P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2025-07-09 00:02:38 +02:00
Code Releases Activity

documentation

Browse Source
This commit is contained in:
dr. M.S. (Matthijs) Berends
2023-01-07 01:51:19 +01:00
parent 84ed8c32bb
commit 2375bfdcb5
8 changed files with 61 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
R/mo.R
View File

@ -83,7 +83,7 @@
#'
#' ### Microbial Prevalence of Pathogens in Humans
#'
#' The coercion rules consider the prevalence of microorganisms in humans grouped into three groups, which is available as the `prevalence` columns in the [microorganisms] data set. The grouping into human pathogenic prevalence is explained in the section *Matching Score for Microorganisms* below.
#' The coercion rules consider the prevalence of microorganisms in humans, which is available as the `prevalence` column in the [microorganisms] data set. The grouping into human pathogenic prevalence is explained in the section *Matching Score for Microorganisms* below.
#' @inheritSection mo_matching_score Matching Score for Microorganisms
#'
# (source as a section here, so it can be inherited by other man pages)
@ -536,7 +536,7 @@ mo_cleaning_regex <- function() {
"|",
"([({]|\\[).+([})]|\\])",
"|",
"(^| )(e?spp|e?ssp|e?ss|e?sp|e?subsp|sube?species|biovar|biotype|serovar|serogr.?up|e?species|group|complex)[.]*( |$))"
"(^| )(e?spp|e?ssp|e?ss|e?sp|e?subsp|sube?species|biovar|biotype|serovar|serogr.?up|e?species)[.]*( |$|(complex|group)$))"
)
}
@ -786,7 +786,7 @@ print.mo_uncertainties <- function(x, ...) {
return(invisible(NULL))
}
cat(word_wrap("Matching scores are based on the resemblance between the input and the full taxonomic name, and the pathogenicity in humans according to Bartlett ", font_italic("et al."), " (2022). See `?mo_matching_score`.\n\n", add_fn = font_blue))
cat(word_wrap("Matching scores are based on the resemblance between the input and the full taxonomic name, and the pathogenicity in humans. See `?mo_matching_score`.\n\n", add_fn = font_blue))
if (has_colour()) {
cat(word_wrap("Colour keys: ",
font_red_bg(" 0.000-0.499 "),

15
R/mo_matching_score.R
View File

@ -44,13 +44,14 @@
#' where:
#'
#' * \eqn{x} is the user input;
#' * \ifelse{html}{\out{<i>n</i> is a taxonomic name (genus, species, and subspecies);}}{\eqn{n} is a taxonomic name (genus, species, and subspecies);}
#' * \ifelse{html}{\out{<i>l<sub>n</sub></i> is the length of <i>n</i>;}}{l_n is the length of \eqn{n};}
#' * \ifelse{html}{\out{<i>lev</i> is the <a href="https://en.wikipedia.org/wiki/Levenshtein_distance">Levenshtein distance function</a> (counting any insertion as 1, and any deletion or substitution as 2) that is needed to change <i>x</i> into <i>n</i>;}}{lev is the Levenshtein distance function (counting any insertion as 1, and any deletion or substitution as 2) that is needed to change \eqn{x} into \eqn{n};}
#' * \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.}
#' * \eqn{n} is a taxonomic name (genus, species, and subspecies);
#' * \eqn{l_n} is the length of \eqn{n};
#' * \ifelse{html}{\out{<i>lev</i> is the
#' * \eqn{lev} is the [Levenshtein distance function](https://en.wikipedia.org/wiki/Levenshtein_distance) (counting any insertion as 1, and any deletion or substitution as 2) that is needed to change \eqn{x} into \eqn{n};
#' * \eqn{p_{n}} is the human pathogenic prevalence group of \eqn{n}, as described below;
#' * \eqn{k_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 recent work from Bartlett *et al.* (2022, \doi{10.1099/mic.0.001269}) who extensively studied medical-scientific literature to categorise all bacterial species into these groups:
#' The grouping into human pathogenic prevalence \eqn{p} is based on recent work from Bartlett *et al.* (2022, \doi{10.1099/mic.0.001269}) who extensively studied medical-scientific literature to categorise all bacterial species into these groups:
#'
#' - **Established**, if a taxonomic species has infected at least three persons in three or more references. These records have `prevalence = 1.0` in the [microorganisms] data set;
#' - **Putative**, if a taxonomic species has fewer than three known cases. These records have `prevalence = 1.25` in the [microorganisms] data set.
@ -69,6 +70,8 @@
#' @export
#' @inheritSection AMR Reference Data Publicly Available
#' @examples
#' mo_reset_session()
#'
#' as.mo("E. coli")
#' mo_uncertainties()
#'

30
R/mo_property.R
View File

@ -36,31 +36,31 @@
#' @param ... other arguments passed on to [as.mo()], such as 'minimum_matching_score', 'ignore_pattern', and 'remove_from_input'
#' @param ab any (vector of) text that can be coerced to a valid antibiotic drug code with [as.ab()]
#' @param open browse the URL using [`browseURL()`][utils::browseURL()]
#' @details All functions will, at default, **not** keep old taxonomic properties, as synonyms are automatically replaced with the current taxonomy. Take for example *Escherichia blattae*, which was renamed to *Shimwellia blattae* in 2010:
#' - `mo_genus("Escherichia blattae")` will return `"Shemwellia"` (with a note about the renaming)
#' - `mo_genus("Escherichia blattae", keep_synonyms = TRUE)` will return `"Escherichia"` (with a warning that the name is outdated)
#' - `mo_ref("Escherichia blattae")` will return `"Priest et al., 2010"` (with a note)
#' - `mo_ref("Escherichia blattae", keep_synonyms = TRUE)` will return `"Burgess et al., 1973"` (with a warning)
#' @details All functions will, at default, **not** keep old taxonomic properties, as synonyms are automatically replaced with the current taxonomy. Take for example *Enterobacter aerogenes*, which was initially named in 1960 but renamed to *Klebsiella aerogenes* in 2017:
#' - `mo_genus("Enterobacter aerogenes")` will return `"Klebsiella"` (with a note about the renaming)
#' - `mo_genus("Enterobacter aerogenes", keep_synonyms = TRUE)` will return `"Enterobacter"` (with a once-per-session warning that the name is outdated)
#' - `mo_ref("Enterobacter aerogenes")` will return `"Tindall et al., 2017"` (with a note)
#' - `mo_ref("Enterobacter aerogenes", keep_synonyms = TRUE)` will return `"Hormaeche et al., 1960"` (with a warning)
#'
#' The short name ([mo_shortname()]) returns the first character of the genus and the full species, such as `"E. coli"`, for species and subspecies. 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"`.
#' The short name ([mo_shortname()]) returns the first character of the genus and the full species, such as `"E. coli"`, for species and subspecies. 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*. As a result, `mo_fullname(mo_shortname("Entamoeba coli"))` returns `"Escherichia coli"`.
#'
#' 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.
#'
#' Determination of human pathogenicity ([mo_pathogenicity()]) is strongly based on Bartlett *et al.* (2022, \doi{10.1099/mic.0.001269}). This function returns a [factor] with the levels *Pathogenic*, *Potentially pathogenic*, *Non-pathogenic*, and *Unknown*.
#'
#' Determination of the Gram stain ([mo_gramstain()]) will be based on the taxonomic kingdom and phylum. Originally, Cavalier-Smith defined the so-called subkingdoms Negibacteria and Posibacteria (2002, [PMID 11837318](https://pubmed.ncbi.nlm.nih.gov/11837318/)), and only considered these phyla as Posibacteria: Actinobacteria, Chloroflexi, Firmicutes, and Tenericutes. These phyla were renamed to Actinomycetota, Chloroflexota, Bacillota, and Mycoplasmatota (2021, [PMID 34694987](https://pubmed.ncbi.nlm.nih.gov/34694987/)). Bacteria in these phyla are considered Gram-positive in this `AMR` package, except for members of the class Negativicutes (within phylum Bacillota) which are Gram-negative. All other bacteria are 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` (or `NA` 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 the Gram stain ([mo_gramstain()]) will be based on the taxonomic kingdom and phylum. Originally, Cavalier-Smith defined the so-called subkingdoms Negibacteria and Posibacteria (2002, [PMID 11837318](https://pubmed.ncbi.nlm.nih.gov/11837318/)), and only considered these phyla as Posibacteria: Actinobacteria, Chloroflexi, Firmicutes, and Tenericutes. These phyla were later renamed to Actinomycetota, Chloroflexota, Bacillota, and Mycoplasmatota (2021, [PMID 34694987](https://pubmed.ncbi.nlm.nih.gov/34694987/)). Bacteria in these phyla are considered Gram-positive in this `AMR` package, except for members of the class Negativicutes (within phylum Bacillota) which are Gram-negative. All other bacteria are 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` (or `NA` 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 Ascomycota, class Saccharomycetes (also called Hemiascomycetes). *True yeasts* are aggregated into the underlying order Saccharomycetales. Thus, for all microorganisms that are member of the taxonomic class Saccharomycetes, the function will return `TRUE`. It returns `FALSE` otherwise (or `NA` when the input is `NA` or the MO code is `UNKNOWN`).
#'
#' Determination of intrinsic resistance ([mo_is_intrinsic_resistant()]) will be based on the [intrinsic_resistant] data set, which is based on `r format_eucast_version_nr(3.3)`. The [mo_is_intrinsic_resistant()] function can be vectorised over both argument `x` (input for microorganisms) and `ab` (input for antibiotics).
#'
#' 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 version of `r documentation_date(TAXONOMY_VERSION$SNOMED$accessed_date)`. See *Source* and the [microorganisms] data set for more info.
#'
#' Old taxonomic names (so-called 'synonyms') can be retrieved with [mo_synonyms()], the current taxonomic name can be retrieved with [mo_current()]. Both functions return full names.
#'
#' All output [will be translated][translate] where possible.
#' @section Matching Score for Microorganisms:
#' This function uses [as.mo()] internally, which uses an advanced algorithm to translate arbitrary user input to valid taxonomy using a so-called matching score. You can read about this public algorithm on the [MO matching score page][mo_matching_score()].
#' @inheritSection as.mo Source
@ -145,10 +145,10 @@
#'
#' # Lancefield classification, see ?as.mo ------------------------------------
#'
#' mo_fullname("S. pyo")
#' mo_fullname("S. pyo", Lancefield = TRUE)
#' mo_shortname("S. pyo")
#' mo_shortname("S. pyo", Lancefield = TRUE)
#' mo_fullname("Strep Group B")
#' mo_fullname("Strep Group B", Lancefield = TRUE)
#' mo_shortname("Strep Group B")
#' mo_shortname("Strep Group B", Lancefield = TRUE)
#'
#'
#' # language support --------------------------------------------------------
@ -158,8 +158,8 @@
#' mo_gramstain("Klebsiella pneumoniae", language = "es") # Spanish
#' mo_gramstain("Klebsiella pneumoniae", language = "el") # Greek
#' mo_gramstain("Klebsiella pneumoniae", language = "uk") # Ukrainian
#'
#' # mo_type is equal to mo_kingdom, but mo_kingdom will remain official
#'
#' # mo_type is equal to mo_kingdom, but mo_kingdom will remain untranslated
#' mo_kingdom("Klebsiella pneumoniae")
#' mo_type("Klebsiella pneumoniae")
#' mo_kingdom("Klebsiella pneumoniae", language = "zh") # Chinese, no effect