P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2024-12-26 18:46:13 +01:00
Code Releases Activity
82239503ee
AMR/man/mo_property.Rd

508 lines
20 KiB
R
Raw Blame History

% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/mo_property.R
\name{mo_property}
\alias{mo_property}
\alias{mo_name}
\alias{mo_fullname}
\alias{mo_shortname}
\alias{mo_subspecies}
\alias{mo_species}
\alias{mo_genus}
\alias{mo_family}
\alias{mo_order}
\alias{mo_class}
\alias{mo_phylum}
\alias{mo_kingdom}
\alias{mo_domain}
\alias{mo_type}
\alias{mo_status}
\alias{mo_pathogenicity}
\alias{mo_gramstain}
\alias{mo_is_gram_negative}
\alias{mo_is_gram_positive}
\alias{mo_is_yeast}
\alias{mo_is_intrinsic_resistant}
\alias{mo_oxygen_tolerance}
\alias{mo_is_anaerobic}
\alias{mo_snomed}
\alias{mo_ref}
\alias{mo_authors}
\alias{mo_year}
\alias{mo_lpsn}
\alias{mo_mycobank}
\alias{mo_gbif}
\alias{mo_rank}
\alias{mo_taxonomy}
\alias{mo_synonyms}
\alias{mo_current}
\alias{mo_group_members}
\alias{mo_info}
\alias{mo_url}
\title{Get Properties of a Microorganism}
\usage{
mo_name(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_fullname(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_shortname(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_subspecies(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_species(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_genus(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_family(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_order(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_class(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_phylum(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_kingdom(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_domain(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_type(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_status(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_pathogenicity(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_gramstain(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_is_gram_negative(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_is_gram_positive(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_is_yeast(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_is_intrinsic_resistant(
x,
ab,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_oxygen_tolerance(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_is_anaerobic(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_snomed(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_ref(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_authors(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_year(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_lpsn(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_mycobank(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_gbif(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_rank(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_taxonomy(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_synonyms(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_current(x, language = get_AMR_locale(), ...)
mo_group_members(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_info(
x,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_url(
x,
open = FALSE,
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
mo_property(
x,
property = "fullname",
language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
...
)
}
\arguments{
\item{x}{any \link{character} (vector) that can be coerced to a valid microorganism code with \code{\link[=as.mo]{as.mo()}}. Can be left blank for auto-guessing the column containing microorganism codes if used in a data set, see \emph{Examples}.}
\item{language}{language to translate text like "no growth", which defaults to the system language (see \code{\link[=get_AMR_locale]{get_AMR_locale()}})}
\item{keep_synonyms}{a \link{logical} to indicate if old, previously valid taxonomic names must be preserved and not be corrected to currently accepted names. The default is \code{FALSE}, which will return a note if old taxonomic names were processed. The default can be set with the \link[=AMR-options]{package option} \code{\link[=AMR-options]{AMR_keep_synonyms}}, i.e. \code{options(AMR_keep_synonyms = TRUE)} or \code{options(AMR_keep_synonyms = FALSE)}.}
\item{...}{other arguments passed on to \code{\link[=as.mo]{as.mo()}}, such as 'minimum_matching_score', 'ignore_pattern', and 'remove_from_input'}
\item{ab}{any (vector of) text that can be coerced to a valid antibiotic drug code with \code{\link[=as.ab]{as.ab()}}}
\item{open}{browse the URL using \code{\link[utils:browseURL]{browseURL()}}}
\item{property}{one of the column names of the \link{microorganisms} data set: "mo", "fullname", "status", "kingdom", "phylum", "class", "order", "family", "genus", "species", "subspecies", "rank", "ref", "oxygen_tolerance", "source", "lpsn", "lpsn_parent", "lpsn_renamed_to", "mycobank", "mycobank_parent", "mycobank_renamed_to", "gbif", "gbif_parent", "gbif_renamed_to", "prevalence", or "snomed", or must be \code{"shortname"}}
}
\value{
\itemize{
\item An \link{integer} in case of \code{\link[=mo_year]{mo_year()}}
\item An \link[=factor]{ordered factor} in case of \code{\link[=mo_pathogenicity]{mo_pathogenicity()}}
\item A \link{list} in case of \code{\link[=mo_taxonomy]{mo_taxonomy()}}, \code{\link[=mo_synonyms]{mo_synonyms()}}, \code{\link[=mo_snomed]{mo_snomed()}}, and \code{\link[=mo_info]{mo_info()}}
\item A \link{logical} in case of \code{\link[=mo_is_anaerobic]{mo_is_anaerobic()}}, \code{\link[=mo_is_gram_negative]{mo_is_gram_negative()}}, \code{\link[=mo_is_gram_positive]{mo_is_gram_positive()}}, \code{\link[=mo_is_intrinsic_resistant]{mo_is_intrinsic_resistant()}}, and \code{\link[=mo_is_yeast]{mo_is_yeast()}}
\item A named \link{character} in case of \code{\link[=mo_synonyms]{mo_synonyms()}} and \code{\link[=mo_url]{mo_url()}}
\item A \link{character} in all other cases
}
}
\description{
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 \code{\link[=as.mo]{as.mo()}}, which makes it possible to use microbial abbreviations, codes and names as input. See \emph{Examples}.
}
\details{
All functions will, at default, \strong{not} keep old taxonomic properties, as synonyms are automatically replaced with the current taxonomy. Take for example \emph{Enterobacter aerogenes}, which was initially named in 1960 but renamed to \emph{Klebsiella aerogenes} in 2017:
\itemize{
\item \code{mo_genus("Enterobacter aerogenes")} will return \code{"Klebsiella"} (with a note about the renaming)
\item \code{mo_genus("Enterobacter aerogenes", keep_synonyms = TRUE)} will return \code{"Enterobacter"} (with a once-per-session warning that the name is outdated)
\item \code{mo_ref("Enterobacter aerogenes")} will return \code{"Tindall et al., 2017"} (with a note about the renaming)
\item \code{mo_ref("Enterobacter aerogenes", keep_synonyms = TRUE)} will return \code{"Hormaeche et al., 1960"} (with a once-per-session warning that the name is outdated)
}
The short name (\code{\link[=mo_shortname]{mo_shortname()}}) returns the first character of the genus and the full species, such as \code{"E. coli"}, for species and subspecies. Exceptions are abbreviations of staphylococci (such as \emph{"CoNS"}, Coagulase-Negative Staphylococci) and beta-haemolytic streptococci (such as \emph{"GBS"}, Group B Streptococci). Please bear in mind that e.g. \emph{E. coli} could mean \emph{Escherichia coli} (kingdom of Bacteria) as well as \emph{Entamoeba coli} (kingdom of Protozoa). Returning to the full name will be done using \code{\link[=as.mo]{as.mo()}} internally, giving priority to bacteria and human pathogens, i.e. \code{"E. coli"} will be considered \emph{Escherichia coli}. As a result, \code{mo_fullname(mo_shortname("Entamoeba coli"))} returns \code{"Escherichia coli"}.
Since the top-level of the taxonomy is sometimes referred to as 'kingdom' and sometimes as 'domain', the functions \code{\link[=mo_kingdom]{mo_kingdom()}} and \code{\link[=mo_domain]{mo_domain()}} return the exact same results.
Determination of human pathogenicity (\code{\link[=mo_pathogenicity]{mo_pathogenicity()}}) is strongly based on Bartlett \emph{et al.} (2022, \doi{10.1099/mic.0.001269}). This function returns a \link{factor} with the levels \emph{Pathogenic}, \emph{Potentially pathogenic}, \emph{Non-pathogenic}, and \emph{Unknown}.
Determination of the Gram stain (\code{\link[=mo_gramstain]{mo_gramstain()}}) will be based on the taxonomic kingdom and phylum. Originally, Cavalier-Smith defined the so-called subkingdoms Negibacteria and Posibacteria (2002, \href{https://pubmed.ncbi.nlm.nih.gov/11837318/}{PMID 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, \href{https://pubmed.ncbi.nlm.nih.gov/34694987/}{PMID 34694987}). Bacteria in these phyla are considered Gram-positive in this \code{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 \code{NA}. Functions \code{\link[=mo_is_gram_negative]{mo_is_gram_negative()}} and \code{\link[=mo_is_gram_positive]{mo_is_gram_positive()}} always return \code{TRUE} or \code{FALSE} (or \code{NA} when the input is \code{NA} or the MO code is \code{UNKNOWN}), thus always return \code{FALSE} for species outside the taxonomic kingdom of Bacteria.
Determination of yeasts (\code{\link[=mo_is_yeast]{mo_is_yeast()}}) will be based on the taxonomic kingdom and class. \emph{Budding yeasts} are yeasts that reproduce asexually through a process called budding, where a new cell develops from a small protrusion on the parent cell. Taxonomically, these are members of the phylum Ascomycota, class Saccharomycetes (also called Hemiascomycetes) or Pichiomycetes. \emph{True yeasts} quite specifically refers to yeasts in the underlying order Saccharomycetales (such as \emph{Saccharomyces cerevisiae}). Thus, for all microorganisms that are member of the taxonomic class Saccharomycetes or Pichiomycetes, the function will return \code{TRUE}. It returns \code{FALSE} otherwise (or \code{NA} when the input is \code{NA} or the MO code is \code{UNKNOWN}).
Determination of intrinsic resistance (\code{\link[=mo_is_intrinsic_resistant]{mo_is_intrinsic_resistant()}}) will be based on the \link{intrinsic_resistant} data set, which is based on \href{https://www.eucast.org/expert_rules_and_expected_phenotypes}{'EUCAST Expert Rules' and 'EUCAST Intrinsic Resistance and Unusual Phenotypes' v3.3} (2021). The \code{\link[=mo_is_intrinsic_resistant]{mo_is_intrinsic_resistant()}} function can be vectorised over both argument \code{x} (input for microorganisms) and \code{ab} (input for antibiotics).
Determination of bacterial oxygen tolerance (\code{\link[=mo_oxygen_tolerance]{mo_oxygen_tolerance()}}) will be based on BacDive, see \emph{Source}. The function \code{\link[=mo_is_anaerobic]{mo_is_anaerobic()}} only returns \code{TRUE} if the oxygen tolerance is \code{"anaerobe"}, indicting an obligate anaerobic species or genus. It always returns \code{FALSE} for species outside the taxonomic kingdom of Bacteria.
The function \code{\link[=mo_url]{mo_url()}} will return the direct URL to the online database entry, which also shows the scientific reference of the concerned species. \href{https://www.mycobank.org}{This MycoBank URL} will be used for fungi wherever available , \href{https://www.mycobank.org}{this LPSN URL} for bacteria wherever available, and \href{https://www.gbif.org}{this GBIF link} otherwise.
SNOMED codes (\code{\link[=mo_snomed]{mo_snomed()}}) was last updated on July 16th, 2024. See \emph{Source} and the \link{microorganisms} data set for more info.
Old taxonomic names (so-called 'synonyms') can be retrieved with \code{\link[=mo_synonyms]{mo_synonyms()}} (which will have the scientific reference as \link[base:names]{name}), the current taxonomic name can be retrieved with \code{\link[=mo_current]{mo_current()}}. Both functions return full names.
All output \link[=translate]{will be translated} where possible.
}
\section{Matching Score for Microorganisms}{
This function uses \code{\link[=as.mo]{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 \link[=mo_matching_score]{MO matching score page}.
}
\section{Source}{
\itemize{
\item Berends MS \emph{et al.} (2022). \strong{AMR: An R Package for Working with Antimicrobial Resistance Data}. \emph{Journal of Statistical Software}, 104(3), 1-31; \doi{10.18637/jss.v104.i03}
\item Parte, AC \emph{et al.} (2020). \strong{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}. Accessed from \url{https://lpsn.dsmz.de} on June 24th, 2024.
\item Vincent, R \emph{et al} (2013). \strong{MycoBank gearing up for new horizons.} IMA Fungus, 4(2), 371-9; \doi{10.5598/imafungus.2013.04.02.16}. Accessed from \url{https://www.mycobank.org} on June 24th, 2024.
\item GBIF Secretariat (2023). GBIF Backbone Taxonomy. Checklist dataset \doi{10.15468/39omei}. Accessed from \url{https://www.gbif.org} on June 24th, 2024.
\item Reimer, LC \emph{et al.} (2022). \strong{\emph{BacDive} in 2022: the knowledge base for standardized bacterial and archaeal data.} Nucleic Acids Res., 50(D1):D741-D74; \doi{10.1093/nar/gkab961}. Accessed from \url{https://bacdive.dsmz.de} on July 16th, 2024.
\item Public Health Information Network Vocabulary Access and Distribution System (PHIN VADS). US Edition of SNOMED CT from 1 September 2020. Value Set Name 'Microorganism', OID 2.16.840.1.114222.4.11.1009 (v12). URL: \url{https://phinvads.cdc.gov}
\item Bartlett A \emph{et al.} (2022). \strong{A comprehensive list of bacterial pathogens infecting humans} \emph{Microbiology} 168:001269; \doi{10.1099/mic.0.001269}
}
}
\section{Reference Data Publicly Available}{
All data sets in this \code{AMR} package (about microorganisms, antibiotics, SIR interpretation, EUCAST rules, etc.) are publicly and freely available for download in the following formats: R, MS Excel, Apache Feather, Apache Parquet, SPSS, SAS, and Stata. We also provide tab-separated plain text files that are machine-readable and suitable for input in any software program, such as laboratory information systems. Please visit \href{https://msberends.github.io/AMR/articles/datasets.html}{our website for the download links}. The actual files are of course available on \href{https://github.com/msberends/AMR/tree/main/data-raw}{our GitHub repository}.
}
\examples{
# taxonomic tree -----------------------------------------------------------
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")
# full names and short names -----------------------------------------------
mo_name("Klebsiella pneumoniae")
mo_fullname("Klebsiella pneumoniae")
mo_shortname("Klebsiella pneumoniae")
# other properties ---------------------------------------------------------
mo_pathogenicity("Klebsiella pneumoniae")
mo_gramstain("Klebsiella pneumoniae")
mo_snomed("Klebsiella pneumoniae")
mo_type("Klebsiella pneumoniae")
mo_rank("Klebsiella pneumoniae")
mo_url("Klebsiella pneumoniae")
mo_is_yeast(c("Candida", "Trichophyton", "Klebsiella"))
mo_group_members(c("Streptococcus group A",
"Streptococcus group C",
"Streptococcus group G",
"Streptococcus group L"))
# scientific reference -----------------------------------------------------
mo_ref("Klebsiella aerogenes")
mo_authors("Klebsiella aerogenes")
mo_year("Klebsiella aerogenes")
mo_synonyms("Klebsiella aerogenes")
mo_lpsn("Klebsiella aerogenes")
mo_gbif("Klebsiella aerogenes")
mo_mycobank("Candida albicans")
mo_mycobank("Candida krusei")
mo_mycobank("Candida krusei", keep_synonyms = TRUE)
# abbreviations known in the field -----------------------------------------
mo_genus("MRSA")
mo_species("MRSA")
mo_shortname("VISA")
mo_gramstain("VISA")
mo_genus("EHEC")
mo_species("EIEC")
mo_name("UPEC")
# known subspecies ---------------------------------------------------------
mo_fullname("K. pneu rh")
mo_shortname("K. pneu rh")
\donttest{
# Becker classification, see ?as.mo ----------------------------------------
mo_fullname("Staph epidermidis")
mo_fullname("Staph epidermidis", Becker = TRUE)
mo_shortname("Staph epidermidis")
mo_shortname("Staph epidermidis", Becker = TRUE)
# Lancefield classification, see ?as.mo ------------------------------------
mo_fullname("Strep agalactiae")
mo_fullname("Strep agalactiae", Lancefield = TRUE)
mo_shortname("Strep agalactiae")
mo_shortname("Strep agalactiae", Lancefield = TRUE)
# language support --------------------------------------------------------
mo_gramstain("Klebsiella pneumoniae", language = "de") # German
mo_gramstain("Klebsiella pneumoniae", language = "nl") # Dutch
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 untranslated
mo_kingdom("Klebsiella pneumoniae")
mo_type("Klebsiella pneumoniae")
mo_kingdom("Klebsiella pneumoniae", language = "zh") # Chinese, no effect
mo_type("Klebsiella pneumoniae", language = "zh") # Chinese, translated
mo_fullname("S. pyogenes", Lancefield = TRUE, language = "de")
mo_fullname("S. pyogenes", Lancefield = TRUE, language = "uk")
# other --------------------------------------------------------------------
# gram stains and intrinsic resistance can be used as a filter in dplyr verbs
if (require("dplyr")) {
example_isolates \%>\%
filter(mo_is_gram_positive()) \%>\%
count(mo_genus(), sort = TRUE)
}
if (require("dplyr")) {
example_isolates \%>\%
filter(mo_is_intrinsic_resistant(ab = "vanco")) \%>\%
count(mo_genus(), sort = TRUE)
}
# get a list with the complete taxonomy (from kingdom to subspecies)
mo_taxonomy("Klebsiella pneumoniae")
# get a list with the taxonomy, the authors, Gram-stain,
# SNOMED codes, and URL to the online database
mo_info("Klebsiella pneumoniae")
}
}
\seealso{
Data set \link{microorganisms}
}
View Git Blame Copy Permalink