P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2025-07-09 15:01:51 +02:00
Code Releases Activity

added mo_shortname

Browse Source
This commit is contained in:
dr. M.S. (Matthijs) Berends
2018-09-05 10:51:46 +02:00
parent 790bd1622d
commit e39a9a8b05
8 changed files with 88 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
R/mo.R
View File

@ -18,7 +18,7 @@
#' Transform to microorganism ID
#'
#' Use this function to determine a valid ID based on a genus (and species). This input can be a full name (like \code{"Staphylococcus aureus"}), an abbreviated name (like \code{"S. aureus"}), or just a genus. You could also \code{\link{select}} a genus and species column, zie Examples.
#' Use this function to determine a valid ID based on a genus (and species). Determination is done using Artificial Intelligence (AI), so the input can be almost anything: a full name (like \code{"Staphylococcus aureus"}), an abbreviated name (like \code{"S. aureus"}), an abbreviation known in the field (like \code{"MRSA"}), or just a genus. You could also \code{\link{select}} a genus and species column, zie Examples.
#' @param x a character vector or a \code{data.frame} with one or two columns
#' @param Becker a logical to indicate whether \emph{Staphylococci} should be categorised into Coagulase Negative \emph{Staphylococci} ("CoNS") and Coagulase Positive \emph{Staphylococci} ("CoPS") instead of their own species, according to Karsten Becker \emph{et al.} [1].
#'
@ -37,6 +37,7 @@
#' \itemize{
#' \item{\code{"E. coli"} will return the ID of \emph{Escherichia coli} and not \emph{Entamoeba coli}, although the latter would alphabetically come first}
#' \item{\code{"H. influenzae"} will return the ID of \emph{Haemophilus influenzae} and not \emph{Haematobacter influenzae}}
#' \item{Something like \code{"s pyo"} will return the ID of \emph{Streptococcus pyogenes} and not \emph{Actinomyes pyogenes}}
#' \item{Something like \code{"p aer"} will return the ID of \emph{Pseudomonas aeruginosa} and not \emph{Pasteurella aerogenes}}
#' \item{Something like \code{"stau"} or \code{"staaur"} will return the ID of \emph{Staphylococcus aureus} and not \emph{Staphylococcus auricularis}}
#' }
@ -62,6 +63,10 @@
#' as.mo("VISA") # Vancomycin Intermediate S. aureus
#' as.mo("VRSA") # Vancomycin Resistant S. aureus
#'
#' as.mo("Streptococcus group A")
#' as.mo("GAS") # Group A Streptococci
#' as.mo("GBS") # Group B Streptococci
#'
#' # guess_mo is an alias of as.mo and works the same
#' guess_mo("S. epidermidis") # will remain species: STAEPI
#' guess_mo("S. epidermidis", Becker = TRUE) # will not remain species: STACNS
@ -172,6 +177,11 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
x[i] <- 'STAAUR'
next
}
if (tolower(x[i]) == '^s.*pyo$') {
# avoid detection of Actinomyces pyogenes in case of Streptococcus pyogenes
x[i] <- 'STCPYO'
next
}
if (tolower(x[i]) == '^p.*aer$') {
# avoid detection of Pasteurella aerogenes in case of Pseudomonas aeruginosa
x[i] <- 'PSEAER'
@ -192,7 +202,7 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
next
}
# translate known trivial names to genus+species
# translate known trivial abbreviations to genus+species
if (!is.na(x_trimmed[i])) {
if (toupper(x_trimmed[i]) == 'MRSA'
| toupper(x_trimmed[i]) == 'VISA'
@ -218,6 +228,10 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
x[i] <- 'STCPNE'
next
}
if (toupper(x_trimmed[i]) %like% '^G[ABCDFHK]S$') {
x[i] <- gsub("G([ABCDFHK])S", "STCGR\\1", x_trimmed[i])
next
}
}
# try any match keeping spaces