptible" = colours_RSI[2],
+              "Incr. exposure" = colours_RSI[3],
+              "Intermediate" = colours_RSI[3])
+    names(vals) <- translate_AMR(names(vals), language = language)
+    p <- p +
+      ggplot2::geom_col(ggplot2::aes(x = disk, y = count, fill = cols)) + 
+      ggplot2::scale_fill_manual(values = vals,
+                                 name = NULL)
+  } else {
+    p <- p +
+      ggplot2::geom_col(ggplot2::aes(x = disk, y = count))
+  }
+  
+  p +
+    ggplot2::labs(title = title, x = xlab, y = ylab, subtitle = cols_sub$sub)
+}
+
+plot_prepare_table <- function(x, expand) {
+  if (is.mic(x)) {
+    if (expand == TRUE) {
+      # expand range for MIC by adding factors of 2 from lowest to highest so all MICs in between also print
+      extra_range <- max(x) / 2
+      while (min(extra_range) / 2 > min(x)) {
+        extra_range <- c(min(extra_range) / 2, extra_range)
+      }
+      nms <- extra_range
+      extra_range <- rep(0, length(extra_range))
+      names(extra_range) <- nms
+      x <- table(droplevels(x, as.mic = FALSE))
+      extra_range <- extra_range[!names(extra_range) %in% names(x)]
+      x <- as.table(c(x, extra_range))
+    } else {
+      x <- table(droplevels(x, as.mic = FALSE))
+    }
+    x <- x[order(as.double(as.mic(names(x))))]
+  } else if (is.disk(x)) {
+    if (expand == TRUE) {
+      # expand range for disks from lowest to highest so all mm's in between also print
+      extra_range <- rep(0, max(x) - min(x) - 1)
+      names(extra_range) <- seq(min(x) + 1, max(x) - 1)
+      x <- table(x)
+      extra_range <- extra_range[!names(extra_range) %in% names(x)]
+      x <- as.table(c(x, extra_range))
+    } else {
+      x <- table(x)
+    }
+    x <- x[order(as.double(names(x)))]
+  }
+  as.table(x)
+}
+
+plot_name_of_I <- function(guideline) {
+  if (!guideline %like% "CLSI" && as.double(gsub("[^0-9]+", "", guideline)) >= 2019) {
+    # interpretation since 2019
+    "Incr. exposure"
+  } else {
+    # interpretation until 2019
+    "Intermediate"
+  }
+}
+
+plot_colours_subtitle_guideline <- function(x, mo, ab, guideline, colours_RSI, fn, language, ...) {
+  guideline <- get_guideline(guideline, AMR::rsi_translation)
+  if (!is.null(mo) && !is.null(ab)) {
+    # interpret and give colour based on MIC values
+    mo <- as.mo(mo)
+    ab <- as.ab(ab)
+    rsi <- suppressWarnings(suppressMessages(as.rsi(fn(names(x)), mo = mo, ab = ab, guideline = guideline, ...)))
+    cols <- character(length = length(rsi))
+    cols[is.na(rsi)] <- "#BEBEBE"
+    cols[rsi == "R"] <- colours_RSI[1]
+    cols[rsi == "S"] <- colours_RSI[2]
+    cols[rsi == "I"] <- colours_RSI[3]
+    moname <- mo_name(mo, language = language)
+    abname <- ab_name(ab, language = language)
+    if (all(cols == "#BEBEBE")) {
+      message_("No ", guideline, " interpretations found for ", 
+               ab_name(ab, language = NULL, tolower = TRUE), " in ", moname)
+      guideline_txt <- ""
+    } else {
+      guideline_txt <- paste0("(", guideline, ")")
+    }
+    sub <- bquote(.(abname)~"in"~italic(.(moname))~.(guideline_txt))
+  } else {
+    cols <- "#BEBEBE"
+    sub <- NULL
+  }
+  list(cols = cols, count = as.double(x), sub = sub, guideline = guideline)
+}
+
+#' @method plot rsi
+#' @export
+#' @importFrom graphics plot text axis
+#' @rdname plot
+plot.rsi <- function(x,
+                     ylab = "Percentage",
+                     xlab = "Antimicrobial Interpretation",
+                     main = paste("Resistance Overview of", deparse(substitute(x))),
+                     ...) {
+  meet_criteria(ylab, allow_class = "character", has_length = 1)
+  meet_criteria(xlab, allow_class = "character", has_length = 1)
+  meet_criteria(main, allow_class = "character", has_length = 1, allow_NULL = TRUE)
+  
+  data <- as.data.frame(table(x), stringsAsFactors = FALSE)
+  colnames(data) <- c("x", "n")
+  data$s <- round((data$n / sum(data$n)) * 100, 1)
+  
+  if (!"S" %in% data$x) {
+    data <- rbind(data, data.frame(x = "S", n = 0, s = 0, stringsAsFactors = FALSE),
+                  stringsAsFactors = FALSE)
+  }
+  if (!"I" %in% data$x) {
+    data <- rbind(data, data.frame(x = "I", n = 0, s = 0, stringsAsFactors = FALSE),
+                  stringsAsFactors = FALSE)
+  }
+  if (!"R" %in% data$x) {
+    data <- rbind(data, data.frame(x = "R", n = 0, s = 0, stringsAsFactors = FALSE),
+                  stringsAsFactors = FALSE)
+  }
+  
+  data$x <- factor(data$x, levels = c("S", "I", "R"), ordered = TRUE)
+  
+  ymax <- pm_if_else(max(data$s) > 95, 105, 100)
+  
+  plot(x = data$x,
+       y = data$s,
+       lwd = 2,
+       ylim = c(0, ymax),
+       ylab = ylab,
+       xlab = xlab,
+       main = main,
+       axes = FALSE)
+  # x axis
+  axis(side = 1, at = 1:pm_n_distinct(data$x), labels = levels(data$x), lwd = 0)
+  # y axis, 0-100%
+  axis(side = 2, at = seq(0, 100, 5))
+  
+  text(x = data$x,
+       y = data$s + 4,
+       labels = paste0(data$s, "% (n = ", data$n, ")"))
+}
+
+
+#' @method barplot rsi
+#' @importFrom graphics barplot axis
+#' @export
+#' @noRd
+barplot.rsi <- function(height,
+                        main = paste("Resistance Overview of", deparse(substitute(height))),
+                        xlab = "Antimicrobial Interpretation",
+                        ylab = "Frequency",
+                        colours_RSI = c("#ED553B", "#3CAEA3", "#F6D55C"),
+                        language = get_locale(),
+                        expand = TRUE,
+                        ...) {
+  meet_criteria(xlab, allow_class = "character", has_length = 1)
+  meet_criteria(main, allow_class = "character", has_length = 1, allow_NULL = TRUE)
+  meet_criteria(ylab, allow_class = "character", has_length = 1)
+  meet_criteria(colours_RSI, allow_class = "character", has_length = c(1, 3))
+  meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
+  meet_criteria(expand, allow_class = "logical", has_length = 1)
+  
+  if (length(colours_RSI) == 1) {
+    colours_RSI <- rep(colours_RSI, 3)
+  }
+  main <- gsub(" +", " ", paste0(main, collapse = " "))
+  
+  x <- table(height)
+  x <- x[c(1, 2, 3)]
+  barplot(x,
+          col = colours_RSI,
+          xlab = xlab,
+          main = main,
+          ylab = ylab,
+          axes = FALSE)
+  axis(2, seq(0, max(x)))
+}
+
+#' @method ggplot rsi
+#' @rdname plot
+# will be exported using s3_register() in R/zzz.R
+ggplot.rsi <- function(data,
+                       mapping = NULL,
+                       title = paste("Resistance Overview of", deparse(substitute(data))),
+                       xlab = "Antimicrobial Interpretation",
+                       ylab = "Frequency",
+                       colours_RSI = c("#ED553B", "#3CAEA3", "#F6D55C"),
+                       ...) {
+  stop_ifnot_installed("ggplot2")
+  meet_criteria(title, allow_class = "character", allow_NULL = TRUE)
+  meet_criteria(ylab, allow_class = "character", has_length = 1)
+  meet_criteria(xlab, allow_class = "character", has_length = 1)
+  meet_criteria(colours_RSI, allow_class = "character", has_length = c(1, 3))
+  
+  if ("main" %in% names(list(...))) {
+    title <- list(...)$main
+  }
+  if (!is.null(title)) {
+    title <- gsub(" +", " ", paste0(title, collapse = " "))
+  }
+  
+  if (length(colours_RSI) == 1) {
+    colours_RSI <- rep(colours_RSI, 3)
+  }
+  
+  df <- as.data.frame(table(data), stringsAsFactors = TRUE)
+  colnames(df) <- c("rsi", "count")
+  if (!is.null(mapping)) {
+    p <- ggplot2::ggplot(df, mapping = mapping)
+  } else {
+    p <- ggplot2::ggplot(df)
+  }
+  
+  p +
+    ggplot2::geom_col(ggplot2::aes(x = rsi, y = count, fill = rsi)) + 
+    ggplot2::scale_fill_manual(values = c("R" = colours_RSI[1],
+                                          "S" = colours_RSI[2],
+                                          "I" = colours_RSI[3])) +
+    ggplot2::labs(title = title, x = xlab, y = ylab) +
+    ggplot2::theme(legend.position = "none")
+}

R/random.R

@@ -25,8 +25,8 @@
 
 #' Random MIC Values/Disk Zones/RSI Generation
 #'
-#' These functions can be used for generating random MIC values and disk diffusion diameters, for AMR data analysis practice.
-#' @inheritSection lifecycle Maturing Lifecycle 
+#' These functions can be used for generating random MIC values and disk diffusion diameters, for AMR data analysis practice. By providing a microorganism and antimicrobial agent, the generated results will reflect reality as much as possible.
+#' @inheritSection lifecycle Stable Lifecycle 
 #' @param size desired size of the returned vector
 #' @param mo any character that can be coerced to a valid microorganism code with [as.mo()]
 #' @param ab any character that can be coerced to a valid antimicrobial agent code with [as.ab()]
@@ -51,9 +51,9 @@
 #' random_mic(100, "Klebsiella pneumoniae", "meropenem")    # range 0.0625-16
 #' random_mic(100, "Streptococcus pneumoniae", "meropenem") # range 0.0625-4
 #' 
-#' random_disk(100, "Klebsiella pneumoniae")                  # range 11-50
-#' random_disk(100, "Klebsiella pneumoniae", "ampicillin")    # range 6-14
-#' random_disk(100, "Streptococcus pneumoniae", "ampicillin") # range 16-22
+#' random_disk(100, "Klebsiella pneumoniae")                  # range 8-50
+#' random_disk(100, "Klebsiella pneumoniae", "ampicillin")    # range 11-17
+#' random_disk(100, "Streptococcus pneumoniae", "ampicillin") # range 12-27
 #' }
 random_mic <- function(size, mo = NULL, ab = NULL, ...) {
   random_exec("MIC", size = size, mo = mo, ab = ab)
@@ -111,18 +111,26 @@ random_exec <- function(type, size, mo = NULL, ab = NULL) {
     if (log(set_range_max, 2) %% 1 == 0) {
       # return powers of 2
       valid_range <- unique(as.double(valid_range))
-      # add one higher MIC level to set_range_max
-      set_range_max <- 2 ^ (log(set_range_max, 2) + 1)
+      # add 1-3 higher MIC levels to set_range_max
+      set_range_max <- 2 ^ (log(set_range_max, 2) + sample(c(1:3), 1))
       set_range <- as.mic(valid_range[log(valid_range, 2) %% 1 == 0 & valid_range <= set_range_max])
     } else {
       # no power of 2, return factors of 2 to left and right side
       valid_mics <- suppressWarnings(as.mic(set_range_max / (2 ^ c(-3:3))))
       set_range <- valid_mics[!is.na(valid_mics)]
     }
-    return(as.mic(sample(set_range, size = size, replace = TRUE)))
+    out <- as.mic(sample(set_range, size = size, replace = TRUE))
+    # 50% chance that lowest will get <= and highest will get >=
+    if (stats::runif(1) > 0.5) {
+      out[out == min(out)] <- paste0("<=", out[out == min(out)])
+    }
+    if (stats::runif(1) > 0.5) {
+      out[out == max(out)] <- paste0(">=", out[out == max(out)])
+    }
+    return(out)
   } else if (type == "DISK") {
-    set_range <- seq(from = as.integer(min(df$breakpoint_R)),
-                     to = as.integer(max(df$breakpoint_S)),
+    set_range <- seq(from = as.integer(min(df$breakpoint_R) / 1.25),
+                     to = as.integer(max(df$breakpoint_S) * 1.25),
                      by = 1)
     out <- sample(set_range, size = size, replace = TRUE)
     out[out < 6] <- sample(c(6:10), length(out[out < 6]), replace = TRUE)

R/resistance_predict.R

@@ -26,7 +26,7 @@
 #' Predict antimicrobial resistance
 #'
 #' Create a prediction model to predict antimicrobial resistance for the next years on statistical solid ground. Standard errors (SE) will be returned as columns `se_min` and `se_max`. See *Examples* for a real live example.
-#' @inheritSection lifecycle Maturing Lifecycle
+#' @inheritSection lifecycle Stable Lifecycle
 #' @param col_ab column name of `x` containing antimicrobial interpretations (`"R"`, `"I"` and `"S"`)
 #' @param col_date column name of the date, will be used to calculate years if this column doesn't consist of years already, defaults to the first column of with a date class
 #' @param year_min lowest year to use in the prediction model, dafaults to the lowest year in `col_date`

R/rsi.R

@@ -252,12 +252,13 @@ is.rsi.eligible <- function(x, threshold = 0.05) {
 }
 
 #' @export
+# extra param: warn (never throw warning)
 as.rsi.default <- function(x, ...) {
   if (is.rsi(x)) {
     return(x)
   }
   
-  if (inherits(x, "integer") & all(x %in% c(1:3, NA))) {
+  if (inherits(x, c("integer", "numeric", "double")) && all(x %in% c(1:3, NA))) {
     x[x == 1] <- "S"
     x[x == 2] <- "I"
     x[x == 3] <- "R"
@@ -265,11 +266,11 @@ as.rsi.default <- function(x, ...) {
   } else if (!all(is.na(x)) && !identical(levels(x), c("S", "I", "R"))) {
     
     if (!any(x %like% "(R|S|I)", na.rm = TRUE)) {
-      # check if they are actually MICs or disks now that the antibiotic name is valid
+      # check if they are actually MICs or disks
       if (all_valid_mics(x)) {
-        warning_("The input seems to be MIC values. Transform them with as.mic() before running as.rsi() to interpret them.")
+        warning_("The input seems to be MIC values. Transform them with `as.mic()` before running `as.rsi()` to interpret them.")
       } else if (all_valid_disks(x)) {
-        warning_("The input seems to be disk diffusion values. Transform them with as.disk() before running as.rsi() to interpret them.")
+        warning_("The input seems to be disk diffusion values. Transform them with `as.disk()` before running `as.rsi()` to interpret them.")
       }
     }
     
@@ -338,7 +339,7 @@ as.rsi.mic <- function(x,
   
   # for dplyr's across()
   cur_column_dplyr <- import_fn("cur_column", "dplyr", error_on_fail = FALSE)
-  if (!is.null(cur_column_dplyr)) {
+  if (!is.null(cur_column_dplyr) && tryCatch(is.data.frame(get_current_data("ab", 0)), error = function(e) FALSE)) {
     # try to get current column, which will only be available when in across()
     ab <- tryCatch(cur_column_dplyr(),
                    error = function(e) ab)
@@ -427,7 +428,7 @@ as.rsi.disk <- function(x,
   
   # for dplyr's across()
   cur_column_dplyr <- import_fn("cur_column", "dplyr", error_on_fail = FALSE)
-  if (!is.null(cur_column_dplyr)) {
+  if (!is.null(cur_column_dplyr) && tryCatch(is.data.frame(get_current_data("ab", 0)), error = function(e) FALSE)) {
     # try to get current column, which will only be available when in across()
     ab <- tryCatch(cur_column_dplyr(),
                    error = function(e) ab)
@@ -703,7 +704,6 @@ exec_as.rsi <- function(method,
                         conserve_capped_values, 
                         add_intrinsic_resistance,
                         reference_data) {
-  
   metadata_mo <- get_mo_failures_uncertainties_renamed()
   
   x_bak <- data.frame(x_mo = paste0(x, mo), stringsAsFactors = FALSE)
@@ -720,10 +720,10 @@ exec_as.rsi <- function(method,
   warned <- FALSE
   method_param <- toupper(method)
   
-  genera <- mo_genus(mo)
-  mo_genus <- as.mo(genera)
-  mo_family <- as.mo(mo_family(mo))
-  mo_order <- as.mo(mo_order(mo))
+  genera <- mo_genus(mo, language = NULL)
+  mo_genus <- as.mo(genera, language = NULL)
+  mo_family <- as.mo(mo_family(mo, language = NULL))
+  mo_order <- as.mo(mo_order(mo, language = NULL))
   if (any(genera == "Staphylococcus", na.rm = TRUE)) {
     mo_becker <- as.mo(mo, Becker = TRUE)
   } else {
@@ -807,23 +807,19 @@ exec_as.rsi <- function(method,
         pm_filter(uti == FALSE) %pm>% # 'uti' is a column in rsi_translation
         pm_arrange(pm_desc(nchar(mo)))
     }
+    
     get_record <- get_record[1L, , drop = FALSE]
     
     if (NROW(get_record) > 0) {
-      if (is.na(x[i])) {
+      if (is.na(x[i]) | (is.na(get_record$breakpoint_S) & is.na(get_record$breakpoint_R))) {
         new_rsi[i] <- NA_character_
       } else if (method == "mic") {
-        mic_input <- x[i]
-        mic_S <- as.mic(get_record$breakpoint_S)
-        mic_R <- as.mic(get_record$breakpoint_R)
-        new_rsi[i] <- quick_case_when(isTRUE(conserve_capped_values) & mic_input %like% "^<[0-9]" ~ "S",
-                                      isTRUE(conserve_capped_values) & mic_input %like% "^>[0-9]" ~ "R",
+        new_rsi[i] <- quick_case_when(isTRUE(conserve_capped_values) & x[i] %like% "^<[0-9]" ~ "S",
+                                      isTRUE(conserve_capped_values) & x[i] %like% "^>[0-9]" ~ "R",
                                       # start interpreting: EUCAST uses <= S and > R, CLSI uses <=S and >= R
-                                      isTRUE(which(levels(mic_input) == mic_input) <= which(levels(mic_S) == mic_S)) ~ "S",
-                                      guideline_coerced %like% "EUCAST" &
-                                        isTRUE(which(levels(mic_input) == mic_input) > which(levels(mic_R) == mic_R)) ~ "R",
-                                      guideline_coerced %like% "CLSI" &
-                                        isTRUE(which(levels(mic_input) == mic_input) >= which(levels(mic_R) == mic_R)) ~ "R",
+                                      x[i] <= get_record$breakpoint_S ~ "S",
+                                      guideline_coerced %like% "EUCAST" & x[i] > get_record$breakpoint_R ~ "R",
+                                      guideline_coerced %like% "CLSI" & x[i] >= get_record$breakpoint_R ~ "R",
                                       # return "I" when not match the bottom or top
                                       !is.na(get_record$breakpoint_S) & !is.na(get_record$breakpoint_R) ~ "I",
                                       # and NA otherwise
@@ -1010,107 +1006,6 @@ summary.rsi <- function(object, ...) {
   value
 }
 
-#' @method plot rsi
-#' @export
-#' @importFrom graphics plot text axis
-#' @rdname plot
-plot.rsi <- function(x,
-                     lwd = 2,
-                     ylim = NULL,
-                     ylab = "Percentage",
-                     xlab = "Antimicrobial Interpretation",
-                     main = paste("Resistance Overview of", deparse(substitute(x))),
-                     axes = FALSE,
-                     ...) {
-  meet_criteria(lwd, allow_class = c("numeric", "integer"), has_length = 1, is_positive = TRUE, is_finite = TRUE)
-  meet_criteria(ylim, allow_class = c("numeric", "integer"), allow_NULL = TRUE)
-  meet_criteria(ylab, allow_class = "character", has_length = 1)
-  meet_criteria(xlab, allow_class = "character", has_length = 1)
-  meet_criteria(main, allow_class = "character", has_length = 1)
-  meet_criteria(axes, allow_class = "logical", has_length = 1)
-  
-  data <- as.data.frame(table(x), stringsAsFactors = FALSE)
-  colnames(data) <- c("x", "n")
-  data$s <- round((data$n / sum(data$n)) * 100, 1)
-  
-  if (!"S" %in% data$x) {
-    data <- rbind(data, data.frame(x = "S", n = 0, s = 0, stringsAsFactors = FALSE),
-                  stringsAsFactors = FALSE)
-  }
-  if (!"I" %in% data$x) {
-    data <- rbind(data, data.frame(x = "I", n = 0, s = 0, stringsAsFactors = FALSE),
-                  stringsAsFactors = FALSE)
-  }
-  if (!"R" %in% data$x) {
-    data <- rbind(data, data.frame(x = "R", n = 0, s = 0, stringsAsFactors = FALSE),
-                  stringsAsFactors = FALSE)
-  }
-  
-  # don't use as.rsi() here, it will confuse plot()
-  data$x <- factor(data$x, levels = c("S", "I", "R"), ordered = TRUE)
-  
-  ymax <- pm_if_else(max(data$s) > 95, 105, 100)
-  
-  plot(x = data$x,
-       y = data$s,
-       lwd = lwd,
-       ylim = c(0, ymax),
-       ylab = ylab,
-       xlab = xlab,
-       main = main,
-       axes = axes,
-       ...)
-  # x axis
-  axis(side = 1, at = 1:pm_n_distinct(data$x), labels = levels(data$x), lwd = 0)
-  # y axis, 0-100%
-  axis(side = 2, at = seq(0, 100, 5))
-  
-  text(x = data$x,
-       y = data$s + 4,
-       labels = paste0(data$s, "% (n = ", data$n, ")"))
-}
-
-
-#' @method barplot rsi
-#' @export
-#' @importFrom graphics barplot axis par
-#' @rdname plot
-barplot.rsi <- function(height,
-                        col = c("chartreuse4", "chartreuse3", "brown3"),
-                        xlab = ifelse(beside, "Antimicrobial Interpretation", ""),
-                        main = paste("Resistance Overview of", deparse(substitute(height))),
-                        ylab = "Frequency",
-                        beside = TRUE,
-                        axes = beside,
-                        ...) {
-  meet_criteria(col, allow_class = "character", has_length = 3)
-  meet_criteria(xlab, allow_class = "character", has_length = 1)
-  meet_criteria(main, allow_class = "character", has_length = 1)
-  meet_criteria(ylab, allow_class = "character", has_length = 1)
-  meet_criteria(beside, allow_class = "logical", has_length = 1)
-  meet_criteria(axes, allow_class = "logical", has_length = 1)
-  
-  if (axes == TRUE) {
-    par(mar =  c(5, 4, 4, 2) + 0.1)
-  } else {
-    par(mar =  c(2, 4, 4, 2) + 0.1)
-  }
-  
-  barplot(as.matrix(table(height)),
-          col = col,
-          xlab = xlab,
-          main = main,
-          ylab = ylab,
-          beside = beside,
-          axes = FALSE,
-          ...)
-  # y axis, 0-100%
-  axis(side = 2, at = seq(0, max(table(height)) + max(table(height)) * 1.1, by = 25))
-  if (axes == TRUE && beside == TRUE) {
-    axis(side = 1, labels = levels(height), at = c(1, 2, 3) + 0.5, lwd = 0)
-  }
-}
-
 #' @method [<- rsi
 #' @export
 #' @noRd

R/translate.R

@@ -142,7 +142,8 @@ translate_AMR <- function(from, language = get_locale(), only_unknown = FALSE, a
              vector_or(LANGUAGES_SUPPORTED, quotes = TRUE),
              call = FALSE)
   
-  df_trans <- subset(df_trans, lang == language)
+  # only keep lines where translation is available for this language
+  df_trans <- df_trans[which(!is.na(df_trans[, language, drop = TRUE])), , drop = FALSE]
   if (only_unknown == TRUE) {
     df_trans <- subset(df_trans, pattern %like% "unknown")
   }
@@ -150,10 +151,10 @@ translate_AMR <- function(from, language = get_locale(), only_unknown = FALSE, a
     df_trans <- subset(df_trans, affect_mo_name == TRUE)
   }
   
-  # default: case sensitive if value if 'ignore.case' is missing:
-  df_trans$ignore.case[is.na(df_trans$ignore.case)] <- FALSE
-  # default: not using regular expressions (fixed = TRUE) if 'fixed' is missing:
-  df_trans$fixed[is.na(df_trans$fixed)] <- TRUE
+  # default: case sensitive if value if 'case_sensitive' is missing:
+  df_trans$case_sensitive[is.na(df_trans$case_sensitive)] <- TRUE
+  # default: not using regular expressions if 'regular_expr' is missing:
+  df_trans$regular_expr[is.na(df_trans$regular_expr)] <- FALSE
   
   # check if text to look for is in one of the patterns
   any_form_in_patterns <- tryCatch(any(from_unique %like% paste0("(", paste(df_trans$pattern, collapse = "|"), ")")),
@@ -167,11 +168,11 @@ translate_AMR <- function(from, language = get_locale(), only_unknown = FALSE, a
   
   lapply(seq_len(nrow(df_trans)), 
          function(i) from_unique_translated <<- gsub(pattern = df_trans$pattern[i],
-                                                     replacement = df_trans$replacement[i],
+                                                     replacement = df_trans[i, language, drop = TRUE],
                                                      x = from_unique_translated,
-                                                     ignore.case = df_trans$ignore.case[i], 
-                                                     fixed = df_trans$fixed[i],
-                                                     perl = !df_trans$fixed[i]))
+                                                     ignore.case = !df_trans$case_sensitive[i], 
+                                                     fixed = !df_trans$regular_expr[i],
+                                                     perl = df_trans$regular_expr[i]))
   
   # force UTF-8 for diacritics
   from_unique_translated <- enc2utf8(from_unique_translated)

R/zzz.R

@@ -50,6 +50,9 @@ pkg_env$mo_failed <- character(0)
   s3_register("skimr::get_skimmers", "rsi")
   s3_register("skimr::get_skimmers", "mic")
   s3_register("skimr::get_skimmers", "disk")
+  s3_register("ggplot2::ggplot", "rsi")
+  s3_register("ggplot2::ggplot", "mic")
+  s3_register("ggplot2::ggplot", "disk")
   
   # if mo source exists, fire it up (see mo_source())
   try({

README.md

@@ -10,13 +10,13 @@
 
 <img src="https://msberends.github.io/AMR/works_great_on.png" align="center" height="150px" />
 
-The latest built **source package** (`AMR_latest.tar.gz`) can be found in folder [/data-raw/](data-raw).
+The latest built **source package** (`AMR_latest.tar.gz`) can be found in folder [/data-raw/](https://github.com/msberends/AMR/tree/master/data-raw).
 
-`AMR` is a free, open-source and independent R package to simplify the analysis and prediction of Antimicrobial Resistance (AMR) and to work with microbial and antimicrobial data and properties, by using evidence-based methods. Our aim is to provide a standard for clean and reproducible antimicrobial resistance data analysis, that can therefore empower epidemiological analyses to continuously enable surveillance and treatment evaluation in any setting.
+`AMR` is a free, open-source and independent R package to simplify the analysis and prediction of Antimicrobial Resistance (AMR) and to work with microbial and antimicrobial data and properties, by using evidence-based methods. Our aim is to provide a standard for clean and reproducible antimicrobial resistance data analysis, that can therefore empower epidemiological analyses to continuously enable surveillance and treatment evaluation in any setting. It is currently being used in over 150 countries.
  
-After installing this package, R knows ~70,000 distinct microbial species and all ~550 antibiotic, antimycotic and antiviral drugs by name and code (including ATC, EARS-NET, LOINC and SNOMED CT), and knows all about valid R/SI and MIC values. It supports any data format, including WHONET/EARS-Net data.
+After installing this package, R knows ~70,000 distinct microbial species and all ~550 antibiotic, antimycotic, and antiviral drugs by name and code (including ATC, EARS-Net, PubChem, LOINC and SNOMED CT), and knows all about valid R/SI and MIC values. It supports any data format, including WHONET/EARS-Net data.
 
-This package is fully independent of any other R package and works on Windows, macOS and Linux with all versions of R since R-3.0.0 (April 2013). It was designed to work in any setting, including those with very limited resources. It was created for both routine data analysis and academic research at the Faculty of Medical Sciences of the University of Groningen, in collaboration with non-profit organisations Certe Medical Diagnostics and Advice and University Medical Center Groningen. This R package is actively maintained and free software; you can freely use and distribute it for both personal and commercial (but not patent) purposes under the terms of the GNU General Public License version 2.0 (GPL-2), as published by the Free Software Foundation.
+This package is fully independent of any other R package and works on Windows, macOS and Linux with all versions of R since R-3.0.0 (April 2013). It was designed to work in any setting, including those with very limited resources. It was created for both routine data analysis and academic research at the Faculty of Medical Sciences of the University of Groningen, in collaboration with non-profit organisations Certe Medical Diagnostics and Advice Foundation and University Medical Center Groningen. This R package is actively maintained and free software; you can freely use and distribute it for both personal and commercial (but not patent) purposes under the terms of the GNU General Public License version 2.0 (GPL-2), as published by the Free Software Foundation.
 
 This is the development source of the `AMR` package for R. Not a developer? Then please visit our website [https://msberends.github.io/AMR/](https://msberends.github.io/AMR/) to read more about this package.
 

_pkgdown.yml

@@ -143,8 +143,6 @@ reference:
     - "`as.mic`"
     - "`as.disk`"
     - "`eucast_rules`"
-    - "`plot`"
-    - "`isolate_identifier`"
     
   - title: "Analysing data: antimicrobial resistance"
     desc: >
@@ -159,6 +157,7 @@ reference:
     - "`key_antibiotics`"
     - "`mdro`"
     - "`count`"
+    - "`plot`"
     - "`ggplot_rsi`"
     - "`bug_drug_combinations`"
     - "`antibiotic_class_selectors`"

cran-comments.md

@@ -1 +1 @@
-* Ever since one of the first CRAN releases, CHECK returns a NOTE for having a data and R directory over 3 MB. This is needed to offer users reference data for the complete taxonomy of microorganisms - one of the most important features of this package.
+* This package has a tarball size of over 7 MB and an installation size of over 5 MB, which will return a NOTE on R CMD CHECK. The package size is needed to offer users reference data for the complete taxonomy of microorganisms - one of the most important features of this package. This was written and explained in a manuscript that was accepted for publication in the Journal of Statistical Software 4 weeks ago. We will add the paper as a vignette in the next version. Please allow this exception in package size for CRAN. We already compressed all data sets using `compression = "xz"` to make them as small as possible.

data-raw/_internals.R

@@ -43,21 +43,23 @@ create_species_cons_cops <- function(type = c("CoNS", "CoPS")) {
   MO_staph <- MO_staph[which(MO_staph$genus == "Staphylococcus"), , drop = FALSE]
   if (type == "CoNS") {
     MO_staph[which(MO_staph$species %in% c("coagulase-negative", "argensis", "arlettae",
-                                           "auricularis", "caeli", "capitis", "caprae", 
-                                           "carnosus", "chromogenes", "cohnii", "condimenti",
+                                           "auricularis", "borealis", "caeli", "capitis", "caprae", 
+                                           "carnosus", "casei", "chromogenes", "cohnii", "condimenti",
+                                           "croceilyticus",
                                            "debuckii", "devriesei", "edaphicus", "epidermidis",
                                            "equorum", "felis", "fleurettii", "gallinarum",
                                            "haemolyticus", "hominis", "jettensis", "kloosii",
                                            "lentus", "lugdunensis", "massiliensis", "microti",
                                            "muscae", "nepalensis", "pasteuri", "petrasii",
-                                           "pettenkoferi", "piscifermentans", "pseudoxylosus",
+                                           "pettenkoferi", "piscifermentans", "pragensis", "pseudoxylosus",
                                            "pulvereri", "rostri", "saccharolyticus", "saprophyticus",
                                            "sciuri", "simulans", "stepanovicii", "succinus",
+                                           "ureilyticus",
                                            "vitulinus", "vitulus", "warneri", "xylosus")
                    | (MO_staph$species == "schleiferi" & MO_staph$subspecies %in% c("schleiferi", ""))),
              "mo", drop = TRUE]
   } else if (type == "CoPS") {
-    MO_staph[which(MO_staph$species %in% c("coagulase-positive",
+    MO_staph[which(MO_staph$species %in% c("coagulase-positive", "coagulans",
                                            "agnetis", "argenteus",
                                            "cornubiensis",
                                            "delphini", "lutrae",
@@ -175,7 +177,7 @@ microorganisms.translation <- readRDS("data-raw/microorganisms.translation.rds")
 INTRINSIC_R <- create_intr_resistance()
 
 # for checking input in `language` argument in e.g. mo_*() and ab_*() functions
-LANGUAGES_SUPPORTED <- sort(c("en", unique(translations_file$lang)))
+LANGUAGES_SUPPORTED <- sort(c("en", colnames(translations_file)[nchar(colnames(translations_file)) == 2]))
 
 # vectors of CoNS and CoPS, improves speed in as.mo()
 MO_CONS <- create_species_cons_cops("CoNS")
@@ -217,11 +219,11 @@ changed_md5 <- function(object) {
     compared
   }, error = function(e) TRUE)
 }
-usethis::ui_done(paste0("Saving raw data to {usethis::ui_value('/data-raw/')}"))
 
 # give official names to ABs and MOs
 rsi <- dplyr::mutate(rsi_translation, ab = ab_name(ab), mo = mo_name(mo))
 if (changed_md5(rsi)) {
+  usethis::ui_info(paste0("Saving {usethis::ui_value('rsi_translation')} to {usethis::ui_value('/data-raw/')}"))
   write_md5(rsi)
   try(saveRDS(rsi, "data-raw/rsi_translation.rds", version = 2, compress = "xz"), silent = TRUE)
   try(write.table(rsi, "data-raw/rsi_translation.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)
@@ -233,16 +235,18 @@ if (changed_md5(rsi)) {
 
 mo <- dplyr::mutate_if(microorganisms, ~!is.numeric(.), as.character)
 if (changed_md5(mo)) {
+  usethis::ui_info(paste0("Saving {usethis::ui_value('microorganisms')} to {usethis::ui_value('/data-raw/')}"))
   write_md5(mo)
   try(saveRDS(mo, "data-raw/microorganisms.rds", version = 2, compress = "xz"), silent = TRUE)
   try(write.table(mo, "data-raw/microorganisms.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)
-  try(haven::write_sas(mo, "data-raw/microorganisms.sas"), silent = TRUE)
-  try(haven::write_sav(mo, "data-raw/microorganisms.sav"), silent = TRUE)
-  try(haven::write_dta(mo, "data-raw/microorganisms.dta"), silent = TRUE)
+  try(haven::write_sas(dplyr::select(mo, -snomed), "data-raw/microorganisms.sas"), silent = TRUE)
+  try(haven::write_sav(dplyr::select(mo, -snomed), "data-raw/microorganisms.sav"), silent = TRUE)
+  try(haven::write_dta(dplyr::select(mo, -snomed), "data-raw/microorganisms.dta"), silent = TRUE)
   try(openxlsx::write.xlsx(mo, "data-raw/microorganisms.xlsx"), silent = TRUE)
 }
 
 if (changed_md5(microorganisms.old)) {
+  usethis::ui_info(paste0("Saving {usethis::ui_value('microorganisms.old')} to {usethis::ui_value('/data-raw/')}"))
   write_md5(microorganisms.old)
   try(saveRDS(microorganisms.old, "data-raw/microorganisms.old.rds", version = 2, compress = "xz"), silent = TRUE)
   try(write.table(microorganisms.old, "data-raw/microorganisms.old.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)
@@ -254,6 +258,7 @@ if (changed_md5(microorganisms.old)) {
 
 ab <- dplyr::mutate_if(antibiotics, ~!is.numeric(.), as.character)
 if (changed_md5(ab)) {
+  usethis::ui_info(paste0("Saving {usethis::ui_value('antibiotics')} to {usethis::ui_value('/data-raw/')}"))
   write_md5(ab)
   try(saveRDS(ab, "data-raw/antibiotics.rds", version = 2, compress = "xz"), silent = TRUE)
   try(write.table(ab, "data-raw/antibiotics.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)
@@ -265,6 +270,7 @@ if (changed_md5(ab)) {
 
 av <- dplyr::mutate_if(antivirals, ~!is.numeric(.), as.character)
 if (changed_md5(av)) {
+  usethis::ui_info(paste0("Saving {usethis::ui_value('antivirals')} to {usethis::ui_value('/data-raw/')}"))
   write_md5(av)
   try(saveRDS(av, "data-raw/antivirals.rds", version = 2, compress = "xz"), silent = TRUE)
   try(write.table(av, "data-raw/antivirals.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)
@@ -275,6 +281,7 @@ if (changed_md5(av)) {
 }
 
 if (changed_md5(intrinsic_resistant)) {
+  usethis::ui_info(paste0("Saving {usethis::ui_value('intrinsic_resistant')} to {usethis::ui_value('/data-raw/')}"))
   write_md5(intrinsic_resistant)
   try(saveRDS(intrinsic_resistant, "data-raw/intrinsic_resistant.rds", version = 2, compress = "xz"), silent = TRUE)
   try(write.table(intrinsic_resistant, "data-raw/intrinsic_resistant.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)
@@ -285,6 +292,7 @@ if (changed_md5(intrinsic_resistant)) {
 }
 
 if (changed_md5(dosage)) {
+  usethis::ui_info(paste0("Saving {usethis::ui_value('dosage')} to {usethis::ui_value('/data-raw/')}"))
   write_md5(dosage)
   try(saveRDS(dosage, "data-raw/dosage.rds", version = 2, compress = "xz"), silent = TRUE)
   try(write.table(dosage, "data-raw/dosage.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)

data-raw/ab.md5

@@ -1 +1 @@
-fa68ab044001078f290218a7de6cc5c4
+77f6cca42687a0e3b1b1045a2d70b226

data-raw/antibiotics.txt

@@ -108,7 +108,7 @@
 "CPT"	"J01DI02"	56841980	"Ceftaroline"	"Cephalosporins (5th gen.)"			"c(\"\", \"cfro\")"	"c(\"teflaro\", \"zinforo\")"			1.2		"character(0)"
 "CPA"			"Ceftaroline/avibactam"	"Cephalosporins (5th gen.)"			""	""					""
 "CAZ"	"J01DD02"	5481173	"Ceftazidime"	"Cephalosporins (3rd gen.)"	"Other beta-lactam antibacterials"	"Third-generation cephalosporins"	"c(\"caz\", \"cefta\", \"cfta\", \"cftz\", \"taz\", \"tz\", \"xtz\")"	"c(\"ceftazidim\", \"ceftazidima\", \"ceftazidime\", \"ceftazidimum\", \"ceptaz\", \"fortaz\", \"fortum\", \"pentacef\", \"tazicef\", \"tazidime\")"			4	"g"	"c(\"21151-6\", \"3449-6\", \"80960-8\")"
-"CZA"			"Ceftazidime/avibactam"	"Cephalosporins (3rd gen.)"			"c(\"\", \"cfav\")"	""					""
+"CZA"	"J01DD52"	90643431	"Ceftazidime/avibactam"	"Cephalosporins (3rd gen.)"	"Other beta-lactam antibacterials"	"Third-generation cephalosporins"	"c(\"\", \"cfav\")"	"c(\"avycaz\", \"zavicefta\")"			6	"g"	""
 "CCV"	"J01DD52"	9575352	"Ceftazidime/clavulanic acid"	"Cephalosporins (3rd gen.)"	"Other beta-lactam antibacterials"	"Third-generation cephalosporins"	"c(\"czcl\", \"xtzl\")"	""			6		""
 "CEM"		6537431	"Cefteram"	"Cephalosporins (3rd gen.)"			""	"c(\"cefteram\", \"cefterame\", \"cefteramum\", \"ceftetrame\")"					"character(0)"
 "CPL"		5362114	"Cefteram pivoxil"	"Cephalosporins (3rd gen.)"			""	"c(\"cefteram pivoxil\", \"tomiron\")"					"character(0)"

data-raw/intrinsic_resistant.md5

@@ -1 +1 @@
-b6de75043ef27eabd6fff22f04638225
+9c58b2d894dbad7593cd44b78d04cd78

data-raw/microorganisms.old.md5

@@ -1 +1 @@
-617b59b8ac3bd1aad7847aafc328f0f3
+8338ff5f079f4519fa3c44f8c5bace64

data-raw/mo.md5

@@ -1 +1 @@
-a5b85c5b3d37d6330865dfe09ef9b354
+82bd6236cf159569f6f5c99f48f92d86

data-raw/reproduction_of_antibiotics.R

@@ -166,7 +166,7 @@ abx2$abbr <- lapply(as.list(abx2$abbr), function(x) unlist(strsplit(x, "|", fixe
 # vector with official names, returns vector with CIDs
 get_CID <- function(ab) {
   CID <- rep(NA_integer_, length(ab))
-  p <- progress_estimated(n = length(ab), min_time = 0)
+  p <- progress_ticker(n = length(ab), min_time = 0)
   for (i in 1:length(ab)) {
     p$tick()$print()
 
@@ -208,10 +208,10 @@ abx2[is.na(CIDs),] %>% View()
 # returns list with synonyms (brand names), with CIDs as names
 get_synonyms <- function(CID, clean = TRUE) {
   synonyms <- rep(NA_character_, length(CID))
-  p <- progress_estimated(n = length(CID), min_time = 0)
+  #p <- progress_ticker(n = length(CID), min_time = 0)
 
   for (i in 1:length(CID)) {
-    p$tick()$print()
+    #p$tick()$print()
 
     synonyms_txt <- ""
 
@@ -564,6 +564,14 @@ antibiotics[which(antibiotics$ab == "CPT"), "atc"] <- "J01DI02"
 antibiotics[which(antibiotics$ab == "FAR"), "atc"] <- "J01DI03"
 # ceftobiprole
 antibiotics[which(antibiotics$ab == "BPR"), "atc"] <- "J01DI01"
+# ceftazidime / avibactam
+antibiotics[which(antibiotics$ab == "CZA"), "atc"] <- "J01DD52"
+antibiotics[which(antibiotics$ab == "CZA"), "cid"] <- 90643431
+antibiotics[which(antibiotics$ab == "CZA"), "atc_group1"] <- "Other beta-lactam antibacterials"
+antibiotics[which(antibiotics$ab == "CZA"), "atc_group2"] <- "Third-generation cephalosporins"
+antibiotics[which(antibiotics$ab == "CZA"), "iv_ddd"] <- 6
+antibiotics[which(antibiotics$ab == "CZA"), "iv_units"] <- "g"
+antibiotics[which(antibiotics$ab == "CZA"), "synonyms"] <- list(c("Avycaz", "Zavicefta"))
 
 # typo
 antibiotics[which(antibiotics$ab == "RXT"), "name"] <- "Roxithromycin"

data-raw/reproduction_of_microorganisms_update.R

@@ -0,0 +1,480 @@
+# ==================================================================== #
+# TITLE                                                                #
+# Antimicrobial Resistance (AMR) Data Analysis for R                   #
+#                                                                      #
+# SOURCE                                                               #
+# https://github.com/msberends/AMR                                     #
+#                                                                      #
+# LICENCE                                                              #
+# (c) 2018-2021 Berends MS, Luz CF et al.                              #
+# Developed at the University of Groningen, the Netherlands, in        #
+# collaboration with non-profit organisations Certe Medical            #
+# Diagnostics & Advice, and University Medical Center Groningen.       # 
+#                                                                      #
+# This R package is free software; you can freely use and distribute   #
+# it for both personal and commercial purposes under the terms of the  #
+# GNU General Public License version 2.0 (GNU GPL-2), as published by  #
+# the Free Software Foundation.                                        #
+# We created this package for both routine data analysis and academic  #
+# research and it was publicly released in the hope that it will be    #
+# useful, but it comes WITHOUT ANY WARRANTY OR LIABILITY.              #
+#                                                                      #
+# Visit our website for the full manual and a complete tutorial about  #
+# how to conduct AMR data analysis: https://msberends.github.io/AMR/   #
+# ==================================================================== #
+
+# Register at List of Prokaryotic names with Standing in Nomenclature (LPSN)
+# then got to https://lpsn.dsmz.de/downloads and download the latest CSV file.
+
+library(tidyverse)
+library(AMR)
+
+# these should still work after this update
+test_fullname <- microorganisms$fullname
+test_mo <- microorganisms$mo
+
+
+# Helper functions --------------------------------------------------------
+
+get_author_year <- function(ref) {
+  # Only keep first author, e.g. transform 'Smith, Jones, 2011' to 'Smith et al., 2011'
+  
+  authors2 <- iconv(ref, from = "UTF-8", to = "ASCII//TRANSLIT")
+  authors2 <- gsub(" ?\\(Approved Lists [0-9]+\\) ?", " () ", authors2)
+  authors2 <- gsub(" [)(]+ $", "", authors2)
+  # remove leading and trailing brackets
+  authors2 <- trimws(gsub("^[(](.*)[)]$", "\\1", authors2))
+  # only take part after brackets if there's a name
+  authors2 <- ifelse(grepl(".*[)] [a-zA-Z]+.*", authors2),
+                     gsub(".*[)] (.*)", "\\1", authors2),
+                     authors2)
+  # get year from last 4 digits
+  lastyear = as.integer(gsub(".*([0-9]{4})$", "\\1", authors2))
+  # can never be later than now
+  lastyear = ifelse(lastyear > as.integer(format(Sys.Date(), "%Y")),
+                    NA,
+                    lastyear)
+  # get authors without last year
+  authors <- gsub("(.*)[0-9]{4}$", "\\1", authors2)
+  # remove nonsense characters from names
+  authors <- gsub("[^a-zA-Z,'& -]", "", authors)
+  # remove trailing and leading spaces
+  authors <- trimws(authors)
+  # only keep first author and replace all others by 'et al'
+  authors <- gsub("(,| and| et| &| ex| emend\\.?) .*", " et al.", authors)
+  # et al. always with ending dot
+  authors <- gsub(" et al\\.?", " et al.", authors)
+  authors <- gsub(" ?,$", "", authors)
+  # don't start with 'sensu' or 'ehrenb'
+  authors <- gsub("^(sensu|Ehrenb.?) ", "", authors, ignore.case = TRUE)
+  # no initials, only surname
+  authors <- gsub("^([A-Z]+ )+", "", authors, ignore.case = FALSE)
+  # combine author and year if year is available
+  ref <- ifelse(!is.na(lastyear),
+                paste0(authors, ", ", lastyear),
+                authors)
+  # fix beginning and ending
+  ref <- gsub(", $", "", ref)
+  ref <- gsub("^, ", "", ref)
+  ref <- gsub("^(emend|et al.,?)", "", ref)
+  ref <- trimws(ref)
+  ref <- gsub("'", "", ref)
+  
+  # a lot start with a lowercase character - fix that
+  ref[!grepl("^d[A-Z]", ref)] <- gsub("^([a-z])", "\\U\\1", ref[!grepl("^d[A-Z]", ref)], perl = TRUE)
+  # specific one for the French that are named dOrbigny 
+  ref[grepl("^d[A-Z]", ref)] <- gsub("^d", "d'", ref[grepl("^d[A-Z]", ref)])
+  ref <- gsub(" +", " ", ref)
+  ref
+}
+
+df_remove_nonASCII <- function(df) {
+  # Remove non-ASCII characters (these are not allowed by CRAN)
+  df %>%
+    mutate_if(is.character, iconv, from = "UTF-8", to = "ASCII//TRANSLIT") %>% 
+    # also remove invalid characters
+    mutate_if(is.character, ~gsub("[\"'`]+", "", .)) %>%
+    AMR:::dataset_UTF8_to_ASCII()
+}
+
+abbreviate_mo <- function(x, minlength = 5, prefix = "", ...) {
+  # keep a starting Latin ae
+  suppressWarnings(
+    gsub("^ae", "\u00E6\u00E6", x, ignore.case = TRUE) %>% 
+      abbreviate(minlength = minlength,
+                 use.classes = TRUE,
+                 method = "both.sides", ...) %>% 
+      paste0(prefix, .) %>% 
+      toupper() %>% 
+      gsub("(\u00C6|\u00E6)+", "AE", .)
+  )
+}
+
+# Read data ---------------------------------------------------------------
+
+taxonomy <- read_csv("~/Downloads/taxonomy.csv")
+
+# Create synonyms ---------------------------------------------------------
+
+new_synonyms <- taxonomy %>%
+  left_join(taxonomy,
+            by = c("record_lnk" = "record_no"), 
+            suffix = c("", ".new")) %>% 
+  filter(!is.na(record_lnk)) %>% 
+  mutate_all(~ifelse(is.na(.), "", .)) %>% 
+  transmute(fullname = trimws(paste(genus_name, sp_epithet, subsp_epithet)),
+            fullname_new = trimws(paste(genus_name.new, sp_epithet.new, subsp_epithet.new)),
+            ref = get_author_year(authors),
+            prevalence = 0) %>% 
+  distinct(fullname, .keep_all = TRUE) %>% 
+  filter(fullname != fullname_new) %>% 
+  # this part joins this table to itself to correct for entries that had >1 renames, 
+  # such as:
+  # Bacteroides tectum -> Bacteroides tectus
+  # Bacteroides tectus -> Bacteroides pyogenes
+  left_join(., ., 
+            by = c("fullname_new" = "fullname"), 
+            suffix = c("", ".2")) %>%
+  mutate(fullname_new = ifelse(!is.na(fullname_new.2), fullname_new.2, fullname_new),
+         ref = ifelse(!is.na(ref.2), ref.2, ref)) %>%
+  select(-ends_with(".2")) 
+
+mo_became_synonym <- microorganisms %>% 
+  filter(fullname %in% new_synonyms$fullname)
+
+updated_microorganisms <- taxonomy %>%
+  filter(is.na(record_lnk)) %>% 
+  mutate_all(~ifelse(is.na(.), "", .)) %>% 
+  transmute(mo = "",
+            fullname = trimws(paste(genus_name, sp_epithet, subsp_epithet)),
+            kingdom = "Bacteria",
+            phylum = "",
+            class = "",
+            order = "",
+            family = "",
+            genus = trimws(genus_name),
+            species = trimws(replace_na(sp_epithet, "")),
+            subspecies = trimws(replace_na(subsp_epithet, "")),
+            rank = case_when(subspecies == "" & species == "" ~ "genus",
+                             subspecies == "" ~ "species",
+                             TRUE ~ "subsp."),
+            ref = get_author_year(authors),
+            species_id = as.character(record_no),
+            source = "LSPN",
+            prevalence = 0,
+            snomed = NA)
+
+new_microorganisms <- updated_microorganisms %>% 
+  filter(!fullname %in% microorganisms$fullname)
+
+genera_with_mo_code <- updated_microorganisms %>%
+  filter(genus %in% (microorganisms %>% filter(kingdom == "Bacteria", rank == "genus") %>% pull(genus))) %>%
+  distinct(genus) %>% 
+  left_join(microorganisms %>% filter(kingdom == "Bacteria", rank == "genus") %>% select(mo, genus),
+            by = "genus")
+  
+genera_without_mo_code <- updated_microorganisms %>% 
+  filter(!genus %in% genera_with_mo_code$genus) %>% 
+  pull(genus) %>% 
+  unique()
+
+genera_without_mo_code_abbr <- genera_without_mo_code %>% 
+  abbreviate_mo(5, prefix = "B_")
+genera_without_mo_code_abbr[genera_without_mo_code_abbr %in% microorganisms$mo] <- abbreviate_mo(genera_without_mo_code[genera_without_mo_code_abbr %in% microorganisms$mo], 6, prefix = "B_")
+genera_without_mo_code_abbr[genera_without_mo_code_abbr %in% microorganisms$mo] <- abbreviate_mo(genera_without_mo_code[genera_without_mo_code_abbr %in% microorganisms$mo], 7, prefix = "B_")
+# all unique??
+sum(genera_without_mo_code_abbr %in% microorganisms$mo) == 0
+
+genus_abb <- tibble(genus = genera_without_mo_code,
+                    abbr = genera_without_mo_code_abbr) %>% 
+  bind_rows(microorganisms %>%
+              filter(kingdom == "Bacteria", rank == "genus", !genus %in% genera_without_mo_code) %>%
+              transmute(genus, abbr = as.character(mo))) %>% 
+  arrange(genus)
+
+
+# Update taxonomy ---------------------------------------------------------
+
+# fill in the taxonomy of new genera
+updated_taxonomy <- tibble(phylum = character(0),
+                           class = character(0),
+                           order = character(0),
+                           family = character(0),
+                           genus = character(0))
+for (page in LETTERS) {
+  message("Downloading page ", page, "... ", appendLF = FALSE)
+  url <- paste0("https://lpsn.dsmz.de/genus?page=", page)
+  
+  x <- xml2::read_html(url) %>% 
+    rvest::html_node(".main-list") %>% 
+    # evety list element with a set <id> attribute
+    rvest::html_nodes("li[id]")
+  for (i in seq_len(length(x))) {
+    txt <- x %>% 
+      magrittr::extract2(i) %>% 
+      rvest::html_text() %>%
+      gsub("\\[[A-Za-z]+, no [a-z]+\\]", "NA", .) %>% 
+      gsub("Candidatus ", "", ., fixed = TRUE) %>% 
+      gsub("[ \t\r\n\"]+", "|", .) %>%
+      gsub("\\|ShowHide.*", "", .) %>% 
+      gsub("[\\[\\]]", "", ., fixed = TRUE) %>% 
+      gsub("^\\|", "", .) %>% 
+      strsplit("|", fixed = TRUE) %>% 
+      unlist()
+    txt[txt == "NA"] <- ""
+    txt <- gsub("[^A-Za-z]+", "", txt)
+    updated_taxonomy <- updated_taxonomy %>% 
+      bind_rows(tibble(phylum = txt[2],
+                       class = txt[3],
+                       order = txt[4],
+                       family = txt[5],
+                       genus = txt[6]))
+  }
+  message(length(x), " entries (total ", nrow(updated_taxonomy), ")")
+}
+
+# Create new microorganisms -----------------------------------------------
+
+new_microorganisms <- new_microorganisms %>% 
+  left_join(genus_abb, by = "genus") %>% 
+  group_by(genus) %>% 
+  mutate(species_abb = abbreviate_mo(species, 4)) %>% 
+  group_by(genus, species) %>% 
+  mutate(subspecies_abb = abbreviate_mo(subspecies, 4)) %>% 
+  ungroup() %>% 
+  mutate(mo = paste(abbr, species_abb, subspecies_abb, sep = "_"),
+         mo = gsub("_+$", "", mo)) %>% 
+  select(-matches("abb"))
+
+# add taxonomy new microorganisms
+MOs <- microorganisms %>%
+  mutate(mo = as.character(mo)) %>%
+  bind_rows(new_microorganisms) %>%
+  arrange(fullname)
+
+# unique MO codes
+MOs$mo[which(duplicated(MOs$mo))] <- paste0(MOs$mo[which(duplicated(MOs$mo))], 1)
+# all unique?
+!any(duplicated(MOs$mo))
+
+MOs <- MOs %>% 
+  # remove entries that are now a synonym
+  filter(!fullname %in% new_synonyms$fullname) %>% 
+  # update the taxonomy
+  left_join(updated_taxonomy, by = "genus", suffix = c("", ".new")) %>%
+  mutate(phylum = ifelse(!is.na(phylum.new), phylum.new, phylum),
+         class = ifelse(!is.na(class.new), class.new, class),
+         order = ifelse(!is.na(order.new), order.new, order),
+         family = ifelse(!is.na(family.new), family.new, family)) %>% 
+  select(-ends_with(".new")) %>%
+  # update prevalence based on taxonomy (Berends et al., 2021)
+  mutate(prevalence = case_when(
+    class == "Gammaproteobacteria"
+    | genus %in% c("Enterococcus", "Staphylococcus", "Streptococcus")
+    ~ 1,
+    kingdom %in% c("Archaea", "Bacteria", "Chromista", "Fungi")
+    & (phylum %in% c("Proteobacteria",
+                     "Firmicutes",
+                     "Actinobacteria",
+                     "Sarcomastigophora")
+       | genus %in% c("Absidia", "Acremonium", "Actinotignum", "Alternaria", "Anaerosalibacter", "Apophysomyces",
+                      "Arachnia", "Aspergillus", "Aureobacterium", "Aureobasidium", "Bacteroides", "Basidiobolus",
+                      "Beauveria", "Blastocystis", "Branhamella", "Calymmatobacterium", "Candida", "Capnocytophaga",
+                      "Catabacter", "Chaetomium", "Chryseobacterium", "Chryseomonas", "Chrysonilia", "Cladophialophora",
+                      "Cladosporium", "Conidiobolus", "Cryptococcus", "Curvularia", "Exophiala", "Exserohilum",
+                      "Flavobacterium", "Fonsecaea", "Fusarium", "Fusobacterium", "Hendersonula", "Hypomyces",
+                      "Koserella", "Lelliottia", "Leptosphaeria", "Leptotrichia", "Malassezia", "Malbranchea",
+                      "Mortierella", "Mucor", "Mycocentrospora", "Mycoplasma", "Nectria", "Ochroconis",
+                      "Oidiodendron", "Phoma", "Piedraia", "Pithomyces", "Pityrosporum", "Prevotella", "Pseudallescheria", 
+                      "Rhizomucor", "Rhizopus", "Rhodotorula", "Scolecobasidium", "Scopulariopsis", "Scytalidium", 
+                      "Sporobolomyces", "Stachybotrys", "Stomatococcus", "Treponema", "Trichoderma", "Trichophyton", 
+                      "Trichosporon", "Tritirachium", "Ureaplasma")
+       | rank %in% c("kingdom", "phylum", "class", "order", "family"))
+    ~ 2,
+    TRUE ~ 3
+  ))
+
+# add all mssing genera, families and orders
+MOs <- MOs %>% 
+  bind_rows(
+    MOs %>% 
+      arrange(genus, species) %>%
+      distinct(genus, .keep_all = TRUE) %>%
+      filter(rank == "species", source != "manually added") %>%
+      mutate(mo = gsub("^([A-Z]_[A-Z]+)_.*", "\\1", mo),
+             fullname = genus, 
+             species = "", 
+             subspecies = "", 
+             rank = "genus", 
+             species_id = "",
+             snomed = NA,
+             ref = NA_character_),
+    MOs %>% 
+      group_by(family) %>%
+      filter(!any(rank == "family") & n() > 1) %>%
+      ungroup() %>% 
+      arrange(family) %>%
+      distinct(family, .keep_all = TRUE) %>% 
+      filter(!family %in% c("", NA), source != "manually added") %>%
+      mutate(mo = paste0(substr(kingdom, 1, 1), "_[FAM]_",
+                         abbreviate(family,
+                                    minlength = 8,
+                                    use.classes = TRUE,
+                                    method = "both.sides",
+                                    strict = FALSE)),
+             mo = toupper(mo),
+             fullname = family,
+             genus = "",
+             species = "", 
+             subspecies = "", 
+             rank = "family", 
+             species_id = "",
+             snomed = NA,
+             ref = NA_character_),
+    MOs %>% 
+      group_by(order) %>%
+      filter(!any(rank == "order") & n() > 1) %>%
+      ungroup() %>% 
+      arrange(order) %>%
+      distinct(order, .keep_all = TRUE) %>% 
+      filter(!order %in% c("", NA), source != "manually added") %>%
+      mutate(mo = paste0(substr(kingdom, 1, 1), "_[ORD]_",
+                         abbreviate(order,
+                                    minlength = 8,
+                                    use.classes = TRUE,
+                                    method = "both.sides",
+                                    strict = FALSE)),
+             mo = toupper(mo),
+             fullname = order,
+             family = "",
+             genus = "",
+             species = "", 
+             subspecies = "", 
+             rank = "order", 
+             species_id = "",
+             snomed = NA,
+             ref = NA_character_)
+  ) %>%
+  arrange(fullname)
+
+# clean up
+MOs <- MOs %>% 
+  df_remove_nonASCII()
+
+
+# Merge synonyms ----------------------------------------------------------
+
+# remove synonyms that are now valid names
+MOs.old <- microorganisms.old %>% 
+  # add new synonyms
+  bind_rows(new_synonyms) %>% 
+  filter(!fullname %in% MOs$fullname) %>% 
+  arrange(fullname) %>% 
+  distinct(fullname, fullname_new, .keep_all = TRUE) %>% 
+  # add prevalence to old taxonomic names
+  select(-prevalence) %>% 
+  left_join(MOs %>% select(fullname, prevalence), by = c("fullname_new" = "fullname")) %>% 
+  # clean up
+  df_remove_nonASCII()
+
+# Keep old codes for translation ------------------------------------------
+
+# add removed microbial IDs to the internal translation table so old package versions keep working
+MOs.translation <- microorganisms %>% 
+  filter(!mo %in% MOs$mo) %>%
+  select(mo, fullname) %>%
+  left_join(new_synonyms) %>% 
+  left_join(MOs %>% transmute(fullname_new = fullname, mo2 = as.character(mo))) %>% 
+  select(mo_old = mo, mo_new = mo2) %>% 
+  distinct()
+MOs.translation <- AMR:::microorganisms.translation %>% 
+  left_join(MOs.translation %>% select(mo_new_update = mo_new, mo_new = mo_old)) %>% 
+  mutate(mo_new = as.character(ifelse(!is.na(mo_new_update), mo_new_update, mo_new))) %>% 
+  select(-mo_new_update) %>% 
+  bind_rows(
+    # old IDs used in microorganisms.codes must put in here as well
+    microorganisms.codes %>%
+      filter(!mo %in% MOs$mo) %>%
+      transmute(mo_old = mo, fullname = mo_name(mo)) %>%
+      left_join(MOs.old %>%
+                  select(fullname, fullname_new)) %>%
+      left_join(MOs %>%
+                  select(mo_new = mo, fullname_new = fullname)) %>%
+      transmute(mo_old = as.character(mo_old), mo_new)) %>% 
+  arrange(mo_old) %>% 
+  filter(mo_old != mo_new,
+         !mo_old %in% MOs$mo) %>%
+  left_join(., ., 
+            by = c("mo_new" = "mo_old"), 
+            suffix = c("", ".2")) %>%
+  mutate(mo_new = ifelse(!is.na(mo_new.2), mo_new.2, mo_new)) %>% 
+  distinct(mo_old, mo_new) %>% 
+  # clean up
+  df_remove_nonASCII()
+
+message("microorganisms new:     ", sum(!MOs$fullname %in% c(microorganisms$fullname, MOs.old$fullname)))
+message("microorganisms renamed: ", sum(!MOs.old$fullname %in% microorganisms.old$fullname))
+
+
+# Save --------------------------------------------------------------------
+
+# class <mo>
+class(MOs$mo) <- c("mo", "character")
+class(MOs.translation$mo_new) <- c("mo", "character")
+
+microorganisms <- MOs
+microorganisms.old <- MOs.old
+microorganisms.translation <- MOs.translation
+
+# on the server, do:
+usethis::use_data(microorganisms, overwrite = TRUE, version = 2, compress = "xz")
+usethis::use_data(microorganisms.old, overwrite = TRUE, version = 2)
+saveRDS(microorganisms.translation, file = "data-raw/microorganisms.translation.rds", version = 2)
+rm(microorganisms)
+rm(microorganisms.old)
+rm(microorganisms.translation)
+# to save microorganisms.translation internally to the package
+devtools::load_all(".")
+source("data-raw/_internals.R")
+
+# load new data sets
+devtools::load_all(".")
+
+# reset previously changed mo codes
+rsi_translation$mo <- as.mo(rsi_translation$mo, language = NULL)
+usethis::use_data(rsi_translation, overwrite = TRUE, version = 2)
+rm(rsi_translation)
+
+microorganisms.codes$mo <- as.mo(microorganisms.codes$mo, language = NULL)
+usethis::use_data(microorganisms.codes, overwrite = TRUE, version = 2)
+rm(microorganisms.codes)
+
+example_isolates$mo <- as.mo(example_isolates$mo, language = NULL)
+usethis::use_data(example_isolates, overwrite = TRUE, version = 2)
+rm(example_isolates)
+
+intrinsic_resistant$microorganism <- suppressMessages(mo_name(intrinsic_resistant$microorganism))
+usethis::use_data(intrinsic_resistant, overwrite = TRUE, version = 2)
+rm(intrinsic_resistant)
+
+# load new data sets again
+devtools::load_all(".")
+source("data-raw/_internals.R")
+devtools::load_all(".")
+
+
+# Test updates ------------------------------------------------------------
+
+# and check: these codes should not be missing (will otherwise throw a unit test error):
+AMR::microorganisms.codes %>% filter(!mo %in% MOs$mo)
+AMR::rsi_translation %>% filter(!mo %in% MOs$mo)
+AMR:::microorganisms.translation %>% filter(!mo_new %in% MOs$mo)
+AMR::example_isolates %>% filter(!mo %in% MOs$mo)
+
+# Don't forget to add SNOMED codes! (data-raw/snomed.R)
+
+# run the unit tests
+Sys.setenv(NOT_CRAN = "true")
+testthat::test_file("tests/testthat/test-data.R")
+testthat::test_file("tests/testthat/test-mo.R")
+testthat::test_file("tests/testthat/test-mo_property.R")

data-raw/rsi.md5

@@ -1 +1 @@
-f816b536ddd71d00e1adcdaba97d0329
+aa80f169fc2cba97f5eedc1d24ca8c03

data-raw/rsi_translation.txt

@@ -1982,7 +1982,7 @@
 "EUCAST 2020"	"MIC"		"Streptococcus pyogenes"	"Azithromycin"	"Streptococcus A,B,C,G"		0.25	0.5	FALSE
 "EUCAST 2020"	"MIC"		"Streptococcus salivarius"	"Azithromycin"	"Streptococcus A,B,C,G"		0.25	0.5	FALSE
 "EUCAST 2020"	"MIC"		"Streptococcus sanguinis"	"Azithromycin"	"Streptococcus A,B,C,G"		0.25	0.5	FALSE
-"EUCAST 2020"	"MIC"		"Mycobacterium africanum"	"Bedaquiline"	"M.tuberculosis"		0.25	0.25	FALSE
+"EUCAST 2020"	"MIC"		"Mycobacterium tuberculosis"	"Bedaquiline"	"M.tuberculosis"		0.25	0.25	FALSE
 "EUCAST 2020"	"DISK"		"Enterobacterales"	"Ceftobiprole"	"Enterobacterales"	"5ug"	23	23	FALSE
 "EUCAST 2020"	"MIC"		"Enterobacterales"	"Ceftobiprole"	"Enterobacterales"		0.25	0.25	FALSE
 "EUCAST 2020"	"DISK"		"Staphylococcus aureus"	"Ceftobiprole"	"Staphylococcus"	"5ug"	17	17	FALSE
@@ -2367,7 +2367,7 @@
 "EUCAST 2020"	"MIC"		"Streptococcus pyogenes"	"Delafloxacin"	"Streptococcus A,B,C,G"		0.03	0.03	FALSE
 "EUCAST 2020"	"MIC"		"Streptococcus salivarius"	"Delafloxacin"	"Streptococcus A,B,C,G"		0.03	0.03	FALSE
 "EUCAST 2020"	"MIC"		"Streptococcus sanguinis"	"Delafloxacin"	"Streptococcus A,B,C,G"		0.03	0.03	FALSE
-"EUCAST 2020"	"MIC"		"Mycobacterium africanum"	"Delamanid"	"M.tuberculosis"		0.06	0.06	FALSE
+"EUCAST 2020"	"MIC"		"Mycobacterium tuberculosis"	"Delamanid"	"M.tuberculosis"		0.06	0.06	FALSE
 "EUCAST 2020"	"MIC"		"Burkholderia pseudomallei"	"Doxycycline"	"B.pseudomallei"		0.001	2	FALSE
 "EUCAST 2020"	"MIC"		"Haemophilus influenzae"	"Doxycycline"	"H.influenzae"		1	2	FALSE
 "EUCAST 2020"	"MIC"		"Kingella kingae"	"Doxycycline"	"K.kingae"		0.5	0.5	FALSE
@@ -3743,7 +3743,7 @@
 "EUCAST 2019"	"MIC"		"Streptococcus pyogenes"	"Azithromycin"	"Streptococcus A,B,C,G"		0.25	0.5	FALSE
 "EUCAST 2019"	"MIC"		"Streptococcus salivarius"	"Azithromycin"	"Streptococcus A,B,C,G"		0.25	0.5	FALSE
 "EUCAST 2019"	"MIC"		"Streptococcus sanguinis"	"Azithromycin"	"Streptococcus A,B,C,G"		0.25	0.5	FALSE
-"EUCAST 2019"	"MIC"		"Mycobacterium africanum"	"Bedaquiline"	"M.tuberculosis"		0.25	0.25	FALSE
+"EUCAST 2019"	"MIC"		"Mycobacterium tuberculosis"	"Bedaquiline"	"M.tuberculosis"		0.25	0.25	FALSE
 "EUCAST 2019"	"DISK"		"Enterobacterales"	"Ceftobiprole"	"Enterobacterales"	"5ug"	23	23	FALSE
 "EUCAST 2019"	"MIC"		"Enterobacterales"	"Ceftobiprole"	"Enterobacterales"		0.25	0.25	FALSE
 "EUCAST 2019"	"DISK"		"Staphylococcus aureus"	"Ceftobiprole"	"Staphylococcus"	"5ug"	17	17	FALSE
@@ -4098,7 +4098,7 @@
 "EUCAST 2019"	"MIC"		"Streptococcus pyogenes"	"Daptomycin"	"Streptococcus A,B,C,G"		1	1	FALSE
 "EUCAST 2019"	"MIC"		"Streptococcus salivarius"	"Daptomycin"	"Streptococcus A,B,C,G"		1	1	FALSE
 "EUCAST 2019"	"MIC"		"Streptococcus sanguinis"	"Daptomycin"	"Streptococcus A,B,C,G"		1	1	FALSE
-"EUCAST 2019"	"MIC"		"Mycobacterium africanum"	"Delamanid"	"M.tuberculosis"		0.06	0.06	FALSE
+"EUCAST 2019"	"MIC"		"Mycobacterium tuberculosis"	"Delamanid"	"M.tuberculosis"		0.06	0.06	FALSE
 "EUCAST 2019"	"MIC"		"Haemophilus influenzae"	"Doxycycline"	"H.influenzae"		1	2	FALSE
 "EUCAST 2019"	"MIC"		"Kingella kingae"	"Doxycycline"	"K.kingae"		0.5	0.5	FALSE
 "EUCAST 2019"	"MIC"		"Moraxella catarrhalis"	"Doxycycline"	"M.catarrhalis"		1	2	FALSE

data-raw/snomed.R

@@ -26,89 +26,44 @@
 library(AMR)
 library(tidyverse)
 
-# go to https://www.nictiz.nl/standaardisatie/terminologiecentrum/referentielijsten/micro-organismen/ (Ctrl/Cmd + A in table)
-# read the table from clipboard
-snomed <- clipr::read_clip_tbl(skip = 2)
-snomed <- snomed %>%
-  dplyr::filter(gsub("(^genus |^familie |^stam |ss.? |subsp.? |subspecies )", "", 
-              Omschrijving.,
-              ignore.case = TRUE) %in% c(microorganisms$fullname, 
-                                         microorganisms.old$fullname)) %>% 
-  dplyr::transmute(fullname = mo_name(Omschrijving.),
-            snomed = as.integer(Id)) %>% 
-  dplyr::filter(!fullname %like% "unknown")
-snomed_trans <- snomed %>%
-  group_by(fullname) %>%
-  mutate(snomed_list = list(snomed)) %>%
-  ungroup() %>%
-  select(fullname, snomed = snomed_list) %>%
-  distinct(fullname, .keep_all = TRUE)
+# we will use Public Health Information Network Vocabulary Access and Distribution System (PHIN VADS)
+# as a source, which copies directly from the latest US SNOMED CT version
+# - go to https://phinvads.cdc.gov/vads/ViewValueSet.action?oid=2.16.840.1.114222.4.11.1009
+# - check that current online version is higher than SNOMED_VERSION$current_version
+# - if so, click on 'Download Value Set', choose 'TXT'
+snomed <- read_tsv("data-raw/SNOMED_PHVS_Microorganism_CDC_V12.txt", skip = 3) %>% 
+  select(1:2) %>% 
+  set_names(c("snomed", "mo"))
 
-microorganisms <- AMR::microorganisms %>% 
-  left_join(snomed_trans)
-# remove the NULLs, set to NA
-microorganisms$snomed <- lapply(microorganisms$snomed, function(x) if (length(x) == 0)  NA else x)
+# save all valid genera, species and subspecies
+vctr <- unique(unlist(strsplit(c(microorganisms$fullname, microorganisms.old$fullname), " ")))
+vctr <- tolower(vctr[vctr %like% "^[a-z]+$"])
 
-microorganisms <- dataset_UTF8_to_ASCII(microorganisms)
+# remove all parts of the name that are no valid values in genera, species or subspecies
+snomed <- snomed %>% 
+  mutate(fullname = vapply(FUN.VALUE = character(1),
+                           # split on space and/or comma
+                           strsplit(tolower(mo), "[ ,]"),
+                           function(x) trimws(paste0(x[x %in% vctr], collapse = " "))),
+         # remove " group"
+         fullname = gsub(" group", "", fullname, fixed = TRUE))
 
-usethis::use_data(microorganisms, overwrite = TRUE)
-rm(microorganisms)
+snomed_keep <- snomed %>% 
+  filter(fullname %in% tolower(c(microorganisms$fullname, microorganisms.old$fullname))) %>% 
+  group_by(fullname_lower = fullname) %>% 
+  summarise(snomed = list(snomed))
 
-# OLD ---------------------------------------------------------------------
+# save to microorganisms data set
+microorganisms <- microorganisms %>%
+  # remove old snomed
+  select(-snomed) %>%
+  # create dummy var for joining
+  mutate(fullname_lower = tolower(fullname)) %>%
+  # join new snomed
+  left_join(snomed_keep) %>%
+  # remove dummy var
+  select(-fullname_lower) %>% 
+  AMR:::dataset_UTF8_to_ASCII()
+usethis::use_data(microorganisms, overwrite = TRUE, compress = "xz")
 
-# baseUrl <- 'https://browser.ihtsdotools.org/snowstorm/snomed-ct'
-# edition <- 'MAIN'
-# version <- '2019-07-31'
-# 
-# microorganisms.snomed <- data.frame(conceptid = character(0),
-#                                     mo = character(0),
-#                                     stringsAsFactors = FALSE)
-# microorganisms$snomed <- ""
-# 
-# # for (i in 1:50) {
-# for (i in 1:1000) {
-#   
-#   if (i %% 10 == 0) {
-#     cat(paste0(i, " - ", cleaner::percentage(i / nrow(microorganisms)), "\n"))
-#   }
-#   
-#   mo_data <- microorganisms %>% 
-#     filter(mo == microorganisms$mo[i]) %>% 
-#     as.list()
-#   
-#   if (!mo_data$rank %in% c("genus", "species")) {
-#     next
-#   }
-#   
-#   searchTerm <- paste0(
-#     ifelse(mo_data$rank == "genus", "Genus ", ""),
-#     mo_data$fullname, 
-#     " (organism)")
-#   
-#   url <- paste0(baseUrl, '/browser/',
-#                 edition, '/', 
-#                 version, 
-#                 '/descriptions?term=', curl::curl_escape(searchTerm),
-#                 '&mode=fullText&activeFilter=true&limit=', 250)
-#   results <- url %>% 
-#     httr::GET() %>%
-#     httr::content(type = "text", encoding = "UTF-8") %>% 
-#     jsonlite::fromJSON(flatten = TRUE) %>% 
-#     .$items
-#   if (NROW(results) == 0) {
-#     next
-#   } else {
-#     message("Adding ", crayon::italic(mo_data$fullname))
-#   }
-#   
-#   tryCatch(
-#     microorganisms$snomed[i] <- results %>% filter(term == searchTerm) %>% pull(concept.conceptId),
-#     error = function(e) invisible()
-#   )
-#   
-#   if (nrow(results) > 1) {
-#       microorganisms.snomed <- microorganisms.snomed %>% 
-#         bind_rows(tibble(conceptid = results %>% filter(term != searchTerm) %>% pull(concept.conceptId) %>% unique(),
-#                          mo = as.character(mo_data$mo)))
-#   }
-# }
+# don't forget to update the version number in SNOMED_VERSION in ./R/globals.R!

data-raw/translations.tsv

@@ -1,412 +1,262 @@
-lang	pattern	replacement	fixed	ignore.case	affect_mo_name
-de	Coagulase-negative Staphylococcus	Koagulase-negative Staphylococcus	FALSE	FALSE	TRUE
-de	Coagulase-positive Staphylococcus	Koagulase-positive Staphylococcus	FALSE	FALSE	TRUE
-de	Beta-haemolytic Streptococcus	Beta-hämolytischer Streptococcus	FALSE	FALSE	TRUE
-de	unknown Gram-negatives	unbekannte Gramnegativen	FALSE	FALSE	TRUE
-de	unknown Gram-positives	unbekannte Grampositiven	FALSE	FALSE	TRUE
-de	unknown fungus	unbekannter Pilze	FALSE	FALSE	TRUE
-de	unknown yeast	unbekannte Hefe	FALSE	FALSE	TRUE
-de	unknown name	unbekannte Name	FALSE	FALSE	TRUE
-de	unknown kingdom	unbekanntes Reich	FALSE	FALSE	TRUE
-de	unknown phylum	unbekannter Stamm	FALSE	FALSE	TRUE
-de	unknown class	unbekannte Klasse	FALSE	FALSE	TRUE
-de	unknown order	unbekannte Ordnung	FALSE	FALSE	TRUE
-de	unknown family	unbekannte Familie	FALSE	FALSE	TRUE
-de	unknown genus	unbekannte Gattung	FALSE	FALSE	TRUE
-de	unknown species	unbekannte Art	FALSE	FALSE	TRUE
-de	unknown subspecies	unbekannte Unterart	FALSE	FALSE	TRUE
-de	unknown rank	unbekannter Rang	FALSE	FALSE	TRUE
-de	CoNS	KNS	TRUE	FALSE	TRUE
-de	CoPS	KPS	TRUE	FALSE	TRUE
-de	Gram-negative	Gramnegativ	FALSE	FALSE	FALSE
-de	Gram-positive	Grampositiv	FALSE	FALSE	FALSE
-de	^Bacteria$	Bakterien	FALSE	FALSE	FALSE
-de	^Fungi$	Pilze	FALSE	FALSE	FALSE
-de	^Yeasts$	Hefen	FALSE	FALSE	FALSE
-de	^Protozoa$	Protozoen	FALSE	FALSE	FALSE
-de	biogroup	Biogruppe	FALSE	FALSE	FALSE
-de	biotype	Biotyp	FALSE	FALSE	FALSE
-de	vegetative	vegetativ	FALSE	FALSE	FALSE
-de	([([ ]*?)group	\\1Gruppe	FALSE	FALSE	FALSE
-de	([([ ]*?)Group	\\1Gruppe	FALSE	FALSE	FALSE
-de	no .*growth	keine? .*wachstum	FALSE	TRUE	FALSE
-de	(^| )no|not	keine?	FALSE	TRUE	FALSE
-nl	Coagulase-negative Staphylococcus	Coagulase-negatieve Staphylococcus	FALSE	FALSE	TRUE
-nl	Coagulase-positive Staphylococcus	Coagulase-positieve Staphylococcus	FALSE	FALSE	TRUE
-nl	Beta-haemolytic Streptococcus	Beta-hemolytische Streptococcus	FALSE	FALSE	TRUE
-nl	unknown Gram-negatives	onbekende Gram-negatieven	FALSE	FALSE	TRUE
-nl	unknown Gram-positives	onbekende Gram-positieven	FALSE	FALSE	TRUE
-nl	unknown fungus	onbekende schimmel	FALSE	FALSE	TRUE
-nl	unknown yeast	onbekende gist	FALSE	FALSE	TRUE
-nl	unknown name	onbekende naam	FALSE	FALSE	TRUE
-nl	unknown kingdom	onbekend koninkrijk	FALSE	FALSE	TRUE
-nl	unknown phylum	onbekend fylum	FALSE	FALSE	TRUE
-nl	unknown class	onbekende klasse	FALSE	FALSE	TRUE
-nl	unknown order	onbekende orde	FALSE	FALSE	TRUE
-nl	unknown family	onbekende familie	FALSE	FALSE	TRUE
-nl	unknown genus	onbekend geslacht	FALSE	FALSE	TRUE
-nl	unknown species	onbekende soort	FALSE	FALSE	TRUE
-nl	unknown subspecies	onbekende ondersoort	FALSE	FALSE	TRUE
-nl	unknown rank	onbekende rang	FALSE	FALSE	TRUE
-nl	CoNS	CNS	TRUE	FALSE	TRUE
-nl	CoPS	CPS	TRUE	FALSE	TRUE
-nl	Gram-negative	Gram-negatief	FALSE	FALSE	FALSE
-nl	Gram-positive	Gram-positief	FALSE	FALSE	FALSE
-nl	^Bacteria$	Bacteriën	FALSE	FALSE	FALSE
-nl	^Fungi$	Schimmels	FALSE	FALSE	FALSE
-nl	^Yeasts$	Gisten	FALSE	FALSE	FALSE
-nl	^Protozoa$	Protozoën	FALSE	FALSE	FALSE
-nl	biogroup	biogroep	FALSE	FALSE	FALSE
-nl	vegetative	vegetatief	FALSE	FALSE	FALSE
-nl	([([ ]*?)group	\\1groep	FALSE	FALSE	FALSE
-nl	([([ ]*?)Group	\\1Groep	FALSE	FALSE	FALSE
-nl	antibiotic	antibioticum	FALSE	FALSE	FALSE
-nl	Antibiotic	Antibioticum	FALSE	FALSE	FALSE
-nl	Drug	Middel	FALSE	FALSE	FALSE
-nl	drug	middel	FALSE	FALSE	FALSE
-nl	no .*growth	geen .*groei	FALSE	TRUE	FALSE
-nl	no|not	geen|niet	FALSE	TRUE	FALSE
-es	Coagulase-negative Staphylococcus	Staphylococcus coagulasa negativo	FALSE	FALSE	TRUE
-es	Coagulase-positive Staphylococcus	Staphylococcus coagulasa positivo	FALSE	FALSE	TRUE
-es	Beta-haemolytic Streptococcus	Streptococcus Beta-hemolítico	FALSE	FALSE	TRUE
-es	unknown Gram-negatives	Gram negativos desconocidos	FALSE	FALSE	TRUE
-es	unknown Gram-positives	Gram positivos desconocidos	FALSE	FALSE	TRUE
-es	unknown fungus	hongo desconocido	FALSE	FALSE	TRUE
-es	unknown yeast	levadura desconocida	FALSE	FALSE	TRUE
-es	unknown name	nombre desconocido	FALSE	FALSE	TRUE
-es	unknown kingdom	reino desconocido	FALSE	FALSE	TRUE
-es	unknown phylum	filo desconocido	FALSE	FALSE	TRUE
-es	unknown class	clase desconocida	FALSE	FALSE	TRUE
-es	unknown order	orden desconocido	FALSE	FALSE	TRUE
-es	unknown family	familia desconocida	FALSE	FALSE	TRUE
-es	unknown genus	género desconocido	FALSE	FALSE	TRUE
-es	unknown species	especie desconocida	FALSE	FALSE	TRUE
-es	unknown subspecies	subespecie desconocida	FALSE	FALSE	TRUE
-es	unknown rank	rango desconocido	FALSE	FALSE	TRUE
-es	CoNS	SCN	TRUE	FALSE	TRUE
-es	CoPS	SCP	TRUE	FALSE	TRUE
-es	Gram-negative	Gram negativo	FALSE	FALSE	FALSE
-es	Gram-positive	Gram positivo	FALSE	FALSE	FALSE
-es	^Bacteria$	Bacterias	FALSE	FALSE	FALSE
-es	^Fungi$	Hongos	FALSE	FALSE	FALSE
-es	^Yeasts$	Levaduras	FALSE	FALSE	FALSE
-es	^Protozoa$	Protozoarios	FALSE	FALSE	FALSE
-es	biogroup	biogrupo	FALSE	FALSE	FALSE
-es	biotype	biotipo	FALSE	FALSE	FALSE
-es	vegetative	vegetativo	FALSE	FALSE	FALSE
-es	([([ ]*?)group	\\1grupo	FALSE	FALSE	FALSE
-es	([([ ]*?)Group	\\1Grupo	FALSE	FALSE	FALSE
-es	no .*growth	no .*crecimientonon	FALSE	TRUE	FALSE
-es	no|not	no|sin	FALSE	TRUE	FALSE
-it	Coagulase-negative Staphylococcus	Staphylococcus negativo coagulasi	FALSE	FALSE	TRUE
-it	Coagulase-positive Staphylococcus	Staphylococcus positivo coagulasi	FALSE	FALSE	TRUE
-it	Beta-haemolytic Streptococcus	Streptococcus Beta-emolitico	FALSE	FALSE	TRUE
-it	unknown Gram-negatives	Gram negativi sconosciuti	FALSE	FALSE	TRUE
-it	unknown Gram-positives	Gram positivi sconosciuti	FALSE	FALSE	TRUE
-it	unknown fungus	fungo sconosciuto	FALSE	FALSE	TRUE
-it	unknown yeast	lievito sconosciuto	FALSE	FALSE	TRUE
-it	unknown name	nome sconosciuto	FALSE	FALSE	TRUE
-it	unknown kingdom	regno sconosciuto	FALSE	FALSE	TRUE
-it	unknown phylum	phylum sconosciuto	FALSE	FALSE	TRUE
-it	unknown class	classe sconosciuta	FALSE	FALSE	TRUE
-it	unknown order	ordine sconosciuto	FALSE	FALSE	TRUE
-it	unknown family	famiglia sconosciuta	FALSE	FALSE	TRUE
-it	unknown genus	genere sconosciuto	FALSE	FALSE	TRUE
-it	unknown species	specie sconosciute	FALSE	FALSE	TRUE
-it	unknown subspecies	sottospecie sconosciute	FALSE	FALSE	TRUE
-it	unknown rank	grado sconosciuto	FALSE	FALSE	TRUE
-it	Gram-negative	Gram negativo	FALSE	FALSE	FALSE
-it	Gram-positive	Gram positivo	FALSE	FALSE	FALSE
-it	^Bacteria$	Batteri	FALSE	FALSE	FALSE
-it	^Fungi$	Funghi	FALSE	FALSE	FALSE
-it	^Yeasts$	Lieviti	FALSE	FALSE	FALSE
-it	^Protozoa$	Protozoi	FALSE	FALSE	FALSE
-it	biogroup	biogruppo	FALSE	FALSE	FALSE
-it	biotype	biotipo	FALSE	FALSE	FALSE
-it	vegetative	vegetativo	FALSE	FALSE	FALSE
-it	([([ ]*?)group	\\1gruppo	FALSE	FALSE	FALSE
-it	([([ ]*?)Group	\\1Gruppo	FALSE	FALSE	FALSE
-it	no .*growth	sem .*crescimento	FALSE	TRUE	FALSE
-it	no|not	sem	FALSE	TRUE	FALSE
-fr	Coagulase-negative Staphylococcus	Staphylococcus à coagulase négative	FALSE	FALSE	TRUE
-fr	Coagulase-positive Staphylococcus	Staphylococcus à coagulase positif	FALSE	FALSE	TRUE
-fr	Beta-haemolytic Streptococcus	Streptococcus Bêta-hémolytique	FALSE	FALSE	TRUE
-fr	unknown Gram-negatives	Gram négatifs inconnus	FALSE	FALSE	TRUE
-fr	unknown Gram-positives	Gram positifs inconnus	FALSE	FALSE	TRUE
-fr	unknown fungus	champignon inconnu	FALSE	FALSE	TRUE
-fr	unknown yeast	levure inconnue	FALSE	FALSE	TRUE
-fr	unknown name	nom inconnu	FALSE	FALSE	TRUE
-fr	unknown kingdom	règme inconnu	FALSE	FALSE	TRUE
-fr	unknown phylum	embranchement inconnu	FALSE	FALSE	TRUE
-fr	unknown class	classe inconnue	FALSE	FALSE	TRUE
-fr	unknown order	ordre inconnu	FALSE	FALSE	TRUE
-fr	unknown family	famille inconnue	FALSE	FALSE	TRUE
-fr	unknown genus	genre inconnu	FALSE	FALSE	TRUE
-fr	unknown species	espèce inconnue	FALSE	FALSE	TRUE
-fr	unknown subspecies	sous-espèce inconnue	FALSE	FALSE	TRUE
-fr	unknown rank	rang inconnu	FALSE	FALSE	TRUE
-fr	Gram-negative	Gram négatif	FALSE	FALSE	FALSE
-fr	Gram-positive	Gram positif	FALSE	FALSE	FALSE
-fr	^Bacteria$	Bactéries	FALSE	FALSE	FALSE
-fr	^Fungi$	Champignons	FALSE	FALSE	FALSE
-fr	^Yeasts$	Levures	FALSE	FALSE	FALSE
-fr	^Protozoa$	Protozoaires	FALSE	FALSE	FALSE
-fr	biogroup	biogroupe	FALSE	FALSE	FALSE
-fr	vegetative	végétatif	FALSE	FALSE	FALSE
-fr	([([ ]*?)group	\\1groupe	FALSE	FALSE	FALSE
-fr	([([ ]*?)Group	\\1Groupe	FALSE	FALSE	FALSE
-fr	no .*growth	pas .*croissance	FALSE	TRUE	FALSE
-fr	no|not	non	FALSE	TRUE	FALSE
-pt	Coagulase-negative Staphylococcus	Staphylococcus coagulase negativo	FALSE	FALSE	TRUE
-pt	Coagulase-positive Staphylococcus	Staphylococcus coagulase positivo	FALSE	FALSE	TRUE
-pt	Beta-haemolytic Streptococcus	Streptococcus Beta-hemolítico	FALSE	FALSE	TRUE
-pt	unknown Gram-negatives	Gram negativos desconhecidos	FALSE	FALSE	TRUE
-pt	unknown Gram-positives	Gram positivos desconhecidos	FALSE	FALSE	TRUE
-pt	unknown fungus	fungo desconhecido	FALSE	FALSE	TRUE
-pt	unknown yeast	levedura desconhecida	FALSE	FALSE	TRUE
-pt	unknown name	nome desconhecido	FALSE	FALSE	TRUE
-pt	unknown kingdom	reino desconhecido	FALSE	FALSE	TRUE
-pt	unknown phylum	filo desconhecido	FALSE	FALSE	TRUE
-pt	unknown class	classe desconhecida	FALSE	FALSE	TRUE
-pt	unknown order	ordem desconhecido	FALSE	FALSE	TRUE
-pt	unknown family	família desconhecida	FALSE	FALSE	TRUE
-pt	unknown genus	gênero desconhecido	FALSE	FALSE	TRUE
-pt	unknown species	espécies desconhecida	FALSE	FALSE	TRUE
-pt	unknown subspecies	subespécies desconhecida	FALSE	FALSE	TRUE
-pt	unknown rank	classificação desconhecido	FALSE	FALSE	TRUE
-pt	Gram-negative	Gram negativo	FALSE	FALSE	FALSE
-pt	Gram-positive	Gram positivo	FALSE	FALSE	FALSE
-pt	^Bacteria$	Bactérias	FALSE	FALSE	FALSE
-pt	^Fungi$	Fungos	FALSE	FALSE	FALSE
-pt	^Yeasts$	Leveduras	FALSE	FALSE	FALSE
-pt	^Protozoa$	Protozoários	FALSE	FALSE	FALSE
-pt	biogroup	biogrupo	FALSE	FALSE	FALSE
-pt	biotype	biótipo	FALSE	FALSE	FALSE
-pt	vegetative	vegetativo	FALSE	FALSE	FALSE
-pt	([([ ]*?)group	\\1grupo	FALSE	FALSE	FALSE
-pt	([([ ]*?)Group	\\1Grupo	FALSE	FALSE	FALSE
-pt	no .*growth	sem .*crescimento	FALSE	TRUE	FALSE
-pt	no|not	sem	FALSE	TRUE	FALSE
-de	clavulanic acid	Clavulansäure	FALSE	TRUE	FALSE
-nl	4-aminosalicylic acid	4-aminosalicylzuur	TRUE	FALSE	FALSE
-nl	Adefovir dipivoxil	Adefovir	TRUE	FALSE	FALSE
-nl	Aldesulfone sodium	Aldesulfon	TRUE	FALSE	FALSE
-nl	Amikacin	Amikacine	TRUE	FALSE	FALSE
-nl	Amoxicillin	Amoxicilline	TRUE	FALSE	FALSE
-nl	Amoxicillin/beta-lactamase inhibitor	Amoxicilline/enzymremmer	TRUE	FALSE	FALSE
-nl	Amphotericin B	Amfotericine B	TRUE	FALSE	FALSE
-nl	Ampicillin	Ampicilline	TRUE	FALSE	FALSE
-nl	Ampicillin/beta-lactamase inhibitor	Ampicilline/enzymremmer	TRUE	FALSE	FALSE
-nl	Anidulafungin	Anidulafungine	TRUE	FALSE	FALSE
-nl	Azidocillin	Azidocilline	TRUE	FALSE	FALSE
-nl	Azithromycin	Azitromycine	TRUE	FALSE	FALSE
-nl	Azlocillin	Azlocilline	TRUE	FALSE	FALSE
-nl	Bacampicillin	Bacampicilline	TRUE	FALSE	FALSE
-nl	Bacitracin	Bacitracine	TRUE	FALSE	FALSE
-nl	Benzathine benzylpenicillin	Benzylpenicillinebenzathine	TRUE	FALSE	FALSE
-nl	Benzathine phenoxymethylpenicillin	Fenoxymethylpenicillinebenzathine	TRUE	FALSE	FALSE
-nl	Benzylpenicillin	Benzylpenicilline	TRUE	FALSE	FALSE
-nl	Calcium aminosalicylate	Aminosalicylzuur	TRUE	FALSE	FALSE
-nl	Capreomycin	Capreomycine	TRUE	FALSE	FALSE
-nl	Carbenicillin	Carbenicilline	TRUE	FALSE	FALSE
-nl	Carindacillin	Carindacilline	TRUE	FALSE	FALSE
-nl	Caspofungin	Caspofungine	TRUE	FALSE	FALSE
-nl	Ce(f|ph)acetrile	Cefacetril	FALSE	FALSE	FALSE
-nl	Ce(f|ph)alexin	Cefalexine	FALSE	FALSE	FALSE
-nl	Ce(f|ph)alotin	Cefalotine	FALSE	FALSE	FALSE
-nl	Ce(f|ph)amandole	Cefamandol	FALSE	FALSE	FALSE
-nl	Ce(f|ph)apirin	Cefapirine	FALSE	FALSE	FALSE
-nl	Ce(f|ph)azedone	Cefazedon	FALSE	FALSE	FALSE
-nl	Ce(f|ph)azolin	Cefazoline	FALSE	FALSE	FALSE
-nl	Ce(f|ph)alothin	Cefalotine	FALSE	FALSE	FALSE
-nl	Ce(f|ph)alexin	Cefalexine	FALSE	FALSE	FALSE
-nl	Ce(f|ph)epime	Cefepim	FALSE	FALSE	FALSE
-nl	Ce(f|ph)ixime	Cefixim	FALSE	FALSE	FALSE
-nl	Ce(f|ph)menoxime	Cefmenoxim	FALSE	FALSE	FALSE
-nl	Ce(f|ph)metazole	Cefmetazol	FALSE	FALSE	FALSE
-nl	Ce(f|ph)odizime	Cefodizim	FALSE	FALSE	FALSE
-nl	Ce(f|ph)onicid	Cefonicide	FALSE	FALSE	FALSE
-nl	Ce(f|ph)operazone	Cefoperazon	FALSE	FALSE	FALSE
-nl	Ce(f|ph)operazone/beta-lactamase inhibitor	Cefoperazon/enzymremmer	FALSE	FALSE	FALSE
-nl	Ce(f|ph)otaxime	Cefotaxim	FALSE	FALSE	FALSE
-nl	Ce(f|ph)oxitin	Cefoxitine	FALSE	FALSE	FALSE
-nl	Ce(f|ph)pirome	Cefpirom	FALSE	FALSE	FALSE
-nl	Ce(f|ph)podoxime	Cefpodoxim	FALSE	FALSE	FALSE
-nl	Ce(f|ph)radine	Cefradine	FALSE	FALSE	FALSE
-nl	Ce(f|ph)sulodin	Cefsulodine	FALSE	FALSE	FALSE
-nl	Ce(f|ph)tazidime	Ceftazidim	FALSE	FALSE	FALSE
-nl	Ce(f|ph)tezole	Ceftezol	FALSE	FALSE	FALSE
-nl	Ce(f|ph)tizoxime	Ceftizoxim	FALSE	FALSE	FALSE
-nl	Ce(f|ph)triaxone	Ceftriaxon	FALSE	FALSE	FALSE
-nl	Ce(f|ph)uroxime	Cefuroxim	FALSE	FALSE	FALSE
-nl	Ce(f|ph)uroxime/metronidazole	Cefuroxim/andere antibacteriele middelen	FALSE	FALSE	FALSE
-nl	Chloramphenicol	Chlooramfenicol	TRUE	FALSE	FALSE
-nl	Chlortetracycline	Chloortetracycline	TRUE	FALSE	FALSE
-nl	Cinoxacin	Cinoxacine	TRUE	FALSE	FALSE
-nl	Ciprofloxacin	Ciprofloxacine	TRUE	FALSE	FALSE
-nl	Clarithromycin	Claritromycine	TRUE	FALSE	FALSE
-nl	Clavulanic acid	Clavulaanzuur	TRUE	FALSE	FALSE
-nl	clavulanic acid	clavulaanzuur	TRUE	FALSE	FALSE
-nl	Clindamycin	Clindamycine	TRUE	FALSE	FALSE
-nl	Clometocillin	Clometocilline	TRUE	FALSE	FALSE
-nl	Clotrimazole	Clotrimazol	TRUE	FALSE	FALSE
-nl	Cloxacillin	Cloxacilline	TRUE	FALSE	FALSE
-nl	Colistin	Colistine	TRUE	FALSE	FALSE
-nl	Dapsone	Dapson	TRUE	FALSE	FALSE
-nl	Daptomycin	Daptomycine	TRUE	FALSE	FALSE
-nl	Dibekacin	Dibekacine	TRUE	FALSE	FALSE
-nl	Dicloxacillin	Dicloxacilline	TRUE	FALSE	FALSE
-nl	Dirithromycin	Diritromycine	TRUE	FALSE	FALSE
-nl	Econazole	Econazol	TRUE	FALSE	FALSE
-nl	Enoxacin	Enoxacine	TRUE	FALSE	FALSE
-nl	Epicillin	Epicilline	TRUE	FALSE	FALSE
-nl	Erythromycin	Erytromycine	TRUE	FALSE	FALSE
-nl	Ethambutol/isoniazid	Ethambutol/isoniazide	TRUE	FALSE	FALSE
-nl	Fleroxacin	Fleroxacine	TRUE	FALSE	FALSE
-nl	Flucloxacillin	Flucloxacilline	TRUE	FALSE	FALSE
-nl	Fluconazole	Fluconazol	TRUE	FALSE	FALSE
-nl	Flucytosine	Fluorocytosine	TRUE	FALSE	FALSE
-nl	Flurithromycin	Fluritromycine	TRUE	FALSE	FALSE
-nl	Fosfomycin	Fosfomycine	TRUE	FALSE	FALSE
-nl	Fusidic acid	Fusidinezuur	TRUE	FALSE	FALSE
-nl	Gatifloxacin	Gatifloxacine	TRUE	FALSE	FALSE
-nl	Gemifloxacin	Gemifloxacine	TRUE	FALSE	FALSE
-nl	Gentamicin	Gentamicine	TRUE	FALSE	FALSE
-nl	Grepafloxacin	Grepafloxacine	TRUE	FALSE	FALSE
-nl	Hachimycin	Hachimycine	TRUE	FALSE	FALSE
-nl	Hetacillin	Hetacilline	TRUE	FALSE	FALSE
-nl	Imipenem/cilastatin	Imipenem/enzymremmer	TRUE	FALSE	FALSE
-nl	Inosine pranobex	Inosiplex	TRUE	FALSE	FALSE
-nl	Isepamicin	Isepamicine	TRUE	FALSE	FALSE
-nl	Isoconazole	Isoconazol	TRUE	FALSE	FALSE
-nl	Isoniazid	Isoniazide	TRUE	FALSE	FALSE
-nl	Itraconazole	Itraconazol	TRUE	FALSE	FALSE
-nl	Josamycin	Josamycine	TRUE	FALSE	FALSE
-nl	Kanamycin	Kanamycine	TRUE	FALSE	FALSE
-nl	Ketoconazole	Ketoconazol	TRUE	FALSE	FALSE
-nl	Levofloxacin	Levofloxacine	TRUE	FALSE	FALSE
-nl	Lincomycin	Lincomycine	TRUE	FALSE	FALSE
-nl	Lomefloxacin	Lomefloxacine	TRUE	FALSE	FALSE
-nl	Lysozyme	Lysozym	TRUE	FALSE	FALSE
-nl	Mandelic acid	Amandelzuur	TRUE	FALSE	FALSE
-nl	Metampicillin	Metampicilline	TRUE	FALSE	FALSE
-nl	Meticillin	Meticilline	TRUE	FALSE	FALSE
-nl	Metisazone	Metisazon	TRUE	FALSE	FALSE
-nl	Metronidazole	Metronidazol	TRUE	FALSE	FALSE
-nl	Mezlocillin	Mezlocilline	TRUE	FALSE	FALSE
-nl	Micafungin	Micafungine	TRUE	FALSE	FALSE
-nl	Miconazole	Miconazol	TRUE	FALSE	FALSE
-nl	Midecamycin	Midecamycine	TRUE	FALSE	FALSE
-nl	Miocamycin	Miocamycine	TRUE	FALSE	FALSE
-nl	Moxifloxacin	Moxifloxacine	TRUE	FALSE	FALSE
-nl	Mupirocin	Mupirocine	TRUE	FALSE	FALSE
-nl	Nalidixic acid	Nalidixinezuur	TRUE	FALSE	FALSE
-nl	Neomycin	Neomycine	TRUE	FALSE	FALSE
-nl	Netilmicin	Netilmicine	TRUE	FALSE	FALSE
-nl	Nitrofurantoin	Nitrofurantoine	TRUE	FALSE	FALSE
-nl	Norfloxacin	Norfloxacine	TRUE	FALSE	FALSE
-nl	Novobiocin	Novobiocine	TRUE	FALSE	FALSE
-nl	Nystatin	Nystatine	TRUE	FALSE	FALSE
-nl	Ofloxacin	Ofloxacine	TRUE	FALSE	FALSE
-nl	Oleandomycin	Oleandomycine	TRUE	FALSE	FALSE
-nl	Ornidazole	Ornidazol	TRUE	FALSE	FALSE
-nl	Oxacillin	Oxacilline	TRUE	FALSE	FALSE
-nl	Oxolinic acid	Oxolinezuur	TRUE	FALSE	FALSE
-nl	Oxytetracycline	Oxytetracycline	TRUE	FALSE	FALSE
-nl	Pazufloxacin	Pazufloxacine	TRUE	FALSE	FALSE
-nl	Pefloxacin	Pefloxacine	TRUE	FALSE	FALSE
-nl	Penamecillin	Penamecilline	TRUE	FALSE	FALSE
-nl	Penicillin	Penicilline	TRUE	FALSE	FALSE
-nl	Pheneticillin	Feneticilline	TRUE	FALSE	FALSE
-nl	Phenoxymethylpenicillin	Fenoxymethylpenicilline	TRUE	FALSE	FALSE
-nl	Pipemidic acid	Pipemidinezuur	TRUE	FALSE	FALSE
-nl	Piperacillin	Piperacilline	TRUE	FALSE	FALSE
-nl	Piperacillin/beta-lactamase inhibitor	Piperacilline/enzymremmer	TRUE	FALSE	FALSE
-nl	Piromidic acid	Piromidinezuur	TRUE	FALSE	FALSE
-nl	Pivampicillin	Pivampicilline	TRUE	FALSE	FALSE
-nl	Polymyxin B	Polymyxine B	TRUE	FALSE	FALSE
-nl	Posaconazole	Posaconazol	TRUE	FALSE	FALSE
-nl	Pristinamycin	Pristinamycine	TRUE	FALSE	FALSE
-nl	Procaine benzylpenicillin	Benzylpenicillineprocaine	TRUE	FALSE	FALSE
-nl	Propicillin	Propicilline	TRUE	FALSE	FALSE
-nl	Prulifloxacin	Prulifloxacine	TRUE	FALSE	FALSE
-nl	Quinupristin/dalfopristin	Quinupristine/dalfopristine	TRUE	FALSE	FALSE
-nl	Ribostamycin	Ribostamycine	TRUE	FALSE	FALSE
-nl	Rifabutin	Rifabutine	TRUE	FALSE	FALSE
-nl	Rifampicin	Rifampicine	TRUE	FALSE	FALSE
-nl	Rifampicin/pyrazinamide/ethambutol/isoniazid	Rifampicine/pyrazinamide/ethambutol/isoniazide	TRUE	FALSE	FALSE
-nl	Rifampicin/pyrazinamide/isoniazid	Rifampicine/pyrazinamide/isoniazide	TRUE	FALSE	FALSE
-nl	Rifampicin/isoniazid	Rifampicine/isoniazide	TRUE	FALSE	FALSE
-nl	Rifamycin	Rifamycine	TRUE	FALSE	FALSE
-nl	Rifaximin	Rifaximine	TRUE	FALSE	FALSE
-nl	Rokitamycin	Rokitamycine	TRUE	FALSE	FALSE
-nl	Rosoxacin	Rosoxacine	TRUE	FALSE	FALSE
-nl	Roxithromycin	Roxitromycine	TRUE	FALSE	FALSE
-nl	Rufloxacin	Rufloxacine	TRUE	FALSE	FALSE
-nl	Sisomicin	Sisomicine	TRUE	FALSE	FALSE
-nl	Sodium aminosalicylate	Aminosalicylzuur	TRUE	FALSE	FALSE
-nl	Sparfloxacin	Sparfloxacine	TRUE	FALSE	FALSE
-nl	Spectinomycin	Spectinomycine	TRUE	FALSE	FALSE
-nl	Spiramycin	Spiramycine	TRUE	FALSE	FALSE
-nl	Spiramycin/metronidazole	Spiramycine/metronidazol	TRUE	FALSE	FALSE
-nl	Staphylococcus immunoglobulin	Stafylokokkenimmunoglobuline	TRUE	FALSE	FALSE
-nl	Streptoduocin	Streptoduocine	TRUE	FALSE	FALSE
-nl	Streptomycin	Streptomycine	TRUE	FALSE	FALSE
-nl	Streptomycin/isoniazid	Streptomycine/isoniazide	TRUE	FALSE	FALSE
-nl	Sulbenicillin	Sulbenicilline	TRUE	FALSE	FALSE
-nl	Sulfadiazine/tetroxoprim	Sulfadiazine/tetroxoprim	TRUE	FALSE	FALSE
-nl	Sulfadiazine/trimethoprim	Sulfadiazine/trimethoprim	TRUE	FALSE	FALSE
-nl	Sulfadimidine/trimethoprim	Sulfadimidine/trimethoprim	TRUE	FALSE	FALSE
-nl	Sulfafurazole	Sulfafurazol	TRUE	FALSE	FALSE
-nl	Sulfaisodimidine	Sulfisomidine	TRUE	FALSE	FALSE
-nl	Sulfalene	Sulfaleen	TRUE	FALSE	FALSE
-nl	Sulfamazone	Sulfamazon	TRUE	FALSE	FALSE
-nl	Sulfamerazine/trimethoprim	Sulfamerazine/trimethoprim	TRUE	FALSE	FALSE
-nl	Sulfamethizole	Sulfamethizol	TRUE	FALSE	FALSE
-nl	Sulfamethoxazole	Sulfamethoxazol	TRUE	FALSE	FALSE
-nl	Sulfamethoxazole/trimethoprim	Sulfamethoxazol/trimethoprim	TRUE	FALSE	FALSE
-nl	Sulfametoxydiazine	Sulfamethoxydiazine	TRUE	FALSE	FALSE
-nl	Sulfametrole/trimethoprim	Sulfametrol/trimethoprim	TRUE	FALSE	FALSE
-nl	Sulfamoxole	Sulfamoxol	TRUE	FALSE	FALSE
-nl	Sulfamoxole/trimethoprim	Sulfamoxol/trimethoprim	TRUE	FALSE	FALSE
-nl	Sulfaperin	Sulfaperine	TRUE	FALSE	FALSE
-nl	Sulfaphenazole	Sulfafenazol	TRUE	FALSE	FALSE
-nl	Sulfathiazole	Sulfathiazol	TRUE	FALSE	FALSE
-nl	Sulfathiourea	Sulfathioureum	TRUE	FALSE	FALSE
-nl	Sultamicillin	Sultamicilline	TRUE	FALSE	FALSE
-nl	Talampicillin	Talampicilline	TRUE	FALSE	FALSE
-nl	Teicoplanin	Teicoplanine	TRUE	FALSE	FALSE
-nl	Telithromycin	Telitromycine	TRUE	FALSE	FALSE
-nl	Temafloxacin	Temafloxacine	TRUE	FALSE	FALSE
-nl	Temocillin	Temocilline	TRUE	FALSE	FALSE
-nl	Tenofovir disoproxil	Tenofovir	TRUE	FALSE	FALSE
-nl	Terizidone	Terizidon	TRUE	FALSE	FALSE
-nl	Thiamphenicol	Thiamfenicol	TRUE	FALSE	FALSE
-nl	Thioacetazone/isoniazid	Thioacetazon/isoniazide	TRUE	FALSE	FALSE
-nl	Ticarcillin	Ticarcilline	TRUE	FALSE	FALSE
-nl	Ticarcillin/beta-lactamase inhibitor	Ticarcilline/enzymremmer	TRUE	FALSE	FALSE
-nl	Ticarcillin/clavulanic acid	Ticarcilline/clavulaanzuur	TRUE	FALSE	FALSE
-nl	Tinidazole	Tinidazol	TRUE	FALSE	FALSE
-nl	Tobramycin	Tobramycine	TRUE	FALSE	FALSE
-nl	Trimethoprim/sulfamethoxazole	Cotrimoxazol	TRUE	FALSE	FALSE
-nl	Troleandomycin	Troleandomycine	TRUE	FALSE	FALSE
-nl	Trovafloxacin	Trovafloxacine	TRUE	FALSE	FALSE
-nl	Vancomycin	Vancomycine	TRUE	FALSE	FALSE
-nl	Voriconazole	Voriconazol	TRUE	FALSE	FALSE
-nl	Aminoglycosides	Aminoglycosiden	TRUE	FALSE	FALSE
-nl	Amphenicols	Amfenicolen	TRUE	FALSE	FALSE
-nl	Antifungals/antimycotics	Antifungica/antimycotica	TRUE	FALSE	FALSE
-nl	Antimycobacterials	Antimycobacteriele middelen	TRUE	FALSE	FALSE
-nl	Beta-lactams/penicillins	Beta-lactams/penicillines	TRUE	FALSE	FALSE
-nl	Cephalosporins (1st gen.)	Cefalosporines (1e gen.)	TRUE	FALSE	FALSE
-nl	Cephalosporins (2nd gen.)	Cefalosporines (2e gen.)	TRUE	FALSE	FALSE
-nl	Cephalosporins (3rd gen.)	Cefalosporines (3e gen.)	TRUE	FALSE	FALSE
-nl	Cephalosporins (4th gen.)	Cefalosporines (4e gen.)	TRUE	FALSE	FALSE
-nl	Cephalosporins (5th gen.)	Cefalosporines (5e gen.)	TRUE	FALSE	FALSE
-nl	Cephalosporins (unclassified gen.)	Cefalosporines (ongeclassificeerd)	TRUE	FALSE	FALSE
-nl	Cephalosporins	Cefalosporines	TRUE	FALSE	FALSE
-nl	Glycopeptides	Glycopeptiden	TRUE	FALSE	FALSE
-nl	Macrolides/lincosamides	Macroliden/lincosamiden	TRUE	FALSE	FALSE
-nl	Other antibacterials	Overige antibiotica	TRUE	FALSE	FALSE
-nl	Polymyxins	Polymyxines	TRUE	FALSE	FALSE
-nl	Quinolones	Quinolonen	TRUE	FALSE	FALSE
+pattern	regular_expr	case_sensitive	affect_mo_name	de	nl	es	it	fr	pt
+Coagulase-negative Staphylococcus	TRUE	TRUE	TRUE	Koagulase-negative Staphylococcus	Coagulase-negatieve Staphylococcus	Staphylococcus coagulasa negativo	Staphylococcus negativo coagulasi	Staphylococcus à coagulase négative	Staphylococcus coagulase negativo
+Coagulase-positive Staphylococcus	TRUE	TRUE	TRUE	Koagulase-positive Staphylococcus	Coagulase-positieve Staphylococcus	Staphylococcus coagulasa positivo	Staphylococcus positivo coagulasi	Staphylococcus à coagulase positif	Staphylococcus coagulase positivo
+Beta-haemolytic Streptococcus	TRUE	TRUE	TRUE	Beta-hämolytischer Streptococcus	Beta-hemolytische Streptococcus	Streptococcus Beta-hemolítico	Streptococcus Beta-emolitico	Streptococcus Bêta-hémolytique	Streptococcus Beta-hemolítico
+unknown Gram-negatives	TRUE	TRUE	TRUE	unbekannte Gramnegativen	onbekende Gram-negatieven	Gram negativos desconocidos	Gram negativi sconosciuti	Gram négatifs inconnus	Gram negativos desconhecidos
+unknown Gram-positives	TRUE	TRUE	TRUE	unbekannte Grampositiven	onbekende Gram-positieven	Gram positivos desconocidos	Gram positivi sconosciuti	Gram positifs inconnus	Gram positivos desconhecidos
+unknown fungus	TRUE	TRUE	TRUE	unbekannter Pilze	onbekende schimmel	hongo desconocido	fungo sconosciuto	champignon inconnu	fungo desconhecido
+unknown yeast	TRUE	TRUE	TRUE	unbekannte Hefe	onbekende gist	levadura desconocida	lievito sconosciuto	levure inconnue	levedura desconhecida
+unknown name	TRUE	TRUE	TRUE	unbekannte Name	onbekende naam	nombre desconocido	nome sconosciuto	nom inconnu	nome desconhecido
+unknown kingdom	TRUE	TRUE	TRUE	unbekanntes Reich	onbekend koninkrijk	reino desconocido	regno sconosciuto	règme inconnu	reino desconhecido
+unknown phylum	TRUE	TRUE	TRUE	unbekannter Stamm	onbekend fylum	filo desconocido	phylum sconosciuto	embranchement inconnu	filo desconhecido
+unknown class	TRUE	TRUE	TRUE	unbekannte Klasse	onbekende klasse	clase desconocida	classe sconosciuta	classe inconnue	classe desconhecida
+unknown order	TRUE	TRUE	TRUE	unbekannte Ordnung	onbekende orde	orden desconocido	ordine sconosciuto	ordre inconnu	ordem desconhecido
+unknown family	TRUE	TRUE	TRUE	unbekannte Familie	onbekende familie	familia desconocida	famiglia sconosciuta	famille inconnue	família desconhecida
+unknown genus	TRUE	TRUE	TRUE	unbekannte Gattung	onbekend geslacht	género desconocido	genere sconosciuto	genre inconnu	gênero desconhecido
+unknown species	TRUE	TRUE	TRUE	unbekannte Art	onbekende soort	especie desconocida	specie sconosciute	espèce inconnue	espécies desconhecida
+unknown subspecies	TRUE	TRUE	TRUE	unbekannte Unterart	onbekende ondersoort	subespecie desconocida	sottospecie sconosciute	sous-espèce inconnue	subespécies desconhecida
+unknown rank	TRUE	TRUE	TRUE	unbekannter Rang	onbekende rang	rango desconocido	grado sconosciuto	rang inconnu	classificação desconhecido
+CoNS	FALSE	TRUE	TRUE	KNS	CNS	SCN			
+CoPS	FALSE	TRUE	TRUE	KPS	CPS	SCP			
+Gram-negative	TRUE	TRUE	FALSE	Gramnegativ	Gram-negatief	Gram negativo	Gram negativo	Gram négatif	Gram negativo
+Gram-positive	TRUE	TRUE	FALSE	Grampositiv	Gram-positief	Gram positivo	Gram positivo	Gram positif	Gram positivo
+^Bacteria$	TRUE	TRUE	FALSE	Bakterien	Bacteriën	Bacterias	Batteri	Bactéries	Bactérias
+^Fungi$	TRUE	TRUE	FALSE	Pilze	Schimmels	Hongos	Funghi	Champignons	Fungos
+^Yeasts$	TRUE	TRUE	FALSE	Hefen	Gisten	Levaduras	Lieviti	Levures	Leveduras
+^Protozoa$	TRUE	TRUE	FALSE	Protozoen	Protozoën	Protozoarios	Protozoi	Protozoaires	Protozoários
+biogroup	TRUE	TRUE	FALSE	Biogruppe	biogroep	biogrupo	biogruppo	biogroupe	biogrupo
+biotype	TRUE	TRUE	FALSE	Biotyp		biotipo	biotipo		biótipo
+vegetative	TRUE	TRUE	FALSE	vegetativ	vegetatief	vegetativo	vegetativo	végétatif	vegetativo
+([([ ]*?)group	TRUE	TRUE	FALSE	\\1Gruppe	\\1groep	\\1grupo	\\1gruppo	\\1groupe	\\1grupo
+([([ ]*?)Group	TRUE	TRUE	FALSE	\\1Gruppe	\\1Groep	\\1Grupo	\\1Gruppo	\\1Groupe	\\1Grupo
+no .*growth	TRUE	FALSE	FALSE	keine? .*wachstum	geen .*groei	no .*crecimientonon	sem .*crescimento	pas .*croissance	sem .*crescimento
+no|not	TRUE	FALSE	FALSE	keine?	geen|niet	no|sin	sem	non	sem
+Susceptible	TRUE	FALSE	FALSE	Empfindlich	Gevoelig	Susceptible			
+Intermediate	TRUE	FALSE	FALSE	Mittlere	Intermediair	Intermedio			
+Incr. exposure	TRUE	FALSE	FALSE	Empfindlich, erh Belastung	'Incr. exposure'	'Incr. exposure'			
+Resistant	TRUE	FALSE	FALSE	Resistent	Resistent	Resistente			
+antibiotic	TRUE	TRUE	FALSE	Antibiotikum	antibioticum	antibiótico			
+Antibiotic	TRUE	TRUE	FALSE	Antibiotikum	Antibioticum	Antibiótico			
+Drug	TRUE	TRUE	FALSE	Medikament	Middel	Fármaco			
+drug	TRUE	TRUE	FALSE	Medikament	middel	fármaco			
+4-aminosalicylic acid	FALSE	TRUE	FALSE	4-Aminosalicylsäure	4-aminosalicylzuur	Ácido 4-aminosalicílico			
+Adefovir dipivoxil	FALSE	TRUE	FALSE	Adefovir Dipivoxil	Adefovir	Adefovir dipivoxil			
+Aldesulfone sodium	FALSE	TRUE	FALSE	Aldesulfon-Natrium	Aldesulfon	Aldesulfona sódica			
+Amikacin	FALSE	TRUE	FALSE	Amikacin	Amikacine	Amikacina			
+Amoxicillin	FALSE	TRUE	FALSE	Amoxicillin	Amoxicilline	Amoxicilina			
+Amoxicillin/beta-lactamase inhibitor	FALSE	TRUE	FALSE	Amoxicillin/Beta-Lactamase-Hemmer	Amoxicilline/enzymremmer	amoxicilina/inhib. de la beta-lactamasa			
+Amphotericin B	FALSE	TRUE	FALSE	Amphotericin B	Amfotericine B	Anfotericina B			
+Ampicillin	FALSE	TRUE	FALSE	Ampicillin	Ampicilline	Ampicilina			
+Ampicillin/beta-lactamase inhibitor	FALSE	TRUE	FALSE	Ampicillin/Beta-Laktamase-Hemmer	Ampicilline/enzymremmer	Ampicilina/inhib. de la betalactamasa			
+Anidulafungin	FALSE	TRUE	FALSE	Anidulafungin	Anidulafungine	Anidulafungina			
+Azidocillin	FALSE	TRUE	FALSE	Azidocillin	Azidocilline	Azidocilina			
+Azithromycin	FALSE	TRUE	FALSE	Azithromycin	Azitromycine	Azitromicina			
+Azlocillin	FALSE	TRUE	FALSE	Azlocillin	Azlocilline	Azlocilina			
+Bacampicillin	FALSE	TRUE	FALSE	Bacampicillin	Bacampicilline	Bacampicilina			
+Bacitracin	FALSE	TRUE	FALSE	Bacitracin	Bacitracine	Bacitracina			
+Benzathine benzylpenicillin	FALSE	TRUE	FALSE	Benzathin-Benzylpenicillin	Benzylpenicillinebenzathine	Bencilpenicilina benzatínica			
+Benzathine phenoxymethylpenicillin	FALSE	TRUE	FALSE	Benzathin-Phenoxymethylpenicillin	Fenoxymethylpenicillinebenzathine	Fenoximetilpenicilina benzatínica			
+Benzylpenicillin	FALSE	TRUE	FALSE	Benzylpenicillin	Benzylpenicilline	Bencilpenicilina			
+Calcium aminosalicylate	FALSE	TRUE	FALSE	Kalzium-Aminosalicylat	Aminosalicylzuur	Aminosalicilato de calcio			
+Capreomycin	FALSE	TRUE	FALSE	Capreomycin	Capreomycine	Capreomicina			
+Carbenicillin	FALSE	TRUE	FALSE	Carbenicillin	Carbenicilline	Carbenicilina			
+Carindacillin	FALSE	TRUE	FALSE	Carindacillin	Carindacilline	Carindacilina			
+Caspofungin	FALSE	TRUE	FALSE	Caspofungin	Caspofungine	Caspofungina			
+Ce(f|ph)acetrile	TRUE	TRUE	FALSE	Cefacetril	Cefacetril	Cefacetrilo			
+Ce(f|ph)alotin	TRUE	TRUE	FALSE	Cefalotin	Cefalotine	Cefalotina			
+Ce(f|ph)amandole	TRUE	TRUE	FALSE	Cefamandol	Cefamandol	Cefamandole			
+Ce(f|ph)apirin	TRUE	TRUE	FALSE	Cefapirin	Cefapirine	Cefapirina			
+Ce(f|ph)azedone	TRUE	TRUE	FALSE	Cefazedon	Cefazedon	Cefazedona			
+Ce(f|ph)azolin	TRUE	TRUE	FALSE	Cefazolin	Cefazoline	Cefazolina			
+Ce(f|ph)alothin	TRUE	TRUE	FALSE	Cefalothin	Cefalotine	Cefalotina			
+Ce(f|ph)alexin	TRUE	TRUE	FALSE	Cefalexin	Cefalexine	Cefalexina			
+Ce(f|ph)epime	TRUE	TRUE	FALSE	Cefepim	Cefepim	Cefepime			
+Ce(f|ph)ixime	TRUE	TRUE	FALSE	Cefixim	Cefixim	Cefixima			
+Ce(f|ph)menoxime	TRUE	TRUE	FALSE	Cefmenoxim	Cefmenoxim	Cefmenoxima			
+Ce(f|ph)metazole	TRUE	TRUE	FALSE	Cefmetazol	Cefmetazol	Cefmetazol			
+Ce(f|ph)odizime	TRUE	TRUE	FALSE	Cefodizim	Cefodizim	Cefodizima			
+Ce(f|ph)onicid	TRUE	TRUE	FALSE	Cefonicid	Cefonicide	Cefonicid			
+Ce(f|ph)operazone	TRUE	TRUE	FALSE	Cefoperazon	Cefoperazon	Cefoperazona			
+Ce(f|ph)operazone/beta-lactamase inhibitor	TRUE	TRUE	FALSE	Cefoperazon/Beta-Lactamase-Hemmer	Cefoperazon/enzymremmer	Cefoperazona/inhib. de la betalactamasa			
+Ce(f|ph)otaxime	TRUE	TRUE	FALSE	Cefotaxim	Cefotaxim	Cefotaxima			
+Ce(f|ph)oxitin	TRUE	TRUE	FALSE	Cefoxitin	Cefoxitine	Cefoxitina			
+Ce(f|ph)pirome	TRUE	TRUE	FALSE	Cefpirom	Cefpirom	Cefpirome			
+Ce(f|ph)podoxime	TRUE	TRUE	FALSE	Cefpodoxim	Cefpodoxim	Cefpodoxima			
+Ce(f|ph)radine	TRUE	TRUE	FALSE	Cefradin	Cefradine	Cefradina			
+Ce(f|ph)sulodin	TRUE	TRUE	FALSE	Cefsulodin	Cefsulodine	Cefsulodina			
+Ce(f|ph)tazidime	TRUE	TRUE	FALSE	Ceftazidim	Ceftazidim	Ceftazidima			
+Ce(f|ph)tezole	TRUE	TRUE	FALSE	Ceftezol	Ceftezol	Ceftezol			
+Ce(f|ph)tizoxime	TRUE	TRUE	FALSE	Ceftizoxim	Ceftizoxim	Ceftizoxima			
+Ce(f|ph)triaxone	TRUE	TRUE	FALSE	Ceftriaxon	Ceftriaxon	Ceftriaxona			
+Ce(f|ph)uroxime	TRUE	TRUE	FALSE	Cefuroxim	Cefuroxim	Cefuroxima			
+Ce(f|ph)uroxime/metronidazole	TRUE	TRUE	FALSE	Cefuroxim/Metronidazol	Cefuroxim/andere antibacteriele middelen	Cefuroxima/metronidazol			
+Chloramphenicol	FALSE	TRUE	FALSE	Chloramphenicol	Chlooramfenicol	Cloranfenicol			
+Chlortetracycline	FALSE	TRUE	FALSE	Chlortetracyclin	Chloortetracycline	Clortetraciclina			
+Cinoxacin	FALSE	TRUE	FALSE	Cinoxacin	Cinoxacine	Cinoxacina			
+Ciprofloxacin	FALSE	TRUE	FALSE	Ciprofloxacin	Ciprofloxacine	Ciprofloxacina			
+Clarithromycin	FALSE	TRUE	FALSE	Clarithromycin	Claritromycine	Claritromicina			
+Clavulanic acid	FALSE	TRUE	FALSE	Clavulansäure	Clavulaanzuur	Ácido clavulánico			
+clavulanic acid	FALSE	TRUE	FALSE	Clavulansäure	clavulaanzuur	ácido clavulánico			
+Clindamycin	FALSE	TRUE	FALSE	Clindamycin	Clindamycine	Clindamicina			
+Clometocillin	FALSE	TRUE	FALSE	Clometocillin	Clometocilline	Clometocilina			
+Clotrimazole	FALSE	TRUE	FALSE	Clotrimazol	Clotrimazol	Clotrimazol			
+Cloxacillin	FALSE	TRUE	FALSE	Cloxacillin	Cloxacilline	Cloxacilina			
+Colistin	FALSE	TRUE	FALSE	Colistin	Colistine	Colistina			
+Dapsone	FALSE	TRUE	FALSE	Dapson	Dapson	Dapsona			
+Daptomycin	FALSE	TRUE	FALSE	Daptomycin	Daptomycine	Daptomicina			
+Dibekacin	FALSE	TRUE	FALSE	Dibekacin	Dibekacine	Dibekacina			
+Dicloxacillin	FALSE	TRUE	FALSE	Dicloxacillin	Dicloxacilline	Dicloxacilina			
+Dirithromycin	FALSE	TRUE	FALSE	Dirithromycin	Diritromycine	Diritromicina			
+Econazole	FALSE	TRUE	FALSE	Econazol	Econazol	Econazol			
+Enoxacin	FALSE	TRUE	FALSE	Enoxacin	Enoxacine	Enoxacina			
+Epicillin	FALSE	TRUE	FALSE	Epicillin	Epicilline	Epicilina			
+Erythromycin	FALSE	TRUE	FALSE	Erythromycin	Erytromycine	Eritromicina			
+Ethambutol/isoniazid	FALSE	TRUE	FALSE	Ethambutol/Isoniazid	Ethambutol/isoniazide	Etambutol/isoniazida			
+Fleroxacin	FALSE	TRUE	FALSE	Fleroxacin	Fleroxacine	Fleroxacina			
+Flucloxacillin	FALSE	TRUE	FALSE	Flucloxacillin	Flucloxacilline	Flucloxacilina			
+Fluconazole	FALSE	TRUE	FALSE	Fluconazol	Fluconazol	Fluconazol			
+Flucytosine	FALSE	TRUE	FALSE	Flucytosin	Fluorocytosine	Flucitosina			
+Flurithromycin	FALSE	TRUE	FALSE	Flurithromycin	Fluritromycine	Fluritromicina			
+Fosfomycin	FALSE	TRUE	FALSE	Fosfomycin	Fosfomycine	Fosfomicina			
+Fusidic acid	FALSE	TRUE	FALSE	Fusidinsäure	Fusidinezuur	Ácido fusídico			
+Gatifloxacin	FALSE	TRUE	FALSE	Gatifloxacin	Gatifloxacine	Gatifloxacina			
+Gemifloxacin	FALSE	TRUE	FALSE	Gemifloxacin	Gemifloxacine	Gemifloxacina			
+Gentamicin	FALSE	TRUE	FALSE	Gentamicin	Gentamicine	Gentamicina			
+Grepafloxacin	FALSE	TRUE	FALSE	Grepafloxacin	Grepafloxacine	Grepafloxacina			
+Hachimycin	FALSE	TRUE	FALSE	Hachimycin	Hachimycine	Hachimycin			
+Hetacillin	FALSE	TRUE	FALSE	Hetacillin	Hetacilline	Hetacilina			
+Imipenem/cilastatin	FALSE	TRUE	FALSE	Imipenem/Cilastatin	Imipenem/enzymremmer	Imipenem/cilastatina			
+Inosine pranobex	FALSE	TRUE	FALSE	Inosin-Pranobex	Inosiplex	Inosina pranobex			
+Isepamicin	FALSE	TRUE	FALSE	Isepamicin	Isepamicine	Isepamicina			
+Isoconazole	FALSE	TRUE	FALSE	Isoconazol	Isoconazol	Isoconazol			
+Isoniazid	FALSE	TRUE	FALSE	Isoniazid	Isoniazide	Isoniazida			
+Itraconazole	FALSE	TRUE	FALSE	Itraconazol	Itraconazol	Itraconazol			
+Josamycin	FALSE	TRUE	FALSE	Josamycin	Josamycine	Josamicina			
+Kanamycin	FALSE	TRUE	FALSE	Kanamycin	Kanamycine	Kanamicina			
+Ketoconazole	FALSE	TRUE	FALSE	Ketoconazol	Ketoconazol	Ketoconazol			
+Levofloxacin	FALSE	TRUE	FALSE	Levofloxacin	Levofloxacine	Levofloxacina			
+Lincomycin	FALSE	TRUE	FALSE	Lincomycin	Lincomycine	Lincomicina			
+Lomefloxacin	FALSE	TRUE	FALSE	Lomefloxacin	Lomefloxacine	Lomefloxacina			
+Lysozyme	FALSE	TRUE	FALSE	Lysozym	Lysozym	Lisozima			
+Mandelic acid	FALSE	TRUE	FALSE	Mandelsäure	Amandelzuur	Ácido mandélico			
+Metampicillin	FALSE	TRUE	FALSE	Metampicillin	Metampicilline	Metampicilina			
+Meticillin	FALSE	TRUE	FALSE	Meticillin	Meticilline	Meticilina			
+Metisazone	FALSE	TRUE	FALSE	Metisazon	Metisazon	Metisazona			
+Metronidazole	FALSE	TRUE	FALSE	Metronidazol	Metronidazol	Metronidazol			
+Mezlocillin	FALSE	TRUE	FALSE	Mezlocillin	Mezlocilline	Mezlocilina			
+Micafungin	FALSE	TRUE	FALSE	Micafungin	Micafungine	Micafungina			
+Miconazole	FALSE	TRUE	FALSE	Miconazol	Miconazol	Miconazol			
+Midecamycin	FALSE	TRUE	FALSE	Midecamycin	Midecamycine	Midecamicina			
+Miocamycin	FALSE	TRUE	FALSE	Miocamycin	Miocamycine	Miocamycin			
+Moxifloxacin	FALSE	TRUE	FALSE	Moxifloxacin	Moxifloxacine	Moxifloxacina			
+Mupirocin	FALSE	TRUE	FALSE	Mupirocin	Mupirocine	Mupirocina			
+Nalidixic acid	FALSE	TRUE	FALSE	Nalidixinsäure	Nalidixinezuur	Ácido nalidíxico			
+Neomycin	FALSE	TRUE	FALSE	Neomycin	Neomycine	Neomicina			
+Netilmicin	FALSE	TRUE	FALSE	Netilmicin	Netilmicine	Netilmicina			
+Nitrofurantoin	FALSE	TRUE	FALSE	Nitrofurantoin	Nitrofurantoine	Nitrofurantoína			
+Norfloxacin	FALSE	TRUE	FALSE	Norfloxacin	Norfloxacine	Norfloxacina			
+Novobiocin	FALSE	TRUE	FALSE	Novobiocin	Novobiocine	Novobiocina			
+Nystatin	FALSE	TRUE	FALSE	Nystatin	Nystatine	Nistatina			
+Ofloxacin	FALSE	TRUE	FALSE	Ofloxacin	Ofloxacine	Ofloxacina			
+Oleandomycin	FALSE	TRUE	FALSE	Oleandomycin	Oleandomycine	Oleandomicina			
+Ornidazole	FALSE	TRUE	FALSE	Ornidazol	Ornidazol	Ornidazol			
+Oxacillin	FALSE	TRUE	FALSE	Oxacillin	Oxacilline	Oxacilina			
+Oxolinic acid	FALSE	TRUE	FALSE	Oxolinsäure	Oxolinezuur	Ácido oxolínico			
+Oxytetracycline	FALSE	TRUE	FALSE	Oxytetracyclin	Oxytetracycline	Oxitetraciclina			
+Pazufloxacin	FALSE	TRUE	FALSE	Pazufloxacin	Pazufloxacine	Pazufloxacina			
+Pefloxacin	FALSE	TRUE	FALSE	Pefloxacin	Pefloxacine	Pefloxacina			
+Penamecillin	FALSE	TRUE	FALSE	Penamecillin	Penamecilline	Penamecilina			
+Penicillin	FALSE	TRUE	FALSE	Penicillin	Penicilline	Penicilina			
+Pheneticillin	FALSE	TRUE	FALSE	Pheneticillin	Feneticilline	Feneticilina			
+Phenoxymethylpenicillin	FALSE	TRUE	FALSE	Phenoxymethylpenicillin	Fenoxymethylpenicilline	Fenoximetilpenicilina			
+Pipemidic acid	FALSE	TRUE	FALSE	Pipemidinsäure	Pipemidinezuur	Ácido pipemídico			
+Piperacillin	FALSE	TRUE	FALSE	Piperacillin	Piperacilline	Piperacilina			
+Piperacillin/beta-lactamase inhibitor	FALSE	TRUE	FALSE	Piperacillin/Beta-Lactamase-Hemmer	Piperacilline/enzymremmer	Piperacilina/inhib. de la betalactamasa			
+Piromidic acid	FALSE	TRUE	FALSE	Piromidinsäure	Piromidinezuur	Ácido piromídico			
+Pivampicillin	FALSE	TRUE	FALSE	Pivampicillin	Pivampicilline	Pivampicilina			
+Polymyxin B	FALSE	TRUE	FALSE	Polymyxin B	Polymyxine B	Polimixina B			
+Posaconazole	FALSE	TRUE	FALSE	Posaconazol	Posaconazol	Posaconazol			
+Pristinamycin	FALSE	TRUE	FALSE	Pristinamycin	Pristinamycine	Pristinamicina			
+Procaine benzylpenicillin	FALSE	TRUE	FALSE	Procain-Benzylpenicillin	Benzylpenicillineprocaine	Bencilpenicilina procaína			
+Propicillin	FALSE	TRUE	FALSE	Propicillin	Propicilline	Propicilina			
+Prulifloxacin	FALSE	TRUE	FALSE	Prulifloxacin	Prulifloxacine	Prulifloxacina			
+Quinupristin/dalfopristin	FALSE	TRUE	FALSE	Quinupristin/Dalfopristin	Quinupristine/dalfopristine	Quinupristina/dalfopristina			
+Ribostamycin	FALSE	TRUE	FALSE	Ribostamycin	Ribostamycine	Ribostamicina			
+Rifabutin	FALSE	TRUE	FALSE	Rifabutin	Rifabutine	Rifabutina			
+Rifampicin	FALSE	TRUE	FALSE	Rifampicin	Rifampicine	Rifampicina			
+Rifampicin/pyrazinamide/ethambutol/isoniazid	FALSE	TRUE	FALSE	Rifampicin/Pyrazinamid/Ethambutol/Isoniazid	Rifampicine/pyrazinamide/ethambutol/isoniazide	Rifampicina/pirazinamida/etambutol/isoniazida			
+Rifampicin/pyrazinamide/isoniazid	FALSE	TRUE	FALSE	Rifampicin/Pyrazinamid/Isoniazid	Rifampicine/pyrazinamide/isoniazide	Rifampicina/pirazinamida/isoniazida			
+Rifampicin/isoniazid	FALSE	TRUE	FALSE	Rifampicin/Isoniazid	Rifampicine/isoniazide	Rifampicina/isoniazida			
+Rifamycin	FALSE	TRUE	FALSE	Rifamycin	Rifamycine	Rifamicina			
+Rifaximin	FALSE	TRUE	FALSE	Rifaximin	Rifaximine	Rifaximina			
+Rokitamycin	FALSE	TRUE	FALSE	Rokitamycin	Rokitamycine	Rokitamicina			
+Rosoxacin	FALSE	TRUE	FALSE	Rosoxacin	Rosoxacine	Rosoxacina			
+Roxithromycin	FALSE	TRUE	FALSE	Roxithromycin	Roxitromycine	Roxitromicina			
+Rufloxacin	FALSE	TRUE	FALSE	Rufloxacin	Rufloxacine	Rufloxacina			
+Sisomicin	FALSE	TRUE	FALSE	Sisomicin	Sisomicine	Sisomicina			
+Sodium aminosalicylate	FALSE	TRUE	FALSE	Natrium-Aminosalicylat	Aminosalicylzuur	Aminosalicilato de sodio			
+Sparfloxacin	FALSE	TRUE	FALSE	Sparfloxacin	Sparfloxacine	Esparfloxacina			
+Spectinomycin	FALSE	TRUE	FALSE	Spectinomycin	Spectinomycine	Espectinomicina			
+Spiramycin	FALSE	TRUE	FALSE	Spiramycin	Spiramycine	Espiramicina			
+Spiramycin/metronidazole	FALSE	TRUE	FALSE	Spiramycin/Metronidazol	Spiramycine/metronidazol	Espiramicina/metronidazol			
+Staphylococcus immunoglobulin	FALSE	TRUE	FALSE	Staphylococcus-Immunoglobulin	Stafylokokkenimmunoglobuline	Inmunoglobulina estafilocócica			
+Streptoduocin	FALSE	TRUE	FALSE	Streptoduocin	Streptoduocine	Estreptoduocina			
+Streptomycin	FALSE	TRUE	FALSE	Streptomycin	Streptomycine	Estreptomicina			
+Streptomycin/isoniazid	FALSE	TRUE	FALSE	Streptomycin/Isoniazid	Streptomycine/isoniazide	Estreptomicina/isoniazida			
+Sulbenicillin	FALSE	TRUE	FALSE	Sulbenicillin	Sulbenicilline	Sulbenicilina			
+Sulfadiazine/tetroxoprim	FALSE	TRUE	FALSE	Sulfadiazin/Tetroxoprim	Sulfadiazine/tetroxoprim	Sulfadiazina/tetroxoprima			
+Sulfadiazine/trimethoprim	FALSE	TRUE	FALSE	Sulfadiazin/Trimethoprim	Sulfadiazine/trimethoprim	Sulfadiazina/trimetoprima			
+Sulfadimidine/trimethoprim	FALSE	TRUE	FALSE	Sulfadimidin/Trimethoprim	Sulfadimidine/trimethoprim	Sulfadimidina/trimetoprima			
+Sulfafurazole	FALSE	TRUE	FALSE	Sulfafurazol	Sulfafurazol	Sulfafurazol			
+Sulfaisodimidine	FALSE	TRUE	FALSE	Sulfaisodimidin	Sulfisomidine	Sulfaisodimidina			
+Sulfalene	FALSE	TRUE	FALSE	Sulfalene	Sulfaleen	Sulfaleno			
+Sulfamazone	FALSE	TRUE	FALSE	Sulfamazon	Sulfamazon	Sulfamazona			
+Sulfamerazine/trimethoprim	FALSE	TRUE	FALSE	Sulfamerazin/Trimethoprim	Sulfamerazine/trimethoprim	Sulfamerazina/trimetoprima			
+Sulfamethizole	FALSE	TRUE	FALSE	Sulfamethizol	Sulfamethizol	Sulfametozol			
+Sulfamethoxazole	FALSE	TRUE	FALSE	Sulfamethoxazol	Sulfamethoxazol	Sulfametoxazol			
+Sulfamethoxazole/trimethoprim	FALSE	TRUE	FALSE	Sulfamethoxazol/Trimethoprim	Sulfamethoxazol/trimethoprim	Sulfametoxazol/trimetoprima			
+Sulfametoxydiazine	FALSE	TRUE	FALSE	Sulfametoxydiazin	Sulfamethoxydiazine	Sulfametoxidiazina			
+Sulfametrole/trimethoprim	FALSE	TRUE	FALSE	Sulfametrole/Trimethoprim	Sulfametrol/trimethoprim	Sulfametrole/trimethoprim			
+Sulfamoxole	FALSE	TRUE	FALSE	Sulfamoxol	Sulfamoxol	Sulfamoxole			
+Sulfamoxole/trimethoprim	FALSE	TRUE	FALSE	Sulfamoxol/Trimethoprim	Sulfamoxol/trimethoprim	Sulfamoxol/trimetoprima			
+Sulfaperin	FALSE	TRUE	FALSE	Sulfaperin	Sulfaperine	Sulfaproxeno			
+Sulfaphenazole	FALSE	TRUE	FALSE	Sulfaphenazol	Sulfafenazol	Sulfafenazol			
+Sulfathiazole	FALSE	TRUE	FALSE	Sulfathiazol	Sulfathiazol	Sulfatiazol			
+Sulfathiourea	FALSE	TRUE	FALSE	Sulfathioharnstoff	Sulfathioureum	Sulfathiourea			
+Sultamicillin	FALSE	TRUE	FALSE	Sultamicillin	Sultamicilline	Sultamicilina			
+Talampicillin	FALSE	TRUE	FALSE	Talampicillin	Talampicilline	Talampicilina			
+Teicoplanin	FALSE	TRUE	FALSE	Teicoplanin	Teicoplanine	Teicoplanina			
+Telithromycin	FALSE	TRUE	FALSE	Telithromycin	Telitromycine	Telitromicina			
+Temafloxacin	FALSE	TRUE	FALSE	Temafloxacin	Temafloxacine	Temafloxacina			
+Temocillin	FALSE	TRUE	FALSE	Temocillin	Temocilline	Temocilina			
+Tenofovir disoproxil	FALSE	TRUE	FALSE	Tenofovir Disoproxil	Tenofovir	Tenofovir disoproxil			
+Terizidone	FALSE	TRUE	FALSE	Terizidon	Terizidon	Terizidona			
+Thiamphenicol	FALSE	TRUE	FALSE	Thiamphenicol	Thiamfenicol	Tiamfenicol			
+Thioacetazone/isoniazid	FALSE	TRUE	FALSE	Thioacetazon/Isoniazid	Thioacetazon/isoniazide	Tioacetazona/isoniazida			
+Ticarcillin	FALSE	TRUE	FALSE	Ticarcillin	Ticarcilline	Ticarcilina			
+Ticarcillin/beta-lactamase inhibitor	FALSE	TRUE	FALSE	Ticarcillin/Beta-Lactamase-Hemmer	Ticarcilline/enzymremmer	Ticarcilina/inhib. de la betalactamasa			
+Ticarcillin/clavulanic acid	FALSE	TRUE	FALSE	Ticarcillin/Clavulansäure	Ticarcilline/clavulaanzuur	Ticarcilina/ácido clavulánico			
+Tinidazole	FALSE	TRUE	FALSE	Tinidazol	Tinidazol	Tinidazol			
+Tobramycin	FALSE	TRUE	FALSE	Tobramycin	Tobramycine	Tobramicina			
+Trimethoprim/sulfamethoxazole	FALSE	TRUE	FALSE	Trimethoprim/Sulfamethoxazol	Cotrimoxazol	Trimetoprima/sulfametoxazol			
+Troleandomycin	FALSE	TRUE	FALSE	Troleandomycin	Troleandomycine	Troleandomicina			
+Trovafloxacin	FALSE	TRUE	FALSE	Trovafloxacin	Trovafloxacine	Trovafloxacina			
+Vancomycin	FALSE	TRUE	FALSE	Vancomycin	Vancomycine	Vancomicina			
+Voriconazole	FALSE	TRUE	FALSE	Voriconazol	Voriconazol	Voriconazol			
+Aminoglycosides	FALSE	TRUE	FALSE	Aminoglykoside	Aminoglycosiden	Aminoglucósidos			
+Amphenicols	FALSE	TRUE	FALSE	Amphenicole	Amfenicolen	Anfenicoles			
+Antifungals/antimycotics	FALSE	TRUE	FALSE	Antimykotika/Antimykotika	Antifungica/antimycotica	Antifúngicos/antimicóticos			
+Antimycobacterials	FALSE	TRUE	FALSE	Antimykobakterielle Mittel	Antimycobacteriele middelen	Antimicrobianos			
+Beta-lactams/penicillins	FALSE	TRUE	FALSE	Beta-Lactame/Penicilline	Beta-lactams/penicillines	Beta-lactámicos/penicilinas			
+Cephalosporins (1st gen.)	FALSE	TRUE	FALSE	Cephalosporine (1. Gen.)	Cefalosporines (1e gen.)	Cefalosporinas (1er gen.)			
+Cephalosporins (2nd gen.)	FALSE	TRUE	FALSE	Cephalosporine (2. Gen.)	Cefalosporines (2e gen.)	Cefalosporinas (2do gen.)			
+Cephalosporins (3rd gen.)	FALSE	TRUE	FALSE	Cephalosporine (3. Gen.)	Cefalosporines (3e gen.)	Cefalosporinas (3er gen.)			
+Cephalosporins (4th gen.)	FALSE	TRUE	FALSE	Cephalosporine (4. Gen.)	Cefalosporines (4e gen.)	Cefalosporinas (4º gen.)			
+Cephalosporins (5th gen.)	FALSE	TRUE	FALSE	Cephalosporine (5. Gen.)	Cefalosporines (5e gen.)	Cefalosporinas (5º gen.)			
+Cephalosporins (unclassified gen.)	FALSE	TRUE	FALSE	Cephalosporine (unklassifiziert)	Cefalosporines (ongeclassificeerd)	Cefalosporinas (no clasificado)			
+Cephalosporins	FALSE	TRUE	FALSE	Cephalosporine	Cefalosporines	Cefalosporinas			
+Glycopeptides	FALSE	TRUE	FALSE	Glykopeptide	Glycopeptiden	Glicopéptidos			
+Macrolides/lincosamides	FALSE	TRUE	FALSE	Makrolide/Linkosamide	Macroliden/lincosamiden	Macrólidos/lincosamidas			
+Other antibacterials	FALSE	TRUE	FALSE	Andere Antibiotika	Overige antibiotica	Otros antibacterianos			
+Polymyxins	FALSE	TRUE	FALSE	Polymyxine	Polymyxines	Polimixinas			
+Quinolones	FALSE	TRUE	FALSE	Quinolone	Quinolonen	Quinolonas			

docs/404.html

@@ -81,7 +81,7 @@
       </button>
       <span class="navbar-brand">
         <a class="navbar-link" href="https://msberends.github.io/AMR//index.html">AMR (for R)</a>
-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9024</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0</span>
       </span>
     </div>
 

docs/LICENSE-text.html

@@ -81,7 +81,7 @@
       </button>
       <span class="navbar-brand">
         <a class="navbar-link" href="index.html">AMR (for R)</a>
-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9024</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.6.0</span>
       </span>
     </div>
 

docs/articles/benchmarks.html

@@ -39,7 +39,7 @@
       </button>
       <span class="navbar-brand">
         <a class="navbar-link" href="../index.html">AMR (for R)</a>
-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9024</span>
+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9027</span>
       </span>
     </div>
 
@@ -226,19 +226,19 @@
   times <span class="op">=</span> <span class="fl">25</span><span class="op">)</span>
 <span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">S.aureus</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">2</span><span class="op">)</span>
 <span class="co"># Unit: milliseconds</span>
-<span class="co">#                                   expr   min  lq  mean median    uq   max neval</span>
-<span class="co">#                           as.mo("sau")   9.3  10  11.0     10  11.0  13.0    25</span>
-<span class="co">#                          as.mo("stau")  52.0  55  73.0     58  92.0 100.0    25</span>
-<span class="co">#                          as.mo("STAU")  50.0  54  73.0     58  96.0 110.0    25</span>
-<span class="co">#                        as.mo("staaur")   9.7  10  14.0     11  12.0  57.0    25</span>
-<span class="co">#                        as.mo("STAAUR")   8.9  10  14.0     10  11.0  52.0    25</span>
-<span class="co">#                     as.mo("S. aureus")  26.0  28  41.0     29  67.0  76.0    25</span>
-<span class="co">#                      as.mo("S aureus")  27.0  28  41.0     30  65.0  76.0    25</span>
-<span class="co">#         as.mo("Staphylococcus aureus")   2.6   3   3.2      3   3.3   4.6    25</span>
-<span class="co">#  as.mo("Staphylococcus aureus (MRSA)") 240.0 260 270.0    260 270.0 380.0    25</span>
-<span class="co">#       as.mo("Sthafilokkockus aaureuz") 160.0 190 200.0    200 200.0 300.0    25</span>
-<span class="co">#                          as.mo("MRSA")   9.3  10  15.0     10  12.0  49.0    25</span>
-<span class="co">#                          as.mo("VISA")  18.0  19  31.0     21  54.0  67.0    25</span></code></pre></div>
+<span class="co">#                                   expr   min    lq  mean median    uq max neval</span>
+<span class="co">#                           as.mo("sau")   9.9  11.0  13.0   11.0  12.0  43    25</span>
+<span class="co">#                          as.mo("stau")  52.0  55.0  68.0   58.0  86.0  95    25</span>
+<span class="co">#                          as.mo("STAU")  53.0  56.0  73.0   62.0  93.0 100    25</span>
+<span class="co">#                        as.mo("staaur")  10.0  11.0  17.0   11.0  12.0  48    25</span>
+<span class="co">#                        as.mo("STAAUR")  10.0  11.0  14.0   11.0  13.0  48    25</span>
+<span class="co">#                     as.mo("S. aureus")  27.0  28.0  41.0   33.0  60.0  73    25</span>
+<span class="co">#                      as.mo("S aureus")  27.0  28.0  49.0   34.0  64.0 160    25</span>
+<span class="co">#         as.mo("Staphylococcus aureus")   2.9   3.2   4.8    3.4   3.7  36    25</span>
+<span class="co">#  as.mo("Staphylococcus aureus (MRSA)") 250.0 260.0 270.0  270.0 280.0 320    25</span>
+<span class="co">#       as.mo("Sthafilokkockus aaureuz") 170.0 200.0 210.0  210.0 210.0 310    25</span>
+<span class="co">#                          as.mo("MRSA")  10.0  11.0  16.0   12.0  12.0  50    25</span>
+<span class="co">#                          as.mo("VISA")  19.0  20.0  27.0   21.0  23.0  60    25</span></code></pre></div>
 <p><img src="benchmarks_files/figure-html/unnamed-chunk-4-1.png" width="750"></p>
 <p>In the table above, all measurements are shown in milliseconds (thousands of seconds). A value of 5 milliseconds means it can determine 200 input values per second. It case of 200 milliseconds, this is only 5 input values per second. It is clear that accepted taxonomic names are extremely fast, but some variations are up to 200 times slower to determine.</p>
 <p>To improve performance, we implemented two important algorithms to save unnecessary calculations: <strong>repetitive results</strong> and <strong>already precalculated results</strong>.</p>
@@ -260,8 +260,8 @@
 <span class="co"># what do these values look like? They are of class &lt;mo&gt;:</span>
 <span class="fu"><a href="https://rdrr.io/r/utils/head.html">head</a></span><span class="op">(</span><span class="va">x</span><span class="op">)</span>
 <span class="co"># Class &lt;mo&gt;</span>
-<span class="co"># [1] B_STPHY_AURS B_STRPT_GRPC B_STPHY_CONS B_STPHY_EPDR B_STRPT_PNMN</span>
-<span class="co"># [6] B_PROTS_VLGR</span>
+<span class="co"># [1] B_STRPT_PYGN  B_STPHY_HMNS  B_STPHY_CONS  B_STRPT_SLVR  B_ENTRBC_CLOC</span>
+<span class="co"># [6] B_STPHY_CONS</span>
   
 <span class="co"># as the example_isolates data set has 2,000 rows, we should have 2 million items</span>
 <span class="fu"><a href="https://rdrr.io/r/base/length.html">length</a></span><span class="op">(</span><span class="va">x</span><span class="op">)</span>
@@ -277,8 +277,8 @@
 <span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
 <span class="co"># Unit: milliseconds</span>
 <span class="co">#        expr min  lq mean median  uq max neval</span>
-<span class="co">#  mo_name(x) 157 187  222    206 224 372    10</span></code></pre></div>
-<p>So getting official taxonomic names of 2,000,000 (!!) items consisting of 90 unique values only takes 0.206 seconds. That is 2.471 milliseconds per unique item on average. You only lose time on your unique input values.</p>
+<span class="co">#  mo_name(x) 161 194  224    204 229 368    10</span></code></pre></div>
+<p>So getting official taxonomic names of 2,000,000 (!!) items consisting of 90 unique values only takes 0.204 seconds. That is 102 nanoseconds on average. You only lose time on your unique input values.</p>
 </div>
 <div id="precalculated-results" class="section level3">
 <h3 class="hasAnchor">
@@ -292,9 +292,9 @@
 <span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
 <span class="co"># Unit: milliseconds</span>
 <span class="co">#  expr   min    lq  mean median    uq   max neval</span>
-<span class="co">#     A  6.97  7.10  7.55   7.21  8.18  8.32    10</span>
-<span class="co">#     B 23.70 24.20 36.30  26.30 29.00 89.70    10</span>
-<span class="co">#     C  1.53  1.65  1.80   1.76  2.00  2.19    10</span></code></pre></div>
+<span class="co">#     A  7.45  7.84 12.70   8.62  9.16 51.10    10</span>
+<span class="co">#     B 23.80 24.50 30.60  26.30 28.80 70.20    10</span>
+<span class="co">#     C  1.66  1.74  1.85   1.79  1.92  2.24    10</span></code></pre></div>
 <p>So going from <code><a href="../reference/mo_property.html">mo_name("Staphylococcus aureus")</a></code> to <code>"Staphylococcus aureus"</code> takes 0.0018 seconds - it doesn’t even start calculating <em>if the result would be the same as the expected resulting value</em>. That goes for all helper functions:</p>
 <div class="sourceCode" id="cb5"><pre class="downlit sourceCode r">
 <code class="sourceCode R"><span class="va">run_it</span> <span class="op">&lt;-</span> <span class="fu"><a href="https://rdrr.io/pkg/microbenchmark/man/microbenchmark.html">microbenchmark</a></span><span class="op">(</span>A <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_species</a></span><span class="op">(</span><span class="st">"aureus"</span><span class="op">)</span>,
@@ -309,14 +309,14 @@
 <span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
 <span class="co"># Unit: milliseconds</span>
 <span class="co">#  expr  min   lq mean median   uq  max neval</span>
-<span class="co">#     A 1.44 1.72 1.69   1.74 1.75 1.78    10</span>
-<span class="co">#     B 1.47 1.55 1.67   1.73 1.74 1.89    10</span>
-<span class="co">#     C 1.52 1.59 1.73   1.74 1.89 1.91    10</span>
-<span class="co">#     D 1.46 1.51 1.64   1.64 1.75 1.89    10</span>
-<span class="co">#     E 1.42 1.47 1.60   1.52 1.71 1.97    10</span>
-<span class="co">#     F 1.44 1.71 1.69   1.72 1.75 1.88    10</span>
-<span class="co">#     G 1.42 1.50 1.68   1.61 1.73 2.36    10</span>
-<span class="co">#     H 1.52 1.54 1.66   1.71 1.73 1.87    10</span></code></pre></div>
+<span class="co">#     A 1.59 1.60 1.91   1.97 2.15 2.28    10</span>
+<span class="co">#     B 1.58 1.61 1.87   1.86 1.96 2.39    10</span>
+<span class="co">#     C 1.55 1.57 1.64   1.63 1.69 1.79    10</span>
+<span class="co">#     D 1.57 1.60 1.83   1.72 1.92 2.73    10</span>
+<span class="co">#     E 1.50 1.74 1.86   1.86 2.03 2.24    10</span>
+<span class="co">#     F 1.49 1.55 1.75   1.67 1.90 2.24    10</span>
+<span class="co">#     G 1.54 1.59 1.69   1.65 1.77 1.95    10</span>
+<span class="co">#     H 1.57 1.58 1.75   1.72 1.78 2.21    10</span></code></pre></div>
 <p>Of course, when running <code><a href="../reference/mo_property.html">mo_phylum("Firmicutes")</a></code> the function has zero knowledge about the actual microorganism, namely <em>S. aureus</em>. But since the result would be <code>"Firmicutes"</code> anyway, there is no point in calculating the result. And because this package contains all phyla of all known bacteria, it can just return the initial value immediately.</p>
 </div>
 <div id="results-in-other-languages" class="section level3">
@@ -344,13 +344,13 @@
 <span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">4</span><span class="op">)</span>
 <span class="co"># Unit: milliseconds</span>
 <span class="co">#  expr   min    lq  mean median    uq   max neval</span>
-<span class="co">#    en 17.12 17.40 22.65  17.54 18.39 78.39   100</span>
-<span class="co">#    de 19.93 20.26 22.60  20.48 20.97 81.27   100</span>
-<span class="co">#    nl 24.87 25.24 30.93  25.50 26.90 87.17   100</span>
-<span class="co">#    es 20.00 20.26 24.39  20.58 21.13 82.01   100</span>
-<span class="co">#    it 19.92 20.26 26.54  20.66 21.38 79.15   100</span>
-<span class="co">#    fr 19.62 19.90 24.74  20.10 21.04 77.20   100</span>
-<span class="co">#    pt 19.74 20.02 26.76  20.41 22.68 82.61   100</span></code></pre></div>
+<span class="co">#    en 17.33 18.21 21.97  19.06 20.40 68.32   100</span>
+<span class="co">#    de 20.44 21.37 30.49  22.33 24.97 78.42   100</span>
+<span class="co">#    nl 25.13 26.10 31.91  27.11 28.50 86.00   100</span>
+<span class="co">#    es 20.28 21.16 26.37  22.03 23.67 74.74   100</span>
+<span class="co">#    it 20.06 21.00 26.05  21.95 23.42 94.16   100</span>
+<span class="co">#    fr 19.90 20.63 24.40  21.85 22.82 69.07   100</span>
+<span class="co">#    pt 20.22 21.03 25.63  21.89 23.24 76.63   100</span></code></pre></div>
 <p>Currently supported non-English languages are German, Dutch, Spanish, Italian, French and Portuguese.</p>
 </div>
   </div>