P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2026-06-25 04:16:25 +02:00
Code Releases Activity

(v3.0.1.9059) Update taxonomy of microorganisms

Browse Source
This commit is contained in:
Matthijs Berends
2026-06-23 01:38:13 +02:00
committed by GitHub
parent 0af3f84655
commit 3f9f931777
123 changed files with 121928 additions and 94162 deletions
Download Patch File Download Diff File Expand all files Collapse all files

73
man/mo_property.Rd
View File

@@ -24,6 +24,7 @@
\alias{mo_is_intrinsic_resistant}
\alias{mo_oxygen_tolerance}
\alias{mo_is_anaerobic}
\alias{mo_morphology}
\alias{mo_snomed}
\alias{mo_ref}
\alias{mo_authors}
@@ -86,7 +87,8 @@ 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), ...)
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
add_morphology = FALSE, ...)
mo_is_gram_negative(x, language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE), ...)
@@ -106,6 +108,9 @@ mo_oxygen_tolerance(x, language = get_AMR_locale(),
mo_is_anaerobic(x, language = get_AMR_locale(),
keep_synonyms = getOption("AMR_keep_synonyms", FALSE), ...)
mo_morphology(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), ...)
@@ -161,51 +166,59 @@ The default is \code{FALSE}, which will return a note if outdated taxonomic name
\item{...}{Other arguments passed on to \code{\link[=as.mo]{as.mo()}}, such as 'minimum_matching_score', 'ignore_pattern', and 'remove_from_input'.}
\item{add_morphology}{a \link{logical} to indicate whether the morphology (from \code{\link[=mo_morphology]{mo_morphology()}}) should be added to the Gram stain result, e.g. \code{"Gram-negative rods"} instead of \code{"Gram-negative"}. The default is \code{FALSE}.}
\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: \code{"mo"}, \code{"fullname"}, \code{"status"}, \code{"kingdom"}, \code{"phylum"}, \code{"class"}, \code{"order"}, \code{"family"}, \code{"genus"}, \code{"species"}, \code{"subspecies"}, \code{"rank"}, \code{"ref"}, \code{"oxygen_tolerance"}, \code{"source"}, \code{"lpsn"}, \code{"lpsn_parent"}, \code{"lpsn_renamed_to"}, \code{"mycobank"}, \code{"mycobank_parent"}, \code{"mycobank_renamed_to"}, \code{"gbif"}, \code{"gbif_parent"}, \code{"gbif_renamed_to"}, \code{"prevalence"}, or \code{"snomed"}, or must be \code{"shortname"}.}
\item{property}{One of the column names of the \link{microorganisms} data set: \code{"mo"}, \code{"fullname"}, \code{"status"}, \code{"domain"}, \code{"kingdom"}, \code{"phylum"}, \code{"class"}, \code{"order"}, \code{"family"}, \code{"genus"}, \code{"species"}, \code{"subspecies"}, \code{"rank"}, \code{"ref"}, \code{"oxygen_tolerance"}, \code{"morphology"}, \code{"source"}, \code{"lpsn"}, \code{"lpsn_parent"}, \code{"lpsn_renamed_to"}, \code{"mycobank"}, \code{"mycobank_parent"}, \code{"mycobank_renamed_to"}, \code{"gbif"}, \code{"gbif_parent"}, \code{"gbif_renamed_to"}, \code{"prevalence"}, or \code{"snomed"}, or must be \code{"shortname"}.}
}
\value{
- An [integer] in case of [mo_year()]
- An [ordered factor][factor] in case of [mo_pathogenicity()]
- A [list] in case of [mo_taxonomy()], [mo_synonyms()], [mo_snomed()], and [mo_info()]
- A [logical] in case of [mo_is_anaerobic()], [mo_is_gram_negative()], [mo_is_gram_positive()], [mo_is_intrinsic_resistant()], and [mo_is_yeast()]
- A named [character] in case of [mo_synonyms()] and [mo_url()]
- A [character] in all other cases
\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, **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 about the renaming)
- `mo_ref("Enterobacter aerogenes", keep_synonyms = TRUE)` will return `"Hormaeche et al., 1960"` (with a once-per-session warning that the name is outdated)
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 ([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"`.
\code{\link[=mo_ref]{mo_ref()}} returns the abbreviated authority of the nomenclatural act that created the queried name combination. When \code{keep_synonyms = FALSE} (default), this is the authority of the currently accepted name. When \code{keep_synonyms = TRUE}, this is the authority under which the queried (possibly outdated) name was published. Emendations (changes to the species description without a name change) are not reflected; only the combination or original description authority is returned.
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 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 always be considered \emph{Escherichia coli}. As a result, \code{mo_fullname(mo_shortname("Entamoeba coli"))} returns \code{"Escherichia coli"}.
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*.
Following the formal introduction of the new kingdom rank into prokaryotic nomenclature by G"{o}ker and Oren (2024, \doi{10.1099/ijsem.0.006242}), \code{\link[=mo_kingdom]{mo_kingdom()}} and \code{\link[=mo_domain]{mo_domain()}} return different results for bacteria and archaea: \code{\link[=mo_kingdom]{mo_kingdom()}} returns the new formal kingdom (e.g. "Pseudomonadati", "Bacillati"), while \code{\link[=mo_domain]{mo_domain()}} returns the new domain (e.g. "Bacteria", "Archaea"). For non-prokaryotic organisms, both functions return identical results.
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 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 yeasts ([mo_is_yeast()]) will be based on the taxonomic kingdom and class. *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. *True yeasts* quite specifically refers to yeasts in the underlying order Saccharomycetales (such as *Saccharomyces cerevisiae*). Thus, for all microorganisms that are member of the taxonomic class Saccharomycetes or Pichiomycetes, the function will return `TRUE`. It returns `FALSE` otherwise (or `NA` when the input is `NA` or the MO code is `UNKNOWN`).
Determination of the Gram stain (\code{\link[=mo_gramstain]{mo_gramstain()}} is 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 intrinsic resistance ([mo_is_intrinsic_resistant()]) will be based on the [intrinsic_resistant] data set, which is based on `r format_eucast_version_nr(names(EUCAST_VERSION_EXPECTED_PHENOTYPES[1]))`. The [mo_is_intrinsic_resistant()] function can be vectorised over both argument `x` (input for microorganisms) and `ab` (input for antimicrobials).
Determination of yeasts (\code{\link[=mo_is_yeast]{mo_is_yeast()}}) is 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 bacterial oxygen tolerance ([mo_oxygen_tolerance()]) will be based on BacDive, see *Source*. The function [mo_is_anaerobic()] only returns `TRUE` if the oxygen tolerance is `"anaerobe"`, indicting an obligate anaerobic species or genus. It always returns `FALSE` for species outside the taxonomic kingdom of Bacteria.
Determination of intrinsic resistance (\code{\link[=mo_is_intrinsic_resistant]{mo_is_intrinsic_resistant()}}) is based on the \link{intrinsic_resistant} data set, which is based on \href{https://www.eucast.org/bacteria/important-additional-information/expert-rules/}{'EUCAST Expected Resistant Phenotypes' v1.2} (2023). 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 antimicrobials).
The function [mo_url()] will return the direct URL to the online database entry, which also shows the scientific reference of the concerned species. [This MycoBank URL](`r TAXONOMY_VERSION$MycoBank$url`) will be used for fungi wherever available , [this LPSN URL](`r TAXONOMY_VERSION$MycoBank$url`) for bacteria wherever available, and [this GBIF link](`r TAXONOMY_VERSION$GBIF$url`) otherwise.
Determination of both bacterial oxygen tolerance (\code{\link[=mo_oxygen_tolerance]{mo_oxygen_tolerance()}}) and morphology (\code{\link[=mo_morphology]{mo_morphology()}}) are 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"}, indicating an obligate anaerobic species or genus. It always returns \code{FALSE} for species outside the taxonomic kingdom of Bacteria.
SNOMED codes ([mo_snomed()]) was last updated on `r documentation_date(TAXONOMY_VERSION$SNOMED$accessed_date)`. See *Source* and the [microorganisms] data set for more info.
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} is 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.
Old taxonomic names (so-called 'synonyms') can be retrieved with [mo_synonyms()] (which will have the scientific reference as [name][base::names()]), the current taxonomic name can be retrieved with [mo_current()]. Both functions return full names.
SNOMED codes (\code{\link[=mo_snomed]{mo_snomed()}}) was last updated on 16th of July, 2024. See \emph{Source} and the \link{microorganisms} data set for more info.
All output [will be translated][translate] where possible.
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}{
@@ -216,10 +229,10 @@ This function uses \code{\link[=as.mo]{as.mo()}} internally, which uses an advan
\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 Freese, HM \emph{et al.} (2026). \strong{TYGS and LPSN in 2025: a Global Core Biodata Resource for genome-based classification and nomenclature of prokaryotes within DSMZ Digital Diversity.} Nucleic Acids Research, 54, D884–D891; \doi{10.1093/nar/gkaf1110}. Accessed from \url{https://lpsn.dsmz.de} on 7th of May, 2026.
\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 7th of May, 2026.
\item Banki, O. \emph{et al.} (2026). Catalogue of Life (2026-04-18 XR). Catalogue of Life Foundation, Amsterdam, Netherlands. \doi{10.48580/dgxjw}. Accessed from \url{https://www.gbif.org} on 7th of May, 2026.
\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 7th of May, 2026.
\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://www.cdc.gov/phin/php/phinvads/}
\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}
}
@@ -256,8 +269,10 @@ mo_shortname("Klebsiella pneumoniae")
# other properties ---------------------------------------------------------
mo_pathogenicity("Klebsiella pneumoniae")
mo_morphology("Klebsiella pneumoniae")
mo_gramstain("Klebsiella pneumoniae")
mo_gramstain("Klebsiella pneumoniae", add_morphology = TRUE)
mo_pathogenicity("Klebsiella pneumoniae")
mo_snomed("Klebsiella pneumoniae")
mo_type("Klebsiella pneumoniae")
mo_rank("Klebsiella pneumoniae")