AMR/R/mo_property.R

762 lines
32 KiB
R
Raw Normal View History

# ==================================================================== #
# TITLE #
# Antimicrobial Resistance (AMR) Data Analysis for R #
# #
2019-01-02 23:24:07 +01:00
# SOURCE #
2020-07-08 14:48:06 +02:00
# https://github.com/msberends/AMR #
# #
# LICENCE #
2021-12-23 18:56:28 +01:00
# (c) 2018-2022 Berends MS, Luz CF et al. #
2020-10-08 11:16:03 +02:00
# Developed at the University of Groningen, the Netherlands, in #
# collaboration with non-profit organisations Certe Medical #
2020-10-26 12:23:03 +01:00
# Diagnostics & Advice, and University Medical Center Groningen. #
# #
2019-01-02 23:24:07 +01:00
# 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. #
2020-10-08 11:16:03 +02:00
# #
# Visit our website for the full manual and a complete tutorial about #
# how to conduct AMR data analysis: https://msberends.github.io/AMR/ #
# ==================================================================== #
#' Get Properties of a Microorganism
#'
#' Use these functions to return a specific property of a microorganism based on the latest accepted taxonomy. All input values will be evaluated internally with [as.mo()], which makes it possible to use microbial abbreviations, codes and names as input. See *Examples*.
2021-05-12 18:15:03 +02:00
#' @param x any [character] (vector) that can be coerced to a valid microorganism code with [as.mo()]. Can be left blank for auto-guessing the column containing microorganism codes if used in a data set, see *Examples*.
#' @param property one of the column names of the [microorganisms] data set: `r vector_or(colnames(microorganisms), sort = FALSE, quotes = TRUE)`, or must be `"shortname"`
#' @param language language of the returned text, defaults to system language (see [get_AMR_locale()]) and can be overwritten by setting the option `AMR_locale`, e.g. `options(AMR_locale = "de")`, see [translate]. Also used to translate text like "no growth". Use `language = NULL` or `language = ""` to prevent translation.
2020-12-22 00:51:17 +01:00
#' @param ... other arguments passed on to [as.mo()], such as 'allow_uncertain' and 'ignore_pattern'
#' @param ab any (vector of) text that can be coerced to a valid antibiotic code with [as.ab()]
#' @param open browse the URL using [`browseURL()`][utils::browseURL()]
#' @details All functions will return the most recently known taxonomic property according to the Catalogue of Life, except for [mo_ref()], [mo_authors()] and [mo_year()]. Please refer to this example, knowing that *Escherichia blattae* was renamed to *Shimwellia blattae* in 2010:
#' - `mo_name("Escherichia blattae")` will return `"Shimwellia blattae"` (with a message about the renaming)
#' - `mo_ref("Escherichia blattae")` will return `"Burgess et al., 1973"` (with a message about the renaming)
#' - `mo_ref("Shimwellia blattae")` will return `"Priest et al., 2010"` (without a message)
2019-02-20 00:04:48 +01:00
#'
2020-12-17 16:22:25 +01:00
#' The short name - [mo_shortname()] - almost always returns the first character of the genus and the full species, like `"E. coli"`. Exceptions are abbreviations of staphylococci (such as *"CoNS"*, Coagulase-Negative Staphylococci) and beta-haemolytic streptococci (such as *"GBS"*, Group B Streptococci). Please bear in mind that e.g. *E. coli* could mean *Escherichia coli* (kingdom of Bacteria) as well as *Entamoeba coli* (kingdom of Protozoa). Returning to the full name will be done using [as.mo()] internally, giving priority to bacteria and human pathogens, i.e. `"E. coli"` will be considered *Escherichia coli*. In other words, `mo_fullname(mo_shortname("Entamoeba coli"))` returns `"Escherichia coli"`.
2020-10-26 12:23:03 +01:00
#'
#' Since the top-level of the taxonomy is sometimes referred to as 'kingdom' and sometimes as 'domain', the functions [mo_kingdom()] and [mo_domain()] return the exact same results.
#'
#' The Gram stain - [mo_gramstain()] - will be determined based on the taxonomic kingdom and phylum. According to Cavalier-Smith (2002, [PMID 11837318](https://pubmed.ncbi.nlm.nih.gov/11837318)), who defined subkingdoms Negibacteria and Posibacteria, only these phyla are Posibacteria: Actinobacteria, Chloroflexi, Firmicutes and Tenericutes. These bacteria are considered Gram-positive, except for members of the class Negativicutes which are Gram-negative. Members of other bacterial phyla are all considered Gram-negative. Species outside the kingdom of Bacteria will return a value `NA`. Functions [mo_is_gram_negative()] and [mo_is_gram_positive()] always return `TRUE` or `FALSE` (except when the input is `NA` or the MO code is `UNKNOWN`), thus always return `FALSE` for species outside the taxonomic kingdom of Bacteria.
#'
#' Determination of yeasts - [mo_is_yeast()] - will be based on the taxonomic kingdom and class. *Budding yeasts* are fungi of the phylum Ascomycetes, class Saccharomycetes (also called Hemiascomycetes). *True yeasts* are aggregated into the underlying order Saccharomycetales. Thus, for all microorganisms that are fungi and member of the taxonomic class Saccharomycetes, the function will return `TRUE`. It returns `FALSE` otherwise (except when the input is `NA` or the MO code is `UNKNOWN`).
#'
#' Intrinsic resistance - [mo_is_intrinsic_resistant()] - will be determined based on the [intrinsic_resistant] data set, which is based on `r format_eucast_version_nr(3.3)`. The [mo_is_intrinsic_resistant()] functions can be vectorised over arguments `x` (input for microorganisms) and over `ab` (input for antibiotics).
2019-02-20 00:04:48 +01:00
#'
#' All output [will be translated][translate] where possible.
2019-05-10 16:44:59 +02:00
#'
#' The function [mo_url()] will return the direct URL to the online database entry, which also shows the scientific reference of the concerned species.
2021-03-11 21:42:30 +01:00
#'
2021-07-04 15:26:50 +02:00
#' SNOMED codes - [mo_snomed()] - are from the `r SNOMED_VERSION$current_source`. See *Source* and the [microorganisms] data set for more info.
#' @inheritSection mo_matching_score Matching Score for Microorganisms
2019-02-20 00:04:48 +01:00
#' @inheritSection catalogue_of_life Catalogue of Life
2018-09-24 23:33:29 +02:00
#' @inheritSection as.mo Source
#' @rdname mo_property
#' @name mo_property
#' @return
#' - 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()]
2021-03-11 21:42:30 +01:00
#' - A [numeric] in case of [mo_snomed()]
#' - A [character] in all other cases
#' @export
2021-07-04 15:26:50 +02:00
#' @seealso Data set [microorganisms]
#' @inheritSection AMR Reference Data Publicly Available
#' @examples
#' # taxonomic tree -----------------------------------------------------------
2022-08-21 16:37:20 +02:00
#' mo_kingdom("Klebsiella pneumoniae")
#' mo_phylum("Klebsiella pneumoniae")
#' mo_class("Klebsiella pneumoniae")
#' mo_order("Klebsiella pneumoniae")
#' mo_family("Klebsiella pneumoniae")
#' mo_genus("Klebsiella pneumoniae")
#' mo_species("Klebsiella pneumoniae")
#' mo_subspecies("Klebsiella pneumoniae")
2018-11-09 13:11:54 +01:00
#'
#' # colloquial properties ----------------------------------------------------
2022-08-21 16:37:20 +02:00
#' mo_name("Klebsiella pneumoniae")
#' mo_fullname("Klebsiella pneumoniae")
#' mo_shortname("Klebsiella pneumoniae")
2018-11-09 13:11:54 +01:00
#'
#' # other properties ---------------------------------------------------------
2022-08-21 16:37:20 +02:00
#' mo_gramstain("Klebsiella pneumoniae")
#' mo_snomed("Klebsiella pneumoniae")
#' mo_type("Klebsiella pneumoniae")
#' mo_rank("Klebsiella pneumoniae")
#' mo_url("Klebsiella pneumoniae")
#' mo_synonyms("Klebsiella pneumoniae")
2018-11-09 13:11:54 +01:00
#'
#' # scientific reference -----------------------------------------------------
2022-08-21 16:37:20 +02:00
#' mo_ref("Klebsiella pneumoniae")
#' mo_authors("Klebsiella pneumoniae")
#' mo_year("Klebsiella pneumoniae")
#' mo_lpsn("Klebsiella pneumoniae")
#'
#' # abbreviations known in the field -----------------------------------------
2022-08-21 16:37:20 +02:00
#' mo_genus("MRSA")
#' mo_species("MRSA")
#' mo_shortname("VISA")
#' mo_gramstain("VISA")
#'
2022-08-21 16:37:20 +02:00
#' mo_genus("EHEC")
#' mo_species("EHEC")
#'
#' # known subspecies ---------------------------------------------------------
2022-08-21 16:37:20 +02:00
#' mo_name("doylei")
#' mo_genus("doylei")
#' mo_species("doylei")
#' mo_subspecies("doylei")
#'
2022-08-21 16:37:20 +02:00
#' mo_fullname("K. pneu rh")
#' mo_shortname("K. pneu rh")
#'
#' \donttest{
#' # Becker classification, see ?as.mo ----------------------------------------
2022-08-21 16:37:20 +02:00
#' mo_fullname("S. epi")
#' mo_fullname("S. epi", Becker = TRUE)
#' mo_shortname("S. epi")
#' mo_shortname("S. epi", Becker = TRUE)
#'
#' # Lancefield classification, see ?as.mo ------------------------------------
2022-08-21 16:37:20 +02:00
#' mo_fullname("S. pyo")
#' mo_fullname("S. pyo", Lancefield = TRUE)
#' mo_shortname("S. pyo")
#' mo_shortname("S. pyo", Lancefield = TRUE)
#'
#'
#' # language support --------------------------------------------------------
2022-08-21 16:37:20 +02:00
#' mo_gramstain("Klebsiella pneumoniae", language = "de")
#' mo_gramstain("Klebsiella pneumoniae", language = "nl")
#' mo_gramstain("Klebsiella pneumoniae", language = "es")
#'
2018-11-09 13:11:54 +01:00
#' # mo_type is equal to mo_kingdom, but mo_kingdom will remain official
2022-08-21 16:37:20 +02:00
#' mo_kingdom("Klebsiella pneumoniae")
#' mo_type("Klebsiella pneumoniae")
#' mo_type("Klebsiella pneumoniae")
2018-11-09 13:11:54 +01:00
#'
2018-09-09 12:11:44 +02:00
#' mo_fullname("S. pyogenes",
#' Lancefield = TRUE,
2022-08-21 16:37:20 +02:00
#' language = "de")
2018-09-09 12:11:44 +02:00
#' mo_fullname("S. pyogenes",
#' Lancefield = TRUE,
2022-08-21 16:37:20 +02:00
#' language = "nl")
2018-09-17 20:53:32 +02:00
#'
#'
#' # other --------------------------------------------------------------------
#'
2022-08-21 16:37:20 +02:00
#' mo_is_yeast(c("Candida", "Trichophyton", "Klebsiella"))
#'
2022-08-21 16:37:20 +02:00
#' # gram stains and intrinsic resistance can be used as a filter in dplyr verbs
2020-11-09 15:18:36 +01:00
#' if (require("dplyr")) {
#' example_isolates %>%
#' filter(mo_is_gram_positive())
#'
#' example_isolates %>%
#' filter(mo_is_intrinsic_resistant(ab = "vanco"))
2020-11-09 15:18:36 +01:00
#' }
#'
#'
2019-05-10 16:44:59 +02:00
#' # get a list with the complete taxonomy (from kingdom to subspecies)
2022-08-21 16:37:20 +02:00
#' mo_taxonomy("Klebsiella pneumoniae")
#'
2021-03-11 21:42:30 +01:00
#' # get a list with the taxonomy, the authors, Gram-stain,
2022-08-21 16:37:20 +02:00
#' # SNOMED codes, and URL to the online database
#' mo_info("Klebsiella pneumoniae")
2021-05-24 09:00:11 +02:00
#' }
mo_name <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_name")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2022-08-19 12:33:14 +02:00
translate_into_language(mo_validate(x = x, property = "fullname", language = language, ...),
language = language,
only_unknown = FALSE,
only_affect_mo_names = TRUE)
2019-05-13 12:21:57 +02:00
}
#' @rdname mo_property
#' @export
2019-06-11 14:18:25 +02:00
mo_fullname <- mo_name
2018-09-05 10:51:46 +02:00
#' @rdname mo_property
#' @export
mo_shortname <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_shortname")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2020-09-14 12:21:23 +02:00
x.mo <- as.mo(x, language = language, ...)
metadata <- get_mo_failures_uncertainties_renamed()
2019-07-10 21:36:51 +02:00
replace_empty <- function(x) {
x[x == ""] <- "spp."
x
}
2019-06-27 11:57:45 +02:00
# get first char of genus and complete species in English
2020-08-26 11:33:54 +02:00
genera <- mo_genus(x.mo, language = NULL)
shortnames <- paste0(substr(genera, 1, 1), ". ", replace_empty(mo_species(x.mo, language = NULL)))
2020-08-26 11:33:54 +02:00
# exceptions for where no species is known
shortnames[shortnames %like% ".[.] spp[.]"] <- genera[shortnames %like% ".[.] spp[.]"]
# exceptions for staphylococci
2019-10-11 17:21:02 +02:00
shortnames[shortnames == "S. coagulase-negative"] <- "CoNS"
shortnames[shortnames == "S. coagulase-positive"] <- "CoPS"
# exceptions for streptococci: Group A Streptococcus -> GAS
shortnames[shortnames %like% "S. group [ABCDFGHK]"] <- paste0("G", gsub("S. group ([ABCDFGHK])", "\\1", shortnames[shortnames %like% "S. group [ABCDFGHK]"], perl = TRUE), "S")
2020-08-26 11:33:54 +02:00
# unknown species etc.
shortnames[shortnames %like% "unknown"] <- paste0("(", trimws(gsub("[^a-zA-Z -]", "", shortnames[shortnames %like% "unknown"], perl = TRUE)), ")")
shortnames[is.na(x.mo)] <- NA_character_
load_mo_failures_uncertainties_renamed(metadata)
2022-08-19 12:33:14 +02:00
translate_into_language(shortnames, language = language, only_unknown = FALSE, only_affect_mo_names = TRUE)
2018-09-05 10:51:46 +02:00
}
2018-09-17 20:53:32 +02:00
#' @rdname mo_property
#' @export
mo_subspecies <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_subspecies")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2022-08-19 12:33:14 +02:00
translate_into_language(mo_validate(x = x, property = "subspecies", language = language, ...), language = language, only_unknown = TRUE)
2018-09-17 20:53:32 +02:00
}
#' @rdname mo_property
#' @export
mo_species <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_species")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2022-08-19 12:33:14 +02:00
translate_into_language(mo_validate(x = x, property = "species", language = language, ...), language = language, only_unknown = TRUE)
2018-09-17 20:53:32 +02:00
}
#' @rdname mo_property
#' @export
mo_genus <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_genus")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2022-08-19 12:33:14 +02:00
translate_into_language(mo_validate(x = x, property = "genus", language = language, ...), language = language, only_unknown = TRUE)
2018-09-17 20:53:32 +02:00
}
#' @rdname mo_property
#' @export
mo_family <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_family")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2022-08-19 12:33:14 +02:00
translate_into_language(mo_validate(x = x, property = "family", language = language, ...), language = language, only_unknown = TRUE)
2018-09-17 20:53:32 +02:00
}
#' @rdname mo_property
#' @export
mo_order <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_order")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2022-08-19 12:33:14 +02:00
translate_into_language(mo_validate(x = x, property = "order", language = language, ...), language = language, only_unknown = TRUE)
2018-09-17 20:53:32 +02:00
}
#' @rdname mo_property
#' @export
mo_class <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_class")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2022-08-19 12:33:14 +02:00
translate_into_language(mo_validate(x = x, property = "class", language = language, ...), language = language, only_unknown = TRUE)
2018-09-17 20:53:32 +02:00
}
#' @rdname mo_property
#' @export
mo_phylum <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_phylum")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2022-08-19 12:33:14 +02:00
translate_into_language(mo_validate(x = x, property = "phylum", language = language, ...), language = language, only_unknown = TRUE)
2018-09-17 20:53:32 +02:00
}
2018-09-05 10:51:46 +02:00
#' @rdname mo_property
#' @export
mo_kingdom <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_kingdom")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2022-08-19 12:33:14 +02:00
translate_into_language(mo_validate(x = x, property = "kingdom", language = language, ...), language = language, only_unknown = TRUE)
}
#' @rdname mo_property
#' @export
mo_domain <- mo_kingdom
#' @rdname mo_property
#' @export
mo_type <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_type")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
x.mo <- as.mo(x, language = language, ...)
out <- mo_kingdom(x.mo, language = NULL)
out[which(mo_is_yeast(x.mo))] <- "Yeasts"
2022-08-19 12:33:14 +02:00
translate_into_language(out, language = language, only_unknown = FALSE)
2018-11-09 13:11:54 +01:00
}
#' @rdname mo_property
#' @export
mo_gramstain <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_gramstain")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2020-09-14 12:21:23 +02:00
x.mo <- as.mo(x, language = language, ...)
metadata <- get_mo_failures_uncertainties_renamed()
x <- rep(NA_character_, length(x))
2019-06-11 14:18:25 +02:00
# make all bacteria Gram negative
x[mo_kingdom(x.mo) == "Bacteria"] <- "Gram-negative"
# overwrite these 4 phyla with Gram-positives
# Source: https://itis.gov/servlet/SingleRpt/SingleRpt?search_topic=TSN&search_value=956097 (Cavalier-Smith, 2002)
x[(mo_phylum(x.mo) %in% c("Actinobacteria",
"Chloroflexi",
"Firmicutes",
"Tenericutes") &
# but class Negativicutes (of phylum Firmicutes) are Gram-negative!
mo_class(x.mo) != "Negativicutes")
# and of course our own ID for Gram-positives
2019-06-11 14:18:25 +02:00
| x.mo == "B_GRAMP"] <- "Gram-positive"
load_mo_failures_uncertainties_renamed(metadata)
2022-08-19 12:33:14 +02:00
translate_into_language(x, language = language, only_unknown = FALSE)
2018-10-01 11:39:43 +02:00
}
#' @rdname mo_property
#' @export
mo_is_gram_negative <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_is_gram_negative")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
2020-10-26 12:23:03 +01:00
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2020-10-26 12:23:03 +01:00
x.mo <- as.mo(x, language = language, ...)
metadata <- get_mo_failures_uncertainties_renamed()
grams <- mo_gramstain(x.mo, language = NULL)
load_mo_failures_uncertainties_renamed(metadata)
out <- grams == "Gram-negative" & !is.na(grams)
out[x.mo %in% c(NA_character_, "UNKNOWN")] <- NA
out
}
#' @rdname mo_property
#' @export
mo_is_gram_positive <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_is_gram_positive")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
2020-10-26 12:23:03 +01:00
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2020-10-26 12:23:03 +01:00
x.mo <- as.mo(x, language = language, ...)
metadata <- get_mo_failures_uncertainties_renamed()
grams <- mo_gramstain(x.mo, language = NULL)
load_mo_failures_uncertainties_renamed(metadata)
out <- grams == "Gram-positive" & !is.na(grams)
out[x.mo %in% c(NA_character_, "UNKNOWN")] <- NA
out
}
#' @rdname mo_property
#' @export
mo_is_yeast <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_is_yeast")
}
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
x.mo <- as.mo(x, language = language, ...)
metadata <- get_mo_failures_uncertainties_renamed()
x.kingdom <- mo_kingdom(x.mo, language = NULL)
x.class <- mo_class(x.mo, language = NULL)
load_mo_failures_uncertainties_renamed(metadata)
out <- rep(FALSE, length(x))
out[x.kingdom == "Fungi" & x.class == "Saccharomycetes"] <- TRUE
out[x.mo %in% c(NA_character_, "UNKNOWN")] <- NA
out
}
#' @rdname mo_property
#' @export
mo_is_intrinsic_resistant <- function(x, ab, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_is_intrinsic_resistant")
}
meet_criteria(x, allow_NA = TRUE)
meet_criteria(ab, allow_NA = FALSE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
x <- as.mo(x, language = language, ...)
ab <- as.ab(ab, language = NULL, flag_multiple_results = FALSE, info = FALSE)
if (length(x) == 1 & length(ab) > 1) {
x <- rep(x, length(ab))
} else if (length(ab) == 1 & length(x) > 1) {
ab <- rep(ab, length(x))
}
if (length(x) != length(ab)) {
stop_("length of `x` and `ab` must be equal, or one of them must be of length 1.")
}
# show used version number once per session (pkg_env will reload every session)
if (message_not_thrown_before("mo_is_intrinsic_resistant", "version.mo", entire_session = TRUE)) {
2020-12-03 22:30:14 +01:00
message_("Determining intrinsic resistance based on ",
format_eucast_version_nr(3.3, markdown = FALSE), ". ",
font_red("This note will be shown once per session."))
2020-12-03 22:30:14 +01:00
}
# runs against internal vector: INTRINSIC_R (see zzz.R)
paste(x, ab) %in% INTRINSIC_R
}
2020-01-27 19:14:23 +01:00
#' @rdname mo_property
#' @export
mo_snomed <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_snomed")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2020-09-14 12:21:23 +02:00
mo_validate(x = x, property = "snomed", language = language, ...)
2020-01-27 19:14:23 +01:00
}
2018-10-01 11:39:43 +02:00
#' @rdname mo_property
#' @export
mo_ref <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_ref")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2020-09-14 12:21:23 +02:00
mo_validate(x = x, property = "ref", language = language, ...)
}
#' @rdname mo_property
#' @export
mo_authors <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_authors")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2020-09-14 12:21:23 +02:00
x <- mo_validate(x = x, property = "ref", language = language, ...)
2019-06-22 14:49:12 +02:00
# remove last 4 digits and presumably the comma and space that preceed them
x[!is.na(x)] <- gsub(",? ?[0-9]{4}", "", x[!is.na(x)], perl = TRUE)
2019-02-22 22:12:10 +01:00
suppressWarnings(x)
2018-11-09 13:11:54 +01:00
}
2018-09-24 23:33:29 +02:00
2018-11-09 13:11:54 +01:00
#' @rdname mo_property
#' @export
mo_year <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_year")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2020-09-14 12:21:23 +02:00
x <- mo_validate(x = x, property = "ref", language = language, ...)
2018-11-09 13:11:54 +01:00
# get last 4 digits
x[!is.na(x)] <- gsub(".*([0-9]{4})$", "\\1", x[!is.na(x)], perl = TRUE)
2019-02-22 22:12:10 +01:00
suppressWarnings(as.integer(x))
}
2021-12-09 10:48:25 +01:00
#' @rdname mo_property
#' @export
mo_lpsn <- function(x, language = get_AMR_locale(), ...) {
2021-12-09 10:48:25 +01:00
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_rank")
}
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
mo_validate(x = x, property = "species_id", language = language, ...)
}
2019-02-22 22:12:10 +01:00
#' @rdname mo_property
#' @export
mo_rank <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_rank")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2020-09-14 12:21:23 +02:00
mo_validate(x = x, property = "rank", language = language, ...)
}
2018-09-17 20:53:32 +02:00
#' @rdname mo_property
#' @export
mo_taxonomy <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_taxonomy")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2020-09-14 12:21:23 +02:00
x <- as.mo(x, language = language, ...)
metadata <- get_mo_failures_uncertainties_renamed()
out <- list(kingdom = mo_kingdom(x, language = language),
phylum = mo_phylum(x, language = language),
class = mo_class(x, language = language),
order = mo_order(x, language = language),
family = mo_family(x, language = language),
genus = mo_genus(x, language = language),
species = mo_species(x, language = language),
subspecies = mo_subspecies(x, language = language))
load_mo_failures_uncertainties_renamed(metadata)
out
2018-09-17 20:53:32 +02:00
}
#' @rdname mo_property
#' @export
mo_synonyms <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_synonyms")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2020-09-14 12:21:23 +02:00
x <- as.mo(x, language = language, ...)
metadata <- get_mo_failures_uncertainties_renamed()
2020-05-27 16:37:49 +02:00
IDs <- mo_name(x = x, language = NULL)
syns <- lapply(IDs, function(newname) {
res <- sort(microorganisms.old[which(microorganisms.old$fullname_new == newname), "fullname"])
2019-06-22 14:49:12 +02:00
if (length(res) == 0) {
NULL
} else {
res
}
})
if (length(syns) > 1) {
names(syns) <- mo_name(x)
result <- syns
2019-06-22 14:49:12 +02:00
} else {
result <- unlist(syns)
}
load_mo_failures_uncertainties_renamed(metadata)
result
}
2019-06-11 14:18:25 +02:00
#' @rdname mo_property
#' @export
mo_info <- function(x, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_info")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2020-09-14 12:21:23 +02:00
x <- as.mo(x, language = language, ...)
metadata <- get_mo_failures_uncertainties_renamed()
2019-06-22 14:49:12 +02:00
info <- lapply(x, function(y)
c(mo_taxonomy(y, language = language),
list(synonyms = mo_synonyms(y),
gramstain = mo_gramstain(y, language = language),
2019-06-22 14:49:12 +02:00
url = unname(mo_url(y, open = FALSE)),
2021-03-11 21:42:30 +01:00
ref = mo_ref(y),
snomed = unlist(mo_snomed(y)))))
2019-06-22 14:49:12 +02:00
if (length(info) > 1) {
names(info) <- mo_name(x)
result <- info
2019-06-22 14:49:12 +02:00
} else {
result <- info[[1L]]
2019-06-22 14:49:12 +02:00
}
load_mo_failures_uncertainties_renamed(metadata)
result
2019-06-11 14:18:25 +02:00
}
2019-02-20 00:04:48 +01:00
#' @rdname mo_property
#' @export
mo_url <- function(x, open = FALSE, language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_url")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(open, allow_class = "logical", has_length = 1)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
x.mo <- as.mo(x = x, language = language, ... = ...)
metadata <- get_mo_failures_uncertainties_renamed()
df <- microorganisms[match(x.mo, microorganisms$mo), c("mo", "fullname", "source", "kingdom", "rank")]
df$url <- ifelse(df$source == "LPSN",
paste0(CATALOGUE_OF_LIFE$url_LPSN, "/species/", gsub(" ", "-", tolower(df$fullname), fixed = TRUE)),
paste0(CATALOGUE_OF_LIFE$url_CoL, "/data/search?type=EXACT&q=", gsub(" ", "%20", df$fullname, fixed = TRUE)))
genera <- which(df$kingdom == "Bacteria" & df$rank == "genus")
df$url[genera] <- gsub("/species/", "/genus/", df$url[genera], fixed = TRUE)
subsp <- which(df$kingdom == "Bacteria" & df$rank %in% c("subsp.", "infraspecies"))
df$url[subsp] <- gsub("/species/", "/subspecies/", df$url[subsp], fixed = TRUE)
2019-03-18 14:29:41 +01:00
u <- df$url
names(u) <- df$fullname
if (isTRUE(open)) {
2019-02-22 22:12:10 +01:00
if (length(u) > 1) {
warning_("in `mo_url()`: only the first URL will be opened, as `browseURL()` only suports one string.")
2019-02-22 22:12:10 +01:00
}
2020-05-16 13:05:47 +02:00
utils::browseURL(u[1L])
2019-02-22 22:12:10 +01:00
}
load_mo_failures_uncertainties_renamed(metadata)
2019-02-20 00:04:48 +01:00
u
}
2018-11-09 13:11:54 +01:00
#' @rdname mo_property
#' @export
mo_property <- function(x, property = "fullname", language = get_AMR_locale(), ...) {
if (missing(x)) {
# this tries to find the data and an <mo> column
x <- find_mo_col(fn = "mo_property")
}
2020-10-19 20:44:45 +02:00
meet_criteria(x, allow_NA = TRUE)
meet_criteria(property, allow_class = "character", has_length = 1, is_in = colnames(microorganisms))
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
2022-08-19 12:33:14 +02:00
translate_into_language(mo_validate(x = x, property = property, language = language, ...), language = language, only_unknown = TRUE)
}
2020-09-14 12:21:23 +02:00
mo_validate <- function(x, property, language, ...) {
2020-02-14 19:54:13 +01:00
check_dataset_integrity()
2018-10-01 11:39:43 +02:00
dots <- list(...)
Becker <- dots$Becker
if (is.null(Becker) | property %in% c("kingdom", "phylum", "class", "order", "family", "genus")) {
2018-10-01 11:39:43 +02:00
Becker <- FALSE
}
Lancefield <- dots$Lancefield
if (is.null(Lancefield) | property %in% c("kingdom", "phylum", "class", "order", "family", "genus")) {
2018-10-01 11:39:43 +02:00
Lancefield <- FALSE
}
has_Becker_or_Lancefield <- Becker %in% c(TRUE, "all") | Lancefield %in% c(TRUE, "all")
if (tryCatch(all(x[!is.na(x)] %in% MO_lookup$mo) & !has_Becker_or_Lancefield, error = function(e) FALSE)) {
# special case for mo_* functions where class is already <mo>
x <- MO_lookup[match(x, MO_lookup$mo), property, drop = TRUE]
2022-08-19 12:33:14 +02:00
} else {
# try to catch an error when inputting an invalid argument
# so the 'call.' can be set to FALSE
tryCatch(x[1L] %in% MO_lookup[1, property, drop = TRUE],
error = function(e) stop(e$message, call. = FALSE))
if (!all(x[!is.na(x)] %in% MO_lookup[, property, drop = TRUE]) | has_Becker_or_Lancefield) {
x <- exec_as.mo(x, property = property, language = language, ...)
}
2019-06-22 14:49:12 +02:00
}
2019-06-22 14:49:12 +02:00
if (property == "mo") {
2020-11-16 20:02:20 +01:00
return(set_clean_class(x, new_class = c("mo", "character")))
2021-12-09 10:48:25 +01:00
} else if (property == "species_id") {
return(as.double(x))
2020-01-27 19:14:23 +01:00
} else if (property == "snomed") {
return(as.double(eval(parse(text = x))))
} else {
2019-06-22 14:49:12 +02:00
return(x)
}
}
find_mo_col <- function(fn) {
# this function tries to find an mo column in the data the function was called in,
# which is useful when functions are used within dplyr verbs
df <- get_current_data(arg_name = "x", 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)) {
if (message_not_thrown_before(fn = fn)) {
message_("Using column '", font_bold(mo), "' as input for `", fn, "()`")
}
return(df[, mo, drop = TRUE])
} else {
stop_("argument `x` is missing and no column with info about microorganisms could be found.", call = -2)
}
}