(v2.1.1.9041) antibiotics update

.github/prehooks/commit-msg

@@ -0,0 +1,57 @@
+#!/bin/bash
+
+# ==================================================================== #
+# TITLE:                                                               #
+# AMR: An R Package for Working with Antimicrobial Resistance Data     #
+#                                                                      #
+# SOURCE CODE:                                                         #
+# https://github.com/msberends/AMR                                     #
+#                                                                      #
+# PLEASE CITE THIS SOFTWARE AS:                                        #
+# Berends MS, Luz CF, Friedrich AW, Sinha BNM, Albers CJ, Glasner C    #
+# (2022). AMR: An R Package for Working with Antimicrobial Resistance  #
+# Data. Journal of Statistical Software, 104(3), 1-31.                 #
+# https://doi.org/10.18637/jss.v104.i03                                #
+#                                                                      #
+# Developed at the University of Groningen and the University Medical  #
+# Center Groningen in The Netherlands, in collaboration with many      #
+# colleagues from around the world, see our website.                   #
+#                                                                      #
+# 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/   #
+# ==================================================================== #
+
+#######################################
+# This script runs on commit-msg hook #
+#######################################
+
+# Path to the commit message file
+COMMIT_MSG_FILE=$1
+
+# Read the current commit message
+COMMIT_MSG=$(cat "$COMMIT_MSG_FILE")
+# check the commit message, cancel commit if needed
+if [[ "$COMMIT_MSG" =~ \(no-check\)|\(no-checks\)|\(no-verify\) ]]; then
+  exit 0
+fi
+
+# Path to the DESCRIPTION file
+DESCRIPTION_FILE="DESCRIPTION"
+# Read the version number from the DESCRIPTION file
+if [ -f "$DESCRIPTION_FILE" ]; then
+  currentversion=$(grep "^Version:" "$DESCRIPTION_FILE" | awk '{print $2}')
+else
+  echo "Error: DESCRIPTION file not found. Unable to prepend version number."
+  exit 1
+fi
+
+# Prepend the version number to the commit message
+echo "(v${currentversion}) ${COMMIT_MSG}" > "$COMMIT_MSG_FILE"

.github/prehooks/pre-commit

@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 
 # ==================================================================== #
 # TITLE:                                                               #
@@ -29,12 +29,32 @@
 # how to conduct AMR data analysis: https://msberends.github.io/AMR/   #
 # ==================================================================== #
 
-echo "Running pre-commit hook..."
+########################################
+# This script runs before every commit #
+########################################
+
+# try to fetch the commit message from the standard location
+COMMIT_MSG_PATH=".git/COMMIT_EDITMSG"
+if [ -f "$COMMIT_MSG_PATH" ]; then
+  COMMIT_MSG=$(cat "$COMMIT_MSG_PATH")
+else
+  echo "Commit message file not found."
+  exit 1
+fi
+# check the commit message, cancel commit if needed
+if [[ "$COMMIT_MSG" =~ \(no-check\)|\(no-checks\)|\(no-verify\) ]]; then
+  echo "Not running pre-commit checks:"
+  echo "Commit message contains '(no-check)', '(no-checks)', or '(no-verify)."
+  echo ""
+  exit 0
+fi
+
+echo "Running pre-commit checks..."
 
 # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 if command -v Rscript > /dev/null; then
   if [ "$(Rscript -e 'cat(all(c('"'pkgload'"', '"'devtools'"', '"'dplyr'"') %in% rownames(installed.packages())))')" = "TRUE" ]; then
-    Rscript -e "source('data-raw/_pre_commit_hook.R')"
+    Rscript -e "source('data-raw/_pre_commit_checks.R')"
     currentpkg=$(Rscript -e "cat(pkgload::pkg_name())")
     echo "- Adding changed files in ./data-raw and ./man to this commit"
     git add data-raw/*

.github/workflows/check-old.yaml

@@ -49,6 +49,7 @@ jobs:
           # Test all old versions of R >= 3.0, we support them all!
           # For these old versions, dependencies and vignettes will not be checked.
           # For recent R versions, see check-recent.yaml (r-lib and tidyverse support the latest 5 major R releases).
+          - {os: ubuntu-latest, r: '3.6', allowfail: false}
           # - {os: windows-latest, r: '3.5', allowfail: true} # always fails, horrible with UTF-8
           - {os: ubuntu-latest, r: '3.4', allowfail: false}
           - {os: ubuntu-latest, r: '3.3', allowfail: false}

.github/workflows/check-recent.yaml

@@ -58,15 +58,15 @@ jobs:
           - {os: ubuntu-latest,  r: 'devel', allowfail: false}
 
           # current 'release' version, check all major OSes:
-          - {os: macOS-latest,   r: '4.3', allowfail: false}
-          - {os: windows-latest, r: '4.3', allowfail: false}
-          - {os: ubuntu-latest,  r: '4.3', allowfail: false}
+          - {os: macOS-latest,   r: 'release', allowfail: false}
+          - {os: windows-latest, r: 'release', allowfail: false}
+          - {os: ubuntu-latest,  r: 'release', allowfail: false}
 
           # older versions (see also check-old.yaml for even older versions):
+          - {os: ubuntu-latest, r: '4.3', allowfail: false}
           - {os: ubuntu-latest, r: '4.2', allowfail: false}
           - {os: ubuntu-latest, r: '4.1', allowfail: false}
-          - {os: ubuntu-latest, r: '4.0', allowfail: false}
-          - {os: ubuntu-latest, r: '3.6', allowfail: false} # when a new R releases, this one has to move to check-old.yaml
+          - {os: ubuntu-latest, r: '4.0', allowfail: false} # when a new R releases, this one has to move to check-old.yaml
 
     env:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}

DESCRIPTION

@@ -1,13 +1,12 @@
 Package: AMR
-Version: 2.1.1
-Date: 2023-10-20
+Version: 2.1.1.9041
+Date: 2024-06-08
 Title: Antimicrobial Resistance Data Analysis
 Description: Functions to simplify and standardise antimicrobial resistance (AMR)
   data analysis and to work with microbial and antimicrobial properties by
   using evidence-based methods, as described in <doi:10.18637/jss.v104.i03>.
 Authors@R: c(
   person(family = "Berends",     c("Matthijs", "S."), role = c("aut", "cre"), comment = c(ORCID = "0000-0001-7620-1800"), email = "m.s.berends@umcg.nl"),
-  person(family = "Luz",         c("Christian", "F."), role = c("aut", "ctb"), comment = c(ORCID = "0000-0001-5809-5995")),
   person(family = "Souverein",   c("Dennis"), role = c("aut", "ctb"), comment = c(ORCID = "0000-0003-0455-0336")),
   person(family = "Hassing",     c("Erwin", "E.", "A."), role = c("aut", "ctb")),
   person(family = "Albers",      c("Casper", "J."), role = "ths", comment = c(ORCID = "0000-0002-9213-6743")),
@@ -18,36 +17,40 @@ Authors@R: c(
   person(family = "Hazenberg",   c("Eric", "H.", "L.", "C.", "M."), role = "ctb"),
   person(family = "Knight",      c("Gwen"), role = "ctb", comment = c(ORCID = "0000-0002-7263-9896")),
   person(family = "Lenglet",     c("Annick"), role = "ctb", comment = c(ORCID = "0000-0003-2013-8405")),
+  person(family = "Luz",         c("Christian", "F."), role = c("ctb"), comment = c(ORCID = "0000-0001-5809-5995")),
   person(family = "Meijer",      c("Bart", "C."), role = "ctb"),
   person(family = "Mykhailenko", c("Dmytro"), role = "ctb"),
   person(family = "Mymrikov",    c("Anton"), role = "ctb"),
   person(family = "Norgan",      c("Andrew", "P."), role = "ctb", comment = c(ORCID = "0000-0002-2955-2066")),
   person(family = "Ny",          c("Sofia"), role = "ctb", comment = c(ORCID = "0000-0002-2017-1363")),
+  person(family = "Saab",        c("Matthew"), role = "ctb"),
   person(family = "Salm",        c("Jonas"), role = "ctb"),
+  person(family = "Sanchez",     c("Javier"), role = "ctb", comment = c(ORCID = "0000-0003-2605-8094")),
   person(family = "Schade",      c("Rogier", "P."), role = "ctb"),
   person(family = "Sinha",       c("Bhanu", "N.", "M."), role = "ths", comment = c(ORCID = "0000-0003-1634-0010")),
+  person(family = "Stull",       c("Jason"), role = "ctb", comment = c(ORCID = "0000-0002-9028-8153")),
   person(family = "Underwood",   c("Anthony"), role = "ctb", comment = c(ORCID = "0000-0002-8547-4277")),
   person(family = "Williams",    c("Anita"), role = "ctb", comment = c(ORCID = "0000-0002-5295-8451")))
 Depends: R (>= 3.0.0)
-Enhances:
-  cleaner,
-  ggplot2,
-  janitor,
-  skimr,
-  tibble,
-  tidyselect,
-  tsibble
 Suggests: 
+  cleaner,
   cli,
   curl,
   data.table,
   dplyr,
+  ggplot2,
+  janitor,
   knitr,
   progress,
   readxl,
   rmarkdown,
   rvest,
+  skimr,
+  tibble,
+  tidyselect,
   tinytest,
+  tsibble,
+  vctrs,
   xml2
 VignetteBuilder: knitr,rmarkdown
 URL: https://msberends.github.io/AMR/, https://github.com/msberends/AMR
@@ -55,5 +58,5 @@ BugReports: https://github.com/msberends/AMR/issues
 License: GPL-2 | file LICENSE
 Encoding: UTF-8
 LazyData: true
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.1
 Roxygen: list(markdown = TRUE)

NAMESPACE

@@ -13,7 +13,6 @@ S3method("[<-",av)
 S3method("[<-",disk)
 S3method("[<-",mic)
 S3method("[<-",mo)
-S3method("[<-",rsi)
 S3method("[<-",sir)
 S3method("[[",ab)
 S3method("[[",av)
@@ -25,7 +24,6 @@ S3method("[[<-",av)
 S3method("[[<-",disk)
 S3method("[[<-",mic)
 S3method("[[<-",mo)
-S3method("[[<-",rsi)
 S3method("[[<-",sir)
 S3method("|",ab_selector)
 S3method(Complex,mic)
@@ -38,24 +36,22 @@ S3method(any,ab_selector)
 S3method(any,ab_selector_any_all)
 S3method(as.data.frame,ab)
 S3method(as.data.frame,av)
+S3method(as.data.frame,mic)
 S3method(as.data.frame,mo)
 S3method(as.double,mic)
 S3method(as.list,custom_eucast_rules)
 S3method(as.list,custom_mdro_guideline)
+S3method(as.list,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(as.sir,data.frame)
 S3method(as.sir,default)
 S3method(as.sir,disk)
 S3method(as.sir,mic)
+S3method(as.vector,mic)
 S3method(barplot,antibiogram)
 S3method(barplot,disk)
 S3method(barplot,mic)
-S3method(barplot,rsi)
 S3method(barplot,sir)
 S3method(c,ab)
 S3method(c,ab_selector)
@@ -65,11 +61,9 @@ S3method(c,custom_mdro_guideline)
 S3method(c,disk)
 S3method(c,mic)
 S3method(c,mo)
-S3method(c,rsi)
 S3method(c,sir)
 S3method(close,progress_bar)
 S3method(droplevels,mic)
-S3method(droplevels,rsi)
 S3method(droplevels,sir)
 S3method(format,bug_drug_combinations)
 S3method(hist,mic)
@@ -87,7 +81,6 @@ S3method(plot,antibiogram)
 S3method(plot,disk)
 S3method(plot,mic)
 S3method(plot,resistance_predict)
-S3method(plot,rsi)
 S3method(plot,sir)
 S3method(print,ab)
 S3method(print,av)
@@ -100,7 +93,6 @@ S3method(print,mo)
 S3method(print,mo_renamed)
 S3method(print,mo_uncertainties)
 S3method(print,pca)
-S3method(print,rsi)
 S3method(print,sir)
 S3method(quantile,mic)
 S3method(rep,ab)
@@ -108,7 +100,6 @@ S3method(rep,av)
 S3method(rep,disk)
 S3method(rep,mic)
 S3method(rep,mo)
-S3method(rep,rsi)
 S3method(rep,sir)
 S3method(skewness,data.frame)
 S3method(skewness,default)
@@ -117,14 +108,12 @@ S3method(sort,mic)
 S3method(summary,mic)
 S3method(summary,mo)
 S3method(summary,pca)
-S3method(summary,rsi)
 S3method(summary,sir)
 S3method(unique,ab)
 S3method(unique,av)
 S3method(unique,disk)
 S3method(unique,mic)
 S3method(unique,mo)
-S3method(unique,rsi)
 S3method(unique,sir)
 export("%like%")
 export("%like_case%")
@@ -132,7 +121,6 @@ export("%unlike%")
 export("%unlike_case%")
 export(NA_disk_)
 export(NA_mic_)
-export(NA_rsi_)
 export(NA_sir_)
 export(ab_atc)
 export(ab_atc_group1)
@@ -171,7 +159,6 @@ export(as.av)
 export(as.disk)
 export(as.mic)
 export(as.mo)
-export(as.rsi)
 export(as.sir)
 export(atc_online_ddd)
 export(atc_online_ddd_units)
@@ -217,21 +204,17 @@ export(custom_mdro_guideline)
 export(eucast_dosage)
 export(eucast_exceptional_phenotypes)
 export(eucast_rules)
-export(facet_rsi)
 export(facet_sir)
 export(filter_first_isolate)
 export(first_isolate)
 export(fluoroquinolones)
 export(full_join_microorganisms)
 export(g.test)
-export(geom_rsi)
 export(geom_sir)
 export(get_AMR_locale)
 export(get_episode)
 export(get_mo_source)
 export(ggplot_pca)
-export(ggplot_rsi)
-export(ggplot_rsi_predict)
 export(ggplot_sir)
 export(ggplot_sir_predict)
 export(glycopeptides)
@@ -242,8 +225,6 @@ export(is.av)
 export(is.disk)
 export(is.mic)
 export(is.mo)
-export(is.rsi)
-export(is.rsi.eligible)
 export(is.sir)
 export(is_new_episode)
 export(is_sir_eligible)
@@ -251,7 +232,6 @@ export(italicise_taxonomy)
 export(italicize_taxonomy)
 export(key_antimicrobials)
 export(kurtosis)
-export(labels_rsi_count)
 export(labels_sir_count)
 export(left_join_microorganisms)
 export(like)
@@ -273,6 +253,7 @@ export(mo_fullname)
 export(mo_gbif)
 export(mo_genus)
 export(mo_gramstain)
+export(mo_group_members)
 export(mo_info)
 export(mo_is_anaerobic)
 export(mo_is_gram_negative)
@@ -304,8 +285,8 @@ export(mo_uncertainties)
 export(mo_url)
 export(mo_year)
 export(mrgn)
-export(n_rsi)
 export(n_sir)
+export(nitrofurans)
 export(not_intrinsic_resistant)
 export(oxazolidinones)
 export(pca)
@@ -320,16 +301,18 @@ export(proportion_df)
 export(quinolones)
 export(random_disk)
 export(random_mic)
-export(random_rsi)
 export(random_sir)
+export(rescale_mic)
 export(reset_AMR_locale)
 export(resistance)
 export(resistance_predict)
+export(rifamycins)
 export(right_join_microorganisms)
-export(rsi_df)
-export(rsi_predict)
-export(scale_rsi_colours)
+export(scale_colour_mic)
+export(scale_fill_mic)
 export(scale_sir_colours)
+export(scale_x_mic)
+export(scale_y_mic)
 export(scale_y_percent)
 export(semi_join_microorganisms)
 export(set_AMR_locale)
@@ -343,7 +326,6 @@ export(skewness)
 export(streptogramins)
 export(susceptibility)
 export(tetracyclines)
-export(theme_rsi)
 export(theme_sir)
 export(translate_AMR)
 export(trimethoprims)

NEWS.md

@@ -1,3 +1,49 @@
+# AMR 2.1.1.9041
+
+*(this beta version will eventually become v3.0. We're happy to reach a new major milestone soon, which will be all about the new One Health support!)*
+
+#### A New Milestone: One Health Support (= Human + Veterinary + Environmental)
+This package now supports not only tools for AMR data analysis in clinical settings, but also for veterinary and environmental microbiology. This was made possible through a collaboration with the [University of Prince Edward Island](https://www.upei.ca/avc), Canada. To celebrate this great improvement of the package, we also updated the package logo to reflect this change.
+
+## Breaking
+* Removed all functions and references that used the deprecated `rsi` class, which were all replaced with their `sir` equivalents over a year ago
+
+## New
+* One Health implementation
+  * Function `as.sir()` now has extensive support for animal breakpoints from CLSI. Use `breakpoint_type = "animal"` and set the `host` argument to a variable that contains animal species names.
+  * The `clinical_breakpoints` data set contains all these breakpoints, and can be downloaded on our [download page](https://msberends.github.io/AMR/articles/datasets.html).
+  * The `antibiotics` data set contains all veterinary antibiotics, such as pradofloxacin and enrofloxacin. All WHOCC codes for veterinary use have been added as well.
+  * `ab_atc()` now supports ATC codes of veterinary antibiotics (that all start with "Q")
+  * `ab_url()` now supports retrieving the WHOCC url of their ATCvet pages
+* `as.sir()` now returns additional factor levels "N" for non-interpretable and "SDD" for susceptible dose-dependent. Users can now set their own criteria (using regular expressions) as to what should be considered S, I, R, SDD, and N.
+* The function group `scale_*_mic()`, namely: `scale_x_mic()`, `scale_y_mic()`, `scale_colour_mic()` and `scale_fill_mic()`. They are advanced ggplot2 extensions to allow easy plotting of MIC values. They allow for manual range definition and plotting missing intermediate log2 levels.
+* Function `rescale_mic()`, which allows to rescale MIC values to a manually set range. This is the powerhouse behind the `scale_*_mic()` functions, but it can be used by users directly to e.g. compare equality in MIC distributions by rescaling them to the same range first.
+* Function `mo_group_members()` to retrieve the member microorganisms of a microorganism group. For example, `mo_group_members("Strep group C")` returns a vector of all microorganisms that are in that group.
+
+## Changed
+* For SIR interpretation, it is now possible to use column names for argument `ab`, `mo`, and `uti`: `as.sir(..., ab = "column1", mo = "column2", uti = "column3")`. This greatly improves the flexibility for users.
+* Extended the antibiotic selectors with `nitrofurans()` and `rifamycins()`
+* Added "clindamycin inducible screening" as `CLI1` to the `antibiotics` data set. Since clindamycin is a lincosamide, the antibiotic selector `lincosamides()` now contains the argument `only_treatable = TRUE` (similar to other antibiotic selectors that contain non-treatable drugs)
+* For MICs:
+  * Added as valid levels: 4096, 6 powers of 0.0625, and 5 powers of 192 (192, 384, 576, 768, 960)
+  * Added new argument `keep_operators` to `as.mic()`. This can be `"all"` (default), `"none"`, or `"edges"`. This argument is also available in the new `rescale_mic()` and `scale_*_mic()` functions.
+  * Comparisons of MIC values are now more strict. For example, `>32` is higher than (and never equal to) `32`. Thus, `as.mic(">32") == as.mic(32)` now returns `FALSE`, and `as.mic(">32") > as.mic(32)` now returns `TRUE`.
+  * Sorting of MIC values (using `sort()`) was fixed in the same manner; `<0.001` now gets sorted before `0.001`, and `>0.001` gets sorted after `0.001`.
+* Updated `italicise_taxonomy()` to support HTML output
+* `custom_eucast_rules()` now supports multiple antibiotics and antibiotic groups to be affected by a single rule
+* `mo_info()` now contains an extra element `group_members`, with the contents of the new `mo_group_members()` function
+* Greatly improved `vctrs` integration, a Tidyverse package working in the background for many Tidyverse functions. For users, this means that functions such as `dplyr`'s `bind_rows()`, `rowwise()` and `c_across()` are now supported for e.g. columns of class `mic`. Despite this, this `AMR` package is still zero-dependent on any other package, including `dplyr` and `vctrs`.
+* Updated all ATC codes from WHOCC
+* Updated all antibiotic DDDs from WHOCC
+* Fix for using a manual value for `mo_transform` in `antibiogram()`
+* Fix for mapping 'high level' antibiotics in `as.ab()` (amphotericin B-high, gentamicin-high, kanamycin-high, streptomycin-high, tobramycin-high)
+* Improved overall algorithm of `as.ab()` for better performance and accuracy
+* When using antibiotic selectors such as `aminoglycosides()` that exclude non-treatable drugs like gentamicin-high, the function now always returns a warning that these can be included using `only_treatable = FALSE`
+
+## Other
+* Added Jordan Stull, Matthew Saab, and Javier Sanchez as contributors, to thank them for their valuable input
+
+
 # AMR 2.1.1
 
 * Fix for selecting first isolates using the phenotype-based method
@@ -132,7 +178,7 @@ The new function `add_custom_antimicrobials()` allows users to add custom antimi
 
 The `antibiotics` data set was greatly updated:
 
-  * The following 20 antibiotics have been added (also includes the [new J01RA ATC group](https://www.whocc.no/atc_ddd_index/?code=J01RA&showdescription=no)): azithromycin/fluconazole/secnidazole (AFC), cefepime/amikacin (CFA), cefixime/ornidazole (CEO), ceftriaxone/beta-lactamase inhibitor (CEB), ciprofloxacin/metronidazole (CIM), ciprofloxacin/ornidazole (CIO), ciprofloxacin/tinidazole (CIT), furazidin (FUR), isoniazid/sulfamethoxazole/trimethoprim/pyridoxine (IST), lascufloxacin (LSC), levofloxacin/ornidazole (LEO), nemonoxacin (NEM), norfloxacin/metronidazole (NME), norfloxacin/tinidazole (NTI), ofloxacin/ornidazole (OOR), oteseconazole (OTE), rifampicin/ethambutol/isoniazid (REI), sarecycline (SRC), tetracycline/oleandomycin (TOL), and thioacetazone (TAT)
+  * The following 20 antibiotics have been added (also includes the [new J01RA ATC group](https://atcddd.fhi.no/atc_ddd_index/?code=J01RA&showdescription=no)): azithromycin/fluconazole/secnidazole (AFC), cefepime/amikacin (CFA), cefixime/ornidazole (CEO), ceftriaxone/beta-lactamase inhibitor (CEB), ciprofloxacin/metronidazole (CIM), ciprofloxacin/ornidazole (CIO), ciprofloxacin/tinidazole (CIT), furazidin (FUR), isoniazid/sulfamethoxazole/trimethoprim/pyridoxine (IST), lascufloxacin (LSC), levofloxacin/ornidazole (LEO), nemonoxacin (NEM), norfloxacin/metronidazole (NME), norfloxacin/tinidazole (NTI), ofloxacin/ornidazole (OOR), oteseconazole (OTE), rifampicin/ethambutol/isoniazid (REI), sarecycline (SRC), tetracycline/oleandomycin (TOL), and thioacetazone (TAT)
   * Added some missing ATC codes
   * Updated DDDs and PubChem Compound IDs
   * Updated some antibiotic name spelling, now used by WHOCC (such as cephalexin -> cefalexin, and phenethicillin -> pheneticillin)
@@ -145,7 +191,7 @@ Also, we added support for using antibiotic selectors in scoped `dplyr` verbs (w
 
 We now added extensive support for antiviral agents! For the first time, the `AMR` package has extensive support for antiviral drugs and to work with their names, codes and other data in any way.
 
-* The `antivirals` data set has been extended with 18 new drugs (also from the [new J05AJ ATC group](https://www.whocc.no/atc_ddd_index/?code=J05AJ&showdescription=no)) and now also contains antiviral identifiers and LOINC codes
+* The `antivirals` data set has been extended with 18 new drugs (also from the [new J05AJ ATC group](https://atcddd.fhi.no/atc_ddd_index/?code=J05AJ&showdescription=no)) and now also contains antiviral identifiers and LOINC codes
 * A new data type `av` (*antivirals*) has been added, which is functionally similar to `ab` for antibiotics
 * Functions `as.av()`, `av_name()`, `av_atc()`, `av_synonyms()`, `av_from_text()` have all been added as siblings to their `ab_*()` equivalents
 

R/aa_globals.R

@@ -28,7 +28,7 @@
 # ==================================================================== #
 
 # add new version numbers here, and add the rules themselves to "data-raw/eucast_rules.tsv" and clinical_breakpoints
-# (sourcing "data-raw/_pre_commit_hook.R" will process the TSV file)
+# (sourcing "data-raw/_pre_commit_checks.R" will process the TSV file)
 EUCAST_VERSION_BREAKPOINTS <- list(
   # "13.0" = list(
   #   version_txt = "v13.0",
@@ -86,8 +86,8 @@ EUCAST_VERSION_EXPERT_RULES <- list(
 
 TAXONOMY_VERSION <- list(
   GBIF = list(
-    accessed_date = as.Date("2022-12-11"),
-    citation = "GBIF Secretariat (2022). GBIF Backbone Taxonomy. Checklist dataset \\doi{10.15468/39omei}.",
+    accessed_date = as.Date("2024-01-08"),
+    citation = "GBIF Secretariat (2023). GBIF Backbone Taxonomy. Checklist dataset \\doi{10.15468/39omei}.",
     url = "https://www.gbif.org"
   ),
   LPSN = list(
@@ -146,6 +146,8 @@ globalVariables(c(
   "group",
   "guideline",
   "hjust",
+  "host_index",
+  "host_match",
   "input",
   "intrinsic_resistant",
   "isolates",

R/aa_helper_functions.R

@@ -237,7 +237,7 @@ addin_insert_like <- function() {
   }
 }
 
-search_type_in_df <- function(x, type, info = TRUE) {
+search_type_in_df <- function(x, type, info = TRUE, add_col_prefix = TRUE) {
   meet_criteria(x, allow_class = "data.frame")
   meet_criteria(type, allow_class = "character", has_length = 1)
 
@@ -280,7 +280,7 @@ search_type_in_df <- function(x, type, info = TRUE) {
       if (!inherits(pm_pull(x, found), c("Date", "POSIXct"))) {
         stop(
           font_red(paste0(
-            "Found column '", font_bold(found), "' to be used as input for `col_", type,
+            "Found column '", font_bold(found), "' to be used as input for `", ifelse(add_col_prefix, "col_", ""), type,
             "`, but this column contains no valid dates. Transform its values to valid dates first."
           )),
           call. = FALSE
@@ -311,6 +311,14 @@ search_type_in_df <- function(x, type, info = TRUE) {
       found <- sort(colnames(x)[colnames_formatted %like_case% "^(specimen)"])
     }
   }
+  # -- host (animals)
+  if (type == "host") {
+    if (any(colnames_formatted %like_case% "^(host|animal)")) {
+      found <- sort(colnames(x)[colnames_formatted %like_case% "^(host|animal)"])
+    } else if (any(colnames_formatted %like_case% "((^|[^A-Za-z])host($|[^A-Za-z])|animal)")) {
+      found <- sort(colnames(x)[colnames_formatted %like_case% "((^|[^A-Za-z])host($|[^A-Za-z])|animal)"])
+    }
+  }
   # -- UTI (urinary tract infection)
   if (type == "uti") {
     if (any(colnames_formatted == "uti")) {
@@ -321,7 +329,7 @@ search_type_in_df <- function(x, type, info = TRUE) {
     if (!is.null(found)) {
       # this column should contain logicals
       if (!is.logical(x[, found, drop = TRUE])) {
-        message_("Column '", font_bold(found), "' found as input for `col_", type,
+        message_("Column '", font_bold(found), "' found as input for `", ifelse(add_col_prefix, "col_", ""), type,
           "`, but this column does not contain 'logical' values (TRUE/FALSE) and was ignored.",
           add_fn = font_red
         )
@@ -334,9 +342,9 @@ search_type_in_df <- function(x, type, info = TRUE) {
 
   if (!is.null(found) && isTRUE(info)) {
     if (message_not_thrown_before("search_in_type", type)) {
-      msg <- paste0("Using column '", font_bold(found), "' as input for `col_", type, "`.")
+      msg <- paste0("Using column '", font_bold(found), "' as input for `", ifelse(add_col_prefix, "col_", ""), type, "`.")
       if (type %in% c("keyantibiotics", "keyantimicrobials", "specimen")) {
-        msg <- paste(msg, "Use", font_bold(paste0("col_", type), "= FALSE"), "to prevent this.")
+        msg <- paste(msg, "Use", font_bold(paste0(ifelse(add_col_prefix, "col_", ""), type), "= FALSE"), "to prevent this.")
       }
       message_(msg)
     }
@@ -456,7 +464,8 @@ word_wrap <- function(...,
   ops <- "([,./><\\]\\[])"
   msg <- gsub(paste0(ops, " ", ops), "\\1\\2", msg, perl = TRUE)
   # we need to correct for already applied style, that adds text like "\033[31m\"
-  msg_stripped <- font_stripstyle(msg)
+  msg_stripped <- gsub("(.*)?\\033\\]8;;.*\\a(.*?)\\033\\]8;;\\a(.*)", "\\1\\2\\3", msg, perl = TRUE) # for font_url()
+  msg_stripped <- font_stripstyle(msg_stripped)
   # where are the spaces now?
   msg_stripped_wrapped <- paste0(
     strwrap(msg_stripped,
@@ -680,7 +689,7 @@ create_eucast_ab_documentation <- function() {
   ab <- character()
   for (val in x) {
     if (paste0("AB_", val) %in% ls(envir = asNamespace("AMR"))) {
-      # antibiotic group names, as defined in data-raw/_pre_commit_hook.R, such as `CARBAPENEMS`
+      # antibiotic group names, as defined in data-raw/_pre_commit_checks.R, such as `CARBAPENEMS`
       val <- eval(parse(text = paste0("AB_", val)), envir = asNamespace("AMR"))
     } else if (val %in% AMR_env$AB_lookup$ab) {
       # separate drugs, such as `AMX`
@@ -734,6 +743,10 @@ vector_or <- function(v, quotes = TRUE, reverse = FALSE, sort = TRUE, initial_ca
     # class 'sir' should be sorted like this
     v <- c("S", "I", "R")
   }
+  if (identical(v, c("I", "N", "R", "S", "SDD"))) {
+    # class 'sir' should be sorted like this
+    v <- c("S", "SDD", "I", "R", "N")
+  }
   # oxford comma
   if (last_sep %in% c(" or ", " and ") && length(v) > 2) {
     last_sep <- paste0(",", last_sep)
@@ -826,7 +839,7 @@ meet_criteria <- function(object, # can be literally `list(...)` for `allow_argu
     return(invisible())
   }
 
-  if (!is.null(allow_class)) {
+  if (!is.null(allow_class) && !(suppressWarnings(all(is.na(object))) && allow_NA == TRUE)) {
     stop_ifnot(inherits(object, allow_class), "argument `", obj_name,
       "` must be ", format_class(allow_class, plural = isTRUE(has_length > 1)),
       ", i.e. not be ", format_class(class(object), plural = isTRUE(has_length > 1)),
@@ -862,12 +875,20 @@ meet_criteria <- function(object, # can be literally `list(...)` for `allow_argu
       object <- tolower(object)
       is_in <- tolower(is_in)
     }
-    stop_ifnot(all(object %in% is_in, na.rm = TRUE), "argument `", obj_name, "` ",
+    is_in.bak <- is_in
+    if ("logical" %in% allow_class) {
+      is_in <- is_in[!is_in %in% c("TRUE", "FALSE")]
+    }
+    or_values <- vector_or(is_in, quotes = !isTRUE(any(c("numeric", "integer") %in% allow_class)))
+    if ("logical" %in% allow_class) {
+      or_values <- paste0(or_values, ", or TRUE or FALSE")
+    }
+    stop_ifnot(all(object %in% is_in.bak, na.rm = TRUE), "argument `", obj_name, "` ",
       ifelse(!is.null(has_length) && length(has_length) == 1 && has_length == 1,
         "must be either ",
         "must only contain values "
       ),
-      vector_or(is_in, quotes = !isTRUE(any(c("double", "numeric", "integer") %in% allow_class))),
+      or_values,
       ifelse(allow_NA == TRUE, ", or NA", ""),
       call = call_depth
     )
@@ -1028,10 +1049,15 @@ get_current_column <- function() {
     if (tryCatch(!is.null(env$i), error = function(e) FALSE)) {
       if (!is.null(env$tibble_vars)) {
         # for mutate_if()
+        # TODO remove later, was part of older dplyr versions (at least not in dplyr 1.1.4)
         env$tibble_vars[env$i]
       } else {
         # for mutate(across())
-        df <- tryCatch(get_current_data(NA, 0), error = function(e) NULL)
+        if (!is.null(env$data) && is.data.frame(env$data)) {
+          df <- env$data
+        } else {
+          df <- tryCatch(get_current_data(NA, 0), error = function(e) NULL)
+        }
         if (is.data.frame(df)) {
           colnames(df)[env$i]
         } else {
@@ -1551,7 +1577,7 @@ readRDS_AMR <- function(file, refhook = NULL) {
 match <- function(x, table, ...) {
   if (!is.null(AMR_env$chmatch) && inherits(x, "character") && inherits(table, "character")) {
     # data.table::chmatch() is much faster than base::match() for character
-    AMR_env$chmatch(x, table, ...)
+    tryCatch(AMR_env$chmatch(x, table, ...), error = function(e) base::match(x, table, ...))
   } else {
     base::match(x, table, ...)
   }
@@ -1559,7 +1585,7 @@ match <- function(x, table, ...) {
 `%in%` <- function(x, table) {
   if (!is.null(AMR_env$chin) && inherits(x, "character") && inherits(table, "character")) {
     # data.table::`%chin%`() is much faster than base::`%in%`() for character
-    AMR_env$chin(x, table)
+    tryCatch(AMR_env$chin(x, table), error = function(e) base::`%in%`(x, table))
   } else {
     base::`%in%`(x, table)
   }

R/aa_options.R

@@ -31,19 +31,19 @@
 #'
 #' This is an overview of all the package-specific [options()] you can set in the `AMR` package.
 #' @section Options:
-#' * `AMR_custom_ab` \cr Allows to use custom antimicrobial drugs with this package. This is explained in [add_custom_antimicrobials()].
-#' * `AMR_custom_mo` \cr Allows to use custom microorganisms with this package. This is explained in [add_custom_microorganisms()].
-#' * `AMR_eucastrules` \cr Used for setting the default types of rules for [eucast_rules()] function, must be one or more of: `"breakpoints"`, `"expert"`, `"other"`, `"custom"`, `"all"`, and defaults to `c("breakpoints", "expert")`.
-#' * `AMR_guideline` \cr Used for setting the default guideline for interpreting MIC values and disk diffusion diameters with [as.sir()]. Can be only the guideline name (e.g., `"CLSI"`) or the name with a year (e.g. `"CLSI 2019"`). The default to the latest implemented EUCAST guideline, currently \code{"`r clinical_breakpoints$guideline[1]`"}. Supported guideline are currently EUCAST (`r min(as.integer(gsub("[^0-9]", "", subset(clinical_breakpoints, guideline %like% "EUCAST")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(clinical_breakpoints, guideline %like% "EUCAST")$guideline)))`) and CLSI (`r min(as.integer(gsub("[^0-9]", "", subset(clinical_breakpoints, guideline %like% "CLSI")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(clinical_breakpoints, guideline %like% "CLSI")$guideline)))`).
+#' * `AMR_breakpoint_type` \cr A [character] to use in [as.sir()], to indicate which breakpoint type to use. This must be either `r vector_or(clinical_breakpoints$type)`.
+#' * `AMR_cleaning_regex` \cr A [regular expression][base::regex] (case-insensitive) to use in [as.mo()] and all [`mo_*`][mo_property()] functions, to clean the user input. The default is the outcome of [mo_cleaning_regex()], which removes texts between brackets and texts such as "species" and "serovar".
+#' * `AMR_custom_ab` \cr A file location to an RDS file, to use custom antimicrobial drugs with this package. This is explained in [add_custom_antimicrobials()].
+#' * `AMR_custom_mo` \cr A file location to an RDS file, to use custom microorganisms with this package. This is explained in [add_custom_microorganisms()].
+#' * `AMR_eucastrules` \cr A [character] to set the default types of rules for [eucast_rules()] function, must be one or more of: `"breakpoints"`, `"expert"`, `"other"`, `"custom"`, `"all"`, and defaults to `c("breakpoints", "expert")`.
+#' * `AMR_guideline` \cr A [character] to set the default guideline for interpreting MIC values and disk diffusion diameters with [as.sir()]. Can be only the guideline name (e.g., `"CLSI"`) or the name with a year (e.g. `"CLSI 2019"`). The default to the latest implemented EUCAST guideline, currently \code{"`r clinical_breakpoints$guideline[1]`"}. Supported guideline are currently EUCAST (`r min(as.integer(gsub("[^0-9]", "", subset(clinical_breakpoints, guideline %like% "EUCAST")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(clinical_breakpoints, guideline %like% "EUCAST")$guideline)))`) and CLSI (`r min(as.integer(gsub("[^0-9]", "", subset(clinical_breakpoints, guideline %like% "CLSI")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(clinical_breakpoints, guideline %like% "CLSI")$guideline)))`).
 #' * `AMR_ignore_pattern` \cr A [regular expression][base::regex] to ignore (i.e., make `NA`) any match given in [as.mo()] and all [`mo_*`][mo_property()] functions.
 #' * `AMR_include_PKPD` \cr A [logical] to use in [as.sir()], to indicate that PK/PD clinical breakpoints must be applied as a last resort - the default is `TRUE`.
-#' * `AMR_ecoff` \cr A [logical] use in [as.sir()], to indicate that ECOFF (Epidemiological Cut-Off) values must be used - the default is `FALSE`.
 #' * `AMR_include_screening` \cr A [logical] to use in [as.sir()], to indicate that clinical breakpoints for screening are allowed - the default is `FALSE`.
 #' * `AMR_keep_synonyms` \cr A [logical] to use in [as.mo()] and all [`mo_*`][mo_property()] functions, to indicate if old, previously valid taxonomic names must be preserved and not be corrected to currently accepted names. The default is `FALSE`.
-#' * `AMR_cleaning_regex` \cr A [regular expression][base::regex] (case-insensitive) to use in [as.mo()] and all [`mo_*`][mo_property()] functions, to clean the user input. The default is the outcome of [mo_cleaning_regex()], which removes texts between brackets and texts such as "species" and "serovar".
-#' * `AMR_locale` \cr A language to use for the `AMR` package, can be one of these supported language names or ISO-639-1 codes: `r vector_or(paste0(sapply(LANGUAGES_SUPPORTED_NAMES, function(x) x[[1]]), " (" , LANGUAGES_SUPPORTED, ")"), quotes = FALSE, sort = FALSE)`. The default is the current system language (if supported).
+#' * `AMR_locale` \cr A [character] to set the language for the `AMR` package, can be one of these supported language names or ISO-639-1 codes: `r vector_or(paste0(sapply(LANGUAGES_SUPPORTED_NAMES, function(x) x[[1]]), " (" , LANGUAGES_SUPPORTED, ")"), quotes = FALSE, sort = FALSE)`. The default is the current system language (if supported, English otherwise).
 #' * `AMR_mo_source` \cr A file location for a manual code list to be used in [as.mo()] and all [`mo_*`][mo_property()] functions. This is explained in [set_mo_source()].
-#'
+#' 
 #' @section Saving Settings Between Sessions:
 #' Settings in \R are not saved globally and are thus lost when \R is exited. You can save your options to your own `.Rprofile` file, which is a user-specific file. You can edit it using:
 #'
@@ -51,18 +51,18 @@
 #'   utils::file.edit("~/.Rprofile")
 #' ```
 #'
-#' In this file, you can set options such as:
+#' In this file, you can set options such as...
 #'
 #' ```r
 #'  options(AMR_locale = "pt")
 #'  options(AMR_include_PKPD = TRUE)
 #'  ```
 #'
-#' to add Portuguese language support of antibiotics, and allow PK/PD rules when interpreting MIC values with [as.sir()].
+#' ...to add Portuguese language support of antibiotics, and allow PK/PD rules when interpreting MIC values with [as.sir()].
 #'
 #' ### Share Options Within Team
 #'
-#' For a more global approach, e.g. within a data team, save an options file to a remote file location, such as a shared network drive. This would work in this way:
+#' For a more global approach, e.g. within a (data) team, save an options file to a remote file location, such as a shared network drive, and have each user read in this file automatically at start-up. This would work in this way:
 #'
 #' 1. Save a plain text file to e.g. "X:/team_folder/R_options.R" and fill it with preferred settings.
 #'

R/ab.R

@@ -51,7 +51,7 @@
 #'
 #' You can add your own manual codes to be considered by [as.ab()] and all [`ab_*`][ab_property()] functions, see [add_custom_antimicrobials()].
 #' @section Source:
-#' World Health Organization (WHO) Collaborating Centre for Drug Statistics Methodology: \url{https://www.whocc.no/atc_ddd_index/}
+#' World Health Organization (WHO) Collaborating Centre for Drug Statistics Methodology: \url{https://atcddd.fhi.no/atc_ddd_index/}
 #'
 #' European Commission Public Health PHARMACEUTICALS - COMMUNITY REGISTER: \url{https://ec.europa.eu/health/documents/community-register/html/reg_hum_atc.htm}
 #' @aliases ab
@@ -107,7 +107,10 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
     ))
   }
 
-  initial_search <- is.null(list(...)$initial_search)
+  loop_time <- list(...)$loop_time
+  if (is.null(loop_time)) {
+    loop_time <- 1
+  }
   already_regex <- isTRUE(list(...)$already_regex)
   fast_mode <- isTRUE(list(...)$fast_mode)
 
@@ -117,8 +120,8 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
   # remove diacritics
   x <- iconv(x, from = "UTF-8", to = "ASCII//TRANSLIT")
   x <- gsub('"', "", x, fixed = TRUE)
-  x <- gsub("(specimen|specimen date|specimen_date|spec_date|gender|^dates?$)", "", x, ignore.case = TRUE, perl = TRUE)
-  # penicillin is a special case: we call it so, but then mean benzylpenicillin
+  x <- gsub("(specimen|specimen date|specimen_date|spec_date|gender|^dates?$|animal|host($|[a-z]))", "", x, ignore.case = TRUE, perl = TRUE)
+  # penicillin is a special case: we call it so, but then most often mean benzylpenicillin
   x[x %like_case% "^PENICILLIN" & x %unlike_case% "[ /+-]"] <- "benzylpenicillin"
   x_bak_clean <- x
   if (already_regex == FALSE) {
@@ -131,16 +134,21 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
   x_unknown_ATCs <- character(0)
 
   note_if_more_than_one_found <- function(found, index, from_text) {
-    if (isTRUE(initial_search) && isTRUE(length(from_text) > 1)) {
-      abnames <- ab_name(from_text, tolower = TRUE, initial_search = FALSE)
+    if (loop_time == 1 && isTRUE(length(from_text) > 1)) {
+      abnames <- ab_name(from_text, tolower = TRUE, loop_time = loop_time + 1)
       if (ab_name(found[1L], language = NULL) %like% "(clavulanic acid|(avi|tazo|mono|vabor)bactam)") {
         abnames <- abnames[!abnames %in% c("clavulanic acid", "avibactam", "tazobactam", "vaborbactam", "monobactam")]
       }
       if (length(abnames) > 1) {
-        message_(
-          "More than one result was found for item ", index, ": ",
-          vector_and(abnames, quotes = FALSE)
-        )
+        if (toupper(paste(abnames, collapse = " ")) %in% AMR_env$AB_lookup$generalised_name) {
+          # if the found values combined is a valid AB, return that
+          found <- AMR_env$AB_lookup$ab[match(toupper(paste(abnames, collapse = " ")), AMR_env$AB_lookup$generalised_name)][1]
+        } else {
+          message_(
+            "More than one result was found for item ", index, ": ",
+            vector_and(abnames, quotes = FALSE)
+          )
+        }
       }
     }
     found[1L]
@@ -174,13 +182,13 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
   x_new[is.na(x)] <- NA
   already_known[is.na(x)] <- FALSE
 
-  if (isTRUE(initial_search) && sum(already_known) < length(x)) {
+  if (loop_time == 1 && sum(already_known) < length(x)) {
     progress <- progress_ticker(n = sum(!already_known), n_min = 25, print = info) # start if n >= 25
     on.exit(close(progress))
   }
 
   for (i in which(!already_known)) {
-    if (isTRUE(initial_search)) {
+    if (loop_time == 1) {
       progress$tick()
     }
 
@@ -202,7 +210,7 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
     }
 
     if (fast_mode == FALSE && flag_multiple_results == TRUE && x[i] %like% "[ ]") {
-      from_text <- tryCatch(suppressWarnings(ab_from_text(x[i], initial_search = FALSE, translate_ab = FALSE)[[1]]),
+      from_text <- tryCatch(suppressWarnings(ab_from_text(x[i], loop_time = loop_time + 1, translate_ab = FALSE)[[1]]),
         error = function(e) character(0)
       )
     } else {
@@ -314,13 +322,12 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
     }
 
     # INITIAL SEARCH - More uncertain results ----
-
-    if (isTRUE(initial_search) && fast_mode == FALSE) {
-      # only run on first try
+    if (loop_time <= 2 && fast_mode == FALSE) {
+      # only run on first and second try
 
       # try by removing all spaces
       if (x[i] %like% " ") {
-        found <- suppressWarnings(as.ab(gsub(" +", "", x[i], perl = TRUE), initial_search = FALSE))
+        found <- suppressWarnings(as.ab(gsub(" +", "", x[i], perl = TRUE), loop_time = loop_time + 2))
         if (length(found) > 0 && !is.na(found)) {
           x_new[i] <- note_if_more_than_one_found(found, i, from_text)
           next
@@ -329,7 +336,7 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
 
       # try by removing all spaces and numbers
       if (x[i] %like% " " || x[i] %like% "[0-9]") {
-        found <- suppressWarnings(as.ab(gsub("[ 0-9]", "", x[i], perl = TRUE), initial_search = FALSE))
+        found <- suppressWarnings(as.ab(gsub("[ 0-9]", "", x[i], perl = TRUE), loop_time = loop_time + 2))
         if (length(found) > 0 && !is.na(found)) {
           x_new[i] <- note_if_more_than_one_found(found, i, from_text)
           next
@@ -355,7 +362,7 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
         )[[1]],
         collapse = "/"
       )
-      x_translated_guess <- suppressWarnings(as.ab(x_translated, initial_search = FALSE))
+      x_translated_guess <- suppressWarnings(as.ab(x_translated, loop_time = loop_time + 2))
       if (!is.na(x_translated_guess)) {
         x_new[i] <- x_translated_guess
         next
@@ -367,7 +374,7 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
           strsplit(x_translated, "[^A-Z0-9 ]"),
           function(y) {
             for (i in seq_len(length(y))) {
-              y_name <- suppressWarnings(ab_name(y[i], language = NULL, initial_search = FALSE))
+              y_name <- suppressWarnings(ab_name(y[i], language = NULL, loop_time = loop_time + 2))
               y[i] <- ifelse(!is.na(y_name),
                 y_name,
                 y[i]
@@ -378,7 +385,7 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
         )[[1]],
         collapse = "/"
       )
-      x_translated_guess <- suppressWarnings(as.ab(x_translated, initial_search = FALSE))
+      x_translated_guess <- suppressWarnings(as.ab(x_translated, loop_time = loop_time + 2))
       if (!is.na(x_translated_guess)) {
         x_new[i] <- x_translated_guess
         next
@@ -386,7 +393,7 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
 
       # try by removing all trailing capitals
       if (x[i] %like_case% "[a-z]+[A-Z]+$") {
-        found <- suppressWarnings(as.ab(gsub("[A-Z]+$", "", x[i], perl = TRUE), initial_search = FALSE))
+        found <- suppressWarnings(as.ab(gsub("[A-Z]+$", "", x[i], perl = TRUE), loop_time = loop_time + 2))
         if (!is.na(found)) {
           x_new[i] <- note_if_more_than_one_found(found, i, from_text)
           next
@@ -394,7 +401,7 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
       }
 
       # keep only letters
-      found <- suppressWarnings(as.ab(gsub("[^A-Z]", "", x[i], perl = TRUE), initial_search = FALSE))
+      found <- suppressWarnings(as.ab(gsub("[^A-Z]", "", x[i], perl = TRUE), loop_time = loop_time + 2))
       if (!is.na(found)) {
         x_new[i] <- note_if_more_than_one_found(found, i, from_text)
         next
@@ -405,7 +412,7 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
       if (flag_multiple_results == TRUE) {
         found <- from_text[1L]
       } else {
-        found <- tryCatch(suppressWarnings(ab_from_text(x[i], initial_search = FALSE, translate_ab = FALSE)[[1]][1L]),
+        found <- tryCatch(suppressWarnings(ab_from_text(x[i], loop_time = loop_time + 2, translate_ab = FALSE)[[1]][1L]),
           error = function(e) NA_character_
         )
       }
@@ -415,12 +422,12 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
       }
 
       # first 5 except for cephalosporins, then first 7 (those cephalosporins all start quite the same!)
-      found <- suppressWarnings(as.ab(substr(x[i], 1, 5), initial_search = FALSE))
-      if (!is.na(found) && ab_group(found, initial_search = FALSE) %unlike% "cephalosporins") {
+      found <- suppressWarnings(as.ab(substr(x[i], 1, 5), loop_time = loop_time + 2))
+      if (!is.na(found) && ab_group(found, loop_time = loop_time + 1) %unlike% "cephalosporins") {
         x_new[i] <- note_if_more_than_one_found(found, i, from_text)
         next
       }
-      found <- suppressWarnings(as.ab(substr(x[i], 1, 7), initial_search = FALSE))
+      found <- suppressWarnings(as.ab(substr(x[i], 1, 7), loop_time = loop_time + 2))
       if (!is.na(found)) {
         x_new[i] <- note_if_more_than_one_found(found, i, from_text)
         next
@@ -428,7 +435,7 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
 
       # make all consonants facultative
       search_str <- gsub("([BCDFGHJKLMNPQRSTVWXZ])", "\\1*", x[i], perl = TRUE)
-      found <- suppressWarnings(as.ab(search_str, initial_search = FALSE, already_regex = TRUE))
+      found <- suppressWarnings(as.ab(search_str, loop_time = loop_time + 2, already_regex = TRUE))
       # keep at least 4 normal characters
       if (nchar(gsub(".\\*", "", search_str, perl = TRUE)) < 4) {
         found <- NA
@@ -440,7 +447,7 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
 
       # make all vowels facultative
       search_str <- gsub("([AEIOUY])", "\\1*", x[i], perl = TRUE)
-      found <- suppressWarnings(as.ab(search_str, initial_search = FALSE, already_regex = TRUE))
+      found <- suppressWarnings(as.ab(search_str, loop_time = loop_time + 2, already_regex = TRUE))
       # keep at least 5 normal characters
       if (nchar(gsub(".\\*", "", search_str, perl = TRUE)) < 5) {
         found <- NA
@@ -456,7 +463,7 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
       x_spelling <- gsub("I+", "[AEIOU]+", x_spelling, fixed = TRUE)
       x_spelling <- gsub("O+", "[AEIOU]+", x_spelling, fixed = TRUE)
       x_spelling <- gsub("U+", "[AEIOU]+", x_spelling, fixed = TRUE)
-      found <- suppressWarnings(as.ab(x_spelling, initial_search = FALSE, already_regex = TRUE))
+      found <- suppressWarnings(as.ab(x_spelling, loop_time = loop_time + 2, already_regex = TRUE))
       if (!is.na(found)) {
         x_new[i] <- note_if_more_than_one_found(found, i, from_text)
         next
@@ -473,7 +480,7 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
           # ending part:
           substr(x[i], j + 2, nchar(x[i]))
         )
-        found <- suppressWarnings(as.ab(x_switched, initial_search = FALSE))
+        found <- suppressWarnings(as.ab(x_switched, loop_time = loop_time + 1))
         if (!is.na(found)) {
           break
         }
@@ -482,18 +489,18 @@ as.ab <- function(x, flag_multiple_results = TRUE, info = interactive(), ...) {
         x_new[i] <- found[1L]
         next
       }
-    } # end of initial_search = TRUE
+    } # end of loop_time <= 2
 
     # not found
     x_unknown <- c(x_unknown, x_bak[x[i] == x_bak_clean][1])
   }
 
-  if (isTRUE(initial_search) && sum(already_known) < length(x)) {
+  if (loop_time == 1 && sum(already_known) < length(x)) {
     close(progress)
   }
 
   # save to package env to save time for next time
-  if (isTRUE(initial_search)) {
+  if (loop_time == 1) {
     AMR_env$ab_previously_coerced <- AMR_env$ab_previously_coerced[which(!AMR_env$ab_previously_coerced$x %in% x), , drop = FALSE]
     AMR_env$ab_previously_coerced <- unique(rbind_AMR(
       AMR_env$ab_previously_coerced,
@@ -645,12 +652,14 @@ generalise_antibiotic_name <- function(x) {
   x <- gsub("_(MIC|RSI|SIR|DIS[CK])$", "", x, perl = TRUE)
   # remove disk concentrations, like LVX_NM -> LVX
   x <- gsub("_[A-Z]{2}[0-9_.]{0,3}$", "", x, perl = TRUE)
-  # remove part between brackets if that's followed by another string
-  x <- gsub("(.*)+ [(].*[)]", "\\1", x)
   # keep only max 1 space
   x <- trimws2(gsub(" +", " ", x, perl = TRUE))
   # non-character, space or number should be a slash
-  x <- gsub("[^A-Z0-9 -]", "/", x, perl = TRUE)
+  x <- gsub("[^A-Z0-9 -)(]", "/", x, perl = TRUE)
+  # correct for 'high level' antibiotics
+  x <- gsub("([^A-Z0-9/ -]+)?(HIGH(.?LE?VE?L)?|[^A-Z0-9/]H[^A-Z0-9]?L)([^A-Z0-9 -]+)?", "-HIGH", x, perl = TRUE)
+  # remove part between brackets if that's followed by another string
+  x <- gsub("(.*)+ [(].*[)]", "\\1", x)
   # spaces around non-characters must be removed: amox + clav -> amox/clav
   x <- gsub("(.*[A-Z0-9]) ([^A-Z0-9].*)", "\\1\\2", x, perl = TRUE)
   x <- gsub("(.*[^A-Z0-9]) ([A-Z0-9].*)", "\\1\\2", x, perl = TRUE)

R/ab_from_text.R

@@ -129,6 +129,10 @@ ab_from_text <- function(text,
       text_split_all <- text_split_all[nchar(text_split_all) >= 4 & grepl("[a-z]+", text_split_all)]
       result <- lapply(text_split_all, function(text_split) {
         progress$tick()
+        text_split <- text_split[text_split %like% "[A-Z]" & text_split %unlike% "[0-9]"]
+        if (length(text_split) == 0) {
+          return(as.ab(NA_character_))
+        }
         suppressWarnings(
           as.ab(text_split, ...)
         )

R/ab_property.R

@@ -245,7 +245,7 @@ ab_ddd <- function(x, administration = "oral", ...) {
     warning_(
       "in `ab_ddd()`: DDDs of some combined products are available for different dose combinations and not (yet) part of the AMR package.",
       "Please refer to the WHOCC website:\n",
-      "www.whocc.no/ddd/list_of_ddds_combined_products/"
+      "atcddd.fhi.no/ddd/list_of_ddds_combined_products/"
     )
   }
   out
@@ -265,7 +265,7 @@ ab_ddd_units <- function(x, administration = "oral", ...) {
     warning_(
       "in `ab_ddd_units()`: DDDs of some combined products are available for different dose combinations and not (yet) part of the AMR package.",
       "Please refer to the WHOCC website:\n",
-      "www.whocc.no/ddd/list_of_ddds_combined_products/"
+      "atcddd.fhi.no/ddd/list_of_ddds_combined_products/"
     )
   }
   out
@@ -310,7 +310,10 @@ ab_url <- function(x, open = FALSE, ...) {
 
   ab <- as.ab(x = x, ...)
   atcs <- ab_atc(ab, only_first = TRUE)
-  u <- paste0("https://www.whocc.no/atc_ddd_index/?code=", atcs, "&showdescription=no")
+  u <- character(length(atcs))
+  # veterinary codes
+  u[atcs %like% "^Q"] <- paste0("https://atcddd.fhi.no/atcvet/atcvet_index/?code=", atcs[atcs %like% "^Q"], "&showdescription=no")
+  u[atcs %unlike% "^Q"] <- paste0("https://atcddd.fhi.no/atc_ddd_index//?code=", atcs[atcs %unlike% "^Q"], "&showdescription=no")
   u[is.na(atcs)] <- NA_character_
   names(u) <- ab_name(ab)
 

R/ab_selectors.R

@@ -226,10 +226,6 @@ ab_class <- function(ab_class,
   meet_criteria(ab_class, allow_class = "character", has_length = 1, allow_NULL = TRUE)
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
   meet_criteria(only_treatable, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec(NULL, only_sir_columns = only_sir_columns, ab_class_args = ab_class, only_treatable = only_treatable)
 }
 
@@ -242,10 +238,6 @@ ab_selector <- function(filter,
                         ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
   meet_criteria(only_treatable, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
 
   # get_current_data() has to run each time, for cases where e.g., filter() and select() are used in same call
   # but it only takes a couple of milliseconds
@@ -277,10 +269,6 @@ ab_selector <- function(filter,
 aminoglycosides <- function(only_sir_columns = FALSE, only_treatable = TRUE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
   meet_criteria(only_treatable, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("aminoglycosides", only_sir_columns = only_sir_columns, only_treatable = only_treatable)
 }
 
@@ -288,10 +276,6 @@ aminoglycosides <- function(only_sir_columns = FALSE, only_treatable = TRUE, ...
 #' @export
 aminopenicillins <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("aminopenicillins", only_sir_columns = only_sir_columns)
 }
 
@@ -299,10 +283,6 @@ aminopenicillins <- function(only_sir_columns = FALSE, ...) {
 #' @export
 antifungals <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("antifungals", only_sir_columns = only_sir_columns)
 }
 
@@ -310,10 +290,6 @@ antifungals <- function(only_sir_columns = FALSE, ...) {
 #' @export
 antimycobacterials <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("antimycobacterials", only_sir_columns = only_sir_columns)
 }
 
@@ -322,10 +298,6 @@ antimycobacterials <- function(only_sir_columns = FALSE, ...) {
 betalactams <- function(only_sir_columns = FALSE, only_treatable = TRUE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
   meet_criteria(only_treatable, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("betalactams", only_sir_columns = only_sir_columns, only_treatable = only_treatable)
 }
 
@@ -334,10 +306,6 @@ betalactams <- function(only_sir_columns = FALSE, only_treatable = TRUE, ...) {
 carbapenems <- function(only_sir_columns = FALSE, only_treatable = TRUE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
   meet_criteria(only_treatable, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("carbapenems", only_sir_columns = only_sir_columns, only_treatable = only_treatable)
 }
 
@@ -345,10 +313,6 @@ carbapenems <- function(only_sir_columns = FALSE, only_treatable = TRUE, ...) {
 #' @export
 cephalosporins <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("cephalosporins", only_sir_columns = only_sir_columns)
 }
 
@@ -356,10 +320,6 @@ cephalosporins <- function(only_sir_columns = FALSE, ...) {
 #' @export
 cephalosporins_1st <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("cephalosporins_1st", only_sir_columns = only_sir_columns)
 }
 
@@ -367,10 +327,6 @@ cephalosporins_1st <- function(only_sir_columns = FALSE, ...) {
 #' @export
 cephalosporins_2nd <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("cephalosporins_2nd", only_sir_columns = only_sir_columns)
 }
 
@@ -378,10 +334,6 @@ cephalosporins_2nd <- function(only_sir_columns = FALSE, ...) {
 #' @export
 cephalosporins_3rd <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("cephalosporins_3rd", only_sir_columns = only_sir_columns)
 }
 
@@ -389,10 +341,6 @@ cephalosporins_3rd <- function(only_sir_columns = FALSE, ...) {
 #' @export
 cephalosporins_4th <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("cephalosporins_4th", only_sir_columns = only_sir_columns)
 }
 
@@ -400,10 +348,6 @@ cephalosporins_4th <- function(only_sir_columns = FALSE, ...) {
 #' @export
 cephalosporins_5th <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("cephalosporins_5th", only_sir_columns = only_sir_columns)
 }
 
@@ -411,10 +355,6 @@ cephalosporins_5th <- function(only_sir_columns = FALSE, ...) {
 #' @export
 fluoroquinolones <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("fluoroquinolones", only_sir_columns = only_sir_columns)
 }
 
@@ -422,32 +362,21 @@ fluoroquinolones <- function(only_sir_columns = FALSE, ...) {
 #' @export
 glycopeptides <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("glycopeptides", only_sir_columns = only_sir_columns)
 }
 
 #' @rdname antibiotic_class_selectors
 #' @export
-lincosamides <- function(only_sir_columns = FALSE, ...) {
+lincosamides <- function(only_sir_columns = FALSE, only_treatable = TRUE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
-  ab_select_exec("lincosamides", only_sir_columns = only_sir_columns)
+  meet_criteria(only_treatable, allow_class = "logical", has_length = 1)
+  ab_select_exec("lincosamides", only_sir_columns = only_sir_columns, only_treatable = only_treatable)
 }
 
 #' @rdname antibiotic_class_selectors
 #' @export
 lipoglycopeptides <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("lipoglycopeptides", only_sir_columns = only_sir_columns)
 }
 
@@ -455,21 +384,20 @@ lipoglycopeptides <- function(only_sir_columns = FALSE, ...) {
 #' @export
 macrolides <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("macrolides", only_sir_columns = only_sir_columns)
 }
 
+#' @rdname antibiotic_class_selectors
+#' @export
+nitrofurans <- function(only_sir_columns = FALSE, ...) {
+  meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
+  ab_select_exec("nitrofurans", only_sir_columns = only_sir_columns)
+}
+
 #' @rdname antibiotic_class_selectors
 #' @export
 oxazolidinones <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("oxazolidinones", only_sir_columns = only_sir_columns)
 }
 
@@ -477,10 +405,6 @@ oxazolidinones <- function(only_sir_columns = FALSE, ...) {
 #' @export
 penicillins <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("penicillins", only_sir_columns = only_sir_columns)
 }
 
@@ -489,43 +413,34 @@ penicillins <- function(only_sir_columns = FALSE, ...) {
 polymyxins <- function(only_sir_columns = FALSE, only_treatable = TRUE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
   meet_criteria(only_treatable, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("polymyxins", only_sir_columns = only_sir_columns, only_treatable = only_treatable)
 }
 
-#' @rdname antibiotic_class_selectors
-#' @export
-streptogramins <- function(only_sir_columns = FALSE, ...) {
-  meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
-  ab_select_exec("streptogramins", only_sir_columns = only_sir_columns)
-}
-
 #' @rdname antibiotic_class_selectors
 #' @export
 quinolones <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("quinolones", only_sir_columns = only_sir_columns)
 }
 
+#' @rdname antibiotic_class_selectors
+#' @export
+rifamycins <- function(only_sir_columns = FALSE, ...) {
+  meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
+  ab_select_exec("rifamycins", only_sir_columns = only_sir_columns)
+}
+
+#' @rdname antibiotic_class_selectors
+#' @export
+streptogramins <- function(only_sir_columns = FALSE, ...) {
+  meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
+  ab_select_exec("streptogramins", only_sir_columns = only_sir_columns)
+}
+
 #' @rdname antibiotic_class_selectors
 #' @export
 tetracyclines <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("tetracyclines", only_sir_columns = only_sir_columns)
 }
 
@@ -533,10 +448,6 @@ tetracyclines <- function(only_sir_columns = FALSE, ...) {
 #' @export
 trimethoprims <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("trimethoprims", only_sir_columns = only_sir_columns)
 }
 
@@ -544,10 +455,6 @@ trimethoprims <- function(only_sir_columns = FALSE, ...) {
 #' @export
 ureidopenicillins <- function(only_sir_columns = FALSE, ...) {
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   ab_select_exec("ureidopenicillins", only_sir_columns = only_sir_columns)
 }
 
@@ -649,10 +556,10 @@ not_intrinsic_resistant <- function(only_sir_columns = FALSE, col_mo = NULL, ver
     ),
     error = function(e) stop_("in not_intrinsic_resistant(): ", e$message, call = FALSE)
   )
-
+  
   agents <- ab_in_data[ab_in_data %in% names(vars_df_R[which(vars_df_R)])]
   if (length(agents) > 0 &&
-    message_not_thrown_before("not_intrinsic_resistant", sort(agents))) {
+      message_not_thrown_before("not_intrinsic_resistant", sort(agents))) {
     agents_formatted <- paste0("'", font_bold(agents, collapse = NULL), "'")
     agents_names <- ab_name(names(agents), tolower = TRUE, language = NULL)
     need_name <- generalise_antibiotic_name(agents) != generalise_antibiotic_name(agents_names)
@@ -663,7 +570,7 @@ not_intrinsic_resistant <- function(only_sir_columns = FALSE, col_mo = NULL, ver
       vector_and(agents_formatted, quotes = FALSE, sort = FALSE)
     )
   }
-
+  
   vars_df_R <- names(vars_df_R)[which(!vars_df_R)]
   # find columns that are abx, but also intrinsic R
   out <- unname(intersect(ab_in_data, vars_df_R))
@@ -687,9 +594,9 @@ ab_select_exec <- function(function_name,
 
   # untreatable drugs
   if (only_treatable == TRUE) {
-    untreatable <- AMR_env$AB_lookup[which(AMR_env$AB_lookup$name %like% "-high|EDTA|polysorbate|macromethod|screening|/nacubactam"), "ab", drop = TRUE]
+    untreatable <- AMR_env$AB_lookup[which(AMR_env$AB_lookup$name %like% "-high|EDTA|polysorbate|macromethod|screening|nacubactam"), "ab", drop = TRUE]
     if (any(untreatable %in% names(ab_in_data))) {
-      if (message_not_thrown_before(function_name, "ab_class", "untreatable", entire_session = TRUE)) {
+      if (message_not_thrown_before(function_name, "ab_class", "untreatable")) {
         warning_(
           "in `", function_name, "()`: some drugs were ignored since they cannot be used for treating patients: ",
           vector_and(
@@ -699,8 +606,7 @@ ab_select_exec <- function(function_name,
             ),
             quotes = FALSE,
             sort = TRUE
-          ), ". They can be included using `", function_name, "(only_treatable = FALSE)`. ",
-          "This warning will be shown once per session."
+          ), ". They can be included using `", function_name, "(only_treatable = FALSE)`."
         )
       }
       ab_in_data <- ab_in_data[!names(ab_in_data) %in% untreatable]
@@ -719,7 +625,7 @@ ab_select_exec <- function(function_name,
     } else if (isTRUE(function_name == "antimycobacterials")) {
       abx <- AMR_env$AB_lookup$ab[which(AMR_env$AB_lookup$group == "Antimycobacterials")]
     } else {
-      # their upper case equivalent are vectors with class 'ab', created in data-raw/_pre_commit_hook.R
+      # their upper case equivalent are vectors with class 'ab', created in data-raw/_pre_commit_checks.R
       # carbapenems() gets its codes from AMR:::AB_CARBAPENEMS
       abx <- get(paste0("AB_", toupper(function_name)), envir = asNamespace("AMR"))
       # manually added codes from add_custom_antimicrobials() must also be supported
@@ -784,10 +690,10 @@ c.ab_selector <- function(...) {
 
 all_any_ab_selector <- function(type, ..., na.rm = TRUE) {
   cols_ab <- c(...)
-  result <- cols_ab[toupper(cols_ab) %in% c("S", "I", "R")]
+  result <- cols_ab[toupper(cols_ab) %in% c("S", "SDD", "I", "R", "N")]
   if (length(result) == 0) {
     message_("Filtering ", type, " of columns ", vector_and(font_bold(cols_ab, collapse = NULL), quotes = "'"), ' to contain value "S", "I" or "R"')
-    result <- c("S", "I", "R")
+    result <- c("S", "SDD", "I", "R", "N")
   }
   cols_ab <- cols_ab[!cols_ab %in% result]
   df <- get_current_data(arg_name = NA, call = -3)
@@ -896,7 +802,7 @@ any.ab_selector_any_all <- function(..., na.rm = FALSE) {
     }
   }
   # this is `!=`, so turn around the values
-  sir <- c("S", "I", "R")
+  sir <- c("S", "SDD", "I", "R", "N")
   e2 <- sir[sir != e2]
   structure(all_any_ab_selector(type = type, e1, e2),
     class = c("ab_selector_any_all", "logical")

R/antibiogram.R

@@ -294,7 +294,7 @@ antibiogram <- function(x,
   } else if (mo_transform == "name") {
     x$`.mo` <- mo_name(x$`.mo`, language = language)
   } else {
-    x$`.mo` <- mo_property(x$`.mo`, language = language)
+    x$`.mo` <- mo_property(x$`.mo`, property = mo_transform, language = language)
   }
   x$`.mo`[is.na(x$`.mo`)] <- "(??)"
 
@@ -348,11 +348,11 @@ antibiogram <- function(x,
       } else {
         # determine whether this new column should contain S, I, R, or NA
         if (isTRUE(combine_SI)) {
-          S_values <- c("S", "I")
+          S_values <- c("S", "SDD", "I")
         } else {
           S_values <- "S"
         }
-        other_values <- setdiff(c("S", "I", "R"), S_values)
+        other_values <- setdiff(c("S", "SDD", "I", "R", "N"), S_values)
         x_transposed <- as.list(as.data.frame(t(x[, abx, drop = FALSE]), stringsAsFactors = FALSE))
         if (isTRUE(only_all_tested)) {
           x[new_colname] <- as.sir(vapply(FUN.VALUE = character(1), x_transposed, function(x) ifelse(anyNA(x), NA_character_, ifelse(any(x %in% S_values), "S", "R")), USE.NAMES = FALSE))

R/atc_online.R

@@ -64,7 +64,7 @@
 #' **N.B. This function requires an internet connection and only works if the following packages are installed: `curl`, `rvest`, `xml2`.**
 #' @export
 #' @rdname atc_online
-#' @source <https://www.whocc.no/atc_ddd_alterations__cumulative/ddd_alterations/abbrevations/>
+#' @source <https://atcddd.fhi.no/atc_ddd_alterations__cumulative/ddd_alterations/abbrevations/>
 #' @examples
 #' \donttest{
 #' if (requireNamespace("curl") && requireNamespace("rvest") && requireNamespace("xml2")) {
@@ -81,9 +81,9 @@
 atc_online_property <- function(atc_code,
                                 property,
                                 administration = "O",
-                                url = "https://www.whocc.no/atc_ddd_index/?code=%s&showdescription=no",
-                                url_vet = "https://www.whocc.no/atcvet/atcvet_index/?code=%s&showdescription=no") {
-  meet_criteria(atc_code, allow_class = "character")
+                                url = "https://atcddd.fhi.no/atc_ddd_index/?code=%s&showdescription=no",
+                                url_vet = "https://atcddd.fhi.no/atcvet/atcvet_index/?code=%s&showdescription=no") {
+  meet_criteria(atc_code, allow_class = "character", allow_NA = TRUE)
   meet_criteria(property, allow_class = "character", has_length = 1, is_in = c("ATC", "Name", "DDD", "U", "unit", "Adm.R", "Note", "groups"), ignore.case = TRUE)
   meet_criteria(administration, allow_class = "character", has_length = 1)
   meet_criteria(url, allow_class = "character", has_length = 1, looks_like = "https?://")
@@ -128,6 +128,10 @@ atc_online_property <- function(atc_code,
 
   for (i in seq_len(length(atc_code))) {
     progress$tick()
+    
+    if (is.na(atc_code[i])) {
+      next
+    }
 
     if (atc_code[i] %like% "^Q") {
       # veterinary drugs, ATC_vet codes start with a "Q"
@@ -176,7 +180,7 @@ atc_online_property <- function(atc_code,
       colnames(out) <- gsub("^atc.*", "atc", tolower(colnames(out)))
 
       if (length(out) == 0) {
-        warning_("in `atc_online_property()`: ATC not found: ", atc_code[i], ". Please check ", atc_url, ".")
+        message_("in `atc_online_property()`: no properties found for ATC ", atc_code[i], ". Please check ", font_url(atc_url, "this WHOCC webpage"), ".")
         returnvalue[i] <- NA
         next
       }
@@ -209,20 +213,20 @@ atc_online_property <- function(atc_code,
 #' @rdname atc_online
 #' @export
 atc_online_groups <- function(atc_code, ...) {
-  meet_criteria(atc_code, allow_class = "character")
+  meet_criteria(atc_code, allow_class = "character", allow_NA = TRUE)
   atc_online_property(atc_code = atc_code, property = "groups", ...)
 }
 
 #' @rdname atc_online
 #' @export
 atc_online_ddd <- function(atc_code, ...) {
-  meet_criteria(atc_code, allow_class = "character")
+  meet_criteria(atc_code, allow_class = "character", allow_NA = TRUE)
   atc_online_property(atc_code = atc_code, property = "ddd", ...)
 }
 
 #' @rdname atc_online
 #' @export
 atc_online_ddd_units <- function(atc_code, ...) {
-  meet_criteria(atc_code, allow_class = "character")
+  meet_criteria(atc_code, allow_class = "character", allow_NA = TRUE)
   atc_online_property(atc_code = atc_code, property = "unit", ...)
 }

R/av.R

@@ -49,7 +49,7 @@
 #'
 #' Note: the [as.av()] and [`av_*`][av_property()] functions may use very long regular expression to match brand names of antimicrobial drugs. This may fail on some systems.
 #' @section Source:
-#' World Health Organization (WHO) Collaborating Centre for Drug Statistics Methodology: \url{https://www.whocc.no/atc_ddd_index/}
+#' World Health Organization (WHO) Collaborating Centre for Drug Statistics Methodology: \url{https://atcddd.fhi.no/atc_ddd_index/}
 #'
 #' European Commission Public Health PHARMACEUTICALS - COMMUNITY REGISTER: \url{https://ec.europa.eu/health/documents/community-register/html/reg_hum_atc.htm}
 #' @aliases av

R/av_property.R

@@ -164,7 +164,7 @@ av_ddd <- function(x, administration = "oral", ...) {
     warning_(
       "in `av_ddd()`: DDDs of some combined products are available for different dose combinations and not (yet) part of the AMR package.",
       "Please refer to the WHOCC website:\n",
-      "www.whocc.no/ddd/list_of_ddds_combined_products/"
+      "atcddd.fhi.no/ddd/list_of_ddds_combined_products/"
     )
   }
   out
@@ -184,7 +184,7 @@ av_ddd_units <- function(x, administration = "oral", ...) {
     warning_(
       "in `av_ddd_units()`: DDDs of some combined products are available for different dose combinations and not (yet) part of the AMR package.",
       "Please refer to the WHOCC website:\n",
-      "www.whocc.no/ddd/list_of_ddds_combined_products/"
+      "atcddd.fhi.no/ddd/list_of_ddds_combined_products/"
     )
   }
   out
@@ -227,7 +227,7 @@ av_url <- function(x, open = FALSE, ...) {
 
   av <- as.av(x = x, ...)
   atcs <- av_atc(av, only_first = TRUE)
-  u <- paste0("https://www.whocc.no/atc_ddd_index/?code=", atcs, "&showdescription=no")
+  u <- paste0("https://atcddd.fhi.no/atc_ddd_index/?code=", atcs, "&showdescription=no")
   u[is.na(atcs)] <- NA_character_
   names(u) <- av_name(av)
 

R/bug_drug_combinations.R

@@ -42,7 +42,7 @@
 #' @details The function [format()] calculates the resistance per bug-drug combination and returns a table ready for reporting/publishing. Use `combine_SI = TRUE` (default) to test R vs. S+I and `combine_SI = FALSE` to test R+I vs. S. This table can also directly be used in R Markdown / Quarto without the need for e.g. [knitr::kable()].
 #' @export
 #' @rdname bug_drug_combinations
-#' @return The function [bug_drug_combinations()] returns a [data.frame] with columns "mo", "ab", "S", "I", "R" and "total".
+#' @return The function [bug_drug_combinations()] returns a [data.frame] with columns "mo", "ab", "S", "SDD", "I", "R", and "total".
 #' @examples
 #' # example_isolates is a data set available in the AMR package.
 #' # run ?example_isolates for more info.
@@ -105,8 +105,10 @@ bug_drug_combinations <- function(x,
       mo = character(0),
       ab = character(0),
       S = integer(0),
+      SDD = integer(0),
       I = integer(0),
       R = integer(0),
+      N = integer(0),
       total = integer(0),
       stringsAsFactors = FALSE
     )
@@ -121,17 +123,19 @@ bug_drug_combinations <- function(x,
       x_mo_filter <- x[which(x[, col_mo, drop = TRUE] == unique_mo[i]), names(which(vapply(FUN.VALUE = logical(1), x, is.sir))), drop = FALSE]
       # turn and merge everything
       pivot <- lapply(x_mo_filter, function(x) {
-        m <- as.matrix(table(x))
-        data.frame(S = m["S", ], I = m["I", ], R = m["R", ], stringsAsFactors = FALSE)
+        m <- as.matrix(table(as.sir(x)))
+        data.frame(S = m["S", ], SDD = m["SDD", ], I = m["I", ], R = m["R", ], N = m["N", ], stringsAsFactors = FALSE)
       })
       merged <- do.call(rbind_AMR, pivot)
       out_group <- data.frame(
         mo = rep(unique_mo[i], NROW(merged)),
         ab = rownames(merged),
         S = merged$S,
+        SDD = merged$SDD,
         I = merged$I,
         R = merged$R,
-        total = merged$S + merged$I + merged$R,
+        N = merged$N,
+        total = merged$S + merged$SDD + merged$I + merged$R + merged$N,
         stringsAsFactors = FALSE
       )
       if (data_has_groups) {
@@ -203,12 +207,16 @@ format.bug_drug_combinations <- function(x,
       mo = gsub("(.*)%%(.*)", "\\1", names(idx)),
       ab = gsub("(.*)%%(.*)", "\\2", names(idx)),
       S = vapply(FUN.VALUE = double(1), idx, function(i) sum(x$S[i], na.rm = TRUE)),
+      SDD = vapply(FUN.VALUE = double(1), idx, function(i) sum(x$SDD[i], na.rm = TRUE)),
       I = vapply(FUN.VALUE = double(1), idx, function(i) sum(x$I[i], na.rm = TRUE)),
       R = vapply(FUN.VALUE = double(1), idx, function(i) sum(x$R[i], na.rm = TRUE)),
+      N = vapply(FUN.VALUE = double(1), idx, function(i) sum(x$R[i], na.rm = TRUE)),
       total = vapply(FUN.VALUE = double(1), idx, function(i) {
         sum(x$S[i], na.rm = TRUE) +
+          sum(x$SDD[i], na.rm = TRUE) +
           sum(x$I[i], na.rm = TRUE) +
-          sum(x$R[i], na.rm = TRUE)
+          sum(x$R[i], na.rm = TRUE) +
+          sum(x$N[i], na.rm = TRUE)
       }),
       stringsAsFactors = FALSE
     )
@@ -223,7 +231,7 @@ format.bug_drug_combinations <- function(x,
   if (combine_SI == TRUE) {
     x$isolates <- x$R
   } else {
-    x$isolates <- x$R + x$I
+    x$isolates <- x$R + x$I + x$SDD
   }
 
   give_ab_name <- function(ab, format, language) {

R/count.R

@@ -135,62 +135,7 @@ count_resistant <- function(..., only_all_tested = FALSE) {
 count_susceptible <- function(..., only_all_tested = FALSE) {
   tryCatch(
     sir_calc(...,
-      ab_result = c("S", "I"),
-      only_all_tested = only_all_tested,
-      only_count = TRUE
-    ),
-    error = function(e) stop_(gsub("in sir_calc(): ", "", e$message, fixed = TRUE), call = -5)
-  )
-}
-
-#' @rdname count
-#' @export
-count_R <- function(..., only_all_tested = FALSE) {
-  tryCatch(
-    sir_calc(...,
-      ab_result = "R",
-      only_all_tested = only_all_tested,
-      only_count = TRUE
-    ),
-    error = function(e) stop_(gsub("in sir_calc(): ", "", e$message, fixed = TRUE), call = -5)
-  )
-}
-
-#' @rdname count
-#' @export
-count_IR <- function(..., only_all_tested = FALSE) {
-  if (message_not_thrown_before("count_IR", entire_session = TRUE)) {
-    message_("Using `count_IR()` is discouraged; use `count_resistant()` instead to not consider \"I\" being resistant. This note will be shown once for this session.", as_note = FALSE)
-  }
-  tryCatch(
-    sir_calc(...,
-      ab_result = c("I", "R"),
-      only_all_tested = only_all_tested,
-      only_count = TRUE
-    ),
-    error = function(e) stop_(gsub("in sir_calc(): ", "", e$message, fixed = TRUE), call = -5)
-  )
-}
-
-#' @rdname count
-#' @export
-count_I <- function(..., only_all_tested = FALSE) {
-  tryCatch(
-    sir_calc(...,
-      ab_result = "I",
-      only_all_tested = only_all_tested,
-      only_count = TRUE
-    ),
-    error = function(e) stop_(gsub("in sir_calc(): ", "", e$message, fixed = TRUE), call = -5)
-  )
-}
-
-#' @rdname count
-#' @export
-count_SI <- function(..., only_all_tested = FALSE) {
-  tryCatch(
-    sir_calc(...,
-      ab_result = c("S", "I"),
+      ab_result = c("S", "SDD", "I"),
       only_all_tested = only_all_tested,
       only_count = TRUE
     ),
@@ -202,7 +147,7 @@ count_SI <- function(..., only_all_tested = FALSE) {
 #' @export
 count_S <- function(..., only_all_tested = FALSE) {
   if (message_not_thrown_before("count_S", entire_session = TRUE)) {
-    message_("Using `count_S()` is discouraged; use `count_susceptible()` instead to also consider \"I\" being susceptible. This note will be shown once for this session.", as_note = FALSE)
+    message_("Using `count_S()` is discouraged; use `count_susceptible()` instead to also consider \"I\" and \"SDD\" being susceptible. This note will be shown once for this session.", as_note = FALSE)
   }
   tryCatch(
     sir_calc(...,
@@ -214,12 +159,73 @@ count_S <- function(..., only_all_tested = FALSE) {
   )
 }
 
+#' @rdname count
+#' @export
+count_SI <- function(..., only_all_tested = FALSE) {
+  if (message_not_thrown_before("count_SI", entire_session = TRUE)) {
+    message_("Note that `count_SI()` will also count dose-dependent susceptibility, 'SDD'. This note will be shown once for this session.", as_note = FALSE)
+  }
+  tryCatch(
+    sir_calc(...,
+             ab_result = c("S", "SDD", "I"),
+             only_all_tested = only_all_tested,
+             only_count = TRUE
+    ),
+    error = function(e) stop_(gsub("in sir_calc(): ", "", e$message, fixed = TRUE), call = -5)
+  )
+}
+
+#' @rdname count
+#' @export
+count_I <- function(..., only_all_tested = FALSE) {
+  if (message_not_thrown_before("count_I", entire_session = TRUE)) {
+    message_("Note that `count_I()` will also count dose-dependent susceptibility, 'SDD'. This note will be shown once for this session.", as_note = FALSE)
+  }
+  tryCatch(
+    sir_calc(...,
+             ab_result = c("I", "SDD"),
+             only_all_tested = only_all_tested,
+             only_count = TRUE
+    ),
+    error = function(e) stop_(gsub("in sir_calc(): ", "", e$message, fixed = TRUE), call = -5)
+  )
+}
+
+#' @rdname count
+#' @export
+count_IR <- function(..., only_all_tested = FALSE) {
+  if (message_not_thrown_before("count_IR", entire_session = TRUE)) {
+    message_("Using `count_IR()` is discouraged; use `count_resistant()` instead to not consider \"I\" and \"SDD\" being resistant. This note will be shown once for this session.", as_note = FALSE)
+  }
+  tryCatch(
+    sir_calc(...,
+             ab_result = c("I", "SDD", "R"),
+             only_all_tested = only_all_tested,
+             only_count = TRUE
+    ),
+    error = function(e) stop_(gsub("in sir_calc(): ", "", e$message, fixed = TRUE), call = -5)
+  )
+}
+
+#' @rdname count
+#' @export
+count_R <- function(..., only_all_tested = FALSE) {
+  tryCatch(
+    sir_calc(...,
+             ab_result = "R",
+             only_all_tested = only_all_tested,
+             only_count = TRUE
+    ),
+    error = function(e) stop_(gsub("in sir_calc(): ", "", e$message, fixed = TRUE), call = -5)
+  )
+}
+
 #' @rdname count
 #' @export
 count_all <- function(..., only_all_tested = FALSE) {
   tryCatch(
     sir_calc(...,
-      ab_result = c("S", "I", "R"),
+      ab_result = c("S", "SDD", "I", "R", "N"),
       only_all_tested = only_all_tested,
       only_count = TRUE
     ),

R/custom_antimicrobials.R

@@ -96,7 +96,7 @@
 #'
 #'
 #' # Add Co-fluampicil, which is one of the many J01CR50 codes, see
-#' # https://www.whocc.no/ddd/list_of_ddds_combined_products/
+#' # https://atcddd.fhi.no/ddd/list_of_ddds_combined_products/
 #' add_custom_antimicrobials(
 #'   data.frame(
 #'     ab = "COFLU",

R/custom_eucast_rules.R

@@ -30,7 +30,7 @@
 #' Define Custom EUCAST Rules
 #'
 #' Define custom EUCAST rules for your organisation or specific analysis and use the output of this function in [eucast_rules()].
-#' @param ... rules in [formula][base::tilde] notation, see *Examples*
+#' @param ... rules in [formula][base::tilde] notation, see below for instructions, and in *Examples*
 #' @details
 #' Some organisations have their own adoption of EUCAST rules. This function can be used to define custom EUCAST rules to be used in the [eucast_rules()] function.
 #' @section How it works:
@@ -89,11 +89,24 @@
 #' #> 2 Klebsiella pneumoniae   R    R     S
 #' ```
 #'
-#' ### Usage of antibiotic group names
+#' ### Usage of multiple antibiotics and antibiotic group names
+#' 
+#' You can define antibiotic groups instead of single antibiotics for the rule consequence, which is the part *after* the tilde (~). In the examples above, the antibiotic group `aminopenicillins` includes both ampicillin and amoxicillin.
+#' 
+#' Rules can also be applied to multiple antibiotics and antibiotic groups simultaneously. Use the `c()` function to combine multiple antibiotics. For instance, the following example sets all aminopenicillins and ureidopenicillins to "R" if column TZP (piperacillin/tazobactam) is "R":
+#' 
+#' ```r
+#' x <- custom_eucast_rules(TZP == "R" ~ c(aminopenicillins, ureidopenicillins) == "R")
+#' x
+#' #> A set of custom EUCAST rules:
+#' #> 
+#' #>   1. If TZP is "R" then set to "R":
+#' #>      amoxicillin (AMX), ampicillin (AMP), azlocillin (AZL), mezlocillin (MEZ), piperacillin (PIP), piperacillin/tazobactam (TZP)
+#' ```
 #'
-#' It is possible to define antibiotic groups instead of single antibiotics for the rule consequence, the part *after* the tilde. In above examples, the antibiotic group `aminopenicillins` is used to include ampicillin and amoxicillin. The following groups are allowed (case-insensitive). Within parentheses are the drugs that will be matched when running the rule.
+#' These `r length(DEFINED_AB_GROUPS)` antibiotic groups are allowed in the rules (case-insensitive) and can be used in any combination:
 #'
-#' `r paste0("  * ", sapply(DEFINED_AB_GROUPS, function(x) paste0("\"", tolower(gsub("^AB_", "", x)), "\"\\cr(", vector_and(ab_name(eval(parse(text = x), envir = asNamespace("AMR")), language = NULL, tolower = TRUE), quotes = FALSE), ")"), USE.NAMES = FALSE), "\n", collapse = "")`
+#' `r paste0("  * ", sapply(DEFINED_AB_GROUPS, function(x) paste0(tolower(gsub("^AB_", "", x)), "\\cr(", vector_and(ab_name(eval(parse(text = x), envir = asNamespace("AMR")), language = NULL, tolower = TRUE), quotes = FALSE), ")"), USE.NAMES = FALSE), "\n", collapse = "")`
 #' @returns A [list] containing the custom rules
 #' @export
 #' @examples
@@ -156,24 +169,34 @@ custom_eucast_rules <- function(...) {
       "the result of rule ", i, " (the part after the `~`) must contain `==`, such as in `... ~ ampicillin == \"R\"`, see `?custom_eucast_rules`"
     )
     result_group <- as.character(result)[[2]]
-    if (paste0("AB_", toupper(result_group), "S") %in% DEFINED_AB_GROUPS) {
-      # support for e.g. 'aminopenicillin' if user meant 'aminopenicillins'
-      result_group <- paste0(result_group, "s")
+    result_group<- as.character(str2lang(result_group))
+    result_group <- result_group[result_group != "c"]
+    result_group_agents <- character(0)
+    for (j in seq_len(length(result_group))) {
+      if (paste0("AB_", toupper(result_group[j]), "S") %in% DEFINED_AB_GROUPS) {
+        # support for e.g. 'aminopenicillin' if user meant 'aminopenicillins'
+        result_group[j] <- paste0(result_group[j], "s")
+      }
+      if (paste0("AB_", toupper(result_group[j])) %in% DEFINED_AB_GROUPS) {
+        result_group_agents <- c(result_group_agents,
+                                 eval(parse(text = paste0("AB_", toupper(result_group[j]))), envir = asNamespace("AMR")))
+      } else {
+        out_group <- tryCatch(
+          suppressWarnings(as.ab(result_group[j],
+                                 fast_mode = TRUE,
+                                 flag_multiple_results = FALSE
+          )),
+          error = function(e) NA_character_
+        )
+        if (!all(is.na(out_group))) {
+          result_group_agents <- c(result_group_agents, out_group)
+        }
+      }
     }
-    if (paste0("AB_", toupper(result_group)) %in% DEFINED_AB_GROUPS) {
-      result_group <- eval(parse(text = paste0("AB_", toupper(result_group))), envir = asNamespace("AMR"))
-    } else {
-      result_group <- tryCatch(
-        suppressWarnings(as.ab(result_group,
-          fast_mode = TRUE,
-          flag_multiple_results = FALSE
-        )),
-        error = function(e) NA_character_
-      )
-    }
-
+    result_group_agents <- result_group_agents[!is.na(result_group_agents)]
+    
     stop_if(
-      any(is.na(result_group)),
+      length(result_group_agents) == 0,
       "this result of rule ", i, " could not be translated to a single antimicrobial drug/group: \"",
       as.character(result)[[2]], "\".\n\nThe input can be a name or code of an antimicrobial drug, or be one of: ",
       vector_or(tolower(gsub("AB_", "", DEFINED_AB_GROUPS)), quotes = FALSE), "."
@@ -181,12 +204,12 @@ custom_eucast_rules <- function(...) {
     result_value <- as.character(result)[[3]]
     result_value[result_value == "NA"] <- NA
     stop_ifnot(
-      result_value %in% c("S", "I", "R", NA),
-      "the resulting value of rule ", i, " must be either \"S\", \"I\", \"R\" or NA"
+      result_value %in% c("S", "SDD", "I", "R", "N", NA),
+      "the resulting value of rule ", i, " must be either \"S\", \"SDD\", \"I\", \"R\", \"N\" or NA"
     )
     result_value <- as.sir(result_value)
 
-    out[[i]]$result_group <- result_group
+    out[[i]]$result_group <- result_group_agents
     out[[i]]$result_value <- result_value
   }
 

R/data.R

@@ -67,7 +67,7 @@
 #' Like all data sets in this package, these data sets are publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit [our website for the download links](https://msberends.github.io/AMR/articles/datasets.html). The actual files are of course available on [our GitHub repository](https://github.com/msberends/AMR/tree/main/data-raw).
 #' @source
 #'
-#' * World Health Organization (WHO) Collaborating Centre for Drug Statistics Methodology (WHOCC): <https://www.whocc.no/atc_ddd_index/>
+#' * World Health Organization (WHO) Collaborating Centre for Drug Statistics Methodology (WHOCC): <https://atcddd.fhi.no/atc_ddd_index/>
 #'
 #' * `r TAXONOMY_VERSION$LOINC$citation` Accessed from <`r TAXONOMY_VERSION$LOINC$url`> on `r documentation_date(TAXONOMY_VERSION$LOINC$accessed_date)`.
 #'
@@ -100,7 +100,7 @@
 #' - `gbif_parent`\cr GBIF identifier of the parent taxon
 #' - `gbif_renamed_to`\cr GBIF identifier of the currently valid taxon
 #' - `source`\cr Either `r vector_or(microorganisms$source)` (see *Source*)
-#' - `prevalence`\cr Prevalence of the microorganism according to Bartlett *et al.* (2022, \doi{10.1099/mic.0.001269}), see [mo_matching_score()] for the full explanation
+#' - `prevalence`\cr Prevalence of the microorganism based on Bartlett *et al.* (2022, \doi{10.1099/mic.0.001269}), see [mo_matching_score()] for the full explanation
 #' - `snomed`\cr Systematized Nomenclature of Medicine (SNOMED) code of the microorganism, version of `r documentation_date(TAXONOMY_VERSION$SNOMED$accessed_date)` (see *Source*). Use [mo_snomed()] to retrieve it quickly, see [mo_property()].
 #' @details
 #' Please note that entries are only based on the List of Prokaryotic names with Standing in Nomenclature (LPSN) and the Global Biodiversity Information Facility (GBIF) (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.
@@ -262,10 +262,17 @@
 
 #' Data Set with Clinical Breakpoints for SIR Interpretation
 #'
-#' Data set containing clinical breakpoints to interpret MIC and disk diffusion to SIR values, according to international guidelines. Currently implemented guidelines are EUCAST (`r min(as.integer(gsub("[^0-9]", "", subset(clinical_breakpoints, guideline %like% "EUCAST")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(clinical_breakpoints, guideline %like% "EUCAST")$guideline)))`) and CLSI (`r min(as.integer(gsub("[^0-9]", "", subset(clinical_breakpoints, guideline %like% "CLSI")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(clinical_breakpoints, guideline %like% "CLSI")$guideline)))`). Use [as.sir()] to transform MICs or disks measurements to SIR values.
+#' @description Data set containing clinical breakpoints to interpret MIC and disk diffusion to SIR values, according to international guidelines. This dataset contain breakpoints for humans, `r length(unique(clinical_breakpoints$host[!clinical_breakpoints$host %in% clinical_breakpoints$type]))` different animal groups, and ECOFFs.
+#' 
+#' Currently available breakpoint guidelines for **clinical microbiology** are EUCAST `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST" & type == "human")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST" & type == "human")$guideline)))` and CLSI `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type == "human")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type == "human")$guideline)))`.
+#' 
+#' Currently available breakpoint guidelines for **veterinary microbiology** are EUCAST `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST" & type == "animal")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST" & type == "animal")$guideline)))` and CLSI `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type == "animal")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type == "animal")$guideline)))`.
+#' 
+#' Use [as.sir()] to transform MICs or disks measurements to SIR values.
 #' @format A [tibble][tibble::tibble] with `r format(nrow(clinical_breakpoints), big.mark = " ")` observations and `r ncol(clinical_breakpoints)` variables:
 #' - `guideline`\cr Name of the guideline
 #' - `type`\cr Breakpoint type, either `r vector_or(clinical_breakpoints$type)`
+#' - `host`\cr Host of infectious agent. This is mostly useful for veterinary breakpoints and is either `r vector_or(clinical_breakpoints$host)`
 #' - `method`\cr Testing method, either `r vector_or(clinical_breakpoints$method)`
 #' - `site`\cr Body site for which the breakpoint must be applied, e.g. "Oral" or "Respiratory"
 #' - `mo`\cr Microbial ID, see [as.mo()]
@@ -291,7 +298,7 @@
 #' ### Download
 #' Like all data sets in this package, this data set is publicly available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. Please visit [our website for the download links](https://msberends.github.io/AMR/articles/datasets.html). The actual files are of course available on [our GitHub repository](https://github.com/msberends/AMR/tree/main/data-raw). They allow for machine reading EUCAST and CLSI guidelines, which is almost impossible with the MS Excel and PDF files distributed by EUCAST and CLSI, though initiatives have started to overcome these burdens.
 #' 
-#' **NOTE:** this `AMR` package (and the WHONET software as well) contains internal methods to apply the guidelines, which is rather complex. For example, some breakpoints must be applied on certain species groups (which are in case of this package available through the [microorganisms.groups] data set). It is important that this is considered when using the breakpoints for own use.
+#' **NOTE:** this `AMR` package (and the WHONET software as well) contains rather complex internal methods to apply the guidelines. For example, some breakpoints must be applied on certain species groups (which are in case of this package available through the [microorganisms.groups] data set). It is important that this is considered when using the breakpoints for own use.
 #' @seealso [intrinsic_resistant]
 #' @examples
 #' clinical_breakpoints

R/disk.R

@@ -165,11 +165,6 @@ pillar_shaft.disk <- function(x, ...) {
   create_pillar_column(out, align = "right", width = 2)
 }
 
-# will be exported using s3_register() in R/zzz.R
-type_sum.disk <- function(x, ...) {
-  "disk"
-}
-
 #' @method print disk
 #' @export
 #' @noRd

R/eucast_rules.R

@@ -103,7 +103,7 @@ format_eucast_version_nr <- function(version, markdown = TRUE) {
 #' @section Antibiotics:
 #' To define antibiotics column names, leave as it is to determine it automatically with [guess_ab_col()] or input a text (case-insensitive), or use `NULL` to skip a column (e.g. `TIC = NULL` to skip ticarcillin). Manually defined but non-existing columns will be skipped with a warning.
 #'
-#' The following antibiotics are eligible 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:
+#' The following antibiotics are eligible for the functions [eucast_rules()] and [mdro()]. These are shown below in the format 'name (`antimicrobial ID`, [ATC code](https://atcddd.fhi.no/atc/structure_and_principles/))', sorted alphabetically:
 #'
 #' `r create_eucast_ab_documentation()`
 #' @aliases EUCAST
@@ -184,7 +184,6 @@ eucast_rules <- function(x,
   meet_criteria(ampc_cephalosporin_resistance, allow_class = c("logical", "character", "sir"), has_length = 1, allow_NA = TRUE, allow_NULL = TRUE)
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
   meet_criteria(custom_rules, allow_class = "custom_eucast_rules", allow_NULL = TRUE)
-  if ("only_rsi_columns" %in% names(list(...))) only_sir_columns <- list(...)$only_rsi_columns
 
   add_MO_lookup_to_AMR_env()
 
@@ -591,7 +590,7 @@ eucast_rules <- function(x,
     # this allows: eucast_rules(x, eucast_rules_df = AMR:::EUCAST_RULES_DF %>% filter(is.na(have_these_values)))
     eucast_rules_df <- list(...)$eucast_rules_df
   } else {
-    # otherwise internal data file, created in data-raw/_pre_commit_hook.R
+    # otherwise internal data file, created in data-raw/_pre_commit_checks.R
     eucast_rules_df <- EUCAST_RULES_DF
   }
 
@@ -890,6 +889,7 @@ eucast_rules <- function(x,
           ),
           type = "ansi"
         ))
+        cat("\n")
         warned <- FALSE
       }
       run_changes <- edit_sir(

R/export_biosample.R

@@ -0,0 +1,57 @@
+# ==================================================================== #
+# TITLE:                                                               #
+# AMR: An R Package for Working with Antimicrobial Resistance Data     #
+#                                                                      #
+# SOURCE CODE:                                                         #
+# https://github.com/msberends/AMR                                     #
+#                                                                      #
+# PLEASE CITE THIS SOFTWARE AS:                                        #
+# Berends MS, Luz CF, Friedrich AW, Sinha BNM, Albers CJ, Glasner C    #
+# (2022). AMR: An R Package for Working with Antimicrobial Resistance  #
+# Data. Journal of Statistical Software, 104(3), 1-31.                 #
+# https://doi.org/10.18637/jss.v104.i03                                #
+#                                                                      #
+# Developed at the University of Groningen and the University Medical  #
+# Center Groningen in The Netherlands, in collaboration with many      #
+# colleagues from around the world, see our website.                   #
+#                                                                      #
+# 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/   #
+# ==================================================================== #
+
+#' Export Data Set as NCBI BioSample Antibiogram
+#'
+#' 
+#' @param x a data set 
+#' @param filename a character string specifying the file name
+#' @param type a character string specifying the type of data set, either "pathogen MIC" or "beta-lactamase MIC", see <https://www.ncbi.nlm.nih.gov/biosample/docs/>
+#' @param save_as_xlsx
+export_biosample <- function(x,
+                             filename = paste0("biosample_", format(Sys.time(), "%Y-%m-%d-%H%M%S"), ".xlsx"),
+                             type = "pathogen MIC",
+                             columns = where(is.mic),
+                             save_as_xlsx = TRUE) {
+  meet_criteria(x, allow_class = "data.frame") # also checks dimensions to be >0
+  meet_criteria(filename, allow_class = "character", has_length = 1)
+  meet_criteria(type, allow_class = "character", has_length = 1, is_in = c("pathogen MIC", "beta-lactamase MIC"))
+  meet_criteria(save_as_xlsx, allow_class = "logical", has_length = 1)
+  
+  out <- x %pm>%
+    pm_select(columns)
+  stop_if(NROW(out) == 0, "No columns found.")
+  
+  if (isTRUE(save_as_xlsx)) {
+    export <- import_fn("write.xlsx", pkg = "openxlsx", error_on_fail = TRUE)
+    export(out, file = filename, overwrite = TRUE, asTable = FALSE)
+  } else {
+    out
+  }
+}

R/first_isolate.R

@@ -227,10 +227,6 @@ 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)
-  if ("include_untested_rsi" %in% names(list(...))) {
-    deprecation_warning("include_untested_rsi", "include_untested_sir", is_function = FALSE)
-    include_untested_sir <- list(...)$include_untested_rsi
-  }
   meet_criteria(include_untested_sir, allow_class = "logical", has_length = 1)
 
   # remove data.table, grouping from tibbles, etc.
@@ -240,7 +236,7 @@ first_isolate <- function(x = NULL,
     FUN.VALUE = logical(1),
     X = x,
     # check only first 10,000 rows
-    FUN = function(x) any(as.character(x[1:10000]) %in% c("S", "I", "R"), na.rm = TRUE),
+    FUN = function(x) any(as.character(x[1:10000]) %in% c("S", "SDD", "I", "R", "N"), na.rm = TRUE),
     USE.NAMES = FALSE
   ))
   if (method == "phenotype-based" && !any_col_contains_sir) {

R/ggplot_pca.R

@@ -85,16 +85,18 @@
 #'   summary(pca_result)
 #'
 #'   # old base R plotting method:
-#'   biplot(pca_result)
+#'   biplot(pca_result, main = "Base R biplot")
 #'
 #'   # new ggplot2 plotting method using this package:
 #'   if (require("ggplot2")) {
-#'     ggplot_pca(pca_result)
-#'
+#'     ggplot_pca(pca_result) +
+#'       labs(title = "ggplot2 biplot")
+#'   }
+#'   if (require("ggplot2")) {
 #'     # still extendible with any ggplot2 function
 #'     ggplot_pca(pca_result) +
 #'       scale_colour_viridis_d() +
-#'       labs(title = "Title here")
+#'       labs(title = "ggplot2 biplot")
 #'   }
 #' }
 #' }

R/guess_ab_col.R

@@ -335,7 +335,7 @@ get_ab_from_namespace <- function(x, cols_ab) {
   x_new <- character()
   for (val in x) {
     if (paste0("AB_", val) %in% ls(envir = asNamespace("AMR"))) {
-      # antibiotic group names, as defined in data-raw/_pre_commit_hook.R, such as `AB_CARBAPENEMS`
+      # antibiotic group names, as defined in data-raw/_pre_commit_checks.R, such as `AB_CARBAPENEMS`
       val <- eval(parse(text = paste0("AB_", val)), envir = asNamespace("AMR"))
     } else if (val %in% AMR_env$AB_lookup$ab) {
       # separate drugs, such as `AMX`

R/italicise_taxonomy.R

@@ -31,11 +31,11 @@
 #'
 #' According to the binomial nomenclature, the lowest four taxonomic levels (family, genus, species, subspecies) should be printed in italics. This function finds taxonomic names within strings and makes them italic.
 #' @param string a [character] (vector)
-#' @param type type of conversion of the taxonomic names, either "markdown" or "ansi", see *Details*
+#' @param type type of conversion of the taxonomic names, either "markdown", "html" or "ansi", see *Details*
 #' @details
 #' This function finds the taxonomic names and makes them italic based on the [microorganisms] data set.
 #'
-#' The taxonomic names can be italicised using markdown (the default) by adding `*` before and after the taxonomic names, or using ANSI colours by adding `\033[3m` before and `\033[23m` after the taxonomic names. If multiple ANSI colours are not available, no conversion will occur.
+#' The taxonomic names can be italicised using markdown (the default) by adding `*` before and after the taxonomic names, or `<i>` and `</i>` when using html. When using 'ansi', ANSI colours will be added using `\033[3m` before and `\033[23m` after the taxonomic names. If multiple ANSI colours are not available, no conversion will occur.
 #'
 #' This function also supports abbreviation of the genus if it is followed by a species, such as "E. coli" and "K. pneumoniae ozaenae".
 #' @export
@@ -44,18 +44,21 @@
 #' italicise_taxonomy("An overview of S. aureus isolates")
 #'
 #' cat(italicise_taxonomy("An overview of S. aureus isolates", type = "ansi"))
-italicise_taxonomy <- function(string, type = c("markdown", "ansi")) {
+italicise_taxonomy <- function(string, type = c("markdown", "ansi", "html")) {
   if (missing(type)) {
     type <- "markdown"
   }
   meet_criteria(string, allow_class = "character")
-  meet_criteria(type, allow_class = "character", has_length = 1, is_in = c("markdown", "ansi"))
+  meet_criteria(type, allow_class = "character", has_length = 1, is_in = c("markdown", "ansi", "html"))
 
   add_MO_lookup_to_AMR_env()
 
   if (type == "markdown") {
     before <- "*"
     after <- "*"
+  } else if (type == "html") {
+    before <- "<i>"
+    after <- "</i>"
   } else if (type == "ansi") {
     if (!has_colour() && !identical(Sys.getenv("IN_PKGDOWN"), "true")) {
       return(string)
@@ -134,7 +137,7 @@ italicise_taxonomy <- function(string, type = c("markdown", "ansi")) {
 
 #' @rdname italicise_taxonomy
 #' @export
-italicize_taxonomy <- function(string, type = c("markdown", "ansi")) {
+italicize_taxonomy <- function(string, type = c("markdown", "ansi", "html")) {
   if (missing(type)) {
     type <- "markdown"
   }

R/key_antimicrobials.R

@@ -149,10 +149,6 @@ key_antimicrobials <- function(x = NULL,
   meet_criteria(gram_positive, allow_class = "character", allow_NULL = TRUE)
   meet_criteria(antifungal, allow_class = "character", allow_NULL = TRUE)
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
 
   # force regular data.frame, not a tibble or data.table
   x <- as.data.frame(x, stringsAsFactors = FALSE)
@@ -286,6 +282,8 @@ generate_antimcrobials_string <- function(df) {
           as.list(df),
           function(x) {
             x <- toupper(as.character(x))
+            x[x == "SDD"] <- "I"
+            # ignore "N" here, no use for determining first isolates
             x[!x %in% c("S", "I", "R")] <- "."
             paste(x)
           }
@@ -316,7 +314,7 @@ antimicrobials_equal <- function(y,
     val <- strsplit(val, "", fixed = TRUE)[[1L]]
     val.int <- rep(NA_real_, length(val))
     val.int[val == "S"] <- 1
-    val.int[val == "I"] <- 2
+    val.int[val %in% c("I", "SDD")] <- 2
     val.int[val == "R"] <- 3
     val.int
   }

R/mdro.R

@@ -192,10 +192,6 @@ mdro <- function(x = NULL,
   meet_criteria(pct_required_classes, allow_class = "numeric", has_length = 1)
   meet_criteria(combine_SI, allow_class = "logical", has_length = 1)
   meet_criteria(verbose, allow_class = "logical", has_length = 1)
-  if ("only_rsi_columns" %in% names(list(...))) {
-    deprecation_warning("only_rsi_columns", "only_sir_columns", is_function = FALSE)
-    only_sir_columns <- list(...)$only_rsi_columns
-  }
   meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
 
   if (!any(is_sir_eligible(x))) {
@@ -736,7 +732,7 @@ mdro <- function(x = NULL,
           sum(vapply(
             FUN.VALUE = logical(1),
             group_tbl,
-            function(group) any(unlist(x[row, group[!is.na(group)], drop = TRUE]) %in% c("S", "I", "R"))
+            function(group) any(unlist(x[row, group[!is.na(group)], drop = TRUE]) %in% c("S", "SDD", "I", "R"))
           ))
         }
       )

R/mean_amr_distance.R

@@ -175,8 +175,8 @@ mean_amr_distance.data.frame <- function(x, ..., combine_SI = TRUE) {
 #' @param row an index, such as a row number
 #' @export
 amr_distance_from_row <- function(amr_distance, row) {
-  meet_criteria(amr_distance, allow_class = c("double", "numeric"), is_finite = TRUE)
-  meet_criteria(row, allow_class = c("logical", "double", "numeric"))
+  meet_criteria(amr_distance, allow_class = "numeric", is_finite = TRUE)
+  meet_criteria(row, allow_class = c("logical", "numeric", "integer"))
   if (is.logical(row)) {
     row <- which(row)
   }

R/mic.R

@@ -27,48 +27,25 @@
 # how to conduct AMR data analysis: https://msberends.github.io/AMR/   #
 # ==================================================================== #
 
-# these are allowed MIC values and will become [factor] levels
-operators <- c("<", "<=", "", ">=", ">")
-valid_mic_levels <- c(
-  c(t(vapply(
-    FUN.VALUE = character(6), operators,
-    function(x) paste0(x, "0.000", c(1:4, 6, 8))
-  ))),
-  c(t(vapply(
-    FUN.VALUE = character(90), operators,
-    function(x) paste0(x, "0.00", c(1:9, 11:19, 21:29, 31:39, 41:49, 51:59, 61:69, 71:79, 81:89, 91:99))
-  ))),
-  unique(c(t(vapply(
-    FUN.VALUE = character(106), operators,
-    function(x) {
-      paste0(x, sort(as.double(paste0(
-        "0.0",
-        sort(c(1:99, 125, 128, 156, 165, 256, 512, 625))
-      ))))
-    }
-  )))),
-  unique(c(t(vapply(
-    FUN.VALUE = character(103), operators,
-    function(x) {
-      paste0(x, sort(as.double(paste0(
-        "0.",
-        c(1:99, 125, 128, 256, 512)
-      ))))
-    }
-  )))),
-  c(t(vapply(
-    FUN.VALUE = character(10), operators,
-    function(x) paste0(x, sort(c(1:9, 1.5)))
-  ))),
-  c(t(vapply(
-    FUN.VALUE = character(45), operators,
-    function(x) paste0(x, c(10:98)[9:98 %% 2 == TRUE])
-  ))),
-  c(t(vapply(
-    FUN.VALUE = character(17), operators,
-    function(x) paste0(x, sort(c(2^c(7:11), 192, 80 * c(2:12))))
-  )))
+# these are allowed MIC values and will become factor levels
+VALID_MIC_LEVELS <- c(
+  as.double(paste0("0.000", c(1:9))),
+  as.double(paste0("0.00", c(1:99, 1953125, 390625, 78125))),
+  as.double(paste0("0.0", c(1:99, 125, 128, 156, 165, 256, 512, 625, 3125, 15625))),
+  as.double(paste0("0.", c(1:99, 125, 128, 256, 512))),
+  1:9, 1.5,
+  c(10:98)[9:98 %% 2 == TRUE],
+  2^c(7:12), 192 * c(1:5), 80 * c(2:12)
 )
+VALID_MIC_LEVELS <- trimws(gsub("[.]?0+$", "", format(unique(sort(VALID_MIC_LEVELS)), scientific = FALSE), perl = TRUE))
+operators <- c("<", "<=", "", ">=", ">")
+VALID_MIC_LEVELS <- c(t(vapply(FUN.VALUE = character(length(VALID_MIC_LEVELS)),
+                               c("<", "<=", "", ">=", ">"),
+                               paste0,
+                               VALID_MIC_LEVELS)))
+COMMON_MIC_VALUES <- c(0.001, 0.002, 0.004, 0.008, 0.016, 0.032, 0.064,
+                       0.125, 0.25, 0.5, 1, 2, 4, 8, 16, 32,
+                       64, 128, 256, 512, 1024)
 
 #' Transform Input to Minimum Inhibitory Concentrations (MIC)
 #'
@@ -76,6 +53,7 @@ valid_mic_levels <- c(
 #' @rdname as.mic
 #' @param x a [character] or [numeric] vector
 #' @param na.rm a [logical] indicating whether missing values should be removed
+#' @param keep_operators a [character] specifying how to handle operators (such as `>` and `<=`) in the input. Accepts one of three values: `"all"` (or `TRUE`) to keep all operators, `"none"` (or `FALSE`) to remove all operators, or `"edges"` to keep operators only at both ends of the range.
 #' @param ... arguments passed on to methods
 #' @details To interpret MIC values as SIR values, use [as.sir()] on MIC values. It supports guidelines from EUCAST (`r min(as.integer(gsub("[^0-9]", "", subset(clinical_breakpoints, guideline %like% "EUCAST")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(clinical_breakpoints, guideline %like% "EUCAST")$guideline)))`) and CLSI (`r min(as.integer(gsub("[^0-9]", "", subset(clinical_breakpoints, guideline %like% "CLSI")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(clinical_breakpoints, guideline %like% "CLSI")$guideline)))`).
 #'
@@ -115,12 +93,16 @@ valid_mic_levels <- c(
 #' #> 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.
+#' All so-called [group generic functions][groupGeneric()] are implemented for the MIC class (such as `!`, `!=`, `<`, `>=`, [exp()], [log2()]). Some functions of the `stats` package are also implemented (such as [quantile()], [median()], [fivenum()]). 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.
 #'
 #' Using [as.double()] or [as.numeric()] on MIC values will remove the operators and return a numeric vector. Do **not** use [as.integer()] on MIC values as by the \R convention on [factor]s, it will return the index of the factor levels (which is often useless for regular users).
 #'
 #' Use [droplevels()] to drop unused levels. At default, it will return a plain factor. Use `droplevels(..., as.mic = TRUE)` to maintain the `mic` class.
-#' @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.
+#' 
+#' With [rescale_mic()], existing MIC ranges can be limited to a defined range of MIC values. This can be useful to better compare MIC distributions.
+#'
+#' For `ggplot2`, use one of the [`scale_*_mic()`][scale_x_mic()] functions to plot MIC values. They allows custom MIC ranges and to plot intermediate log2 levels for missing MIC values.
+#' @return Ordered [factor] with additional class [`mic`], that in mathematical operations acts as a [numeric] vector. Bear in mind that the outcome of any mathematical operation on MICs will return a [numeric] value.
 #' @aliases mic
 #' @export
 #' @seealso [as.sir()]
@@ -136,6 +118,9 @@ valid_mic_levels <- c(
 #' fivenum(mic_data)
 #' quantile(mic_data)
 #' all(mic_data < 512)
+#' 
+#' # limit MICs using rescale_mic()
+#' rescale_mic(mic_data, mic_range = c(4, 16))
 #'
 #' # interpret MIC values
 #' as.sir(
@@ -161,112 +146,182 @@ valid_mic_levels <- c(
 #' if (require("ggplot2")) {
 #'   autoplot(mic_data, mo = "E. coli", ab = "cipro", language = "nl") # Dutch
 #' }
-as.mic <- function(x, na.rm = FALSE) {
+as.mic <- function(x, na.rm = FALSE, keep_operators = "all") {
   meet_criteria(x, allow_NA = TRUE)
   meet_criteria(na.rm, allow_class = "logical", has_length = 1)
-
-  if (is.mic(x)) {
-    x
+  meet_criteria(keep_operators, allow_class = c("character", "logical"), is_in = c("all", "none", "edges", FALSE, TRUE), has_length = 1)
+  if (isTRUE(keep_operators)) {
+    keep_operators <- "all"
+  } else if (isFALSE(keep_operators)) {
+    keep_operators <- "none"
+  }
+  
+  if (is.mic(x) && (keep_operators == "all" || !any(x %like% "[>=<]", na.rm = TRUE))) {
+    if (!identical(levels(x), VALID_MIC_LEVELS)) {
+      # from an older AMR version - just update MIC factor levels
+      x <- set_clean_class(factor(as.character(x), levels = VALID_MIC_LEVELS, ordered = TRUE),
+                           new_class = c("mic", "ordered", "factor"))
+    }
+    return(x)
+  }
+  
+  x.bak <- NULL
+  if (is.numeric(x)) {
+    x.bak <- format(x, scientific = FALSE)
+    # MICs never have more than 9 decimals, so:
+    x <- format(round(x, 9), scientific = FALSE)
   } else {
-    if (is.numeric(x)) {
-      x <- format(x, scientific = FALSE)
-    } else {
-      x <- as.character(unlist(x))
-    }
-    if (isTRUE(na.rm)) {
-      x <- x[!is.na(x)]
-    }
-    x[trimws2(x) == ""] <- NA
+    x <- as.character(unlist(x))
+  }
+  if (isTRUE(na.rm)) {
+    x <- x[!is.na(x)]
+  }
+  x <- trimws2(x)
+  x[x == ""] <- NA
+  if (is.null(x.bak)) {
     x.bak <- x
-
-    # comma to period
-    x <- gsub(",", ".", x, fixed = TRUE)
-    # transform scientific notation
-    x[x %like% "[-]?[0-9]+([.][0-9]+)?e[-]?[0-9]+"] <- as.double(x[x %like% "[-]?[0-9]+([.][0-9]+)?e[-]?[0-9]+"])
-    # transform Unicode for >= and <=
-    x <- gsub("\u2264", "<=", x, fixed = TRUE)
-    x <- gsub("\u2265", ">=", x, fixed = TRUE)
-    # remove other invalid characters
-    x <- gsub("[^a-zA-Z0-9.><= ]+", "", x, perl = TRUE)
-    # remove space between operator and number ("<= 0.002" -> "<=0.002")
-    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, perl = TRUE)
-    # values like "<=0.2560.512" should be 0.512
-    x <- gsub(".*[.].*[.]", "0.", x, perl = TRUE)
-    # remove ending .0
-    x <- gsub("[.]+0$", "", x, perl = TRUE)
-    # remove all after last digit
-    x <- gsub("[^0-9]+$", "", x, perl = TRUE)
-    # keep only one zero before dot
-    x <- gsub("0+[.]", "0.", x, perl = TRUE)
-    # starting 00 is probably 0.0 if there's no dot yet
-    x[x %unlike% "[.]"] <- gsub("^00", "0.0", x[!x %like% "[.]"])
-    # remove last zeroes
-    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, perl = TRUE)
-    # trim it
-    x <- trimws2(x)
-
-    ## previously unempty values now empty - should return a warning later on
-    x[x.bak != "" & x == ""] <- "invalid"
-
-    na_before <- x[is.na(x) | x == ""] %pm>% length()
-    x[!x %in% valid_mic_levels] <- NA
-    na_after <- x[is.na(x) | x == ""] %pm>% length()
-
-    if (na_before != na_after) {
-      list_missing <- x.bak[is.na(x) & !is.na(x.bak) & x.bak != ""] %pm>%
-        unique() %pm>%
-        sort() %pm>%
-        vector_and(quotes = TRUE)
-      cur_col <- get_current_column()
-      warning_("in `as.mic()`: ", na_after - na_before, " result",
-        ifelse(na_after - na_before > 1, "s", ""),
-        ifelse(is.null(cur_col), "", paste0(" in column '", cur_col, "'")),
-        " truncated (",
-        round(((na_after - na_before) / length(x)) * 100),
-        "%) that were invalid MICs: ",
-        list_missing,
-        call = FALSE
-      )
-    }
-
-    set_clean_class(factor(x, levels = valid_mic_levels, ordered = TRUE),
-      new_class = c("mic", "ordered", "factor")
+  }
+  
+  # comma to period
+  x <- gsub(",", ".", x, fixed = TRUE)
+  # transform scientific notation
+  x[x %like% "[-]?[0-9]+([.][0-9]+)?e[-]?[0-9]+"] <- as.double(x[x %like% "[-]?[0-9]+([.][0-9]+)?e[-]?[0-9]+"])
+  # transform Unicode for >= and <=
+  x <- gsub("\u2264", "<=", x, fixed = TRUE)
+  x <- gsub("\u2265", ">=", x, fixed = TRUE)
+  # remove other invalid characters
+  x <- gsub("[^a-zA-Z0-9.><= ]+", "", x, perl = TRUE)
+  # remove space between operator and number ("<= 0.002" -> "<=0.002")
+  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, perl = TRUE)
+  # values like "<=0.2560.512" should be 0.512
+  x <- gsub(".*[.].*[.]", "0.", x, perl = TRUE)
+  # remove ending .0
+  x <- gsub("[.]+0$", "", x, perl = TRUE)
+  # remove all after last digit
+  x <- gsub("[^0-9]+$", "", x, perl = TRUE)
+  # keep only one zero before dot
+  x <- gsub("0+[.]", "0.", x, perl = TRUE)
+  # starting 00 is probably 0.0 if there's no dot yet
+  x[x %unlike% "[.]"] <- gsub("^00", "0.0", x[!x %like% "[.]"])
+  # remove last zeroes
+  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, perl = TRUE)
+  # trim it
+  x <- trimws2(x)
+  
+  ## previously unempty values now empty - should return a warning later on
+  x[x.bak != "" & x == ""] <- "invalid"
+  
+  na_before <- x[is.na(x) | x == ""] %pm>% length()
+  x[!x %in% VALID_MIC_LEVELS] <- NA
+  na_after <- x[is.na(x) | x == ""] %pm>% length()
+  
+  if (na_before != na_after) {
+    list_missing <- x.bak[is.na(x) & !is.na(x.bak) & x.bak != ""] %pm>%
+      unique() %pm>%
+      sort() %pm>%
+      vector_and(quotes = TRUE)
+    cur_col <- get_current_column()
+    warning_("in `as.mic()`: ", na_after - na_before, " result",
+             ifelse(na_after - na_before > 1, "s", ""),
+             ifelse(is.null(cur_col), "", paste0(" in column '", cur_col, "'")),
+             " truncated (",
+             round(((na_after - na_before) / length(x)) * 100),
+             "%) that were invalid MICs: ",
+             list_missing,
+             call = FALSE
     )
   }
+  
+  if (keep_operators == "none" && !all(is.na(x))) {
+    x <- gsub("[>=<]", "", x)
+  } else if (keep_operators == "edges" && !all(is.na(x))) {
+    dbls <- as.double(gsub("[>=<]", "", x))
+    x[dbls == min(dbls, na.rm = TRUE)] <- paste0("<=", min(dbls, na.rm = TRUE))
+    x[dbls == max(dbls, na.rm = TRUE)] <- paste0(">=", max(dbls, na.rm = TRUE))
+    keep <- x[dbls == max(dbls, na.rm = TRUE) | dbls == min(dbls, na.rm = TRUE)]
+    x[!x %in% keep] <- gsub("[>=<]", "", x[!x %in% keep])
+  }
+  
+  set_clean_class(factor(x, levels = VALID_MIC_LEVELS, ordered = TRUE),
+                  new_class = c("mic", "ordered", "factor"))
 }
 
-all_valid_mics <- function(x) {
-  if (!inherits(x, c("mic", "character", "factor", "numeric", "integer"))) {
-    return(FALSE)
-  }
-  x_mic <- tryCatch(suppressWarnings(as.mic(x[!is.na(x)])),
-    error = function(e) NA
-  )
-  !any(is.na(x_mic)) && !all(is.na(x))
+#' @rdname as.mic
+#' @export
+is.mic <- function(x) {
+  inherits(x, "mic")
 }
 
 #' @rdname as.mic
 #' @details `NA_mic_` is a missing value of the new `mic` class, analogous to e.g. base \R's [`NA_character_`][base::NA].
 #' @format NULL
 #' @export
-NA_mic_ <- set_clean_class(factor(NA, levels = valid_mic_levels, ordered = TRUE),
+NA_mic_ <- set_clean_class(factor(NA, levels = VALID_MIC_LEVELS, ordered = TRUE),
   new_class = c("mic", "ordered", "factor")
 )
 
 #' @rdname as.mic
+#' @param mic_range a manual range to limit the MIC values, e.g., `mic_range = c(0.001, 32)`. Use `NA` to set no limit on one side, e.g., `mic_range = c(NA, 32)`.
 #' @export
-is.mic <- function(x) {
-  inherits(x, "mic")
+rescale_mic <- function(x, mic_range, keep_operators = "edges", as.mic = TRUE) {
+  meet_criteria(mic_range, allow_class = c("numeric", "integer", "logical"), has_length = 2, allow_NA = TRUE, allow_NULL = TRUE)
+  stop_ifnot(all(mic_range %in% c(VALID_MIC_LEVELS, NA)),
+             "Values in `mic_range` must be valid MIC values. Unvalid: ", vector_and(mic_range[mic_range %in% c(VALID_MIC_LEVELS, NA)]))
+  x <- as.mic(x)
+  if (is.null(mic_range)) {
+    mic_range <- c(NA, NA)
+  }
+  mic_range <- as.mic(mic_range)
+  
+  min_mic <- mic_range[1]
+  max_mic <- mic_range[2]
+  if (!is.na(min_mic)) {
+    x[x < min_mic] <- min_mic
+  }
+  if (!is.na(max_mic)) {
+    x[x > max_mic] <- max_mic
+  }
+  
+  x <- as.mic(x, keep_operators = ifelse(keep_operators == "edges", "none", keep_operators))
+  
+  if (isTRUE(as.mic)) {
+    if (keep_operators == "edges") {
+      x[x == min(x, na.rm = TRUE)] <- paste0("<=", x[x == min(x, na.rm = TRUE)])
+      x[x == max(x, na.rm = TRUE)] <- paste0(">=", x[x == max(x, na.rm = TRUE)])
+    }
+    return(x)
+  }
+  
+  # create a manual factor with levels only within desired range
+  expanded <- plotrange_as_table(x,
+                             expand = TRUE,
+                             keep_operators = ifelse(keep_operators == "edges", "none", keep_operators),
+                             mic_range = mic_range)
+  if (keep_operators == "edges") {
+    names(expanded)[1] <- paste0("<=", names(expanded)[1])
+    names(expanded)[length(expanded)] <- paste0(">=", names(expanded)[length(expanded)])
+  }
+  # MICs contain all MIC levels, so strip this to only existing levels and their intermediate values
+  out <- factor(names(expanded),
+                levels = names(expanded),
+                ordered = TRUE)
+  # and only keep the ones in the data
+  if (keep_operators == "edges") {
+    out <- out[match(x, as.double(as.mic(out, keep_operators = "all")))]  
+  } else {
+    out <- out[match(x, out)]  
+  }
+  out
 }
 
 #' @method as.double mic
@@ -288,6 +343,7 @@ as.numeric.mic <- function(x, ...) {
 #' @param as.mic a [logical] to indicate whether the `mic` class should be kept - the default is `FALSE`
 #' @export
 droplevels.mic <- function(x, as.mic = FALSE, ...) {
+  x <- as.mic(x) # make sure that currently implemented MIC levels are used
   x <- droplevels.factor(x, ...)
   if (as.mic == TRUE) {
     class(x) <- c("mic", "ordered", "factor")
@@ -295,32 +351,50 @@ droplevels.mic <- function(x, as.mic = FALSE, ...) {
   x
 }
 
+all_valid_mics <- function(x) {
+  if (!inherits(x, c("mic", "character", "factor", "numeric", "integer"))) {
+    return(FALSE)
+  }
+  x_mic <- tryCatch(suppressWarnings(as.mic(x[!is.na(x)])),
+                    error = function(e) NA
+  )
+  !any(is.na(x_mic)) && !all(is.na(x))
+}
+
 # will be exported using s3_register() in R/zzz.R
 pillar_shaft.mic <- function(x, ...) {
+  if(!identical(levels(x), VALID_MIC_LEVELS) && message_not_thrown_before("pillar_shaft.mic")) {
+    warning_(AMR_env$sup_1_icon, " These columns contain an outdated or altered structure - convert with `as.mic()` to update",
+             call = FALSE)
+  }
   crude_numbers <- as.double(x)
   operators <- gsub("[^<=>]+", "", as.character(x))
   operators[!is.na(operators) & operators != ""] <- font_silver(operators[!is.na(operators) & operators != ""], collapse = NULL)
   out <- trimws(paste0(operators, trimws(format(crude_numbers))))
   out[is.na(x)] <- font_na(NA)
-  # maketrailing zeroes almost invisible
-  out[out %like% "[.]"] <- gsub("([.]?0+)$", font_white("\\1"), out[out %like% "[.]"], perl = TRUE)
+  # make trailing zeroes less visible
+  out[out %like% "[.]"] <- gsub("([.]?0+)$", font_silver("\\1"), out[out %like% "[.]"], perl = TRUE)
   create_pillar_column(out, align = "right", width = max(nchar(font_stripstyle(out))))
 }
 
 # will be exported using s3_register() in R/zzz.R
 type_sum.mic <- function(x, ...) {
-  "mic"
+  if(!identical(levels(x), VALID_MIC_LEVELS)) {
+    paste0("mic", AMR_env$sup_1_icon)
+  } else {
+    "mic"
+  }
 }
 
 #' @method print mic
 #' @export
 #' @noRd
 print.mic <- function(x, ...) {
-  cat("Class 'mic'",
-    ifelse(length(levels(x)) < length(valid_mic_levels), font_red(" with dropped levels"), ""),
-    "\n",
-    sep = ""
-  )
+  cat("Class 'mic'")
+  if(!identical(levels(x), VALID_MIC_LEVELS)) {
+    cat(font_red(" with an outdated or altered structure - convert with `as.mic()` to update"))
+  }
+  cat("\n")
   print(as.character(x), quote = FALSE)
   att <- attributes(x)
   if ("na.action" %in% names(att)) {
@@ -341,22 +415,44 @@ summary.mic <- function(object, ...) {
 as.matrix.mic <- function(x, ...) {
   as.matrix(as.double(x), ...)
 }
+#' @method as.vector mic
+#' @export
+#' @noRd
+as.vector.mic <- function(x, mode = "numneric", ...) {
+  y <- NextMethod()
+  y <- as.mic(y)
+  calls <- unlist(lapply(sys.calls(), as.character))
+  if (any(calls %in% c("rbind", "cbind")) && message_not_thrown_before("as.vector.mic")) {
+    warning_("Functions `rbind()` and `cbind()` cannot preserve the structure of MIC values. Use dplyr's `bind_rows()` or `bind_cols()` instead.", call = FALSE)
+  }
+  y
+}
+#' @method as.list mic
+#' @export
+#' @noRd
+as.list.mic <- function(x, ...) {
+  lapply(as.list(as.character(x), ...), as.mic)
+}
+#' @method as.data.frame mic
+#' @export
+#' @noRd
+as.data.frame.mic <- function(x, ...) {
+  as.data.frame.vector(as.mic(x), ...)
+}
 
 #' @method [ mic
 #' @export
 #' @noRd
 "[.mic" <- function(x, ...) {
   y <- NextMethod()
-  attributes(y) <- attributes(x)
-  y
+  as.mic(y)
 }
 #' @method [[ mic
 #' @export
 #' @noRd
 "[[.mic" <- function(x, ...) {
   y <- NextMethod()
-  attributes(y) <- attributes(x)
-  y
+  as.mic(y)
 }
 #' @method [<- mic
 #' @export
@@ -364,8 +460,7 @@ as.matrix.mic <- function(x, ...) {
 "[<-.mic" <- function(i, j, ..., value) {
   value <- as.mic(value)
   y <- NextMethod()
-  attributes(y) <- attributes(i)
-  y
+  as.mic(y)
 }
 #' @method [[<- mic
 #' @export
@@ -373,8 +468,7 @@ as.matrix.mic <- function(x, ...) {
 "[[<-.mic" <- function(i, j, ..., value) {
   value <- as.mic(value)
   y <- NextMethod()
-  attributes(y) <- attributes(i)
-  y
+  as.mic(y)
 }
 #' @method c mic
 #' @export
@@ -388,8 +482,7 @@ c.mic <- function(...) {
 #' @noRd
 unique.mic <- function(x, incomparables = FALSE, ...) {
   y <- NextMethod()
-  attributes(y) <- attributes(x)
-  y
+  as.mic(y)
 }
 
 #' @method rep mic
@@ -397,20 +490,25 @@ unique.mic <- function(x, incomparables = FALSE, ...) {
 #' @noRd
 rep.mic <- function(x, ...) {
   y <- NextMethod()
-  attributes(y) <- attributes(x)
-  y
+  as.mic(y)
 }
 
 #' @method sort mic
 #' @export
 #' @noRd
 sort.mic <- function(x, decreasing = FALSE, ...) {
+  x <- as.mic(x) # make sure that currently implemented MIC levels are used
+  dbl <- as.double(x)
+  # make sure that e.g. '<0.001' comes before '0.001', and '>0.001' comes after
+  dbl[as.character(x) %like% "<[0-9]"] <- dbl[as.character(x) %like% "<[0-9]"] - 0.000002
+  dbl[as.character(x) %like% "<="] <- dbl[as.character(x) %like% "<="] - 0.000001
+  dbl[as.character(x) %like% ">="] <- dbl[as.character(x) %like% ">="] + 0.000001
+  dbl[as.character(x) %like% ">[0-9]"] <- dbl[as.character(x) %like% ">[0-9]"] + 0.000002
   if (decreasing == TRUE) {
-    ord <- order(-as.double(x))
+    x[order(-dbl)]
   } else {
-    ord <- order(as.double(x))
+    x[order(dbl)]
   }
-  x[ord]
 }
 
 #' @method hist mic
@@ -424,6 +522,7 @@ hist.mic <- function(x, ...) {
 
 # will be exported using s3_register() in R/zzz.R
 get_skimmers.mic <- function(column) {
+  column <- as.mic(column) # make sure that currently implemented MIC levels are used
   skimr::sfl(
     skim_type = "mic",
     p0 = ~ stats::quantile(., probs = 0, na.rm = TRUE, names = FALSE),
@@ -475,12 +574,23 @@ Math.mic <- function(x, ...) {
 
 #' @export
 Ops.mic <- function(e1, e2) {
+  e1_chr <- as.character(e1)
+  e2_chr <- character(0)
   e1 <- as.double(e1)
   if (!missing(e2)) {
-    # when e1 is `!`, e2 is missing
+    # when .Generic is `!`, e2 is missing
+    e2_chr <- as.character(e2)
     e2 <- as.double(e2)
   }
-  # set class to numeric, because otherwise NextMethod will be factor (since mic is a factor)
+  if (as.character(.Generic) %in% c("<", "<=", "==", "!=", ">", ">=")) {
+    # make sure that <0.002 is lower than 0.002
+    # and that >32 is higher than 32, but equal to >=32
+    e1[e1_chr %like% "<" & e1_chr %unlike% "="] <- e1[e1_chr %like% "<" & e1_chr %unlike% "="] - 0.000001
+    e1[e1_chr %like% ">" & e1_chr %unlike% "="] <- e1[e1_chr %like% ">" & e1_chr %unlike% "="] + 0.000001
+    e2[e2_chr %like% "<" & e2_chr %unlike% "="] <- e2[e2_chr %like% "<" & e2_chr %unlike% "="] - 0.000001
+    e2[e2_chr %like% ">" & e2_chr %unlike% "="] <- e2[e2_chr %like% ">" & e2_chr %unlike% "="] + 0.000001
+  }
+  # set .Class to numeric, because otherwise NextMethod will be factor (since mic is a factor)
   .Class <- class(e1)
   NextMethod(.Generic)
 }

R/mo.R

@@ -250,7 +250,7 @@ as.mo <- function(x,
     x_unique <- unique(x[is.na(out) & !is.na(x)])
     
     # set up progress bar
-    progress <- progress_ticker(n = length(x_unique), n_min = 10, print = info)
+    progress <- progress_ticker(n = length(x_unique), n_min = 10, print = info, title = "Converting microorganism input")
     on.exit(close(progress))
     
     msg <- character(0)
@@ -460,7 +460,7 @@ as.mo <- function(x,
       }
     }
     
-    # 'MO_CONS' and 'MO_COPS' are 'mo' vectors created in R/_pre_commit_hook.R
+    # 'MO_CONS' and 'MO_COPS' are 'mo' vectors created in R/_pre_commit_checks.R
     out[out %in% MO_CONS] <- "B_STPHY_CONS"
     out[out %in% MO_COPS] <- "B_STPHY_COPS"
     if (Becker == "all") {

R/mo_property.R

@@ -106,7 +106,12 @@
 #' mo_rank("Klebsiella pneumoniae")
 #' mo_url("Klebsiella pneumoniae")
 #' mo_is_yeast(c("Candida", "Trichophyton", "Klebsiella"))
-#'
+#' 
+#' mo_group_members("Streptococcus group A")
+#' mo_group_members(c("Streptococcus group C",
+#'                    "Streptococcus group G",
+#'                    "Streptococcus group L"))
+#' 
 #'
 #' # scientific reference -----------------------------------------------------
 #'
@@ -245,7 +250,7 @@ mo_shortname <- function(x, language = get_AMR_locale(), keep_synonyms = getOpti
   # unknown species etc.
   shortnames[shortnames %like% "unknown"] <- paste0("(", trimws2(gsub("[^a-zA-Z -]", "", shortnames[shortnames %like% "unknown"], perl = TRUE)), ")")
 
-  shortnames[mo_rank(x.mo) %in% c("kingdom", "phylum", "class", "order", "family")] <- mo_name(x.mo, language = NULL, keep_synonyms = keep_synonyms)
+  shortnames[mo_rank(x.mo) %in% c("kingdom", "phylum", "class", "order", "family")] <- mo_name(x.mo[mo_rank(x.mo) %in% c("kingdom", "phylum", "class", "order", "family")], language = NULL, keep_synonyms = keep_synonyms)
 
   shortnames[is.na(x.mo)] <- NA_character_
   load_mo_uncertainties(metadata)
@@ -796,6 +801,37 @@ mo_current <- function(x, language = get_AMR_locale(), ...) {
   mo_name(out, language = language)
 }
 
+
+#' @rdname mo_property
+#' @export
+mo_group_members <- function(x, language = get_AMR_locale(), keep_synonyms = getOption("AMR_keep_synonyms", FALSE), ...) {
+  if (missing(x)) {
+    # this tries to find the data and an 'mo' column
+    x <- find_mo_col(fn = "mo_synonyms")
+  }
+  meet_criteria(x, allow_NA = TRUE)
+  language <- validate_language(language)
+  meet_criteria(keep_synonyms, allow_class = "logical", has_length = 1)
+  
+  add_MO_lookup_to_AMR_env()
+  
+  x.mo <- as.mo(x, language = language, keep_synonyms = keep_synonyms, ...)
+  metadata <- get_mo_uncertainties()
+  
+  members <- lapply(x.mo, function(y) {
+    AMR::microorganisms.groups$mo_name[which(AMR::microorganisms.groups$mo_group == y)]
+  })
+  names(members) <- mo_name(x, keep_synonyms = TRUE, language = language)
+  
+  if (length(members) == 1) {
+    members <- unname(unlist(members))
+  }
+  
+  load_mo_uncertainties(metadata)
+  members
+}
+
+
 #' @rdname mo_property
 #' @export
 mo_info <- function(x, language = get_AMR_locale(), keep_synonyms = getOption("AMR_keep_synonyms", FALSE), ...) {
@@ -823,7 +859,8 @@ mo_info <- function(x, language = get_AMR_locale(), keep_synonyms = getOption("A
         ref = mo_ref(y, keep_synonyms = keep_synonyms),
         snomed = unlist(mo_snomed(y, keep_synonyms = keep_synonyms)),
         lpsn = mo_lpsn(y, language = language, keep_synonyms = keep_synonyms),
-        gbif = mo_gbif(y, language = language, keep_synonyms = keep_synonyms)
+        gbif = mo_gbif(y, language = language, keep_synonyms = keep_synonyms),
+        group_members = mo_group_members(y, language = language, keep_synonyms = keep_synonyms)
       )
     )
   })

R/mo_source.R

@@ -125,14 +125,13 @@
 #' If the original file (in the previous case an Excel file) is moved or deleted, the `mo_source.rds` file will be removed upon the next use of [as.mo()] or any [`mo_*`][mo_property()] function.
 #' @export
 set_mo_source <- function(path, destination = getOption("AMR_mo_source", "~/mo_source.rds")) {
+  stop_ifnot(interactive(), "this function can only be used in interactive mode, since it must ask for the user's permission to write a file to their file system.")
+
   meet_criteria(path, allow_class = "character", has_length = 1, allow_NULL = TRUE)
   meet_criteria(destination, allow_class = "character", has_length = 1)
   stop_ifnot(destination %like% "[.]rds$", "the `destination` must be a file location with file extension .rds.")
-
   mo_source_destination <- path.expand(destination)
 
-  stop_ifnot(interactive(), "this function can only be used in interactive mode, since it must ask for the user's permission to write a file to their file system.")
-
   if (is.null(path) || path %in% c(FALSE, "")) {
     AMR_env$mo_source <- NULL
     if (file.exists(mo_source_destination)) {
@@ -247,6 +246,12 @@ get_mo_source <- function(destination = getOption("AMR_mo_source", "~/mo_source.
     }
     return(NULL)
   }
+  if (destination %unlike% "[.]rds$") {
+    current_ext <- regexpr("\\.([[:alnum:]]+)$", destination)
+    current_ext <- ifelse(current_ext > -1L, substring(destination, current_ext + 1L), "")
+    vowel <- ifelse(current_ext %like% "^[AEFHILMNORSX]", "n", "")
+    stop_("The AMR mo source must be an RDS file, not a", vowel, " ", toupper(current_ext), " file. If `\"", basename(destination), "\"` was meant as your input file, use `set_mo_source()` on this file. In any case, the option `AMR_mo_source` must be set to another path.")
+  }
   if (is.null(AMR_env$mo_source)) {
     AMR_env$mo_source <- readRDS_AMR(path.expand(destination))
   }

R/plot.R

@@ -29,8 +29,10 @@
 
 #' Plotting for Classes `sir`, `mic` and `disk`
 #'
+#' @description
 #' Functions to plot classes `sir`, `mic` and `disk`, with support for base \R and `ggplot2`.
-
+#' 
+#' Especially the `scale_*_mic()` functions are relevant wrappers to plot MIC values for `ggplot2`. They allows custom MIC ranges and to plot intermediate log2 levels for missing MIC values.
 #' @param x,object values created with [as.mic()], [as.disk()] or [as.sir()] (or their `random_*` variants, such as [random_mic()])
 #' @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 drug code with [as.ab()]
@@ -66,9 +68,35 @@
 #' plot(some_mic_values, mo = "S. aureus", ab = "ampicillin")
 #' plot(some_disk_values, mo = "Escherichia coli", ab = "cipro")
 #' plot(some_disk_values, mo = "Escherichia coli", ab = "cipro", language = "nl")
-#'
+#' 
+#' 
+#' # Plotting using scale_x_mic()
 #' \donttest{
 #' if (require("ggplot2")) {
+#'   mic_plot <- ggplot(data.frame(mics = as.mic(c(0.125, "<=4", 4, 8, 32, ">=32")),
+#'                                 counts = c(1, 1, 2, 2, 3, 3)),
+#'                      aes(mics, counts)) +
+#'     geom_col()
+#'   mic_plot +
+#'     labs(title = "without scale_x_mic()")
+#' }
+#' if (require("ggplot2")) {
+#'   mic_plot +
+#'     scale_x_mic() +
+#'     labs(title = "with scale_x_mic()")
+#' }
+#' if (require("ggplot2")) {
+#'   mic_plot +
+#'     scale_x_mic(keep_operators = "all") +
+#'     labs(title = "with scale_x_mic() keeping all operators")
+#' }
+#' if (require("ggplot2")) {
+#'   mic_plot +
+#'     scale_x_mic(mic_range = c(1, 128)) +
+#'     labs(title = "with scale_x_mic() using a manual range")
+#' }
+#' 
+#' if (require("ggplot2")) {
 #'   autoplot(some_mic_values)
 #' }
 #' if (require("ggplot2")) {
@@ -80,6 +108,59 @@
 #' }
 NULL
 
+#' @export
+#' @inheritParams as.mic
+#' @param drop a [logical] to remove intermediate MIC values, defaults to `FALSE`
+#' @rdname plot
+scale_x_mic <- function(keep_operators = "edges", mic_range = NULL, drop = FALSE, ...) {
+  stop_ifnot_installed("ggplot2")
+  meet_criteria(drop, allow_class = "logical", has_length = 1)
+  scale <- ggplot2::scale_x_discrete(drop = drop, ...)
+  scale$transform <- function(x, keep_ops = keep_operators, mic_rng = mic_range) {
+    rescale_mic(x = x, keep_operators = keep_ops, mic_range = mic_rng, as.mic = FALSE)
+  }
+  scale
+}
+
+#' @export
+#' @inheritParams as.mic
+#' @rdname plot
+scale_y_mic <- function(keep_operators = "edges", mic_range = NULL, drop = FALSE, ...) {
+  stop_ifnot_installed("ggplot2")
+  meet_criteria(drop, allow_class = "logical", has_length = 1)
+  scale <- ggplot2::scale_y_discrete(drop = drop, ...)
+  scale$transform <- function(x, keep_ops = keep_operators, mic_rng = mic_range) {
+    rescale_mic(x = x, keep_operators = keep_ops, mic_range = mic_rng, as.mic = FALSE)
+  }
+  scale
+}
+
+#' @export
+#' @inheritParams as.mic
+#' @rdname plot
+scale_colour_mic <- function(keep_operators = "edges", mic_range = NULL, drop = FALSE, ...) {
+  stop_ifnot_installed("ggplot2")
+  meet_criteria(drop, allow_class = "logical", has_length = 1)
+  scale <- ggplot2::scale_colour_discrete(drop = drop, ...)
+  scale$transform <- function(x, keep_ops = keep_operators, mic_rng = mic_range) {
+    rescale_mic(x = x, keep_operators = keep_ops, mic_range = mic_rng, as.mic = FALSE)
+  }
+  scale
+}
+
+#' @export
+#' @inheritParams as.mic
+#' @rdname plot
+scale_fill_mic <- function(keep_operators = "edges", mic_range = NULL, drop = FALSE, ...) {
+  stop_ifnot_installed("ggplot2")
+  meet_criteria(drop, allow_class = "logical", has_length = 1)
+  scale <- ggplot2::scale_fill_discrete(drop = drop, ...)
+  scale$transform <- function(x, keep_ops = keep_operators, mic_rng = mic_range) {
+    rescale_mic(x = x, keep_operators = keep_ops, mic_range = mic_rng, as.mic = FALSE)
+  }
+  scale
+}
+
 #' @method plot mic
 #' @importFrom graphics barplot axis mtext legend
 #' @export
@@ -103,21 +184,18 @@ plot.mic <- function(x,
   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)
-  if ("colours_RSI" %in% names(list(...))) {
-    deprecation_warning(extra_msg = "The 'colours_RSI' argument has been replaced with 'colours_SIR'.")
-    colours_SIR <- list(...)$colours_RSI
-  }
   meet_criteria(colours_SIR, allow_class = "character", has_length = c(1, 3))
   language <- validate_language(language)
   meet_criteria(expand, allow_class = "logical", has_length = 1)
 
+  x <- as.mic(x) # make sure that currently implemented MIC levels are used
+  
   if (length(colours_SIR) == 1) {
     colours_SIR <- rep(colours_SIR, 3)
   }
   main <- gsub(" +", " ", paste0(main, collapse = " "))
 
-  x <- plot_prepare_table(x, expand = expand)
-
+  x <- plotrange_as_table(x, expand = expand)
   cols_sub <- plot_colours_subtitle_guideline(
     x = x,
     mo = mo,
@@ -193,15 +271,13 @@ barplot.mic <- function(height,
   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)
-  if ("colours_RSI" %in% names(list(...))) {
-    deprecation_warning(extra_msg = "The 'colours_RSI' argument has been replaced with 'colours_SIR'.")
-    colours_SIR <- list(...)$colours_RSI
-  }
   meet_criteria(colours_SIR, allow_class = "character", has_length = c(1, 3))
   language <- validate_language(language)
   meet_criteria(expand, allow_class = "logical", has_length = 1)
 
   main <- gsub(" +", " ", paste0(main, collapse = " "))
+  
+  height <- as.mic(height) # make sure that currently implemented MIC levels are used
 
   plot(
     x = height,
@@ -239,10 +315,6 @@ autoplot.mic <- function(object,
   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)
-  if ("colours_RSI" %in% names(list(...))) {
-    deprecation_warning(extra_msg = "The 'colours_RSI' argument has been replaced with 'colours_SIR'.")
-    colours_SIR <- list(...)$colours_RSI
-  }
   meet_criteria(colours_SIR, allow_class = "character", has_length = c(1, 3))
   language <- validate_language(language)
   meet_criteria(expand, allow_class = "logical", has_length = 1)
@@ -254,7 +326,8 @@ autoplot.mic <- function(object,
     title <- gsub(" +", " ", paste0(title, collapse = " "))
   }
 
-  x <- plot_prepare_table(object, expand = expand)
+  object <- as.mic(object) # make sure that currently implemented MIC levels are used
+  x <- plotrange_as_table(object, expand = expand)
   cols_sub <- plot_colours_subtitle_guideline(
     x = x,
     mo = mo,
@@ -290,6 +363,7 @@ autoplot.mic <- function(object,
   if (any(colours_SIR %in% cols_sub$cols)) {
     vals <- c(
       "(S) Susceptible" = colours_SIR[1],
+      "(SDD) Susceptible dose-dependent" = colours_SIR[2],
       "(I) Susceptible, incr. exp." = colours_SIR[2],
       "(I) Intermediate" = colours_SIR[2],
       "(R) Resistant" = colours_SIR[3]
@@ -316,12 +390,14 @@ autoplot.mic <- function(object,
 #' @rdname plot
 # will be exported using s3_register() in R/zzz.R
 fortify.mic <- function(object, ...) {
+  object <- as.mic(object) # make sure that currently implemented MIC levels are used
   stats::setNames(
-    as.data.frame(plot_prepare_table(object, expand = FALSE)),
+    as.data.frame(plotrange_as_table(object, expand = FALSE)),
     c("x", "y")
   )
 }
 
+
 #' @method plot disk
 #' @export
 #' @importFrom graphics barplot axis mtext legend
@@ -345,10 +421,6 @@ plot.disk <- function(x,
   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)
-  if ("colours_RSI" %in% names(list(...))) {
-    deprecation_warning(extra_msg = "The 'colours_RSI' argument has been replaced with 'colours_SIR'.")
-    colours_SIR <- list(...)$colours_RSI
-  }
   meet_criteria(colours_SIR, allow_class = "character", has_length = c(1, 3))
   language <- validate_language(language)
   meet_criteria(expand, allow_class = "logical", has_length = 1)
@@ -358,8 +430,7 @@ plot.disk <- function(x,
   }
   main <- gsub(" +", " ", paste0(main, collapse = " "))
 
-  x <- plot_prepare_table(x, expand = expand)
-
+  x <- plotrange_as_table(x, expand = expand)
   cols_sub <- plot_colours_subtitle_guideline(
     x = x,
     mo = mo,
@@ -435,10 +506,6 @@ barplot.disk <- function(height,
   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)
-  if ("colours_RSI" %in% names(list(...))) {
-    deprecation_warning(extra_msg = "The 'colours_RSI' argument has been replaced with 'colours_SIR'.")
-    colours_SIR <- list(...)$colours_RSI
-  }
   meet_criteria(colours_SIR, allow_class = "character", has_length = c(1, 3))
   language <- validate_language(language)
   meet_criteria(expand, allow_class = "logical", has_length = 1)
@@ -481,10 +548,6 @@ autoplot.disk <- function(object,
   meet_criteria(mo, allow_class = c("mo", "character"), allow_NULL = TRUE)
   meet_criteria(ab, allow_class = c("ab", "character"), allow_NULL = TRUE)
   meet_criteria(guideline, allow_class = "character", has_length = 1)
-  if ("colours_RSI" %in% names(list(...))) {
-    deprecation_warning(extra_msg = "The 'colours_RSI' argument has been replaced with 'colours_SIR'.")
-    colours_SIR <- list(...)$colours_RSI
-  }
   meet_criteria(colours_SIR, allow_class = "character", has_length = c(1, 3))
   language <- validate_language(language)
   meet_criteria(expand, allow_class = "logical", has_length = 1)
@@ -496,7 +559,7 @@ autoplot.disk <- function(object,
     title <- gsub(" +", " ", paste0(title, collapse = " "))
   }
 
-  x <- plot_prepare_table(object, expand = expand)
+  x <- plotrange_as_table(object, expand = expand)
   cols_sub <- plot_colours_subtitle_guideline(
     x = x,
     mo = mo,
@@ -533,6 +596,7 @@ autoplot.disk <- function(object,
   if (any(colours_SIR %in% cols_sub$cols)) {
     vals <- c(
       "(S) Susceptible" = colours_SIR[1],
+      "(SDD) Susceptible dose-dependent" = colours_SIR[2],
       "(I) Susceptible, incr. exp." = colours_SIR[2],
       "(I) Intermediate" = colours_SIR[2],
       "(R) Resistant" = colours_SIR[3]
@@ -560,7 +624,7 @@ autoplot.disk <- function(object,
 # will be exported using s3_register() in R/zzz.R
 fortify.disk <- function(object, ...) {
   stats::setNames(
-    as.data.frame(plot_prepare_table(object, expand = FALSE)),
+    as.data.frame(plotrange_as_table(object, expand = FALSE)),
     c("x", "y")
   )
 }
@@ -586,14 +650,21 @@ plot.sir <- function(x,
   if (!"S" %in% data$x) {
     data <- rbind_AMR(data, data.frame(x = "S", n = 0, s = 0, stringsAsFactors = FALSE))
   }
+  if (!"SDD" %in% data$x) {
+    data <- rbind_AMR(data, data.frame(x = "SDD", n = 0, s = 0, stringsAsFactors = FALSE))
+  }
   if (!"I" %in% data$x) {
     data <- rbind_AMR(data, data.frame(x = "I", n = 0, s = 0, stringsAsFactors = FALSE))
   }
   if (!"R" %in% data$x) {
     data <- rbind_AMR(data, data.frame(x = "R", n = 0, s = 0, stringsAsFactors = FALSE))
   }
-
-  data$x <- factor(data$x, levels = c("S", "I", "R"), ordered = TRUE)
+  if (!"N" %in% data$x) {
+    data <- rbind_AMR(data, data.frame(x = "N", n = 0, s = 0, stringsAsFactors = FALSE))
+  }
+  
+  data <- data[!(data$n == 0 & data$x %in% c("SDD", "I", "N")), , drop = FALSE]
+  data$x <- factor(data$x, levels = intersect(unique(data$x), c("S", "SDD", "I", "R", "N")), ordered = TRUE)
 
   ymax <- pm_if_else(max(data$s) > 95, 105, 100)
 
@@ -635,10 +706,6 @@ barplot.sir <- function(height,
   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)
-  if ("colours_RSI" %in% names(list(...))) {
-    deprecation_warning(extra_msg = "The 'colours_RSI' argument has been replaced with 'colours_SIR'.")
-    colours_SIR <- list(...)$colours_RSI
-  }
   meet_criteria(colours_SIR, allow_class = "character", has_length = c(1, 3))
   language <- validate_language(language)
   meet_criteria(expand, allow_class = "logical", has_length = 1)
@@ -646,10 +713,15 @@ barplot.sir <- function(height,
   if (length(colours_SIR) == 1) {
     colours_SIR <- rep(colours_SIR, 3)
   }
+  # add SDD and N to colours
+  colours_SIR <- c(colours_SIR[1:2], colours_SIR[2], colours_SIR[3], "#888888")
   main <- gsub(" +", " ", paste0(main, collapse = " "))
 
   x <- table(height)
-  x <- x[c(1, 2, 3)]
+  # remove missing I, SDD, and N
+  colours_SIR <- colours_SIR[!(names(x) %in% c("SDD", "I", "N") & x == 0)]
+  x <- x[!(names(x) %in% c("SDD", "I", "N") & x == 0)]
+  # plot it
   barplot(x,
     col = colours_SIR,
     xlab = xlab,
@@ -688,15 +760,18 @@ autoplot.sir <- function(object,
   }
 
   df <- as.data.frame(table(object), stringsAsFactors = TRUE)
-  colnames(df) <- c("sir", "count")
+  colnames(df) <- c("x", "n")
+  df <- df[!(df$n == 0 & df$x %in% c("SDD", "I", "N")), , drop = FALSE]
   ggplot2::ggplot(df) +
-    ggplot2::geom_col(ggplot2::aes(x = sir, y = count, fill = sir)) +
+    ggplot2::geom_col(ggplot2::aes(x = x, y = n, fill = x)) +
     # limits = force is needed because of a ggplot2 >= 3.3.4 bug (#4511)
     ggplot2::scale_fill_manual(
       values = c(
         "S" = colours_SIR[1],
+        "SDD" = colours_SIR[2],
         "I" = colours_SIR[2],
-        "R" = colours_SIR[3]
+        "R" = colours_SIR[3],
+        "N" = "#888888"
       ),
       limits = force
     ) +
@@ -714,22 +789,20 @@ fortify.sir <- function(object, ...) {
   )
 }
 
-plot_prepare_table <- function(x, expand) {
+plotrange_as_table <- function(x, expand, keep_operators = "all", mic_range = NULL) {
   x <- x[!is.na(x)]
-  stop_if(length(x) == 0, "no observations to plot", call = FALSE)
   if (is.mic(x)) {
+    x <- as.mic(x, keep_operators = keep_operators)
     if (expand == TRUE) {
-      # expand range for MIC by adding factors of 2 from lowest to highest so all MICs in between also print
-      valid_lvls <- levels(x)
-      extra_range <- max(x) / 2
-      while (min(extra_range) / 2 > min(x)) {
-        extra_range <- c(min(extra_range) / 2, extra_range)
-      }
+      # expand range for MIC by adding common intermediate factors levels
+      extra_range <- COMMON_MIC_VALUES[COMMON_MIC_VALUES > min(x, na.rm = TRUE) & COMMON_MIC_VALUES < max(x, na.rm = TRUE)]
+      # remove the ones that are in 25% range of user values
+      extra_range <- extra_range[!vapply(FUN.VALUE = logical(1), extra_range, function(r) any(abs(r - x) / x < 0.25, na.rm = TRUE))]
       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) & names(extra_range) %in% valid_lvls]
+      extra_range <- extra_range[!names(extra_range) %in% names(x) & names(extra_range) %in% VALID_MIC_LEVELS]
       x <- as.table(c(x, extra_range))
     } else {
       x <- table(droplevels(x, as.mic = FALSE))
@@ -751,6 +824,15 @@ plot_prepare_table <- function(x, expand) {
   as.table(x)
 }
 
+ggplot2_get_from_dots <- function(arg, default, ...) {
+  dots <- list(...)
+  if (!arg %in% names(dots)) {
+    default
+  } else {
+    dots[[arg]]
+  }
+}
+
 plot_name_of_I <- function(guideline) {
   if (guideline %unlike% "CLSI" && as.double(gsub("[^0-9]+", "", guideline)) >= 2019) {
     # interpretation since 2019
@@ -762,6 +844,8 @@ plot_name_of_I <- function(guideline) {
 }
 
 plot_colours_subtitle_guideline <- function(x, mo, ab, guideline, colours_SIR, fn, language, method, breakpoint_type, include_PKPD, ...) {
+  stop_if(length(x) == 0, "no observations to plot", call = FALSE)
+  
   guideline <- get_guideline(guideline, AMR::clinical_breakpoints)
   
   # store previous interpretations to backup
@@ -804,8 +888,10 @@ plot_colours_subtitle_guideline <- function(x, mo, ab, guideline, colours_SIR, f
     cols <- character(length = length(sir))
     cols[is.na(sir)] <- "#BEBEBE"
     cols[sir == "S"] <- colours_SIR[1]
+    cols[sir == "SDD"] <- colours_SIR[2]
     cols[sir == "I"] <- colours_SIR[2]
     cols[sir == "R"] <- colours_SIR[3]
+    cols[sir == "N"] <- "#888888"
     sub <- bquote(.(abname) ~ "-" ~ italic(.(moname)) ~ .(guideline_txt))
   } else {
     cols <- "#BEBEBE"

R/proportion.R

@@ -48,7 +48,7 @@
 #' @details
 #' **Remember that you should filter your data to let it contain only first isolates!** This is needed to exclude duplicates and to reduce selection bias. Use [first_isolate()] to determine them in your data set with one of the four available algorithms.
 #' 
-#' The function [resistance()] is equal to the function [proportion_R()]. The function [susceptibility()] is equal to the function [proportion_SI()].
+#' The function [resistance()] is equal to the function [proportion_R()]. The function [susceptibility()] is equal to the function [proportion_SI()]. Since AMR v3.0, [proportion_SI()] and [proportion_I()] include dose-dependent susceptibility ('SDD').
 #'
 #' Use [sir_confidence_interval()] to calculate the confidence interval, which relies on [binom.test()], i.e., the Clopper-Pearson method. This function returns a vector of length 2 at default for antimicrobial *resistance*. Change the `side` argument to "left"/"min" or "right"/"max" to return a single value, and change the `ab_result` argument to e.g. `c("S", "I")` to test for antimicrobial *susceptibility*, see Examples.
 #'
@@ -247,7 +247,7 @@ susceptibility <- function(...,
                            only_all_tested = FALSE) {
   tryCatch(
     sir_calc(...,
-      ab_result = c("S", "I"),
+      ab_result = c("S", "SDD", "I"),
       minimum = minimum,
       as_percent = as_percent,
       only_all_tested = only_all_tested,
@@ -267,7 +267,7 @@ sir_confidence_interval <- function(...,
                                     confidence_level = 0.95,
                                     side = "both",
                                     collapse = FALSE) {
-  meet_criteria(ab_result, allow_class = c("character", "sir"), has_length = c(1, 2, 3), is_in = c("S", "I", "R"))
+  meet_criteria(ab_result, allow_class = c("character", "sir"), has_length = c(1:5), is_in = c("S", "SDD", "I", "R", "N"))
   meet_criteria(minimum, allow_class = c("numeric", "integer"), has_length = 1, is_positive_or_zero = TRUE, is_finite = TRUE)
   meet_criteria(as_percent, allow_class = "logical", has_length = 1)
   meet_criteria(only_all_tested, allow_class = "logical", has_length = 1)
@@ -285,7 +285,7 @@ sir_confidence_interval <- function(...,
   )
   n <- tryCatch(
     sir_calc(...,
-      ab_result = c("S", "I", "R"),
+      ab_result = c("S", "SDD", "I", "R", "N"),
       only_all_tested = only_all_tested,
       only_count = TRUE
     ),
@@ -294,7 +294,7 @@ sir_confidence_interval <- function(...,
 
   # this applies the Clopper-Pearson method
   out <- stats::binom.test(x = x, n = n, conf.level = confidence_level)$conf.int
-  out <- set_clean_class(out, "double")
+  out <- set_clean_class(out, "numeric")
 
   if (side %in% c("left", "l", "lower", "lowest", "less", "min")) {
     out <- out[1]
@@ -351,9 +351,12 @@ proportion_IR <- function(...,
                           minimum = 30,
                           as_percent = FALSE,
                           only_all_tested = FALSE) {
+  if (message_not_thrown_before("proportion_IR", entire_session = TRUE)) {
+    message_("Note that `proportion_IR()` will also include dose-dependent susceptibility, 'SDD'. This note will be shown once for this session.", as_note = FALSE)
+  }
   tryCatch(
     sir_calc(...,
-      ab_result = c("I", "R"),
+      ab_result = c("I", "SDD", "R"),
       minimum = minimum,
       as_percent = as_percent,
       only_all_tested = only_all_tested,
@@ -369,9 +372,12 @@ proportion_I <- function(...,
                          minimum = 30,
                          as_percent = FALSE,
                          only_all_tested = FALSE) {
+  if (message_not_thrown_before("proportion_I", entire_session = TRUE)) {
+    message_("Note that `proportion_I()` will also include dose-dependent susceptibility, 'SDD'. This note will be shown once for this session.", as_note = FALSE)
+  }
   tryCatch(
     sir_calc(...,
-      ab_result = "I",
+      ab_result = c("I", "SDD"),
       minimum = minimum,
       as_percent = as_percent,
       only_all_tested = only_all_tested,
@@ -387,9 +393,12 @@ proportion_SI <- function(...,
                           minimum = 30,
                           as_percent = FALSE,
                           only_all_tested = FALSE) {
+  if (message_not_thrown_before("proportion_SI", entire_session = TRUE)) {
+    message_("Note that `proportion_SI()` will also include dose-dependent susceptibility, 'SDD'. This note will be shown once for this session.", as_note = FALSE)
+  }
   tryCatch(
     sir_calc(...,
-      ab_result = c("S", "I"),
+      ab_result = c("S", "I", "SDD"),
       minimum = minimum,
       as_percent = as_percent,
       only_all_tested = only_all_tested,

R/random.R

@@ -83,10 +83,6 @@ random_disk <- function(size = NULL, mo = NULL, ab = NULL, ...) {
 #' @export
 random_sir <- function(size = NULL, prob_SIR = c(0.33, 0.33, 0.33), ...) {
   meet_criteria(size, allow_class = c("numeric", "integer"), has_length = 1, is_positive = TRUE, is_finite = TRUE, allow_NULL = TRUE)
-  if ("prob_RSI" %in% names(list(...))) {
-    deprecation_warning("prob_RSI", "prob_SIR", is_function = FALSE)
-    prob_SIR <- list(...)$prob_RSI
-  }
   meet_criteria(prob_SIR, allow_class = c("numeric", "integer"), has_length = 3)
   if (is.null(size)) {
     size <- NROW(get_current_data(arg_name = "size", call = -3))

R/sir.R

@@ -29,47 +29,61 @@
 
 #' Translate MIC and Disk Diffusion to SIR, or Clean Existing SIR Data
 #'
-#' @description Interpret minimum inhibitory concentration (MIC) values and disk diffusion diameters according to EUCAST or CLSI, or clean up existing SIR values. This transforms the input to a new class [`sir`], which is an ordered [factor] with levels `S < I < R`.
+#' @description Clean up existing SIR values, or interpret minimum inhibitory concentration (MIC) values and disk diffusion diameters according to EUCAST or CLSI. [as.sir()] transforms the input to a new class [`sir`], which is an ordered [factor].
 #' 
-#' Currently available **breakpoint guidelines** are EUCAST `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST")$guideline)))` and CLSI `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI")$guideline)))`, and available **breakpoint types** are `r vector_and(clinical_breakpoints$type)`.
-#'
-#' All breakpoints used for interpretation are publicly available in the [clinical_breakpoints] data set.
+#' These breakpoints are currently implemented:
+#' - For **clinical microbiology**: EUCAST `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST" & type == "human")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST" & type == "human")$guideline)))` and CLSI `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type == "human")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type == "human")$guideline)))`;
+#' - For **veterinary microbiology**: EUCAST `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST" & type == "animal")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST" & type == "animal")$guideline)))` and CLSI `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type == "animal")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type == "animal")$guideline)))`;
+#' - ECOFFs (Epidemiological cut-off values): EUCAST `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST" & type == "ECOFF")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST" & type == "ECOFF")$guideline)))` and CLSI `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type == "ECOFF")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type == "ECOFF")$guideline)))`.
+#' 
+#' All breakpoints used for interpretation are available in our [clinical_breakpoints] data set.
 #' @rdname as.sir
 #' @param x vector of values (for class [`mic`]: MIC values in mg/L, for class [`disk`]: a disk diffusion radius in millimetres)
-#' @param mo any (vector of) text that can be coerced to valid microorganism codes with [as.mo()], can be left empty to determine it automatically
-#' @param ab any (vector of) text that can be coerced to a valid antimicrobial drug code with [as.ab()]
-#' @param uti (Urinary Tract Infection) A vector with [logical]s (`TRUE` or `FALSE`) to specify whether a UTI specific interpretation from the guideline should be chosen. For using [as.sir()] on a [data.frame], this can also be a column containing [logical]s or when left blank, the data set will be searched for a column 'specimen', and rows within this column containing 'urin' (such as 'urine', 'urina') will be regarded isolates from a UTI. See *Examples*.
+#' @param mo a vector (or column name) with [character]s that can be coerced to valid microorganism codes with [as.mo()], can be left empty to determine it automatically
+#' @param ab a vector (or column name) with [character]s that can be coerced to a valid antimicrobial drug code with [as.ab()]
+#' @param uti (Urinary Tract Infection) a vector (or column name) with [logical]s (`TRUE` or `FALSE`) to specify whether a UTI specific interpretation from the guideline should be chosen. For using [as.sir()] on a [data.frame], this can also be a column containing [logical]s or when left blank, the data set will be searched for a column 'specimen', and rows within this column containing 'urin' (such as 'urine', 'urina') will be regarded isolates from a UTI. See *Examples*.
 #' @inheritParams first_isolate
 #' @param guideline defaults to EUCAST `r  max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST")$guideline)))` (the latest implemented EUCAST guideline in the [AMR::clinical_breakpoints] data set), but can be set with the [package option][AMR-options] [`AMR_guideline`][AMR-options]. Currently supports EUCAST (`r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST")$guideline)))`) and CLSI (`r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI")$guideline)))`), see *Details*.
 #' @param conserve_capped_values a [logical] to indicate that MIC values starting with `">"` (but not `">="`) must always return "R" , and that MIC values starting with `"<"` (but not `"<="`) must always return "S"
 #' @param add_intrinsic_resistance *(only useful when using a EUCAST guideline)* a [logical] to indicate whether intrinsic antibiotic resistance must also be considered for applicable bug-drug combinations, meaning that e.g. ampicillin will always return "R" in *Klebsiella* species. Determination is based on the [intrinsic_resistant] data set, that itself is based on `r format_eucast_version_nr(3.3)`.
 #' @param include_screening a [logical] to indicate that clinical breakpoints for screening are allowed - the default is `FALSE`. Can also be set with the [package option][AMR-options] [`AMR_include_screening`][AMR-options].
 #' @param include_PKPD a [logical] to indicate that PK/PD clinical breakpoints must be applied as a last resort - the default is `TRUE`. Can also be set with the [package option][AMR-options] [`AMR_include_PKPD`][AMR-options].
-#' @param breakpoint_type the type of breakpoints to use, either `r vector_or(clinical_breakpoints$type)`. ECOFF stands for Epidemiological Cut-Off values. The default is `"human"`, which can also be set with the [package option][AMR-options] [`AMR_breakpoint_type`][AMR-options].
+#' @param breakpoint_type the type of breakpoints to use, either `r vector_or(clinical_breakpoints$type)`. ECOFF stands for Epidemiological Cut-Off values. The default is `"human"`, which can also be set with the [package option][AMR-options] [`AMR_breakpoint_type`][AMR-options]. If `host` is set to values of veterinary species, this will automatically be set to `"animal"`.
+#' @param host a vector (or column name) with [character]s to indicate the host. Only useful for veterinary breakpoints, as it requires `breakpoint_type = "animal"`. The values can be any text resembling the animal species, even in any of the `r length(LANGUAGES_SUPPORTED)` supported languages of this package. For foreign languages, be sure to set the language with [set_AMR_locale()] (though it will be automatically guessed based on the system language).
 #' @param reference_data a [data.frame] to be used for interpretation, which defaults to the [clinical_breakpoints] data set. Changing this argument allows for using own interpretation guidelines. This argument must contain a data set that is equal in structure to the [clinical_breakpoints] data set (same column names and column types). Please note that the `guideline` argument will be ignored when `reference_data` is manually set.
 #' @param threshold maximum fraction of invalid antimicrobial interpretations of `x`, see *Examples*
 #' @param ... for using on a [data.frame]: names of columns to apply [as.sir()] on (supports tidy selection such as `column1:column4`). Otherwise: arguments passed on to methods.
 #' @details
-#' *Note: The clinical breakpoints in this package were validated through and imported from [WHONET](https://whonet.org) and the public use of this `AMR` package has been endorsed by CLSI and EUCAST, please see [clinical_breakpoints] for more information.*
+#' *Note: The clinical breakpoints in this package were validated through, and imported from, [WHONET](https://whonet.org). The public use of this `AMR` package has been endorsed by both CLSI and EUCAST. See [clinical_breakpoints] for more information.*
 #' 
 #' ### How it Works
 #'
-#' The [as.sir()] function works in four ways:
+#' The [as.sir()] function can work in four ways:
 #'
-#' 1. For **cleaning raw / untransformed data**. The data will be cleaned to only contain values S, I and R and will try its best to determine this with some intelligence. For example, mixed values with SIR interpretations and MIC values such as `"<0.25; S"` will be coerced to `"S"`. Combined interpretations for multiple test methods (as seen in laboratory records) such as `"S; S"` will be coerced to `"S"`, but a value like `"S; I"` will return `NA` with a warning that the input is unclear.
+#' 1. For **cleaning raw / untransformed data**. The data will be cleaned to only contain valid values, namely: **S** for susceptible, **I** for intermediate or 'susceptible, increased exposure', **R** for resistant, **N** for non-interpretable, and **SDD** for susceptible dose-dependent. Each of these can be set using a [regular expression][base::regex]. Furthermore, [as.sir()] will try its best to clean with some intelligence. For example, mixed values with SIR interpretations and MIC values such as `"<0.25; S"` will be coerced to `"S"`. Combined interpretations for multiple test methods (as seen in laboratory records) such as `"S; S"` will be coerced to `"S"`, but a value like `"S; I"` will return `NA` with a warning that the input is invalid.
 #'
 #' 2. For **interpreting minimum inhibitory concentration (MIC) values** according to EUCAST or CLSI. You must clean your MIC values first using [as.mic()], that also gives your columns the new data class [`mic`]. Also, be sure to have a column with microorganism names or codes. It will be found automatically, but can be set manually using the `mo` argument.
 #'    * Using `dplyr`, SIR interpretation can be done very easily with either:
-#'      ```
+#'      ```r
 #'      your_data %>% mutate_if(is.mic, as.sir)
 #'      your_data %>% mutate(across(where(is.mic), as.sir))
+#'      your_data %>% mutate_if(is.mic, as.sir, ab = "column_with_antibiotics", mo = "column_with_microorganisms")
+#'      your_data %>% mutate_if(is.mic, as.sir, ab = c("cipro", "ampicillin", ...), mo = c("E. coli", "K. pneumoniae", ...))
+#'      
+#'      # for veterinary breakpoints, also set `host`:
+#'      your_data %>% mutate_if(is.mic, as.sir, host = "column_with_animal_hosts", guideline = "CLSI")
 #'      ```
 #'    * Operators like "<=" will be stripped before interpretation. When using `conserve_capped_values = TRUE`, an MIC value of e.g. ">2" will always return "R", even if the breakpoint according to the chosen guideline is ">=4". This is to prevent that capped values from raw laboratory data would not be treated conservatively. The default behaviour (`conserve_capped_values = FALSE`) considers ">2" to be lower than ">=4" and might in this case return "S" or "I".
 #' 3. For **interpreting disk diffusion diameters** according to EUCAST or CLSI. You must clean your disk zones first using [as.disk()], that also gives your columns the new data class [`disk`]. Also, be sure to have a column with microorganism names or codes. It will be found automatically, but can be set manually using the `mo` argument.
 #'    * Using `dplyr`, SIR interpretation can be done very easily with either:
-#'      ```
+#'      ```r
 #'      your_data %>% mutate_if(is.disk, as.sir)
 #'      your_data %>% mutate(across(where(is.disk), as.sir))
+#'      your_data %>% mutate_if(is.disk, as.sir, ab = "column_with_antibiotics", mo = "column_with_microorganisms")
+#'      your_data %>% mutate_if(is.disk, as.sir, ab = c("cipro", "ampicillin", ...), mo = c("E. coli", "K. pneumoniae", ...))
+#'      
+#'      # for veterinary breakpoints, also set `host`:
+#'      your_data %>% mutate_if(is.disk, as.sir, host = "column_with_animal_hosts", guideline = "CLSI")
 #'      ```
 #' 4. For **interpreting a complete data set**, with automatic determination of MIC values, disk diffusion diameters, microorganism names or codes, and antimicrobial test results. This is done very simply by running `as.sir(your_data)`.
 #'
@@ -77,7 +91,7 @@
 #'
 #' ### Supported Guidelines
 #'
-#' For interpreting MIC values as well as disk diffusion diameters, currently implemented guidelines are EUCAST (`r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST")$guideline)))`) and CLSI (`r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI")$guideline)))`).
+#' For interpreting MIC values as well as disk diffusion diameters, currently implemented guidelines are for **clinical microbiology**: EUCAST `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST" & type == "human")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST" & type == "human")$guideline)))` and CLSI `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type == "human")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type == "human")$guideline)))`, and for **veterinary microbiology**: EUCAST `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST" & type == "animal")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST" & type == "animal")$guideline)))` and CLSI `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type == "animal")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type == "animal")$guideline)))`.
 #'
 #' Thus, the `guideline` argument must be set to e.g., ``r paste0('"', subset(AMR::clinical_breakpoints, guideline %like% "EUCAST")$guideline[1], '"')`` or ``r paste0('"', subset(AMR::clinical_breakpoints, guideline %like% "CLSI")$guideline[1], '"')``. By simply using `"EUCAST"` (the default) or `"CLSI"` as input, the latest included version of that guideline will automatically be selected. You can set your own data set using the `reference_data` argument. The `guideline` argument will then be ignored.
 #'
@@ -90,6 +104,13 @@
 #'   # or to reset:
 #'   options(AMR_guideline = NULL)
 #' ```
+#' 
+#' For veterinary guidelines, these might be the best options:
+#' 
+#' ```
+#'   options(AMR_guideline = "CLSI")
+#'   options(AMR_breakpoint_type = "animal")
+#' ```
 #'
 #' ### After Interpretation
 #'
@@ -103,7 +124,7 @@
 #'
 #' The function [is.sir()] detects if the input contains class `sir`. If the input is a [data.frame], it iterates over all columns and returns a [logical] vector.
 #'
-#' The function [is_sir_eligible()] returns `TRUE` when a columns contains at most 5% invalid antimicrobial interpretations (not S and/or I and/or R), and `FALSE` otherwise. The threshold of 5% can be set with the `threshold` argument. If the input is a [data.frame], it iterates over all columns and returns a [logical] vector.
+#' The function [is_sir_eligible()] returns `TRUE` when a columns contains at most 5% invalid antimicrobial interpretations (not S and/or I and/or R and/or N and/or SDD), and `FALSE` otherwise. The threshold of 5% can be set with the `threshold` argument. If the input is a [data.frame], it iterates over all columns and returns a [logical] vector.
 #' @section Interpretation of SIR:
 #' In 2019, the European Committee on Antimicrobial Susceptibility Testing (EUCAST) has decided to change the definitions of susceptibility testing categories S, I, and R as shown below (<https://www.eucast.org/newsiandr>):
 #'
@@ -124,9 +145,10 @@
 #' @source
 #' For interpretations of minimum inhibitory concentration (MIC) values and disk diffusion diameters:
 #'
-#' - **M39 Analysis and Presentation of Cumulative Antimicrobial Susceptibility Test Data**, `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI")$guideline)))`, *Clinical and Laboratory Standards Institute* (CLSI). <https://clsi.org/standards/products/microbiology/documents/m39/>.
-#' - **M100 Performance Standard for Antimicrobial Susceptibility Testing**, `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI")$guideline)))`, *Clinical and Laboratory Standards Institute* (CLSI). <https://clsi.org/standards/products/microbiology/documents/m100/>.
-#' - **Breakpoint tables for interpretation of MICs and zone diameters**, `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST")$guideline)))`, *European Committee on Antimicrobial Susceptibility Testing* (EUCAST). <https://www.eucast.org/clinical_breakpoints>.
+#' - **CLSI M39: Analysis and Presentation of Cumulative Antimicrobial Susceptibility Test Data**, `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI")$guideline)))`, *Clinical and Laboratory Standards Institute* (CLSI). <https://clsi.org/standards/products/microbiology/documents/m39/>.
+#' - **CLSI M100: Performance Standard for Antimicrobial Susceptibility Testing**, `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type != "animal")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type != "animal")$guideline)))`, *Clinical and Laboratory Standards Institute* (CLSI). <https://clsi.org/standards/products/microbiology/documents/m100/>.
+#' - **CLSI VET01: Performance Standards for Antimicrobial Disk and Dilution Susceptibility Tests for Bacteria Isolated From Animals**, `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type == "animal")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "CLSI" & type == "animal")$guideline)))`, *Clinical and Laboratory Standards Institute* (CLSI). <https://clsi.org/standards/products/veterinary-medicine/documents/vet01//>.
+#' - **EUCAST Breakpoint tables for interpretation of MICs and zone diameters**, `r min(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST")$guideline)))`-`r max(as.integer(gsub("[^0-9]", "", subset(AMR::clinical_breakpoints, guideline %like% "EUCAST")$guideline)))`, *European Committee on Antimicrobial Susceptibility Testing* (EUCAST). <https://www.eucast.org/clinical_breakpoints>.
 #' @inheritSection AMR Reference Data Publicly Available
 #' @examples
 #' example_isolates
@@ -173,7 +195,7 @@
 #'   df %>% mutate(across(AMP:TOB, as.sir))
 #'
 #'   df %>%
-#'     mutate_at(vars(AMP:TOB), as.sir, mo = .$microorganism)
+#'     mutate_at(vars(AMP:TOB), as.sir, mo = "microorganism")
 #'
 #'   # to include information about urinary tract infections (UTI)
 #'   data.frame(
@@ -196,7 +218,7 @@
 #'
 #' # For CLEANING existing SIR values ------------------------------------
 #'
-#' as.sir(c("S", "I", "R", "A", "B", "C"))
+#' as.sir(c("S", "SDD", "I", "R", "N", "A", "B", "C"))
 #' as.sir("<= 0.002; S") # will return "S"
 #' sir_data <- as.sir(c(rep("S", 474), rep("I", 36), rep("R", 370)))
 #' is.sir(sir_data)
@@ -224,12 +246,18 @@ as.sir <- function(x, ...) {
   UseMethod("as.sir")
 }
 
+as_sir_structure <- function(x) {
+  structure(factor(as.character(unlist(unname(x))),
+                   levels = c("S", "SDD", "I", "R", "N"),
+                   ordered = TRUE),
+            class = c("sir", "ordered", "factor"))
+}
+
 #' @rdname as.sir
 #' @details `NA_sir_` is a missing value of the new `sir` class, analogous to e.g. base \R's [`NA_character_`][base::NA].
+#' @format NULL
 #' @export
-NA_sir_ <- set_clean_class(factor(NA_character_, levels = c("S", "I", "R"), ordered = TRUE),
-  new_class = c("sir", "ordered", "factor")
-)
+NA_sir_ <- as_sir_structure(NA_character_)
 
 #' @rdname as.sir
 #' @export
@@ -237,12 +265,7 @@ is.sir <- function(x) {
   if (inherits(x, "data.frame")) {
     unname(vapply(FUN.VALUE = logical(1), x, is.sir))
   } else {
-    rsi <- inherits(x, "rsi")
-    sir <- inherits(x, "sir")
-    if (isTRUE(rsi) && message_not_thrown_before("is.sir-rsi")) {
-      deprecation_warning(extra_msg = "The 'rsi' class has been replaced with 'sir'. Transform your 'rsi' columns to 'sir' with `as.sir()`, e.g.:\n  your_data %>% mutate_if(is.rsi, as.sir)")
-    }
-    isTRUE(rsi) || isTRUE(sir)
+    isTRUE(inherits(x, "sir"))
   }
 }
 
@@ -272,9 +295,9 @@ is_sir_eligible <- function(x, threshold = 0.05) {
   %in% class(x))) {
     # no transformation needed
     return(FALSE)
-  } else if (all(x %in% c("S", "I", "R", NA)) & !all(is.na(x))) {
+  } else if (all(x %in% c("S", "SDD", "I", "R", "N", NA)) & !all(is.na(x))) {
     return(TRUE)
-  } else if (!any(c("S", "I", "R") %in% x, na.rm = TRUE) & !all(is.na(x))) {
+  } else if (!any(c("S", "SDD", "I", "R", "N") %in% x, na.rm = TRUE) & !all(is.na(x))) {
     return(FALSE)
   } else {
     x <- x[!is.na(x) & !is.null(x) & !x %in% c("", "-", "NULL")]
@@ -302,17 +325,19 @@ is_sir_eligible <- function(x, threshold = 0.05) {
   }
 }
 
+#' @rdname as.sir
 #' @export
+#' @param S,I,R,N,SDD a case-independent [regular expression][base::regex] to translate input to this result. This regular expression will be run *after* all non-letters are removed from the input.
 # extra param: warn (logical, to never throw a warning)
-as.sir.default <- function(x, ...) {
+as.sir.default <- function(x, S = "^(S|U)+$", I = "^(I|H)+$", R = "^(R)+$", N = "^(N|V)+$", SDD = "^(SDD|D)+$", ...) {
   if (inherits(x, "sir")) {
-    return(x)
+    return(as_sir_structure(x))
   }
 
   x.bak <- x
   x <- as.character(x) # this is needed to prevent the vctrs pkg from throwing an error
 
-  if (inherits(x.bak, c("integer", "numeric", "double")) && all(x %in% c(1:3, NA))) {
+  if (inherits(x.bak, c("numeric", "integer")) && all(x %in% c(1:3, NA))) {
     # support haven package for importing e.g., from SPSS - it adds the 'labels' attribute
     lbls <- attributes(x.bak)$labels
     if (!is.null(lbls) && all(c("S", "I", "R") %in% names(lbls)) && all(c(1:3) %in% lbls)) {
@@ -324,12 +349,12 @@ as.sir.default <- function(x, ...) {
       x[x.bak == 2] <- "I"
       x[x.bak == 3] <- "R"
     }
-  } else if (inherits(x.bak, "character") && all(x %in% c("1", "2", "3", "S", "I", "R", NA_character_))) {
+  } else if (inherits(x.bak, "character") && all(x %in% c("1", "2", "3", c("S", "SDD", "I", "R", "N"), NA_character_))) {
     x[x.bak == "1"] <- "S"
     x[x.bak == "2"] <- "I"
     x[x.bak == "3"] <- "R"
-  } else if (!all(is.na(x)) && !identical(levels(x), c("S", "I", "R")) && !all(x %in% c("S", "I", "R", NA))) {
-    if (all(x %unlike% "(R|S|I)", na.rm = TRUE)) {
+  } else if (!all(is.na(x)) && !identical(levels(x), c("S", "SDD", "I", "R", "N")) && !all(x %in% c("S", "SDD", "I", "R", "N", NA))) {
+    if (all(x %unlike% "(S|I|R)", na.rm = TRUE)) {
       # check if they are actually MICs or disks
       if (all_valid_mics(x)) {
         warning_("in `as.sir()`: the input seems to contain MIC values. You can transform them with `as.mic()` before running `as.sir()` to interpret them.")
@@ -365,23 +390,14 @@ as.sir.default <- function(x, ...) {
     x[x %like% "([^a-z]|^)res(is(tant)?)?"] <- "R"
     x[x %like% "([^a-z]|^)sus(cep(tible)?)?"] <- "S"
     x[x %like% "([^a-z]|^)int(er(mediate)?)?|incr.*exp"] <- "I"
-    # remove other invalid characters
-    # set to capitals
-    x <- toupper(x)
     x <- gsub("[^A-Z]+", "", x, perl = TRUE)
-    # CLSI uses SDD for "susceptible dose-dependent"
-    x <- gsub("SDD", "I", x, fixed = TRUE)
-    # some labs now report "H" instead of "I" to not interfere with EUCAST prior to 2019
-    x <- gsub("H", "I", x, fixed = TRUE)
-    # MIPS uses D for Dose-dependent (which is I, but it will throw a note)
-    x <- gsub("D", "I", x, fixed = TRUE)
-    # MIPS uses U for "susceptible urine"
-    x <- gsub("U", "S", x, fixed = TRUE)
-    # in cases of "S;S" keep S, but in case of "S;I" make it NA
-    x <- gsub("^S+$", "S", x)
-    x <- gsub("^I+$", "I", x)
-    x <- gsub("^R+$", "R", x)
-    x[!x %in% c("S", "I", "R")] <- NA_character_
+    # apply regexes set by user
+    x[x %like% S] <- "S"
+    x[x %like% I] <- "I"
+    x[x %like% R] <- "R"
+    x[x %like% N] <- "N"
+    x[x %like% SDD] <- "SDD"
+    x[!x %in% c("S", "SDD", "I", "R", "N")] <- NA_character_
     na_after <- length(x[is.na(x) | x == ""])
 
     if (!isFALSE(list(...)$warn)) { # so as.sir(..., warn = FALSE) will never throw a warning
@@ -401,24 +417,10 @@ as.sir.default <- function(x, ...) {
           call = FALSE
         )
       }
-      if (any(toupper(x.bak[!is.na(x.bak)]) == "U") && message_not_thrown_before("as.sir", "U")) {
-        warning_("in `as.sir()`: 'U' was interpreted as 'S', following some laboratory systems")
-      }
-      if (any(toupper(x.bak[!is.na(x.bak)]) == "D") && message_not_thrown_before("as.sir", "D")) {
-        warning_("in `as.sir()`: 'D' (dose-dependent) was interpreted as 'I', following some laboratory systems")
-      }
-      if (any(toupper(x.bak[!is.na(x.bak)]) == "SDD") && message_not_thrown_before("as.sir", "SDD")) {
-        warning_("in `as.sir()`: 'SDD' (susceptible dose-dependent, coined by CLSI) was interpreted as 'I' to comply with EUCAST's 'I'")
-      }
-      if (any(toupper(x.bak[!is.na(x.bak)]) == "H") && message_not_thrown_before("as.sir", "H")) {
-        warning_("in `as.sir()`: 'H' was interpreted as 'I', following some laboratory systems")
-      }
     }
   }
 
-  set_clean_class(factor(x, levels = c("S", "I", "R"), ordered = TRUE),
-    new_class = c("sir", "ordered", "factor")
-  )
+  as_sir_structure(x)
 }
 
 #' @rdname as.sir
@@ -434,6 +436,7 @@ as.sir.mic <- function(x,
                        include_screening = getOption("AMR_include_screening", FALSE),
                        include_PKPD = getOption("AMR_include_PKPD", TRUE),
                        breakpoint_type = getOption("AMR_breakpoint_type", "human"),
+                       host = NULL,
                        ...) {
   as_sir_method(
     method_short = "mic",
@@ -449,6 +452,7 @@ as.sir.mic <- function(x,
     include_screening = include_screening,
     include_PKPD = include_PKPD,
     breakpoint_type = breakpoint_type,
+    host = host,
     ...
   )
 }
@@ -465,6 +469,7 @@ as.sir.disk <- function(x,
                         include_screening = getOption("AMR_include_screening", FALSE),
                         include_PKPD = getOption("AMR_include_PKPD", TRUE),
                         breakpoint_type = getOption("AMR_breakpoint_type", "human"),
+                        host = NULL,
                         ...) {
   as_sir_method(
     method_short = "disk",
@@ -480,6 +485,7 @@ as.sir.disk <- function(x,
     include_screening = include_screening,
     include_PKPD = include_PKPD,
     breakpoint_type = breakpoint_type,
+    host = NULL,
     ...
   )
 }
@@ -496,7 +502,8 @@ as.sir.data.frame <- function(x,
                               reference_data = AMR::clinical_breakpoints,
                               include_screening = getOption("AMR_include_screening", FALSE),
                               include_PKPD = getOption("AMR_include_PKPD", TRUE),
-                              breakpoint_type = getOption("AMR_breakpoint_type", "human")) {
+                              breakpoint_type = getOption("AMR_breakpoint_type", "human"),
+                              host = NULL) {
   meet_criteria(x, allow_class = "data.frame") # will also check for dimensions > 0
   meet_criteria(col_mo, allow_class = "character", is_in = colnames(x), allow_NULL = TRUE)
   meet_criteria(guideline, allow_class = "character", has_length = 1)
@@ -507,7 +514,7 @@ as.sir.data.frame <- function(x,
   meet_criteria(include_screening, allow_class = "logical", has_length = 1)
   meet_criteria(include_PKPD, allow_class = "logical", has_length = 1)
   meet_criteria(breakpoint_type, allow_class = "character", is_in = reference_data$type, has_length = 1)
-
+  meet_criteria(host, allow_class = c("character", "factor"), allow_NULL = TRUE, allow_NA = TRUE)
   x.bak <- x
   for (i in seq_len(ncol(x))) {
     # don't keep factors, overwriting them is hard
@@ -521,15 +528,26 @@ as.sir.data.frame <- function(x,
   if (is.null(col_mo)) {
     col_mo <- search_type_in_df(x = x, type = "mo", info = FALSE)
   }
-
+  
+  # -- host
+  if (breakpoint_type == "animal") {
+    if (is.null(host)) {
+      host <- search_type_in_df(x = x, type = "host", add_col_prefix = FALSE)
+    } else if (length(host) == 1 && as.character(host) %in% colnames(x)) {
+      host <- x[[as.character(host)]]
+    }
+  } else {
+    host <- breakpoint_type
+  }
+  
   # -- UTIs
   col_uti <- uti
   if (is.null(col_uti)) {
-    col_uti <- search_type_in_df(x = x, type = "uti")
+    col_uti <- search_type_in_df(x = x, type = "uti", add_col_prefix = FALSE)
   }
   if (!is.null(col_uti)) {
     if (is.logical(col_uti)) {
-      # already a [logical] vector as input
+      # already a logical vector as input
       if (length(col_uti) == 1) {
         uti <- rep(col_uti, NROW(x))
       } else {
@@ -639,6 +657,7 @@ as.sir.data.frame <- function(x,
           include_screening = include_screening,
           include_PKPD = include_PKPD,
           breakpoint_type = breakpoint_type,
+          host = host,
           is_data.frame = TRUE
         )
     } else if (types[i] == "disk") {
@@ -657,16 +676,17 @@ as.sir.data.frame <- function(x,
           include_screening = include_screening,
           include_PKPD = include_PKPD,
           breakpoint_type = breakpoint_type,
+          host = host,
           is_data.frame = TRUE
         )
     } else if (types[i] == "sir") {
       show_message <- FALSE
       ab <- ab_cols[i]
       ab_coerced <- suppressWarnings(as.ab(ab))
-      if (!all(x[, ab_cols[i], drop = TRUE] %in% c("S", "I", "R", NA), na.rm = TRUE)) {
+      if (!all(x[, ab_cols[i], drop = TRUE] %in% c("S", "SDD", "I", "R", "N", NA), na.rm = TRUE)) {
         show_message <- TRUE
         # only print message if values are not already clean
-        message_("=> Cleaning values in column '", font_bold(ab), "' (",
+        message_("Cleaning values in column '", font_bold(ab), "' (",
           ifelse(ab_coerced != toupper(ab), paste0(ab_coerced, ", "), ""),
           ab_name(ab_coerced, tolower = TRUE), ")... ",
           appendLF = FALSE,
@@ -675,7 +695,7 @@ as.sir.data.frame <- function(x,
       } else if (!is.sir(x.bak[, ab_cols[i], drop = TRUE])) {
         show_message <- TRUE
         # only print message if class not already set
-        message_("=> Assigning class 'sir' to already clean column '", font_bold(ab), "' (",
+        message_("Assigning class 'sir' to already clean column '", font_bold(ab), "' (",
           ifelse(ab_coerced != toupper(ab), paste0(ab_coerced, ", "), ""),
           ab_name(ab_coerced, tolower = TRUE, language = NULL), ")... ",
           appendLF = FALSE,
@@ -684,7 +704,7 @@ as.sir.data.frame <- function(x,
       }
       x[, ab_cols[i]] <- as.sir.default(x = as.character(x[, ab_cols[i], drop = TRUE]))
       if (show_message == TRUE) {
-        message_(" OK.", add_fn = list(font_green), as_note = FALSE)
+        message(font_green_bg(" OK "))
       }
     }
   }
@@ -714,6 +734,23 @@ get_guideline <- function(guideline, reference_data) {
   guideline_param
 }
 
+convert_host <- function(x, lang = get_AMR_locale()) {
+  x <- trimws2(tolower(as.character(x)))
+  x_out <- rep(NA_character_, length(x))
+  x_out[trimws2(tolower(x)) == "human"] <- "human"
+  x_out[trimws2(tolower(x)) == "ecoff"] <- "ecoff"
+  # this order is based on: clinical_breakpoints |> filter(type == "animal") |> count(host, sort = TRUE)
+  x_out[is.na(x_out) & (x %like% "dog|canine" | x %like% translate_AMR("dog|dogs|canine", lang))] <- "dogs"
+  x_out[is.na(x_out) & (x %like% "cattle|bovine" | x %like% translate_AMR("cattle|bovine", lang))] <- "cattle"
+  x_out[is.na(x_out) & (x %like% "swine|suida(e)?" | x %like% translate_AMR("swine|swines", lang))] <- "swine"
+  x_out[is.na(x_out) & (x %like% "cat|feline" | x %like% translate_AMR("cat|cats|feline", lang))] <- "cats"
+  x_out[is.na(x_out) & (x %like% "horse|equine" | x %like% translate_AMR("horse|horses|equine", lang))] <- "horse"
+  x_out[is.na(x_out) & (x %like% "aqua|fish" | x %like% translate_AMR("aquatic|fish", lang))] <- "aquatic"
+  x_out[is.na(x_out) & (x %like% "bird|chicken|poultry|avia" | x %like% translate_AMR("bird|birds|poultry", lang))] <- "poultry"
+  x_out[x_out == "ecoff"] <- "ECOFF"
+  x_out
+}
+
 as_sir_method <- function(method_short,
                           method_long,
                           x,
@@ -727,12 +764,13 @@ as_sir_method <- function(method_short,
                           include_screening,
                           include_PKPD,
                           breakpoint_type,
+                          host,
                           ...) {
   meet_criteria(x, allow_NA = TRUE, .call_depth = -2)
-  meet_criteria(mo, allow_class = c("mo", "character"), allow_NULL = TRUE, .call_depth = -2)
-  meet_criteria(ab, allow_class = c("ab", "character"), has_length = 1, .call_depth = -2)
+  meet_criteria(mo, allow_class = c("mo", "character"), has_length = c(1, length(x)), allow_NULL = TRUE, .call_depth = -2)
+  meet_criteria(ab, allow_class = c("ab", "character"), has_length = c(1, length(x)), .call_depth = -2)
   meet_criteria(guideline, allow_class = "character", has_length = 1, .call_depth = -2)
-  meet_criteria(uti, allow_class = "logical", has_length = c(1, length(x)), allow_NULL = TRUE, allow_NA = TRUE, .call_depth = -2)
+  meet_criteria(uti, allow_class = c("logical", "character"), has_length = c(1, length(x)), allow_NULL = TRUE, allow_NA = TRUE, .call_depth = -2)
   meet_criteria(conserve_capped_values, allow_class = "logical", has_length = 1, .call_depth = -2)
   meet_criteria(add_intrinsic_resistance, allow_class = "logical", has_length = 1, .call_depth = -2)
   meet_criteria(reference_data, allow_class = "data.frame", .call_depth = -2)
@@ -740,44 +778,88 @@ as_sir_method <- function(method_short,
   meet_criteria(include_PKPD, allow_class = "logical", has_length = 1, .call_depth = -2)
   check_reference_data(reference_data, .call_depth = -2)
   meet_criteria(breakpoint_type, allow_class = "character", is_in = reference_data$type, has_length = 1, .call_depth = -2)
-
+  meet_criteria(host, allow_class = c("character", "factor"), allow_NULL = TRUE, allow_NA = TRUE, .call_depth = -2)
+  
+  # backward compatibilty
+  dots <- list(...)
+  dots <- dots[which(!names(dots) %in% c("warn", "mo.bak", "is_data.frame"))]
+  if (length(dots) != 0) {
+    warning_("These arguments in `as.sir()` are no longer used: ", vector_and(names(dots), quotes = "`"), ".", call = FALSE)
+  }
+  
   guideline_coerced <- get_guideline(guideline, reference_data)
   
+  if (breakpoint_type == "animal") {
+    if (is.null(host)) {
+      host <- AMR_env$host_preferred_order[1]
+      if (message_not_thrown_before("as.sir", "host_missing")) {
+        message_("Animal hosts not set in `host`, assuming `host = \"", host, "\"`, since these have the highest breakpoint availability.\n\n")  
+      }
+    }
+  } else {
+    if (!is.null(host) && !all(toupper(as.character(host)) %in% c("HUMAN", "ECOFF"))) {
+      if (message_not_thrown_before("as.sir", "assumed_breakpoint_animal")) {
+        message_("Assuming `breakpoint_type = \"animal\"`, since `host` is set.", ifelse(guideline_coerced %like% "EUCAST", " Do you also need to set `guideline = \"CLSI\"`?", ""), "\n\n")
+      }
+      breakpoint_type <- "animal"
+    } else {
+      host <- breakpoint_type
+    }
+  }
+  host <- convert_host(host)
+  
   if (message_not_thrown_before("as.sir", "sir_interpretation_history")) {
-    message_("Run `sir_interpretation_history()` afterwards to retrieve a logbook with all the details of the breakpoint interpretations. Note that some microorganisms might not have breakpoints for each antimicrobial drug in ", guideline_coerced, ".\n\n")  
+    message_("Run `sir_interpretation_history()` afterwards to retrieve a logbook with all the details of the breakpoint interpretations. Note that some ", ifelse(breakpoint_type == "animal", "animal hosts and ", ""), "microorganisms might not have breakpoints for each antimicrobial drug in ", guideline_coerced, ".\n\n")
+  }
+  if (breakpoint_type == "animal" && message_not_thrown_before("as.sir", "host_preferred_order")) {
+    message_("Please note that in the absence of specific veterinary breakpoints for certain animal hosts, breakpoints for dogs, cattle, swine, cats, horse, aquatic, and poultry, in that order, are used as substitutes.\n\n")
   }
   
-  # for dplyr's across()
-  cur_column_dplyr <- import_fn("cur_column", "dplyr", error_on_fail = FALSE)
-  if (!is.null(cur_column_dplyr) && tryCatch(is.data.frame(get_current_data("ab", call = 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
-    )
-  }
+  current_df <- tryCatch(get_current_data(NA, 0), error = function(e) NULL)
 
-  # for auto-determining mo
-  mo_var_found <- ""
-  if (is.null(mo)) {
-    tryCatch(
-      {
-        df <- get_current_data(arg_name = "mo", call = -3) # will return an error if not found
-        mo <- NULL
-        try(
-          {
-            mo <- suppressMessages(search_type_in_df(df, "mo"))
-          },
-          silent = TRUE
-        )
-        if (!is.null(df) && !is.null(mo) && is.data.frame(df)) {
-          mo_var_found <- paste0(" based on column '", font_bold(mo), "'")
-          mo <- df[, mo, drop = TRUE]
+  # get ab
+  if (!is.null(current_df) && length(ab) == 1 && ab %in% colnames(current_df) && any(current_df[[ab]] %like% "[A-Z]", na.rm = TRUE)) {
+    ab <- current_df[[ab]]
+  } else if (length(ab) != length(x)) {
+    # for dplyr's across()
+    cur_column_dplyr <- import_fn("cur_column", "dplyr", error_on_fail = FALSE)
+    if (!is.null(cur_column_dplyr) && is.data.frame(current_df)) {
+      # try to get current column, which will only be available when in across()
+      ab <- tryCatch(cur_column_dplyr(),
+                     error = function(e) ab
+      )
+    }
+  }
+  
+  # get mo
+  if (!is.null(current_df) && length(mo) == 1 && mo %in% colnames(current_df)) {
+    mo_var_found <- paste0(" based on column '", font_bold(mo), "'")
+    mo <- current_df[[mo]]
+  } else if (length(mo) != length(x)) {
+    mo_var_found <- ""
+    if (is.null(mo)) {
+      tryCatch(
+        {
+          df <- get_current_data(arg_name = "mo", call = -3) # will return an error if not found
+          mo <- NULL
+          try(
+            {
+              mo <- suppressMessages(search_type_in_df(df, "mo", add_col_prefix = FALSE))
+            },
+            silent = TRUE
+          )
+          if (!is.null(df) && !is.null(mo) && is.data.frame(df)) {
+            mo_var_found <- paste0(" based on column '", font_bold(mo), "'")
+            mo <- df[, mo, drop = TRUE]
+          }
+        },
+        error = function(e) {
+          mo <- NULL
         }
-      },
-      error = function(e) {
-        mo <- NULL
-      }
-    )
+      )
+    }
+  } else {
+    mo_var_found <- ""
   }
   if (is.null(mo)) {
     stop_("No information was supplied about the microorganisms (missing argument `mo` and no column of class 'mo' found). See ?as.sir.\n\n",
@@ -786,6 +868,32 @@ as_sir_method <- function(method_short,
       call = FALSE
     )
   }
+  
+  # get uti
+  if (!is.null(current_df) && length(uti) == 1 && uti %in% colnames(current_df)) {
+    uti <- current_df[[uti]]
+  } else if (length(uti) != length(x)) {
+    if (is.null(uti)) {
+      tryCatch(
+        {
+          df <- get_current_data(arg_name = "uti", call = -3) # will return an error if not found
+          uti <- NULL
+          try(
+            {
+              uti <- suppressMessages(search_type_in_df(df, "uti", add_col_prefix = FALSE))
+            },
+            silent = TRUE
+          )
+          if (!is.null(df) && !is.null(uti) && is.data.frame(df)) {
+            uti <- df[, uti, drop = TRUE]
+          }
+        },
+        error = function(e) {
+          uti <- NULL
+        }
+      )
+    }
+  }
 
   if (length(ab) == 1 && ab %like% paste0("as.", method_short)) {
     stop_("No unambiguous name was supplied about the antibiotic (argument `ab`). See ?as.sir.", call = FALSE)
@@ -800,9 +908,9 @@ as_sir_method <- function(method_short,
   }
   # be sure to take current taxonomy, as the 'clinical_breakpoints' data set only contains current taxonomy
   mo <- suppressWarnings(suppressMessages(as.mo(mo, keep_synonyms = FALSE, info = FALSE)))
-  if (is.na(ab)) {
-    message_("Returning NAs for unknown antibiotic: '", font_bold(ab.bak),
-      "'. Rename this column to a valid name or code, and check the output with `as.ab()`.",
+  if (all(is.na(ab))) {
+    message_("Returning NAs for unknown antibiotic: ", vector_and(ab.bak, sort = FALSE, quotes = TRUE),
+      ". Rename this column to a valid name or code, and check the output with `as.ab()`.",
       add_fn = font_red,
       as_note = FALSE
     )
@@ -811,44 +919,44 @@ as_sir_method <- function(method_short,
   if (length(mo) == 1) {
     mo <- rep(mo, length(x))
   }
+  if (length(ab) == 1) {
+    ab <- rep(ab, length(x))
+  }
+  if (length(host) == 1) {
+    host <- rep(host, length(x))
+  }
   if (is.null(uti)) {
     uti <- NA
   }
   if (length(uti) == 1) {
     uti <- rep(uti, length(x))
   }
-
+  uti[is.na(uti)] <- FALSE
   if (isTRUE(add_intrinsic_resistance) && guideline_coerced %unlike% "EUCAST") {
     if (message_not_thrown_before("as.sir", "intrinsic")) {
       warning_("in `as.sir()`: using 'add_intrinsic_resistance' is only useful when using EUCAST guidelines, since the rules for intrinsic resistance are based on EUCAST.")
     }
   }
 
-  agent_formatted <- paste0("'", font_bold(ab.bak), "'")
+  agent_formatted <- paste0("'", font_bold(ab.bak, collapse = NULL), "'")
   agent_name <- ab_name(ab, tolower = TRUE, language = NULL)
-  if (generalise_antibiotic_name(ab.bak) == generalise_antibiotic_name(agent_name)) {
-    agent_formatted <- paste0(
-      agent_formatted,
-      " (", ab, ")"
-    )
-  } else if (generalise_antibiotic_name(ab) != generalise_antibiotic_name(agent_name)) {
-    agent_formatted <- paste0(
-      agent_formatted,
-      " (", ifelse(ab.bak == ab, "",
-        paste0(ab, ", ")
-      ), agent_name, ")"
-    )
-  }
-  
-  # this intro text will also be printed in the progress bar in the `progress` package is installed
+  same_ab <- generalise_antibiotic_name(ab) == generalise_antibiotic_name(agent_name)
+  same_ab.bak <- generalise_antibiotic_name(ab.bak) == generalise_antibiotic_name(agent_name)
+  agent_formatted[same_ab.bak] <- paste0(agent_formatted[same_ab.bak], " (", ab[same_ab.bak], ")")
+  agent_formatted[!same_ab.bak & !same_ab] <- paste0(agent_formatted[!same_ab.bak & !same_ab],
+                                                    " (", ifelse(ab.bak[!same_ab.bak & !same_ab] == ab[!same_ab.bak & !same_ab],
+                                                                 "",
+                                                                 paste0(ab[!same_ab.bak & !same_ab], ", ")),
+                                                    agent_name[!same_ab.bak & !same_ab],
+                                                    ")")
+  # this intro text will also be printed in the progress bar if the `progress` package is installed
   intro_txt <- paste0("Interpreting ", method_long, ": ", ifelse(isTRUE(list(...)$is_data.frame), "column ", ""),
-                      agent_formatted,
+                      ifelse(length(unique(agent_formatted)) == 1, unique(agent_formatted), paste0("for ", vector_and(ab, quotes = FALSE, sort = FALSE))),
                       mo_var_found,
                       ifelse(identical(reference_data, AMR::clinical_breakpoints),
                              paste0(", ", font_bold(guideline_coerced)),
                              ""),
                       "... ")
-  message_(intro_txt, appendLF = FALSE, as_note = FALSE)
   
   msg_note <- function(messages) {
     messages <- unique(messages)
@@ -865,22 +973,6 @@ as_sir_method <- function(method_short,
 
   metadata_mo <- get_mo_uncertainties()
 
-  df <- data.frame(
-    values = x,
-    mo = mo,
-    result = NA_sir_,
-    uti = uti,
-    stringsAsFactors = FALSE
-  )
-  if (method == "mic") {
-    # when as.sir.mic is called directly
-    df$values <- as.mic(df$values)
-  } else if (method == "disk") {
-    # when as.sir.disk is called directly
-    df$values <- as.disk(df$values)
-  }
-  df_unique <- unique(df[ , c("mo", "uti"), drop = FALSE])
-
   rise_warning <- FALSE
   rise_note <- FALSE
   method_coerced <- toupper(method)
@@ -888,20 +980,41 @@ as_sir_method <- function(method_short,
   
   if (identical(reference_data, AMR::clinical_breakpoints)) {
     breakpoints <- reference_data %pm>%
-      subset(guideline == guideline_coerced & method == method_coerced & ab == ab_coerced)
-    if (ab_coerced == "AMX" && nrow(breakpoints) == 0) {
-      ab_coerced <- "AMP"
+      subset(guideline == guideline_coerced & method == method_coerced & ab %in% ab_coerced)
+    if (any(ab_coerced == "AMX") && nrow(breakpoints[breakpoints$ab == "AMX", , drop = FALSE]) == 0) {
+      ab_coerced[ab_coerced == "AMX"] <- "AMP"
       breakpoints <- reference_data %pm>%
-        subset(guideline == guideline_coerced & method == method_coerced & ab == ab_coerced)
+        subset(guideline == guideline_coerced & method == method_coerced & ab %in% ab_coerced)
     }
   } else {
     breakpoints <- reference_data %pm>%
-      subset(method == method_coerced & ab == ab_coerced)
+      subset(method == method_coerced & ab %in% ab_coerced)
   }
-
+  
+  # create the unique data frame to be filled to save time
+  df <- data.frame(
+    values = x,
+    mo = mo,
+    ab = ab,
+    result = NA_sir_,
+    uti = uti,
+    host = host,
+    stringsAsFactors = FALSE
+  )
+  
+  if (method == "mic") {
+    # when as.sir.mic is called directly
+    df$values <- as.mic(df$values)
+  } else if (method == "disk") {
+    # when as.sir.disk is called directly
+    df$values <- as.disk(df$values)
+  }
+  df_unique <- unique(df[ , c("mo", "ab", "uti", "host"), drop = FALSE])
+  
+  # get all breakpoints
   breakpoints <- breakpoints %pm>%
     subset(type == breakpoint_type)
-
+  
   if (isFALSE(include_screening)) {
     # remove screening rules from the breakpoints table
     breakpoints <- breakpoints %pm>%
@@ -918,7 +1031,7 @@ as_sir_method <- function(method_short,
     # apparently no breakpoints found
     message(
       paste0(font_rose_bg(" WARNING "), "\n"),
-      font_black(paste0("  ", AMR_env$bullet_icon, " No ", method_coerced, " breakpoints available for ",
+      font_black(paste0("  ", AMR_env$bullet_icon, " No ", guideline_coerced, " ", method_coerced, " breakpoints available for ",
         suppressMessages(suppressWarnings(ab_name(ab_coerced, language = NULL, tolower = TRUE))),
         " (", ab_coerced, ").")))
     
@@ -931,20 +1044,26 @@ as_sir_method <- function(method_short,
     add_intrinsic_resistance_to_AMR_env()
   }
   
+  if (nrow(df_unique) < 10) {
+    # only print intro under 10 items, otherwise progressbar will print this and then it will be printed double
+    message_(intro_txt, appendLF = FALSE, as_note = FALSE)
+  }
   p <- progress_ticker(n = nrow(df_unique), n_min = 10, title = font_blue(intro_txt), only_bar_percent = TRUE)
   has_progress_bar <- !is.null(import_fn("progress_bar", "progress", error_on_fail = FALSE)) && nrow(df_unique) >= 10
   on.exit(close(p))
   
-  # run the rules
+  # run the rules (df_unique is a row combination per mo/ab/uti/host)
   for (i in seq_len(nrow(df_unique))) {
     p$tick()
     mo_current <- df_unique[i, "mo", drop = TRUE]
+    ab_current <- df_unique[i, "ab", drop = TRUE]
+    host_current <- df_unique[i, "host", drop = TRUE]
     uti_current <- df_unique[i, "uti", drop = TRUE]
-    if (is.na(uti_current)) {
+    if (isFALSE(uti_current)) {
       # no preference, so no filter on UTIs
-      rows <- which(df$mo == mo_current)
+      rows <- which(df$mo == mo_current & df$ab == ab_current & df$host == host_current)
     } else {
-      rows <- which(df$mo == mo_current & df$uti == uti_current)
+      rows <- which(df$mo == mo_current & df$ab == ab_current & df$host == host_current & df$uti == uti_current)
     }
     values <- df[rows, "values", drop = TRUE]
     new_sir <- rep(NA_sir_, length(rows))
@@ -966,39 +1085,61 @@ as_sir_method <- function(method_short,
     # formatted for notes
     mo_formatted <- mo_current_name
     if (!mo_current_rank %in% c("kingdom", "phylum", "class", "order")) {
-      mo_formatted <- font_italic(mo_formatted)
+      mo_formatted <- font_italic(mo_formatted, collapse = NULL)
     }
     ab_formatted <- paste0(
-      suppressMessages(suppressWarnings(ab_name(ab_coerced, language = NULL, tolower = TRUE))),
-      " (", ab_coerced, ")"
+      suppressMessages(suppressWarnings(ab_name(ab_current, language = NULL, tolower = TRUE))),
+      " (", ab_current, ")"
     )
-
-    # gather all available breakpoints for current MO and sort on taxonomic rank
-    # (this will prefer species breakpoints over order breakpoints)
+    
+   
+    # gather all available breakpoints for current MO
     breakpoints_current <- breakpoints %pm>%
+      subset(ab == ab_current) %pm>%
       subset(mo %in% c(
         mo_current, mo_current_genus, mo_current_family,
         mo_current_order, mo_current_class,
         mo_current_species_group,
         mo_current_other
       ))
-
-    if (is.na(unique(uti_current))) {
+    # set the host index according to most available breakpoints (see R/zzz.R where this is set in the pkg environment)
+    breakpoints_current$host_index <- match(breakpoints_current$host, c("human", "ECOFF", AMR_env$host_preferred_order))
+    
+    # sort on host and taxonomic rank
+    # (this will e.g. prefer 'species' breakpoints over 'order' breakpoints)
+    if (all(uti_current == FALSE, na.rm = TRUE)) {
       breakpoints_current <- breakpoints_current %pm>%
-        # this will put UTI = FALSE first, then UTI = TRUE, then UTI = NA
-        pm_arrange(rank_index, uti) # 'uti' is a column in data set 'clinical_breakpoints'  
-    } else if (unique(uti_current) == TRUE) {
+        # this will put UTI = FALSE first, then UTI = NA, then UTI = TRUE
+        pm_mutate(uti_index = ifelse(uti == FALSE, 1, 
+                                     ifelse(is.na(uti), 2,
+                                            3))) %pm>%
+        # be as specific as possible (i.e. prefer species over genus):
+        pm_arrange(host_index, rank_index, uti_index)
+    } else if (all(uti_current == TRUE, na.rm = TRUE)) {
       breakpoints_current <- breakpoints_current %pm>%
         subset(uti == TRUE) %pm>%
         # be as specific as possible (i.e. prefer species over genus):
-        pm_arrange(rank_index)
-    } else if (unique(uti_current) == FALSE) {
-      breakpoints_current <- breakpoints_current %pm>%
-        subset(uti == FALSE) %pm>%
-        # be as specific as possible (i.e. prefer species over genus):
-        pm_arrange(rank_index)
+        pm_arrange(host_index, rank_index)
     }
-
+    
+    if (NROW(breakpoints_current) == 0) {
+      # no note about missing breakpoints - it's already in the header before the interpretation starts
+      next
+    }
+    
+    # veterinary host check
+    host_current <- unique(df_unique[i, "host", drop = TRUE])[1]
+    breakpoints_current$host_match <- breakpoints_current$host == host_current
+    if (breakpoint_type == "animal") {
+      if (any(breakpoints_current$host_match == TRUE, na.rm = TRUE)) {
+        breakpoints_current <- breakpoints_current %pm>%
+          subset(host_match == TRUE)
+      } else {
+        # no breakpoint found for this host, so sort on mostly available guidelines
+        msgs <- c(msgs, paste0("No ", guideline_coerced, " breakpoints for ", font_bold(host_current), " available for ", ab_formatted, " in ", mo_formatted, " - using ", font_bold(breakpoints_current$host[1]), " breakpoints instead."))
+      }
+    }
+ 
     # throw notes for different body sites
     site <- breakpoints_current[1L, "site", drop = FALSE] # this is the one we'll take
     if (is.na(site)) {
@@ -1012,15 +1153,12 @@ as_sir_method <- function(method_short,
       rise_warning <- TRUE
     } else if (nrow(breakpoints_current) > 1 && length(unique(breakpoints_current$site)) > 1 && any(is.na(uti_current)) && all(c(TRUE, FALSE) %in% breakpoints_current$uti, na.rm = TRUE) && message_not_thrown_before("as.sir", "siteUTI", mo_current, ab_coerced)) {
       # both UTI and Non-UTI breakpoints available
-      msgs <- c(msgs, paste0("Breakpoints for UTI ", font_underline("and"), " non-UTI available for ", ab_formatted, " in ", mo_formatted, " - assuming ", site, ". Use argument `uti` to set which isolates are from urine. See `?as.sir`."))
+      msgs <- c(msgs, paste0("Breakpoints for UTI ", font_bold("and"), " non-UTI available for ", ab_formatted, " in ", mo_formatted, " - assuming ", site, ". Use argument `uti` to set which isolates are from urine. See `?as.sir`."))
       breakpoints_current <- breakpoints_current %pm>%
         pm_filter(uti == FALSE)
     } else if (nrow(breakpoints_current) > 1 && length(unique(breakpoints_current$site)) > 1 && all(breakpoints_current$uti == FALSE, na.rm = TRUE) && message_not_thrown_before("as.sir", "siteOther", mo_current, ab_coerced)) {
       # breakpoints for multiple body sites available
       msgs <- c(msgs, paste0("Multiple breakpoints available for ", ab_formatted, " in ", mo_formatted, " - assuming ", site, "."))
-    } else if (nrow(breakpoints_current) == 0) {
-      # # do not note - it's already in the header before the interpretation starts
-      next
     }
     
     # first check if mo is intrinsic resistant
@@ -1072,15 +1210,16 @@ as_sir_method <- function(method_short,
         data.frame(
           datetime = rep(Sys.time(), length(rows)),
           index = rows,
-          ab_user = rep(ab.bak, length(rows)),
+          ab_user = rep(ab.bak[match(ab_current, df$ab)][1], length(rows)),
           mo_user = rep(mo.bak[match(mo_current, df$mo)][1], length(rows)),
-          ab = rep(ab_coerced, length(rows)),
+          ab = rep(ab_current, length(rows)),
           mo = rep(breakpoints_current[, "mo", drop = TRUE], length(rows)),
           input = as.double(values),
           outcome = as.sir(new_sir),
           method = rep(method_coerced, length(rows)),
           breakpoint_S_R = rep(paste0(breakpoints_current[, "breakpoint_S", drop = TRUE], "-", breakpoints_current[, "breakpoint_R", drop = TRUE]), length(rows)),
           guideline = rep(guideline_coerced, length(rows)),
+          host = rep(breakpoints_current[, "host", drop = TRUE], length(rows)),
           ref_table = rep(breakpoints_current[, "ref_tbl", drop = TRUE], length(rows)),
           uti = rep(breakpoints_current[, "uti", drop = TRUE], length(rows)),
           stringsAsFactors = FALSE
@@ -1145,8 +1284,10 @@ pillar_shaft.sir <- function(x, ...) {
     # colours will anyway not work when has_colour() == FALSE,
     # but then the indentation should also not be applied
     out[is.na(x)] <- font_grey("  NA")
+    out[x == "N"] <- font_grey_bg("  N  ")
     out[x == "S"] <- font_green_bg("  S  ")
     out[x == "I"] <- font_orange_bg("  I  ")
+    out[x == "SDD"] <- font_orange_bg(" SDD ")
     if (is_dark()) {
       out[x == "R"] <- font_red_bg("  R  ")
     } else {

R/sir_calc.R

@@ -41,7 +41,7 @@ sir_calc <- function(...,
                      as_percent = FALSE,
                      only_all_tested = FALSE,
                      only_count = FALSE) {
-  meet_criteria(ab_result, allow_class = c("character", "numeric", "integer"), has_length = c(1, 2, 3))
+  meet_criteria(ab_result, allow_class = c("character", "numeric", "integer"), has_length = c(1:5))
   meet_criteria(minimum, allow_class = c("numeric", "integer"), has_length = 1, is_positive_or_zero = TRUE, is_finite = TRUE)
   meet_criteria(as_percent, allow_class = "logical", has_length = 1)
   meet_criteria(only_all_tested, allow_class = "logical", has_length = 1)
@@ -135,13 +135,20 @@ sir_calc <- function(...,
 
     x_transposed <- as.list(as.data.frame(t(x), stringsAsFactors = FALSE))
     if (isTRUE(only_all_tested)) {
+      get_integers <- function(x) {
+        ints <- rep(NA_integer_, length(x))
+        ints[x == "S"] <- 1L
+        ints[x %in% c("SDD", "I")] <- 2L
+        ints[x == "R"] <- 3L
+        ints
+      }
       # no NAs in any column
       y <- apply(
-        X = as.data.frame(lapply(x, as.integer), stringsAsFactors = FALSE),
+        X = as.data.frame(lapply(x, get_integers), stringsAsFactors = FALSE),
         MARGIN = 1,
         FUN = min
       )
-      numerator <- sum(as.integer(y) %in% as.integer(ab_result), na.rm = TRUE)
+      numerator <- sum(!is.na(y) & y %in% get_integers(ab_result), na.rm = TRUE)
       denominator <- sum(vapply(FUN.VALUE = logical(1), x_transposed, function(y) !(anyNA(y))))
     } else {
       # may contain NAs in any column
@@ -223,7 +230,7 @@ sir_calc_df <- function(type, # "proportion", "count" or "both"
                         combine_SI = TRUE,
                         confidence_level = 0.95) {
   meet_criteria(type, is_in = c("proportion", "count", "both"), has_length = 1)
-  meet_criteria(data, allow_class = "data.frame", contains_column_class = c("sir", "rsi"))
+  meet_criteria(data, allow_class = "data.frame", contains_column_class = "sir")
   meet_criteria(translate_ab, allow_class = c("character", "logical"), has_length = 1, allow_NA = TRUE)
   language <- validate_language(language)
   meet_criteria(minimum, allow_class = c("numeric", "integer"), has_length = 1, is_positive_or_zero = TRUE, is_finite = TRUE)
@@ -249,7 +256,13 @@ sir_calc_df <- function(type, # "proportion", "count" or "both"
     for (i in seq_len(ncol(data))) {
       if (is.sir(data[, i, drop = TRUE])) {
         data[, i] <- as.character(data[, i, drop = TRUE])
-        data[, i] <- gsub("(I|S)", "SI", data[, i, drop = TRUE])
+        if ("SDD" %in% data[, i, drop = TRUE]) {
+          if (message_not_thrown_before("sir_calc_df", combine_SI, entire_session = TRUE)) {
+            message_("Note that `sir_calc_df()` will also count dose-dependent susceptibility, 'SDD', as 'SI' when `combine_SI = TRUE`. This note will be shown once for this session.", as_note = FALSE)
+          }
+          
+        }
+        data[, i] <- gsub("(I|S|SDD)", "SI", data[, i, drop = TRUE])
       }
     }
   }
@@ -272,9 +285,9 @@ sir_calc_df <- function(type, # "proportion", "count" or "both"
     for (i in seq_len(ncol(.data))) {
       values <- .data[, i, drop = TRUE]
       if (isTRUE(combine_SI)) {
-        values <- factor(values, levels = c("SI", "R"), ordered = TRUE)
+        values <- factor(values, levels = c("SI", "R", "N"), ordered = TRUE)
       } else {
-        values <- factor(values, levels = c("S", "I", "R"), ordered = TRUE)
+        values <- factor(values, levels = c("S", "SDD", "I", "R", "N"), ordered = TRUE)
       }
       col_results <- as.data.frame(as.matrix(table(values)), stringsAsFactors = FALSE)
       col_results$interpretation <- rownames(col_results)
@@ -351,8 +364,10 @@ sir_calc_df <- function(type, # "proportion", "count" or "both"
   } else {
     # don't use as.sir() here, as it would add the class 'sir' and we would like
     # the same data structure as output, regardless of input
-    out$interpretation <- factor(out$interpretation, levels = c("S", "I", "R"), ordered = TRUE)
+    out$interpretation <- factor(out$interpretation, levels = c("S", "SDD", "I", "R", "N"), ordered = TRUE)
   }
+  
+  out <- out[!is.na(out$interpretation), , drop = FALSE]
 
   if (data_has_groups) {
     # ordering by the groups and two more: "antibiotic" and "interpretation"
@@ -373,5 +388,5 @@ sir_calc_df <- function(type, # "proportion", "count" or "both"
 
   rownames(out) <- NULL
   out <- as_original_data_class(out, class(data.bak)) # will remove tibble groups
-  structure(out, class = c("sir_df", "rsi_df", class(out)))
+  structure(out, class = c("sir_df", class(out)))
 }

R/translate.R

@@ -244,6 +244,7 @@ translate_into_language <- function(from,
     # starting with longest pattern, since more general translations are shorter, such as 'Group'
     order(nchar(df_trans$pattern), decreasing = TRUE),
     function(i) {
+      if (df_trans$pattern[i] %like% "[/]") return(df_trans$pattern[i])
       from_unique_translated <<- gsub(
         pattern = df_trans$pattern[i],
         replacement = df_trans[i, lang, drop = TRUE],

R/vctrs.R

@@ -34,7 +34,8 @@
 
 # see https://github.com/tidyverse/dplyr/issues/5955 why this is required
 
-# S3: ab_selector
+# S3: ab_selector ----
+# this does not need a .default method since it's used internally only
 vec_ptype2.character.ab_selector <- function(x, y, ...) {
   x
 }
@@ -45,7 +46,8 @@ vec_cast.character.ab_selector <- function(x, to, ...) {
   unclass(x)
 }
 
-# S3: ab_selector_any_all
+# S3: ab_selector_any_all ----
+# this does not need a .default method since it's used internally only
 vec_ptype2.logical.ab_selector_any_all <- function(x, y, ...) {
   x
 }
@@ -56,12 +58,12 @@ vec_cast.logical.ab_selector_any_all <- function(x, to, ...) {
   unclass(x)
 }
 
-# S3: ab
-vec_ptype2.character.ab <- function(x, y, ...) {
+# S3: ab ----
+vec_ptype2.ab.default <- function (x, y, ..., x_arg = "", y_arg = "") {
   x
 }
-vec_ptype2.ab.character <- function(x, y, ...) {
-  y
+vec_ptype2.ab.ab <- function(x, y, ...) {
+  x
 }
 vec_cast.character.ab <- function(x, to, ...) {
   as.character(x)
@@ -70,12 +72,12 @@ vec_cast.ab.character <- function(x, to, ...) {
   return_after_integrity_check(x, "antimicrobial drug code", as.character(AMR_env$AB_lookup$ab))
 }
 
-# S3: av
-vec_ptype2.character.av <- function(x, y, ...) {
+# S3: av ----
+vec_ptype2.av.default <- function (x, y, ..., x_arg = "", y_arg = "") {
   x
 }
-vec_ptype2.av.character <- function(x, y, ...) {
-  y
+vec_ptype2.av.av <- function(x, y, ...) {
+  x
 }
 vec_cast.character.av <- function(x, to, ...) {
   as.character(x)
@@ -84,12 +86,12 @@ vec_cast.av.character <- function(x, to, ...) {
   return_after_integrity_check(x, "antiviral drug code", as.character(AMR_env$AV_lookup$av))
 }
 
-# S3: mo
-vec_ptype2.character.mo <- function(x, y, ...) {
+# S3: mo ----
+vec_ptype2.mo.default <- function (x, y, ..., x_arg = "", y_arg = "") {
   x
 }
-vec_ptype2.mo.character <- function(x, y, ...) {
-  y
+vec_ptype2.mo.mo <- function(x, y, ...) {
+  x
 }
 vec_cast.character.mo <- function(x, to, ...) {
   as.character(x)
@@ -99,12 +101,18 @@ vec_cast.mo.character <- function(x, to, ...) {
   return_after_integrity_check(x, "microorganism code", as.character(AMR_env$MO_lookup$mo))
 }
 
-# S3: disk
-vec_ptype2.integer.disk <- function(x, y, ...) {
+# S3: disk ----
+vec_ptype_full.disk <- function(x, ...) {
+  "disk"
+}
+vec_ptype_abbr.disk <- function(x, ...) {
+  "dsk"
+}
+vec_ptype2.disk.default <- function (x, y, ..., x_arg = "", y_arg = "") {
   x
 }
-vec_ptype2.disk.integer <- function(x, y, ...) {
-  y
+vec_ptype2.disk.disk <- function(x, y, ...) {
+  x
 }
 vec_cast.integer.disk <- function(x, to, ...) {
   unclass(x)
@@ -125,29 +133,56 @@ vec_cast.disk.character <- function(x, to, ...) {
   as.disk(x)
 }
 
-# S3: mic
+# S3: mic ----
+vec_ptype2.mic.default <- function (x, y, ..., x_arg = "", y_arg = "") {
+  # this will make sure that currently implemented MIC levels are returned
+  as.mic(x)
+}
+vec_ptype2.mic.mic <- function(x, y, ...) {
+  # this will make sure that currently implemented MIC levels are returned
+  as.mic(x)
+}
+vec_cast.mic.mic <- function(x, to, ...) {
+  # this will make sure that currently implemented MIC levels are returned
+  as.mic(x)
+}
 vec_cast.character.mic <- function(x, to, ...) {
   as.character(x)
 }
 vec_cast.double.mic <- function(x, to, ...) {
   as.double(x)
 }
+vec_cast.integer.mic <- function(x, to, ...) {
+  as.integer(x)
+}
+vec_cast.factor.mic <- function(x, to, ...) {
+  factor(as.character(x))
+}
 vec_cast.mic.double <- function(x, to, ...) {
   as.mic(x)
 }
 vec_cast.mic.character <- function(x, to, ...) {
   as.mic(x)
 }
+vec_cast.mic.integer <- function(x, to, ...) {
+  as.mic(x)
+}
+vec_cast.mic.factor <- function(x, to, ...) {
+  as.mic(x)
+}
 vec_math.mic <- function(.fn, x, ...) {
   .fn(as.double(x), ...)
 }
+vec_arith.mic <- function(op, x, y, ...) {
+  vctrs::vec_arith(op, as.double(x), as.double(y))
+}
 
-# S3: sir
-vec_ptype2.character.sir <- function(x, y, ...) {
+# S3: sir ----
+vec_ptype2.sir.default <- function (x, y, ..., x_arg = "", y_arg = "") {
   x
 }
-vec_ptype2.sir.character <- function(x, y, ...) {
-  y
+vec_ptype2.sir.sir <- function(x, y, ...) {
+  x
 }
 vec_cast.character.sir <- function(x, to, ...) {
   as.character(x)

R/whocc.R

@@ -31,13 +31,13 @@
 #'
 #' All antimicrobial drugs and their official names, ATC codes, ATC groups and defined daily dose (DDD) are included in this package, using the WHO Collaborating Centre for Drug Statistics Methodology.
 #' @section WHOCC:
-#' This package contains **all ~550 antibiotic, antimycotic and antiviral drugs** and their Anatomical Therapeutic Chemical (ATC) codes, ATC groups and Defined Daily Dose (DDD) from the World Health Organization Collaborating Centre for Drug Statistics Methodology (WHOCC, <https://www.whocc.no>) and the Pharmaceuticals Community Register of the European Commission (<https://ec.europa.eu/health/documents/community-register/html/reg_hum_atc.htm>).
+#' This package contains **all ~550 antibiotic, antimycotic and antiviral drugs** and their Anatomical Therapeutic Chemical (ATC) codes, ATC groups and Defined Daily Dose (DDD) from the World Health Organization Collaborating Centre for Drug Statistics Methodology (WHOCC, <https://atcddd.fhi.no>) and the Pharmaceuticals Community Register of the European Commission (<https://ec.europa.eu/health/documents/community-register/html/reg_hum_atc.htm>).
 #'
 #' These have become the gold standard for international drug utilisation monitoring and research.
 #'
 #' The WHOCC is located in Oslo at the Norwegian Institute of Public Health and funded by the Norwegian government. The European Commission is the executive of the European Union and promotes its general interest.
 #'
-#' **NOTE: The WHOCC copyright does not allow use for commercial purposes, unlike any other info from this package.** See <https://www.whocc.no/copyright_disclaimer/.>
+#' **NOTE: The WHOCC copyright does not allow use for commercial purposes, unlike any other info from this package.** See <https://atcddd.fhi.no/copyright_disclaimer/.>
 
 #' @name WHOCC
 #' @rdname WHOCC

R/zz_deprecated.R

@@ -27,171 +27,14 @@
 # how to conduct AMR data analysis: https://msberends.github.io/AMR/   #
 # ==================================================================== #
 
-#' Deprecated Functions
-#'
-#' These functions are so-called '[Deprecated]'. **They will be removed in a future release.** Using the functions will give a warning with the name of the function it has been replaced by (if there is one).
-#' @keywords internal
-#' @name AMR-deprecated
-#' @rdname AMR-deprecated
-#' @export
-NA_rsi_ <- set_clean_class(factor(NA_character_, levels = c("S", "I", "R"), ordered = TRUE),
-  new_class = c("rsi", "ordered", "factor")
-)
-#' @rdname AMR-deprecated
-#' @export
-as.rsi <- function(x, ...) {
-  deprecation_warning("as.rsi", "as.sir")
-  UseMethod("as.rsi")
-}
-#' @noRd
-#' @export
-as.rsi.default <- function(...) {
-  as.sir.default(...)
-}
-#' @noRd
-#' @export
-as.rsi.mic <- function(...) {
-  as.sir.mic(...)
-}
-#' @noRd
-#' @export
-as.rsi.disk <- function(...) {
-  as.sir.disk(...)
-}
-#' @noRd
-#' @export
-as.rsi.data.frame <- function(...) {
-  as.sir.data.frame(...)
-}
-
-#' @rdname AMR-deprecated
-#' @export
-facet_rsi <- function(...) {
-  deprecation_warning("facet_rsi", "facet_sir")
-  facet_sir(...)
-}
-#' @rdname AMR-deprecated
-#' @export
-geom_rsi <- function(...) {
-  deprecation_warning("geom_rsi", "geom_sir")
-  geom_sir(...)
-}
-#' @rdname AMR-deprecated
-#' @export
-ggplot_rsi <- function(...) {
-  deprecation_warning("ggplot_rsi", "ggplot_sir")
-  ggplot_sir(...)
-}
-#' @rdname AMR-deprecated
-#' @export
-ggplot_rsi_predict <- function(...) {
-  deprecation_warning("ggplot_rsi_predict", "ggplot_sir_predict")
-  ggplot_sir_predict(...)
-}
-#' @rdname AMR-deprecated
-#' @export
-is.rsi <- function(...) {
-  # REMINDER: change as.sir() to remove the deprecation warning there
-  suppressWarnings(is.sir(...))
-}
-#' @rdname AMR-deprecated
-#' @export
-is.rsi.eligible <- function(...) {
-  deprecation_warning("is.rsi.eligible", "is_sir_eligible")
-  is_sir_eligible(...)
-}
-#' @rdname AMR-deprecated
-#' @export
-labels_rsi_count <- function(...) {
-  deprecation_warning("labels_rsi_count", "labels_sir_count")
-  labels_sir_count(...)
-}
-#' @rdname AMR-deprecated
-#' @export
-n_rsi <- function(...) {
-  deprecation_warning("n_rsi", "n_sir")
-  n_sir(...)
-}
-#' @rdname AMR-deprecated
-#' @export
-random_rsi <- function(...) {
-  deprecation_warning("random_rsi", "random_sir")
-  random_sir(...)
-}
-#' @rdname AMR-deprecated
-#' @export
-rsi_df <- function(...) {
-  deprecation_warning("rsi_df", "sir_df")
-  sir_df(...)
-}
-#' @rdname AMR-deprecated
-#' @export
-rsi_predict <- function(...) {
-  deprecation_warning("rsi_predict", "sir_predict")
-  sir_predict(...)
-}
-#' @rdname AMR-deprecated
-#' @export
-scale_rsi_colours <- function(...) {
-  deprecation_warning("scale_rsi_colours", "scale_sir_colours")
-  scale_sir_colours(...)
-}
-#' @rdname AMR-deprecated
-#' @export
-theme_rsi <- function(...) {
-  deprecation_warning("theme_rsi", "theme_sir")
-  theme_sir(...)
-}
-
-# will be exported using s3_register() in R/zzz.R
-pillar_shaft.rsi <- pillar_shaft.sir
-type_sum.rsi <- function(x, ...) {
-  if (message_not_thrown_before("type_sum.rsi")) {
-    deprecation_warning(extra_msg = "The 'rsi' class has been replaced with 'sir'. Transform your 'rsi' columns to 'sir' with `as.sir()`, e.g.:\n  your_data %>% mutate_if(is.rsi, as.sir)")
-  }
-  "rsi"
-}
-
-#' @method print rsi
-#' @export
-#' @noRd
-print.rsi <- function(x, ...) {
-  deprecation_warning(extra_msg = "The 'rsi' class has been replaced with 'sir' - transform your 'rsi' data with `as.sir()`")
-  cat("Class 'rsi'", font_bold(font_red("[!]\n")))
-  print(as.character(x), quote = FALSE)
-}
-
-#' @noRd
-#' @export
-`[<-.rsi` <- `[<-.sir`
-#' @noRd
-#' @export
-`[[<-.rsi` <- `[[<-.sir`
-#' @noRd
-#' @export
-barplot.rsi <- barplot.sir
-#' @noRd
-#' @export
-c.rsi <- c.sir
-#' @noRd
-#' @export
-droplevels.rsi <- droplevels.sir
-#' @noRd
-#' @export
-plot.rsi <- plot.sir
-#' @noRd
-#' @export
-rep.rsi <- rep.sir
-#' @noRd
-#' @export
-summary.rsi <- summary.sir
-#' @noRd
-#' @export
-unique.rsi <- unique.sir
-
-# WHEN REMOVING RSI, DON'T FORGET TO REMOVE :
-# - THE "rsi_df" CLASS FROM R/sir_calc.R
-# - CODE CONTAINING only_rsi_columns, colours_RSI, include_untested_rsi, prob_RSI
+# #' Deprecated Functions
+# #' 
+# #' These functions are so-called '[Deprecated]'. **They will be removed in a future release.** Using the functions will give a warning with the name of the function it has been replaced by (if there is one).
+# #' @keywords internal
+# #' @name AMR-deprecated
+# #' @rdname AMR-deprecated
+# #' @export
+# NULL
 
 deprecation_warning <- function(old = NULL, new = NULL, extra_msg = NULL, is_function = TRUE) {
   if (is.null(old)) {

R/zzz.R

@@ -67,6 +67,7 @@ AMR_env$sir_interpretation_history <- data.frame(
   method = character(0),
   breakpoint_S_R = character(0),
   guideline = character(0),
+  host = character(0),
   ref_table = character(0),
   stringsAsFactors = FALSE
 )
@@ -77,17 +78,11 @@ AMR_env$is_dark_theme <- NULL
 AMR_env$chmatch <- import_fn("chmatch", "data.table", error_on_fail = FALSE)
 AMR_env$chin <- import_fn("%chin%", "data.table", error_on_fail = FALSE)
 
-# determine info icon for messages
-if (pkg_is_available("cli")) {
-  # let cli do the determination of supported symbols
-  AMR_env$info_icon <- import_fn("symbol", "cli")$info
-  AMR_env$bullet_icon <- import_fn("symbol", "cli")$bullet
-  AMR_env$dots <- import_fn("symbol", "cli")$ellipsis
-} else {
-  AMR_env$info_icon <- "i"
-  AMR_env$bullet_icon <- "*"
-  AMR_env$dots <- "..."
-}
+# take cli symbols if available
+AMR_env$info_icon <- import_fn("symbol", "cli", error_on_fail = FALSE)$info %or% "i"
+AMR_env$bullet_icon <- import_fn("symbol", "cli", error_on_fail = FALSE)$bullet %or% "*"
+AMR_env$dots <- import_fn("symbol", "cli", error_on_fail = FALSE)$ellipsis %or% "..."
+AMR_env$sup_1_icon <- import_fn("symbol", "cli", error_on_fail = FALSE)$sup_1 %or% "*"
 
 .onLoad <- function(lib, pkg) {
   # Support for tibble headers (type_sum) and tibble columns content (pillar_shaft)
@@ -98,16 +93,13 @@ if (pkg_is_available("cli")) {
   s3_register("pillar::pillar_shaft", "av")
   s3_register("pillar::pillar_shaft", "mo")
   s3_register("pillar::pillar_shaft", "sir")
-  s3_register("pillar::pillar_shaft", "rsi") # remove in a later version
   s3_register("pillar::pillar_shaft", "mic")
   s3_register("pillar::pillar_shaft", "disk")
   s3_register("pillar::type_sum", "ab")
   s3_register("pillar::type_sum", "av")
   s3_register("pillar::type_sum", "mo")
   s3_register("pillar::type_sum", "sir")
-  s3_register("pillar::type_sum", "rsi") # remove in a later version
   s3_register("pillar::type_sum", "mic")
-  s3_register("pillar::type_sum", "disk")
   # Support for frequency tables from the cleaner package
   s3_register("cleaner::freq", "mo")
   s3_register("cleaner::freq", "sir")
@@ -132,6 +124,7 @@ if (pkg_is_available("cli")) {
   s3_register("knitr::knit_print", "antibiogram")
   s3_register("knitr::knit_print", "formatted_bug_drug_combinations")
   # Support vctrs package for use in e.g. dplyr verbs
+  # NOTE 2024-02-22 this is the right way - it should be 2 S3 classes in the second argument
   # S3: ab_selector
   s3_register("vctrs::vec_ptype2", "character.ab_selector")
   s3_register("vctrs::vec_ptype2", "ab_selector.character")
@@ -141,23 +134,25 @@ if (pkg_is_available("cli")) {
   s3_register("vctrs::vec_ptype2", "ab_selector_any_all.logical")
   s3_register("vctrs::vec_cast", "logical.ab_selector_any_all")
   # S3: ab
-  s3_register("vctrs::vec_ptype2", "character.ab")
-  s3_register("vctrs::vec_ptype2", "ab.character")
+  s3_register("vctrs::vec_ptype2", "ab.default")
+  s3_register("vctrs::vec_ptype2", "ab.ab")
   s3_register("vctrs::vec_cast", "character.ab")
   s3_register("vctrs::vec_cast", "ab.character")
   # S3: av
-  s3_register("vctrs::vec_ptype2", "character.av")
-  s3_register("vctrs::vec_ptype2", "av.character")
+  s3_register("vctrs::vec_ptype2", "av.default")
+  s3_register("vctrs::vec_ptype2", "av.av")
   s3_register("vctrs::vec_cast", "character.av")
   s3_register("vctrs::vec_cast", "av.character")
   # S3: mo
-  s3_register("vctrs::vec_ptype2", "character.mo")
-  s3_register("vctrs::vec_ptype2", "mo.character")
+  s3_register("vctrs::vec_ptype2", "mo.default")
+  s3_register("vctrs::vec_ptype2", "mo.mo")
   s3_register("vctrs::vec_cast", "character.mo")
   s3_register("vctrs::vec_cast", "mo.character")
   # S3: disk
-  s3_register("vctrs::vec_ptype2", "integer.disk")
-  s3_register("vctrs::vec_ptype2", "disk.integer")
+  s3_register("vctrs::vec_ptype_full", "disk")
+  s3_register("vctrs::vec_ptype_abbr", "disk")
+  s3_register("vctrs::vec_ptype2", "disk.default")
+  s3_register("vctrs::vec_ptype2", "disk.disk")
   s3_register("vctrs::vec_cast", "integer.disk")
   s3_register("vctrs::vec_cast", "disk.integer")
   s3_register("vctrs::vec_cast", "double.disk")
@@ -165,14 +160,22 @@ if (pkg_is_available("cli")) {
   s3_register("vctrs::vec_cast", "character.disk")
   s3_register("vctrs::vec_cast", "disk.character")
   # S3: mic
+  s3_register("vctrs::vec_ptype2", "mic.default")
+  s3_register("vctrs::vec_ptype2", "mic.mic")
   s3_register("vctrs::vec_cast", "character.mic")
   s3_register("vctrs::vec_cast", "double.mic")
+  s3_register("vctrs::vec_cast", "integer.mic")
+  s3_register("vctrs::vec_cast", "factor.mic")
   s3_register("vctrs::vec_cast", "mic.character")
   s3_register("vctrs::vec_cast", "mic.double")
+  s3_register("vctrs::vec_cast", "mic.integer")
+  s3_register("vctrs::vec_cast", "mic.factor")
+  s3_register("vctrs::vec_cast", "mic.mic")
   s3_register("vctrs::vec_math", "mic")
+  s3_register("vctrs::vec_arith", "mic")
   # S3: sir
-  s3_register("vctrs::vec_ptype2", "character.sir")
-  s3_register("vctrs::vec_ptype2", "sir.character")
+  s3_register("vctrs::vec_ptype2", "sir.default")
+  s3_register("vctrs::vec_ptype2", "sir.sir")
   s3_register("vctrs::vec_cast", "character.sir")
   s3_register("vctrs::vec_cast", "sir.character")
 
@@ -189,31 +192,41 @@ if (pkg_is_available("cli")) {
   # they cannot be part of R/sysdata.rda since CRAN thinks it would make the package too large (+3 MB)
   AMR_env$AB_lookup <- cbind(AMR::antibiotics, AB_LOOKUP)
   AMR_env$AV_lookup <- cbind(AMR::antivirals, AV_LOOKUP)
+  
+  AMR_env$host_preferred_order <- names(sort(table(AMR::clinical_breakpoints$host[!AMR::clinical_breakpoints$host %in% AMR::clinical_breakpoints$type]), decreasing = TRUE))
 }
 
 .onAttach <- function(lib, pkg) {
   # if custom ab option is available, load it
   if (!is.null(getOption("AMR_custom_ab")) && file.exists(getOption("AMR_custom_ab", default = ""))) {
-    packageStartupMessage("Adding custom antimicrobials from '", getOption("AMR_custom_ab"), "'...", appendLF = FALSE)
-    x <- readRDS_AMR(getOption("AMR_custom_ab"))
-    tryCatch(
-      {
-        suppressWarnings(suppressMessages(add_custom_antimicrobials(x)))
-        packageStartupMessage("OK.")
-      },
-      error = function(e) packageStartupMessage("Failed: ", e$message)
-    )
+    if (getOption("AMR_custom_ab") %unlike% "[.]rds$") {
+      packageStartupMessage("The file with custom antimicrobials must be an RDS file. Set the option `AMR_custom_ab` to another path.")
+    } else {
+      packageStartupMessage("Adding custom antimicrobials from '", getOption("AMR_custom_ab"), "'...", appendLF = FALSE)
+      x <- readRDS_AMR(getOption("AMR_custom_ab"))
+      tryCatch(
+        {
+          suppressWarnings(suppressMessages(add_custom_antimicrobials(x)))
+          packageStartupMessage("OK.")
+        },
+        error = function(e) packageStartupMessage("Failed: ", e$message)
+      )
+    }
   }
   # if custom mo option is available, load it
   if (!is.null(getOption("AMR_custom_mo")) && file.exists(getOption("AMR_custom_mo", default = ""))) {
-    packageStartupMessage("Adding custom microorganisms from '", getOption("AMR_custom_mo"), "'...", appendLF = FALSE)
-    x <- readRDS_AMR(getOption("AMR_custom_mo"))
-    tryCatch(
-      {
-        suppressWarnings(suppressMessages(add_custom_microorganisms(x)))
-        packageStartupMessage("OK.")
-      },
-      error = function(e) packageStartupMessage("Failed: ", e$message)
-    )
+    if (getOption("AMR_custom_mo") %unlike% "[.]rds$") {
+      packageStartupMessage("The file with custom microorganisms must be an RDS file. Set the option `AMR_custom_mo` to another path.")
+    } else {
+      packageStartupMessage("Adding custom microorganisms from '", getOption("AMR_custom_mo"), "'...", appendLF = FALSE)
+      x <- readRDS_AMR(getOption("AMR_custom_mo"))
+      tryCatch(
+        {
+          suppressWarnings(suppressMessages(add_custom_microorganisms(x)))
+          packageStartupMessage("OK.")
+        },
+        error = function(e) packageStartupMessage("Failed: ", e$message)
+      )
+    }
   }
 }

README.md

@@ -4,9 +4,7 @@
 
 ----
 
-This work was published in the Journal of Statistical Software (Volume 104(3); [DOI 10.18637/jss.v104.i03](https://doi.org/10.18637/jss.v104.i03)) and formed the basis of two PhD theses ([DOI 10.33612/diss.177417131](https://doi.org/10.33612/diss.177417131) and [DOI 10.33612/diss.192486375](https://doi.org/10.33612/diss.192486375)).
-
-`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 175 countries.
+`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 175 countries. This work was published in the Journal of Statistical Software (2022, Volume 104(3); [DOI 10.18637/jss.v104.i03](https://doi.org/10.18637/jss.v104.i03)) and formed the basis of two PhD theses ([DOI 10.33612/diss.177417131](https://doi.org/10.33612/diss.177417131) and [DOI 10.33612/diss.192486375](https://doi.org/10.33612/diss.192486375)).
  
 After installing this package, R knows ~52,000 distinct microbial species and all ~600 antibiotic, antimycotic, and antiviral drugs by name and code (including ATC, WHONET/EARS-Net, PubChem, LOINC and SNOMED CT), and knows all about valid SIR and MIC values. It supports any data format, including WHONET/EARS-Net data. Antimicrobial names and group names are available in English, Chinese, Danish, Dutch, French, German, Greek, Italian, Japanese, Polish, Portuguese, Russian, Spanish, Swedish, Turkish, and Ukrainian.
 

_pkgdown.yml

@@ -35,15 +35,11 @@ template:
   bootswatch: "flatly"
   assets: "pkgdown/logos" # use logos in this folder
   bslib:
+    base_font: {google: "Lato"}
+    heading_font: {google: "Lato"}
     code_font: {google: "Fira Code"}
     # body-text-align: "justify"
     line-height-base: 1.75
-    # the green "success" colour of this bootstrap theme should be the same as the green in our logo
-    success: "#128f76"
-    link-color: "#128f76"
-    light: "#128f76a6" # this is success with 60% alpha
-    # the template "info" is blue - this should be a green fitting our theme
-    info: "#60a799"
     # make top bar a bit wider
     navbar-padding-y: "0.5rem"
   opengraph:
@@ -174,7 +170,7 @@ reference:
     - "`atc_online_property`"
     - "`add_custom_antimicrobials`"
 
-  - title: "Preparing data: antimicrobial resistance"
+  - title: "Preparing data"
     desc: >
       With `as.mic()` and `as.disk()` you can transform your raw input to valid MIC or disk diffusion values.
       Use `as.sir()` for cleaning raw data to let it only contain "R", "I" and "S", or to interpret MIC or disk diffusion values as SIR based on the lastest EUCAST and CLSI guidelines.
@@ -186,7 +182,7 @@ reference:
     - "`eucast_rules`"
     - "`custom_eucast_rules`"
 
-  - title: "Analysing data: antimicrobial resistance"
+  - title: "Analysing data"
     desc: >
       Use these function for the analysis part. You can use `susceptibility()` or `resistance()` on any antibiotic column.
       With `antibiogram()`, you can generate a traditional, combined, syndromic, or weighted-incidence syndromic combination
@@ -202,14 +198,25 @@ reference:
     - "`key_antimicrobials`"
     - "`mdro`"
     - "`count`"
-    - "`plot`"
-    - "`ggplot_sir`"
     - "`bug_drug_combinations`"
     - "`antibiotic_class_selectors`"
     - "`mean_amr_distance`"
     - "`resistance_predict`"
     - "`guess_ab_col`"
     
+  - title: "Plotting data"
+    desc: >
+      Use these functions for the plotting part. The `scale_*_mic()` functions extend the ggplot2 package to allow plotting of 
+      MIC values, even within a manually set range.
+      If using `plot()` (base R) or `autoplot()` (ggplot2) on MIC values or disk diffusion values, the user can
+      set the interpretation guideline to give the bars the right SIR colours.
+      The `ggplot_sir()` function is a short wrapper for users not much accustomed to ggplot2 yet.
+      The `ggplot_pca()` function is a specific function to plot so-called biplots for PCA (principal component analysis).
+    contents:
+    - "`plot`"
+    - "`ggplot_sir`"
+    - "`ggplot_pca`"
+    
   - title: "Other: AMR-specific options"
     desc: >
       The AMR package is customisable, by providing settings that can be set per user or per team. For
@@ -257,7 +264,6 @@ reference:
     - "`age`"
     - "`availability`"
     - "`get_AMR_locale`"
-    - "`ggplot_pca`"
     - "`italicise_taxonomy`"
     - "`join`"
     - "`like`"
@@ -273,10 +279,10 @@ reference:
     - "`kurtosis`"
     - "`skewness`"
 
-  - title: "Other: deprecated functions"
-    desc: >
-      These functions are deprecated, meaning that they will still
-      work but show a warning with every use and will be removed
-      in a future version.
-    contents:
-    - "`AMR-deprecated`"
+  # - title: "Other: deprecated functions"
+  #   desc: >
+  #     These functions are deprecated, meaning that they will still
+  #     work but show a warning with every use and will be removed
+  #     in a future version.
+  #   contents:
+  #   - "`AMR-deprecated`"

data-raw/AMR new logo.txt

@@ -0,0 +1,3 @@
+green grass #a7dbc3
+green bacteria #128F76
+blue sky #a8d5ef

data-raw/AMR_vet.qmd

@@ -0,0 +1,71 @@
+---
+title: "AMR Goes Vet"
+author: "Jason, Matthew, Javier, Matthijs"
+date: "2024-02-20"
+format: 
+  html: 
+    embed-resources: true
+---
+
+## Import WHONET data set
+
+```{r, message=FALSE, warning=FALSE}
+library(dplyr)
+library(readr)
+library(tidyr)
+library(janitor)
+
+# WHONET version of 16th Feb 2024
+whonet_breakpoints <- read_tsv("WHONET/Resources/Breakpoints.txt", na = c("", "NA", "-"),
+                               show_col_types = FALSE, guess_max = Inf) %>%
+  filter(GUIDELINES %in% c("CLSI", "EUCAST"))
+
+dim(whonet_breakpoints)
+```
+
+# EDA of Animal Breakpoints
+
+```{r}
+whonet_breakpoints |>
+  filter(BREAKPOINT_TYPE != "Human")
+whonet_breakpoints |>
+  filter(BREAKPOINT_TYPE != "Human") |>
+  count(BREAKPOINT_TYPE)
+whonet_breakpoints |>
+  filter(BREAKPOINT_TYPE == "Animal")
+```
+
+### Count of all animal breakpoints
+
+```{r}
+whonet_breakpoints |>
+  filter(BREAKPOINT_TYPE == "Animal") |>
+  count(YEAR, HOST, REFERENCE_TABLE = gsub("VET[0-9]+ ", "", REFERENCE_TABLE)) |>
+  pivot_wider(names_from = YEAR, values_from = n, values_fill = list(n = 0)) |>
+  arrange(HOST, REFERENCE_TABLE) |> 
+  adorn_totals(name = "TOTAL")
+```
+
+### Cats only
+
+```{r}
+whonet_breakpoints |>
+  filter(HOST == "Cats", YEAR >= 2021) |> 
+  select(GUIDELINES, YEAR, TEST_METHOD, ORGANISM_CODE, R, S) |> 
+  mutate(MO_NAME = AMR::mo_shortname(ORGANISM_CODE), .before = R) |> 
+  as.data.frame()
+```
+
+### Site of infection in cats (2023)
+
+```{r}
+whonet_breakpoints |>
+  filter(HOST == "Cats", YEAR == 2023) |> 
+  mutate(MO = AMR::mo_shortname(ORGANISM_CODE),
+         AB = AMR::ab_name(WHONET_ABX_CODE),
+         SITE_OF_INFECTION = substr(SITE_OF_INFECTION, 1, 25)) |> 
+  arrange(MO, AB) |> 
+  select(MO, AB, SITE_OF_INFECTION) |> 
+  as.data.frame()
+```
+

data-raw/_pre_commit_checks.R

@@ -28,7 +28,7 @@
 # ==================================================================== #
 
 # Run this file to update the package using:
-# source("data-raw/_pre_commit_hook.R")
+# source("data-raw/_pre_commit_checks.R")
 
 library(dplyr, warn.conflicts = FALSE)
 try(detach("package:data.table", unload = TRUE), silent = TRUE) # to prevent like() to precede over AMR::like
@@ -157,20 +157,21 @@ MO_STREP_ABCG <- AMR::microorganisms$mo[which(AMR::microorganisms$genus == "Stre
 MO_LANCEFIELD <- AMR::microorganisms$mo[which(AMR::microorganisms$mo %like% "^(B_STRPT_PYGN(_|$)|B_STRPT_AGLC(_|$)|B_STRPT_(DYSG|EQUI)(_|$)|B_STRPT_ANGN(_|$)|B_STRPT_(DYSG|CANS)(_|$)|B_STRPT_SNGN(_|$)|B_STRPT_SLVR(_|$))")]
 MO_PREVALENT_GENERA <- c(
   "Absidia", "Acanthamoeba", "Acremonium", "Aedes", "Alternaria", "Amoeba", "Ancylostoma", "Angiostrongylus",
-  "Anisakis", "Anopheles", "Apophysomyces", "Aspergillus", "Aureobasidium", "Basidiobolus", "Beauveria",
-  "Blastocystis", "Blastomyces", "Candida", "Capillaria", "Chaetomium", "Chrysonilia", "Cladophialophora",
+  "Anisakis", "Anopheles", "Apophysomyces", "Arthroderma", "Aspergillus", "Aureobasidium", "Basidiobolus", "Beauveria",
+  "Blastocystis", "Blastomyces", "Candida", "Capillaria", "Chaetomium", "Chrysonilia", "Chrysosporium", "Cladophialophora",
   "Cladosporium", "Conidiobolus", "Contracaecum", "Cordylobia", "Cryptococcus", "Curvularia", "Demodex",
   "Dermatobia", "Dientamoeba", "Diphyllobothrium", "Dirofilaria", "Echinostoma", "Entamoeba", "Enterobius",
-  "Exophiala", "Exserohilum", "Fasciola", "Fonsecaea", "Fusarium", "Giardia", "Haloarcula", "Halobacterium",
+  "Exophiala", "Exserohilum", "Fasciola", "Fonsecaea", "Fusarium", "Geotrichum", "Giardia", "Haloarcula", "Halobacterium",
   "Halococcus", "Hendersonula", "Heterophyes", "Histomonas", "Histoplasma", "Hymenolepis", "Hypomyces",
-  "Hysterothylacium", "Leishmania", "Malassezia", "Malbranchea", "Metagonimus", "Meyerozyma", "Microsporidium",
-  "Microsporum", "Mortierella", "Mucor", "Mycocentrospora", "Necator", "Nectria", "Ochroconis", "Oesophagostomum",
-  "Oidiodendron", "Opisthorchis", "Pediculus", "Penicillium", "Phlebotomus", "Phoma", "Pichia", "Piedraia", "Pithomyces",
+  "Hysterothylacium", "Kloeckera", "Kodamaea", "Leishmania", "Lichtheimia", "Lodderomyces",
+  "Malassezia", "Malbranchea", "Metagonimus", "Meyerozyma", "Microsporidium",
+  "Microsporum", "Millerozyma", "Mortierella", "Mucor", "Mycocentrospora", "Necator", "Nectria", "Ochroconis", "Oesophagostomum",
+  "Oidiodendron", "Opisthorchis", "Paecilomyces", "Pediculus", "Penicillium", "Phlebotomus", "Phoma", "Pichia", "Piedraia", "Pithomyces",
   "Pityrosporum", "Pneumocystis", "Pseudallescheria", "Pseudoterranova", "Pulex", "Rhizomucor", "Rhizopus",
-  "Rhodotorula", "Saccharomyces", "Sarcoptes", "Scolecobasidium", "Scopulariopsis", "Scytalidium", "Spirometra",
-  "Sporobolomyces", "Stachybotrys", "Strongyloides", "Syngamus", "Taenia", "Talaromyces", "Toxocara", "Trichinella",
+  "Rhodotorula", "Saccharomyces", "Saprochaete", "Sarcoptes", "Scedosporium", "Scolecobasidium", "Scopulariopsis", "Scytalidium", "Spirometra",
+  "Sporobolomyces", "Sporotrichum", "Stachybotrys", "Strongyloides", "Syngamus", "Taenia", "Talaromyces", "Toxocara", "Trichinella",
   "Trichobilharzia", "Trichoderma", "Trichomonas", "Trichophyton", "Trichosporon", "Trichostrongylus", "Trichuris",
-  "Tritirachium", "Trombicula", "Trypanosoma", "Tunga", "Wuchereria"
+  "Tritirachium", "Trombicula", "Trypanosoma", "Tunga", "Verticillium", "Wuchereria"
 )
 
 # antibiotic groups
@@ -180,10 +181,10 @@ AB_AMINOGLYCOSIDES <- antibiotics %>%
   filter(group %like% "aminoglycoside") %>%
   pull(ab)
 AB_AMINOPENICILLINS <- as.ab(c("AMP", "AMX"))
-AB_ANTIFUNGALS <- AMR_env$AB_lookup %>%
+AB_ANTIFUNGALS <- antibiotics %>%
   filter(group %like% "antifungal") %>%
   pull(ab)
-AB_ANTIMYCOBACTERIALS <- AMR_env$AB_lookup %>%
+AB_ANTIMYCOBACTERIALS <- antibiotics %>%
   filter(group %like% "antimycobacterial") %>%
   pull(ab)
 AB_CARBAPENEMS <- antibiotics %>%
@@ -220,7 +221,10 @@ AB_LINCOSAMIDES <- antibiotics %>%
   filter(atc_group2 %like% "lincosamide" | (group %like% "lincosamide" & is.na(atc_group2))) %>%
   pull(ab)
 AB_MACROLIDES <- antibiotics %>%
-  filter(atc_group2 %like% "macrolide" | (group %like% "macrolide" & is.na(atc_group2))) %>%
+  filter(atc_group2 %like% "macrolide" | (group %like% "macrolide" & is.na(atc_group2) & name %unlike% "screening|inducible")) %>%
+  pull(ab)
+AB_NITROFURANS <- antibiotics %>%
+  filter(name %like% "^furaz|nitrofura" | atc_group2 %like% "nitrofuran") %>%
   pull(ab)
 AB_OXAZOLIDINONES <- antibiotics %>%
   filter(group %like% "oxazolidinone") %>%
@@ -234,6 +238,9 @@ AB_POLYMYXINS <- antibiotics %>%
 AB_QUINOLONES <- antibiotics %>%
   filter(group %like% "quinolone") %>%
   pull(ab)
+AB_RIFAMYCINS <- antibiotics %>%
+  filter(name %like% "Rifampi|Rifabutin|Rifapentine|rifamy") %>%
+  pull(ab)
 AB_STREPTOGRAMINS <- antibiotics %>%
   filter(atc_group2 %like% "streptogramin") %>%
   pull(ab)
@@ -309,10 +316,12 @@ suppressMessages(usethis::use_data(EUCAST_RULES_DF,
   AB_GLYCOPEPTIDES_EXCEPT_LIPO,
   AB_LINCOSAMIDES,
   AB_MACROLIDES,
+  AB_NITROFURANS,
   AB_OXAZOLIDINONES,
   AB_PENICILLINS,
   AB_POLYMYXINS,
   AB_QUINOLONES,
+  AB_RIFAMYCINS,
   AB_STREPTOGRAMINS,
   AB_TETRACYCLINES,
   AB_TETRACYCLINES_EXCEPT_TGC,

data-raw/ab.md5

@@ -1 +1 @@
-3d8c509ec95d61889cae83af43b0e6b7
+3e7a1cbb21b49cdc7626ea3016a017cc

data-raw/antibiotics.txt

@@ -8,19 +8,19 @@
 "AMX"	33613	"Amoxicillin"	"Beta-lactams/penicillins"	"J01CA04"	"Beta-lactam antibacterials, penicillins"	"Penicillins with extended spectrum"	"ac,amox,amx"	"actimoxi,amoclen,amolin,amopen,amopenixin,amoxibiotic,amoxicaps,amoxicilina,amoxicillin,amoxicillin hydrate,amoxicilline,amoxicillinum,amoxiden,amoxil,amoxivet,amoxy,amoxycillin,amoxyke,anemolin,aspenil,atoksilin,biomox,bristamox,cemoxin,clamoxyl,damoxy,delacillin,demoksil,dispermox,efpenix,flemoxin,hiconcil,histocillin,hydroxyampicillin,ibiamox,imacillin,lamoxy,largopen,metafarma capsules,metifarma capsules,moksilin,moxacin,moxatag,ospamox,pamoxicillin,piramox,promoxil,remoxil,robamox,sawamox pm,tolodina,topramoxin,unicillin,utimox,vetramox"	1.5	"g"	3	"g"	"101498-4,15-8,16-6,16365-9,17-4,18-2,18861-5,18862-3,19-0,20-8,21-6,22-4,25274-2,25310-4,3344-9,55614-2,55615-9,55616-7,6976-5,6977-3,80133-2"
 "AMC"	23665637	"Amoxicillin/clavulanic acid"	"Beta-lactams/penicillins"	"J01CR02"	"Beta-lactam antibacterials, penicillins"	"Combinations of penicillins, incl. beta-lactamase inhibitors"	"a/c,amcl,aml,aug,xl"	"amocla,amoclan,amoclav,amoksiclav,amoxsiklav,amoxyclav,augmentan,augmentin,augmentin xr,augmentine,auspilic,clamentin,clamobit,clavamox,clavinex,clavoxilin plus,clavulin,clavumox,coamoxiclav,eumetinex,kmoxilin,spectramox,spektramox,synulox,viaclav,xiclav"	1.5	"g"	3	"g"	""
 "AXS"	465441	"Amoxicillin/sulbactam"	"Beta-lactams/penicillins"	"NA"			""	""					"55614-2,55615-9,55616-7"
-"AMB"	5280965	"Amphotericin B"	"Antifungals/antimycotics"	"A01AB04,A07AA07,G01AA03,J02AA01"	"Antimycotics for systemic use"	"Antibiotics"	"amf,amfb,amph"	"abelcet,abelecet,ambisome,amfotericina b,amphocin,amphomoronal,amphortericin b,amphotec,amphotericin,amphotericin b,amphotericine b,amphotericinum b,amphozone,anfotericine b,fungilin,fungisome,fungisone,fungizone,halizon"	40	"mg"	35	"mg"	"16370-9,18863-1,23-2,24-0,25-7,26-5,3353-0,3354-8,40707-2,40757-7,49859-2,6978-1"
+"AMB"	5280965	"Amphotericin B"	"Antifungals/antimycotics"	"A01AB04,A07AA07,G01AA03,J02AA01"	"Antimycotics for systemic use"	"Antibiotics"	"amf,amfb,amph"	"abelcet,abelecet,ambisome,amfotericina b,amphocin,amphomoronal,amphortericin b,amphotec,amphotericin,amphotericin b,amphotericine b,amphotericinum b,amphozone,anfotericine b,fungilin,fungisome,fungisone,fungizone,halizon"	40	"mg"	210	"mg"	"16370-9,18863-1,23-2,24-0,25-7,26-5,3353-0,3354-8,40707-2,40757-7,49859-2,6978-1"
 "AMH"		"Amphotericin B-high"	"Aminoglycosides"	"NA"			"amfo b high,amhl,ampho b high,amphotericin high"	""					""
 "AMP"	6249	"Ampicillin"	"Beta-lactams/penicillins"	"J01CA01,S01AA19"	"Beta-lactam antibacterials, penicillins"	"Penicillins with extended spectrum"	"am,amp,ampi"	"acillin,adobacillin,amblosin,amcill,amfipen,amfipen v,amipenix s,ampichel,ampicil,ampicilina,ampicillin,ampicillin a,ampicillin acid,ampicillin anhydrate,ampicillin anhydrous,ampicillin base,ampicillin hydrate,ampicillin sodium,ampicillina,ampicilline,ampicillinum,ampicin,ampifarm,ampikel,ampimed,ampipenin,ampiscel,ampisyn,ampivax,ampivet,amplacilina,amplin,amplipenyl,amplisom,amplital,anhydrous ampicillin,austrapen,binotal,bonapicillin,britacil,campicillin,copharcilin,delcillin,deripen,divercillin,doktacillin,duphacillin,grampenil,guicitrina,guicitrine,lifeampil,marcillin,morepen,norobrittin,nuvapen,olin kid,omnipen,orbicilina,pen a oral,pen ampil,penbristol,penbritin,penbritin paediatric,penbritin syrup,penbrock,penicline,penimic,pensyn,pentrex,pentrexl,pentrexyl,pentritin,pfizerpen a,polycillin,polyflex,ponecil,princillin,principen,qidamp,racenacillin,redicilin,rosampline,roscillin,semicillin,semicillin r,servicillin,sumipanto,synpenin,texcillin,tokiocillin,tolomol,totacillin,totalciclina,totapen,trifacilina,ukapen,ultrabion,ultrabron,vampen,viccillin,viccillin s,vidocillin,wypicil"	2	"g"	6	"g"	"101477-8,101478-6,18864-9,18865-6,20374-5,21066-6,23618-2,27-3,28-1,29-9,30-7,31-5,32-3,33-1,3355-5,33562-0,33919-2,34-9,43883-8,43884-6,6979-9,6980-7,87604-5"
 "SAM"	119561	"Ampicillin/sulbactam"	"Beta-lactams/penicillins"	"J01CR01"	"Beta-lactam antibacterials, penicillins"	"Combinations of penicillins, incl. beta-lactamase inhibitors"	"a/s,ab,ams,amsu,apsu,sam"	"sulacillin"			6	"g"	"101478-6,18865-6,20374-5,23618-2,31-5,32-3,33-1,34-9,6980-7"
-"AMR"	73341	"Amprolium"	"Other antibacterials"	"NA"			""	"amprocidum,amprol,amprolio,amprolium,amprolium chloride,amprovine,thiacoccid"					""
+"AMR"	73341	"Amprolium"	"Other antibacterials"	"QP51BX02"			""	"amprocidum,amprol,amprolio,amprolium,amprolium chloride,amprovine,thiacoccid"					""
 "ANI"	166548	"Anidulafungin"	"Antifungals/antimycotics"	"J02AX06"	"Antimycotics for systemic use"	"Other antimycotics for systemic use"	"anid"	"anidulafungin,anidulafungina,anidulafungine,anidulafunginum,ecalta,eraxis"			0.1	"g"	"55343-8,57095-2,58420-1,77162-6"
 "APL"	6602341	"Apalcillin"	"Beta-lactams/penicillins"	"NA"			""	"apalcilina,apalcillin,apalcilline,apalcillinum"					""
-"APR"	3081545	"Apramycin"	"Aminoglycosides"	"NA"			""	"ambylan,apralan,apramicina,apramycin,apramycine,apramycinum,nebramycin ii"					"23659-6,73652-0,73653-8"
+"APR"	3081545	"Apramycin"	"Aminoglycosides"	"QA07AA92,QJ01GB90,QJ51GB90"			""	"ambylan,apralan,apramicina,apramycin,apramycine,apramycinum,nebramycin ii"					"23659-6,73652-0,73653-8"
 "ARB"	68682	"Arbekacin"	"Aminoglycosides"	"J01GB12"			""	"arbekacin,arbekacina,arbekacine,arbekacini sulfas,arbekacinum,habekacin,haberacin"			0.2	"g"	"32373-3,53818-1,54173-0"
 "APX"	71961	"Aspoxicillin"	"Beta-lactams/penicillins"	"J01CA19"			""	"aspoxicilina,aspoxicillan,aspoxicillin,aspoxicilline,aspoxicillinum"			4	"g"	""
 "AST"	5284517	"Astromicin"	"Aminoglycosides"	"NA"			""	"astromicin,astromicin a,astromicina,astromicine,astromicinum,fortimicin,fortimicin a"					""
 "AVB"	9835049	"Avibactam"	"Beta-lactams/penicillins"	"NA"			""	"avibactam,avibactam free acid,avibactamfreeacid"					""
-"AVI"	71674	"Avilamycin"	"Other antibacterials"	"NA"			""	"avilamycin,avilamycina,avilamycine,avilamycinum,surmax"					"35754-1,35755-8,35756-6,55619-1"
+"AVI"	71674	"Avilamycin"	"Other antibacterials"	"QA07AA95"			""	"avilamycin,avilamycina,avilamycine,avilamycinum,surmax"					"35754-1,35755-8,35756-6,55619-1"
 "AVO"	16131159	"Avoparcin"	"Glycopeptides"	"NA"			""	"avoparcin,avoparcina,avoparcine,avoparcinum,avotan"					""
 "AZD"	15574941	"Azidocillin"	"Beta-lactams/penicillins"	"J01CE04"	"Beta-lactam antibacterials, penicillins"	"Beta-lactamase sensitive penicillins"	""	"azidocilina,azidocillin,azidocillina,azidocilline,azidocillinum"	1.5	"g"			""
 "AZM"	447043	"Azithromycin"	"Macrolides/lincosamides"	"J01FA10,S01AA26"	"Macrolides, lincosamides and streptogramins"	"Macrolides"	"az,azi,azit,azm"	"aritromicina,aruzilina,azasite,azenil,azifast,azigram,azimakrol,azithramycine,azithrocin,azithromycin,azithromycine,azithromycinum,azitrocin,azitromax,azitromicina,azitromicine,azitromin,aziwin,aziwok,aztrin,azyter,azythromycin,durasite,hemomycin,macrozit,misultina,mixoterin,setron,sumamed,toraseptol,tromix,trozocina,trulimax,xithrone,zentavion,zithrax,zithromac,zithromax,zithromax iv,zithromycin,zitrim,zitromax,zitrotek,zmax sr,zythromax"	0.3	"g"	0.5	"g"	"100043-9,16420-2,16421-0,18866-4,23612-5,25233-8,35-6,36-4,37-2,38-0,6981-5,89480-8"
@@ -30,7 +30,7 @@
 "AZA"		"Aztreonam/avibactam"	"Beta-lactams/penicillins"	"NA"			""	""					""
 "ANC"		"Aztreonam/nacubactam"	"Beta-lactams/penicillins"	"NA"			""	""					""
 "BAM"	441397	"Bacampicillin"	"Beta-lactams/penicillins"	"J01CA06"	"Beta-lactam antibacterials, penicillins"	"Penicillins with extended spectrum"	""	"bacampicilina,bacampicillin,bacampicilline,bacampicillinum,penglobe"	1.2	"g"			"18869-8,47-1,48-9,49-7,50-5,55620-9"
-"BAC"	78358334	"Bacitracin"	"Other antibacterials"	"R02AB04,J01XX10"			"baci"	"fortracin,md bacitracin"					"10868-8,16428-5,18870-6,6827-0,6983-1,87603-7"
+"BAC"	78358334	"Bacitracin"	"Other antibacterials"	"D06AX05,J01XX10,R02AB04,S01AA32"			"baci"	"fortracin,md bacitracin"					"10868-8,16428-5,18870-6,6827-0,6983-1,87603-7"
 "BDQ"	5388906	"Bedaquiline"	"Other antibacterials"	"J04AK05"			""	"bedaquiline,sirturo"	86	"mg"			"80637-2,88703-4,88704-2,94274-8,96107-8"
 "BEK"	439318	"Bekanamycin"	"Aminoglycosides"	"J01GB13"			""	"aminodeoxykanamycin,becanamicina,bekanamycin,bekanamycine,bekanamycinum,kanamycin b,klebcil,nebramycin v"			0.6	"g"	""
 "BNB"		"Benzathine benzylpenicillin"	"Beta-lactams/penicillins"	"J01CE08"	"Beta-lactam antibacterials, penicillins"	"Beta-lactamase sensitive penicillins"	""	"beacillin,cepacilina,extencilline,lentopenil,penidural,tardocillin"			3.6	"g"	""
@@ -75,10 +75,10 @@
 "CPI"	5486182	"Cefetamet pivoxil"	"Cephalosporins (3rd gen.)"	"NA"			""	"cefetamet pivoxyl,globocef"					""
 "CCL"	71719688	"Cefetecol"	"Cephalosporins (4th gen.)"	"NA"			"cefcatacol"	"cefetecol,cefetecol anhydrous"					""
 "CZL"	193956	"Cefetrizole"	"Cephalosporins (unclassified gen.)"	"NA"			""	"cefetrizole,cefetrizolum"					""
-"FDC"	77843966	"Cefiderocol"	"Other antibacterials"	"J01DI04"			""	"cefiderocol"					"95767-0,99280-0,99503-5"
+"FDC"	77843966	"Cefiderocol"	"Other antibacterials"	"J01DI04"			""	"cefiderocol"			6	"g"	"95767-0,99280-0,99503-5"
 "CFM"	5362065	"Cefixime"	"Cephalosporins (3rd gen.)"	"J01DD08"	"Other beta-lactam antibacterials"	"Third-generation cephalosporins"	"cfe,cfix,cfxm,dcfm,fix,ix"	"anhydrous cefixime,cefixim,cefixima,cefixime,cefixime anhydrous,cefixime hydrate,cefiximum,cefixoral,cefspan,cephoral,citropen,denvar,necopen,oroken,suprax,tricef,unixime"	0.4	"g"			"16567-0,18880-5,25236-1,35766-5,79-4,80-2,81-0,82-8"
 "CEO"		"Cefixime/ornidazole"	"Other antibacterials"	"J01RA15"	"Combinations of antibacterials"	"Combinations of antibacterials"	""	""					""
-"CMX"	9570757	"Cefmenoxime"	"Cephalosporins (3rd gen.)"	"J01DD05"	"Other beta-lactam antibacterials"	"Third-generation cephalosporins"	""	"bestron,cefmax,cefmenoxima,cefmenoxime,cefmenoximum"			2	"g"	"32375-8,54174-8,54203-5,55641-5"
+"CMX"	9570757	"Cefmenoxime"	"Cephalosporins (3rd gen.)"	"J01DD05,S01AA31,S02AA18"	"Other beta-lactam antibacterials"	"Third-generation cephalosporins"	""	"bestron,cefmax,cefmenoxima,cefmenoxime,cefmenoximum"			2	"g"	"32375-8,54174-8,54203-5,55641-5"
 "CMZ"	42008	"Cefmetazole"	"Cephalosporins (2nd gen.)"	"J01DC09"	"Other beta-lactam antibacterials"	"Second-generation cephalosporins"	""	"cefmetazole,cefmetazolesodium,cefmetazolo,cefmetazolum"			4	"g"	"11575-8,18881-3,25222-1,87-7,88-5,89-3,90-1"
 "CNX"	71141	"Cefminox"	"Other antibacterials"	"J01DC12"			""	"cefminox,cefminoxum"			4	"g"	"54908-9"
 "DIZ"	5361871	"Cefodizime"	"Cephalosporins (3rd gen.)"	"J01DD09"	"Other beta-lactam antibacterials"	"Third-generation cephalosporins"	""	"cefodizima,cefodizime,cefodizime acid,cefodizime disodium,cefodizimum,cefodizme,diezime,modivid,neucef,timecef"			2	"g"	"18882-1,6988-0,91-9,92-7,93-5,94-3"
@@ -93,7 +93,7 @@
 "CTT"	53025	"Cefotetan"	"Cephalosporins (2nd gen.)"	"J01DC05"	"Other beta-lactam antibacterials"	"Second-generation cephalosporins"	"cftt,cn,cte,ctn,ctt,tans"	"apacef,cefotan,cefotetan,cefotetan acid,cefotetan free acid,cefotetanum"			4	"g"	"111-5,112-3,113-1,114-9,18887-0,25239-5,3447-0,41672-7,41673-5,41674-3,41729-5,6990-6"
 "CTF"	43708	"Cefotiam"	"Cephalosporins (2nd gen.)"	"J01DC07"	"Other beta-lactam antibacterials"	"Second-generation cephalosporins"	""	"cefotiam,cefotiam?,cefotiamum,ceradolan,ceradon,haloapor"	1.2	"g"	4	"g"	"32374-1,35772-3,35773-1,55645-6,55737-1,55738-9,55739-7,55740-5"
 "CHE"	125846	"Cefotiam hexetil"	"Cephalosporins (3rd gen.)"	"NA"			""	"cefotiam cilexetil,pansporin t"					"55737-1,55738-9,55739-7,55740-5"
-"FOV"	9578573	"Cefovecin"	"Cephalosporins (3rd gen.)"	"NA"			""	"cefovecin"					"76147-8,87792-8"
+"FOV"	9578573	"Cefovecin"	"Cephalosporins (3rd gen.)"	"QJ01DD91"			""	"cefovecin"					"76147-8,87792-8"
 "FOX"	441199	"Cefoxitin"	"Cephalosporins (2nd gen.)"	"J01DC01"	"Other beta-lactam antibacterials"	"Second-generation cephalosporins"	"cfox,cfx,cfxt,cx,fox,fx"	"cefoxitin,cefoxitina,cefoxitine,cefoxitinum,cefoxotin,cenomycin,cephoxitin,mefoxin,mefoxitin,rephoxitin"			6	"g"	"101492-7,115-6,116-4,117-2,118-0,18888-8,25220-5,25240-3,25366-6,3448-8,41675-0,41676-8,41677-6,41730-3,6991-4"
 "FOX1"		"Cefoxitin screening"	"Cephalosporins (2nd gen.)"	"NA"			"cfsc"	""					""
 "ZOP"	9571080	"Cefozopran"	"Cephalosporins (4th gen.)"	"J01DE03"			""	"cefozopran"			4	"g"	"100045-4,53820-7"
@@ -104,7 +104,7 @@
 "CPX"	6526396	"Cefpodoxime proxetil"	"Cephalosporins (3rd gen.)"	"NA"			""	"cefodox,cefoprox,cefpodoxime proxetil,cepodem,orelox,orelox paed,otreon,podomexef,simplicef,vantin"					""
 "CDC"		"Cefpodoxime/clavulanic acid"	"Cephalosporins (3rd gen.)"	"NA"			"cecl"	""					""
 "CPR"	5281006	"Cefprozil"	"Cephalosporins (2nd gen.)"	"J01DC10"	"Other beta-lactam antibacterials"	"Second-generation cephalosporins"	"cpr,cpz,fp"	"arzimol,brisoral,cefprozil,cefprozil anhydrous,cefprozil hydrate,cefprozilo,cefprozilum,cefzil,cronocef,procef,serozil"	1	"g"			"123-0,124-8,125-5,126-3,18891-2,6994-8"
-"CEQ"	5464355	"Cefquinome"	"Cephalosporins (4th gen.)"	"NA"			""	"cefquinoma,cefquinome,cefquinomum,cobactan"					"100046-2,76150-2"
+"CEQ"	5464355	"Cefquinome"	"Cephalosporins (4th gen.)"	"QG51AA07,QJ01DE90,QJ51DE90"			""	"cefquinoma,cefquinome,cefquinomum,cobactan"					"100046-2,76150-2"
 "CRD"	5284529	"Cefroxadine"	"Cephalosporins (1st gen.)"	"J01DB11"	"Other beta-lactam antibacterials"	"First-generation cephalosporins"	""	"cefroxadin,cefroxadine,cefroxadino,cefroxadinum,oraspor"	2.1	"g"			""
 "CFS"	656575	"Cefsulodin"	"Cephalosporins (3rd gen.)"	"J01DD03"	"Other beta-lactam antibacterials"	"Third-generation cephalosporins"	"cfsl,cfsu"	"cefonomil,cefsulodin,cefsulodine,cefsulodino,cefsulodinum"			4	"g"	"127-1,128-9,129-7,130-5,131-3,18892-0,25242-9,55647-2"
 "CSU"	68718	"Cefsumide"	"Cephalosporins (unclassified gen.)"	"NA"			""	"cefsulmid,cefsumide,cefsumido,cefsumidum"					""
@@ -117,12 +117,12 @@
 "CPL"	5362114	"Cefteram pivoxil"	"Cephalosporins (3rd gen.)"	"NA"			""	"cefteram pivoxil,cefterampivoxil,tomiron"					""
 "CTL"	65755	"Ceftezole"	"Cephalosporins (1st gen.)"	"J01DB12"	"Other beta-lactam antibacterials"	"First-generation cephalosporins"	""	"ceftezol,ceftezole,ceftezolo,ceftezolum,demethylcefazolin"			3	"g"	""
 "CTB"	5282242	"Ceftibuten"	"Cephalosporins (3rd gen.)"	"J01DD14"	"Other beta-lactam antibacterials"	"Third-generation cephalosporins"	"cb,cfbu,ctb,tib"	"ceftem,ceftibuten,ceftibuten dihydrate,ceftibuten hydrate,ceftibutene,ceftibuteno,ceftibutenum,ceftibutin,cephem,ceprifran,isocef,keimax"	0.4	"g"			"35777-2,35778-0,35779-8,6996-3"
-"TIO"	6328657	"Ceftiofur"	"Cephalosporins (3rd gen.)"	"NA"			""	"ceftiofur,ceftiofurum,excede,excenel,naxcel"					"23709-9,35780-6,35781-4,55652-2"
+"TIO"	6328657	"Ceftiofur"	"Cephalosporins (3rd gen.)"	"QJ01DD90,QJ51DD90"			""	"ceftiofur,ceftiofurum,excede,excenel,naxcel"					"23709-9,35780-6,35781-4,55652-2"
 "CZX"	6533629	"Ceftizoxime"	"Cephalosporins (3rd gen.)"	"J01DD07"	"Other beta-lactam antibacterials"	"Third-generation cephalosporins"	"cfzx,ctz,cz,czx,tiz,zox"	"cefizox,ceftisomin,ceftix,ceftizoxima,ceftizoxime,ceftizoximum,epocelin,eposerin"			4	"g"	"136-2,137-0,138-8,139-6,18894-6,20378-6,23622-4,25243-7,3450-4,6997-1"
 "CZP"	9578661	"Ceftizoxime alapivoxil"	"Cephalosporins (3rd gen.)"	"NA"			""	""					""
 "BPR"	135413542	"Ceftobiprole"	"Cephalosporins (5th gen.)"	"NA"			""	"ceftobiprole"					"43269-0,43270-8,43271-6,43272-4,85052-9"
 "CFM1"	135413544	"Ceftobiprole medocaril"	"Cephalosporins (5th gen.)"	"J01DI01"	"Other beta-lactam antibacterials"	"Other cephalosporins and penems"	""	""			1.5	"g"	""
-"CZT"	86291594	"Ceftolozane/tazobactam"	"Cephalosporins (5th gen.)"	"J01DI54"	"Other beta-lactam antibacterials"	"Other cephalosporins and penems"	"CEI"	"zerbaxa"			3	"g"	"101484-4,73602-5,73624-9,73647-0,87735-7"
+"CZT"	86291594	"Ceftolozane/tazobactam"	"Cephalosporins (5th gen.)"	"J01DI54"	"Other beta-lactam antibacterials"	"Other cephalosporins and penems"	"cei"	"zerbaxa"			3	"g"	"101484-4,73602-5,73624-9,73647-0,87735-7"
 "CRO"	5479530	"Ceftriaxone"	"Cephalosporins (3rd gen.)"	"J01DD04"	"Other beta-lactam antibacterials"	"Third-generation cephalosporins"	"axo,cax,cftr,cro,ctr,frx,tx"	"biotrakson,cefatriaxone,cefatriaxone hydrate,ceftriaxon,ceftriaxona,ceftriaxone,ceftriaxone sodium,ceftriaxonum,ceftriazone,cephtriaxone,longacef,rocefin,rocephalin,rocephin,rocephine,rophex"			2	"g"	"101485-1,140-4,141-2,142-0,143-8,18895-3,25244-5,25367-4,31140-7,31141-5,3451-2,41681-8,41682-6,41683-4,41732-9,50633-7,55190-3,6998-9,80957-4"
 "CEB"		"Ceftriaxone/beta-lactamase inhibitor"	"Cephalosporins (3rd gen.)"	"J01DD63"	"Other beta-lactam antibacterials"	"Third-generation cephalosporins"	""	""			2	"g"	""
 "CXM"	5479529	"Cefuroxime"	"Cephalosporins (2nd gen.)"	"J01DC02,S01AA27"	"Other beta-lactam antibacterials"	"Second-generation cephalosporins"	"cfrx,cfur,cfx,crm,cxm,fur,rox,xm"	"biofuroksym,cefuril,cefuroxim,cefuroxima,cefuroxime,cefuroxime acid,cefuroximine,cefuroximo,cefuroximum,cephuroxime,kefurox,sharox,zinacef,zinacef danmark"	0.5	"g"	3	"g"	"101503-1,144-6,145-3,146-1,147-9,18896-1,20460-2,25245-2,3452-0,35782-2,35783-0,51724-3,51774-8,55653-0,55654-8,6999-7,74699-0,80608-3,80617-4"
@@ -137,13 +137,14 @@
 "CIX"	47472	"Ciclopirox"	"Antifungals/antimycotics"	"D01AE14,G01AX12"	"Antifungals for topical use"	"Other antifungals for topical use"	"cipx"	"butaconazole,butoconazol,butoconazole,butoconazolum,ciclodan,ciclopirox,ciclopirox gel,ciclopirox olamin,ciclopiroxum,compositenstarke,dahlin,femstat,gynofort,loprox,loprox cream,loprox gel,penlac,polyfructosanum,stieprox"					""
 "CIN"	2762	"Cinoxacin"	"Quinolones"	"J01MB06"	"Quinolone antibacterials"	"Other quinolones"	"cino,cnox"	"azolinic acid,cinobac,cinobactin,cinoxacin,cinoxacine,cinoxacino,cinoxacinum,clinoxacin,noxigram,uronorm"	1	"g"			"180-0,181-8,182-6,183-4,18905-0,55656-3"
 "CIP"	2764	"Ciprofloxacin"	"Quinolones"	"J01MA02,S01AE03,S02AA15,S03AA07"	"Quinolone antibacterials"	"Fluoroquinolones"	"ci,cip,cipr,cp"	"alcon cilox,auripro,bacquinor,baflox,baycip,bernoflox,cetraxal,ciflox,cifloxin,ciloxan,ciplus,ciprecu,ciprine,ciprinol,cipro i.v.,cipro iv,cipro xl,cipro xr,ciprobay,ciprobay uro,ciprocinol,ciprodar,ciproflox,ciprofloxacin,ciprofloxacina,ciprofloxacine,ciprofloxacino,ciprofloxacinum,ciprogis,ciprolin,ciprolon,cipromycin,ciproquinol,ciprowin,ciproxan,ciproxin,ciproxina,ciproxine,ciriax,citopcin,corsacin,cyprobay,fimoflox,flociprin,ipiflox,italnik,linhaliq,otiprio,probiox,proflaxin,quinolid,quintor,rancif,roxytal,septicide,sophixin ofteno,spitacin,superocin,velmonit,velomonit,zumaflox"	1	"g"	0.8	"g"	"101500-7,14031-9,14032-7,14058-2,14059-0,184-2,185-9,186-7,187-5,18906-8,20377-8,23621-6,25180-1,25181-9,25188-4,25189-2,25248-6,34636-1,3484-3,42644-5,55194-5,7002-9"
-"CIM"		"Ciprofloxacin/metronidazole"	"Other antibacterials"	"J01RA10"	"Combinations of antibacterials"	"Combinations of antibacterials"	""	""					""
-"CIO"		"Ciprofloxacin/ornidazole"	"Other antibacterials"	"J01RA12"	"Combinations of antibacterials"	"Combinations of antibacterials"	""	""					""
-"CIT"		"Ciprofloxacin/tinidazole"	"Other antibacterials"	"J01RA11"	"Combinations of antibacterials"	"Combinations of antibacterials"	""	""					""
+"CIM"		"Ciprofloxacin/metronidazole"	"Quinolones"	"J01RA10"	"Combinations of antibacterials"	"Combinations of antibacterials"	""	""					""
+"CIO"		"Ciprofloxacin/ornidazole"	"Quinolones"	"J01RA12"	"Combinations of antibacterials"	"Combinations of antibacterials"	""	""					""
+"CIT"		"Ciprofloxacin/tinidazole"	"Quinolones"	"J01RA11"	"Combinations of antibacterials"	"Combinations of antibacterials"	""	""					""
 "CLR"	84029	"Clarithromycin"	"Macrolides/lincosamides"	"J01FA09"	"Macrolides, lincosamides and streptogramins"	"Macrolides"	"ch,cla,clar,clm,clr"	"abbotic,astromen,biaxin,biaxin filmtab,biaxin hp,biaxin xl,biaxin xl filmtab,bicrolid,clacee,clacid,clacine,clambiotic,clarem,claribid,claricide,claridar,claripen,clarith,clarithromycin,clarithromycine,clarithromycinum,claritromicina,clathromycin,crixan,cyllid,cyllind,fromilid,heliclar,klabax,klacid,klaciped,klaricid,klaricid h.p,klaricid h.p.,klaricid pediatric,klaricid xl,klarid,klarin,kofron,mabicrol,macladin,maclar,prevpac,veclam,vikrol,zeclar"	0.5	"g"	1	"g"	"100048-8,16619-9,16620-7,188-3,189-1,18907-6,190-9,191-7,20375-2,23619-0,25190-0,25191-8,25192-6,25253-6,34638-7,43987-7,43990-1,43991-9,7003-7,80559-8,89485-7"
 "CLA1"	5280980	"Clavulanic acid"	"Other antibacterials"	"NA"			""	"acide clavulanique,acido clavulanico,acidum clavulanicum,clavulanate,clavulanate acid,clavulanate lithium,clavulanateacid,clavulanic acid,clavulansaeure,clavulansaure,clavulinic acid,clavulox,serdaxin,sodium clavulanate"					""
 "CLX"	60063	"Clinafloxacin"	"Quinolones"	"NA"			""	"clinafloxacin"					"32376-6,33284-1,35785-5,35786-3,7004-5"
 "CLI"	446598	"Clindamycin"	"Macrolides/lincosamides"	"D10AF01,G01AA10,J01FF01"	"Macrolides, lincosamides and streptogramins"	"Lincosamides"	"cc,cd,cli,clin,cm,da"	"antirobe,chlolincocin,clindaderm,clindamicina,clindamycin,clindamycine,clindamycinum,clinimycin,dalacin c,dalacine,klimicin,sobelin"	1.2	"g"	1.8	"g"	"16621-5,16622-3,18908-4,192-5,193-3,194-1,195-8,25249-4,3486-8,42720-3,55657-1,55658-9,55659-7,55660-5,61188-9,7005-2"
+"CLI1"		"Clindamycin inducible screening"	"Macrolides/lincosamides"	"NA"			"clindamycin inducible,clinda inducible,clin inducible"	""					""
 "CLF"	2794	"Clofazimine"	"Antimycobacterials"	"J04BA01"	"Drugs for treatment of lepra"	"Drugs for treatment of lepra"	"clof"	"chlofazimine,clofazimin,clofazimina,clofazimine,clofaziminum,colfazimine,lampren,lamprene,riminophenazine"	0.1	"g"			"16623-1,20376-0,23620-8,23627-3,43986-9,43988-5,43989-3,55661-3,55662-1,96108-6"
 "CLF1"	2799	"Clofoctol"	"Other antibacterials"	"J01XX03"	"Other antibacterials"	"Other antibacterials"	""	"clofoctol,clofoctolo,clofoctolum,gramplus,octofene"					""
 "CLM"	71807	"Clometocillin"	"Beta-lactams/penicillins"	"J01CE07"	"Beta-lactam antibacterials, penicillins"	"Beta-lactamase sensitive penicillins"	""	"chlomethocillin,clometacillin,clometocilina,clometocillin,clometocilline,clometocillinum,rixapen"	1	"g"			""
@@ -154,32 +155,32 @@
 "COP"		"Colistin/polysorbate"	"Other antibacterials"	"NA"			""	""					""
 "CYC"	6234	"Cycloserine"	"Oxazolidinones"	"J04AB01"	"Drugs for treatment of tuberculosis"	"Antibiotics"	"cycl"	"cicloserina,closerin,closina,cyclorin,cycloserin,cycloserine,cycloserinum,farmiserina,micoserina,miroserina,miroseryn,novoserin,oxamicina,oxamycin,seromycin,tebemicina,tisomycin,wasserina"	0.75	"g"			"16702-3,18914-2,212-1,213-9,214-7,215-4,23608-3,25207-2,25208-0,25209-8,25251-0,3519-6,55667-0"
 "DAL"	23724878	"Dalbavancin"	"Glycopeptides"	"J01XA04"	"Other antibacterials"	"Glycopeptide antibacterials"	"dalb"	"dalbavancin,dalvance"			1.5	"g"	"41688-3,41689-1,41690-9,41734-5"
-"DAN"	71335	"Danofloxacin"	"Quinolones"	"NA"			""	"advocin,danofloxacin,danofloxacine,danofloxacino,danofloxacinum"					"73601-7,73623-1,73646-2"
+"DAN"	71335	"Danofloxacin"	"Quinolones"	"QJ01MA92"			""	"advocin,danofloxacin,danofloxacine,danofloxacino,danofloxacinum"					"73601-7,73623-1,73646-2"
 "DPS"	2955	"Dapsone"	"Other antibacterials"	"D10AX05,J04BA02"	"Drugs for treatment of lepra"	"Drugs for treatment of lepra"	""	"aczone,araldite ht,atrisone,avlosulfon,avlosulfone,avlosulphone,avsulfor,bis sulfone,bissulfone,bissulphone,croysulfone,croysulphone,dapson,dapsona,dapsone,dapsonum,di sulfone,diaphenyl sulfone,diaphenylsulfon,diaphenylsulfone,diaphenylsulphon,diaphenylsulphone,dimitone,diphenasone,diphone,disulfone,disulone,disulphone,dubronax,dubronaz,dumitone,eporal,metabolite c,novophone,protogen,servidapson,slphadione,sulfadione,sulfona,sulfone ucb,sulfonyldianiline,sulphadione,sulphonyldianiline,sumicure s,tarimyl,udolac"	50	"mg"			"51698-9,9747-7"
 "DAP"	16134395	"Daptomycin"	"Other antibacterials"	"J01XX09"	"Other antibacterials"	"Other antibacterials"	"dap,dapt"	"cidecin,cubicin,dapcin,daptomicina,daptomycine,daptomycinum"			0.28	"g"	"35787-1,35788-9,35789-7,41691-7"
 "DFX"	487101	"Delafloxacin"	"Quinolones"	"J01MA23"			""	"baxdela,delafloxacin,delafloxacinum,quofenix"	0.9	"g"	0.6	"g"	"88885-9,90447-4,93790-4"
 "DLM"	6480466	"Delamanid"	"Antimycobacterials"	"J04AK06"	"Drugs for treatment of tuberculosis"	"Other drugs for treatment of tuberculosis"	"dela"	"delamanid,deltyba"	0.2	"g"			"93851-4,96109-4"
 "DEM"	54680690	"Demeclocycline"	"Tetracyclines"	"D06AA01,J01AA01"	"Tetracyclines"	"Tetracyclines"	""	"bioterciclin,clortetrin,declomycin,deganol,demeclociclina,demeclocycline,demeclocyclinum,demeclor,demetraclin,diuciclin,elkamicina,ledermycin,mexocine,novotriclina,perciclina,sumaclina"	0.6	"g"			"10982-7,18915-9,216-2,217-0,218-8,219-6,29494-2,7006-0"
-"DKB"	470999	"Dibekacin"	"Aminoglycosides"	"J01GB09"	"Aminoglycoside antibacterials"	"Other aminoglycosides"	""	"debecacin,dibekacin,dibekacin sulfate,dibekacina,dibekacine,dibekacinum,dideoxykanamycin b,kappati,orbicin,panamicin"			0.14	"g"	"55669-6,55670-4,55671-2,55672-0"
+"DKB"	470999	"Dibekacin"	"Aminoglycosides"	"J01GB09,S01AA29"	"Aminoglycoside antibacterials"	"Other aminoglycosides"	""	"debecacin,dibekacin,dibekacin sulfate,dibekacina,dibekacine,dibekacinum,dideoxykanamycin b,kappati,orbicin,panamicin"			0.14	"g"	"55669-6,55670-4,55671-2,55672-0"
 "DIC"	18381	"Dicloxacillin"	"Beta-lactams/penicillins"	"J01CF01"	"Beta-lactam antibacterials, penicillins"	"Beta-lactamase resistant penicillins"	"dicl"	"dichloroxacillin,diclossacillina,dicloxaciclin,dicloxacilin,dicloxacilina,dicloxacillin,dicloxacillin sodium,dicloxacillina,dicloxacilline,dicloxacillinum,dicloxacycline,dycill,dynapen,maclicine,nm|| dicloxacillin,pathocil"	2	"g"	2	"g"	"10984-3,16769-2,18916-7,220-4,221-2,222-0,223-8,25252-8,32380-8,55668-8"
-"DIF"	56206	"Difloxacin"	"Quinolones"	"NA"			""	"dicural,difloxacin,pulsaflox"					"35790-5,35791-3,35792-1"
+"DIF"	56206	"Difloxacin"	"Quinolones"	"QJ01MA94"			""	"dicural,difloxacin,pulsaflox"					"35790-5,35791-3,35792-1"
 "DIR"	6473883	"Dirithromycin"	"Macrolides/lincosamides"	"J01FA13"	"Macrolides, lincosamides and streptogramins"	"Macrolides"	""	"dirithromycin,dirithromycine,dirithromycinum,diritromicina,divitross,dynabac,noriclan,valodin"	0.5	"g"			"35793-9,35794-7,35795-4,7007-8"
 "DOR"	73303	"Doripenem"	"Carbapenems"	"J01DH04"	"Other beta-lactam antibacterials"	"Carbapenems"	"dori"	"doribax,doripenem,doripenem hydrate,finibax"			1.5	"g"	"56031-8,58711-3,60535-2,72893-1"
 "DOX"	54671203	"Doxycycline"	"Tetracyclines"	"A01AB22,J01AA02"	"Tetracyclines"	"Tetracyclines"	"dox,doxy"	"atridox,azudoxat,deoxymykoin,dossiciclina,doxcycline anhydrous,doxiciclina,doxirobe,doxitard,doxivetin,doxycen,doxychel,doxycin,doxycyclin,doxycycline,doxycycline calcium,doxycycline hyclate,doxycyclinum,doxylin,doxysol,doxytec,doxytetracycline,hydramycin,investin,jenacyclin,liviatin,monodox,oracea,periostat,ronaxan,spanor,supracyclin,vibramycin,vibramycin novum,vibramycine,vibravenos,zenavod"	0.1	"g"	0.1	"g"	"10986-8,18917-5,20379-4,21250-6,224-6,225-3,226-1,227-9,23623-2,25223-9,26902-7,7008-6"
 "ECO"	3198	"Econazole"	"Antifungals/antimycotics"	"D01AC03,G01AF05"	"Antifungals for topical use"	"Imidazole and triazole derivatives"	"econ"	"econazol,econazole,econazolum,ecostatin,ecostatin cream,palavale,pevaryl,spectazole,spectazole cream"					"25595-0,25637-0,54178-9,55673-8"
 "ENX"	3229	"Enoxacin"	"Quinolones"	"J01MA04"	"Quinolone antibacterials"	"Fluoroquinolones"	"enox"	"almitil,bactidan,bactidron,comprecin,enofloxacine,enoksetin,enoram,enoxacin,enoxacina,enoxacine,enoxacino,enoxacinum,enoxen,enoxin,enoxor,flumark,penetrex"	0.8	"g"			"16816-1,18918-3,228-7,229-5,230-3,231-1,3590-7,41692-5"
-"ENR"	71188	"Enrofloxacin"	"Quinolones"	"NA"			""	"baytril,enrofloxacin,enrofloxacine,enrofloxacino,enrofloxacinum,enroxil"					"23712-3,35796-2,35797-0,35798-8"
-"ENV"	135565326	"Enviomycin"	"Antimycobacterials"	"J04AB06"			"tuberactinomycin"	"enviomicina,enviomycin,enviomycina,enviomycinum,tuberactin"					""
+"ENR"	71188	"Enrofloxacin"	"Quinolones"	"QJ01MA90"			""	"baytril,enrofloxacin,enrofloxacine,enrofloxacino,enrofloxacinum,enroxil"					"23712-3,35796-2,35797-0,35798-8"
+"ENV"	135565326	"Enviomycin"	"Antimycobacterials"	"J04AB06"			"tuberactinomycin"	"enviomicina,enviomycin,enviomycina,enviomycinum,tuberactin"			1	"g"	""
 "EPE"		"Eperozolid"	"Other antibacterials"	"NA"			""	""					""
 "EPC"	71392	"Epicillin"	"Beta-lactams/penicillins"	"J01CA07"	"Beta-lactam antibacterials, penicillins"	"Penicillins with extended spectrum"	""	"dexacillin,dihydroampicillin,epicilina,epicillin,epicilline,epicillinum"	2	"g"	2	"g"	""
 "EPP"	68916	"Epiroprim"	"Other antibacterials"	"NA"			""	"epiroprim,epiroprima,epiroprime,epiroprimum"					""
-"ERV"	54726192	"Eravacycline"	"Tetracyclines"	"J01AA13"	"Tetracyclines"	"Tetracyclines"	"erav"	"eravacycline,xerava"					"100049-6,85423-2,93767-2"
+"ERV"	54726192	"Eravacycline"	"Tetracyclines"	"J01AA13"	"Tetracyclines"	"Tetracyclines"	"erav"	"eravacycline,xerava"			0.14	"g"	"100049-6,85423-2,93767-2"
 "ETP"	150610	"Ertapenem"	"Carbapenems"	"J01DH03"	"Other beta-lactam antibacterials"	"Carbapenems"	"erta,etp"	"ertapenem,invanz"			1	"g"	"101486-9,35799-6,35800-2,35801-0,35802-8"
 "ERY"	12560	"Erythromycin"	"Macrolides/lincosamides"	"D10AF02,J01FA01,S01AA17"	"Macrolides, lincosamides and streptogramins"	"Macrolides"	"e,em,ery,eryt"	"abboticin,abomacetin,acneryne,acnesol,akne cordes losung,aknederm ery gel,aknemycin,austrias,benzamycin,bristamycin,derimer,deripil,dotycin,dumotrycin,emuvin,emycin,endoeritrin,erecin,erisone,eritomicina,eritrocina,eritromicina,ermycin,eryacne,eryacnen,eryc sprinkles,erycen,erycette,erycin,erycinum,eryderm,erydermer,erygel,eryhexal,erymax,erymed,erypar,erysafe,erytab,erythrocin,erythrocin stearate,erythroderm,erythrogran,erythroguent,erythromid,erythromycin,erythromycin a,erythromycin base,erythromycin lactate,erythromycine,erythromycines,erythromycinum,erytop,erytrociclin,ilocaps,ilosone,iloticina,ilotycin,ilotycin gluceptate,ilotycin t.s.,inderm,inderm gel,indermretcin,latotryd,lederpax,mephamycin,mercina,oftamolets,paediathrocin,pantoderm,pantodrin,pantomicina,pce dispertab,pharyngocin,primacine,propiocine,proterytrin,retcin,robimycin,romycin,sansac,skid gel e,staticin,stiemicyn,stiemycin,theramycin z,tiloryth,tiprocin,torlamicina,udima ery gel,wyamycin s"	2	"g"	1	"g"	"100050-4,11576-6,12298-6,16829-4,16830-2,18919-1,18920-9,20380-2,232-9,233-7,234-5,235-2,236-0,23633-1,237-8,238-6,239-4,25224-7,25275-9,3597-2,7009-4"
 "ETH"	14052	"Ethambutol"	"Antimycobacterials"	"J04AK02"	"Drugs for treatment of tuberculosis"	"Other drugs for treatment of tuberculosis"	"etha"	"aethambutolum,diambutol,ebutol,etambutol,etambutolo,etapiam,ethambutol,ethambutolum,myambutol,mycobutol,purderal,servambutol,tibutol"	1.2	"g"	1.2	"g"	"100051-2,16841-9,18921-7,20381-0,23625-7,240-2,241-0,242-8,243-6,25187-6,25194-2,25195-9,25230-4,25404-5,3607-9,42645-2,42646-0,55154-9,55674-6,56025-0,7010-2,89491-5"
 "ETI"	456476	"Ethambutol/isoniazid"	"Antimycobacterials"	"J04AM03"	"Drugs for treatment of tuberculosis"	"Combinations of drugs for treatment of tuberculosis"	""	""					""
 "ETI1"	2761171	"Ethionamide"	"Antimycobacterials"	"J04AD03"	"Drugs for treatment of tuberculosis"	"Thiocarbamide derivatives"	"ethi"	"aethionamidum,aetina,aetiva,amidazin,amidazine,ethatyl,ethimide,ethina,ethinamide,ethionamide,ethionamidum,ethioniamide,ethylisothiamide,ethyonomide,etimid,etiocidan,etionamid,etionamida,etionamide,etioniamid,etionid,etionizin,etionizina,etionizine,fatoliamid,iridocin,iridocin bayer,iridozin,isothin,isotiamida,itiocide,nicotion,nisotin,nizotin,rigenicid,sertinon,teberus,thianid,thianide,thioamide,thiodine,thiomid,thioniden,tianid,tiomid,trecator,trecator sc,trekator,trescatyl,trescazide,tubenamide,tubermin,tuberoid,tuberoson"	0.75	"g"			"16099-4,16845-0,18922-5,20382-8,23617-4,25183-5,25196-7,25198-3,25231-2,41693-3,42647-8,42648-6,7011-0,96110-2"
-"ETO"	6034	"Ethopabate"	"Other antibacterials"	"NA"			""	"amprol plus,ethopabat,ethopabate,ethyl pabate"					""
+"ETO"	6034	"Ethopabate"	"Other antibacterials"	"QP51AX17"			""	"amprol plus,ethopabat,ethopabate,ethyl pabate"					""
 "EXE"		"Exebacase"		"NA"			""	""					""
 "FAR"	65894	"Faropenem"	"Other antibacterials"	"J01DI03"	"Other beta-lactam antibacterials"	"Other cephalosporins and penems"	""	"faropenem,faropenem sodium,fropenem,fropenum sodium"	0.75	"g"			"73600-9,73622-3,73645-4"
 "FDX"	10034073	"Fidaxomicin"	"Other antibacterials"	"A07AA12"			""	"dificid,dificlir,difimicin,fidaxomicin,lipiarmicin,lipiarmycin,lipiarrmycin,tiacumicin b"	0.4	"g"			"73599-3,73621-5,73644-7"
@@ -187,23 +188,23 @@
 "FLA"	46783781	"Flavomycin"	"Other antibacterials"	"NA"			""	"flavophospholipol,moenomycin complex"					""
 "FLE"	3357	"Fleroxacin"	"Quinolones"	"J01MA08"	"Quinolone antibacterials"	"Fluoroquinolones"	"fler"	"fleroxacin,fleroxacine,fleroxacino,fleroxacinum,fleroxicin,megalocin,megalone,megalosin,quinodis"	0.4	"g"	0.4	"g"	"25411-0,32372-5,35806-9,7012-8"
 "FLO"	65864	"Flomoxef"	"Other antibacterials"	"J01DC14"			""	"flomoxef,flomoxefo,flomoxefum"			2	"g"	"100052-0,53822-3"
-"FLR"	114811	"Florfenicol"	"Other antibacterials"	"NA"			""	"aquafen,florfenicol,nuflor,nuflor gold"					"23740-4,35807-7,35808-5,87599-7"
+"FLR"	114811	"Florfenicol"	"Other antibacterials"	"QJ01BA90,QJ51BA90"			""	"aquafen,florfenicol,nuflor,nuflor gold"					"23740-4,35807-7,35808-5,87599-7"
 "FLC"	21319	"Flucloxacillin"	"Beta-lactams/penicillins"	"J01CF05"	"Beta-lactam antibacterials, penicillins"	"Beta-lactamase resistant penicillins"	"clox,flux"	"culpen,floxacillin,floxacillin sodium,floxapen,floxapen sodium salt,fluclox,flucloxacilina,flucloxacillin,flucloxacilline,flucloxacillinum,fluorochloroxacillin,staphylex"	2	"g"	2	"g"	""
 "FLU"	3365	"Fluconazole"	"Antifungals/antimycotics"	"D01AC15,J02AC01"	"Antimycotics for systemic use"	"Triazole derivatives"	"fluc,fluz,flz"	"alflucoz,alfumet,alkanazole,biocanol,biozole,biozolene,canzol,cryptal,diflazon,diflucan,dimycon,elazor,flucazol,fluconazol,fluconazole,fluconazole capsules,fluconazoli,fluconazolum,flucoral,flucostat,flukezol,flunazol,flunizol,flusol,fluzon,fluzone,forcan,fuconal,fungata,loitin,oxifugol,pritenzol,syscan,trican,triconal,triflucan,zoltec"	0.2	"g"	0.2	"g"	"10987-6,16870-8,18924-1,248-5,249-3,250-1,251-9,25255-1,7013-6,80530-9"
-"FCT"	3366	"Flucytosine"	"Antifungals/antimycotics"	"D01AE21,J02AX01"	"Antifungals for topical use"	"Other antifungals for topical use"	"5flc,fcu,fluo,fluy"	"alcobon,ancoban,ancobon,ancotil,ancotyl,flourocytosine,flucitosina,flucystine,flucytosin,flucytosine,flucytosinum,flucytosone,fluocytosine,fluorcytosine,fluorocytosine"					""
+"FCT"	3366	"Flucytosine"	"Antifungals/antimycotics"	"D01AE21,J02AX01"	"Antifungals for topical use"	"Other antifungals for topical use"	"5flc,fcu,fluo,fluy"	"alcobon,ancoban,ancobon,ancotil,ancotyl,flourocytosine,flucitosina,flucystine,flucytosin,flucytosine,flucytosinum,flucytosone,fluocytosine,fluorcytosine,fluorocytosine"	10	"g"	10	"g"	""
 "FLM"	3374	"Flumequine"	"Quinolones"	"J01MB07"	"Quinolone antibacterials"	"Other quinolones"	""	"apurone,fantacin,flumequine,flumequino,flumequinum,flumigal,flumiquil,flumisol,flumix,imequyl"	1.2	"g"			"55675-3,55676-1,55677-9,55678-7"
 "FLR1"	71260	"Flurithromycin"	"Macrolides/lincosamides"	"J01FA14"	"Macrolides, lincosamides and streptogramins"	"Macrolides"	""	"flurithromicina,flurithromycime,flurithromycin,flurithromycine,flurithromycinum,fluritromicina,fluritromycinum,flurizic"	0.75	"g"			""
 "FFL"	214356	"Fosfluconazole"	"Antifungals/antimycotics"	"NA"			""	"fosfluconazole,phosfluconazole,procif,prodif"					""
-"FOS"	446987	"Fosfomycin"	"Other antibacterials"	"J01XX01"	"Other antibacterials"	"Other antibacterials"	"ff,fm,fo,fof,fos,fosf"	"calcium fosfomycin,fosfocina,fosfomicin,fosfomicina,fosfomycin,fosfomycin sodium,fosfomycine,fosfomycinum,fosfonomycin,infectophos,monuril,monurol,phosphonemycin,phosphonomycin,veramina"	3	"g"	8	"g"	"25596-8,25653-7,35809-3,35810-1"
+"FOS"	446987	"Fosfomycin"	"Other antibacterials"	"J01XX01,S02AA17"	"Other antibacterials"	"Other antibacterials"	"ff,fm,fo,fof,fos,fosf"	"calcium fosfomycin,fosfocina,fosfomicin,fosfomicina,fosfomycin,fosfomycin sodium,fosfomycine,fosfomycinum,fosfonomycin,infectophos,monuril,monurol,phosphonemycin,phosphonomycin,veramina"	3	"g"	8	"g"	"25596-8,25653-7,35809-3,35810-1"
 "FMD"	572	"Fosmidomycin"	"Other antibacterials"	"NA"			""	"fosmidomycin,fosmidomycina,fosmidomycine,fosmidomycinum"					""
 "FRM"	8378	"Framycetin"	"Aminoglycosides"	"D09AA01,R01AX08,S01AA07"			"fram"	"actilin,actiline,antibiotique,bycomycin,dekamycin iii,endomixin,enterfram,fradiomycin,fradiomycin b,fradiomycinum,framicetina,framidal,framycetin,framycetin sulfate,framycetine,framycetinum,framycin,framygen,francetin,fraquinol,jernadex,myacine,myacyne,mycerin,mycifradin,neobrettin,neolate,neomas,neomcin,neomicina,neomin,neomycin,neomycin b,neomycin b sulfate,neomycin solution,neomycin sulfate,neomycin sulphate,neomycinb,neomycine,neomycinum,nivemycin,pimavecort,soframycin,soframycine,tuttomycin,vonamycin,vonamycin powder v"					"18926-6,257-6,258-4,259-2,260-0,55679-5"
 "FUR"	6870646	"Furazidin"	"Other antibacterials"	"J01XE03"	"Other antibacterials"	"Nitrofuran derivatives"	""	"akritoin,furagin,furaginum,furamag,furazidin,furazidine"	0.3	"g"			""
 "FRZ"	5323714	"Furazolidone"	"Other antibacterials"	"G01AX06"			""	"bifuron,corizium,coryzium,diafuron,enterotoxon,furall,furaxon,furaxone,furazol,furazolidine,furazolidon,furazolidona,furazolidone,furazolidonum,furazolum,furazon,furidon,furovag,furox aerosol powder,furoxal,furoxane,furoxon,furoxone,furoxone liquid,furoxone swine mix,furozolidine,giardil,giarlam,medaron,neftin,nicolen,nifulidone,nifuran,nifurazolidone,nifurazolidonum,nitrofurazolidone,nitrofurazolidonum,nitrofuroxon,optazol,ortazol,puradin,roptazol,sclaventerol,tikofuran,topazone,trichofuron,tricofuron,tricoron,trifurox,viofuragyn"					"69574-2,87794-4"
 "FUS"	3000226	"Fusidic acid"	"Other antibacterials"	"D06AX01,D09AA02,J01XC01,S01AA13"	"Other antibacterials"	"Steroid antibacterials"	"fa,fusi"	"acide fusidique,acido fusidico,acidum fusidicum,flucidin,fucidate,fucidate sodium,fucidic acid,fucidin,fucidin acid,fucithalmic,fusidate,fusidate acid,fusidic acid,fusidicacid,fusidine,fusidinic acid,ramycin,taksta"	1.5	"g"	1.5	"g"	""
-"GAM"	59364992	"Gamithromycin"	"Macrolides/lincosamides"	"NA"			""	"gamithromycin"					"100054-6,88376-9,88378-5"
+"GAM"	59364992	"Gamithromycin"	"Macrolides/lincosamides"	"QJ01FA95"			""	"gamithromycin"					"100054-6,88376-9,88378-5"
 "GRN"	124093	"Garenoxacin"	"Quinolones"	"J01MA19"			""	"ganefloxacin,garenfloxacin,garenoxacin"	0.4	"g"			"35811-9,35812-7,35813-5"
 "GAT"	5379	"Gatifloxacin"	"Quinolones"	"J01MA16,S01AE06"	"Quinolone antibacterials"	"Fluoroquinolones"	"gati"	"gatiflo,gatifloxacin,gatifloxacin hydrate,gatifloxacine,gatifloxcin,gatilox,gatiquin,gatispan,tequin,tequin and zymar,zymaxid"	0.4	"g"	0.4	"g"	"31036-7,31038-3,31040-9,31042-5,41494-6"
-"GEM"	9571107	"Gemifloxacin"	"Quinolones"	"J01MA15"	"Quinolone antibacterials"	"Fluoroquinolones"	""	"factiv,factive,gemifioxacin,gemifloxacin,gemifloxacine,gemifloxacino,gemifloxacinum"	0.32	"g"			"35814-3,35815-0,35816-8,41697-4"
+"GEM"	9571107	"Gemifloxacin"	"Quinolones"	"J01MA15"	"Quinolone antibacterials"	"Fluoroquinolones"	""	"factiv,factive,gemifioxacin,gemifloxacin,gemifloxacine,gemifloxacino,gemifloxacinum"	0.32	"g"	0.2	"g"	"35814-3,35815-0,35816-8,41697-4"
 "GEN"	3467	"Gentamicin"	"Aminoglycosides"	"D06AX07,J01GB03,S01AA11,S02AA14,S03AA06"	"Aminoglycoside antibacterials"	"Other aminoglycosides"	"cn,gen,gent,gm"	"apogen,centicin,cidomycin,garamycin,garasol,genoptic liquifilm,genoptic s.o.p.,gentacycol,gentafair,gentak,gentamar,gentamcin sulfate,gentamicin,gentamicina,gentamicine,gentamicins,gentamicinum,gentamycin,gentamycins,gentamycinum,gentavet,gentocin,jenamicin,lyramycin,oksitselanim,refobacin,refobacin tm,septigen,uromycine"			0.24	"g"	"101494-3,13561-6,13562-4,15106-8,18928-2,18929-0,22746-2,22747-0,266-7,267-5,268-3,269-1,31091-2,31092-0,31093-8,35668-3,35817-6,3663-2,3664-0,3665-7,39082-3,47109-4,50630-3,59379-8,7016-9,7017-7,7018-5,80971-5,88111-0,89481-6"
 "GEH"		"Gentamicin-high"	"Aminoglycosides"	"NA"			"gehi,gehl,genta high,gentamicin high"	""					"18929-0,35817-6,7017-7,7018-5"
 "GEP"	25101874	"Gepotidacin"	"Other antibacterials"	"NA"			""	"gepotidacin"					""
@@ -213,11 +214,11 @@
 "HCH"	11979956	"Hachimycin"	"Antifungals/antimycotics"	"D01AA03,G01AA06,J02AA02"	"Antimycotics for systemic use"	"Antibiotics"	""	"cabimicina,hachimicina,hachimycin,hachimycine,hachimycinum,trichomycinum,trichonat"					""
 "HET"	443387	"Hetacillin"	"Beta-lactams/penicillins"	"J01CA18"	"Beta-lactam antibacterials, penicillins"	"Penicillins with extended spectrum"	""	"etacillina,hetacilina,hetacillin,hetacillin acid,hetacilline,hetacillinum,phenazacillin,versapen"	2	"g"			"18931-6,274-1,275-8,276-6,277-4"
 "HYG"	56928061	"Hygromycin"	"Aminoglycosides"	"NA"			""	"antihelmycin,hydromycin b,hygrovetine"					""
-"IBX"		"Ibrexafungerp"	"Antifungals"	"NA"			""	"ibrexafungerp"					""
+"IBX"		"Ibrexafungerp"	"Antifungals"	"J02AX07"			""	"ibrexafungerp"					""
 "ICL"	213043	"Iclaprim"	"Other antibacterials"	"J01EA03"			""	"iclaprim,mersarex"					"73597-7,73619-9,73642-1"
 "IPM"	104838	"Imipenem"	"Carbapenems"	"J01DH51"	"Other beta-lactam antibacterials"	"Carbapenems"	"imci,imi,imip,imp"	"imipemide,imipenem,imipenem anhydrous,imipenem hydrate,imipenem/cilastatin,imipenemum,imipenen,primaxin,recarbrio .,tienamycin"			2	"g"	"101487-7,17010-0,18932-4,18933-2,23613-3,25221-3,25257-7,27331-8,278-2,279-0,280-8,281-6,282-4,283-2,284-0,285-7,35819-2,3688-9,54170-6,54171-4,54172-2,7019-3,85424-0,93232-7,96372-8"
 "IPE"		"Imipenem/EDTA"	"Carbapenems"	"NA"			""	""					"35819-2,54170-6,54171-4,54172-2"
-"IMR"		"Imipenem/relebactam"	"Carbapenems"	"NA,J01DH56"			""	""					"85424-0,93232-7,96372-8"
+"IMR"		"Imipenem/relebactam"	"Carbapenems"	"NA,J01DH56"			""	""			2	"g"	"85424-0,93232-7,96372-8"
 "ISV"	6918485	"Isavuconazole"	"Antifungals/antimycotics"	"J02AC05"			"isav"	"isavuconazole"	0.2	"g"	0.2	"g"	"85381-2,88887-5"
 "ISE"	3037209	"Isepamicin"	"Aminoglycosides"	"J01GB11"	"Aminoglycoside antibacterials"	"Other aminoglycosides"	""	"isepacin,isepalline,isepamicin,isepamicina,isepamicine,isepamicinsulphate,isepamicinum"			0.4	"g"	"32381-6,35820-0,35821-8,55680-3"
 "ISO"	3760	"Isoconazole"	"Antifungals/antimycotics"	"D01AC05,G01AF07"	"Antimycotics for topic use"	"Triazole derivatives"	""	"isoconazol,isoconazole,isoconazolum,travogen"					"55681-1,55682-9,55683-7,55684-5"
@@ -229,8 +230,8 @@
 "KAH"		"Kanamycin-high"	"Aminoglycosides"	"NA"			"k_h,kahl"	""					"18936-5,7023-5,7024-3"
 "KAC"		"Kanamycin/cephalexin"	"Aminoglycosides"	"NA"			""	""					""
 "KET"	456201	"Ketoconazole"	"Antifungals/antimycotics"	"D01AC08,G01AF11,H02CA03,J02AB02"	"Antimycotics for systemic use"	"Imidazole derivatives"	"keto,ktc"	"extina,fungarest,fungoral,ketocanazole,ketoconazol,ketoconazole,ketoconazolum,ketoderm,nizoral,xolegel"	0.6	"g"			"10990-0,12393-5,18937-3,25259-3,294-9,295-6,296-4,297-2,60091-6,60092-4,7025-0"
-"KIT"		"Kitasamycin"	"Macrolides/lincosamides"	"NA"			"leucomycin"	"jomybel,josacine,josamicina,josamycin,josamycine,josamycinum"					""
-"LAS"	5360807	"Lasalocid"	"Other antibacterials"	"NA"			""	"avatec,lasalocid,lasalocid a,lasalocide,lasalocide a,lasalocido,lasalocidum"					"87598-9"
+"KIT"		"Kitasamycin"	"Macrolides/lincosamides"	"QJ01FA93"			"leucomycin"	"jomybel,josacine,josamicina,josamycin,josamycine,josamycinum"					""
+"LAS"	5360807	"Lasalocid"	"Other antibacterials"	"QP51BB02"			""	"avatec,lasalocid,lasalocid a,lasalocide,lasalocide a,lasalocido,lasalocidum"					"87598-9"
 "LSC"	71528768	"Lascufloxacin"	"Quinolones"	"J01MA25"	"Quinolone antibacterials"	"Fluoroquinolones"	""	"lascufloxacin"	75	"mg"			""
 "LTM"	47499	"Latamoxef"	"Cephalosporins (3rd gen.)"	"J01DD06"	"Other beta-lactam antibacterials"	"Third-generation cephalosporins"	"mox,moxa,moxalactam"	"disodium moxalactam,festamoxin,lamoxactam,latamoxef,latamoxefum,moxalactamsupplement,shiomarin"			4	"g"	""
 "LMU"	25185057	"Lefamulin"	"Other antibacterials"	"J01XX12"			""	"lefamulin,xenleta"					"85425-7,99281-8"
@@ -247,7 +248,7 @@
 "LYM"	54707177	"Lymecycline"	"Tetracyclines"	"J01AA04"	"Tetracyclines"	"Tetracyclines"	""	"biovetin,chlortetracyclin,ciclisin,ciclolysal,ciclolysine,infaciclina,limeciclina,lisinbiotic,lymecyclin,lymecycline,lymecyclinum,mucomycin,ntetracycline,tetralisal,tetralysal,vebicyclysal"	0.6	"g"	0.6	"g"	"18941-5,310-3,311-1,312-9,313-7"
 "MNA"	1292	"Mandelic acid"	"Other antibacterials"	"B05CA06,J01XX06"	"Other antibacterials"	"Other antibacterials"	""	"acido mandelico,almond acid,ammonium mandelate,amygdalic acid,benzoglycolic acid,hydroxyacetic acid,kyselina mandlova,mandelic acid,paramandelic acid,phenylglycolic acid,uromaline"	12	"g"			""
 "MGX"		"Manogepix"	"Antifungals"	"NA"			""	"manogepix"					""
-"MAR"	60651	"Marbofloxacin"	"Quinolones"	"NA"			""	"marbocyl,marbofloxacin,marbofloxacine,marbofloxacino,marbofloxacinum,zeniquin"					"73596-9,73618-1,73641-3"
+"MAR"	60651	"Marbofloxacin"	"Quinolones"	"QJ01MA93"			""	"marbocyl,marbofloxacin,marbofloxacine,marbofloxacino,marbofloxacinum,zeniquin"					"73596-9,73618-1,73641-3"
 "MEC"	36273	"Mecillinam"	"Beta-lactams/penicillins"	"J01CA11"	"Beta-lactam antibacterials, penicillins"	"Penicillins with extended spectrum"	"amdinocillin"	"amdinocillin,coactin,hexacillin,mecilinamo,mecillinam,mecillinamum,micillinam,penicillin hx,selexidin"			1.2	"g"	""
 "MEL"	71306732	"Meleumycin"	"Macrolides/lincosamides"	"NA"			""	""					""
 "MEM"	441130	"Meropenem"	"Carbapenems"	"J01DH02"	"Other beta-lactam antibacterials"	"Carbapenems"	"mem,mer,mero,mp,mrp"	"meronem,meropen,meropenem,meropenem anhydrous,meropenem hydrate,meropenem trihydrate,meropenemum,merrem,merrem i.v.,merrem iv"			3	"g"	"101222-8,101488-5,101489-3,18943-1,41406-0,6651-4,6652-2,6653-0,6654-8,7029-2,85426-5,85427-3,88892-5,90980-4"
@@ -279,9 +280,9 @@
 "NAF"	8982	"Nafcillin"	"Beta-lactams/penicillins"	"J01CF06"			""	"nafcilina,nafcillin,nafcillin sodium,nafcilline,nafcillinum,nallpen,naphcillin,unipen"			3	"g"	"10993-4,18951-4,25232-0,346-7,347-5,348-3,349-1,41704-8"
 "ZWK"	117587595	"Nafithromycin"	"Macrolides/lincosamides"	"NA"			""	"nafithromycin"					""
 "NAL"	4421	"Nalidixic acid"	"Quinolones"	"J01MB02"	"Quinolone antibacterials"	"Other quinolones"	"na,nal,nali"	"acide nalidixico,acide nalidixique,acido nalidissico,acido nalidixico,acidum nalidixicum,betaxina,dixiben,dixinal,eucisten,eucistin,innoxalomn,innoxalon,jicsron,kusnarin,naldixic acid,nalidic acid,nalidicron,nalidixan,nalidixane,nalidixate,nalidixate sodium,nalidixic,nalidixic acid,nalidixicacid,nalidixin,nalidixinic acid,nalidixinsaure,nalitucsan,nalurin,narigix,naxuril,neggram,negram,nevigramon,nicelate,nogram,poleon,sicmylon,specifen,specifin,unaserus,uralgin,uriben,uriclar,urisal,urodixin,uroman,uroneg,uronidix,uropan,wintomylon,wintron"	4	"g"			""
-"NAR"	65452	"Narasin"	"Other antibacterials"	"NA"			""	"monteban,narasin,narasin a,narasine,narasino,narasinum,narasul"					"87570-8"
+"NAR"	65452	"Narasin"	"Other antibacterials"	"QP51BB04"			""	"monteban,narasin,narasin a,narasine,narasino,narasinum,narasul"					"87570-8"
 "NEM"	11993740	"Nemonoxacin"	"Quinolones"	"J01MB08"	"Quinolone antibacterials"	"Other quinolones"	""	"nemonoxacin"					""
-"NEO"	8378	"Neomycin"	"Aminoglycosides"	"A01AB08,A07AA01,B05CA09,D06AX04,J01GB05,R02AB01,S01AA03,S02AA07,S03AA01"	"Aminoglycoside antibacterials"	"Other aminoglycosides"	"neom"	"actilin,actiline,antibiotique,bycomycin,dekamycin iii,endomixin,enterfram,fradiomycin,fradiomycin b,fradiomycinum,framicetina,framidal,framycetin,framycetin sulfate,framycetine,framycetinum,framycin,framygen,francetin,fraquinol,jernadex,myacine,myacyne,mycerin,mycifradin,neobrettin,neolate,neomas,neomcin,neomicina,neomin,neomycin,neomycin b,neomycin b sulfate,neomycin solution,neomycin sulfate,neomycin sulphate,neomycinb,neomycine,neomycinum,nivemycin,pimavecort,soframycin,soframycine,tuttomycin,vonamycin,vonamycin powder v"	5	"g"			"10995-9,18953-0,25262-7,354-1,355-8,356-6,357-4,41705-5"
+"NEO"	8378	"Neomycin"	"Aminoglycosides"	"A01AB08,A07AA01,B05CA09,D06AX04,J01GB05,R02AB01,S01AA03,S02AA07,S03AA01"	"Aminoglycoside antibacterials"	"Other aminoglycosides"	"neom"	"actilin,actiline,antibiotique,bycomycin,dekamycin iii,endomixin,enterfram,fradiomycin,fradiomycin b,fradiomycinum,framicetina,framidal,framycetin,framycetin sulfate,framycetine,framycetinum,framycin,framygen,francetin,fraquinol,jernadex,myacine,myacyne,mycerin,mycifradin,neobrettin,neolate,neomas,neomcin,neomicina,neomin,neomycin,neomycin b,neomycin b sulfate,neomycin solution,neomycin sulfate,neomycin sulphate,neomycinb,neomycine,neomycinum,nivemycin,pimavecort,soframycin,soframycine,tuttomycin,vonamycin,vonamycin powder v"	5	"g"	1	"g"	"10995-9,18953-0,25262-7,354-1,355-8,356-6,357-4,41705-5"
 "NET"	441306	"Netilmicin"	"Aminoglycosides"	"J01GB07,S01AA23"	"Aminoglycoside antibacterials"	"Other aminoglycosides"	"neti"	"netillin,netilmicin,netilmicin sulfate,netilmicina,netilmicine,netilmicinum,netilyn,netira,nettacin,vectacin"	0.35	"g"	0.35	"g"	"18954-8,25263-5,358-2,359-0,360-8,361-6,3848-9,3849-7,3850-5,47385-0,59565-2,59566-0,59567-8,7035-9"
 "NIC"	9507	"Nicarbazin"	"Other antibacterials"	"NA"			""	"nicarb,nicarbasin,nicarbazin,nicarbazine,nicoxin,nicrazin,nicrazine,nirazin"					""
 "NIF"	71946	"Nifuroquine"	"Quinolones"	"NA"			""	"abimasten,nifuroquina,nifuroquine,nifuroquinum,quinaldofur"					""
@@ -294,24 +295,24 @@
 "NME"		"Norfloxacin/metronidazole"	"Other antibacterials"	"J01RA14"	"Combinations of antibacterials"	"Combinations of antibacterials"	""	""					""
 "NTI"		"Norfloxacin/tinidazole"	"Other antibacterials"	"J01RA13"	"Combinations of antibacterials"	"Combinations of antibacterials"	""	""					""
 "NVA"	10419027	"Norvancomycin"	"Glycopeptides"	"NA"			""	"norvancomycin"					""
-"NOV"	54675769	"Novobiocin"	"Other antibacterials"	"NA"			"novo"	"albamix,albamycin,cardelmycin,cathocin,cathomycin,crystallinic acid,inamycin,novobiocin,novobiocina,novobiocine,novobiocinum,robiocina,sirbiocina,spheromycin,stilbiocina,streptonivicin"					"17378-1,18957-1,370-7,371-5,372-3,373-1,41706-3"
+"NOV"	54675769	"Novobiocin"	"Other antibacterials"	"QJ01XX95"			"novo"	"albamix,albamycin,cardelmycin,cathocin,cathomycin,crystallinic acid,inamycin,novobiocin,novobiocina,novobiocine,novobiocinum,robiocina,sirbiocina,spheromycin,stilbiocina,streptonivicin"					"17378-1,18957-1,370-7,371-5,372-3,373-1,41706-3"
 "NYS"	6433272	"Nystatin"	"Antifungals/antimycotics"	"A07AA02,D01AA01,G01AA01"			"nyst"	"biofanal,candex lotion,comycin,diastatin,herniocid,moronal,myconystatin,mycostatin,mycostatin pastilles,mykinac,mykostatyna,nilstat,nistatin,nistatina,nyamyc,nyotran,nyotrantrade mark,nystaform,nystan,nystatin,nystatin a,nystatin g,nystatin hydrate,nystatin lf,nystatine,nystatinum,nystatyna,nystavescent,nystex,nystop,stamycin,terrastatin,zydin e"	1.5	"MU"			"10697-1,10698-9,18958-9,35824-2,55689-4"
 "OFX"	4583	"Ofloxacin"	"Quinolones"	"J01MA01,S01AE01,S02AA16"	"Quinolone antibacterials"	"Fluoroquinolones"	"of,ofl,oflo,ofx"	"bactocin,danoflox,dextrofloxacin,effexin,exocin,exocine,flobacin,flodemex,flotavid,flovid,floxal,floxil,floxin,floxin otic,floxstat,fugacin,inoflox,kinflocin,kinoxacin,levofloxacin hcl,liflox,loxinter,marfloxacin,medofloxine,mergexin,monoflocet,novecin,nufafloqo,occidal,ocuflox,oflocee,oflocet,oflocin,oflodal,oflodex,oflodura,ofloxacin,ofloxacin otic,ofloxacina,ofloxacine,ofloxacino,ofloxacinum,ofloxin,onexacin,operan,orocin,otonil,oxaldin,pharflox,praxin,puiritol,qinolon,quinolon,quotavil,sinflo,tabrin,taravid,tariflox,tarivid,telbit,tructum,uro tarivid,viotisone,visiren,zanocin"	0.4	"g"	0.4	"g"	"18959-7,20384-4,23948-3,25264-3,374-9,375-6,376-4,377-2,3877-8,41408-6,41409-4,41410-2,42653-6,7038-3,72168-8"
 "OOR"		"Ofloxacin/ornidazole"	"Other antibacterials"	"J01RA09"	"Combinations of antibacterials"	"Combinations of antibacterials"	""	""					""
 "OLE"	72493	"Oleandomycin"	"Macrolides/lincosamides"	"J01FA05"	"Macrolides, lincosamides and streptogramins"	"Macrolides"	""	"amimycin,landomycin,matromycin,oleandomicina,oleandomycin,oleandomycin a,oleandomycine,oleandomycinum,romicil"	1	"g"			"18960-5,378-0,379-8,380-6,381-4,55690-2"
 "OMC"	54697325	"Omadacycline"	"Tetracyclines"	"J01AA15"			""	"amadacycline,omadacycline"	0.3	"g"	0.1	"g"	"73594-4,73616-5,73639-7"
 "OPT"	87880	"Optochin"	"Other antibacterials"	"NA"			""	"numoquin,optochin,optoquine"					"100055-3,73665-2"
-"ORB"	60605	"Orbifloxacin"	"Quinolones"	"NA"			""	"orbifloxacin"					"35825-9,35826-7,35827-5"
+"ORB"	60605	"Orbifloxacin"	"Quinolones"	"QJ01MA95"			""	"orbifloxacin"					"35825-9,35826-7,35827-5"
 "ORI"	16136912	"Oritavancin"	"Glycopeptides"	"J01XA05"	"Other antibacterials"	"Glycopeptide antibacterials"	"orit"	"kimyrsa,oritavancin"					"41707-1,41708-9,41709-7,41736-0"
 "ORS"		"Ormetroprim/sulfamethoxazole"	"Other antibacterials"	"NA"			""	""					"73593-6,73615-7,73638-9"
 "ORN"	28061	"Ornidazole"	"Other antibacterials"	"G01AF06,J01XD03,P01AB03"	"Other antibacterials"	"Imidazole derivatives"	""	"madelen,ornidal,ornidazol,ornidazole,ornidazolum,tiberal"	1.5	"g"	1	"g"	"55691-0,55692-8,55693-6,55694-4"
-"OTE"	77050711	"Oteseconazole"	"Antifungals/antimycotics"	"J02AC06"	"Antimycotics for systemic use"	"Triazole derivatives"	""	"oteseconazole"					""
+"OTE"	77050711	"Oteseconazole"	"Antifungals/antimycotics"	"J02AC06"	"Antimycotics for systemic use"	"Triazole derivatives"	""	"oteseconazole"	21	"mg"			""
 "OXA"	6196	"Oxacillin"	"Beta-lactams/penicillins"	"J01CF04"	"Beta-lactam antibacterials, penicillins"	"Beta-lactamase resistant penicillins"	"ox,oxa,oxac,oxal,oxs"	"bactocill,ossacillina,oxacilina,oxacillin,oxacillin sodium,oxacilline,oxacillinum,oxazocillin,oxazocilline,prostaphlin,prostaphlyn,sodium oxacillin"	2	"g"	2	"g"	"18961-3,25265-0,382-2,383-0,384-8,385-5,3882-8,7039-1"
 "OXO"	4628	"Oxolinic acid"	"Quinolones"	"J01MB05"	"Quinolone antibacterials"	"Other quinolones"	""	"acide oxolinique,acido ossolico,acido oxolinico,acidum oxolinicum,aqualinic,cistopax,dioxacin,emyrenil,gramurin,inoxyl,nidantin,oksaren,orthurine,ossian,oxoboi,oxolinic,oxolinic acid,pietil,prodoxal,prodoxol,starner,tiurasin,ultibid,urinox,uritrate,urotrate,uroxol,utibid"	1	"g"			""
-"OXY"	54675779	"Oxytetracycline"	"Tetracyclines"	"D06AA03,G01AA07,J01AA06,S01AA04"	"Tetracyclines"	"Tetracyclines"	""	"adamycin,berkmycen,biostat,biostat pa,bisolvomycin,dabicycline,dalimycin,embryostat,fanterrin,galsenomycin,geomycin,geotilin,hydroxytetracyclinum,imperacin,lenocycline,macocyn,medamycin,mepatar,oksisyklin,ossitetraciclina,oxacycline,oxitetraciclina,oxitetracyclin,oxitetracycline,oxitetracyclinum,oxydon,oxymycin,oxymykoin,oxypam,oxysteclin,oxyterracin,oxyterracine,oxyterracyne,oxytetracid,oxytetracyclin,oxytetracycline,oxytetracycline base,oxytetracyclinum,proteroxyna,riomitsin,ryomycin,solkaciclina,stecsolin,stevacin,tarocyn,tarosin,teravit,terrafungine,terramitsin,terramycin,terramycin im,terramycine,tetran,unimycin,ursocyclin,ursocycline,vendarcin"	1	"g"	1	"g"	"17396-3,18962-1,25266-8,386-3,387-1,388-9,389-7,55699-3,87595-5"
+"OXY"	54675779	"Oxytetracycline"	"Tetracyclines"	"A01AB25,D06AA03,G01AA07,J01AA06,S01AA04"	"Tetracyclines"	"Tetracyclines"	""	"adamycin,berkmycen,biostat,biostat pa,bisolvomycin,dabicycline,dalimycin,embryostat,fanterrin,galsenomycin,geomycin,geotilin,hydroxytetracyclinum,imperacin,lenocycline,macocyn,medamycin,mepatar,oksisyklin,ossitetraciclina,oxacycline,oxitetraciclina,oxitetracyclin,oxitetracycline,oxitetracyclinum,oxydon,oxymycin,oxymykoin,oxypam,oxysteclin,oxyterracin,oxyterracine,oxyterracyne,oxytetracid,oxytetracyclin,oxytetracycline,oxytetracycline base,oxytetracyclinum,proteroxyna,riomitsin,ryomycin,solkaciclina,stecsolin,stevacin,tarocyn,tarosin,teravit,terrafungine,terramitsin,terramycin,terramycin im,terramycine,tetran,unimycin,ursocyclin,ursocycline,vendarcin"	1	"g"	1	"g"	"17396-3,18962-1,25266-8,386-3,387-1,388-9,389-7,55699-3,87595-5"
 "OZN"		"Ozenoxacin"		"D06AX14"			""	"ozadub,ozenoxacin,ozenoxacin cream"					""
 "PAS"	4649	"P-aminosalicylic acid"	"Antimycobacterials"	"NA"			""	"aminopar,aminosalicylic,aminosalicylic acid,aminosalyl,aminox,apacil,deapasil,entepas,ferrosan,gabbropas,granupas,helipidyl,hellipidyl,neopasalate,osacyl,pamacyl,pamisyl,paramycin,parasal,parasalicil,parasalindon,pasalon,pasara,pascorbic,pasdium,paser granules,paskalium,pasmed,pasnodia,pasolac,propasa,rezipas,teebacin"					""
-"PAN"	72015	"Panipenem"	"Carbapenems"	"NA,J01DH55"			""	"panipenem,panipenem/betamipron,panipenemum,penipanem"					"100056-1,53823-1"
+"PAN"	72015	"Panipenem"	"Carbapenems"	"NA,J01DH55"			""	"panipenem,panipenem/betamipron,panipenemum,penipanem"			2	"g"	"100056-1,53823-1"
 "PAR"	165580	"Paromomycin"	"Other antibacterials"	"A07AA06"			""	"aminosidin,aminosidine,aminosidine i,aminosidine sulfate,amminosidin,crestomycin,estomycin,gabbromicina,gabbromycin,gabromycin,humatin,humycin,hydroxymycin,hydroxymycin sulfate,monomycin,monomycin a,neomycin e,paramomycin,paramomycin sulfate,paromomicina,paromomycin,paromomycin i,paromomycine,paromomycinum,paucimycin,paucimycinum,quintomycin c"	3	"g"			"51719-3,53824-9,55700-9,55701-7,55702-5"
 "PAZ"	65957	"Pazufloxacin"	"Quinolones"	"J01MA18"	"Quinolone antibacterials"	"Fluoroquinolones"	""	"pazufloxacin,pazufloxacine,pazufloxacino,pazufloxacinum"			1	"g"	""
 "PEF"	51081	"Pefloxacin"	"Quinolones"	"J01MA03"	"Quinolone antibacterials"	"Fluoroquinolones"	"pefl"	"abactal,labocton,pefloxacin,pefloxacine,pefloxacinium,pefloxacino,pefloxacinum,perfloxacin,silver pefloxacin"	0.8	"g"	0.8	"g"	"18963-9,35828-3,390-5,3906-5,7040-9"
@@ -330,7 +331,7 @@
 "PIS"		"Piperacillin/sulbactam"	"Beta-lactams/penicillins"	"NA"			""	""					"54197-9,54198-7,54199-5,55704-1"
 "TZP"	461573	"Piperacillin/tazobactam"	"Beta-lactams/penicillins"	"J01CR05"	"Beta-lactam antibacterials, penicillins"	"Combinations of penicillins, incl. beta-lactamase inhibitors"	"p/t,piptaz,piptazo,pit,pita,pt,ptc,ptz,tzp"	"tazocel,tazocillin,tazocin,zosyn"			14	"g"	"101491-9,18970-4,411-9,412-7,413-5,414-3,7044-1"
 "PRC"	71978	"Piridicillin"	"Beta-lactams/penicillins"	"NA"			""	"piridicillin"					""
-"PRL"	157385	"Pirlimycin"	"Macrolides/lincosamides"	"NA"			""	"pirlimycin,pirlimycina,pirlimycine,pirlimycinum,pirsue"					"35829-1,35830-9,35831-7"
+"PRL"	157385	"Pirlimycin"	"Macrolides/lincosamides"	"QJ51FF90"			""	"pirlimycin,pirlimycina,pirlimycine,pirlimycinum,pirsue"					"35829-1,35830-9,35831-7"
 "PIR"	4855	"Piromidic acid"	"Quinolones"	"J01MB03"	"Quinolone antibacterials"	"Other quinolones"	""	"acide piromidique,acido piromidico,acidum piromidicum,actrun c,bactramyl,enterol,gastrurol,panacid,pirodal,piromidate,piromidic acid,piromidicacid,pyrido,reelon,septural,urisept,uropir,zaomeal"	2	"g"			""
 "PVM"	33478	"Pivampicillin"	"Beta-lactams/penicillins"	"J01CA02"	"Beta-lactam antibacterials, penicillins"	"Penicillins with extended spectrum"	""	"berocillin,pivaloylampicillin,pivampicilina,pivampicillin,pivampicilline,pivampicillinum,pondocillin"	1.05	"g"			"18971-2,415-0,416-8,417-6,418-4"
 "PME"	115163	"Pivmecillinam"	"Beta-lactams/penicillins"	"J01CA08"	"Beta-lactam antibacterials, penicillins"	"Penicillins with extended spectrum"	""	"amdinocillin pivoxil,coactabs,hydroxymethyl,pivmecilinamo,pivmecillinam,pivmecillinam hcl,pivmecillinamum"	0.6	"g"			""
@@ -338,9 +339,9 @@
 "PLB"	49800004	"Polymyxin B"	"Polymyxins"	"A07AA05,J01XB02,S01AA18,S02AA11,S03AA03"	"Other antibacterials"	"Polymyxins"	"pb,pol,polb,poly,poly b,polymixin,polymixin b"	"polimixina b,polumyxin b,polymixin b,polymyxine b"	3	"MU"	0.15	"g"	"17473-0,18972-0,25269-2,35832-5,419-2,420-0,421-8,422-6"
 "POP"		"Polymyxin B/polysorbate 80"	"Polymyxins"	"NA"			""	""					""
 "POS"	468595	"Posaconazole"	"Antifungals/antimycotics"	"J02AC04"	"Antimycotics for systemic use"	"Triazole derivatives"	"posa"	"noxafil,posaconazole,posaconazole sp,posconazole"	0.3	"g"	0.3	"g"	"53731-6,54186-2,54187-0,54188-8,54189-6,80545-7"
-"PRA"	9802884	"Pradofloxacin"	"Quinolones"	"NA"			""	"pradofloxacin,pudofloxacin,veraflox"					"76148-6,87800-9"
+"PRA"	9802884	"Pradofloxacin"	"Quinolones"	"QJ01MA97"			""	"pradofloxacin,pudofloxacin,veraflox"					"76148-6,87800-9"
 "PRX"	71455	"Premafloxacin"	"Quinolones"	"NA"			""	"premafloxacin,remafloxacin"					"73591-0,73613-2,73636-3"
-"PMD"	456199	"Pretomanid"	"Antimycobacterials"	"J04AK08"	"Drugs for treatment of tuberculosis"	"Other drugs for treatment of tuberculosis"	""	"oxazine,pretomanid"					"93850-6"
+"PMD"	456199	"Pretomanid"	"Antimycobacterials"	"J04AK08"	"Drugs for treatment of tuberculosis"	"Other drugs for treatment of tuberculosis"	""	"oxazine,pretomanid"	0.2	"g"			"93850-6"
 "PRM"	6446787	"Primycin"	"Macrolides/lincosamides"	"NA"			""	"primycin"					""
 "PRI"	11979535	"Pristinamycin"	"Macrolides/lincosamides"	"J01FG01"	"Macrolides, lincosamides and streptogramins"	"Streptogramins"	"pris"	"eskalin v,mikamycin,mikamycine,mikamycinum,ostreogrycinum,pristinamycine,pristinamycinum,stafac,stafytracine,staphylomycin,starfac,streptogramin,vernamycin,virgimycin,virgimycine,virginiamycin,virginiamycina,virginiamycine,virginiamycinum"	2	"g"			"32383-2,35833-3,35834-1,55709-0"
 "PRB"	5903	"Procaine benzylpenicillin"	"Beta-lactams/penicillins"	"J01CE09"	"Beta-lactam antibacterials, penicillins"	"Beta-lactamase sensitive penicillins"	""	"depocillin,duphapen,hostacillin,hydracillin,jenacillin o,nopcaine,penicillin procaine,retardillin,vetspen,vitablend"			0.6	"g"	""
@@ -349,13 +350,13 @@
 "PTH"	666418	"Protionamide"	"Antimycobacterials"	"J04AD01"	"Drugs for treatment of tuberculosis"	"Thiocarbamide derivatives"	"prot"	"ektebin,peteha,prothionamide,prothionamidum,protion,protionamid,protionamida,protionamide,protionamidum,protionizina,tebeform,trevintix,tuberex"	0.75	"g"			""
 "PRU"	65947	"Prulifloxacin"	"Quinolones"	"J01MA17"	"Quinolone antibacterials"	"Fluoroquinolones"	""	"prulifloxacin,pruvel,pufloxacin dioxolil,quisnon"	0.6	"g"			"100058-7,76145-2"
 "PZA"	1046	"Pyrazinamide"	"Antimycobacterials"	"J04AK01"	"Drugs for treatment of tuberculosis"	"Other drugs for treatment of tuberculosis"	"pyra"	"aldinamid,aldinamide,braccopiral,corsazinmid,dipimide,eprazin,farmizina,isopas,lynamide,novamid,p ezetamid,pezetamid,pharozinamide,piraldina,pirazimida,pirazinamid,pirazinamida,pirazinamide,prazina,pyrafat,pyramide,pyrazide,pyrazinamdie,pyrazinamid,pyrazinamide,pyrazinamidum,pyrazine carboxamide,pyrazineamide,pyrizinamide,rifafour,rozide,tebrazid,tebrazio,tisamid,unipyranamide,zinamide,zinastat"	1.5	"g"			"11001-5,18973-8,20461-0,23632-3,25186-8,25229-6,25270-0,423-4,424-2,425-9,426-7,42935-7,55710-8,55711-6,56026-8,92242-7"
-"QDA"	11979418	"Quinupristin/dalfopristin"	"Macrolides/lincosamides"	"J01FG02"	"Macrolides, lincosamides and streptogramins"	"Streptogramins"	"q/d,qda,qida,quda,rp,syn"	""			1.5	"g"	"23640-6,23641-4,33334-4,35835-8,58712-1"
+"QDA"	11979418	"Quinupristin/dalfopristin"	"Macrolides/lincosamides"	"QJ01FG02"	"Macrolides, lincosamides and streptogramins"	"Streptogramins"	"q/d,qda,qida,quda,rp,syn"	""					"23640-6,23641-4,33334-4,35835-8,58712-1"
 "RAC"	56052	"Ractopamine"	"Other antibacterials"	"NA"			""	"optaflexx,paylean,ractopamina,ractopamine,ractopaminum"					""
 "RAM"	16132338	"Ramoplanin"	"Glycopeptides"	"NA"			""	"ramoplanin"					"41710-5,41711-3,41712-1,41737-8"
 "RZM"	10993211	"Razupenem"	"Carbapenems"	"NA"			""	"razupenem"					"73590-2,73612-4,73635-5"
 "RTP"	6918462	"Retapamulin"	"Other antibacterials"	"D06AX13"	"Antibiotics for topical use"	"Other antibiotics for topical use"	"ret"	"altabax,altargo,retapamulin"					""
 "RZF"		"Rezafungin"	"Antifungals"	"NA"			""	"biafungin,rezafungin cation,rezafungin ion"					""
-"RBC"	44631912	"Ribociclib"	"Antifungals/antimycotics"	"L01EF02"	"Antimycotics for systemic use"	"Triazole derivatives"	"ribo"	"kisqali,ribociclib"	0.45				""
+"RBC"	44631912	"Ribociclib"	"Antifungals/antimycotics"	"L01EF02"	"Antimycotics for systemic use"	"Triazole derivatives"	"ribo"	"kisqali,ribociclib"	0.45	"g"			""
 "RST"	33042	"Ribostamycin"	"Aminoglycosides"	"J01GB10"	"Aminoglycoside antibacterials"	"Other aminoglycosides"	""	"dekamycin iv,hetangmycin,ribastamin,ribostamicina,ribostamycin,ribostamycine,ribostamycinum,vistamycin,xylostatin"			1	"g"	""
 "RID1"	16659285	"Ridinilazole"	"Other antibacterials"	"NA"			""	"ridinilazole"					""
 "RIB"	135398743	"Rifabutin"	"Antimycobacterials"	"J04AB04"	"Drugs for treatment of tuberculosis"	"Antibiotics"	"rifb"	"alfacid,ansamicin,ansamycin,ansatipin,ansatipine,assatipin,mycobutin,rifabutin,rifabutina,rifabutine,rifabutinum"	0.15	"g"			"100699-8,16100-0,16386-5,16387-3,19149-4,20386-9,23630-7,24032-5,25199-1,25200-7,25201-5,42655-1,42656-9,54183-9,96113-6"
@@ -364,7 +365,7 @@
 "RFI"		"Rifampicin/isoniazid"	"Antimycobacterials"	"J04AM02"	"Drugs for treatment of tuberculosis"	"Combinations of drugs for treatment of tuberculosis"	""	"rifinah,rimactazid"					""
 "RPEI"		"Rifampicin/pyrazinamide/ethambutol/isoniazid"	"Antimycobacterials"	"J04AM06"	"Drugs for treatment of tuberculosis"	"Combinations of drugs for treatment of tuberculosis"	""	""					""
 "RPI"		"Rifampicin/pyrazinamide/isoniazid"	"Antimycobacterials"	"J04AM05"	"Drugs for treatment of tuberculosis"	"Combinations of drugs for treatment of tuberculosis"	""	""					""
-"RFM"	6324616	"Rifamycin"	"Antimycobacterials"	"A07AA13,D06AX15,J04AB03,S01AA16,S02AA12"	"Drugs for treatment of tuberculosis"	"Antibiotics"	""	"aemcolo,rifacin,rifamicina,rifamicine sv,rifamycin,rifamycine,rifamycinum,rifocin,rifocyn,rifomycin,rifomycin sv,tuborin"			0.6	"g"	""
+"RFM"	6324616	"Rifamycin"	"Antimycobacterials"	"A07AA13,D06AX15,J04AB03,S01AA16,S02AA12"	"Drugs for treatment of tuberculosis"	"Antibiotics"	""	"aemcolo,rifacin,rifamicina,rifamicine sv,rifamycin,rifamycine,rifamycinum,rifocin,rifocyn,rifomycin,rifomycin sv,tuborin"	0.8	"g"	0.6	"g"	""
 "RFP"	135403821	"Rifapentine"	"Antimycobacterials"	"J04AB05"	"Drugs for treatment of tuberculosis"	"Antibiotics"	"rifp,rpt"	"cyclopentyl rifampin,prifitin,priftin,rifapentin,rifapentina,rifapentine,rifapentinum"	0.11	"g"			"100059-5,76627-9"
 "RFX"	6436173	"Rifaximin"	"Other antibacterials"	"A07AA11,D06AX11"	"Intestinal antiinfectives"	"Antibiotics"	""	"fatroximin,flonorm,lormyx,lumenax,normix,redactiv,rifacol,rifamixin,rifaxidin,rifaximin,rifaximina,rifaximine,rifaximinum,rifaxin,ritacol,spiraxin,xifaxan,xifaxsan"	0.6	"g"			"73589-4,73611-6,73634-8"
 "RIT"	65633	"Ritipenem"	"Carbapenems"	"NA"			""	"ritipenem"					""
@@ -374,8 +375,8 @@
 "ROS"	287180	"Rosoxacin"	"Quinolones"	"J01MB01"	"Quinolone antibacterials"	"Other quinolones"	""	"acrosoxacin,eracine,eradacil,eradacin,eradicin,rosoxacin,rosoxacine,rosoxacino,rosoxacinum,roxadyl,winoxacin,winuron"	0.3	"g"			"18977-9,439-0,440-8,441-6,442-4,55713-2"
 "RXT"		"Roxithromycin"	"Macrolides/lincosamides"	"J01FA06"	"Macrolides, lincosamides and streptogramins"	"Macrolides"	"roxi"	"roxithromycin,roxithromycine,roxithromycinum,roxitromicina,rulide"	0.3	"g"			"18978-7,443-2,444-0,445-7,446-5,7046-6"
 "RFL"	58258	"Rufloxacin"	"Quinolones"	"J01MA10"	"Quinolone antibacterials"	"Fluoroquinolones"	""	"rufloxacin,rufloxacin hcl,rufloxacine,rufloxacino,rufloxacinum"	0.2	"g"			""
-"SAL"	3085092	"Salinomycin"	"Other antibacterials"	"NA"			""	"coxistac,procoxacin,salinomicina,salinomycin,salinomycine,salinomycinum"					"35836-6,35837-4,35838-2,87593-0"
-"SAR"	56208	"Sarafloxacin"	"Quinolones"	"NA"			""	"difloxacine,difloxacino,difloxacinum,quinolone der.,saraflox,sarafloxacin,sarafloxacine,sarafloxacino,sarafloxacinum"					"73588-6,73610-8,73633-0"
+"SAL"	3085092	"Salinomycin"	"Other antibacterials"	"QP51BB01"			""	"coxistac,procoxacin,salinomicina,salinomycin,salinomycine,salinomycinum"					"35836-6,35837-4,35838-2,87593-0"
+"SAR"	56208	"Sarafloxacin"	"Quinolones"	"QJ01MA98"			""	"difloxacine,difloxacino,difloxacinum,quinolone der.,saraflox,sarafloxacin,sarafloxacine,sarafloxacino,sarafloxacinum"					"73588-6,73610-8,73633-0"
 "SRC"	54681908	"Sarecycline"	"Tetracyclines"	"J01AA14"	"Tetracyclines"	"Tetracyclines"	""	"sarecycline,seysara"	0.1	"g"			""
 "SRX"	9933415	"Sarmoxicillin"	"Beta-lactams/penicillins"	"NA"			""	"sarmoxicillin"					""
 "SEC"	71815	"Secnidazole"	"Other antibacterials"	"P01AB07"			""	"flagentyl,secnidal,secnidazol,secnidazole,secnidazolum,secnil,sindose,solosec"	2	"g"			""
@@ -395,7 +396,7 @@
 "SUL"	130313	"Sulbactam"	"Beta-lactams/penicillins"	"J01CG01"	"Beta-lactam antibacterials, penicillins"	"Beta-lactamase inhibitors"	""	"betamaze,sulbactam,sulbactam acid,sulbactam free acid,sulbactamum"			1	"g"	"41716-2,41717-0,41718-8,41739-4"
 "SBC"	20055036	"Sulbenicillin"	"Beta-lactams/penicillins"	"J01CA16"	"Beta-lactam antibacterials, penicillins"	"Penicillins with extended spectrum"	""	"kedacillina,sulbenicilina,sulbenicillin,sulbenicilline,sulbenicillinum"			15	"g"	""
 "SUC"	5318	"Sulconazole"	"Antifungals/antimycotics"	"D01AC09"			""	"sulconazol,sulconazole,sulconazolum"					""
-"SUP"	6634	"Sulfachlorpyridazine"	"Other antibacterials"	"NA"			""	"cluricol,cosulid,cosumix,durasulf,nefrosul,nsulfanilamide,prinzone vet,prinzone vet.,solfaclorpiridazina,sonilyn,sulfachlorpyridazine,sulfacloropiridazina,vetisulid"					""
+"SUP"	6634	"Sulfachlorpyridazine"	"Other antibacterials"	"QJ01EQ12"			""	"cluricol,cosulid,cosumix,durasulf,nefrosul,nsulfanilamide,prinzone vet,prinzone vet.,solfaclorpiridazina,sonilyn,sulfachlorpyridazine,sulfacloropiridazina,vetisulid"					""
 "SDI"	5215	"Sulfadiazine"	"Trimethoprims"	"J01EC02"	"Sulfonamides and trimethoprim"	"Intermediate-acting sulfonamides"	""	"adiazin,adiazine,cocodiazine,codiazine,cremodiazine,cremotres,debenal,deltazina,diazin,diazolone,diazovit,diazyl,eskadiazine,honey diazine,liquadiazine,microsulfon,neazine,neotrizine,nsulfanilamide,palatrize,piridisir,pirimal,pyrimal,quadetts,quadramoid,sanodiazine,sildaflo,silvadene,solfadiazina,spofadrizine,sterazine,sulfacombin,sulfadiazene,sulfadiazin,sulfadiazina,sulfadiazine,sulfadiazinum,sulfapirimidin,sulfapyrimidin,sulfapyrimidine,sulfatryl,sulfazine,sulfolex,sulfonamides duplex,sulfonsol,sulfose,sulphadiazine,sulphadiazine e,terfonyl,theradiazine,thermazene,trifonamide,triple sulfa,triple sulfas,trisem,truozine,zinc sulfadiazine"	0.6	"g"			"18984-5,27216-1,463-0,464-8,465-5,466-3,59742-7,6907-0,7050-8"
 "SLT"	122284	"Sulfadiazine/tetroxoprim"	"Trimethoprims"	"J01EE06"	"Sulfonamides and trimethoprim"	"Combinations of sulfonamides and trimethoprim, incl. derivatives"	""	"cotetroxazine"					""
 "SLT1"	64932	"Sulfadiazine/trimethoprim"	"Trimethoprims"	"J01EE02"	"Sulfonamides and trimethoprim"	"Combinations of sulfonamides and trimethoprim, incl. derivatives"	""	"antastmon,cotrimazine,diaziprim forte,ditrim,ditrivet,sultrisan,triglobe,trimin,tucoprim,uniprim"					""
@@ -432,7 +433,7 @@
 "TAL"	71447	"Talampicillin"	"Beta-lactams/penicillins"	"J01CA15"	"Beta-lactam antibacterials, penicillins"	"Penicillins with extended spectrum"	""	"talampicilina,talampicillin,talampicilline,talampicillinum"	2	"g"			"18988-6,479-6,480-4,481-2,482-0"
 "TLP"	163307	"Talmetoprim"	"Other antibacterials"	"NA"			""	"talmetoprim"					""
 "TAZ"	123630	"Tazobactam"	"Beta-lactams/penicillins"	"J01CG02"	"Beta-lactam antibacterials, penicillins"	"Beta-lactamase inhibitors"	"tazo"	"tazobactam,tazobactam acid,tazobactamum,tazobactum"					"41719-6,41720-4,41721-2,41740-2"
-"TBP"	9800194	"Tebipenem"	"Carbapenems"	"NA,J01DH06"			""	"tebipenem pivoxil"					""
+"TBP"	9800194	"Tebipenem"	"Carbapenems"	"NA,J01DH06"			""	"tebipenem pivoxil"	0.56	"g"			""
 "TZD"	11234049	"Tedizolid"	"Oxazolidinones"	"J01XX11"	"Other antibacterials"	"Other antibacterials"	"tedi"	"sivextro,tedizolid,torezolid"	0.2	"g"	0.2	"g"	"73586-0,73608-2,73631-4"
 "TEC"	16131923	"Teicoplanin"	"Glycopeptides"	"J01XA02"	"Other antibacterials"	"Glycopeptide antibacterials"	"tec,tei,teic,tp,tpl,tpn"	"targocid,tecoplanina,tecoplanine,tecoplaninum,teichomycin,teicoplanin,teicoplanina,teicoplanine,teicoplaninum"			0.4	"g"	"18989-4,25534-9,25535-6,34378-0,34379-8,4043-6,483-8,484-6,485-3,486-1,7051-6,80968-1"
 "TCM"		"Teicoplanin-macromethod"	"Glycopeptides"	"NA"			""	""					""
@@ -450,29 +451,29 @@
 "THI"	27200	"Thiamphenicol"	"Amphenicols"	"J01BA02"	"Amphenicols"	"Amphenicols"	""	"descocin,dexawin,dextrosulfenidol,dextrosulphenidol,efnicol,hyrazin,igralin,macphenicol,masatirin,neomyson,racefenicol,racefenicolo,racefenicolum,raceophenidol,racephenicol,rincrol,thiamcol,thiamphenicol,thiamphenicolum,thiocymetin,thiomycetin,thiophenicol,tiamfenicol,tiamfenicolo,urfamicina,urfamycine,vicemycetin"	1.5	"g"	1.5	"g"	"41723-8,41724-6,41725-3,54169-8"
 "TAT"	9568512	"Thioacetazone"	"Antimycobacterials"	"J04AK07"	"Drugs for treatment of tuberculosis"	"Other drugs for treatment of tuberculosis"	""	"aktivan,ambathizon,amithiozone,amitiozon,benthiozone,benzothiozane,benzothiozon,berculon a,berkazon,citazone,conteben,diasan,domakol,ilbion,livazone,mirizone neustab,mivizon,myvizone,neotibil,neustab,novakol,nuclon argentinian,panrone,parazone,seroden,siocarbazone,tebalon,tebecure,tebemar,tebesone i,tebethion,tebethione,tebezon,thiacetone,thiacetozone,thibon,thibone,thioacetazon,thioacetazone,thioacetazonum,thioazetazone,thiocarbazil,thiomicid,thionicid,thioparamizon,thioparamizone,thiosemicarbarzone,thiosemicarbazone,thiotebesin,thiotebezin,thiotebicina,thizone,tiacetazon,tibicur,tibion,tibione,tibizan,tibone,tioacetazon,tioacetazona,tioatsetazon,tiobicina,tiocarone,tiosecolo,tubercazon,tubigal"					""
 "THI1"		"Thioacetazone/isoniazid"	"Antimycobacterials"	"J04AM04"	"Drugs for treatment of tuberculosis"	"Combinations of drugs for treatment of tuberculosis"	""	""					""
-"TIA"	656958	"Tiamulin"	"Other antibacterials"	"NA"			""	"denagard,thiamutilin,tiamulin,tiamulin pamoate,tiamulina,tiamuline,tiamulinum,tiavet p"					"35846-5,35847-3,35848-1,87589-8"
+"TIA"	656958	"Tiamulin"	"Other antibacterials"	"QJ01XQ01"			""	"denagard,thiamutilin,tiamulin,tiamulin pamoate,tiamulina,tiamuline,tiamulinum,tiavet p"					"35846-5,35847-3,35848-1,87589-8"
 "TIC"	36921	"Ticarcillin"	"Beta-lactams/penicillins"	"J01CA13"	"Beta-lactam antibacterials, penicillins"	"Penicillins with extended spectrum"	"tc,ti,tic,tica"	"ticarcilina,ticarcillin,ticarcilline,ticarcillinum,ticillin,timentin"			15	"g"	"18994-4,18995-1,25254-4,4054-3,4055-0,499-4,500-9,501-7,502-5,503-3,504-1,505-8,506-6,55716-5,55717-3,55718-1,55719-9,7053-2,7054-0"
 "TCC"	6437075	"Ticarcillin/clavulanic acid"	"Beta-lactams/penicillins"	"J01CR03"	"Beta-lactam antibacterials, penicillins"	"Combinations of penicillins, incl. beta-lactamase inhibitors"	"t/c,tcc,ticl,tim,tlc"	"timentin"			15	"g"	""
 "TGC"	54686904	"Tigecycline"	"Tetracyclines"	"J01AA12"	"Tetracyclines"	"Tetracyclines"	"tgc,tig,tige"	"haizheng li xing,tigeciclina,tigecyclin,tigecycline,tigecycline hydrate,tigecyclinum,tigilcycline,tygacil"			0.1	"g"	"101499-2,42354-1,42355-8,42356-6,42357-4,55158-0"
 "TBQ"	65592	"Tilbroquinol"	"Quinolones"	"P01AA05"			""	"tilbroquinol,tilbroquinolum"					""
-"TIP"	24860548	"Tildipirosin"	"Macrolides/lincosamides"	"NA"			""	"tildipirosin,zuprevo"					"100060-3,88375-1,88377-7"
-"TIL"	5282521	"Tilmicosin"	"Macrolides/lincosamides"	"NA"			""	"micotil,pulmotil,tilmicosin,tilmicosina,tilmicosine,tilmicosinum"					"35849-9,35850-7,35851-5,87588-0"
-"TIN"	5479	"Tinidazole"	"Other antibacterials"	"J01XD02,P01AB02"	"Other antibacterials"	"Imidazole derivatives"	"tini"	"amtiba,bioshik,ethyl sulfone,fasigin,fasigyn,fasigyntrade mark,fasygin,glongyn,haisigyn,pletil,simplotan,simplotantrade mark,sorquetan,symplotan,tindamax,tindamaxtrade mark,tinidazol,tinidazole,tinidazolum,tricolam,trimonase"	2	"g"	1.5	"g"	"54928-7,55720-7,55721-5,55722-3"
+"TIP"	24860548	"Tildipirosin"	"Macrolides/lincosamides"	"QJ01FA96"			""	"tildipirosin,zuprevo"					"100060-3,88375-1,88377-7"
+"TIL"	5282521	"Tilmicosin"	"Macrolides/lincosamides"	"QJ01FA91"			""	"micotil,pulmotil,tilmicosin,tilmicosina,tilmicosine,tilmicosinum"					"35849-9,35850-7,35851-5,87588-0"
+"TIN"	5479	"Tinidazole"	"Other antibacterials"	"G01AF21,J01XD02,P01AB02"	"Other antibacterials"	"Imidazole derivatives"	"tini"	"amtiba,bioshik,ethyl sulfone,fasigin,fasigyn,fasigyntrade mark,fasygin,glongyn,haisigyn,pletil,simplotan,simplotantrade mark,sorquetan,symplotan,tindamax,tindamaxtrade mark,tinidazol,tinidazole,tinidazolum,tricolam,trimonase"	2	"g"	1.5	"g"	"54928-7,55720-7,55721-5,55722-3"
 "TCR"	3001386	"Tiocarlide"	"Antimycobacterials"	"J04AD02"	"Drugs for treatment of tuberculosis"	"Thiocarbamide derivatives"	""	"amixyl,datanil,disocarban,disoxyl,isoxyl,thiocarlide,tiocarlid,tiocarlida,tiocarlide,tiocarlidum"	7	"g"			""
 "TDC"	10247721	"Tiodonium chloride"	"Other antibacterials"	"NA"			""	"cloruro de tiodonio,tiodonii chloridum,tiodonium chloride"					""
 "TXC"	65788	"Tioxacin"	"Quinolones"	"NA"			""	"tioxacin,tioxacine,tioxacino,tioxacinum,tioxic acid"					""
 "TIZ"	394397	"Tizoxanide"	"Other antibacterials"	"NA"			""	"ntzdes"					"73585-2,73607-4,73629-8"
 "TOB"	36294	"Tobramycin"	"Aminoglycosides"	"J01GB01,S01AA12"	"Aminoglycoside antibacterials"	"Other aminoglycosides"	"nn,tm,to,tob,tobr"	"bethkis,brulamycin,deoxykanamycin b,distobram,gernebcin,gotabiotic,kitabis,kitabis pak,nebcin,nebicin,nebramycin,nebramycin vi,obramycin,sybryx,tenebrimycin,tenemycin,tobacin,tobi podhaler,tobracin,tobradex,tobradistin,tobralex,tobramaxin,tobramicin,tobramicina,tobramitsetin,tobramycetin,tobramycin,tobramycin base,tobramycin sulfate,tobramycine,tobramycinum,tobrased,tobrasone,tobrex"			0.24	"g"	"101496-8,13584-8,17808-7,18996-9,22750-4,22751-2,22752-0,25227-0,25800-4,31094-6,31095-3,31096-1,35239-3,35670-9,4057-6,4058-4,4059-2,507-4,508-2,509-0,50927-3,510-8,52962-8,59380-6,7055-7,80966-5"
 "TOH"		"Tobramycin-high"	"Aminoglycosides"	"NA"			"tobra high,tobramycin high,tohl"	""					""
-"TFX"	5517	"Tosufloxacin"	"Quinolones"	"J01MA22"			""	"tosufloxacin"	0.45	"g"			"100061-1,76146-0"
+"TFX"	5517	"Tosufloxacin"	"Quinolones"	"J01MA22,S01AE09"			""	"tosufloxacin"	0.45	"g"			"100061-1,76146-0"
 "TMP"	5578	"Trimethoprim"	"Trimethoprims"	"J01EA01"	"Sulfonamides and trimethoprim"	"Trimethoprim and derivatives"	"t,tmp,tr,tri,trim,w"	"abaprim,alprim,anitrim,antrima,antrimox,bacdan,bacidal,bacide,bacterial,bacticel,bactifor,bactin,bactoprim,bactramin,bactrim,bencole,bethaprim,biosulten,briscotrim,chemotrin,colizole,colizole ds,conprim,cotrimel,cotrimoxizole,deprim,dosulfin,duocide,esbesul,espectrin,euctrim,exbesul,fermagex,fortrim,idotrim,ikaprim,infectotrimet,instalac,kombinax,lagatrim,lagatrim forte,lastrim,lescot,methoprim,metoprim,monoprim,monotrim,monotrimin,novotrimel,omstat,oraprim,pancidim,polytrim,priloprim,primosept,primsol,proloprim,protrin,purbal,resprim,resprim forte,roubac,roubal,salvatrim,septrin ds,septrin forte,septrin s,setprin,sinotrim,stopan,streptoplus,sugaprim,sulfamar,sulfamethoprim,sulfoxaprim,sulthrim,sultrex,syraprim,tiempe,tmp smx,toprim,trimanyl,trimethioprim,trimethopim,trimethoprim,trimethoprime,trimethoprimum,trimethopriom,trimetoprim,trimetoprima,trimexazole,trimexol,trimezol,trimogal,trimono,trimopan,trimpex,triprim,trisul,trisulcom,trisulfam,trisural,uretrim,urobactrim,utetrin,velaten,wellcoprim,wellcoprin,xeroprim,zamboprim"	0.4	"g"	0.4	"g"	"101495-0,11005-6,17747-7,18997-7,18998-5,20387-7,23614-1,23631-5,25273-4,32342-8,4079-0,4080-8,4081-6,511-6,512-4,513-2,514-0,515-7,516-5,517-3,518-1,55584-7,7056-5,7057-3,80552-3,80973-1"
 "SXT"	358641	"Trimethoprim/sulfamethoxazole"	"Trimethoprims"	"J01EE01"	"Sulfonamides and trimethoprim"	"Combinations of sulfonamides and trimethoprim, incl. derivatives"	"cot,cotrim,sxt,t/s,trsu,trsx,ts"	"abacin,abactrim,agoprim,alfatrim,aposulfatrim,bacteral,bacterial forte,bactilen,bactiver,bacton,bactoreduct,bactrim,bactrim ds,bactrim forte,bactrim pediatric,bactrimel,bactrizol,bactromin,bactropin,baktar,belcomycine,berlocid,bibacrim,biseptol,chemitrim,chemotrim,ciplin,colimycin,colimycin sulphate,colisticin,colistimethate,colistimethate sodium,colistin sulfate,colistin sulphate,colomycin,coly-mycin,cotribene,cotrim d.s.,cotrim eu rho,cotrim holsen,cotrim.l.u.t.,cotrimaxazol,cotrimazole,cotrimhexal,cotrimoxazol,cotrimoxazol al,cotrimoxazole,cotrimstada,cotriver,dibaprim,drylin,duratrimet,eltrianyl,escoprim,esteprim,eusaprim,fectrim,gantaprim,gantaprin,gantrim,groprim,helveprim,imexim,jenamoxazol,kemoprim,kepinol,kepinol forte,laratrim,linaris,maxtrim,microtrim,microtrim forte,mikrosid,momentol,oecotrim,oriprim,oxaprim,pantoprim,polymyxin e,polymyxin e. sulfate,primazole,promixin,septra,septra ds,septra grape,septrim,septrin,servitrim,sigaprim,sigaprin,sulfatrim pediatric,sulfotrim,sulfotrimin,sulmeprim pediatric,sulprim,sumetrolim,supracombin,suprim,tacumil,teleprim,teleprin,thiocuran,totazina,tribakin,trifen,trigonyl,trimesulf,trimetho comp,trimethoprimsulfa,trimetoger,trimexazol,trimforte,trimosulfa,uroplus,uroplus ds,uroplus ss"					"101495-0,18998-5,20387-7,23631-5,25273-4,32342-8,4081-6,515-7,516-5,517-3,518-1,7057-3"
 "TRL"	202225	"Troleandomycin"	"Macrolides/lincosamides"	"J01FA08"	"Macrolides, lincosamides and streptogramins"	"Macrolides"	""	"acetyloleandomycin,aovine,cyclamycin,evramicina,matromicina,matromycin t,micotil,oleandocetine,oleandomycin,t.a.o.,treolmicina,tribiocillina,triocetin,triolan,troleandomicina,troleandomycin,troleandomycine,troleandomycinum,viamicina,wytrion"	1	"g"			"18999-3,519-9,520-7,521-5,522-3"
 "TRO"	55886	"Trospectomycin"	"Other antibacterials"	"NA"			""	"rubidiumnitrate,trospectinomycin,trospectomicina,trospectomycin,trospectomycine,trospectomycinum"					""
 "TVA"	62959	"Trovafloxacin"	"Quinolones"	"J01MA13"	"Quinolone antibacterials"	"Fluoroquinolones"	"trov"	"trovafloxacin,trovan"	0.2	"g"	0.2	"g"	"23642-2,23643-0,35855-6,7058-1"
-"TUL"	9832301	"Tulathromycin"	"Macrolides/lincosamides"	"NA"			""	"draxxin,tulathrmycin a,tulathromycin,tulathromycin a"					"76149-4,87798-5"
-"TYL"	5280440	"Tylosin"	"Macrolides/lincosamides"	"NA"			""	"fradizine,tilosina,tylocine,tylosin,tylosin a,tylosine,tylosinum"					"35856-4,35857-2,35858-0,87587-2"
-"TYL1"	6441094	"Tylvalosin"	"Macrolides/lincosamides"	"NA"			"tvn"	"tylvalosin"					"101526-2,87586-4"
+"TUL"	9832301	"Tulathromycin"	"Macrolides/lincosamides"	"QJ01FA94"			""	"draxxin,tulathrmycin a,tulathromycin,tulathromycin a"					"76149-4,87798-5"
+"TYL"	5280440	"Tylosin"	"Macrolides/lincosamides"	"QJ01FA90,QJ51FA90"			""	"fradizine,tilosina,tylocine,tylosin,tylosin a,tylosine,tylosinum"					"35856-4,35857-2,35858-0,87587-2"
+"TYL1"	6441094	"Tylvalosin"	"Macrolides/lincosamides"	"QJ01FA92"			"tvn"	"tylvalosin"					"101526-2,87586-4"
 "PRU1"	124225	"Ulifloxacin (Prulifloxacin)"	"Other antibacterials"	"NA"			""	"ulifloxacin"					""
 "VAN"	14969	"Vancomycin"	"Glycopeptides"	"A07AA09,J01XA01,S01AA28"	"Other antibacterials"	"Glycopeptide antibacterials"	"va,van,vanc"	"vancocin,vancocin hcl,vancoled,vancomicina,vancomycin,vancomycin hcl,vancomycine,vancomycinum,vancor,viomycin derivative"	2	"g"	2	"g"	"13586-3,13587-1,19000-9,20578-1,23615-8,25228-8,31012-8,39092-2,39796-8,39797-6,4089-9,4090-7,4091-5,4092-3,50938-0,523-1,524-9,525-6,526-4,59381-4,7059-9,92241-9,97657-1"
 "VAM"		"Vancomycin-macromethod"	"Glycopeptides"	"NA"			""	""					""

data-raw/clin_break.md5

@@ -1 +1 @@
-c4a5519e0ecc74220fc768e944a372f7
+25f9e2b995124710eb121cc4e62eba16

data-raw/eucast_rules.tsv

@@ -2,7 +2,7 @@
 # For editing this EUCAST reference file, these values can all be used for targeting antibiotics:
 # aminoglycosides, aminopenicillins, antifungals, antimycobacterials, betalactams, carbapenems, cephalosporins, cephalosporins_1st, cephalosporins_2nd, cephalosporins_3rd, cephalosporins_4th, cephalosporins_5th, cephalosporins_except_CAZ, fluoroquinolones, glycopeptides, glycopeptides_except_lipo, lincosamides, lipoglycopeptides, macrolides, oxazolidinones, penicillins, polymyxins, quinolones, streptogramins, tetracyclines, tetracyclines_except_TGC, trimethoprims, ureidopenicillins
 # and all separate EARS-Net letter codes such as AMC. They can be separated by comma: 'AMC, fluoroquinolones'.
-# The 'if_mo_property' column can be any column name from the AMR::microorganisms data set, or "genus_species" or "gramstain".
+# The 'if_mo_property' column can be any column name from the AMR::microorganisms data set, or 'genus_species' or 'gramstain'.
 # The like.is.one_of column must be 'like' or 'is' or 'one_of' ('like' will read the 'this_value' column as regular expression)
 # The EUCAST guideline contains references to the 'Burkholderia cepacia complex'. All species in this group are noted on the 'B.cepacia' sheet of the EUCAST Clinical Breakpoint v.10.0 Excel file of 2020 and later
 # >>>>> IF YOU WANT TO IMPORT THIS FILE INTO YOUR OWN SOFTWARE, HAVE THE FIRST 9 LINES SKIPPED <<<<<

data-raw/extractATCs.R

@@ -4,7 +4,7 @@ library(tidyr)
 library(AMR)
 # we need J01, J02 and J04 (J03 does not exist)
 
-url <- "https://www.whocc.no/atc_ddd_index/?code={code}&showdescription=no"
+url <- "https://atcddd.fhi.no/atc_ddd_index/?code={code}&showdescription=no"
 complete_vector <- character(0)
 for (Jxx in c("J01", "J02", "J04")) {
   site <- gsub("{code}", Jxx, url, fixed = TRUE)

data-raw/reproduction_of_antibiotics.R

@@ -735,6 +735,18 @@ antibiotics <- antibiotics %>%
   ))
 antibiotics[which(antibiotics$ab %in% c("CYC", "LNZ", "THA", "TZD")), "group"] <- "Oxazolidinones"
 
+# add clindamycin inducible screening
+clin <- antibiotics |>
+  filter(ab == "FOX1") |>
+  mutate(ab = as.character("CLI1"),
+         name = "Clindamycin inducible screening",
+         group = "Macrolides/lincosamides")
+antibiotics <- antibiotics |>
+  mutate(ab = as.character(ab)) |>
+  bind_rows(clin)
+class(antibiotics$ab) <- c("ab", "character")
+antibiotics[which(antibiotics$ab == "CLI1"), "abbreviations"][[1]] <- list(c("clindamycin inducible", "clinda inducible", "clin inducible"))
+
 # add pretomanid
 antibiotics <- antibiotics %>%
   mutate(ab = as.character(ab)) %>%
@@ -754,12 +766,20 @@ antibiotics <- antibiotics %>%
 
 # update ATC codes from WHOCC website -------------------------------------
 
-# last time checked: 2022-10-29
+# last time checked: 2024-02-22
 
 library(rvest)
 updated_atc <- as.list(antibiotics$atc)
 
-get_atcs <- function(ab_name, url = "https://www.whocc.no/atc_ddd_index/") {
+get_atcs <- function(ab_name, type = "human") {
+  if (type == "human") {
+    url <- "https://atcddd.fhi.no/atc_ddd_index/"
+  } else if (type == "veterinary") {
+    url <- "https://atcddd.fhi.no/atcvet/atcvet_index/"  
+  } else {
+    stop("invalid type")
+  }
+  
   ab_name <- gsub("/", " and ", tolower(ab_name), fixed = TRUE)
 
   # we will do a search on their website, which means:
@@ -780,6 +800,7 @@ get_atcs <- function(ab_name, url = "https://www.whocc.no/atc_ddd_index/") {
     html_node("table") %>%
     # transform it to an R data set
     html_table(header = FALSE)
+  
   # and get the ATCs (first column) of only exact hits
   unique(as.character(atc_tbl[which(tolower(atc_tbl[, 2, drop = TRUE]) == ab_name), 1, drop = TRUE]))
 }
@@ -790,7 +811,10 @@ for (i in seq_len(nrow(antibiotics))) {
     " - Downloading ", antibiotics$name[i],
     appendLF = FALSE
   )
-  atcs <- get_atcs(antibiotics$name[i])
+  atcs <- get_atcs(antibiotics$name[i], type = "human")
+  if (all(is.na(atcs))) {
+    atcs <- get_atcs(antibiotics$name[i], type = "veterinary")
+  }
   if (length(atcs) > 0) {
     updated_atc[[i]] <- atcs
     message(" (", length(atcs), " results)")
@@ -805,7 +829,7 @@ antibiotics$atc <- updated_atc
 
 # update DDDs from WHOCC website ------------------------------------------
 
-# last time checked: 2022-10-29
+# last time checked: 2024-02-22
 ddd_oral <- rep(NA_real_, nrow(antibiotics))
 ddd_oral_units <- rep(NA_character_, nrow(antibiotics))
 ddd_iv <- rep(NA_real_, nrow(antibiotics))

data-raw/reproduction_of_antivirals.R

@@ -34,7 +34,7 @@ library(rvest)
 # get all data from the WHOCC website
 get_atc_table <- function(atc_group) {
   # give as input J0XXX, like atc_group = "J05AB"
-  downloaded <- read_html(paste0("https://www.whocc.no/atc_ddd_index/?code=", atc_group, "&showdescription=no"))
+  downloaded <- read_html(paste0("https://atcddd.fhi.no/atc_ddd_index/?code=", atc_group, "&showdescription=no"))
   table_title <- downloaded %>%
     html_nodes(paste0('a[href^="./?code=', atc_group, '&"]')) %>%
     html_text()
@@ -62,7 +62,7 @@ get_atc_table <- function(atc_group) {
   )
 }
 
-# these are the relevant groups for input: https://www.whocc.no/atc_ddd_index/?code=J05A (J05 only contains J05A)
+# these are the relevant groups for input: https://atcddd.fhi.no/atc_ddd_index/?code=J05A (J05 only contains J05A)
 atc_groups <- c("J05AA", "J05AB", "J05AC", "J05AD", "J05AE", "J05AF", "J05AG", "J05AH", "J05AJ", "J05AP", "J05AR", "J05AX")
 
 # get the first

data-raw/reproduction_of_clinical_breakpoints.R

@@ -213,7 +213,10 @@ unknown <- breakpoints %>%
 breakpoints %>% 
   filter(code %in% unknown) %>% 
   count(GUIDELINES, YEAR, ORGANISM_CODE, BREAKPOINT_TYPE, sort = TRUE)
-# these codes are currently (2023-07-08): clu, kma. No clue (are not in MO list of WHONET), so remove them:
+# 2024-02-22: clu and kma are know (see below), fix the PBI one
+breakpoints$mo[breakpoints$ORGANISM_CODE == "PBI"] <- as.mo("Parabacteroides")
+breakpoints$ORGANISM_CODE[breakpoints$ORGANISM_CODE == "PBI"] <- "Parabacteroides"
+# 2023-07-08: these codes are currently: clu, kma. No clue (are not in MO list of WHONET), so remove them:
 breakpoints <- breakpoints %>% 
   filter(!is.na(mo))
 
@@ -236,6 +239,7 @@ breakpoints_new <- breakpoints %>%
   transmute(
     guideline = paste(GUIDELINES, YEAR),
     type = ifelse(BREAKPOINT_TYPE == "ECOFF", "ECOFF", tolower(BREAKPOINT_TYPE)),
+    host = ifelse(BREAKPOINT_TYPE == "ECOFF", "ECOFF", tolower(HOST)),
     method = TEST_METHOD,
     site = SITE_OF_INFECTION,
     mo,
@@ -263,15 +267,15 @@ breakpoints_new <- breakpoints %>%
     gsub("–", "-", ., fixed = TRUE)) %>%
   arrange(desc(guideline), mo, ab, type, method) %>%
   filter(!(is.na(breakpoint_S) & is.na(breakpoint_R)) & !is.na(mo) & !is.na(ab)) %>%
-  distinct(guideline, type, ab, mo, method, site, breakpoint_S, .keep_all = TRUE)
+  distinct(guideline, type, host, ab, mo, method, site, breakpoint_S, .keep_all = TRUE)
 
 # check the strange duplicates
 breakpoints_new %>% 
-  mutate(id = paste(guideline, type, ab, mo, method, site)) %>% 
+  mutate(id = paste(guideline, type, host, ab, mo, method, site)) %>% 
   filter(id %in% .$id[which(duplicated(id))])
 # remove duplicates
 breakpoints_new <- breakpoints_new %>% 
-  distinct(guideline, type, ab, mo, method, site, .keep_all = TRUE)
+  distinct(guideline, type, host, ab, mo, method, site, .keep_all = TRUE)
 
 # fix reference table names
 breakpoints_new %>% filter(guideline %like% "EUCAST", is.na(ref_tbl)) %>% View()
@@ -284,6 +288,10 @@ breakpoints_new <- breakpoints_new %>%
 breakpoints_new[which(breakpoints_new$method == "DISK"), "breakpoint_S"] <- as.double(as.disk(breakpoints_new[which(breakpoints_new$method == "DISK"), "breakpoint_S", drop = TRUE]))
 breakpoints_new[which(breakpoints_new$method == "DISK"), "breakpoint_R"] <- as.double(as.disk(breakpoints_new[which(breakpoints_new$method == "DISK"), "breakpoint_R", drop = TRUE]))
 
+# regarding animal breakpoints, CLSI has adults and foals for horses, but only for amikacin - remove them
+breakpoints_new <- breakpoints_new |> 
+  filter(host %unlike% "foal") |> 
+  mutate(host = ifelse(host %like% "horse", "horse", host))
 
 # FIXES FOR WHONET ERRORS ----
 
@@ -301,27 +309,29 @@ breakpoints_new[which(breakpoints_new$breakpoint_R == 513), "breakpoint_R"] <- 5
 breakpoints_new[which(breakpoints_new$breakpoint_R == 1025), "breakpoint_R"] <- 1024
 
 # fix streptococci in WHONET table of EUCAST: Strep A, B, C and G must only include these groups and not all streptococci:
-clinical_breakpoints$mo[clinical_breakpoints$mo == "B_STRPT" & clinical_breakpoints$ref_tbl %like% "^strep.* a.* b.*c.*g"] <- as.mo("B_STRPT_ABCG")
+breakpoints_new$mo[breakpoints_new$mo == "B_STRPT" & breakpoints_new$ref_tbl %like% "^strep.* a.* b.*c.*g"] <- as.mo("B_STRPT_ABCG")
 # Haemophilus same error (must only be H. influenzae)
-clinical_breakpoints$mo[clinical_breakpoints$mo == "B_HMPHL" & clinical_breakpoints$ref_tbl %like% "^h.* influenzae"] <- as.mo("B_HMPHL_INFL")
+breakpoints_new$mo[breakpoints_new$mo == "B_HMPHL" & breakpoints_new$ref_tbl %like% "^h.* influenzae"] <- as.mo("B_HMPHL_INFL")
 # EUCAST says that for H. parainfluenzae the H. influenza rules can be used, so add them
-clinical_breakpoints <- clinical_breakpoints %>% 
+breakpoints_new <- breakpoints_new %>% 
   bind_rows(
-    clinical_breakpoints %>%
+    breakpoints_new %>%
       filter(guideline %like% "EUCAST", mo == "B_HMPHL_INFL") %>% 
       mutate(mo = as.mo("B_HMPHL_PRNF"))
   ) %>% 
-  arrange(desc(guideline), mo, ab, type, method)
+  arrange(desc(guideline), mo, ab, type, host, method)
 # Achromobacter denitrificans is in WHONET included in their A. xylosoxidans table, must be removed
-clinical_breakpoints <- clinical_breakpoints %>% filter(mo != as.mo("Achromobacter denitrificans"))
+breakpoints_new <- breakpoints_new %>% filter(mo != as.mo("Achromobacter denitrificans"))
 # WHONET contains gentamicin breakpoints for viridans streptocci, which are intrinsic R - they meant genta-high, which is ALSO in their table, so we just remove gentamicin in viridans streptococci
-clinical_breakpoints <- clinical_breakpoints %>% filter(!(mo == as.mo("Streptococcus viridans") & ab == "GEN"))
+breakpoints_new <- breakpoints_new %>% filter(!(mo == as.mo("Streptococcus viridans") & ab == "GEN"))
 # Nitrofurantoin in Staph (EUCAST) only applies to S. saprophyticus, while WHONET has the DISK correct but the MIC on genus level
-clinical_breakpoints$mo[clinical_breakpoints$mo == "B_STPHY" & clinical_breakpoints$ab == "NIT" & clinical_breakpoints$guideline %like% "EUCAST"] <- as.mo("B_STPHY_SPRP")
+breakpoints_new$mo[breakpoints_new$mo == "B_STPHY" & breakpoints_new$ab == "NIT" & breakpoints_new$guideline %like% "EUCAST"] <- as.mo("B_STPHY_SPRP")
 # WHONET sets the 2023 breakpoints for SAM to MIC of 16/32 for Enterobacterales, should be MIC 8/32 like AMC (see issue #123 on github.com/msberends/AMR)
-clinical_breakpoints$breakpoint_S[clinical_breakpoints$mo == "B_[ORD]_ENTRBCTR" & clinical_breakpoints$ab == "SAM" & clinical_breakpoints$guideline %like% "CLSI 2023" & clinical_breakpoints$method == "MIC"] <- 8
+# UPDATE 2024-02-22: fixed now
+# breakpoints_new$breakpoint_S[breakpoints_new$mo == "B_[ORD]_ENTRBCTR" & breakpoints_new$ab == "SAM" & breakpoints_new$guideline %like% "CLSI 2023" & breakpoints_new$method == "MIC"] <- 8
+
 # determine rank again now that some changes were made on taxonomic level (genus -> species)
-clinical_breakpoints <- clinical_breakpoints %>% 
+breakpoints_new <- breakpoints_new %>% 
   mutate(rank_index = case_when(
     is.na(mo_rank(mo, keep_synonyms = TRUE)) ~ 6, # for UNKNOWN, B_GRAMN, B_ANAER, B_ANAER-NEG, etc.
     mo_rank(mo, keep_synonyms = TRUE) %like% "(infra|sub)" ~ 1,
@@ -337,7 +347,7 @@ clinical_breakpoints <- clinical_breakpoints %>%
 # EUCAST 2022 guideline: S <= 8 and R > 8
 #           WHONET file: S <= 8 and R >= 16
 breakpoints_new %>% filter(guideline == "EUCAST 2023", ab == "AMC", mo == "B_[ORD]_ENTRBCTR", method == "MIC")
-# this will make an MIC of 12 I, which should be R, so:
+# this will make an MIC of 12 I, which should be R according to EUCAST, so:
 breakpoints_new <- breakpoints_new %>%
   mutate(breakpoint_R = ifelse(guideline %like% "EUCAST" & method == "MIC" & log2(breakpoint_R) - log2(breakpoint_S) != 0,
     pmax(breakpoint_S, breakpoint_R / 2),
@@ -350,7 +360,7 @@ breakpoints_new <- breakpoints_new %>%
     breakpoint_R + 1,
     breakpoint_R
   ))
-# fix missing R breakpoint where there is an S breakpoint
+# fill missing R breakpoint where there is an S breakpoint
 breakpoints_new[which(is.na(breakpoints_new$breakpoint_R)), "breakpoint_R"] <- breakpoints_new[which(is.na(breakpoints_new$breakpoint_R)), "breakpoint_S"]
 
 

data-raw/reproduction_of_microorganisms.R

@@ -150,12 +150,14 @@ df_remove_nonASCII <- function(df) {
 
 # to retrieve LPSN and authors from LPSN website
 get_lpsn_and_author <- function(rank, name) {
+  name <- gsub("^Candidatus ", "", name)
   url <- paste0("https://lpsn.dsmz.de/", tolower(rank), "/", tolower(name))
   page_txt <- tryCatch(read_html(url), error = function(e) NULL)
   if (is.null(page_txt)) {
     warning("No LPSN found for ", tolower(rank), " '", name, "'")
     lpsn <- NA_character_
     ref <- NA_character_
+    status <- "unknown"
   } else {
     page_txt <- page_txt %>%
       html_element("#detail-page") %>%
@@ -164,9 +166,33 @@ get_lpsn_and_author <- function(rank, name) {
     ref <- page_txt %>%
       gsub(".*?Name: (.*[0-9]{4}?).*", "\\1", ., perl = FALSE) %>%
       gsub(name, "", ., fixed = TRUE) %>%
+      gsub("^\"?Candidatus ?\"?", "", .) %>%
       trimws()
+    status <- trimws(gsub(".*Nomenclatural status:[\r\n\t ]*([a-zA-Z, ]+)[\r\n\t].*", "\\1", page_txt, perl = FALSE))
+    if ((status %like% "validly published" & status %unlike% "not valid") | status %like% "[\r\n\t]") {
+      # we used to take "accepted" for every LPSN record, also candidates. Now only for missing values and explicit accepted ones.
+      status <- "accepted"
+    } else {
+      status <- "not validly published"
+    }
+  }
+  c("lpsn" = lpsn, "ref" = ref, "status" = status)
+}
+
+# this will e.g. take the family from the root genus record, and gives all species that family
+get_top_lvl <- function(current, rank, rank_target) {
+  if (!rank_target %in% rank) {
+    current[1]
+  } else {
+    out <- current[rank == rank_target][1]
+    if (out %in% c("", NA)) {
+      out <- names(sort(table(current[which(!current %in% c("", NA))]), decreasing = TRUE)[1])
+      if (is.null(out)) {
+        out <- ""
+      }
+    }
+    out
   }
-  c("lpsn" = lpsn, "ref" = ref)
 }
 
 # MB/ August 2022: useless, does not contain full taxonomy, e.g. LPSN::request(cred, category = "family") is empty.
@@ -208,11 +234,12 @@ include_fungal_orders_ids <- taxonomy_gbif.bak %>%
 include_fungal_orders <- taxonomy_gbif.bak %>%
   filter(taxonID %in% c(include_fungal_orders_ids$taxonID, include_fungal_orders_ids$acceptedNameUsageID)) %>%
   distinct(order) %>%
-  pull(order)
+  pull(order) |> 
+  sort()
 
 # check some columns to validate below filters
-sort(table(taxonomy_gbif.bak$taxonomicStatus))
-sort(table(taxonomy_gbif.bak$taxonRank))
+taxonomy_gbif.bak$taxonomicStatus |> table() |> sort() |> as.data.frame()
+taxonomy_gbif.bak$taxonRank |> table() |> sort() |> as.data.frame()
 
 taxonomy_gbif <- taxonomy_gbif.bak %>%
   # immediately filter rows we really never want
@@ -223,11 +250,8 @@ taxonomy_gbif <- taxonomy_gbif.bak %>%
     #  include these kingdoms (no Chromista)
     kingdom %in% c("Archaea", "Bacteria", "Protozoa") |
       # include all of these fungal orders
-      order %in% c(
-        "Eurotiales", "Microascales", "Mucorales", "Saccharomycetales",
-        "Schizosaccharomycetales", "Tremellales", "Onygenales", "Pneumocystales"
-      ) |
-      # and all of these important genera (see "data-raw/_pre_commit_hook.R")
+      order %in% include_fungal_orders |
+      # and all of these important genera (see "data-raw/_pre_commit_checks.R")
       # (they also contain bacteria and protozoa, but these will get prevalence = 2 later on)
       genus %in% AMR:::MO_PREVALENT_GENERA
   ) %>%
@@ -289,9 +313,6 @@ taxonomy_gbif
 
 taxonomy_lpsn.bak <- vroom(file_lpsn)
 
-# check some columns to validate below filters
-sort(table(is.na(taxonomy_lpsn.bak$record_lnk))) # accepted = TRUE
-
 taxonomy_lpsn <- taxonomy_lpsn.bak %>%
   transmute(
     genus = genus_name,
@@ -309,6 +330,10 @@ taxonomy_lpsn <- taxonomy_lpsn.bak %>%
     lpsn_renamed_to = as.character(record_lnk)
   ) %>%
   mutate(source = "LPSN")
+
+# integrity tests
+sort(table(taxonomy_lpsn$rank))
+sort(table(taxonomy_lpsn$status))
 taxonomy_lpsn
 
 # download additional taxonomy to the domain/kingdom level (their API is not sufficient...)
@@ -322,17 +347,22 @@ taxonomy_lpsn_missing <- tibble(
 )
 for (page in LETTERS) {
   # this will not alter `taxonomy_lpsn` yet
-  message("Downloading page ", page, "...", appendLF = FALSE)
+  message("Downloading page ", page, "...", appendLF = TRUE)
   url <- paste0("https://lpsn.dsmz.de/genus?page=", page)
-  x <- read_html(url) %>%
+  x <- tryCatch(read_html(url),
+                error = function(e) {
+                  message("Waiting 10 seconds because of error: ", e$message)
+                  Sys.sleep(10)
+                  read_html(url)
+                })
+  x <- x %>%
     # class "main-list" is the main table
     html_element(".main-list") %>%
     # get every list element with a set <id> attribute
     html_elements("li[id]")
+  pb <- progress_bar$new(total = length(x), format = "[:bar] :current/:total :eta")
   for (i in seq_len(length(x))) {
-    if (i %% 25 == 0) {
-      message(".", appendLF = FALSE)
-    }
+    pb$tick()
     elements <- x[[i]] %>% html_elements("a")
     hrefs <- elements %>% html_attr("href")
     ranks <- hrefs %>% gsub(".*/(.*?)/.*", "\\1", .)
@@ -344,21 +374,26 @@ for (page in LETTERS) {
     names <- names[ranks != "species"]
     ranks <- ranks[ranks != "species"]
     ranks[ranks == "domain"] <- "kingdom"
-
-    df <- names %>%
-      tibble() %>%
-      t() %>%
-      as_tibble(.name_repair = "unique") %>%
-      setNames(ranks) %>%
-      # no candidates please
-      filter(genus %unlike% "^(Candidatus|\\[)")
+    
+    suppressMessages(
+      df <- names %>%
+        tibble() %>%
+        t() %>%
+        as_tibble(.name_repair = "unique") %>%
+        setNames(ranks) %>%
+        # no candidates please
+        filter(genus %unlike% "^(Candidatus|\\[)")
+    )
 
     taxonomy_lpsn_missing <- taxonomy_lpsn_missing %>%
       bind_rows(df)
   }
-  message(length(x), " entries incl. candidates (cleaned total: ", nrow(taxonomy_lpsn_missing), ")")
+  message("  => ", length(x), " entries incl. candidates (cleaned total: ", nrow(taxonomy_lpsn_missing), ")")
 }
-taxonomy_lpsn_missing
+taxonomy_lpsn_missing <- taxonomy_lpsn_missing |> distinct()
+# had to pick the right genus/family combination here:
+taxonomy_lpsn_missing <- taxonomy_lpsn_missing |> filter(!(genus == "Pusillimonas" & family == "Oscillospiraceae"))
+taxonomy_lpsn.bak2 <- taxonomy_lpsn.bak
 
 taxonomy_lpsn <- taxonomy_lpsn %>%
   left_join(taxonomy_lpsn_missing, by = "genus") %>%
@@ -367,8 +402,10 @@ taxonomy_lpsn <- taxonomy_lpsn %>%
   mutate_all(function(x) ifelse(x %like_case% " no ", NA_character_, x))
 
 taxonomy_lpsn.bak2 <- taxonomy_lpsn
-# download family directly from LPSN website using scraping
-pb <- progress_bar$new(total = length(unique(taxonomy_lpsn$family)))
+# download family directly from LPSN website using scraping, by using get_lpsn_and_author()
+# try it first:
+# get_lpsn_and_author("genus", "Escherichia")
+pb <- progress_bar$new(total = length(unique(taxonomy_lpsn$family)), format = "[:bar] :current/:total :eta")
 for (f in unique(taxonomy_lpsn$family)) {
   pb$tick()
   if (is.na(f)) next
@@ -381,14 +418,14 @@ for (f in unique(taxonomy_lpsn$family)) {
       order = taxonomy_lpsn$order[which(taxonomy_lpsn$family == f)[1]],
       family = f,
       rank = "family",
-      status = "accepted",
+      status = unname(tax_info["status"]),
       source = "LPSN",
       lpsn = unname(tax_info["lpsn"]),
       ref = unname(tax_info["ref"])
     ))
 }
 # download order directly from LPSN website using scraping
-pb <- progress_bar$new(total = length(unique(taxonomy_lpsn$order)))
+pb <- progress_bar$new(total = length(unique(taxonomy_lpsn$order)), format = "[:bar] :current/:total :eta")
 for (o in unique(taxonomy_lpsn$order)) {
   pb$tick()
   if (is.na(o)) next
@@ -400,14 +437,14 @@ for (o in unique(taxonomy_lpsn$order)) {
       class = taxonomy_lpsn$class[which(taxonomy_lpsn$order == o)[1]],
       order = o,
       rank = "order",
-      status = "accepted",
+      status = unname(tax_info["status"]),
       source = "LPSN",
       lpsn = unname(tax_info["lpsn"]),
       ref = unname(tax_info["ref"])
     ))
 }
 # download class directly from LPSN website using scraping
-pb <- progress_bar$new(total = length(unique(taxonomy_lpsn$class)))
+pb <- progress_bar$new(total = length(unique(taxonomy_lpsn$class)), format = "[:bar] :current/:total :eta")
 for (cc in unique(taxonomy_lpsn$class)) {
   pb$tick()
   if (is.na(cc)) next
@@ -418,14 +455,14 @@ for (cc in unique(taxonomy_lpsn$class)) {
       phylum = taxonomy_lpsn$phylum[which(taxonomy_lpsn$class == cc)[1]],
       class = cc,
       rank = "class",
-      status = "accepted",
+      status = unname(tax_info["status"]),
       source = "LPSN",
       lpsn = unname(tax_info["lpsn"]),
       ref = unname(tax_info["ref"])
     ))
 }
 # download phylum directly from LPSN website using scraping
-pb <- progress_bar$new(total = length(unique(taxonomy_lpsn$phylum)))
+pb <- progress_bar$new(total = length(unique(taxonomy_lpsn$phylum)), format = "[:bar] :current/:total :eta")
 for (p in unique(taxonomy_lpsn$phylum)) {
   pb$tick()
   if (is.na(p)) next
@@ -435,14 +472,14 @@ for (p in unique(taxonomy_lpsn$phylum)) {
       kingdom = taxonomy_lpsn$kingdom[which(taxonomy_lpsn$phylum == p)[1]],
       phylum = p,
       rank = "phylum",
-      status = "accepted",
+      status = unname(tax_info["status"]),
       source = "LPSN",
       lpsn = unname(tax_info["lpsn"]),
       ref = unname(tax_info["ref"])
     ))
 }
 # download kingdom directly from LPSN website using scraping
-pb <- progress_bar$new(total = length(unique(taxonomy_lpsn$kingdom)))
+pb <- progress_bar$new(total = length(unique(taxonomy_lpsn$kingdom)), format = "[:bar] :current/:total :eta")
 for (k in unique(taxonomy_lpsn$kingdom)) {
   pb$tick()
   if (is.na(k)) next
@@ -451,7 +488,7 @@ for (k in unique(taxonomy_lpsn$kingdom)) {
     bind_rows(tibble(
       kingdom = k,
       rank = "kingdom",
-      status = "accepted",
+      status = unname(tax_info["status"]),
       source = "LPSN",
       lpsn = unname(tax_info["lpsn"]),
       ref = unname(tax_info["ref"])
@@ -469,6 +506,7 @@ saveRDS(taxonomy_gbif, "data-raw/taxonomy_gbif.rds", version = 2)
 saveRDS(taxonomy_lpsn, "data-raw/taxonomy_lpsn.rds", version = 2)
 # this allows to always get back to this point by simply loading the files from data-raw/.
 
+
 # Add full names ----------------------------------------------------------
 
 taxonomy_gbif <- taxonomy_gbif %>%
@@ -515,29 +553,28 @@ taxonomy_lpsn$lpsn_parent[taxonomy_lpsn$rank == "subspecies"] <- taxonomy_lpsn$l
 
 # Combine the datasets ----------------------------------------------------
 
-# basis must be LPSN as it's most recent
-taxonomy <- taxonomy_lpsn %>%
-  # join GBIF identifiers to them
-  left_join(taxonomy_gbif %>% select(kingdom, fullname, starts_with("gbif")),
-    by = c("kingdom", "fullname")
-  )
-
-# for everything else, add the GBIF data
-taxonomy <- taxonomy %>%
-  bind_rows(taxonomy_gbif %>%
-    filter(!paste(kingdom, fullname) %in% paste(taxonomy$kingdom, taxonomy$fullname))) %>%
-  arrange(fullname) %>%
-  filter(fullname != "")
+taxonomy <- taxonomy_lpsn |>
+  # start by adding GBIF to the bottom
+  bind_rows(taxonomy_gbif) |> 
+  # group on unique species
+  group_by(kingdom, fullname) |>
+  # fill the NAs in LPSN/GBIF fields and ref with the other source (so LPSN: 123 and GBIF: NA will become LPSN: 123 and GBIF: 123)
+  mutate(across(matches("^(lpsn|gbif|ref)"), function(x) rep(x[!is.na(x)][1], length(x)))) |>
+  # ungroup again
+  ungroup() |> 
+  # only keep unique species per kingdom
+  distinct(kingdom, fullname, .keep_all = TRUE) |> 
+  arrange(fullname)
 
 # get missing entries from existing microorganisms data set
-taxonomy <- taxonomy %>%
-  bind_rows(AMR::microorganisms %>%
+taxonomy.old <- AMR::microorganisms %>%
     select(all_of(colnames(taxonomy))) %>%
     filter(
       !paste(kingdom, fullname) %in% paste(taxonomy$kingdom, taxonomy$fullname),
       # these will be added later:
-      source != "manually added"
-    )) %>%
+      source != "manually added")
+taxonomy <- taxonomy %>%
+  bind_rows(taxonomy.old) %>%
   arrange(fullname) %>%
   filter(fullname != "")
 
@@ -557,6 +594,29 @@ taxonomy <- taxonomy %>%
   ))
 table(taxonomy$rank, useNA = "always")
 
+# at this point, it happens that some genera within kingdoms have multiple families / orders, etc., see here:
+taxonomy |> filter(genus != "") |> group_by(kingdom, genus) |> filter(n_distinct(family) > 1) |> View()
+# so make this universal
+taxonomy <- taxonomy |> 
+  group_by(kingdom, genus) |> 
+  mutate(family = get_top_lvl(family, rank, "genus")) |> 
+  group_by(kingdom, family) |>
+  mutate(order = get_top_lvl(order, rank, "family")) |> 
+  group_by(kingdom, order) |>
+  mutate(class = get_top_lvl(class, rank, "order")) |> 
+  group_by(kingdom, class) |>
+  mutate(phylum = get_top_lvl(phylum, rank, "class")) |> 
+  ungroup()
+# and remove the taxonomy where it must remain empty
+taxonomy <- taxonomy |> 
+  mutate(phylum = ifelse(rank %in% c("kingdom"), "", phylum),
+         class = ifelse(rank %in% c("kingdom", "phylum"), "", class),
+         order = ifelse(rank %in% c("kingdom", "phylum", "class"), "", order),
+         family = ifelse(rank %in% c("kingdom", "phylum", "class", "order"), "", family),
+         genus = ifelse(rank %in% c("kingdom", "phylum", "class", "order", "family"), "", genus),
+         species = ifelse(rank %in% c("kingdom", "phylum", "class", "order", "family", "genus"), "", species),
+         subspecies = ifelse(rank %in% c("kingdom", "phylum", "class", "order", "family", "genus", "species"), "", subspecies))
+
 
 # Save intermediate results (0) -------------------------------------------
 
@@ -575,28 +635,23 @@ current_gbif <- taxonomy_gbif.bak %>%
   )
 
 # add missing kingdoms
-taxonomy <- taxonomy %>%
-  bind_rows(
-    taxonomy %>%
-      filter(kingdom != "") %>%
-      distinct(kingdom) %>%
-      mutate(
-        fullname = kingdom,
-        rank = "kingdom",
-        status = "accepted",
-        source = "manually added"
-      ) %>%
-      filter(!paste(kingdom, rank) %in% paste(taxonomy$kingdom, taxonomy$rank)) %>%
-      left_join(
-        current_gbif %>%
-          select(kingdom, rank = taxonRank, ref = scientificNameAuthorship, gbif = taxonID, gbif_parent = parentNameUsageID),
-        by = c("kingdom", "rank")
-      ) %>%
-      mutate(source = ifelse(!is.na(gbif), "GBIF", source))
-  )
+taxonomy_all_missing <- taxonomy %>%
+  filter(kingdom != "") %>%
+  distinct(kingdom) %>%
+  mutate(
+    fullname = kingdom,
+    rank = "kingdom"
+  ) %>%
+  filter(!paste(kingdom, rank) %in% paste(taxonomy$kingdom, taxonomy$rank)) %>%
+  left_join(
+    current_gbif %>%
+      select(kingdom, rank = taxonRank, ref = scientificNameAuthorship, gbif = taxonID, gbif_parent = parentNameUsageID),
+    by = c("kingdom", "rank")
+  ) %>%
+  mutate(source = ifelse(!is.na(gbif), "GBIF", "manually added"),
+         status = ifelse(!is.na(gbif), "accepted", "unknown"))
 
 # 2 = phylum ... 6 = genus
-taxonomy_all_missing <- NULL
 for (i in 2:6) {
   i_name <- colnames(taxonomy)[i + 1]
   message("Adding missing: ", i_name, "... ", appendLF = FALSE)
@@ -606,25 +661,20 @@ for (i in 2:6) {
     select(kingdom:(i + 1)) %>%
     mutate(
       fullname = .[[ncol(.)]],
-      rank = i_name,
-      status = "accepted",
-      source = "manually added"
+      rank = i_name
     ) %>%
-    filter(!paste(kingdom, .[[ncol(.) - 4]], rank) %in% paste(taxonomy$kingdom, taxonomy[[i + 1]], taxonomy$rank)) %>%
+    filter(!paste(kingdom, .[[ncol(.) - 2]], rank) %in% paste(taxonomy$kingdom, taxonomy[[i + 1]], taxonomy$rank)) %>%
     # get GBIF identifier where available
     left_join(
       current_gbif %>%
         select(kingdom, all_of(i_name), rank = taxonRank, ref = scientificNameAuthorship, gbif = taxonID, gbif_parent = parentNameUsageID),
       by = c("kingdom", "rank", i_name)
     ) %>%
-    mutate(source = ifelse(!is.na(gbif), "GBIF", source))
+    mutate(source = ifelse(!is.na(gbif), "GBIF", "manually added"),
+           status = ifelse(!is.na(gbif), "accepted", "unknown"))
   message("n = ", nrow(to_add))
-  if (is.null(taxonomy_all_missing)) {
-    taxonomy_all_missing <- to_add
-  } else {
-    taxonomy_all_missing <- taxonomy_all_missing %>%
-      bind_rows(to_add)
-  }
+  taxonomy_all_missing <- taxonomy_all_missing %>%
+    bind_rows(to_add)
 }
 taxonomy_all_missing %>% View()
 
@@ -652,7 +702,7 @@ taxonomy <- taxonomy %>%
   select(-fullname_rank, -rank_index) %>%
   arrange(fullname)
 
-# now also add missing species (requires combination with genus)
+# now also add missing species that have subspecies (requires combination with genus)
 taxonomy <- taxonomy %>%
   bind_rows(
     taxonomy %>%
@@ -661,9 +711,7 @@ taxonomy <- taxonomy %>%
       select(kingdom:species) %>%
       mutate(
         fullname = paste(genus, species),
-        rank = "species",
-        status = "accepted",
-        source = "manually added"
+        rank = "species"
       ) %>%
       filter(!paste(kingdom, genus, species, rank) %in% paste(taxonomy$kingdom, taxonomy$genus, taxonomy$species, taxonomy$rank)) %>%
       # get GBIF identifier where available
@@ -672,13 +720,15 @@ taxonomy <- taxonomy %>%
           select(kingdom, genus, species = specificEpithet, rank = taxonRank, ref = scientificNameAuthorship, gbif = taxonID, gbif_parent = parentNameUsageID),
         by = c("kingdom", "rank", "genus", "species")
       ) %>%
-      mutate(source = ifelse(!is.na(gbif), "GBIF", source))
+      mutate(source = ifelse(!is.na(gbif), "GBIF", "manually added"),
+             status = ifelse(!is.na(gbif), "accepted", "unknown"))
   )
 
 
 # remove NAs from taxonomy again, and keep unique full names
 taxonomy <- taxonomy %>%
   mutate(across(kingdom:subspecies, function(x) ifelse(is.na(x), "", x))) %>%
+  arrange(kingdom, fullname, ref) |>
   distinct(kingdom, fullname, .keep_all = TRUE) %>%
   filter(kingdom != "")
 
@@ -691,12 +741,11 @@ saveRDS(taxonomy, "data-raw/taxonomy1.rds")
 # Get previously manually added entries -----------------------------------
 
 manually_added <- AMR::microorganisms %>%
-  filter(source == "manually added", !paste(kingdom, fullname) %in% paste(taxonomy$kingdom, taxonomy$fullname)) %>%
+  filter(source == "manually added",
+         !paste(kingdom, fullname) %in% paste(taxonomy$kingdom, taxonomy$fullname),
+         !rank %in% c("kingdom", "phylum", "class", "order", "family")) %>%
   select(fullname:subspecies, ref, source, rank)
 
-manually_added <- manually_added %>%
-  bind_rows(salmonellae)
-
 # get latest taxonomy for those entries
 for (g in unique(manually_added$genus[manually_added$genus != "" & manually_added$genus %in% taxonomy$genus])) {
   manually_added$family[which(manually_added$genus == g)] <- taxonomy$family[which(taxonomy$genus == g & is.na(taxonomy$lpsn))][1]
@@ -716,11 +765,14 @@ for (p in unique(manually_added$phylum[manually_added$phylum != "" & manually_ad
 
 manually_added <- manually_added %>%
   mutate(
-    status = "accepted",
+    status = "unknown",
     rank = ifelse(fullname %like% "unknown", "(unknown rank)", rank)
   )
 manually_added
 
+# these are now included in the new taxonomy, check them
+manually_added |> filter(fullname %in% taxonomy$fullname)
+
 taxonomy <- taxonomy %>%
   # here also the 'unknowns' are added, such as "(unknown fungus)"
   bind_rows(manually_added) %>%
@@ -728,6 +780,31 @@ taxonomy <- taxonomy %>%
 
 table(taxonomy$rank, useNA = "always")
 
+# Get LPSN data for records missing from `taxonomy_lpsn` ------------------
+
+# Weirdly enough, some LPSN records were lacking from `taxonomy_lpsn`, 
+# such as family Thiotrichaceae and its order Thiotrichales. When running
+# get_lpsn_and_author("family", "Thiotrichaceae") you do get a result.
+# So check every non-LPSN records from the kingdom of Bacteria and add it
+gbif_bacteria <- which(taxonomy$kingdom == "Bacteria" & taxonomy$source == "GBIF" & taxonomy$rank %in% c("phylum", "class", "order", "family"))
+added <- 0
+pb <- progress_bar$new(total = length(gbif_bacteria), format = "[:bar] :current/:total :eta")
+for (record in gbif_bacteria) {
+  pb$tick()
+  lpsn <- get_lpsn_and_author(rank = taxonomy$rank[record],
+                              name = taxonomy$fullname[record])
+  if (is.na(lpsn["lpsn"])) {
+    next
+  } else {
+    added <- added + 1
+    taxonomy$source[record] <- "LPSN"
+    taxonomy$lpsn[record] <- unname(lpsn["lpsn"])
+    taxonomy$ref[record] <- unname(lpsn["ref"])
+    taxonomy$status[record] <- unname(lpsn["status"])
+  }
+}
+message(added, " GBIF records altered to latest LPSN")
+taxbak <- taxonomy
 
 # Clean scientific reference ----------------------------------------------
 
@@ -737,7 +814,7 @@ taxonomy <- taxonomy %>%
 
 # Get the latest upper taxonomy from LPSN for non-LPSN data ---------------
 
-# (e.g., phylum above class "Bacilli" was still "Firmicutes", should be "Bacillota" in 2022)
+# (e.g., phylum above class "Bacilli" was still "Firmicutes" in 2023, should be "Bacillota")
 for (k in unique(taxonomy$kingdom[taxonomy$kingdom != ""])) {
   message("Fixing GBIF taxonomy for kingdom ", k, ".", appendLF = FALSE)
   i <- 0
@@ -765,17 +842,25 @@ for (k in unique(taxonomy$kingdom[taxonomy$kingdom != ""])) {
 }
 
 # we need to fix parent GBIF identifiers
-taxonomy$gbif_parent[taxonomy$rank == "phylum" & !is.na(taxonomy$gbif)] <- taxonomy$gbif[match(taxonomy$kingdom[taxonomy$rank == "phylum" & !is.na(taxonomy$gbif)], taxonomy$fullname)]
-taxonomy$gbif_parent[taxonomy$rank == "class" & !is.na(taxonomy$gbif)] <- taxonomy$gbif[match(taxonomy$phylum[taxonomy$rank == "class" & !is.na(taxonomy$gbif)], taxonomy$fullname)]
-taxonomy$gbif_parent[taxonomy$rank == "order" & !is.na(taxonomy$gbif)] <- taxonomy$gbif[match(taxonomy$class[taxonomy$rank == "order" & !is.na(taxonomy$gbif)], taxonomy$fullname)]
-taxonomy$gbif_parent[taxonomy$rank == "family" & !is.na(taxonomy$gbif)] <- taxonomy$gbif[match(taxonomy$order[taxonomy$rank == "family" & !is.na(taxonomy$gbif)], taxonomy$fullname)]
-taxonomy$gbif_parent[taxonomy$rank == "genus" & !is.na(taxonomy$gbif)] <- taxonomy$gbif[match(taxonomy$family[taxonomy$rank == "genus" & !is.na(taxonomy$gbif)], taxonomy$fullname)]
-taxonomy$gbif_parent[taxonomy$rank == "species" & !is.na(taxonomy$gbif)] <- taxonomy$gbif[match(taxonomy$genus[taxonomy$rank == "species" & !is.na(taxonomy$gbif)], taxonomy$fullname)]
-taxonomy$gbif_parent[taxonomy$rank == "subspecies" & !is.na(taxonomy$gbif)] <- taxonomy$gbif[match(paste(taxonomy$genus[taxonomy$rank == "subspecies" & !is.na(taxonomy$gbif)], taxonomy$species[taxonomy$rank == "subspecies" & !is.na(taxonomy$gbif)]), taxonomy$fullname)]
+taxonomy$gbif_parent[taxonomy$rank == "phylum"] <- taxonomy$gbif[match(taxonomy$kingdom[taxonomy$rank == "phylum"], taxonomy$fullname)]
+taxonomy$gbif_parent[taxonomy$rank == "class"] <- taxonomy$gbif[match(taxonomy$phylum[taxonomy$rank == "class"], taxonomy$fullname)]
+taxonomy$gbif_parent[taxonomy$rank == "order"] <- taxonomy$gbif[match(taxonomy$class[taxonomy$rank == "order"], taxonomy$fullname)]
+taxonomy$gbif_parent[taxonomy$rank == "family"] <- taxonomy$gbif[match(taxonomy$order[taxonomy$rank == "family"], taxonomy$fullname)]
+taxonomy$gbif_parent[taxonomy$rank == "genus"] <- taxonomy$gbif[match(taxonomy$family[taxonomy$rank == "genus"], taxonomy$fullname)]
+taxonomy$gbif_parent[taxonomy$rank == "species"] <- taxonomy$gbif[match(taxonomy$genus[taxonomy$rank == "species"], taxonomy$fullname)]
+taxonomy$gbif_parent[taxonomy$rank == "subspecies"] <- taxonomy$gbif[match(paste(taxonomy$genus[taxonomy$rank == "subspecies"], taxonomy$species[taxonomy$rank == "subspecies"]), taxonomy$fullname)]
+# and LPSN parents
+taxonomy$lpsn_parent[taxonomy$rank == "phylum"] <- taxonomy$lpsn[match(taxonomy$kingdom[taxonomy$rank == "phylum"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "class"] <- taxonomy$lpsn[match(taxonomy$phylum[taxonomy$rank == "class"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "order"] <- taxonomy$lpsn[match(taxonomy$class[taxonomy$rank == "order"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "family"] <- taxonomy$lpsn[match(taxonomy$order[taxonomy$rank == "family"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "genus"] <- taxonomy$lpsn[match(taxonomy$family[taxonomy$rank == "genus"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "species"] <- taxonomy$lpsn[match(taxonomy$genus[taxonomy$rank == "species"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "subspecies"] <- taxonomy$lpsn[match(paste(taxonomy$genus[taxonomy$rank == "subspecies"], taxonomy$species[taxonomy$rank == "subspecies"]), taxonomy$fullname)]
 
 # these still have no record in our data set:
-all(taxonomy$lpsn_parent %in% taxonomy$lpsn)
-all(taxonomy$gbif_parent %in% taxonomy$gbif)
+which(!taxonomy$lpsn_parent %in% taxonomy$lpsn)
+which(!taxonomy$gbif_parent %in% taxonomy$gbif)
 
 # fix rank
 taxonomy <- taxonomy %>%
@@ -794,6 +879,7 @@ taxonomy <- taxonomy %>%
 
 # Add prevalence ----------------------------------------------------------
 
+taxonomy_lpsn.bak3 <- taxonomy
 pathogens <- read_excel(file_bartlett, sheet = "Tab 6 Full List")
 
 # get all established, both old and current taxonomic names
@@ -902,6 +988,7 @@ mo_kingdom <- taxonomy %>%
     kingdom == "Protozoa" ~ "P",
     TRUE ~ ""
   ))
+
 # phylum until family are abbreviated with 8 characters and prefixed with their rank
 
 # Phylum - keep old and fill up for new ones
@@ -1196,58 +1283,120 @@ taxonomy <- taxonomy %>%
 taxonomy %>%
   filter(fullname %in% .[duplicated(fullname), "fullname", drop = TRUE]) %>%
   View()
+
+# fullnames must be unique, we'll keep the most relevant ones only
 taxonomy <- taxonomy %>%
   mutate(rank_index = case_when(
     kingdom == "Bacteria" ~ 1,
     kingdom == "Fungi" ~ 2,
     kingdom == "Protozoa" ~ 3,
     kingdom == "Archaea" ~ 4,
-    TRUE ~ 5
+    kingdom == "Animalia" ~ 5,
+    TRUE ~ 6
   )) %>%
   arrange(fullname, rank_index) %>%
   distinct(fullname, .keep_all = TRUE) %>%
   select(-rank_index) %>%
   filter(mo != "")
 
+# keep the codes from manually added ones
+manual_mos <- as.character(AMR::microorganisms$mo)[match(taxonomy$fullname[taxonomy$source == "manually added"], AMR::microorganisms$fullname)]
+taxonomy$mo[taxonomy$source == "manually added"][!is.na(manual_mos)] <- manual_mos[!is.na(manual_mos)]
+
 # this must not exist:
 taxonomy %>%
   filter(mo %like% "__") %>%
   View()
 taxonomy <- taxonomy %>% filter(mo %unlike% "__")
+taxonomy_lpsn.bak4 <- taxonomy
 
 
 # Some integrity checks ---------------------------------------------------
 
 # are mo codes unique?
-taxonomy %>% filter(mo %in% .[duplicated(mo), "mo", drop = TRUE])
-taxonomy <- taxonomy %>% distinct(mo, .keep_all = TRUE)
+taxonomy %>% filter(mo %in% .[duplicated(mo), "mo", drop = TRUE]) |> arrange(mo) |> View()
+# no, there are not, so sort on MO and keep the first
+taxonomy <- taxonomy %>% arrange(mo) |> distinct(mo, .keep_all = TRUE)
 
+taxonomy <- taxonomy |> 
+  mutate(fullname = case_match(rank,
+                               "phylum" ~ phylum,
+                               "class" ~ class,
+                               "order" ~ order,
+                               "family" ~ family,
+                               .default = fullname))
 # are fullnames unique?
 taxonomy %>% filter(fullname %in% .[duplicated(fullname), "fullname", drop = TRUE])
 
 # are all GBIFs available?
 taxonomy %>%
-  filter(!gbif_parent %in% gbif) %>%
-  count(rank)
-# try to find the right gbif IDs
-taxonomy$gbif_parent[which(!taxonomy$gbif_parent %in% taxonomy$gbif & taxonomy$rank == "species")] <- taxonomy$gbif[match(taxonomy$genus[which(!taxonomy$gbif_parent %in% taxonomy$gbif & taxonomy$rank == "species")], taxonomy$genus)]
-taxonomy$gbif_parent[which(!taxonomy$gbif_parent %in% taxonomy$gbif & taxonomy$rank == "class")] <- taxonomy$gbif[match(taxonomy$phylum[which(!taxonomy$gbif_parent %in% taxonomy$gbif & taxonomy$rank == "class")], taxonomy$phylum)]
-taxonomy %>%
-  filter(!gbif_parent %in% gbif) %>%
-  count(rank)
+  filter((!gbif_parent %in% gbif) | (!lpsn_parent %in% lpsn)) %>%
+  count(source = ifelse(!gbif_parent %in% gbif, "GBIF", "LPSN"),
+        rank)
 
-# are all LPSNs available?
+# so fix again all parent GBIF identifiers
+taxonomy$gbif_parent[taxonomy$rank == "phylum"] <- taxonomy$gbif[match(taxonomy$kingdom[taxonomy$rank == "phylum"], taxonomy$fullname)]
+taxonomy$gbif_parent[taxonomy$rank == "class"] <- taxonomy$gbif[match(taxonomy$phylum[taxonomy$rank == "class"], taxonomy$fullname)]
+taxonomy$gbif_parent[taxonomy$rank == "order"] <- taxonomy$gbif[match(taxonomy$class[taxonomy$rank == "order"], taxonomy$fullname)]
+taxonomy$gbif_parent[taxonomy$rank == "family"] <- taxonomy$gbif[match(taxonomy$order[taxonomy$rank == "family"], taxonomy$fullname)]
+taxonomy$gbif_parent[taxonomy$rank == "genus"] <- taxonomy$gbif[match(taxonomy$family[taxonomy$rank == "genus"], taxonomy$fullname)]
+taxonomy$gbif_parent[taxonomy$rank == "species"] <- taxonomy$gbif[match(taxonomy$genus[taxonomy$rank == "species"], taxonomy$fullname)]
+taxonomy$gbif_parent[taxonomy$rank == "subspecies"] <- taxonomy$gbif[match(paste(taxonomy$genus[taxonomy$rank == "subspecies"], taxonomy$species[taxonomy$rank == "subspecies"]), taxonomy$fullname)]
+# and LPSN identifiers
+taxonomy$lpsn_parent[taxonomy$rank == "phylum"] <- taxonomy$lpsn[match(taxonomy$kingdom[taxonomy$rank == "phylum"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "class"] <- taxonomy$lpsn[match(taxonomy$phylum[taxonomy$rank == "class"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "order"] <- taxonomy$lpsn[match(taxonomy$class[taxonomy$rank == "order"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "family"] <- taxonomy$lpsn[match(taxonomy$order[taxonomy$rank == "family"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "genus"] <- taxonomy$lpsn[match(taxonomy$family[taxonomy$rank == "genus"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "species"] <- taxonomy$lpsn[match(taxonomy$genus[taxonomy$rank == "species"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "subspecies"] <- taxonomy$lpsn[match(paste(taxonomy$genus[taxonomy$rank == "subspecies"], taxonomy$species[taxonomy$rank == "subspecies"]), taxonomy$fullname)]
+
+# check again
 taxonomy %>%
-  filter(!lpsn_parent %in% lpsn) %>%
-  count(rank)
-# make GBIF refer to newest renaming according to LPSN
-taxonomy$gbif_renamed_to[which(!is.na(taxonomy$gbif_renamed_to) & !is.na(taxonomy$lpsn_renamed_to))] <- taxonomy$gbif[match(taxonomy$lpsn_renamed_to[which(!is.na(taxonomy$gbif_renamed_to) & !is.na(taxonomy$lpsn_renamed_to))], taxonomy$lpsn)]
+  filter((!gbif_parent %in% gbif) | (!lpsn_parent %in% lpsn)) %>%
+  count(source = ifelse(!gbif_parent %in% gbif, "GBIF", "LPSN"),
+        rank)
+
+
 
 # Save intermediate results (3) -------------------------------------------
 
 saveRDS(taxonomy, "data-raw/taxonomy3.rds")
 
 
+# Redo LPSN missings and parents ------------------------------------------
+
+gbif_bacteria_second_run <- which(taxonomy$kingdom == "Bacteria" & taxonomy$source == "GBIF" & taxonomy$rank %in% c("phylum", "class", "order", "family"))
+gbif_bacteria_second_run <- gbif_bacteria_second_run[!gbif_bacteria_second_run %in% gbif_bacteria]
+added <- 0
+pb <- progress_bar$new(total = length(gbif_bacteria_second_run), format = "[:bar] :current/:total :eta")
+for (record in gbif_bacteria_second_run) {
+  pb$tick()
+  lpsn <- get_lpsn_and_author(rank = taxonomy$rank[record],
+                              name = taxonomy$fullname[record])
+  if (is.na(lpsn["lpsn"])) {
+    next
+  } else {
+    added <- added + 1
+    taxonomy$source[record] <- "LPSN"
+    taxonomy$lpsn[record] <- unname(lpsn["lpsn"])
+    taxonomy$ref[record] <- unname(lpsn["ref"])
+    taxonomy$status[record] <- unname(lpsn["status"])
+  }
+}
+message(added, " GBIF records altered to latest LPSN")
+taxbak <- taxonomy
+taxonomy$lpsn_parent[taxonomy$rank == "phylum"] <- taxonomy$lpsn[match(taxonomy$kingdom[taxonomy$rank == "phylum"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "class"] <- taxonomy$lpsn[match(taxonomy$phylum[taxonomy$rank == "class"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "order"] <- taxonomy$lpsn[match(taxonomy$class[taxonomy$rank == "order"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "family"] <- taxonomy$lpsn[match(taxonomy$order[taxonomy$rank == "family"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "genus"] <- taxonomy$lpsn[match(taxonomy$family[taxonomy$rank == "genus"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "species"] <- taxonomy$lpsn[match(taxonomy$genus[taxonomy$rank == "species"], taxonomy$fullname)]
+taxonomy$lpsn_parent[taxonomy$rank == "subspecies"] <- taxonomy$lpsn[match(paste(taxonomy$genus[taxonomy$rank == "subspecies"], taxonomy$species[taxonomy$rank == "subspecies"]), taxonomy$fullname)]
+
+# TODO: there is no order Eggerthellales anymore
+
+
 # Remove unwanted taxonomic entries from Protoza/Fungi --------------------
 
 # this must be done after the microbial ID generation, since it will otherwise generate a lot of different IDs
@@ -1256,12 +1405,12 @@ taxonomy <- taxonomy %>%
     # Protozoa:
     !(phylum %in% c("Choanozoa", "Mycetozoa") & prevalence == 3),
     # Fungi:
-    !(phylum %in% c("Ascomycota", "Zygomycota", "Basidiomycota") & prevalence == 3),
+    !(phylum %in% c("Ascomycota", "Zygomycota", "Basidiomycota") & prevalence == 3 & rank %in% c("genus", "species", "subspecies")),
     !(genus %in% c("Phoma", "Leptosphaeria", "Physarum") & rank %in% c("species", "subspecies")), # only genus of this rare fungus, with resp. 1300 and 800 species
     # (leave Alternaria in there, part of human mycobiome and opportunistic pathogen)
     # Animalia:
     !genus %in% c("Lucilia", "Lumbricus"),
-    !(class == "Insecta" & rank %in% c("species", "subspecies")), # keep only genus of insects
+    !(class == "Insecta" & rank %in% c("species", "subspecies")), # keep only genus of insects, not all of their (sub)species
     !(genus == "Amoeba" & kingdom == "Animalia"),
     !(genus %in% c("Aedes", "Anopheles") & rank %in% c("species", "subspecies")), # only genus of the many hundreds of mosquitoes species
     kingdom != "Plantae"
@@ -1270,7 +1419,8 @@ taxonomy <- taxonomy %>%
 # no ghost families, orders classes, phyla
 taxonomy <- taxonomy %>%
   group_by(kingdom, family) %>%
-  filter(n() > 1 | fullname %like% "unknown" | rank == "kingdom") %>%
+  # (but keep the ghost families of bacteria)
+  filter(n() > 1 | fullname %like% "unknown" | rank == "kingdom" | kingdom == "Bacteria") %>%
   group_by(kingdom, order) %>%
   filter(n() > 1 | fullname %like% "unknown" | rank == "kingdom") %>%
   group_by(kingdom, class) %>%
@@ -1280,6 +1430,34 @@ taxonomy <- taxonomy %>%
   ungroup()
 
 
+for (i in which(colnames(taxonomy) %in% c("phylum", "class", "order", "family")) - 1) {
+  i_name <- colnames(taxonomy)[i + 1]
+  message("Adding missing: ", i_name, "... ", appendLF = FALSE)
+  to_add <- taxonomy %>%
+    filter(.[[i + 1]] != "") %>%
+    distinct(kingdom, .[[i + 1]], .keep_all = TRUE) %>%
+    select(kingdom:(i + 1)) %>%
+    mutate(
+      fullname = .[[ncol(.)]],
+      rank = i_name
+    ) %>%
+    filter(!paste(kingdom, .[[ncol(.) - 2]], rank) %in% paste(taxonomy$kingdom, taxonomy[[i + 1]], taxonomy$rank)) %>%
+    # get GBIF identifier where available
+    left_join(
+      current_gbif %>%
+        select(kingdom, all_of(i_name), rank = taxonRank, ref = scientificNameAuthorship, gbif = taxonID, gbif_parent = parentNameUsageID),
+      by = c("kingdom", "rank", i_name)
+    ) %>%
+    mutate(source = ifelse(!is.na(gbif), "GBIF", "manually added"),
+           status = ifelse(!is.na(gbif), "accepted", "unknown"))
+  message("n = ", nrow(to_add))
+  # taxonomy_all_missing <- taxonomy_all_missing %>%
+  #   bind_rows(to_add)
+}
+
+
+
+
 message(
   "\nCongratulations! The new taxonomic table will contain ", format(nrow(taxonomy), big.mark = " "), " rows.\n",
   "This was ", format(nrow(AMR::microorganisms), big.mark = " "), " rows.\n"
@@ -1493,7 +1671,7 @@ if (!identical(example_isolates$mo, as.mo(example_isolates$mo, language = NULL))
 
 # load new data sets again
 devtools::load_all(".")
-source("data-raw/_pre_commit_hook.R")
+source("data-raw/_pre_commit_checks.R")
 devtools::load_all(".")
 
 if (!identical(intrinsic_resistant$mo, as.mo(intrinsic_resistant$mo, language = NULL))) {

data-raw/translations.tsv

@@ -73,6 +73,7 @@ Bacitracin	FALSE	TRUE	TRUE	FALSE	阿奇霉素	Bacitracin	Bacitracin	Bacitracine
 Benzathine benzylpenicillin	FALSE	TRUE	TRUE	FALSE	苄丝肼青霉素	Benzathine benzylpenicillin	Benzathinbenzylpenicillin	Benzylpenicillinebenzathine	Bentsatiinibentsyylipenisilliini	Benzathine benzylpénicilline	Benzathin-Benzylpenicillin	Βενζαθίνη βενζυλπενικιλλίνη	Benzatina benzilpenicillina	ベンズシン・ベンジルペニシリン	Benzathine benzylpenicillin	Benzylpenicylina benzylowa	Benzatina benzatina benzilpenicilina	Benzatină benzilpenicilină	Бензатин бензилпенициллин	Bencilpenicilina benzatínica	Benzathinbenzylpenicillin	Benzatin benzilpenisilin	Бензатину бензилпеніцилін
 Benzathine phenoxymethylpenicillin	FALSE	TRUE	TRUE	FALSE	苄星苯氧甲基青霉素	Benzatinový fenoxymethylpenicilin	Benzathinfenoxymethylpenicillin	Fenoxymethylpenicillinebenzathine	Bentsatiinifenoksimetyylipenisilliini	Phénoxyméthylpénicilline benzathine	Benzathin-Phenoxymethylpenicillin	Βενζαθίνη φαινοξυμεθυλοπενικιλλίνη	Benzatina fenossimetilpenicillina	ベンザチンフェノキシメチルペニシリン	Benzathine fenoksymetylpenicillin	Fenoksymetylopenicylina benzylowa	Benzatina fenoximetilpenicilina	Benzatină fenoximetilpenicilină	Бензатин феноксиметилпенициллин	Fenoximetilpenicilina benzatínica	Bensathinfenoximetylpenicillin	Benzatin fenoksimetilpenisilin	Бензатину феноксиметилпеніцилін
 Benzylpenicillin	FALSE	TRUE	TRUE	FALSE	苄基青霉素	Benzylpenicilin	Benzylpenicillin	Benzylpenicilline	Bentsyylipenisilliini	Benzylpénicilline	Benzylpenicillin	Βενζυλοπενικιλλίνη	Benzilpenicillina	ベンジルペニシリン	Benzylpenicillin	Benzylpenicylina	Benzilpenicilina	Benzilpenicilină	Бензилпенициллин	Bencilpenicilina	Bensylpenicillin	Benzilpenisilin	Бензилпеніцилін
+Cadazolid	FALSE	TRUE	TRUE	FALSE	卡达唑利德	Kadazolid	Cadazolid	Cadazolid	Kadazolid	Cadazolid	Cadazolid	Καδαζολίδη	Cadazolid	カダゾリド	Cadazolid	Kadazolid	Cadazolid	Cadazolid	Кадазолид	Cadazolid	Cadazolid	Cadazolid	Кадазолід
 Calcium aminosalicylate	FALSE	TRUE	TRUE	FALSE	氨基水杨酸钙	Aminosalicylát vápenatý	Calciumaminosalicylat	Aminosalicylzuur	Kalsiumaminosalisylaatti	Aminosalicylate de calcium	Kalzium-Aminosalicylat	Αμινοσαλικυλικό ασβέστιο	Calcio aminosalicilato	アミノサリチル酸カルシウム	Kalsiumaminosalicylat	Aminosalicylan wapnia	Aminosalicilato de cálcio	Aminosalicilat de calciu	Аминосалицилат кальция	Aminosalicilato de calcio	Kalciumaminosalicylat	Kalsiyum aminosalisilat	Кальцію аміносаліцилат
 Capreomycin	FALSE	TRUE	TRUE	FALSE	氨水杨酸钙	Kapreomycin	Capreomycin	Capreomycine	Kapreomysiini	Capréomycine	Capreomycin	Καπρεομυκίνη	Capreomicina	カプレオマイシン	Capreomycin	Kapreomycyna	Capreomicina	Capreomicină	Капреомицин	Capreomicina	Kapreomycin	Kapreomisin	Капреоміцин
 Carbenicillin	FALSE	TRUE	TRUE	FALSE	羧基青霉素	Karbenicilin	Carbenicillin	Carbenicilline	Karbenisilliini	Carbénicilline	Carbenicillin	Καρβενικιλλίνη	Carbenicillina	カルベニシリン	Karbenicillin	Karbenicylina	Carbenicilina	Carbenicilină	Карбенициллин	Carbenicilina	Karbenicillin	Karbenisilin	Карбеніцилін
@@ -110,14 +111,19 @@ Chloramphenicol	FALSE	TRUE	TRUE	FALSE	氯霉素	Chloramfenikol	Kloramfenicol	Chl
 Chlortetracycline	FALSE	TRUE	TRUE	FALSE	金霉素	Chlortetracyklin	Chlortetracyclin	Chloortetracycline	Klortetasykliini	Chlortétracycline	Chlortetracyclin	Χλωροτετρακυκλίνη	Clorotetraciclina	クロルテトラサイクリン	Klortetracyklin	Chlortetracyklina	Chlortetracycline	Clortetraciclină	Хлортетрациклин	Clortetraciclina	Klortetracyklin	Klortetrasiklin	Хлортетрациклін
 Cinoxacin	FALSE	TRUE	TRUE	FALSE	西诺沙星	Cinoxacin	Cinoxacin	Cinoxacine	Kinoksasiini	Cinoxacine	Cinoxacin	Τσινοξακίνη	Cinoxacina	シノキサシン	Cinoxacin	Cinoxacin	Cinoxacin	Cinoxacină	Циноксацин	Cinoxacina	Cinoxacin	Cinoxacin	Циноксацин
 Ciprofloxacin	FALSE	TRUE	TRUE	FALSE	环丙沙星	Ciprofloxacin	Ciprofloxacin	Ciprofloxacine	Siprofloksasiini	Ciprofloxacine	Ciprofloxacin	Σιπροφλοξασίνη	Ciprofloxacina	シプロフロキサシン	Ciprofloxacin	Ciprofloksacyna	Ciprofloxacin	Ciprofloxacină	Ципрофлоксацин	Ciprofloxacina	Ciprofloxacin	Siprofloksasin	Ципрофлоксацин
+Ciprofloxacin/metronidazole	FALSE	TRUE	TRUE	FALSE	环丙沙星/甲硝唑	Ciprofloxacin/metronidazol	Ciprofloxacin/metronidazol	Ciprofloxacine/metronidazol	Siprofloksasiini/metronidatsoli	Ciprofloxacine/métronidazole	Ciprofloxacin/metronidazol	Σιπροφλοξασίνη/μετρονιδαζόλη	Ciprofloxacina/metronidazolo	シプロフロキサシン/メトロニダゾール	Ciprofloxacin/metronidazol	Ciprofloksacyna/metronidazol	Ciprofloxacin/metronidazol	Ciprofloxacină/metronidazol	Ципрофлоксацин/метронидазол	Ciprofloxacina/metronidazol	Ciprofloxacin/metronidazol	Siprofloksasin/metronidazol	Ципрофлоксацин/метронідазол
+Ciprofloxacin/ornidazole	FALSE	TRUE	TRUE	FALSE	环丙沙星/奥硝唑	Ciprofloxacin/ornidazol	Ciprofloxacin/ornidazol	Ciprofloxacine/ornidazol	Siprofloksasiini/ornidatsoli	Ciprofloxacine/ornidazole	Ciprofloxacin/ornidazol	Σιπροφλοξασίνη/ορνιδαζόλη	Ciprofloxacina/ornidazolo	シプロフロキサシン/オルニダゾール	Ciprofloxacin/ornidazol	Ciprofloksacyna/ornidazol	Ciprofloxacin/ornidazole	Ciprofloxacină/ornidazol	Ципрофлоксацин/орнидазол	Ciprofloxacina/ornidazol	Ciprofloxacin/ornidazol	Siprofloksasin/ornidazol	Ципрофлоксацин/орнідазол
+Ciprofloxacin/tinidazole	FALSE	TRUE	TRUE	FALSE	环丙沙星/替尼唑	Ciprofloxacin/tinidazol	Ciprofloxacin/tinidazol	Ciprofloxacine/tinidazol	Siprofloksasiini/tinidatsoli	Ciprofloxacine/tinidazole	Ciprofloxacin/tinidazol	Σιπροφλοξασίνη/τινιδαζόλη	Ciprofloxacina/tinidazolo	シプロフロキサシン/チニダゾール	Ciprofloxacin/tinidazol	Ciprofloksacyna/tinidazol	Ciprofloxacin/tinidazole	Ciprofloxacină/tinidazol	Ципрофлоксацин/тинидазол	Ciprofloxacina/tinidazol	Ciprofloxacin/tinidazol	Siprofloksasin/tinidazol	Ципрофлоксацин/тинідазол
 Clarithromycin	FALSE	TRUE	TRUE	FALSE	克拉霉素	Klaritromycin	Clarithromycin	Claritromycine	Klaritromysiini	Clarithromycine	Clarithromycin	Κλαριθρομυκίνη	Claritromicina	クラリスロマイシン	Klaritromycin	Klarytromycyna	Claritromicina	Claritromicină	Кларитромицин	Claritromicina	Claritromycin	Klaritromisin	Кларитроміцин
 Clavulanic acid	FALSE	TRUE	TRUE	FALSE	克拉维酸	Kyselina klavulanová	Clavulansyre	Clavulaanzuur	Klavulaanihappo	Acide clavulanique	Clavulansäure	Κλαβουλανικό οξύ	Acido clavulanico	クラビュラン酸	Klavulansyre	Kwas klawulanowy	Ácido clavulânico	Acid clavulanic	Клавулановая кислота	Ácido clavulánico	Clavulansyra	Klavulanik asit	Клавуланова кислота
 clavulanic acid	FALSE	TRUE	TRUE	FALSE	克拉维酸	kyselina klavulanová	clavulansyre	clavulaanzuur	klavulaanihappo	acide clavulanique	Clavulansäure	Κλαβουλανικό οξύ	acido clavulanico	クラビュラン酸	klavulansyre	kwas klawulanowy	ácido clavulânico	acid clavulanic	клавулановая кислота	ácido clavulánico	clavulansyra	klavulanik asit	клавуланова кислота
 Clindamycin	FALSE	TRUE	TRUE	FALSE	克林霉素	Klindamycin	Clindamycin	Clindamycine	Klindamysiini	Clindamycine	Clindamycin	Κλινδαμυκίνη	Clindamicina	クリンダマイシン	Klindamycin	Klindamycyna	Clindamicina	Clindamicină	Клиндамицин	Clindamicina	Clindamycin	Klindamisin	Кліндаміцин
+Clindamycin inducible screening	FALSE	TRUE	TRUE	FALSE	克林霉素诱导筛选	Klindamycin induzierbares Screening	Clindamycin inducible screening	Clindamycine induceerbare screening	Klindamysiini indusoitava seulonta	Clindamycine dépistage inductible	Clindamycin induzierbares Screening	Κλινδαμυκίνη επαγόμενο προσυμπτωματικό έλεγχο	Clindamicina inducción del cribado	クリンダマイシン誘導スクリーニング	Klindamycin inducible screening	Klindamycyna badanie indukcyjne	Clindamicina cribado inducible	Clindamicină screening inductibil	Клиндамицин индуцируемый скрининг	Clindamicina cribado inducible	Clindamycin inducible screening	Klindamisin indüklenebilir tarama	Кліндаміцин індукційний скринінг
 Clometocillin	FALSE	TRUE	TRUE	FALSE	克罗米修斯（	Clometocillin	Clometocillin	Clometocilline	Klometosilliini	Clométocilline	Clometocillin	Κλομετοκιλλίνη	Clometocillina	クロメトシリン	Klometocillin	Clometocillin	Clometocillin	Clometocilină	Клометоциллин	Clometocilina	Klometocillin	Clometocillin	Клометоцилін
 Clotrimazole	FALSE	TRUE	TRUE	FALSE	克霉唑	Klotrimazol	Clotrimazol	Clotrimazol	Klotrimatsoli	Clotrimazole	Clotrimazol	Κλοτριμαζόλη	Clotrimazolo	クロトリマゾール	Klotrimazol	Klotrimazol	Clotrimazole	Clotrimazol	Клотримазол	Clotrimazol	Klotrimazol	Klotrimazol	Клотримазол
 Cloxacillin	FALSE	TRUE	TRUE	FALSE	克罗西林	Kloxacilin	Cloxacillin	Cloxacilline	Kloksasilliini	Cloxacilline	Cloxacillin	Κλοξακιλλίνη	Cloxacillina	クロキサシリン	Cloxacillin	Cloxacillin	Cloxacillin	Cloxacilină	Клоксациллин	Cloxacilina	Kloxacillin	Cloxacillin	Клоксацилін
 Colistin	FALSE	TRUE	TRUE	FALSE	唑啉酮	Kolistin	Colistin	Colistine	Kolistiini	Colistine	Colistin	Κολιστίνη	Colistina	コリスチン	Kolistin	Kolistyna	Colistin	Colistină	Колистин	Colistina	Kolistin	Kolistin	Колістин
+Cycloserine	FALSE	TRUE	TRUE	FALSE	环丝氨酸	Cykloserin	Cykloserin	Cycloserine	Sykloserini	Cyclosérine	Cycloserin	Κυκλοσερίνη	Cicloserina	サイクロセリン	Cycloserine	Cykloseryna	Cicloserina	Cicloserină	Циклосерин	Cicloserina	Cycloserine	Sikloserin	Циклосерин
 Dapsone	FALSE	TRUE	TRUE	FALSE	多普生	Dapson	Dapson	Dapson	Dapsoni	Dapsone	Dapson	Δαψόνη	Dapsone	ダプソン	Dapsone	Dapson	Dapsone	Dapsone	Дапсон	Dapsona	Dapson	Dapson	Дапсон
 Daptomycin	FALSE	TRUE	TRUE	FALSE	达托霉素	Daptomycin	Daptomycin	Daptomycine	Daptomysiini	Daptomycine	Daptomycin	Δαπτομυκίνη	Daptomicina	ダプトマイシン	Daptomycin	Daptomycyna	Daptomicina	Daptomicină	Даптомицин	Daptomicina	Daptomycin	Daptomisin	Даптоміцин
 Dibekacin	FALSE	TRUE	TRUE	FALSE	迪贝卡星	Dibekacin	Dibekacin	Dibekacine	Dibekasiini	Dibekacine	Dibekacin	Διβεκακίνη	Dibekacin	ジベカシン	Dibekacin	Dibekacin	Dibekacin	Dibekacin	Дибекацин	Dibekacina	Dibekacin	Dibekacin	Дібекацин
@@ -153,6 +159,7 @@ Kanamycin	FALSE	TRUE	TRUE	FALSE	卡那霉素	Kanamycin	Kanamycin	Kanamycine	Kana
 Ketoconazole	FALSE	TRUE	TRUE	FALSE	酮康唑	Ketokonazol	Ketoconazol	Ketoconazol	Ketokonatsoli	Kétoconazole	Ketoconazol	Κετοκοναζόλη	Ketoconazolo	ケトコナゾール	Ketokonazol	Ketokonazol	Ketoconazole	Ketoconazol	Кетоконазол	Ketoconazol	Ketokonazol	Ketokonazol	Кетоконазол
 Levofloxacin	FALSE	TRUE	TRUE	FALSE	氧氟沙星	Levofloxacin	Levofloxacin	Levofloxacine	Levofloksasiini	Lévofloxacine	Levofloxacin	Λεβοφλοξασίνη	Levofloxacina	レボフロキサシン	Levofloxacin	Levofloxacin	Levofloxacin	Levofloxacină	Левофлоксацин	Levofloxacina	Levofloxacin	Levofloksasin	Левофлоксацин
 Lincomycin	FALSE	TRUE	TRUE	FALSE	林可霉素	Linkomycin	Lincomycin	Lincomycine	Lincomycin	Lincomycine	Lincomycin	Λινκομυκίνη	Lincomicina	リンコマイシン	Lincomycin	Lincomycyna	Lincomycin	Lincomicină	Линкомицин	Lincomicina	Lincomycin	Lincomycin	Лінкоміцин
+Linezolid	FALSE	TRUE	TRUE	FALSE	利奈唑胺	Linezolid	Linezolid	Linezolid	Linezolid	Linezolid	Linezolid	Λινεζολίδη	Linezolid	リネゾリド	Linezolid	Linezolid	Linezolid	Linezolid	Линезолид	Linezolid	Linezolid	Linezolid	Лінезолід
 Lomefloxacin	FALSE	TRUE	TRUE	FALSE	洛美沙星	Lomefloxacin	Lomefloxacin	Lomefloxacine	Lomefloksasiini	Loméfloxacine	Lomefloxacin	Λομεφλοξασίνη	Lomefloxacina	ロメフロキサシン	Lomefloksacin	Lomefloxacin	Lomefloxacin	Lomefloxacină	Ломефлоксацин	Lomefloxacina	Lomefloxacin	Lomefloksasin	Ломефлоксацин
 Lysozyme	FALSE	TRUE	TRUE	FALSE	硫酸钠	Lysozym	Lysozym	Lysozym	Lysotsyymi	Lysozyme	Lysozym	Λυσοζύμη	Lisozima	リゾチーム	Lysozym	Lizozym	Lysozyme	Lizozimă	Лизоцим	Lisozima	Lysozym	Lizozim	Лізоцим
 Mandelic acid	FALSE	TRUE	TRUE	FALSE	扁桃酸	Kyselina mandlová	Mandelinsyre	Amandelzuur	Mandelihappo	Acide mandélique	Mandelsäure	Μανδελικό οξύ	Acido mandelico	マンデル酸	Mandelsyre	Kwas migdałowy	Ácido mandélico	Acid mandelic	Мандаловая кислота	Ácido mandélico	Mandelsyra	Mandelik asit	Мигдалева кислота
@@ -243,12 +250,14 @@ Sulfathiazole	FALSE	TRUE	TRUE	FALSE	磺胺噻唑	Sulfathiazol	Sulfathiazol	Sulfa
 Sulfathiourea	FALSE	TRUE	TRUE	FALSE	磺胺硫脲	Sulfathiomočovina	Sulfathiourea	Sulfathioureum	Sulfathiourea	Sulfathiourée	Sulfathioharnstoff	Σουλφαθειουρία	Sulfathiourea	スルファチオ尿素	Sulfathiourea	Sulfathiourea	Sulfathiourea	Sulfathiourea	Сульфатиомочевина	Sulfathiourea	Sulfatiourea	Sulfathiourea	Сульфатіосечовина
 Sultamicillin	FALSE	TRUE	TRUE	FALSE	苏打米林	Sultamicilin	Sultamicillin	Sultamicilline	Sultamisilliini	Sultamicilline	Sultamicillin	Σουλταμικιλλίνη	Sultamicillina	スルタミシリン	Sultamicillin	Sultamicillin	Sultamicillin	Sultamicilină	Сультамициллин	Sultamicilina	Sultamicillin	Sultamicillin	Сультаміцилін
 Talampicillin	FALSE	TRUE	TRUE	FALSE	塔拉比西林	Talampicilin	Talampicillin	Talampicilline	Talampisilliini	Talampicilline	Talampicillin	Ταλαμπικιλλίνη	Talampicillina	タランピシリン	Talampicillin	Talampicylina	Talampicilina	Talampicilină	Талампициллин	Talampicilina	Talampicillin	Talampisilin	Талампіцилін
+Tedizolid	FALSE	TRUE	TRUE	FALSE	特地唑胺	Tedizolid	Tedizolid	Tedizolid	Tedizolid	Tedizolid	Tedizolid	Τεντιζολίδη	Tedizolid	テジゾリド	Tedizolid	Tedizolid	Tedizolid	Tedizolid	Тедизолид	Tedizolid	Tedizolid	Tedizolid	Тедізолід
 Teicoplanin	FALSE	TRUE	TRUE	FALSE	泰科普兰素	Teicoplanin	Teicoplanin	Teicoplanine	Teikoplaniini	Teicoplanine	Teicoplanin	Τεϊκοπλανίνη	Teicoplanina	テイコプラニン	Teicoplanin	Teicoplanin	Teicoplanin	Teicoplanin	Тейкопланин	Teicoplanina	Teicoplanin	Teikoplanin	Тейкопланін
 Telithromycin	FALSE	TRUE	TRUE	FALSE	泰利霉素	Telithromycin	Telithromycin	Telitromycine	Telitromysiini	Télithromycine	Telithromycin	Τελιθρομυκίνη	Telitromicina	テリスロマイシン	Telitromycin	Telitromycyna	Telitromicina	Telitromicină	Телитромицин	Telitromicina	Telitromycin	Telitromisin	Телітроміцин
 Temafloxacin	FALSE	TRUE	TRUE	FALSE	氨甲环酸	Temafloxacin	Temafloxacin	Temafloxacine	Temafloksasiini	Temafloxacine	Temafloxacin	Τεμαφλοξασίνη	Temafloxacina	テマフロキサシン	Temafloxacin	Temafloksacyna	Temafloxacin	Temafloxacin	Темафлоксацин	Temafloxacina	Temafloxacin	Temafloksasin	Темафлоксацин
 Temocillin	FALSE	TRUE	TRUE	FALSE	氨甲蝶呤	Temocillin	Temocillin	Temocilline	Temosilliini	Temocillin	Temocillin	Τεμοκιλλίνη	Temocillina	テモシリン	Temocillin	Temocillin	Temocillin	Temocilină	Темоциллин	Temocilina	Temocillin	Temocillin	Темоцилін
 Tenofovir disoproxil	FALSE	TRUE	TRUE	FALSE	特诺福韦酯	Tenofovir disoproxil	Tenofovir disoproxil	Tenofovir	Tenofoviiridisoproksiili	Tenofovir disoproxil	Tenofovir Disoproxil	Τενοφοβίρη δισοπροξίλη	Tenofovir disoproxil	テノホビルジソプロキシル	Tenofovir disoproxil	Tenofovir disoproxil	Tenofovir disoproxil	Tenofovir disoproxil	Тенофовир дизопроксил	Tenofovir disoproxil	Tenofovir disoproxil	Tenofovir disoproksil	Тенофовір дизопроксил
 Terizidone	FALSE	TRUE	TRUE	FALSE	特立兹酮	Terizidon	Terizidon	Terizidon	Teritsidoni	Terizidone	Terizidon	Τεριζιδόνη	Terizidone	テリジドン	Terizidon	Terizidon	Terizidone	Terizidonă	Теризидон	Terizidona	Terizidon	Terizidon	Теризидон
+Thiacetazone	FALSE	TRUE	TRUE	FALSE	噻乙唑酮	Thiacetazon	Thiacetazon	Thiacetazone	Thiacetazoni	Thiacétazone	Thiacetazon	Θιακεταζόνη	Thiacetazona	チアセタゾン	Thiacetazone	Thiacetazon	Thiacetazona	Thiacetazonă	Тиазетазон	Thiacetazona	Thiacetazone	Thiasetazon	Тіацетазон
 Thiamphenicol	FALSE	TRUE	TRUE	FALSE	硫苯尼考	Thiamfenikol	Thiamphenicol	Thiamfenicol	Tiamfenikoli	Thiamphénicol	Thiamphenicol	Θειαμφενικόλη	Tiamfenicolo	チアンフェニコール	Tiamfenikol	Tiamfenikol	Tiamfenicol	Tiamfenicol	Тиамфеникол	Tiamfenicol	Tiamfenikol	Thiamphenicol	Тіамфенікол
 Thioacetazone/isoniazid	FALSE	TRUE	TRUE	FALSE	硫乙酰唑酮/异烟肼	Thioacetazon/isoniazid	Thioacetazon/isoniazid	Thioacetazon/isoniazide	Tioasetatsoni/isonatsidi	Thioacétazone/isoniazide	Thioacetazon/Isoniazid	Θειοακεταζόνη/ισονιαζίδη	Tioacetazone/isoniazide	チオアセタゾン／イソニアジド	Thioacetazon/isoniazid	Tioacetazon/izoniazyd	Thioacetazone/isoniazid	Tioacetazonă/isoniazidă	Тиоацетазон/изониазид	Tioacetazona/isoniazida	Thioacetazon/isoniazid	Tiyoasetazon/izoniazid	Тіоацетазон/ізоніазид
 Ticarcillin	FALSE	TRUE	TRUE	FALSE	替卡西林	Tykarcilinu	Ticarcillin	Ticarcilline	Ticarcillin	Ticarcilline	Ticarcillin	Τικαρκιλλίνη	Ticarcillina	チカルシリン	Ticarcillin	Ticarcillin	Ticarcilina	Ticarcilină	Тикарциллин	Ticarcilina	Ticarcillin	Ticarcillin	Тикарцилін
@@ -278,3 +287,10 @@ Macrolides/lincosamides	FALSE	TRUE	TRUE	FALSE	大环内酯类/林可酰胺类	Ma
 Other antibacterials	FALSE	TRUE	TRUE	FALSE	其他抗菌剂	Ostatní antibakteriální látky	Andre antibakterielle stoffer	Overige antibiotica	Muut antibakteeriset aineet	Autres antibactériens	Andere Antibiotika	Άλλα αντιβακτηριακά	Altri antibatterici	その他の抗菌薬	Andre antibakterielle midler	Inne środki przeciwbakteryjne	Outros antibacterianos	Alte antibacteriene	Другие антибактериальные препараты	Otros antibacterianos	Andra antibakteriella medel	Diğer antibakteriyeller	Інші антибактеріальні засоби
 Polymyxins	FALSE	TRUE	TRUE	FALSE	多粘菌素类	Polymyxiny	Polymyxiner	Polymyxines	Polymysiinit	Polymyxines	Polymyxine	Πολυμυξίνες	Polimixine	ポリミキシン	Polymyxiner	Polimyksyny	Polimixinas	Polimixine	Полимиксины	Polimixinas	Polymyxiner	Polimiksinler	Поліміксини
 Quinolones	FALSE	TRUE	TRUE	FALSE	喹诺酮类	Chinolony	Kinoloner	Quinolonen	Kinolonit	Quinolones	Quinolone	Κινολόνες	Chinoloni	キノロン	Kinoloner	Quinolony	Quinolones	Quinolone	Хинолоны	Quinolonas	Kinoloner	Kinolonlar	Хінолони
+aquatic|fish	FALSE	FALSE	FALSE	FALSE	水生|条鱼|鱼	vodní|ryba|ryby	akvatisk|fisk	aquatisch|vis|vissen	vesieliö|kala|kalaa	aquatique|poisson|poissons	wasser|fisch|fische	υδρόβια|ψάρι|ψάρια	acquatico|pesce|pesci	アクアティック|1匹|魚	akvatisk|fisk	wodny|ryba|ryby	aquático|peixe|peixes	acvatic|pește|pești	водные|рыба|рыбы	acuático|pez|peces	vattenlevande|fisk|fiskar	sucul|balık	водний|риба|рибки
+cattle|bovine	FALSE	FALSE	FALSE	FALSE	牛|牛	skot	kvæg	vee|rund	karja|nauta	bovins|bovin	rinder	βοοειδή	bovini|bovino	牛|ウシ	storfe|storfe	bydło|bydło	bovinos|bovino	bovine|bovine	крупный рогатый скот|крупный рогатый скот	bovino|bovino	nötkreatur|nötkreatur	sığır|büyükbaş hayvan	велика рогата худоба|бичачий
+cat|cats|feline	FALSE	FALSE	FALSE	FALSE	猫|猫|猫科动物	kočka|kočky|kočky	kat|katte|kat	kat|katten|katachtig	kissa|kissat|kissa	chat|chats|félin	katze|katzen	γάτα|γάτες|αιλουροειδή	gatto|gatti|felino	猫|猫|ネコ	katt	kot|koty	gato|gatos|felino	pisică|pisici|felină	кошка|кошки|кошка	gato|gatos|felino	katt|katter|kattdjur	kedi|kediler|kedi	кіт|коти|котячий
+dog|dogs|canine	FALSE	FALSE	FALSE	FALSE	狗|狗|犬类	pes|psi|psí	hund|hunde	hond|honden	koira|koirat|koira	chien|canine	hund|hunde|hund	σκύλος|σκύλοι|σκύλος	cane|cani|canino	犬|犬|イヌ	hund	pies|psy|pies	cão|cães|canino	câine|câini|canin	собака|собаки|собака	perro|perros|canino	hund|hundar	köpek|köpekler	пес|собаки|собачий
+horse|horses|equine	FALSE	FALSE	FALSE	FALSE	马|马|马	kůň|koně|koně	hest|heste	paard|paarden	hevonen|hevoset|hevoset	cheval|chevaux|équine	pferd|pferde	άλογο|άλογα|ιπποειδή	cavallo|cavalli|equino	馬|馬|馬	hest	koń|konie|koń	cavalo|cavalos|equinos	cal|cai|ecvideu	лошадь|лошади|лошадь	caballo|caballos|equino	häst|hästar|häst	at|atlar|atçılık	кінь|коні|конячий
+bird|birds|poultry	FALSE	FALSE	FALSE	FALSE	鸟类|鸟类|家禽	ptáci|ptáci|drůbež	fugl|fugle|fjerkræ	vogel|vogels|pluimvee	lintu|linnut|siipikarja	oiseaux|oiseaux|volaille	vogel|vögel|geflügel	πουλιά|πουλιά|πουλερικά	uccello|uccelli|pollame	鳥|鳥|家禽	fugl|fugler|fjørfe	ptak|ptaki|drób	aves|aves|aves de capoeira	pasăre|păsări|păsări de curte	птица|птицы|домашняя птица	aves|aves|aves de corral	fågel|fåglar|fjäderfä	kuş|kuşlar|kümes hayvanları	птах|птахів|птиця
+swine|swines	FALSE	FALSE	FALSE	FALSE	猪|猪	prasata|prasata	svin	varken|varkens	sika|sikaa	porcine|porcs	schwein|schweine	χοίροι|χοίροι	suino|suini	豚|豚|頭	svin	trzoda chlewna|świnie	suínos	porc|porcine	свинья|свиньи	porcino|porcinos	svin	domuz|domuz	свиня|свині

index.md

@@ -1,15 +1,18 @@
 # The `AMR` Package for R <a href="https://msberends.github.io/AMR/"><img src="./logo.svg" align="right" height="139" /></a>
 
+<img src="./endorsement_clsi_eucast.jpg" align="right" height="120" />
+
+* Provides an **all-in-one solution** for AMR data analysis in a One Health approach
 * Generates **antibiograms** - traditional, combined, syndromic, and even WISCA
-* Provides the **full microbiological taxonomy** and data on **all antimicrobial drugs**
-* Applies all recent **CLSI and EUCAST clinical breakpoints** for MICs and disk zones
+* Provides the **full microbiological taxonomy** and extensive info on **all antimicrobial drugs**
+* Applies all recent **CLSI and EUCAST clinical and veterinary breakpoints** for MICs and disk zones
 * Corrects for duplicate isolates, **calculates and predicts AMR** per antibiotic class
-* Integrates with **WHONET**, ATC, **EARS-Net**, PubChem, **LOINC** and **SNOMED CT**
+* Integrates with **WHONET**, ATC, **EARS-Net**, PubChem, **LOINC**, **SNOMED CT**, and **NCBI**
 * Works on Windows, macOS and Linux with **all versions of R** since R-3.0 and is completely **dependency-free**, highly suitable for places with **limited resources**
 
 <div style="display: flex; font-size: 0.8em;">
 <p style="text-align:left; width: 50%;"><small><a href="https://msberends.github.io/AMR/">https://msberends.github.io/AMR</a></small></p>
-<p style="text-align:right; width: 50%;"><small><a href="https://doi.org/10.18637/jss.v104.i03">https://doi.org/10.18637/jss.v104.i03</a></small></p>
+<p style="text-align:right; width: 50%;"><small><a href="https://doi.org/10.18637/jss.v104.i03" target="_blank">https://doi.org/10.18637/jss.v104.i03</a></small></p>
 </div>
 
 ----
@@ -24,7 +27,7 @@ After installing this package, R knows [**~52,000 distinct microbial species**](
 
 ##### Used in over 175 countries, translated into 20 languages
 
-<a href="./countries_large.png"><img src="./countries.png" target="_blank" align="right" style="max-width: 300px;" /></a>
+<a href="./countries_large.png" target="_blank"><img src="./countries.png" align="right" style="max-width: 300px;" /></a>
 
 Since its first public release in early 2018, this R package has been used in almost all countries in the world. Click the map to enlarge and to see the country names.
 
@@ -240,7 +243,8 @@ It will be downloaded and installed automatically. For RStudio, click on the men
 
 #### Latest development version
 
-[![R-code-check](https://github.com/msberends/AMR/workflows/R-code-check/badge.svg?branch=main)](https://codecov.io/gh/msberends/AMR?branch=main)
+[![check-recent](https://github.com/msberends/AMR/workflows/check-old/badge.svg?branch=main)](https://codecov.io/gh/msberends/AMR?branch=main)
+[![check-recent](https://github.com/msberends/AMR/workflows/check-recent/badge.svg?branch=main)](https://codecov.io/gh/msberends/AMR?branch=main)
 [![CodeFactor](https://www.codefactor.io/repository/github/msberends/amr/badge)](https://www.codefactor.io/repository/github/msberends/amr)
 [![Codecov](https://codecov.io/gh/msberends/AMR/branch/main/graph/badge.svg)](https://codecov.io/gh/msberends/AMR?branch=main)
 

inst/tinytest/test-_deprecated.R

@@ -27,38 +27,4 @@
 # how to conduct AMR data analysis: https://msberends.github.io/AMR/   #
 # ==================================================================== #
 
-sir <- random_sir(100)
-rsi <- sir
-class(rsi) <- gsub("sir", "rsi", class(rsi))
-mic <- random_mic(100)
-disk <- random_disk(100)
 
-expect_identical(summary(sir), summary(rsi))
-expect_identical(c(sir), c(rsi))
-
-expect_identical(suppressWarnings(suppressMessages(as.rsi(as.character(rsi)))),
-                 suppressWarnings(suppressMessages(as.sir(as.character(sir)))))
-expect_identical(suppressWarnings(suppressMessages(as.rsi(mic, mo = "Escherichia coli", ab = "CIP"))),
-                 suppressWarnings(suppressMessages(as.sir(mic, mo = "Escherichia coli", ab = "CIP"))))
-expect_identical(suppressWarnings(suppressMessages(as.rsi(disk, mo = "Escherichia coli", ab = "CIP"))),
-                 suppressWarnings(suppressMessages(as.sir(disk, mo = "Escherichia coli", ab = "CIP"))))
-expect_identical(suppressWarnings(suppressMessages(as.rsi(data.frame(CIP = mic, mo = "Escherichia coli")))),
-                 suppressWarnings(suppressMessages(as.sir(data.frame(CIP = mic, mo = "Escherichia coli")))))
-
-expect_identical(suppressWarnings(n_rsi(example_isolates$CIP)),
-                 suppressWarnings(n_sir(example_isolates$CIP)))
-
-expect_identical(suppressWarnings(rsi_df(example_isolates)),
-                 suppressWarnings(sir_df(example_isolates)))
-
-expect_identical(suppressWarnings(is.rsi.eligible(example_isolates)),
-                 suppressWarnings(is_sir_eligible(example_isolates)))
-
-if (AMR:::pkg_is_available("ggplot2")) {
-  expect_equal(suppressWarnings(ggplot_rsi(example_isolates[, c("CIP", "GEN", "TOB")])),
-               suppressWarnings(ggplot_sir(example_isolates[, c("CIP", "GEN", "TOB")])))
-  
-  p <- ggplot2::ggplot(example_isolates[, c("CIP", "GEN", "TOB")])
-  expect_equal(suppressWarnings(p + geom_rsi() + scale_rsi_colours() + labels_rsi_count() + facet_rsi() + theme_rsi()),
-               suppressWarnings(p + geom_sir() + scale_sir_colours() + labels_sir_count() + facet_sir() + theme_sir()))
-}

inst/tinytest/test-ab.R

@@ -79,6 +79,16 @@ expect_equal(
 # based on Levenshtein distance
 expect_identical(ab_name("ceftazidim/avibactam", language = NULL), "Ceftazidime/avibactam")
 
+expect_identical(as.character(as.ab(c("gentamicine High Level",
+                                      "gentamicine High",
+                                      "gentamicine (High Level)",
+                                      "gentamicine (High)",
+                                      "gentamicine HL",
+                                      "gentamicine H-L",
+                                      "gentamicine (HL)",
+                                      "gentamicine (H-L)"))),
+                 rep("GEH", 8))
+
 # assigning and subsetting
 x <- antibiotics$ab
 expect_inherits(x[1], "ab")

inst/tinytest/test-ab_property.R

@@ -66,8 +66,7 @@ expect_equal(
   c("101477-8", "101478-6", "18864-9", "18865-6", "20374-5", "21066-6", "23618-2", "27-3", "28-1", "29-9", "30-7", "31-5", "32-3", "33-1", "3355-5", "33562-0", "33919-2", "34-9", "43883-8", "43884-6", "6979-9", "6980-7", "87604-5")
 )
 
-expect_true(ab_url("AMX") %like% "whocc.no")
-# expect_warning(ab_url("ASP"))
+expect_true(ab_url("AMX") %like% "fhi[.]no")
 
 expect_identical(
   colnames(set_ab_names(example_isolates[, 17:22])),

inst/tinytest/test-av_property.R

@@ -60,5 +60,4 @@ expect_equal(
   c("29113-8", "30273-7", "30287-7", "30303-2", "78772-1", "78773-9", "79134-3", "80118-3")
 )
 
-expect_true(av_url("ACI") %like% "whocc.no")
-# expect_warning(av_url("ASP"))
+expect_true(av_url("ACI") %like% "fhi[.]no")

inst/tinytest/test-count.R

@@ -69,7 +69,7 @@ if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0", also_load = TRUE)) {
     example_isolates %>% count_susceptible(AMC, GEN, only_all_tested = TRUE) +
       example_isolates %>% count_resistant(AMC, GEN, only_all_tested = TRUE)
   )
-
+  
   # count of cases
   expect_equal(
     example_isolates %>%
@@ -95,8 +95,10 @@ if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0", also_load = TRUE)) {
     example_isolates %>% select(AMX) %>% count_df(combine_SI = FALSE) %>% pull(value),
     c(
       suppressWarnings(example_isolates$AMX %>% count_S()),
+      0,
       example_isolates$AMX %>% count_I(),
-      example_isolates$AMX %>% count_R()
+      example_isolates$AMX %>% count_R(),
+      0
     )
   )
 

inst/tinytest/test-italicise_taxonomy.R

@@ -41,3 +41,7 @@ if (AMR:::has_colour()) {
     "test for \033[3mE. coli\033[23m"
   )
 }
+expect_identical(
+  italicise_taxonomy("test for E. coli", "html"),
+  "test for <i>E. coli</i>"
+)

inst/tinytest/test-mic.R

@@ -142,10 +142,35 @@ suppressWarnings(expect_identical(el1^el2, el1_double^el2_double))
 suppressWarnings(expect_identical(el1 %% el2, el1_double %% el2_double))
 suppressWarnings(expect_identical(el1 %/% el2, el1_double %/% el2_double))
 suppressWarnings(expect_identical(el1 & el2, el1_double & el2_double))
-suppressWarnings(expect_identical(el1 | el2, el1_double | el2_double))
-suppressWarnings(expect_identical(el1 == el2, el1_double == el2_double))
-suppressWarnings(expect_identical(el1 != el2, el1_double != el2_double))
-suppressWarnings(expect_identical(el1 < el2, el1_double < el2_double))
-suppressWarnings(expect_identical(el1 <= el2, el1_double <= el2_double))
-suppressWarnings(expect_identical(el1 >= el2, el1_double >= el2_double))
-suppressWarnings(expect_identical(el1 > el2, el1_double > el2_double))
+
+# for comparison operators, be more strict:
+expect_true(as.mic(">32") > as.mic(32))
+expect_true(as.mic(">32") >= as.mic(32))
+expect_true(as.mic(">32") >= as.mic("<32"))
+expect_true(as.mic(">32") >= as.mic("<=32"))
+expect_true(as.mic(">32") > as.mic("<=32"))
+
+expect_false(as.mic("32") > as.mic(32))
+expect_true(as.mic("32") >= as.mic(32))
+expect_true(as.mic("32") >= as.mic("<32"))
+expect_true(as.mic("32") >= as.mic("<=32"))
+expect_false(as.mic("32") > as.mic("<=32"))
+
+expect_true(as.mic("32") == as.mic(32))
+expect_true(as.mic("32") == as.mic(32))
+expect_false(as.mic("32") == as.mic("<32"))
+expect_true(as.mic("32") == as.mic("<=32"))
+expect_true(as.mic("32") == as.mic("<=32"))
+
+expect_false(as.mic(">32") < as.mic(32))
+expect_false(as.mic(">32") <= as.mic(32))
+expect_false(as.mic(">32") <= as.mic("<32"))
+expect_false(as.mic(">32") <= as.mic("<=32"))
+expect_false(as.mic(">32") < as.mic("<=32"))
+
+expect_false(as.mic("32") < as.mic(32))
+expect_true(as.mic("32") <= as.mic(32))
+expect_false(as.mic("32") <= as.mic("<32"))
+expect_true(as.mic("32") <= as.mic("<=32"))
+expect_false(as.mic("32") < as.mic("<=32"))
+

inst/tinytest/test-mo_property.R

@@ -98,9 +98,11 @@ expect_equal(names(mo_info("Escherichia coli")), c(
   "mo",
   "kingdom", "phylum", "class", "order", "family", "genus", "species", "subspecies",
   "status", "synonyms", "gramstain", "oxygen_tolerance",
-  "url", "ref", "snomed", "lpsn", "gbif"
+  "url", "ref", "snomed", "lpsn", "gbif", "group_members"
 ))
 expect_inherits(mo_info(c("Escherichia coli", "Staphylococcus aureus")), "list")
+expect_true(length(mo_group_members("B_HACEK")) > 1)
+expect_inherits(mo_group_members(c("Candida albicans", "Escherichia coli")), "list")
 
 expect_identical(mo_oxygen_tolerance(c("Klebsiella pneumoniae", "Clostridioides difficile")),
                  c("aerobe", "anaerobe"))