(v1.5.0.9041) SNOMED update

2025-08-28 00:42:37 +02:00 · 2021-03-11 21:42:30 +01:00
parent 8d6ceb6a15
commit 4e0a9533ad
65 changed files with 86943 additions and 67626 deletions
--- a/R/catalogue_of_life.R
+++ b/R/catalogue_of_life.R
@@ -108,15 +108,15 @@ catalogue_of_life_version <- function() {
  
  check_dataset_integrity()
  
-  # see the `catalogue_of_life` list in R/data.R
+  # see the `CATALOGUE_OF_LIFE` list in R/globals.R
  lst <- list(CoL =
-                list(version = gsub("{year}", catalogue_of_life$year, catalogue_of_life$version, fixed = TRUE),
-                     url = gsub("{year}", catalogue_of_life$year, catalogue_of_life$url_CoL, fixed = TRUE),
+                list(version = gsub("{year}", CATALOGUE_OF_LIFE$year, CATALOGUE_OF_LIFE$version, fixed = TRUE),
+                     url = gsub("{year}", CATALOGUE_OF_LIFE$year, CATALOGUE_OF_LIFE$url_CoL, fixed = TRUE),
                     n = nrow(pm_filter(microorganisms, source == "CoL"))),
              LPSN =
                list(version = "List of Prokaryotic names with Standing in Nomenclature",
-                     url = catalogue_of_life$url_LPSN,
-                     yearmonth = catalogue_of_life$yearmonth_LPSN,
+                     url = CATALOGUE_OF_LIFE$url_LPSN,
+                     yearmonth = CATALOGUE_OF_LIFE$yearmonth_LPSN,
                     n = nrow(pm_filter(microorganisms, source == "LPSN"))),
              total_included =
                list(
--- a/R/data.R
+++ b/R/data.R
@@ -83,7 +83,7 @@

 #' Data Set with `r format(nrow(microorganisms), big.mark = ",")` Microorganisms
 #'
-#' A data set containing the microbial taxonomy, last updated in `r catalogue_of_life$yearmonth_LPSN`, of six kingdoms from the Catalogue of Life (CoL) and the List of Prokaryotic names with Standing in Nomenclature (LPSN). MO codes can be looked up using [as.mo()].
+#' A data set containing the microbial taxonomy, last updated in `r CATALOGUE_OF_LIFE$yearmonth_LPSN`, of six kingdoms from the Catalogue of Life (CoL) and the List of Prokaryotic names with Standing in Nomenclature (LPSN). MO codes can be looked up using [as.mo()].
 #' @inheritSection catalogue_of_life Catalogue of Life
 #' @format A [data.frame] with `r format(nrow(microorganisms), big.mark = ",")` observations and `r ncol(microorganisms)` variables:
 #' - `mo`\cr ID of microorganism as used by this package
@@ -94,7 +94,7 @@
 #' - `species_id`\cr ID of the species as used by the Catalogue of Life
 #' - `source`\cr Either `r vector_or(microorganisms$source)` (see *Source*)
 #' - `prevalence`\cr Prevalence of the microorganism, see [as.mo()]
-#' - `snomed`\cr SNOMED code of the microorganism. Use [mo_snomed()] to retrieve it quickly, see [mo_property()].
+#' - `snomed`\cr Systematized Nomenclature of Medicine (SNOMED) code of the microorganism, according to the `r SNOMED_VERSION$current_source` (see *Source*). Use [mo_snomed()] to retrieve it quickly, see [mo_property()].
 #' @details 
 #' Please note that entries are only based on the Catalogue of Life and the LPSN (see below). Since these sources incorporate entries based on (recent) publications in the International Journal of Systematic and Evolutionary Microbiology (IJSEM), it can happen that the year of publication is sometimes later than one might expect.
 #' 
@@ -124,29 +124,25 @@
 #' 
 #' As of February 2020, the regularly augmented LPSN database at DSMZ is the basis of the new LPSN service. The new database was implemented for the Type-Strain Genome Server and augmented in 2018 to store all kinds of nomenclatural information. Data from the previous version of LPSN and from the Prokaryotic Nomenclature Up-to-date (PNU) service were imported into the new system. PNU had been established in 1993 as a service of the Leibniz Institute DSMZ, and was curated by Norbert Weiss, Manfred Kracht and Dorothea Gleim.
 #' @source 
-#' `r gsub("{year}", catalogue_of_life$year, catalogue_of_life$version, fixed = TRUE)`
+#' `r gsub("{year}", CATALOGUE_OF_LIFE$year, CATALOGUE_OF_LIFE$version, fixed = TRUE)` as currently implemented in this `AMR` package:
 #' 
 #' * Annual Checklist (public online taxonomic database), <http://www.catalogueoflife.org>
 #' 
-#' List of Prokaryotic names with Standing in Nomenclature: `r catalogue_of_life$yearmonth_LPSN`
+#' List of Prokaryotic names with Standing in Nomenclature (`r CATALOGUE_OF_LIFE$yearmonth_LPSN`) as currently implemented in this `AMR` package:
 #' 
 #' * Parte, A.C., Sarda Carbasse, J., Meier-Kolthoff, J.P., Reimer, L.C. and Goker, M. (2020). List of Prokaryotic names with Standing in Nomenclature (LPSN) moves to the DSMZ. International Journal of Systematic and Evolutionary Microbiology, 70, 5607-5612; \doi{10.1099/ijsem.0.004332}
 #' * Parte, A.C. (2018). LPSN — List of Prokaryotic names with Standing in Nomenclature (bacterio.net), 20 years on. International Journal of Systematic and Evolutionary Microbiology, 68, 1825-1829; \doi{10.1099/ijsem.0.002786}
 #' * Parte, A.C. (2014). LPSN — List of Prokaryotic names with Standing in Nomenclature. Nucleic Acids Research, 42, Issue D1, D613–D616; \doi{10.1093/nar/gkt1111}
 #' * Euzeby, J.P. (1997). List of Bacterial Names with Standing in Nomenclature: a Folder Available on the Internet. International Journal of Systematic Bacteriology, 47, 590-592; \doi{10.1099/00207713-47-2-590}
+#' 
+#' `r SNOMED_VERSION$current_source` as currently implemented in this `AMR` package:
+#' 
+#' * Retrieved from the `r SNOMED_VERSION$title`, OID `r SNOMED_VERSION$current_oid`, version `r SNOMED_VERSION$current_version`; url: <`r SNOMED_VERSION$url`>
 #' @inheritSection AMR Reference Data Publicly Available
 #' @inheritSection AMR Read more on Our Website!
 #' @seealso [as.mo()], [mo_property()], [microorganisms.codes], [intrinsic_resistant]
 "microorganisms"

-catalogue_of_life <- list(
-  year = 2019,
-  version = "Catalogue of Life: {year} Annual Checklist",
-  url_CoL = "http://www.catalogueoflife.org/col/",
-  url_LPSN = "https://lpsn.dsmz.de",
-  yearmonth_LPSN = "March 2021"
-)
-
 #' Data Set with Previously Accepted Taxonomic Names
 #'
 #' A data set containing old (previously valid or accepted) taxonomic names according to the Catalogue of Life. This data set is used internally by [as.mo()].
--- a/R/eucast_rules.R
+++ b/R/eucast_rules.R
@@ -23,25 +23,6 @@
 # how to conduct AMR data analysis: https://msberends.github.io/AMR/   #
 # ==================================================================== #

-# add new version numbers here, and add the rules themselves to "data-raw/eucast_rules.tsv" and rsi_translation
-# (sourcing "data-raw/_internals.R" will process the TSV file)
-EUCAST_VERSION_BREAKPOINTS <- list("11.0" = list(version_txt = "v11.0",
-                                                 year = 2021, 
-                                                 title = "'EUCAST Clinical Breakpoint Tables'",
-                                                 url = "https://www.eucast.org/clinical_breakpoints/"),
-                                   "10.0" = list(version_txt = "v10.0",
-                                                 year = 2020, 
-                                                 title = "'EUCAST Clinical Breakpoint Tables'",
-                                                 url = "https://www.eucast.org/ast_of_bacteria/previous_versions_of_documents/"))
-EUCAST_VERSION_EXPERT_RULES <- list("3.1" = list(version_txt = "v3.1",
-                                                 year = 2016, 
-                                                 title = "'EUCAST Expert Rules, Intrinsic Resistance and Exceptional Phenotypes'",
-                                                 url = "https://www.eucast.org/expert_rules_and_intrinsic_resistance/"),
-                                    "3.2" = list(version_txt = "v3.2",
-                                                 year = 2020, 
-                                                 title = "'EUCAST Expert Rules' and 'EUCAST Intrinsic Resistance and Unusual Phenotypes'",
-                                                 url = "https://www.eucast.org/expert_rules_and_intrinsic_resistance/"))
-
 format_eucast_version_nr <- function(version, markdown = TRUE) {
  # for documentation - adds title, version number, year and url in markdown language
  lst <- c(EUCAST_VERSION_BREAKPOINTS, EUCAST_VERSION_EXPERT_RULES)
@@ -74,11 +55,11 @@ format_eucast_version_nr <- function(version, markdown = TRUE) {
 #' @param verbose a [logical] to turn Verbose mode on and off (default is off). In Verbose mode, the function does not apply rules to the data, but instead returns a data set in logbook form with extensive info about which rows and columns would be effected and in which way. Using Verbose mode takes a lot more time.
 #' @param version_breakpoints the version number to use for the EUCAST Clinical Breakpoints guideline. Can be either `r vector_or(names(EUCAST_VERSION_BREAKPOINTS), reverse = TRUE)`.
 #' @param version_expertrules the version number to use for the EUCAST Expert Rules and Intrinsic Resistance guideline. Can be either `r vector_or(names(EUCAST_VERSION_EXPERT_RULES), reverse = TRUE)`.
-#' @param ampc_cephalosporin_resistance a character value that should be applied for AmpC de-repressed cephalosporin-resistant mutants, defaults to `NA`. Currently only works when `version_expertrules` is `3.2`; '*EUCAST Expert Rules v3.2 on Enterobacterales*' states that results of cefotaxime, ceftriaxone and ceftazidime should be reported with a note, or results should be suppressed (emptied) for these agents. A value of `NA` for this argument will remove results for these agents, while e.g. a value of `"R"` will make the results for these agents resistant. Use `NULL` to not alter the results for AmpC de-repressed cephalosporin-resistant mutants. \cr For *EUCAST Expert Rules* v3.2, this rule applies to: `r vector_and(gsub("[^a-zA-Z ]+", "", unlist(strsplit(eucast_rules_file[which(eucast_rules_file$reference.version == 3.2 & eucast_rules_file$reference.rule %like% "ampc"), "this_value"][1], "|", fixed = TRUE))), quotes = "*")`.
+#' @param ampc_cephalosporin_resistance a character value that should be applied to cefotaxime, ceftriaxone and ceftazidime for AmpC de-repressed cephalosporin-resistant mutants, defaults to `NA`. Currently only works when `version_expertrules` is `3.2`; '*EUCAST Expert Rules v3.2 on Enterobacterales*' states that results of cefotaxime, ceftriaxone and ceftazidime should be reported with a note, or results should be suppressed (emptied) for these three agents. A value of `NA` (the default) for this argument will remove results for these three agents, while e.g. a value of `"R"` will make the results for these agents resistant. Use `NULL` or `FALSE` to not alter results for these three agents of AmpC de-repressed cephalosporin-resistant mutants. Using `TRUE` is equal to using `"R"`. \cr For *EUCAST Expert Rules* v3.2, this rule applies to: `r vector_and(gsub("[^a-zA-Z ]+", "", unlist(strsplit(eucast_rules_file[which(eucast_rules_file$reference.version == 3.2 & eucast_rules_file$reference.rule %like% "ampc"), "this_value"][1], "|", fixed = TRUE))), quotes = "*")`.
 #' @param ... column name of an antibiotic, see section *Antibiotics* below
 #' @param ab any (vector of) text that can be coerced to a valid antibiotic code with [as.ab()]
 #' @param administration route of administration, either `r vector_or(dosage$administration)`
-#' @param only_rsi_columns a logical to indicate whether only antibiotic columns must be detected that were [transformed to class `<rsi>`]([rsi]) on beforehand (defaults to `FALSE`)
+#' @param only_rsi_columns a logical to indicate whether only antibiotic columns must be detected that were transformed to class `<rsi>` (see [as.rsi()]) on beforehand (defaults to `FALSE`)
 #' @inheritParams first_isolate
 #' @details
 #' **Note:** This function does not translate MIC values to RSI values. Use [as.rsi()] for that. \cr
@@ -101,7 +82,7 @@ format_eucast_version_nr <- function(version, markdown = TRUE) {
 #'
 #' The following antibiotics are used for the functions [eucast_rules()] and [mdro()]. These are shown below in the format 'name (`antimicrobial ID`, [ATC code](https://www.whocc.no/atc/structure_and_principles/))', sorted alphabetically:
 #'
-#' `r create_ab_documentation(c("AMC", "AMK", "AMP", "AMX", "ATM", "AVO", "AZL", "AZM", "BAM", "BPR", "CAC", "CAT", "CAZ", "CCP", "CCV", "CCX", "CDC", "CDR", "CDZ", "CEC", "CED", "CEI", "CEM", "CEP", "CFM", "CFM1", "CFP", "CFR", "CFS", "CFZ", "CHE", "CHL", "CID", "CIP", "CLI", "CLR", "CMX", "CMZ", "CND", "COL", "CPD", "CPI", "CPL", "CPM", "CPO", "CPR", "CPT", "CPX", "CRB", "CRD", "CRN", "CRO", "CSL", "CTB", "CTC", "CTF", "CTL", "CTS", "CTT", "CTX", "CTZ", "CXM", "CYC", "CZA", "CZD", "CZO", "CZP", "CZX", "DAL", "DAP", "DIR", "DIT", "DIX", "DIZ", "DKB", "DOR", "DOX", "ENX", "EPC", "ERY", "ETP", "FEP", "FLC", "FLE", "FLR1", "FOS", "FOV", "FOX", "FOX1", "FUS", "GAT", "GEM", "GEN", "GRX", "HAP", "HET", "IPM", "ISE", "JOS", "KAN", "LEX", "LIN", "LNZ", "LOM", "LOR", "LTM", "LVX", "MAN", "MCM", "MEC", "MEM", "MEV", "MEZ", "MFX", "MID", "MNO", "MTM", "NAL", "NEO", "NET", "NIT", "NOR", "NOV", "NVA", "OFX", "OLE", "ORI", "OXA", "PAZ", "PEF", "PEN", "PHN", "PIP", "PLB", "PME", "PRI", "PRL", "PRU", "PVM", "QDA", "RAM", "RFL", "RID", "RIF", "ROK", "RST", "RXT", "SAM", "SBC", "SDI", "SDM", "SIS", "SLF", "SLF1", "SLF10", "SLF11", "SLF12", "SLF13", "SLF2", "SLF3", "SLF4", "SLF5", "SLF6", "SLF7", "SLF8", "SLF9", "SLT1", "SLT2", "SLT3", "SLT4", "SLT5", "SMX", "SPI", "SPX", "STR", "STR1", "SUD", "SUT", "SXT", "SZO", "TAL", "TCC", "TCM", "TCY", "TEC", "TEM", "TGC", "THA", "TIC", "TIO", "TLT", "TLV", "TMP", "TMX", "TOB", "TRL", "TVA", "TZD", "TZP", "VAN"))`
+#' `r create_ab_documentation(c("AMC", "AMK", "AMP", "AMX", "APL", "APX", "ATM", "AVB", "AVO", "AZD", "AZL", "AZM", "BAM", "BPR", "CAC", "CAT", "CAZ", "CCP", "CCV", "CCX", "CDC", "CDR", "CDZ", "CEC", "CED", "CEI", "CEM", "CEP", "CFM", "CFM1", "CFP", "CFR", "CFS", "CFZ", "CHE", "CHL", "CIC", "CID", "CIP", "CLI", "CLM", "CLO", "CLR", "CMX", "CMZ", "CND", "COL", "CPD", "CPI", "CPL", "CPM", "CPO", "CPR", "CPT", "CPX", "CRB", "CRD", "CRN", "CRO", "CSL", "CTB", "CTC", "CTF", "CTL", "CTS", "CTT", "CTX", "CTZ", "CXM", "CYC", "CZA", "CZD", "CZO", "CZP", "CZX", "DAL", "DAP", "DIC", "DIR", "DIT", "DIX", "DIZ", "DKB", "DOR", "DOX", "ENX", "EPC", "ERY", "ETP", "FEP", "FLC", "FLE", "FLR1", "FOS", "FOV", "FOX", "FOX1", "FUS", "GAT", "GEM", "GEN", "GRX", "HAP", "HET", "IPM", "ISE", "JOS", "KAN", "LEN", "LEX", "LIN", "LNZ", "LOM", "LOR", "LTM", "LVX", "MAN", "MCM", "MEC", "MEM", "MET", "MEV", "MEZ", "MFX", "MID", "MNO", "MTM", "NAC", "NAF", "NAL", "NEO", "NET", "NIT", "NOR", "NOV", "NVA", "OFX", "OLE", "ORI", "OXA", "PAZ", "PEF", "PEN", "PHE", "PHN", "PIP", "PLB", "PME", "PNM", "PRC", "PRI", "PRL", "PRP", "PRU", "PVM", "QDA", "RAM", "RFL", "RID", "RIF", "ROK", "RST", "RXT", "SAM", "SBC", "SDI", "SDM", "SIS", "SLF", "SLF1", "SLF10", "SLF11", "SLF12", "SLF13", "SLF2", "SLF3", "SLF4", "SLF5", "SLF6", "SLF7", "SLF8", "SLF9", "SLT1", "SLT2", "SLT3", "SLT4", "SLT5", "SLT6", "SMX", "SPI", "SPX", "SRX", "STR", "STR1", "SUD", "SUL", "SUT", "SXT", "SZO", "TAL", "TAZ", "TCC", "TCM", "TCY", "TEC", "TEM", "TGC", "THA", "TIC", "TIO", "TLT", "TLV", "TMP", "TMX", "TOB", "TRL", "TVA", "TZD", "TZP", "VAN"))`
 #' @aliases EUCAST
 #' @rdname eucast_rules
 #' @export
@@ -176,7 +157,7 @@ eucast_rules <- function(x,
  meet_criteria(verbose, allow_class = "logical", has_length = 1)
  meet_criteria(version_breakpoints, allow_class = c("numeric", "integer"), has_length = 1, is_in = as.double(names(EUCAST_VERSION_BREAKPOINTS)))
  meet_criteria(version_expertrules, allow_class = c("numeric", "integer"), has_length = 1, is_in = as.double(names(EUCAST_VERSION_EXPERT_RULES)))
-  meet_criteria(ampc_cephalosporin_resistance, has_length = 1, allow_NA = TRUE, allow_NULL = TRUE, is_in = c("R", "S", "I"))
+  meet_criteria(ampc_cephalosporin_resistance, allow_class = c("logical", "character", "rsi"), has_length = 1, allow_NA = TRUE, allow_NULL = TRUE)
  meet_criteria(only_rsi_columns, allow_class = "logical", has_length = 1)
  
  x_deparsed <- deparse(substitute(x))
@@ -287,8 +268,12 @@ eucast_rules <- function(x,
  AMK <- cols_ab["AMK"]
  AMP <- cols_ab["AMP"]
  AMX <- cols_ab["AMX"]
+  APL <- cols_ab["APL"]
+  APX <- cols_ab["APX"]
  ATM <- cols_ab["ATM"]
+  AVB <- cols_ab["AVB"]
  AVO <- cols_ab["AVO"]
+  AZD <- cols_ab["AZD"]
  AZL <- cols_ab["AZL"]
  AZM <- cols_ab["AZM"]
  BAM <- cols_ab["BAM"]
@@ -315,9 +300,12 @@ eucast_rules <- function(x,
  CFZ <- cols_ab["CFZ"]
  CHE <- cols_ab["CHE"]
  CHL <- cols_ab["CHL"]
+  CIC <- cols_ab["CIC"]
  CID <- cols_ab["CID"]
  CIP <- cols_ab["CIP"]
  CLI <- cols_ab["CLI"]
+  CLM <- cols_ab["CLM"]
+  CLO <- cols_ab["CLO"]
  CLR <- cols_ab["CLR"]
  CMX <- cols_ab["CMX"]
  CMZ <- cols_ab["CMZ"]
@@ -353,6 +341,7 @@ eucast_rules <- function(x,
  CZX <- cols_ab["CZX"]
  DAL <- cols_ab["DAL"]
  DAP <- cols_ab["DAP"]
+  DIC <- cols_ab["DIC"]
  DIR <- cols_ab["DIR"]
  DIT <- cols_ab["DIT"]
  DIX <- cols_ab["DIX"]
@@ -383,6 +372,7 @@ eucast_rules <- function(x,
  ISE <- cols_ab["ISE"]
  JOS <- cols_ab["JOS"]
  KAN <- cols_ab["KAN"]
+  LEN <- cols_ab["LEN"]
  LEX <- cols_ab["LEX"]
  LIN <- cols_ab["LIN"]
  LNZ <- cols_ab["LNZ"]
@@ -394,12 +384,15 @@ eucast_rules <- function(x,
  MCM <- cols_ab["MCM"]
  MEC <- cols_ab["MEC"]
  MEM <- cols_ab["MEM"]
+  MET <- cols_ab["MET"]
  MEV <- cols_ab["MEV"]
  MEZ <- cols_ab["MEZ"]
  MFX <- cols_ab["MFX"]
  MID <- cols_ab["MID"]
  MNO <- cols_ab["MNO"]
  MTM <- cols_ab["MTM"]
+  NAC <- cols_ab["NAC"]
+  NAF <- cols_ab["NAF"]
  NAL <- cols_ab["NAL"]
  NEO <- cols_ab["NEO"]
  NET <- cols_ab["NET"]
@@ -414,12 +407,16 @@ eucast_rules <- function(x,
  PAZ <- cols_ab["PAZ"]
  PEF <- cols_ab["PEF"]
  PEN <- cols_ab["PEN"]
+  PHE <- cols_ab["PHE"]
  PHN <- cols_ab["PHN"]
  PIP <- cols_ab["PIP"]
  PLB <- cols_ab["PLB"]
  PME <- cols_ab["PME"]
+  PNM <- cols_ab["PNM"]
+  PRC <- cols_ab["PRC"]
  PRI <- cols_ab["PRI"]
  PRL <- cols_ab["PRL"]
+  PRP <- cols_ab["PRP"]
  PRU <- cols_ab["PRU"]
  PVM <- cols_ab["PVM"]
  QDA <- cols_ab["QDA"]
@@ -454,16 +451,20 @@ eucast_rules <- function(x,
  SLT3 <- cols_ab["SLT3"]
  SLT4 <- cols_ab["SLT4"]
  SLT5 <- cols_ab["SLT5"]
+  SLT6 <- cols_ab["SLT6"]
  SMX <- cols_ab["SMX"]
  SPI <- cols_ab["SPI"]
  SPX <- cols_ab["SPX"]
+  SRX <- cols_ab["SRX"]
  STR <- cols_ab["STR"]
  STR1 <- cols_ab["STR1"]
  SUD <- cols_ab["SUD"]
+  SUL <- cols_ab["SUL"]
  SUT <- cols_ab["SUT"]
  SXT <- cols_ab["SXT"]
  SZO <- cols_ab["SZO"]
  TAL <- cols_ab["TAL"]
+  TAZ <- cols_ab["TAZ"]
  TCC <- cols_ab["TCC"]
  TCM <- cols_ab["TCM"]
  TCY <- cols_ab["TCY"]
@@ -765,10 +766,14 @@ eucast_rules <- function(x,
                                (reference.rule_group %like% "expert" & reference.version == version_expertrules))
  }
  # filter out AmpC de-repressed cephalosporin-resistant mutants ----
-  if (is.null(ampc_cephalosporin_resistance)) {
+  # cefotaxime, ceftriaxone, ceftazidime
+  if (is.null(ampc_cephalosporin_resistance) || isFALSE(ampc_cephalosporin_resistance)) {
    eucast_rules_df <- subset(eucast_rules_df,
                              !reference.rule %like% "ampc")
  } else {
+    if (isTRUE(ampc_cephalosporin_resistance)) {
+      ampc_cephalosporin_resistance <- "R"
+    }
    eucast_rules_df[which(eucast_rules_df$reference.rule %like% "ampc"), "to_value"] <- as.character(ampc_cephalosporin_resistance)
  }
  
--- a/R/filter_ab_class.R
+++ b/R/filter_ab_class.R
@@ -31,7 +31,7 @@
 #' @param ab_class an antimicrobial class, like `"carbapenems"`. The columns `group`, `atc_group1` and `atc_group2` of the [antibiotics] data set will be searched (case-insensitive) for this value.
 #' @param result an antibiotic result: S, I or R (or a combination of more of them)
 #' @param scope the scope to check which variables to check, can be `"any"` (default) or `"all"`
-#' @param only_rsi_columns a logical to indicate whether only columns must be included that were [transformed to class `<rsi>`]([rsi]) on beforehand (defaults to `FALSE`)
+#' @param only_rsi_columns a logical to indicate whether only columns must be included that were transformed to class `<rsi>` (see [as.rsi()]) on beforehand (defaults to `FALSE`)
 #' @param ... arguments passed on to [filter_ab_class()]
 #' @details All columns of `x` will be searched for known antibiotic names, abbreviations, brand names and codes (ATC, EARS-Net, WHO, etc.). This means that a filter function like e.g. [filter_aminoglycosides()] will include column names like 'gen', 'genta', 'J01GB03', 'tobra', 'Tobracin', etc.
 #' @rdname filter_ab_class
--- a/R/globals.R
+++ b/R/globals.R
@@ -23,6 +23,40 @@
 # how to conduct AMR data analysis: https://msberends.github.io/AMR/   #
 # ==================================================================== #

+# add new version numbers here, and add the rules themselves to "data-raw/eucast_rules.tsv" and rsi_translation
+# (sourcing "data-raw/_internals.R" will process the TSV file)
+EUCAST_VERSION_BREAKPOINTS <- list("11.0" = list(version_txt = "v11.0",
+                                                 year = 2021, 
+                                                 title = "'EUCAST Clinical Breakpoint Tables'",
+                                                 url = "https://www.eucast.org/clinical_breakpoints/"),
+                                   "10.0" = list(version_txt = "v10.0",
+                                                 year = 2020, 
+                                                 title = "'EUCAST Clinical Breakpoint Tables'",
+                                                 url = "https://www.eucast.org/ast_of_bacteria/previous_versions_of_documents/"))
+EUCAST_VERSION_EXPERT_RULES <- list("3.1" = list(version_txt = "v3.1",
+                                                 year = 2016, 
+                                                 title = "'EUCAST Expert Rules, Intrinsic Resistance and Exceptional Phenotypes'",
+                                                 url = "https://www.eucast.org/expert_rules_and_intrinsic_resistance/"),
+                                    "3.2" = list(version_txt = "v3.2",
+                                                 year = 2020, 
+                                                 title = "'EUCAST Expert Rules' and 'EUCAST Intrinsic Resistance and Unusual Phenotypes'",
+                                                 url = "https://www.eucast.org/expert_rules_and_intrinsic_resistance/"))
+
+SNOMED_VERSION <- list(title = "Public Health Information Network Vocabulary Access and Distribution System (PHIN VADS)",
+                       current_source = "US Edition of SNOMED CT from 1 September 2020",
+                       current_version = 12,
+                       current_oid = "2.16.840.1.114222.4.11.1009",
+                       value_set_name = "Microorganism",
+                       url = "https://phinvads.cdc.gov/vads/ViewValueSet.action?oid=2.16.840.1.114222.4.11.1009")
+
+CATALOGUE_OF_LIFE <- list(
+  year = 2019,
+  version = "Catalogue of Life: {year} Annual Checklist",
+  url_CoL = "http://www.catalogueoflife.org/col/",
+  url_LPSN = "https://lpsn.dsmz.de",
+  yearmonth_LPSN = "March 2021"
+)
+
 globalVariables(c(".rowid",
                  "ab",
                  "ab_txt",
--- a/R/guess_ab_col.R
+++ b/R/guess_ab_col.R
@@ -30,7 +30,7 @@
 #' @param x a [data.frame]
 #' @param search_string a text to search `x` for, will be checked with [as.ab()] if this value is not a column in `x`
 #' @param verbose a logical to indicate whether additional info should be printed
-#' @param only_rsi_columns a logical to indicate whether only antibiotic columns must be detected that were [transformed to class `<rsi>`]([rsi]) on beforehand (defaults to `FALSE`)
+#' @param only_rsi_columns a logical to indicate whether only antibiotic columns must be detected that were transformed to class `<rsi>` (see [as.rsi()]) on beforehand (defaults to `FALSE`)
 #' @details You can look for an antibiotic (trade) name or abbreviation and it will search `x` and the [antibiotics] data set for any column containing a name or code of that antibiotic. **Longer columns names take precedence over shorter column names.**
 #' @return A column name of `x`, or `NULL` when no result is found.
 #' @export
--- a/R/lifecycle.R
+++ b/R/lifecycle.R
@@ -27,10 +27,10 @@
 # NOTE TO SELF: could also have done this with the 'lifecycle' package, but why add a package dependency for such an easy job??
 ###############

-#' Lifecycles of Functions in the `amr` Package
+#' Lifecycles of Functions in the `AMR` Package
 #' @name lifecycle
 #' @rdname lifecycle
-#' @description Functions in this `AMR` package are categorised using [the lifecycle circle of the Tidyverse as found on www.tidyverse.org/lifecycle](https://www.Tidyverse.org/lifecycle).
+#' @description Functions in this `AMR` package are categorised using [the lifecycle circle of the Tidyverse as found on www.tidyverse.org/lifecycle](https://lifecycle.r-lib.org/articles/stages.html).
 #' 
 #' \if{html}{\figure{lifecycle_tidyverse.svg}{options: height=200px style=margin-bottom:5px} \cr}
 #' This page contains a section for every lifecycle (with text borrowed from the aforementioned Tidyverse website), so they can be used in the manual pages of the functions. 
--- a/R/mo.R
+++ b/R/mo.R
@@ -106,7 +106,9 @@
 #' 2. Becker K *et al.* **Implications of identifying the recently defined members of the *S. aureus* complex, *S. argenteus* and *S. schweitzeri*: A position paper of members of the ESCMID Study Group for staphylococci and Staphylococcal Diseases (ESGS).** 2019. Clin Microbiol Infect; \doi{10.1016/j.cmi.2019.02.028}
 #' 3. Becker K *et al.* **Emergence of coagulase-negative staphylococci** 2020. Expert Rev Anti Infect Ther. 18(4):349-366; \doi{10.1080/14787210.2020.1730813}
 #' 4. Lancefield RC **A serological differentiation of human and other groups of hemolytic streptococci**. 1933. J Exp Med. 57(4): 571–95; \doi{10.1084/jem.57.4.571}
-#' 5. Catalogue of Life: Annual Checklist (public online taxonomic database), <http://www.catalogueoflife.org> (check included annual version with [catalogue_of_life_version()]).
+#' 5. `r gsub("{year}", CATALOGUE_OF_LIFE$year, CATALOGUE_OF_LIFE$version, fixed = TRUE)`, <http://www.catalogueoflife.org>
+#' 6. List of Prokaryotic names with Standing in Nomenclature (`r CATALOGUE_OF_LIFE$yearmonth_LPSN`), \doi{10.1099/ijsem.0.004332}
+#' 7. `r SNOMED_VERSION$current_source`, retrieved from the `r SNOMED_VERSION$title`, OID `r SNOMED_VERSION$current_oid`, version `r SNOMED_VERSION$current_version`; url: <`r SNOMED_VERSION$url`>
 #' @export
 #' @return A [character] [vector] with additional class [`mo`]
 #' @seealso [microorganisms] for the [data.frame] that is being used to determine ID's.
--- a/R/mo_matching_score.R
+++ b/R/mo_matching_score.R
@@ -44,7 +44,7 @@
 #' * \ifelse{html}{\out{<i>p<sub>n</sub></i> is the human pathogenic prevalence group of <i>n</i>, as described below;}}{p_n is the human pathogenic prevalence group of \eqn{n}, as described below;}
 #' * \ifelse{html}{\out{<i>k<sub>n</sub></i> is the taxonomic kingdom of <i>n</i>, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.}}{l_n is the taxonomic kingdom of \eqn{n}, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.}
 #' 
-#' The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. **Group 1** (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is *Enterococcus*, *Staphylococcus* or *Streptococcus*. This group consequently contains all common Gram-negative bacteria, such as *Pseudomonas* and *Legionella* and all species within the order Enterobacterales. **Group 2** consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is *Absidia*, *Acremonium*, *Actinotignum*, *Alternaria*, *Anaerosalibacter*, *Apophysomyces*, *Arachnia*, *Aspergillus*, *Aureobacterium*, *Aureobasidium*, *Bacteroides*, *Basidiobolus*, *Beauveria*, *Blastocystis*, *Branhamella*, *Calymmatobacterium*, *Candida*, *Capnocytophaga*, *Catabacter*, *Chaetomium*, *Chryseobacterium*, *Chryseomonas*, *Chrysonilia*, *Cladophialophora*, *Cladosporium*, *Conidiobolus*, *Cryptococcus*, *Curvularia*, *Exophiala*, *Exserohilum*, *Flavobacterium*, *Fonsecaea*, *Fusarium*, *Fusobacterium*, *Hendersonula*, *Hypomyces*, *Koserella*, *Lelliottia*, *Leptosphaeria*, *Leptotrichia*, *Malassezia*, *Malbranchea*, *Mortierella*, *Mucor*, *Mycocentrospora*, *Mycoplasma*, *Nectria*, *Ochroconis*, *Oidiodendron*, *Phoma*, *Piedraia*, *Pithomyces*, *Pityrosporum*, *Prevotella*,\\*Pseudallescheria*, *Rhizomucor*, *Rhizopus*, *Rhodotorula*, *Scolecobasidium*, *Scopulariopsis*, *Scytalidium*,*Sporobolomyces*, *Stachybotrys*, *Stomatococcus*, *Treponema*, *Trichoderma*, *Trichophyton*, *Trichosporon*, *Tritirachium* or *Ureaplasma*. **Group 3** consists of all other microorganisms.
+#' The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. **Group 1** (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is *Enterococcus*, *Staphylococcus* or *Streptococcus*. This group consequently contains all common Gram-negative bacteria, such as *Pseudomonas* and *Legionella* and all species within the order Enterobacterales. **Group 2** consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is *Absidia*, *Acremonium*, *Actinotignum*, *Alternaria*, *Anaerosalibacter*, *Apophysomyces*, *Arachnia*, *Aspergillus*, *Aureobacterium*, *Aureobasidium*, *Bacteroides*, *Basidiobolus*, *Beauveria*, *Blastocystis*, *Branhamella*, *Calymmatobacterium*, *Candida*, *Capnocytophaga*, *Catabacter*, *Chaetomium*, *Chryseobacterium*, *Chryseomonas*, *Chrysonilia*, *Cladophialophora*, *Cladosporium*, *Conidiobolus*, *Cryptococcus*, *Curvularia*, *Exophiala*, *Exserohilum*, *Flavobacterium*, *Fonsecaea*, *Fusarium*, *Fusobacterium*, *Hendersonula*, *Hypomyces*, *Koserella*, *Lelliottia*, *Leptosphaeria*, *Leptotrichia*, *Malassezia*, *Malbranchea*, *Mortierella*, *Mucor*, *Mycocentrospora*, *Mycoplasma*, *Nectria*, *Ochroconis*, *Oidiodendron*, *Phoma*, *Piedraia*, *Pithomyces*, *Pityrosporum*, *Prevotella*, *Pseudallescheria*, *Rhizomucor*, *Rhizopus*, *Rhodotorula*, *Scolecobasidium*, *Scopulariopsis*, *Scytalidium*,*Sporobolomyces*, *Stachybotrys*, *Stomatococcus*, *Treponema*, *Trichoderma*, *Trichophyton*, *Trichosporon*, *Tritirachium* or *Ureaplasma*. **Group 3** consists of all other microorganisms.
 #' 
 #' All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., `"E. coli"` will return the microbial ID of *Escherichia coli* (\eqn{m = `r round(mo_matching_score("E. coli", "Escherichia coli"), 3)`}, a highly prevalent microorganism found in humans) and not *Entamoeba coli* (\eqn{m = `r round(mo_matching_score("E. coli", "Entamoeba coli"), 3)`}, a less prevalent microorganism in humans), although the latter would alphabetically come first. 
 #' @export
--- a/R/mo_property.R
+++ b/R/mo_property.R
@@ -51,6 +51,8 @@
 #' All output [will be translated][translate] where possible.
 #'
 #' The function [mo_url()] will return the direct URL to the online database entry, which also shows the scientific reference of the concerned species.
+#' 
+#' SNOMED codes - [mo_snomed()] - are from the `r SNOMED_VERSION$current_source`. See the [microorganisms] data set for more info.
 #' @inheritSection mo_matching_score Matching Score for Microorganisms
 #' @inheritSection catalogue_of_life Catalogue of Life
 #' @inheritSection as.mo Source
@@ -60,7 +62,7 @@
 #' - An [integer] in case of [mo_year()]
 #' - A [list] in case of [mo_taxonomy()] and [mo_info()]
 #' - A named [character] in case of [mo_url()]
-#' - A [double] in case of [mo_snomed()]
+#' - A [numeric] in case of [mo_snomed()]
 #' - A [character] in all other cases
 #' @export
 #' @seealso [microorganisms]
@@ -161,7 +163,8 @@
 #' 
 #' # get a list with the complete taxonomy (from kingdom to subspecies)
 #' mo_taxonomy("E. coli")
-#' # get a list with the taxonomy, the authors, Gram-stain and URL to the online database
+#' # get a list with the taxonomy, the authors, Gram-stain,
+#' #   SNOMED codes, and URL to the online database
 #' mo_info("E. coli")
 #' }
 mo_name <- function(x, language = get_locale(), ...) {
@@ -629,7 +632,8 @@ mo_info <- function(x, language = get_locale(),  ...) {
      list(synonyms = mo_synonyms(y),
           gramstain = mo_gramstain(y, language = language),
           url = unname(mo_url(y, open = FALSE)),
-           ref = mo_ref(y))))
+           ref = mo_ref(y),
+           snomed = unlist(mo_snomed(y)))))
  if (length(info) > 1) {
    names(info) <- mo_name(x)
    result <- info
@@ -659,10 +663,10 @@ mo_url <- function(x, open = FALSE, language = get_locale(), ...) {
  df <- data.frame(mo, stringsAsFactors = FALSE) %pm>%
    pm_left_join(pm_select(microorganisms, mo, source, species_id), by = "mo")
  df$url <- ifelse(df$source == "CoL",
-                   paste0(catalogue_of_life$url_CoL, "details/species/id/", df$species_id, "/"),
+                   paste0(CATALOGUE_OF_LIFE$url_CoL, "details/species/id/", df$species_id, "/"),
                   NA_character_)
  u <- df$url
-  u[mo_kingdom(mo) == "Bacteria"] <- paste0(catalogue_of_life$url_LPSN, "/species/", gsub(" ", "-", tolower(mo_names), fixed = TRUE))
+  u[mo_kingdom(mo) == "Bacteria"] <- paste0(CATALOGUE_OF_LIFE$url_LPSN, "/species/", gsub(" ", "-", tolower(mo_names), fixed = TRUE))
  u[mo_kingdom(mo) == "Bacteria" & mo_rank(mo) == "genus"] <- gsub("/species/",
                                                                   "/genus/",
                                                                   u[mo_kingdom(mo) == "Bacteria" & mo_rank(mo) == "genus"],
--- a/R/sysdata.rda
+++ b/R/sysdata.rda