1
0
mirror of https://github.com/msberends/AMR.git synced 2025-07-09 04:02:19 +02:00

(v1.2.0.9035) as.mo() speed improvement

This commit is contained in:
2020-07-22 10:24:23 +02:00
parent 6ab468362d
commit 09fba38ea6
37 changed files with 174 additions and 441 deletions

View File

@ -94,6 +94,7 @@
#' - 11 entries of *Streptococcus* (beta-haemolytic: groups A, B, C, D, F, G, H, K and unspecified; other: viridans, milleri)
#' - 2 entries of *Staphylococcus* (coagulase-negative (CoNS) and coagulase-positive (CoPS))
#' - 3 entries of *Trichomonas* (*Trichomonas vaginalis*, and its family and genus)
#' - 1 entry of *Candida* (*Candida krusei*), that is not (yet) in the Catalogue of Life
#' - 1 entry of *Blastocystis* (*Blastocystis hominis*), although it officially does not exist (Noel *et al.* 2005, PMID 15634993)
#' - 5 other 'undefined' entries (unknown, unknown Gram negatives, unknown Gram positives, unknown yeast and unknown fungus)
#' - 6 families under the Enterobacterales order, according to Adeolu *et al.* (2016, PMID 27620848), that are not (yet) in the Catalogue of Life
@ -109,13 +110,14 @@
#' * <https://github.com/msberends/AMR/raw/master/data/microorganisms.rda>
#' @section About the records from DSMZ (see source):
#' Names of prokaryotes are defined as being validly published by the International Code of Nomenclature of Bacteria. Validly published are all names which are included in the Approved Lists of Bacterial Names and the names subsequently published in the International Journal of Systematic Bacteriology (IJSB) and, from January 2000, in the International Journal of Systematic and Evolutionary Microbiology (IJSEM) as original articles or in the validation lists.
#'
#' From: <https://www.dsmz.de/services/online-tools/prokaryotic-nomenclature-up-to-date/complete-list-readme>
#' *(from <https://www.dsmz.de/services/online-tools/prokaryotic-nomenclature-up-to-date/complete-list-readme>)*
#'
#' In February 2020, the DSMZ records were merged with the List of Prokaryotic names with Standing in Nomenclature (LPSN).
#' @source Catalogue of Life: Annual Checklist (public online taxonomic database), <http://www.catalogueoflife.org> (check included annual version with [catalogue_of_life_version()]).
#'
#' Parte, A.C. (2018). LPSN — List of Prokaryotic names with Standing in Nomenclature (bacterio.net), 20 years on. International Journal of Systematic and Evolutionary Microbiology, 68, 1825-1829; doi: 10.1099/ijsem.0.002786
#'
#' Leibniz Institute DSMZ-German Collection of Microorganisms and Cell Cultures, Germany, Prokaryotic Nomenclature Up-to-Date, <https://www.dsmz.de/services/online-tools/prokaryotic-nomenclature-up-to-date> (check included version with [catalogue_of_life_version()]).
#' Leibniz Institute DSMZ-German Collection of Microorganisms and Cell Cultures, Germany, Prokaryotic Nomenclature Up-to-Date, <https://www.dsmz.de/services/online-tools/prokaryotic-nomenclature-up-to-date> and <https://lpsn.dsmz.de> (check included version with [catalogue_of_life_version()]).
#' @inheritSection AMR Read more on our website!
#' @seealso [as.mo()], [mo_property()], [microorganisms.codes]
"microorganisms"
@ -231,6 +233,6 @@ catalogue_of_life <- list(
#' - `breakpoint_S`\cr Lowest MIC value or highest number of millimetres that leads to "S"
#' - `breakpoint_R`\cr Highest MIC value or lowest number of millimetres that leads to "R"
#' - `uti`\cr A logical value (`TRUE`/`FALSE`) to indicate whether the rule applies to a urinary tract infection (UTI)
#' @details The repository of this `AMR` package contains a file comprising this exact data set: <https://github.com/msberends/AMR/blob/master/data-raw/rsi_translation.txt>. This file **allows for machine reading EUCAST and CLSI guidelines**, which is almost impossible with the Excel and PDF files distributed by EUCAST and CLSI. This file is updated automatically.
#' @details The repository of this `AMR` package contains a file comprising this exact data set: <https://github.com/msberends/AMR/blob/master/data-raw/rsi_translation.txt>. This file **allows for machine reading EUCAST and CLSI guidelines**, which is almost impossible with the Excel and PDF files distributed by EUCAST and CLSI. The file is updated automatically.
#' @inheritSection AMR Read more on our website!
"rsi_translation"

View File

@ -174,10 +174,6 @@ first_isolate <- function(x,
col_date <- search_type_in_df(x = x, type = "date")
stop_if(is.null(col_date), "`col_date` must be set")
}
# convert to Date
dates <- as.Date(x[, col_date, drop = TRUE])
dates[is.na(dates)] <- as.Date("1970-01-01")
x[, col_date] <- dates
# -- patient id
if (is.null(col_patient_id)) {
@ -223,12 +219,17 @@ first_isolate <- function(x,
check_columns_existance(col_icu)
check_columns_existance(col_keyantibiotics)
# convert dates to Date
dates <- as.Date(x[, col_date, drop = TRUE])
dates[is.na(dates)] <- as.Date("1970-01-01")
x[, col_date] <- dates
# create original row index
x$newvar_row_index <- seq_len(nrow(x))
x$newvar_mo <- x %>% pull(col_mo) %>% as.mo()
x$newvar_mo <- x[, col_mo, drop = TRUE]
x$newvar_genus_species <- paste(mo_genus(x$newvar_mo), mo_species(x$newvar_mo))
x$newvar_date <- x %>% pull(col_date)
x$newvar_patient_id <- x %>% pull(col_patient_id)
x$newvar_date <- x[, col_date, drop = TRUE]
x$newvar_patient_id <- x[, col_patient_id, drop = TRUE]
if (is.null(col_testcode)) {
testcodes_exclude <- NULL
@ -317,10 +318,10 @@ first_isolate <- function(x,
}
# Analysis of first isolate ----
x$other_pat_or_mo <- if_else(x$newvar_patient_id == lag(x$newvar_patient_id) &
x$newvar_genus_species == lag(x$newvar_genus_species),
FALSE,
TRUE)
x$other_pat_or_mo <- ifelse(x$newvar_patient_id == lag(x$newvar_patient_id) &
x$newvar_genus_species == lag(x$newvar_genus_species),
FALSE,
TRUE)
x$episode_group <- paste(x$newvar_patient_id, x$newvar_genus_species)
x$more_than_episode_ago <- unlist(lapply(unique(x$episode_group),
function(g,

View File

@ -19,100 +19,47 @@
# Visit our website for more info: https://msberends.github.io/AMR. #
# ==================================================================== #
globalVariables(c(".",
"..property",
"ab",
globalVariables(c("ab",
"ab_txt",
"abbreviations",
"angle",
"antibiotic",
"antibiotics",
"atc_group1",
"atc_group2",
"CNS_CPS",
"code",
"col_id",
"count",
"count.x",
"data",
"date_lab",
"diff.percent",
"First name",
"first_isolate_row_index",
"fullname",
"fullname_lower",
"g_species",
"genus",
"gr",
"gramstain",
"group",
"hjust",
"index",
"input",
"interpretation",
"isolates",
"item",
"key_ab",
"key_ab_lag",
"key_ab_other",
"kingdom",
"kingdom_index",
"lang",
"Last name",
"lookup",
"mdr",
"MDRO",
"median",
"microorganisms",
"microorganisms.codes",
"microorganisms.old",
"missing_names",
"mo",
"mo_new",
"mo_old",
"mono_count",
"more_than_episode_ago",
"name",
"new",
"newvar_date",
"newvar_genus_species",
"newvar_mo",
"newvar_patient_id",
"newvar_row_index",
"newvar_row_index_sorted",
"observations",
"observed",
"old",
"old_name",
"other_pat_or_mo",
"package_version",
"patient_id",
"pattern",
"plural",
"prevalence",
"R",
"real_first_isolate",
"ref",
"rsi_translation",
"rule_group",
"rule_name",
"S",
"se_max",
"se_min",
"second",
"Sex",
"species",
"species_id",
"subspecies",
"synonyms",
"total",
"txt",
"uncertainty_level",
"value",
"varname",
"x",
"xdr",
"xvar",
"y",
"year",
"yvar"))

View File

@ -40,7 +40,7 @@
#' # [1] "tetr"
#'
#' guess_ab_col(df, "J01AA07", verbose = TRUE)
#' # Note: Using column `tetr` as input for "J01AA07".
#' # NOTE: Using column `tetr` as input for `J01AA07` (tetracycline).
#' # [1] "tetr"
#'
#' # WHONET codes

View File

@ -968,12 +968,12 @@ mdro <- function(x,
}
x$mono_count <- 0
x[drug_is_R(INH), "mono_count"] <- x[drug_is_R(INH), "mono_count"] + 1
x[drug_is_R(RIF), "mono_count"] <- x[drug_is_R(RIF), "mono_count"] + 1
x[drug_is_R(ETH), "mono_count"] <- x[drug_is_R(ETH), "mono_count"] + 1
x[drug_is_R(PZA), "mono_count"] <- x[drug_is_R(PZA), "mono_count"] + 1
x[drug_is_R(RIB), "mono_count"] <- x[drug_is_R(RIB), "mono_count"] + 1
x[drug_is_R(RFP), "mono_count"] <- x[drug_is_R(RFP), "mono_count"] + 1
x[drug_is_R(INH), "mono_count"] <- x[drug_is_R(INH), "mono_count", drop = TRUE] + 1
x[drug_is_R(RIF), "mono_count"] <- x[drug_is_R(RIF), "mono_count", drop = TRUE] + 1
x[drug_is_R(ETH), "mono_count"] <- x[drug_is_R(ETH), "mono_count", drop = TRUE] + 1
x[drug_is_R(PZA), "mono_count"] <- x[drug_is_R(PZA), "mono_count", drop = TRUE] + 1
x[drug_is_R(RIB), "mono_count"] <- x[drug_is_R(RIB), "mono_count", drop = TRUE] + 1
x[drug_is_R(RFP), "mono_count"] <- x[drug_is_R(RFP), "mono_count", drop = TRUE] + 1
x$mono <- x$mono_count > 0
x$poly <- x$mono_count > 1 & drug_is_not_R(RIF) & drug_is_not_R(INH)

91
R/mo.R
View File

@ -55,7 +55,7 @@
#' C (Chromista), F (Fungi), P (Protozoa)
#' ```
#'
#' Values that cannot be coered will be considered 'unknown' and will get the MO code `UNKNOWN`.
#' Values that cannot be coerced will be considered 'unknown' and will get the MO code `UNKNOWN`.
#'
#' Use the [`mo_*`][mo_property()] functions to get properties based on the returned code, see Examples.
#'
@ -77,27 +77,27 @@
#' - Uncertainty level 2: allow all of level 1, strip values between brackets, inverse the words of the input, strip off text elements from the end keeping at least two elements;
#' - Uncertainty level 3: allow all of level 1 and 2, strip off text elements from the end, allow any part of a taxonomic name.
#'
#' This leads to e.g.:
#' The level of uncertainty can be set using the argument `allow_uncertain`. The default is `allow_uncertain = TRUE`, which is equal to uncertainty level 2. Using `allow_uncertain = FALSE` is equal to uncertainty level 0 and will skip all rules. You can also use e.g. `as.mo(..., allow_uncertain = 1)` to only allow up to level 1 uncertainty.
#'
#' With the default setting (`allow_uncertain = TRUE`, level 2), below examples will lead to valid results:
#' - `"Streptococcus group B (known as S. agalactiae)"`. The text between brackets will be removed and a warning will be thrown that the result *Streptococcus group B* (``r as.mo("Streptococcus group B")``) needs review.
#' - `"S. aureus - please mind: MRSA"`. The last word will be stripped, after which the function will try to find a match. If it does not, the second last word will be stripped, etc. Again, a warning will be thrown that the result *Staphylococcus aureus* (``r as.mo("Staphylococcus aureus")``) needs review.
#' - `"Fluoroquinolone-resistant Neisseria gonorrhoeae"`. The first word will be stripped, after which the function will try to find a match. A warning will be thrown that the result *Neisseria gonorrhoeae* (``r as.mo("Neisseria gonorrhoeae")``) needs review.
#'
#' The level of uncertainty can be set using the argument `allow_uncertain`. The default is `allow_uncertain = TRUE`, which is equal to uncertainty level 2. Using `allow_uncertain = FALSE` is equal to uncertainty level 0 and will skip all rules. You can also use e.g. `as.mo(..., allow_uncertain = 1)` to only allow up to level 1 uncertainty.
#'
#' There are three helper functions that can be run after then [as.mo()] function:
#' - Use [mo_uncertainties()] to get a [`data.frame`] with all values that were coerced to a valid value, but with uncertainty. The output contains a score, that is calculated as \eqn{(n - 0.5 * L) / n}, where *n* is the number of characters of the returned full name of the microorganism, and *L* is the [Levenshtein distance](https://en.wikipedia.org/wiki/Levenshtein_distance) between that full name and the user input.
#' - Use [mo_failures()] to get a [`vector`] with all values that could not be coerced to a valid value.
#' - Use [mo_renamed()] to get a [`data.frame`] with all values that could be coerced based on an old, previously accepted taxonomic name.
#' There are three helper functions that can be run after using the [as.mo()] function:
#' - Use [mo_uncertainties()] to get a [`data.frame`] with all values that were coerced to a valid value, but with uncertainty. The output contains a score, that is calculated as \eqn{(n - 0.5 * L) / n}, where *n* is the number of characters of the full taxonomic name of the microorganism, and *L* is the [Levenshtein distance](https://en.wikipedia.org/wiki/Levenshtein_distance) between that full name and the user input.
#' - Use [mo_failures()] to get a [`character`] [`vector`] with all values that could not be coerced to a valid value.
#' - Use [mo_renamed()] to get a [`data.frame`] with all values that could be coerced based on old, previously accepted taxonomic names.
#'
#' ## Microbial prevalence of pathogens in humans
#'
#' The intelligent rules consider the prevalence of microorganisms in humans grouped into three groups, which is available as the `prevalence` columns in the [microorganisms] and [microorganisms.old] data sets. The grouping into prevalence groups 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 Enterobacteriales.
#' 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 *Klebsiella*, *Pseudomonas* and *Legionella*.
#'
#' Group 2 consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is *Aspergillus*, *Bacteroides*, *Candida*, *Capnocytophaga*, *Chryseobacterium*, *Cryptococcus*, *Elisabethkingia*, *Flavobacterium*, *Fusobacterium*, *Giardia*, *Leptotrichia*, *Mycoplasma*, *Prevotella*, *Rhodotorula*, *Treponema*, *Trichophyton* or *Ureaplasma*.
#' Group 2 consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is *Aspergillus*, *Bacteroides*, *Candida*, *Capnocytophaga*, *Chryseobacterium*, *Cryptococcus*, *Elisabethkingia*, *Flavobacterium*, *Fusobacterium*, *Giardia*, *Leptotrichia*, *Mycoplasma*, *Prevotella*, *Rhodotorula*, *Treponema*, *Trichophyton* or *Ureaplasma*. This group consequently contains all less common and rare human pathogens.
#'
#' Group 3 (least prevalent microorganisms) consists of all other microorganisms.
#' Group 3 (least prevalent microorganisms) consists of all other microorganisms. This group contains microorganisms most probably not found in humans.
#' @inheritSection catalogue_of_life Catalogue of Life
# (source as a section here, so it can be inherited by other man pages:)
#' @section Source:
@ -106,7 +106,7 @@
#' 3. Lancefield RC **A serological differentiation of human and other groups of hemolytic streptococci**. 1933. J Exp Med. 57(4): 57195. <https://dx.doi.org/10.1084/jem.57.4.571>
#' 4. Catalogue of Life: Annual Checklist (public online taxonomic database), <http://www.catalogueoflife.org> (check included annual version with [catalogue_of_life_version()]).
#' @export
#' @return A [`character`] vector with class [`mo`]
#' @return A [`character`] [`vector`] with additional class [`mo`]
#' @seealso [microorganisms] for the [`data.frame`] that is being used to determine ID's.
#'
#' The [mo_property()] functions (like [mo_genus()], [mo_gramstain()]) to get properties based on the returned code.
@ -177,7 +177,9 @@ as.mo <- function(x,
# start off with replaced language-specific non-ASCII characters with ASCII characters
x <- parse_and_convert(x)
# replace mo codes used in older package versions
x <- replace_old_mo_codes(x)
# WHONET: xxx = no growth
x[tolower(as.character(paste0(x, ""))) %in% c("", "xxx", "na", "nan")] <- NA_character_
# Laboratory systems: remove entries like "no growth" etc
@ -288,6 +290,8 @@ exec_as.mo <- function(x,
# start off with replaced language-specific non-ASCII characters with ASCII characters
x <- parse_and_convert(x)
# replace mo codes used in older package versions
x <- replace_old_mo_codes(x)
# WHONET: xxx = no growth
x[tolower(as.character(paste0(x, ""))) %in% c("", "xxx", "na", "nan")] <- NA_character_
@ -324,30 +328,6 @@ exec_as.mo <- function(x,
& !identical(x, "")
& !identical(x, "xxx")]
# conversion of old MO codes from v0.5.0 (ITIS) to later versions (Catalogue of Life)
if (any(x %like_case% "^[BFP]_[A-Z]{3,7}") & !all(x %in% microorganisms$mo)) {
leftpart <- gsub("^([BFP]_[A-Z]{3,7}).*", "\\1", x)
if (any(leftpart %in% names(mo_codes_v0.5.0))) {
old_mo_warning <- TRUE
rightpart <- gsub("^[BFP]_[A-Z]{3,7}(.*)", "\\1", x)
leftpart <- mo_codes_v0.5.0[leftpart]
x[!is.na(leftpart)] <- paste0(leftpart[!is.na(leftpart)], rightpart[!is.na(leftpart)])
}
# now check if some are still old
still_old <- x[x %in% names(mo_codes_v0.5.0)]
if (length(still_old) > 0) {
old_mo_warning <- TRUE
x[x %in% names(mo_codes_v0.5.0)] <- data.frame(old = still_old, stringsAsFactors = FALSE) %>%
left_join(data.frame(old = names(mo_codes_v0.5.0),
new = mo_codes_v0.5.0,
stringsAsFactors = FALSE), by = "old") %>%
# if they couldn't be found, replace them with the old ones again,
# so they will throw a warning in the end
mutate(new = ifelse(is.na(new), old, new)) %>%
pull(new)
}
}
# defined df to check for
if (!is.null(reference_df)) {
mo_source_isvalid(reference_df)
@ -412,15 +392,6 @@ exec_as.mo <- function(x,
# on = "mo",
# ..property][[1]]
} else if (all(x %in% microorganisms.translation$mo_old)) {
# is an old mo code, used in previous versions of this package
old_mo_warning <- TRUE
x <- data.frame(mo_old = toupper(x), stringsAsFactors = FALSE) %>%
left_join(microorganisms.translation, by = "mo_old") %>%
rename(mo = mo_new) %>%
left_join_MO_lookup(by = "mo") %>%
pull(property)
} else if (!all(x %in% microorganisms[, property])) {
strip_whitespace <- function(x, dyslexia_mode) {
@ -592,18 +563,6 @@ exec_as.mo <- function(x,
next
}
# old mo code, used in previous versions of this package ----
if (x_backup[i] %in% microorganisms.translation$mo_old) {
old_mo_warning <- TRUE
found <- lookup(mo_old == toupper(x_backup[i]), column = "mo_new", haystack = microorganisms.translation)
found <- lookup(mo == found)
if (!is.na(found)) {
# get property
x[i] <- found[1L]
next
}
}
if (x_backup[i] %like_case% "\\(unknown [a-z]+\\)" | tolower(x_backup_without_spp[i]) %in% c("other", "none", "unknown")) {
# empty and nonsense values, ignore without warning
x[i] <- lookup(mo == "UNKNOWN")
@ -1584,12 +1543,14 @@ summary.mo <- function(object, ...) {
x <- as.mo(object) # force again, could be mo from older pkg version
top <- as.data.frame(table(x), responseName = "n", stringsAsFactors = FALSE)
top_3 <- top[order(-top$n), 1][1:3]
c("Class" = "mo",
value <- c("Class" = "mo",
"<NA>" = length(x[is.na(x)]),
"Unique" = n_distinct(x[!is.na(x)]),
"#1" = top_3[1],
"#2" = top_3[2],
"#3" = top_3[3])
class(value) <- c("summaryDefault", "table")
value
}
#' @method as.data.frame mo
@ -1821,6 +1782,18 @@ parse_and_convert <- function(x) {
parsed
}
replace_old_mo_codes <- function(x) {
if (any(toupper(x) %in% microorganisms.translation$mo_old, na.rm = TRUE)) {
# get the ones that match
matched <- match(toupper(x), microorganisms.translation$mo_old)
# and their new codes
mo_new <- microorganisms.translation$mo_new[matched]
# assign on places where a match was found
x[which(!is.na(matched))] <- mo_new[which(!is.na(matched))]
}
x
}
left_join_MO_lookup <- function(x, ...) {
left_join(x = x, y = MO_lookup, ...)
}

View File

@ -437,8 +437,6 @@ mo_validate <- function(x, property, ...) {
if (property == "mo") {
return(to_class_mo(x))
} else if (property == "col_id") {
return(as.integer(x))
} else if (property == "snomed") {
return(as.double(eval(parse(text = x))))
} else {

View File

@ -550,13 +550,15 @@ summary.rsi <- function(object, ...) {
S <- sum(x == "S", na.rm = TRUE)
I <- sum(x == "I", na.rm = TRUE)
R <- sum(x == "R", na.rm = TRUE)
c(
value <- c(
"Class" = "rsi",
"%R" = paste0(percentage(R / n), " (n=", R, ")"),
"%SI" = paste0(percentage((S + I) / n), " (n=", S + I, ")"),
"- %S" = paste0(percentage(S / n), " (n=", S, ")"),
"- %I" = paste0(percentage(I / n), " (n=", I, ")")
)
class(value) <- c("summaryDefault", "table")
value
}
#' @method plot rsi

Binary file not shown.

209
R/zzz.R
View File

@ -27,10 +27,6 @@
assign(x = "MO.old_lookup",
value = create_MO.old_lookup(),
envir = asNamespace("AMR"))
assign(x = "mo_codes_v0.5.0",
value = make_trans_tbl(),
envir = asNamespace("AMR"))
}
# maybe add survey later: "https://www.surveymonkey.com/r/AMR_for_R"
@ -44,8 +40,7 @@ create_MO_lookup <- function() {
MO_lookup[which(MO_lookup$kingdom == "Protozoa"), "kingdom_index"] <- 3
MO_lookup[which(MO_lookup$kingdom == "Archaea"), "kingdom_index"] <- 4
# use this paste instead of `fullname` to
# work with Viridans Group Streptococci, etc.
# use this paste instead of `fullname` to work with Viridans Group Streptococci, etc.
MO_lookup$fullname_lower <- tolower(trimws(paste(MO_lookup$genus,
MO_lookup$species,
MO_lookup$subspecies)))
@ -62,9 +57,6 @@ create_MO_lookup <- function() {
create_MO.old_lookup <- function() {
MO.old_lookup <- AMR::microorganisms.old
# use this paste instead of `fullname` to
# work with Viridans Group Streptococci, etc.
MO.old_lookup$fullname_lower <- gsub("[^.a-z0-9/ \\-]+", "", tolower(trimws(MO.old_lookup$fullname)))
# add a column with only "e coli" like combinations
@ -73,202 +65,3 @@ create_MO.old_lookup <- function() {
# so arrange data on prevalence first, then full name
MO.old_lookup[order(MO.old_lookup$prevalence, MO.old_lookup$fullname_lower), ]
}
make_trans_tbl <- function() {
# conversion of old MO codes from v0.5.0 (ITIS) to later versions (Catalogue of Life)
c(B_ACHRMB = "B_ACHRM", B_ANNMA = "B_ACTNS", B_ACLLS = "B_ALCYC",
B_AHNGM = "B_ARCHN", B_ARMTM = "B_ARMTMN", B_ARTHR = "B_ARTHRB", B_ARTHRS = "B_ARTHR",
B_APHLS = "B_AZRHZP", B_BRCHA = "B_BRCHY", B_BCTRM = "B_BRVBCT",
B_CLRBCT = "B_CLRBC", B_CTRDM = "B_CLSTR", B_CPRMM = "B_CYLND",
B_DLCLN = "B_DPLCL", B_DMCLM = "B_DSLFT", B_DSLFVB = "B_DSLFV",
B_FCTRM = "B_FSBCT", B_GNRLA = "B_GRDNR", B_HNRBM = "B_HLNRB",
B_HPHGA = "B_HNPHGA", B_HCCCS = "B_HYDRC", B_MCRCLS = "B_MCRCL",
B_MTHYLS = "B_MLSMA", B_MARCLS = "B_MRCLS", B_MGCLS = "B_MSTGC",
B_MCLLA = "B_MTHYLC", B_MYCPLS = "B_MYCPL", B_NBCTR = "B_NTRBC",
B_OCLLS = "B_OCNBC", B_PTHRX = "B_PLNKT", B_PCCCS = "B_PRCHL",
B_PSPHN = "B_PRPHY", B_PDMNS = "B_PSDMN", B_SCCHRP = "B_SCCHR",
B_SRBCTR = "B_SHRBCTR", B_STRPTC = "B_STRPT", B_SHMNS = "B_SYNTR",
B_TRBCTR = "B_THRMN", P_ALBMN = "C_ABMNA", F_ACHLY = "C_ACHLY",
P_ACINT = "C_ACINT", P_ARTCL = "C_ACLNA", P_ACRVL = "C_ACRVL",
P_ADRCT = "C_ADRCT", P_AMPHS = "C_AHSRS", F_ALBUG = "C_ALBUG",
P_ALCNT = "C_ALCNT", P_ALFRD = "C_ALFRD", P_ALLGR = "C_ALLGR",
P_AMPHL = "C_ALPTS", F_ALTHR = "C_ALTHR", P_AMLLA = "C_AMLLA",
P_ANMLN = "C_AMLNA", P_AMMBC = "C_AMMBC", P_AMMDS = "C_AMMDS",
P_AMMLG = "C_AMMLG", P_AMMMR = "C_AMMMR", P_AMMMS = "C_AMMMS",
P_AMMON = "C_AMMON", P_AMMSC = "C_AMMSC", P_AMMSP = "C_AMMSP",
P_AMMST = "C_AMMST", P_AMMTM = "C_AMMTM", F_AMYCS = "C_AMYCS",
P_ANARM = "C_ANARM", P_ANGLD = "C_ANGLD", P_ANGLG = "C_ANGLG",
P_ANNLC = "C_ANNLC", F_ANSLP = "C_ANSLP", F_APDCH = "C_APDCH",
F_APHND = "C_APHND", F_APLNC = "C_APLNC", F_AQLND = "C_AQLND",
P_ARCHS = "C_ARCHAS", P_ASTRN = "C_ARNNN", P_ARNPR = "C_ARNPR",
F_ARSPR = "C_ARSPR", P_ARTST = "C_ARTSTR", P_AMPHC = "C_ARYNA",
P_ASCHM = "C_ASCHM", P_ASPDS = "C_ASPDS", P_ASTCL = "C_ASTCL",
P_ASTRG = "C_ASTRGR", P_ASTRM = "C_ASTRMM", P_ASTRR = "C_ASTRR",
P_ASTRT = "C_ASTRTR", F_ATKNS = "C_ATKNS", F_AYLLA = "C_AYLLA",
P_BAGGN = "C_BAGGN", P_BCCLL = "C_BCCLL", P_BDLLD = "C_BDLLD",
P_BGNRN = "C_BGNRN", P_BLCLN = "C_BLCLN", P_BLMND = "C_BLMND",
P_BLMNL = "C_BLMNL", P_BLPHR = "C_BLPHR", P_BLVNT = "C_BLVNT",
P_BOLVN = "C_BOLVN", P_BORLS = "C_BORLS", P_BRNNM = "C_BRNNM",
P_BRSLN = "C_BRSLN", P_BRSRD = "C_BRSRD", F_BRVLG = "C_BRVLG",
F_BNLLA = "C_BRVLGN", P_BSCCM = "C_BSCCM", F_BSDPH = "C_BSDPH",
P_BTHYS = "C_BTHYS", P_BTLLN = "C_BTLLN", P_BULMN = "C_BULMN",
P_CCLDM = "C_CCLDM", P_CDNLL = "C_CDNLL", P_CLPSS = "C_CDNLLP",
P_CHLDN = "C_CHLDNL", P_CHLST = "C_CHLST", P_CHNLM = "C_CHNLM",
P_CHRYS = "C_CHRYSL", P_CHTSP = "C_CHTSP", P_CBCDS = "C_CIBCDS",
P_CLCRN = "C_CLCRN", P_CLMNA = "C_CLMNA", P_CLPDM = "C_CLPDM",
P_CLPHR = "C_CLPHRY", P_CLVLN = "C_CLVLN", P_CMPNL = "C_CMPNL",
P_CNCRS = "C_CNCRS", P_CNTCH = "C_CNTCH", F_CNTRM = "C_CNTRMY",
P_COLPD = "C_COLPD", P_COLPS = "C_COLPS", P_CPRDS = "C_CPRDS",
P_CRNSP = "C_CPRMA", P_CRBNL = "C_CRBNL", P_CRBRB = "C_CRBRB",
P_CRBRG = "C_CRBRG", P_CRBRS = "C_CRBRS", P_CRCHS = "C_CRCHS",
P_CRCLC = "C_CRCLC", P_CRNLC = "C_CRNLC", P_CRNTH = "C_CRNTH",
P_CRPNT = "C_CRPNT", P_CRSTG = "C_CRSTG", P_CRTHN = "C_CRTHN",
P_CRTRN = "C_CRTRN", P_CYMBL = "C_CRTTA", P_CRYPT = "C_CRYPT",
P_CSHMN = "C_CSHMNL", P_CSSDL = "C_CSSDL", P_CLNDS = "C_CSSDLN",
P_CHRNA = "C_CTHRN", P_CTPSS = "C_CTPSS", P_CUNLN = "C_CUNLN",
P_CYLND = "C_CVLNA", P_CYCLC = "C_CYCLCB", P_CDNTA = "C_CYCLD",
P_CYCLG = "C_CYCLG", P_CYCLM = "C_CYCLM", P_CYRTL = "C_CYRTL",
P_CYSTM = "C_CYSTM", P_DCHLM = "C_DCHLM", P_DCRBS = "C_DCRBS",
P_DCTYC = "C_DCTYC", P_DIDNM = "C_DIDNM", P_DLPTS = "C_DLPTS",
P_DNTLN = "C_DNTLN", P_DNTST = "C_DNTST", P_DORTH = "C_DORTH",
P_DCTYP = "C_DPHMS", F_DPLCY = "C_DPLCY", P_DNDRT = "C_DRTNA",
P_DSCMM = "C_DSCMM", P_DSCRB = "C_DSCRB", P_DSCRN = "C_DSCRN",
P_DSCSP = "C_DSCSP", P_DSNBR = "C_DSNBR", P_DYCBC = "C_DYCBC",
F_DCTYC = "C_DYCHS", F_ECTRG = "C_ECTRG", B_EDWRD = "C_EDWRD",
P_EGGRL = "C_EGGRL", P_EHLYS = "C_EHLYS", P_EHRNB = "C_EHRNB",
P_ELPHD = "C_ELPHD", P_ENCHL = "C_ELYDM", P_EPHDM = "C_EPHDM",
P_EPLTS = "C_EPLTS", P_EPLXL = "C_EPLXL", P_EPNDL = "C_EPNDL",
P_EPNDS = "C_EPNDS", P_ENLLA = "C_EPSTM", P_EPSTY = "C_EPSTY",
F_ERYCH = "C_ERYCH", F_ESMDM = "C_ESMDM", P_ESSYR = "C_ESSYR",
P_FSCHR = "C_FHRNA", P_FLRLS = "C_FLRLS", P_FLNTN = "C_FNTNA",
P_FRNDC = "C_FRNDC", P_FRNTN = "C_FRNTN", P_FRSNK = "C_FRSNK",
P_FNLLA = "C_FSCHRN", P_FSSRN = "C_FSSRN", P_FVCSS = "C_FVCSS",
P_GDRYN = "C_GDRYN", F_GELGN = "C_GELGN", P_GERDA = "C_GERDA",
P_GLACM = "C_GLACM", P_GLBBL = "C_GLBBL", P_GLBGR = "C_GLBGR",
P_GLBLN = "C_GLBLN", P_GRTLA = "C_GLBRT", P_GLBTX = "C_GLBTX",
P_GLLNA = "C_GLLNA", P_GLMSP = "C_GLMSP", P_GLNDL = "C_GLNDL",
F_GNMCH = "C_GNMCH", P_GOSLL = "C_GOSLL", P_GRNDS = "C_GRNDS",
P_GRNTA = "C_GRNTA", P_GLBRT = "C_GTLLA", P_GTTLN = "C_GTTLN",
P_GVLNP = "C_GVLNP", P_GYPSN = "C_GYPSN", P_GYRDN = "C_GYRDN",
P_HALTR = "C_HALTR", P_HANZW = "C_HANZW", P_HAURN = "C_HAURN",
P_HELNN = "C_HELNN", P_HLPHR = "C_HHRYA", P_HLNTA = "C_HLNTA",
F_HLPHT = "C_HLPHT", P_HLSTC = "C_HLSTC", P_HMSPH = "C_HMSPH",
P_HMTRM = "C_HMTRM", P_HPKNS = "C_HPKNS", P_HPLPH = "C_HPLPH",
P_HPPCR = "C_HPPCR", P_HNLLA = "C_HPPCRP", P_HRMSN = "C_HRMSN",
P_HRNLL = "C_HRNLL", F_HRPCH = "C_HRPCH", P_HSTGR = "C_HSTGR",
P_HSTTL = "C_HSTTL", P_HTRST = "C_HTGNA", P_HTRLL = "C_HTRLL",
P_HTRPH = "C_HTRPH", F_HYPHC = "C_HYPHC", P_HYPRM = "C_HYPRM",
P_INTRN = "C_INTRN", P_IRIDI = "C_IRIDI", P_ISLND = "C_ISLND",
P_JCLLL = "C_JCLLL", P_KHLLL = "C_KHLLL", P_KRNPS = "C_KRNPS",
P_KRRRL = "C_KRRRL", P_LABOE = "C_LABOE", P_LAGEN = "C_LAGEN",
P_LBSLL = "C_LBSLL", F_LTHLA = "C_LBYRN", P_LCRYM = "C_LCRYM",
P_LEMBS = "C_LEMBS", F_LGNDM = "C_LGNDM", P_LGNMM = "C_LGNMM",
P_LGNPH = "C_LGNPHR", F_LGNSM = "C_LGNSM", P_LGYNP = "C_LGYNP",
P_LITTB = "C_LITTB", P_LITUL = "C_LITUL", P_LMBDN = "C_LMBDN",
P_LMRCK = "C_LMRCK", F_LBYRN = "C_LMYXA", P_LNGLN = "C_LNGLN",
P_LNTCL = "C_LNTCL", P_LOXDS = "C_LOXDS", F_LPTLG = "C_LPTLG",
F_LNLLA = "C_LPTLGN", F_LPTMT = "C_LPTMT", P_LRYNG = "C_LRYNG",
P_LTCRN = "C_LTCRN", P_LTHPL = "C_LTHPL", P_LTNTS = "C_LTNTS",
F_LTRST = "C_LTRST", P_LXPHY = "C_LXPHY", P_MCRTH = "C_MCRTH",
P_MELNS = "C_MELNS", P_MSDNM = "C_MESDNM", P_METPS = "C_METPS",
P_MIMSN = "C_MIMSN", P_MINCN = "C_MINCN", P_MLLNL = "C_MLLNL",
P_MLMMN = "C_MLMMN", F_MNDNL = "C_MNDNL", P_MNLYS = "C_MNLYS",
P_MNPSS = "C_MNPSS", P_MRGNL = "C_MRGNL", P_MRGNP = "C_MRGNP",
P_MRSPL = "C_MRSPL", P_MRTNT = "C_MRTNT", P_MSSLN = "C_MSSLN",
P_MSSSS = "C_MSSSS", P_MTCNT = "C_MTCNT", P_MYCHS = "C_MYCHS",
P_MYSCH = "C_MYSCH", F_MYZCY = "C_MYZCY", P_NASSL = "C_NASSL",
P_NBCLN = "C_NBCLN", P_NBCLR = "C_NBCLR", P_NCNRB = "C_NCNRB",
P_NDBCL = "C_NDBCL", P_NRLLA = "C_NDBCLR", P_NMMLC = "C_NMMLC",
F_NMTPH = "C_NMTPH", P_NNNLL = "C_NNNLL", P_NODSR = "C_NODSR",
P_NONIN = "C_NONIN", P_NOURI = "C_NOURI", P_OCLNA = "C_OCLNA",
P_OGLNA = "C_OGLNA", P_OPHTH = "C_OLMDM", F_OLPDP = "C_OLPDP",
P_ONYCH = "C_OMPSS", P_OOLIN = "C_OOLIN", P_OPRCL = "C_OPRCL",
P_ORBLN = "C_ORBLN", F_ORCAD = "C_ORCAD", P_ORDRS = "C_ORDRS",
P_OPHRY = "C_ORYDM", P_OSNGL = "C_OSNGL", P_OXYTR = "C_OXYTR",
P_PARRN = "C_PARRN", P_PATRS = "C_PATRS", P_PAVNN = "C_PAVNN",
P_PTYCH = "C_PCYLS", P_PDPHR = "C_PDPHR", P_PELSN = "C_PELSN",
F_PHGMY = "C_PHGMY", F_PSDSP = "C_PHRTA", P_PHRYG = "C_PHRYG",
P_PHYSL = "C_PHYSL", F_PHYTP = "C_PHYTP", P_PLACS = "C_PLACS",
P_PLCPS = "C_PLCPS", P_PLCPSL = "C_PLCPSL", P_PLCTN = "C_PLCTN",
P_PLGPH = "C_PLGPH", B_PLGTH = "C_PLGTH", P_PLMRN = "C_PLMRN",
P_PLNCT = "C_PLNCT", P_PLNDSC = "C_PLNDSC", P_PLNGY = "C_PLNGY",
P_PLNRBL = "C_PLNLLA", P_PLNLN = "C_PLNLN", P_PLNLR = "C_PLNLR",
P_PLNRB = "C_PLNRB", P_PLNSP = "C_PLNSPR", P_PLRNM = "C_PLRNM",
P_PLRST = "C_PLRST", P_PLRTR = "C_PLRTR", F_PLSMD = "C_PLSMD",
P_PLTYC = "C_PLTYC", P_PSDBL = "C_PLVNA", P_PLYMR = "C_PLYMR",
P_PLTYN = "C_PNMTM", P_PNRPL = "C_PNRPL", F_PNTSM = "C_PNTSM",
P_PRCNT = "C_PRCNT", P_PRFSS = "C_PRFSS", P_PRMCM = "C_PRMCUM",
F_PRNSP = "C_PRNSP", P_PRPND = "C_PRPND", P_PRPYX = "C_PRPYX",
P_PRRDN = "C_PRRDN", P_PSDDF = "C_PSDDF", P_PSDMC = "C_PSDMC",
P_PSDND = "C_PSDND", P_PSDNN = "C_PSDNN", P_PSDPL = "C_PSDPLY",
P_PSMMS = "C_PSMMS", P_PTLLN = "C_PTLLN", P_PTLLND = "C_PTLLND",
F_PTRSN = "C_PTRSN", P_PULLN = "C_PULLN", P_PUTLN = "C_PUTLN",
P_PRTTR = "C_PYMNA", P_PYRGL = "C_PYRGL", P_PYRGO = "C_PYRGO",
P_PYRLN = "C_PYRLN", F_PYTHM = "C_PYTHIM", F_PYTHL = "C_PYTHL",
P_PYXCL = "C_PYXCL", P_QNQLC = "C_QNQLC", P_RAMLN = "C_RAMLN",
P_RBRTN = "C_RBRTN", P_RCRVD = "C_RCRVD", P_RCTBL = "C_RCTBL",
P_RCTCB = "C_RCTCB", P_RCTGL = "C_RCTGL", P_RCTVG = "C_RCTVG",
P_RDGDR = "C_RDGDR", P_REMNC = "C_REMNC", P_REPHX = "C_REPHX",
P_RHBDM = "C_RHBDMM", F_RHBDS = "C_RHBDSP", P_RHPDD = "C_RHPDD",
F_RHPDM = "C_RHPDM", F_RHZDMY = "C_RHZDM", P_RHZMM = "C_RHZMM",
P_RIVRN = "C_RIVRN", P_ROSLN = "C_ROSLN", P_ROTAL = "C_ROTAL",
P_RPHDP = "C_RPHDP", P_RPRTN = "C_RPRTN", P_RSSLL = "C_RSSLL",
P_RTLMM = "C_RTLMM", P_RTYLA = "C_RTYLA", P_RUGID = "C_RUGID",
F_RZLLP = "C_RZLLP", P_SAGRN = "C_SAGRN", P_SCCMM = "C_SCCMM",
P_SCCRH = "C_SCCRH", P_SCHLM = "C_SCHLM", F_SCLRS = "C_SCLRS",
P_SCTLR = "C_SCTLR", P_SEBRK = "C_SEBRK", P_SGMLN = "C_SGMLN",
P_SGMLP = "C_SGMLP", P_SGMMR = "C_SGMMR", P_SGMVR = "C_SGMVR",
F_SMMRS = "C_SMMRS", P_SNNDS = "C_SNNDS", P_SORTS = "C_SORTS",
P_SPHGN = "C_SPHGN", P_SPHNN = "C_SPHNN", P_SNLLA = "C_SPHNNL",
P_SPHTR = "C_SPHTR", P_SPHTX = "C_SPHTX", P_SPHVG = "C_SPHVG",
P_SPRDT = "C_SPRDT", P_SPRLC = "C_SPRLC", F_SPRLG = "C_SPRLG",
P_SPRLL = "C_SPRLL", F_SPRMY = "C_SPRMY", P_SPRPL = "C_SPRPL",
P_SPRSG = "C_SPRSG", P_SPRST = "C_SPRST", P_SPHNP = "C_SPRTA",
P_SPRZN = "C_SPRZN", P_SPHRG = "C_SPSNA", P_STHDM = "C_SPTHD",
P_SRCNR = "C_SRCNR", F_SRLPD = "C_SRLPD", F_SPNGS = "C_SSPRA",
F_STEIN = "C_STEIN", P_SPTHD = "C_STHDDS", P_STHRP = "C_STHRP",
P_STNFR = "C_STNFR", P_STNSM = "C_STNSM", P_STNTR = "C_STNTR",
P_STRBL = "C_STRBL", P_STRMB = "C_STRMB", P_STTSN = "C_STTSN",
P_STYLN = "C_SYCHA", F_SCHZC = "C_SYTRM", P_TBNLL = "C_TBNLL",
P_TRCHL = "C_TCHLS", P_TCHNT = "C_TCHNT", P_THRCL = "C_THRCL",
P_THRMM = "C_THRMM", P_TIARN = "C_TIARN", P_TKPHR = "C_TKPHR",
P_TLNMA = "C_TLNMA", P_TLYPM = "C_TLYPM", P_TMNDS = "C_TMNDS",
P_TMNTA = "C_TMNTA", P_TNTNN = "C_TNNDM", P_TTNNS = "C_TNTNN",
P_TNPSS = "C_TNTNNP", P_TONTN = "C_TONTN", P_TOSAI = "C_TOSAI",
P_TPHTR = "C_TPHTR", P_TRCHH = "C_TRCHH", P_TRPHS = "C_TRCHLR",
P_TMMNA = "C_TRCHM", P_TRCHS = "C_TRCHSP", P_TRFRN = "C_TRFRN",
P_TRLCL = "C_TRLCL", P_TRTXL = "C_TRTXL", P_TRTXS = "C_TRTXS",
P_TTRHY = "C_TTRHY", F_TTRMY = "C_TTRMY", P_TXTLR = "C_TXTLR",
F_THRST = "C_TYTRM", P_URLPT = "C_ULPTS", P_UNGLT = "C_UNGLT",
P_URCNT = "C_URCNT", P_URONM = "C_URONM", P_UROSM = "C_UROSM",
P_URTRC = "C_URTRC", P_URSTY = "C_UTYLA", P_UVGRN = "C_UVGRN",
P_VLVLN = "C_VALVLN", P_VGNLN = "C_VGNLN", P_VGNLNP = "C_VGNLNP",
P_VLNRA = "C_VLVLN", P_VGNCL = "C_VNCLA", P_VRGLN = "C_VRGLN",
P_VRGLNP = "C_VRGLNP", P_VRTCL = "C_VRTCL", P_WBBNL = "C_WBBNL",
P_WEBBN = "C_WEBBN", P_WSNRL = "C_WSNRL", P_ZTHMN = "C_ZHMNM",
B_ZOOGL = "C_ZOOGL", F_DDSCS = "F_DPDSC", F_SCCHR = "F_SMYCS",
P_AMTRN = "P_ACNTH", F_AMBDM = "P_AMBDM", F_ARCYR = "P_ARCYR",
F_BADHM = "P_BADHM", F_BDHMP = "P_BDHMP", F_BRBYL = "P_BRBYL",
F_BRFLD = "P_BRFLD", F_CLMYX = "P_CLMYX", F_CLSTD = "P_CLSTD",
F_CMTRC = "P_CMTRC", F_CRBRR = "P_CRBRR", F_CRTMY = "P_CRTMY",
F_CRTRM = "P_CRTRM", F_DCTYD = "P_DCTYD", F_DDYMM = "P_DDYMM",
F_DIACH = "P_DIACH", F_DIANM = "P_DIANM", F_DIDRM = "P_DIDRM",
F_ELMYX = "P_ELMYX", F_ESTLM = "P_ESTLM", F_FULIG = "P_FULIG",
F_HMTRC = "P_HMTRC", F_LCRPS = "P_LCRPS", F_LICEA = "P_LICEA",
F_LMPRD = "P_LMPRD", F_LPTDR = "P_LPTDR", F_LSTRL = "P_LSTRL",
F_LYCGL = "P_LYCGL", F_MCBRD = "P_MCBRD", F_MNKTL = "P_MNKTL",
F_MTTRC = "P_MTTRC", F_MUCLG = "P_MUCLG", F_PHYSR = "P_PHYSR",
F_PRCHN = "P_PRCHN", F_PRMBD = "P_PRMBD", F_PRTPH = "P_PRTPH",
F_PSRNA = "P_PSRNA", F_PYSRM = "P_PYSRM", F_RTCLR = "P_RTCLR",
F_STMNT = "P_STMNT", F_SYMPH = "P_SYMPH", F_TRBRK = "P_TRBRK",
F_TRICH = "P_TRICH", F_TUBFR = "P_TUBFR",
B_GRDNR = "B_GRLLA", B_SGMNS = "B_SNGMNS", B_TCLLS = "B_THBCL",
F_CCCCS = "F_CRYPT",
# renamings of old genus + species
# putting full names here will throw notes with new taxonomic names
F_CANDD_GLB = "F_CANDD_GLA", F_CANDD_KRU = "Candida krusei",
F_CANDD_GUI = "Candida guilliermondii", F_HNSNL_ANO = "Hansenula anomala",
F_CANDD_LUS = "Candida lusitaniae", B_STRPT_TUS = "B_STRPT",
B_PRVTL_OLA = "B_PRVTL_OULO", B_FSBCT_RUM = "B_FSBCT",
B_CRYNB_EYI = "B_CRYNB_FRE", B_OLGLL_LIS = "B_OLGLL_URE")
}