mirror of https://github.com/msberends/AMR.git
216 lines
18 KiB
R
216 lines
18 KiB
R
% Generated by roxygen2: do not edit by hand
|
|
% Please edit documentation in R/mo.R
|
|
\name{as.mo}
|
|
\alias{as.mo}
|
|
\alias{mo}
|
|
\alias{is.mo}
|
|
\alias{mo_uncertainties}
|
|
\alias{mo_renamed}
|
|
\alias{mo_failures}
|
|
\alias{mo_reset_session}
|
|
\alias{mo_cleaning_regex}
|
|
\title{Transform Input to a Microorganism Code}
|
|
\usage{
|
|
as.mo(
|
|
x,
|
|
Becker = FALSE,
|
|
Lancefield = FALSE,
|
|
minimum_matching_score = NULL,
|
|
keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
|
|
reference_df = get_mo_source(),
|
|
ignore_pattern = getOption("AMR_ignore_pattern", NULL),
|
|
remove_from_input = mo_cleaning_regex(),
|
|
language = get_AMR_locale(),
|
|
info = interactive(),
|
|
...
|
|
)
|
|
|
|
is.mo(x)
|
|
|
|
mo_uncertainties()
|
|
|
|
mo_renamed()
|
|
|
|
mo_failures()
|
|
|
|
mo_reset_session()
|
|
|
|
mo_cleaning_regex()
|
|
}
|
|
\arguments{
|
|
\item{x}{a \link{character} vector or a \link{data.frame} with one or two columns}
|
|
|
|
\item{Becker}{a \link{logical} to indicate whether staphylococci should be categorised into coagulase-negative staphylococci ("CoNS") and coagulase-positive staphylococci ("CoPS") instead of their own species, according to Karsten Becker \emph{et al.} (see Source).
|
|
|
|
This excludes \emph{Staphylococcus aureus} at default, use \code{Becker = "all"} to also categorise \emph{S. aureus} as "CoPS".}
|
|
|
|
\item{Lancefield}{a \link{logical} to indicate whether a beta-haemolytic \emph{Streptococcus} should be categorised into Lancefield groups instead of their own species, according to Rebecca C. Lancefield (see Source). These streptococci will be categorised in their first group, e.g. \emph{Streptococcus dysgalactiae} will be group C, although officially it was also categorised into groups G and L.
|
|
|
|
This excludes enterococci at default (who are in group D), use \code{Lancefield = "all"} to also categorise all enterococci as group D.}
|
|
|
|
\item{minimum_matching_score}{a numeric value to set as the lower limit for the \link[=mo_matching_score]{MO matching score}. When left blank, this will be determined automatically based on the character length of \code{x}, its \link[=microorganisms]{taxonomic kingdom} and \link[=mo_matching_score]{human pathogenicity}.}
|
|
|
|
\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 \code{options(AMR_keep_synonyms = TRUE)} or \code{options(AMR_keep_synonyms = FALSE)}.}
|
|
|
|
\item{reference_df}{a \link{data.frame} to be used for extra reference when translating \code{x} to a valid \code{\link{mo}}. See \code{\link[=set_mo_source]{set_mo_source()}} and \code{\link[=get_mo_source]{get_mo_source()}} to automate the usage of your own codes (e.g. used in your analysis or organisation).}
|
|
|
|
\item{ignore_pattern}{a \link[base:regex]{regular expression} (case-insensitive) of which all matches in \code{x} must return \code{NA}. This can be convenient to exclude known non-relevant input and can also be set with the option \code{AMR_ignore_pattern}, e.g. \code{options(AMR_ignore_pattern = "(not reported|contaminated flora)")}.}
|
|
|
|
\item{remove_from_input}{a \link[base:regex]{regular expression} (case-insensitive) to clean the input of \code{x}. Everything matched in \code{x} will be removed. At default, this is the outcome of \code{\link[=mo_cleaning_regex]{mo_cleaning_regex()}}, which removes texts between brackets and texts such as "species" and "serovar".}
|
|
|
|
\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{info}{a \link{logical} to indicate if a progress bar should be printed if more than 25 items are to be coerced, defaults to \code{TRUE} only in interactive mode}
|
|
|
|
\item{...}{other arguments passed on to functions}
|
|
}
|
|
\value{
|
|
A \link{character} \link{vector} with additional class \code{\link{mo}}
|
|
}
|
|
\description{
|
|
Use this function to determine a valid microorganism code (\code{\link{mo}}). Determination is done using intelligent rules and the complete taxonomic kingdoms Animalia, Archaea, Bacteria and Protozoa, and most microbial species from the kingdom Fungi (see \emph{Source}). The input can be almost anything: a full name (like \code{"Staphylococcus aureus"}), an abbreviated name (such as \code{"S. aureus"}), an abbreviation known in the field (such as \code{"MRSA"}), or just a genus. See \emph{Examples}.
|
|
}
|
|
\details{
|
|
A microorganism (MO) code from this package (class: \code{\link{mo}}) is human readable and typically looks like these examples:
|
|
|
|
\if{html}{\out{<div class="sourceCode">}}\preformatted{ Code Full name
|
|
--------------- --------------------------------------
|
|
B_KLBSL Klebsiella
|
|
B_KLBSL_PNMN Klebsiella pneumoniae
|
|
B_KLBSL_PNMN_RHNS Klebsiella pneumoniae rhinoscleromatis
|
|
| | | |
|
|
| | | |
|
|
| | | \\---> subspecies, a 3-5 letter acronym
|
|
| | \\----> species, a 3-6 letter acronym
|
|
| \\----> genus, a 4-8 letter acronym
|
|
\\----> taxonomic kingdom: A (Archaea), AN (Animalia), B (Bacteria),
|
|
F (Fungi), PL (Plantae), P (Protozoa)
|
|
}\if{html}{\out{</div>}}
|
|
|
|
Values that cannot be coerced will be considered 'unknown' and will be returned as the MO code \code{UNKNOWN} with a warning.
|
|
|
|
Use the \code{\link[=mo_property]{mo_*}} functions to get properties based on the returned code, see \emph{Examples}.
|
|
|
|
The \code{\link[=as.mo]{as.mo()}} function uses a novel \link[=mo_matching_score]{matching score algorithm} (see \emph{Matching Score for Microorganisms} below) to match input against the \link[=microorganisms]{available microbial taxonomy} in this package. This will lead to the effect that e.g. \code{"E. coli"} (a microorganism highly prevalent in humans) will return the microbial ID of \emph{Escherichia coli} and not \emph{Entamoeba coli} (a microorganism less prevalent in humans), although the latter would alphabetically come first. The algorithm uses data from the List of Prokaryotic names with Standing in Nomenclature (LPSN) and the Global Biodiversity Information Facility (GBIF) (see \link{microorganisms}).
|
|
\subsection{Coping with Uncertain Results}{
|
|
|
|
Results of non-exact taxonomic input are based on their \link[=mo_matching_score]{matching score}. The lowest allowed score can be set with the \code{minimum_matching_score} argument. At default this will be determined based on the character length of the input, and the \link[=microorganisms]{taxonomic kingdom} and \link[=mo_matching_score]{human pathogenicity} of the taxonomic outcome. If values are matched with uncertainty, a message will be shown to suggest the user to evaluate the results with \code{\link[=mo_uncertainties]{mo_uncertainties()}}, which returns a \link{data.frame} with all specifications.
|
|
|
|
To increase the quality of matching, the \code{remove_from_input} argument can be used to clean the input (i.e., \code{x}). This must be a \link[base:regex]{regular expression} that matches parts of the input that should be removed before the input is matched against the \link[=microorganisms]{available microbial taxonomy}. It will be matched Perl-compatible and case-insensitive. The default value of \code{remove_from_input} is the outcome of the helper function \code{\link[=mo_cleaning_regex]{mo_cleaning_regex()}}.
|
|
|
|
There are three helper functions that can be run after using the \code{\link[=as.mo]{as.mo()}} function:
|
|
\itemize{
|
|
\item Use \code{\link[=mo_uncertainties]{mo_uncertainties()}} to get a \link{data.frame} that prints in a pretty format with all taxonomic names that were guessed. The output contains the matching score for all matches (see \emph{Matching Score for Microorganisms} below).
|
|
\item Use \code{\link[=mo_failures]{mo_failures()}} to get a \link{character} \link{vector} with all values that could not be coerced to a valid value.
|
|
\item Use \code{\link[=mo_renamed]{mo_renamed()}} to get a \link{data.frame} with all values that could be coerced based on old, previously accepted taxonomic names.
|
|
}
|
|
}
|
|
|
|
\subsection{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 \code{prevalence} columns in the \link{microorganisms} data set. The grouping into human pathogenic prevalence is explained in the section \emph{Matching Score for Microorganisms} below.
|
|
}
|
|
}
|
|
\section{Source}{
|
|
|
|
\enumerate{
|
|
\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 Becker K \emph{et al.} (2014). \strong{Coagulase-Negative Staphylococci.} \emph{Clin Microbiol Rev.} 27(4): 870-926; \doi{10.1128/CMR.00109-13}
|
|
\item Becker K \emph{et al.} (2019). \strong{Implications of identifying the recently defined members of the \emph{S. aureus} complex, \emph{S. argenteus} and \emph{S. schweitzeri}: A position paper of members of the ESCMID Study Group for staphylococci and Staphylococcal Diseases (ESGS).} \emph{Clin Microbiol Infect}; \doi{10.1016/j.cmi.2019.02.028}
|
|
\item Becker K \emph{et al.} (2020). \strong{Emergence of coagulase-negative staphylococci} \emph{Expert Rev Anti Infect Ther.} 18(4):349-366; \doi{10.1080/14787210.2020.1730813}
|
|
\item Lancefield RC (1933). \strong{A serological differentiation of human and other groups of hemolytic streptococci}. \emph{J Exp Med.} 57(4): 571-95; \doi{10.1084/jem.57.4.571}
|
|
\item Berends MS \emph{et al.} (2022). \strong{Trends in Occurrence and Phenotypic Resistance of Coagulase-Negative Staphylococci (CoNS) Found in Human Blood in the Northern Netherlands between 2013 and 2019} \emph{Microorganisms} 10(9), 1801; \doi{10.3390/microorganisms10091801}
|
|
\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 11 December, 2022.
|
|
\item GBIF Secretariat (2022). GBIF Backbone Taxonomy. Checklist dataset \doi{10.15468/39omei}. Accessed from \url{https://www.gbif.org} on 11 December, 2022.
|
|
\item Public Health Information Network Vocabulary Access and Distribution System (PHIN VADS). US Edition of SNOMED CT from 1 September 2020. Value Set Name 'Microoganism', 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{Matching Score for Microorganisms}{
|
|
|
|
With ambiguous user input in \code{\link[=as.mo]{as.mo()}} and all the \code{\link[=mo_property]{mo_*}} functions, the returned results are chosen based on their matching score using \code{\link[=mo_matching_score]{mo_matching_score()}}. This matching score \eqn{m}, is calculated as:
|
|
|
|
\ifelse{latex}{\deqn{m_{(x, n)} = \frac{l_{n} - 0.5 \cdot \min \begin{cases}l_{n} \\ \textrm{lev}(x, n)\end{cases}}{l_{n} \cdot p_{n} \cdot k_{n}}}}{\ifelse{html}{\figure{mo_matching_score.png}{options: width="300" alt="mo matching score"}}{m(x, n) = ( l_n * min(l_n, lev(x, n) ) ) / ( l_n * p_n * k_n )}}
|
|
|
|
where:
|
|
\itemize{
|
|
\item \ifelse{html}{\out{<i>x</i> is the user input;}}{\eqn{x} is the user input;}
|
|
\item \ifelse{html}{\out{<i>n</i> is a taxonomic name (genus, species, and subspecies);}}{\eqn{n} is a taxonomic name (genus, species, and subspecies);}
|
|
\item \ifelse{html}{\out{<i>l<sub>n</sub></i> is the length of <i>n</i>;}}{l_n is the length of \eqn{n};}
|
|
\item \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};}
|
|
\item \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;}
|
|
\item \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.}
|
|
}
|
|
|
|
The grouping into human pathogenic prevalence (\eqn{p}) is based on recent work from Bartlett \emph{et al.} (2022, \doi{10.1099/mic.0.001269}) who extensively studied medical-scientific literature to categorise all bacterial species into these groups:
|
|
\itemize{
|
|
\item \strong{Established}, if a taxonomic species has infected at least three persons in three or more references. These records have \code{prevalence = 1.0} in the \link{microorganisms} data set;
|
|
\item \strong{Putative}, if a taxonomic species has fewer than three known cases. These records have \code{prevalence = 1.25} in the \link{microorganisms} data set.
|
|
}
|
|
|
|
Furthermore,
|
|
\itemize{
|
|
\item Any genus present in the \strong{established} list also has \code{prevalence = 1.0} in the \link{microorganisms} data set;
|
|
\item Any other genus present in the \strong{putative} list has \code{prevalence = 1.25} in the \link{microorganisms} data set;
|
|
\item Any other species or subspecies of which the genus is present in the two aforementioned groups, has \code{prevalence = 1.5} in the \link{microorganisms} data set;
|
|
\item Any \emph{non-bacterial} genus, species or subspecies of which the genus is present in the following list, has \code{prevalence = 1.5} in the \link{microorganisms} data set: \emph{Absidia}, \emph{Acanthamoeba}, \emph{Acremonium}, \emph{Aedes}, \emph{Alternaria}, \emph{Amoeba}, \emph{Ancylostoma}, \emph{Angiostrongylus}, \emph{Anisakis}, \emph{Anopheles}, \emph{Apophysomyces}, \emph{Aspergillus}, \emph{Aureobasidium}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Blastomyces}, \emph{Candida}, \emph{Capillaria}, \emph{Chaetomium}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Contracaecum}, \emph{Cordylobia}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Demodex}, \emph{Dermatobia}, \emph{Dientamoeba}, \emph{Diphyllobothrium}, \emph{Dirofilaria}, \emph{Echinostoma}, \emph{Entamoeba}, \emph{Enterobius}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Fasciola}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Giardia}, \emph{Haloarcula}, \emph{Halobacterium}, \emph{Halococcus}, \emph{Hendersonula}, \emph{Heterophyes}, \emph{Histomonas}, \emph{Histoplasma}, \emph{Hymenolepis}, \emph{Hypomyces}, \emph{Hysterothylacium}, \emph{Leishmania}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Metagonimus}, \emph{Meyerozyma}, \emph{Microsporidium}, \emph{Microsporum}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Necator}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oesophagostomum}, \emph{Oidiodendron}, \emph{Opisthorchis}, \emph{Pediculus}, \emph{Phlebotomus}, \emph{Phoma}, \emph{Pichia}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Pneumocystis}, \emph{Pseudallescheria}, \emph{Pseudoterranova}, \emph{Pulex}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Saccharomyces}, \emph{Sarcoptes}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium}, \emph{Spirometra}, \emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Strongyloides}, \emph{Syngamus}, \emph{Taenia}, \emph{Toxocara}, \emph{Trichinella}, \emph{Trichobilharzia}, \emph{Trichoderma}, \emph{Trichomonas}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Trichostrongylus}, \emph{Trichuris}, \emph{Tritirachium}, \emph{Trombicula}, \emph{Trypanosoma}, \emph{Tunga} or \emph{Wuchereria};
|
|
\item All other records have \code{prevalence = 2.0} in the \link{microorganisms} data set.
|
|
}
|
|
|
|
When calculating the matching score, all characters in \eqn{x} and \eqn{n} are ignored that are other than A-Z, a-z, 0-9, spaces and parentheses.
|
|
|
|
All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., \code{"E. coli"} will return the microbial ID of \emph{Escherichia coli} (\eqn{m = 0.688}, a highly prevalent microorganism found in humans) and not \emph{Entamoeba coli} (\eqn{m = 0.159}, a less prevalent microorganism in humans), although the latter would alphabetically come first.
|
|
}
|
|
|
|
\section{Reference Data Publicly Available}{
|
|
|
|
All data sets in this \code{AMR} package (about microorganisms, antibiotics, R/SI 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{
|
|
\donttest{
|
|
# These examples all return "B_STPHY_AURS", the ID of S. aureus:
|
|
as.mo(c(
|
|
"sau", # WHONET code
|
|
"stau",
|
|
"STAU",
|
|
"staaur",
|
|
"S. aureus",
|
|
"S aureus",
|
|
"Sthafilokkockus aureus", # handles incorrect spelling
|
|
"Staphylococcus aureus (MRSA)",
|
|
"MRSA", # Methicillin Resistant S. aureus
|
|
"VISA", # Vancomycin Intermediate S. aureus
|
|
"VRSA", # Vancomycin Resistant S. aureus
|
|
115329001 # SNOMED CT code
|
|
))
|
|
|
|
# Dyslexia is no problem - these all work:
|
|
as.mo(c(
|
|
"Ureaplasma urealyticum",
|
|
"Ureaplasma urealyticus",
|
|
"Ureaplasmium urealytica",
|
|
"Ureaplazma urealitycium"
|
|
))
|
|
|
|
as.mo("Streptococcus group A")
|
|
|
|
as.mo("S. epidermidis") # will remain species: B_STPHY_EPDR
|
|
as.mo("S. epidermidis", Becker = TRUE) # will not remain species: B_STPHY_CONS
|
|
|
|
as.mo("S. pyogenes") # will remain species: B_STRPT_PYGN
|
|
as.mo("S. pyogenes", Lancefield = TRUE) # will not remain species: B_STRPT_GRPA
|
|
|
|
# All mo_* functions use as.mo() internally too (see ?mo_property):
|
|
mo_genus("E. coli")
|
|
mo_gramstain("ESCO")
|
|
mo_is_intrinsic_resistant("ESCCOL", ab = "vanco")
|
|
}
|
|
}
|
|
\seealso{
|
|
\link{microorganisms} for the \link{data.frame} that is being used to determine ID's.
|
|
|
|
The \code{\link[=mo_property]{mo_*}} functions (such as \code{\link[=mo_genus]{mo_genus()}}, \code{\link[=mo_gramstain]{mo_gramstain()}}) to get properties based on the returned code.
|
|
}
|