mirror of
https://github.com/msberends/AMR.git
synced 2025-08-27 17:02:12 +02:00
first inclusion of ITIS data
This commit is contained in:
46
R/data.R
46
R/data.R
@@ -120,30 +120,48 @@
|
||||
#
|
||||
"antibiotics"
|
||||
|
||||
#' Data set with human pathogenic microorganisms
|
||||
#' Data set with taxonomic data from ITIS
|
||||
#'
|
||||
#' A data set containing (potential) human pathogenic microorganisms. MO codes can be looked up using \code{\link{guess_mo}}.
|
||||
#' @format A \code{\link{tibble}} with 2,642 observations and 14 variables:
|
||||
#' A data set containing the complete microbial taxonomy of the kingdoms Bacteria, Fungi and Protozoa. MO codes can be looked up using \code{\link{as.mo}}.
|
||||
#' @inheritSection as.mo ITIS
|
||||
#' @format A \code{\link{data.frame}} with 18,831 observations and 15 variables:
|
||||
#' \describe{
|
||||
#' \item{\code{mo}}{ID of microorganism}
|
||||
#' \item{\code{bactsys}}{Bactsyscode of microorganism}
|
||||
#' \item{\code{genus}}{Genus name of microorganism, like \code{"Echerichia"}}
|
||||
#' \item{\code{species}}{Species name of microorganism, like \code{"coli"}}
|
||||
#' \item{\code{subspecies}}{Subspecies name of bio-/serovar of microorganism, like \code{"EHEC"}}
|
||||
#' \item{\code{fullname}}{Full name, like \code{"Echerichia coli (EHEC)"}}
|
||||
#' \item{\code{gramstain}}{Gram of microorganism, like \code{"Negative rods"}}
|
||||
#' \item{\code{aerobic}}{Logical whether bacteria is aerobic}
|
||||
#' \item{\code{tsn}}{Taxonomic Serial Number (TSN), as defined by ITIS}
|
||||
#' \item{\code{genus}}{Taxonomic genus of the microorganism as found in ITIS, see Source}
|
||||
#' \item{\code{species}}{Taxonomic species of the microorganism as found in ITIS, see Source}
|
||||
#' \item{\code{subspecies}}{Taxonomic subspecies of the microorganism as found in ITIS, see Source}
|
||||
#' \item{\code{fullname}}{Full name, like \code{"Echerichia coli"}}
|
||||
#' \item{\code{family}}{Taxonomic family of the microorganism as found in ITIS, see Source}
|
||||
#' \item{\code{order}}{Taxonomic order of the microorganism as found in ITIS, see Source}
|
||||
#' \item{\code{class}}{Taxonomic class of the microorganism as found in ITIS, see Source}
|
||||
#' \item{\code{phylum}}{Taxonomic phylum of the microorganism as found in ITIS, see Source}
|
||||
#' \item{\code{type}}{Type of microorganism, like \code{"Bacteria"} and \code{"Fungus/yeast"}}
|
||||
#' \item{\code{subkingdom}}{Taxonomic subkingdom of the microorganism as found in ITIS, see Source}
|
||||
#' \item{\code{gramstain}}{Gram of microorganism, like \code{"Gram negative"}}
|
||||
#' \item{\code{type}}{Type of microorganism, like \code{"Bacteria"} and \code{"Fungi"}}
|
||||
#' \item{\code{prevalence}}{A rounded integer based on prevalence of the microorganism. Used internally by \code{\link{as.mo}}, otherwise quite meaningless.}
|
||||
#' \item{\code{mo.old}}{The old ID for package versions 0.3.0 and lower.}
|
||||
#' }
|
||||
#' @source Integrated Taxonomic Information System (ITIS) on-line database, \url{https://www.itis.gov}.
|
||||
#' @seealso \code{\link{guess_mo}} \code{\link{antibiotics}} \code{\link{microorganisms.umcg}}
|
||||
#' @source [3] Integrated Taxonomic Information System (ITIS) on-line database, \url{https://www.itis.gov}.
|
||||
#' @seealso \code{\link{as.mo}} \code{\link{mo_property}} \code{\link{microorganisms.umcg}}
|
||||
"microorganisms"
|
||||
|
||||
#' Data set with old taxonomic data from ITIS
|
||||
#'
|
||||
#' A data set containing old, previously valid, taxonomic names. This data set is used internally by \code{\link{as.mo}}.
|
||||
#' @inheritSection as.mo ITIS
|
||||
#' @format A \code{\link{data.frame}} with 58 observations and 5 variables:
|
||||
#' \describe{
|
||||
#' \item{\code{tsn}}{Old Taxonomic Serial Number (TSN), as defined by ITIS}
|
||||
#' \item{\code{name}}{Old taxonomic name of the microorganism as found in ITIS, see Source}
|
||||
#' \item{\code{tsn_new}}{New Taxonomic Serial Number (TSN), as defined by ITIS}
|
||||
#' \item{\code{authors}}{Authors responsible for renaming as found in ITIS, see Source}
|
||||
#' \item{\code{year}}{Year in which the literature was published about the renaming as found in ITIS, see Source}
|
||||
#' }
|
||||
#' @source [3] Integrated Taxonomic Information System (ITIS) on-line database, \url{https://www.itis.gov}.
|
||||
#' @seealso \code{\link{as.mo}} \code{\link{mo_property}} \code{\link{microorganisms}}
|
||||
"microorganisms.old"
|
||||
|
||||
#' Translation table for UMCG
|
||||
#'
|
||||
#' A data set containing all bacteria codes of UMCG MMB. These codes can be joined to data with an ID from \code{\link{microorganisms}$mo} (using \code{\link{left_join_microorganisms}}). GLIMS codes can also be translated to valid \code{MO}s with \code{\link{guess_mo}}.
|
||||
@@ -152,7 +170,7 @@
|
||||
#' \item{\code{umcg}}{Code of microorganism according to UMCG MMB}
|
||||
#' \item{\code{mo}}{Code of microorganism in \code{\link{microorganisms}}}
|
||||
#' }
|
||||
#' @seealso \code{\link{guess_mo}} \code{\link{microorganisms}}
|
||||
#' @seealso \code{\link{as.mo}} \code{\link{microorganisms}}
|
||||
"microorganisms.umcg"
|
||||
|
||||
#' Data set with 2000 blood culture isolates of septic patients
|
||||
|
||||
11
R/globals.R
11
R/globals.R
@@ -17,9 +17,11 @@
|
||||
# ==================================================================== #
|
||||
|
||||
globalVariables(c(".",
|
||||
"..property",
|
||||
"antibiotic",
|
||||
"Antibiotic",
|
||||
"antibiotics",
|
||||
"authors",
|
||||
"cnt",
|
||||
"count",
|
||||
"cum_count",
|
||||
@@ -29,6 +31,7 @@ globalVariables(c(".",
|
||||
"fctlvl",
|
||||
"first_isolate_row_index",
|
||||
"Freq",
|
||||
"fullname",
|
||||
"genus",
|
||||
"gramstain",
|
||||
"Interpretation",
|
||||
@@ -40,8 +43,11 @@ globalVariables(c(".",
|
||||
"median",
|
||||
"mic",
|
||||
"microorganisms",
|
||||
"microorganisms.old",
|
||||
"mo",
|
||||
"mo.old",
|
||||
"n",
|
||||
"name",
|
||||
"observations",
|
||||
"other_pat_or_mo",
|
||||
"Pasted",
|
||||
@@ -52,6 +58,9 @@ globalVariables(c(".",
|
||||
"S",
|
||||
"septic_patients",
|
||||
"species",
|
||||
"tsn",
|
||||
"tsn_new",
|
||||
"value",
|
||||
"Value",
|
||||
"y"))
|
||||
"y",
|
||||
"year"))
|
||||
|
||||
@@ -150,7 +150,7 @@ key_antibiotics <- function(tbl,
|
||||
|
||||
# Gram +
|
||||
tbl <- tbl %>% mutate(key_ab =
|
||||
if_else(gramstain %like% '^Positive ',
|
||||
if_else(gramstain == "Gram positive",
|
||||
apply(X = tbl[, gram_positive],
|
||||
MARGIN = 1,
|
||||
FUN = function(x) paste(x, collapse = "")),
|
||||
@@ -158,7 +158,7 @@ key_antibiotics <- function(tbl,
|
||||
|
||||
# Gram -
|
||||
tbl <- tbl %>% mutate(key_ab =
|
||||
if_else(gramstain %like% '^Negative ',
|
||||
if_else(gramstain == "Gram negative",
|
||||
apply(X = tbl[, gram_negative],
|
||||
MARGIN = 1,
|
||||
FUN = function(x) paste(x, collapse = "")),
|
||||
|
||||
6
R/misc.R
6
R/misc.R
@@ -157,6 +157,12 @@ tbl_parse_guess <- function(tbl,
|
||||
|
||||
#' @importFrom dplyr case_when
|
||||
Sys.locale <- function() {
|
||||
alreadyset <- getOption("AMR_locale")
|
||||
if (!is.null(alreadyset)) {
|
||||
if (tolower(alreadyset) %in% c("en", "de", "nl", "es", "fr", "pt", "it")) {
|
||||
return(tolower(alreadyset))
|
||||
}
|
||||
}
|
||||
sys <- base::Sys.getlocale()
|
||||
case_when(
|
||||
sys %like% '(Deutsch|German|de_)' ~ "de",
|
||||
|
||||
406
R/mo.R
406
R/mo.R
@@ -18,38 +18,62 @@
|
||||
|
||||
#' Transform to microorganism ID
|
||||
#'
|
||||
#' 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.
|
||||
#' Use this function to determine a valid microorganism ID (\code{mo}). Determination is done using Artificial Intelligence (AI) and the complete taxonomic kingdoms \emph{Bacteria}, \emph{Fungi} and \emph{Protozoa} (see Source), 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].
|
||||
#'
|
||||
#' This excludes \emph{Staphylococcus aureus} at default, use \code{Becker = "all"} to also categorise \emph{S. aureus} as "CoPS".
|
||||
#' @param Lancefield a logical to indicate whether beta-haemolytic \emph{Streptococci} should be categorised into Lancefield groups instead of their own species, according to Rebecca C. Lancefield [2]. These \emph{Streptococci} will be categorised in their first group, i.e. \emph{Streptococcus dysgalactiae} will be group C, although officially it was also categorised into groups G and L.
|
||||
#' @param Lancefield a logical to indicate whether beta-haemolytic \emph{Streptococci} should be categorised into Lancefield groups instead of their own species, according to Rebecca C. Lancefield [2]. These \emph{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 \emph{Enterococci} at default (who are in group D), use \code{Lancefield = "all"} to also categorise all \emph{Enterococci} as group D.
|
||||
#' @param allow_uncertain a logical to indicate whether empty results should be checked for only a part of the input string. When results are found, a warning will be given about the uncertainty and the result.
|
||||
#' @rdname as.mo
|
||||
#' @aliases mo
|
||||
#' @keywords mo Becker becker Lancefield lancefield guess
|
||||
#' @details \code{guess_mo} is an alias of \code{as.mo}.
|
||||
#' @details
|
||||
#' A microbial ID (class: \code{mo}) typically looks like these examples:\cr
|
||||
#' \preformatted{
|
||||
#' Code Full name
|
||||
#' --------------- --------------------------------------
|
||||
#' B_KLBSL Klebsiella
|
||||
#' B_KLBSL_PNE Klebsiella pneumoniae
|
||||
#' B_KLBSL_PNE_RHI Klebsiella pneumoniae rhinoscleromatis
|
||||
#' | | | |
|
||||
#' | | | |
|
||||
#' | | | ----> subspecies, a 3-4 letter acronym
|
||||
#' | | ----> species, a 3-4 letter acronym
|
||||
#' | ----> genus, a 5-7 letter acronym, mostly without vowels
|
||||
#' ----> taxonomic kingdom, either Bacteria (B), Fungi (F) or Protozoa (P)
|
||||
#' }
|
||||
#'
|
||||
#' Use the \code{\link{mo_property}} functions to get properties based on the returned code, see Examples.
|
||||
#'
|
||||
#' Thus function uses Artificial Intelligence (AI) to help getting more logical results, based on type of input and known prevalence of human pathogens. For example:
|
||||
#' This function uses Artificial Intelligence (AI) to help getting more logical results, based on type of input and known prevalence of human pathogens. For example:
|
||||
#' \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} for the same reason}
|
||||
#' \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{"S aur"} will return the ID of \emph{Staphylococcus aureus} and not \emph{Staphylococcus auricularis}}
|
||||
#' }
|
||||
#' Moreover, this function also supports ID's based on only Gram stain, when the species is not known. \cr
|
||||
#' For example, \code{"Gram negative rods"} and \code{"GNR"} will both return the ID of a Gram negative rod: \code{GNR}.
|
||||
#' @source
|
||||
#' This means that looking up human non-pathogenic microorganisms takes a longer time compares to human pathogenic microorganisms.
|
||||
#'
|
||||
#' \code{guess_mo} is an alias of \code{as.mo}.
|
||||
#' @section ITIS:
|
||||
#' \if{html}{\figure{itis_logo.jpg}{options: height=60px style=margin-bottom:5px} \cr}
|
||||
#' This \code{AMR} package contains the \strong{complete microbial taxonomic data} from the publicly available Integrated Taxonomic Information System (ITIS, https://www.itis.gov). ITIS is a partnership of U.S., Canadian, and Mexican agencies and taxonomic specialists [3]. The complete taxonomic kingdoms Bacteria, Fungi and Protozoa (from subkingdom to the subspecies level) are included in this package.
|
||||
# (source as section, so it can be inherited by mo_property:)
|
||||
#' @section Source:
|
||||
#' [1] Becker K \emph{et al.} \strong{Coagulase-Negative Staphylococci}. 2014. Clin Microbiol Rev. 27(4): 870–926. \url{https://dx.doi.org/10.1128/CMR.00109-13}
|
||||
#'
|
||||
#' [2] Lancefield RC \strong{A serological differentiation of human and other groups of hemolytic streptococci}. 1933. J Exp Med. 57(4): 571–95. \url{https://dx.doi.org/10.1084/jem.57.4.571}
|
||||
#'
|
||||
#' [3] Integrated Taxonomic Information System (ITIS). Retrieved September 2018. \url{http://www.itis.gov}
|
||||
#' @export
|
||||
#' @importFrom dplyr %>% pull left_join arrange
|
||||
#' @importFrom dplyr %>% pull left_join
|
||||
#' @importFrom data.table as.data.table setkey
|
||||
#' @return Character (vector) with class \code{"mo"}. Unknown values will return \code{NA}.
|
||||
#' @seealso \code{\link{microorganisms}} for the dataframe that is being used to determine ID's.
|
||||
#' @seealso \code{\link{microorganisms}} for the \code{data.frame} with ITIS content that is being used to determine ID's. \cr
|
||||
#' The \code{\link{mo_property}} functions (like \code{\link{mo_genus}}, \code{\link{mo_gramstain}}) to get properties based on the returned code.
|
||||
#' @examples
|
||||
#' # These examples all return "STAAUR", the ID of S. aureus:
|
||||
#' as.mo("stau")
|
||||
@@ -61,22 +85,27 @@
|
||||
#' as.mo("MRSA") # Methicillin Resistant S. aureus
|
||||
#' as.mo("VISA") # Vancomycin Intermediate S. aureus
|
||||
#' as.mo("VRSA") # Vancomycin Resistant S. aureus
|
||||
#' as.mo(369) # Search on TSN (Taxonomic Serial Number), a unique identifier
|
||||
#' # for the Integrated Taxonomic Information System (ITIS)
|
||||
#'
|
||||
#' 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
|
||||
#' guess_mo("S. epidermidis") # will remain species: B_STPHY_EPI
|
||||
#' guess_mo("S. epidermidis", Becker = TRUE) # will not remain species: B_STPHY_CNS
|
||||
#'
|
||||
#' guess_mo("S. pyogenes") # will remain species: STCPYO
|
||||
#' guess_mo("S. pyogenes", Lancefield = TRUE) # will not remain species: STCGRA
|
||||
#' guess_mo("S. pyogenes") # will remain species: B_STRPTC_PYO
|
||||
#' guess_mo("S. pyogenes", Lancefield = TRUE) # will not remain species: B_STRPTC_GRA
|
||||
#'
|
||||
#' # Use mo_* functions to get a specific property based on `mo`
|
||||
#' Ecoli <- as.mo("E. coli") # returns `ESCCOL`
|
||||
#' Ecoli <- as.mo("E. coli") # returns `B_ESCHR_COL`
|
||||
#' mo_genus(Ecoli) # returns "Escherichia"
|
||||
#' mo_gramstain(Ecoli) # returns "Negative rods"
|
||||
#' mo_gramstain(Ecoli) # returns "Gram negative"
|
||||
#' # but it uses as.mo internally too, so you could also just use:
|
||||
#' mo_genus("E. coli") # returns "Escherichia"
|
||||
#'
|
||||
#'
|
||||
#' \dontrun{
|
||||
#' df$mo <- as.mo(df$microorganism_name)
|
||||
@@ -96,7 +125,7 @@
|
||||
#' df <- df %>%
|
||||
#' mutate(mo = guess_mo(paste(genus, species)))
|
||||
#' }
|
||||
as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
|
||||
as.mo <- function(x, Becker = FALSE, Lancefield = FALSE, allow_uncertain = FALSE) {
|
||||
|
||||
if (NCOL(x) == 2) {
|
||||
# support tidyverse selection like: df %>% select(colA, colB)
|
||||
@@ -118,17 +147,33 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
|
||||
}
|
||||
}
|
||||
|
||||
MOs <- AMR::microorganisms %>%
|
||||
arrange(prevalence) %>% # more expected result on multiple findings
|
||||
filter(!mo %like% '^_FAM', # don't search in those
|
||||
(nchar(mo) > 3 | mo %in% c("GNR", "GPR", "GNC", "GPC"))) # no genera
|
||||
MOs <- as.data.table(AMR::microorganisms)
|
||||
setkey(MOs, prevalence, tsn)
|
||||
MOs_mostprevalent <- MOs[prevalence != 9999,]
|
||||
MOs_allothers <- NULL # will be set later, if needed
|
||||
MOs_old <- NULL # will be set later, if needed
|
||||
|
||||
|
||||
if (all(unique(x) %in% MOs[,mo])) {
|
||||
class(x) <- "mo"
|
||||
attr(x, 'package') <- 'AMR'
|
||||
attr(x, 'ITIS') <- TRUE
|
||||
return(x)
|
||||
}
|
||||
if (AMR::is.mo(x) & isTRUE(attributes(x)$ITIS)) {
|
||||
# check for new mo class, data coming from ITIS
|
||||
return(x)
|
||||
}
|
||||
|
||||
|
||||
failures <- character(0)
|
||||
x_input <- x
|
||||
|
||||
# only check the uniques, which is way faster
|
||||
x <- unique(x)
|
||||
|
||||
x_backup <- x
|
||||
x_backup <- trimws(x, which = "both")
|
||||
x_species <- paste(x_backup, "species")
|
||||
# translate to English for supported languages of mo_property
|
||||
x <- gsub("(Gruppe|gruppe|groep|grupo|gruppo|groupe)", "group", x)
|
||||
# remove 'empty' genus and species values
|
||||
@@ -138,6 +183,7 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
|
||||
# but spaces before and after should be omitted
|
||||
x <- trimws(x, which = "both")
|
||||
x_trimmed <- x
|
||||
x_trimmed_species <- paste(x_trimmed, "species")
|
||||
# replace space by regex sign
|
||||
x_withspaces <- gsub(" ", ".* ", x, fixed = TRUE)
|
||||
x <- gsub(" ", ".*", x, fixed = TRUE)
|
||||
@@ -148,111 +194,137 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
|
||||
x_withspaces <- paste0('^', x_withspaces, '$')
|
||||
|
||||
# cat(paste0('x "', x, '"\n'))
|
||||
# cat(paste0('x_species "', x_species, '"\n'))
|
||||
# cat(paste0('x_withspaces_all "', x_withspaces_all, '"\n'))
|
||||
# cat(paste0('x_withspaces_start "', x_withspaces_start, '"\n'))
|
||||
# cat(paste0('x_withspaces "', x_withspaces, '"\n'))
|
||||
# cat(paste0('x_backup "', x_backup, '"\n'))
|
||||
# cat(paste0('x_trimmed "', x_trimmed, '"\n'))
|
||||
# cat(paste0('x_trimmed_species "', x_trimmed_species, '"\n'))
|
||||
|
||||
for (i in 1:length(x)) {
|
||||
if (identical(x_trimmed[i], "")) {
|
||||
if (identical(x_trimmed[i], "") | is.na(x_trimmed[i])) {
|
||||
# empty values
|
||||
x[i] <- NA
|
||||
next
|
||||
}
|
||||
if (toupper(x_backup[i]) %in% AMR::microorganisms$mo) {
|
||||
# is already a valid MO code
|
||||
x[i] <- toupper(x_backup[i])
|
||||
next
|
||||
}
|
||||
if (toupper(x_trimmed[i]) %in% AMR::microorganisms$mo) {
|
||||
# is already a valid MO code
|
||||
x[i] <- toupper(x_trimmed[i])
|
||||
next
|
||||
}
|
||||
if (tolower(x_backup[i]) %in% tolower(AMR::microorganisms$fullname)) {
|
||||
# is exact match in fullname
|
||||
x[i] <- AMR::microorganisms[which(AMR::microorganisms$fullname == x_backup[i]), ]$mo[1L]
|
||||
next
|
||||
}
|
||||
|
||||
# CoNS/CoPS in different languages (support for German, Dutch, Spanish, Portuguese) ----
|
||||
if (tolower(x[i]) %like% '[ck]oagulas[ea] negatie?[vf]'
|
||||
| tolower(x_trimmed[i]) %like% '[ck]oagulas[ea] negatie?[vf]'
|
||||
| tolower(x[i]) %like% '[ck]o?ns[^a-z]?$') {
|
||||
# coerce S. coagulase negative
|
||||
x[i] <- 'STACNS'
|
||||
next
|
||||
}
|
||||
if (tolower(x[i]) %like% '[ck]oagulas[ea] positie?[vf]'
|
||||
| tolower(x_trimmed[i]) %like% '[ck]oagulas[ea] positie?[vf]'
|
||||
| tolower(x[i]) %like% '[ck]o?ps[^a-z]?$') {
|
||||
# coerce S. coagulase positive
|
||||
x[i] <- 'STACPS'
|
||||
next
|
||||
}
|
||||
|
||||
# translate known trivial abbreviations to genus + species ----
|
||||
if (!is.na(x_trimmed[i])) {
|
||||
if (toupper(x_trimmed[i]) == 'MRSA'
|
||||
| toupper(x_trimmed[i]) == 'VISA'
|
||||
| toupper(x_trimmed[i]) == 'VRSA') {
|
||||
x[i] <- 'STAAUR'
|
||||
x[i] <- 'B_STPHY_AUR'
|
||||
next
|
||||
}
|
||||
if (toupper(x_trimmed[i]) == 'MRSE') {
|
||||
x[i] <- 'STAEPI'
|
||||
x[i] <- 'B_STPHY_EPI'
|
||||
next
|
||||
}
|
||||
if (toupper(x_trimmed[i]) == 'VRE') {
|
||||
x[i] <- 'ENCSPP'
|
||||
x[i] <- 'B_ENTRC'
|
||||
next
|
||||
}
|
||||
if (toupper(x_trimmed[i]) == 'MRPA') {
|
||||
# multi resistant P. aeruginosa
|
||||
x[i] <- 'PSEAER'
|
||||
x[i] <- 'B_PDMNS_AER'
|
||||
next
|
||||
}
|
||||
if (toupper(x_trimmed[i]) %in% c('PISP', 'PRSP', 'VISP', 'VRSP')) {
|
||||
# peni I, peni R, vanco I, vanco R: S. pneumoniae
|
||||
x[i] <- 'STCPNE'
|
||||
x[i] <- 'B_STRPTC_PNE'
|
||||
next
|
||||
}
|
||||
if (toupper(x_trimmed[i]) %like% '^G[ABCDFHK]S$') {
|
||||
x[i] <- gsub("G([ABCDFHK])S", "STCGR\\1", x_trimmed[i])
|
||||
if (toupper(x_trimmed[i]) %like% '^G[ABCDFGHK]S$') {
|
||||
x[i] <- gsub("G([ABCDFGHK])S", "B_STRPTC_GR\\1", x_trimmed[i])
|
||||
next
|
||||
}
|
||||
# CoNS/CoPS in different languages (support for German, Dutch, Spanish, Portuguese) ----
|
||||
if (tolower(x[i]) %like% '[ck]oagulas[ea] negatie?[vf]'
|
||||
| tolower(x_trimmed[i]) %like% '[ck]oagulas[ea] negatie?[vf]'
|
||||
| tolower(x[i]) %like% '[ck]o?ns[^a-z]?$') {
|
||||
# coerce S. coagulase negative
|
||||
x[i] <- 'B_STPHY_CNS'
|
||||
next
|
||||
}
|
||||
if (tolower(x[i]) %like% '[ck]oagulas[ea] positie?[vf]'
|
||||
| tolower(x_trimmed[i]) %like% '[ck]oagulas[ea] positie?[vf]'
|
||||
| tolower(x[i]) %like% '[ck]o?ps[^a-z]?$') {
|
||||
# coerce S. coagulase positive
|
||||
x[i] <- 'B_STPHY_CPS'
|
||||
next
|
||||
}
|
||||
}
|
||||
|
||||
# FIRST TRY FULLNAMES AND CODES
|
||||
# if only genus is available, don't select species
|
||||
if (all(!c(x[i], x_trimmed[i]) %like% " ")) {
|
||||
found <- MOs[tolower(fullname) %in% tolower(c(x_species[i], x_trimmed_species[i])), mo]
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
if (nchar(x_trimmed[i]) > 4) {
|
||||
# not when abbr is esco, stau, klpn, etc.
|
||||
found <- MOs[tolower(fullname) %like% gsub(" ", ".*", x_trimmed_species[i], fixed = TRUE), mo]
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
# search for GLIMS code ----
|
||||
found <- AMR::microorganisms.umcg[which(toupper(AMR::microorganisms.umcg$umcg) == toupper(x_trimmed[i])),]$mo
|
||||
if (length(found) > 0) {
|
||||
x[i] <- MOs[mo.old == found, mo][1L]
|
||||
next
|
||||
}
|
||||
|
||||
# TRY FIRST THOUSAND MOST PREVALENT IN HUMAN INFECTIONS ----
|
||||
|
||||
found <- MOs_mostprevalent[tolower(fullname) %in% tolower(c(x_backup[i], x_trimmed[i])), mo]
|
||||
# most probable: is exact match in fullname
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
found <- MOs_mostprevalent[tsn == x_trimmed[i], mo]
|
||||
# is a valid TSN
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
found <- MOs_mostprevalent[mo == toupper(x_backup[i]), mo]
|
||||
# is a valid mo
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
found <- MOs_mostprevalent[mo.old == toupper(x_backup[i])
|
||||
| (substr(x_backup[i], 4, 6) == "SPP" & mo.old == substr(x_backup[i], 1, 3)), mo]
|
||||
# is a valid old mo
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
|
||||
# try any match keeping spaces ----
|
||||
found <- MOs[which(MOs$fullname %like% x_withspaces[i]),]$mo
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
|
||||
# try the same, now based on genus + species ----
|
||||
found <- MOs[which(paste(MOs$genus, MOs$species) %like% x_withspaces[i]),]$mo
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
|
||||
# try any match with genus, keeping spaces, not ending with $ ----
|
||||
found <- MOs[which(MOs$genus %like% x_withspaces_start[i] & MOs$mo %like% 'SPP$'),]$mo
|
||||
found <- MOs_mostprevalent[fullname %like% x_withspaces[i], mo]
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
|
||||
# try any match keeping spaces, not ending with $ ----
|
||||
found <- MOs[which(MOs$fullname %like% x_withspaces_start[i]),]$mo
|
||||
found <- MOs_mostprevalent[fullname %like% x_withspaces_start[i], mo]
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
|
||||
# try any match diregarding spaces ----
|
||||
found <- MOs[which(MOs$fullname %like% x[i]),]$mo
|
||||
found <- MOs_mostprevalent[fullname %like% x[i], mo]
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
@@ -260,14 +332,7 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
|
||||
|
||||
# try fullname without start and stop regex, to also find subspecies ----
|
||||
# like "K. pneu rhino" -> "Klebsiella pneumoniae (rhinoscleromatis)" = KLEPNERH
|
||||
found <- MOs[which(gsub("[\\(\\)]", "", MOs$fullname) %like% x_withspaces_all[i]),]$mo
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
|
||||
# search for GLIMS code ----
|
||||
found <- AMR::microorganisms.umcg[which(toupper(AMR::microorganisms.umcg$umcg) == toupper(x_trimmed[i])),]$mo
|
||||
found <- MOs_mostprevalent[fullname %like% x_withspaces_start[i], mo]
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
@@ -280,7 +345,7 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
|
||||
x_split[i] <- paste0(x_trimmed[i] %>% substr(1, x_length / 2) %>% trimws(),
|
||||
'.* ',
|
||||
x_trimmed[i] %>% substr((x_length / 2) + 1, x_length) %>% trimws())
|
||||
found <- MOs[which(MOs$fullname %like% paste0('^', x_split[i])),]$mo
|
||||
found <- MOs_mostprevalent[fullname %like% paste0('^', x_split[i]), mo]
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
@@ -288,15 +353,137 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
|
||||
|
||||
# try any match with text before and after original search string ----
|
||||
# so "negative rods" will be "GNR"
|
||||
if (x_trimmed[i] %like% "^Gram") {
|
||||
x_trimmed[i] <- gsub("^Gram", "", x_trimmed[i], ignore.case = TRUE)
|
||||
# remove leading and trailing spaces again
|
||||
x_trimmed[i] <- trimws(x_trimmed[i], which = "both")
|
||||
# if (x_trimmed[i] %like% "^Gram") {
|
||||
# x_trimmed[i] <- gsub("^Gram", "", x_trimmed[i], ignore.case = TRUE)
|
||||
# # remove leading and trailing spaces again
|
||||
# x_trimmed[i] <- trimws(x_trimmed[i], which = "both")
|
||||
# }
|
||||
# if (!is.na(x_trimmed[i])) {
|
||||
# found <- MOs_mostprevalent[fullname %like% x_trimmed[i], mo]
|
||||
# if (length(found) > 0) {
|
||||
# x[i] <- found[1L]
|
||||
# next
|
||||
# }
|
||||
# }
|
||||
|
||||
# THEN TRY ALL OTHERS ----
|
||||
if (is.null(MOs_allothers)) {
|
||||
MOs_allothers <- MOs[prevalence == 9999,]
|
||||
}
|
||||
if (!is.na(x_trimmed[i])) {
|
||||
found <- MOs[which(MOs$fullname %like% x_trimmed[i]),]$mo
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
|
||||
found <- MOs_allothers[tolower(fullname) == tolower(x_backup[i]), mo]
|
||||
# most probable: is exact match in fullname
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
found <- MOs_allothers[tolower(fullname) == tolower(x_trimmed[i]), mo]
|
||||
# most probable: is exact match in fullname
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
found <- MOs_allothers[tsn == x_trimmed[i], mo]
|
||||
# is a valid TSN
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
found <- MOs_allothers[mo == toupper(x_backup[i]), mo]
|
||||
# is a valid mo
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
found <- MOs_allothers[mo.old == toupper(x_backup[i]), mo]
|
||||
# is a valid old mo
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
|
||||
# try any match keeping spaces ----
|
||||
found <- MOs_allothers[fullname %like% x_withspaces[i], mo]
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
|
||||
# try any match keeping spaces, not ending with $ ----
|
||||
found <- MOs_allothers[fullname %like% x_withspaces_start[i], mo]
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
|
||||
# try any match diregarding spaces ----
|
||||
found <- MOs_allothers[fullname %like% x[i], mo]
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
|
||||
# try fullname without start and stop regex, to also find subspecies ----
|
||||
# like "K. pneu rhino" -> "Klebsiella pneumoniae (rhinoscleromatis)" = KLEPNERH
|
||||
found <- MOs_allothers[fullname %like% x_withspaces_start[i], mo]
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
|
||||
# try splitting of characters and then find ID ----
|
||||
# like esco = E. coli, klpn = K. pneumoniae, stau = S. aureus
|
||||
x_split <- x
|
||||
x_length <- nchar(x_trimmed[i])
|
||||
x_split[i] <- paste0(x_trimmed[i] %>% substr(1, x_length / 2) %>% trimws(),
|
||||
'.* ',
|
||||
x_trimmed[i] %>% substr((x_length / 2) + 1, x_length) %>% trimws())
|
||||
found <- MOs_allothers[fullname %like% paste0('^', x_split[i]), mo]
|
||||
if (length(found) > 0) {
|
||||
x[i] <- found[1L]
|
||||
next
|
||||
}
|
||||
|
||||
# # try any match with text before and after original search string ----
|
||||
# # so "negative rods" will be "GNR"
|
||||
# if (x_trimmed[i] %like% "^Gram") {
|
||||
# x_trimmed[i] <- gsub("^Gram", "", x_trimmed[i], ignore.case = TRUE)
|
||||
# # remove leading and trailing spaces again
|
||||
# x_trimmed[i] <- trimws(x_trimmed[i], which = "both")
|
||||
# }
|
||||
# if (!is.na(x_trimmed[i])) {
|
||||
# found <- MOs_allothers[fullname %like% x_trimmed[i], mo]
|
||||
# if (length(found) > 0) {
|
||||
# x[i] <- found[1L]
|
||||
# next
|
||||
# }
|
||||
# }
|
||||
|
||||
# MISCELLANEOUS ----
|
||||
|
||||
# look for old taxonomic names ----
|
||||
if (is.null(MOs_old)) {
|
||||
MOs_old <- as.data.table(microorganisms.old)
|
||||
setkey(MOs_old, name, tsn_new)
|
||||
}
|
||||
found <- MOs_old[tolower(name) == tolower(x_backup[i]) |
|
||||
tsn == x_trimmed[i],]
|
||||
if (NROW(found) > 0) {
|
||||
x[i] <- MOs[tsn == found[1, tsn_new], mo]
|
||||
message("Note: '", found[1, name], "' was renamed to '",
|
||||
MOs[tsn == found[1, tsn_new], fullname], "' by ",
|
||||
found[1, authors], " in ", found[1, year])
|
||||
next
|
||||
}
|
||||
|
||||
# check for uncertain results ----
|
||||
# (1) try to strip off one element and check the remains
|
||||
if (allow_uncertain == TRUE) {
|
||||
x_strip <- x_backup[i] %>% strsplit(" ") %>% unlist()
|
||||
x_strip <- x_strip[1:length(x_strip) - 1]
|
||||
x[i] <- suppressWarnings(suppressMessages(as.mo(x_strip)))
|
||||
if (!is.na(x[i])) {
|
||||
warning("Uncertain result: '", x_backup[i], "' -> '", MOs[mo == x[i], fullname], "' (", x[i], ")")
|
||||
next
|
||||
}
|
||||
}
|
||||
@@ -309,7 +496,7 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
|
||||
|
||||
failures <- failures[!failures %in% c(NA, NULL, NaN)]
|
||||
if (length(failures) > 0) {
|
||||
warning("These ", length(failures) , " values could not be coerced to a valid mo: ",
|
||||
warning("These ", length(failures) , " values could not be coerced (try again with allow_uncertain = TRUE):\n",
|
||||
paste('"', unique(failures), '"', sep = "", collapse = ', '),
|
||||
".",
|
||||
call. = FALSE)
|
||||
@@ -341,43 +528,36 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
|
||||
"pseudintermedius", "pseudointermedius",
|
||||
"schleiferi")) %>%
|
||||
pull(mo)
|
||||
x[x %in% CoNS] <- "STACNS"
|
||||
x[x %in% CoPS] <- "STACPS"
|
||||
x[x %in% CoNS] <- "B_STPHY_CNS"
|
||||
x[x %in% CoPS] <- "B_STPHY_CPS"
|
||||
if (Becker == "all") {
|
||||
x[x == "STAAUR"] <- "STACPS"
|
||||
x[x == "B_STPHY_AUR"] <- "B_STPHY_CPS"
|
||||
}
|
||||
}
|
||||
|
||||
# Lancefield ----
|
||||
if (Lancefield == TRUE | Lancefield == "all") {
|
||||
# group A
|
||||
x[x == "STCPYO"] <- "STCGRA" # S. pyogenes
|
||||
x[x == "B_STRPTC_PYO"] <- "B_STRPTC_GRA" # S. pyogenes
|
||||
# group B
|
||||
x[x == "STCAGA"] <- "STCGRB" # S. agalactiae
|
||||
x[x == "B_STRPTC_AGA"] <- "B_STRPTC_GRB" # S. agalactiae
|
||||
# group C
|
||||
S_groupC <- MOs %>% filter(genus == "Streptococcus",
|
||||
species %in% c("equisimilis", "equi",
|
||||
"zooepidemicus", "dysgalactiae")) %>%
|
||||
pull(mo)
|
||||
x[x %in% S_groupC] <- "STCGRC" # S. agalactiae
|
||||
x[x %in% S_groupC] <- "B_STRPTC_GRC" # S. agalactiae
|
||||
if (Lancefield == "all") {
|
||||
x[substr(x, 1, 3) == "ENC"] <- "STCGRD" # all Enterococci
|
||||
x[substr(x, 1, 7) == "B_ENTRC"] <- "B_STRPTC_GRD" # all Enterococci
|
||||
}
|
||||
# group F
|
||||
x[x == "STCANG"] <- "STCGRF" # S. anginosus
|
||||
x[x == "B_STRPTC_ANG"] <- "B_STRPTC_GRF" # S. anginosus
|
||||
# group H
|
||||
x[x == "STCSAN"] <- "STCGRH" # S. sanguis
|
||||
x[x == "B_STRPTC_SAN"] <- "B_STRPTC_GRH" # S. sanguinis
|
||||
# group K
|
||||
x[x == "STCSAL"] <- "STCGRK" # S. salivarius
|
||||
x[x == "B_STRPTC_SAL"] <- "B_STRPTC_GRK" # S. salivarius
|
||||
}
|
||||
|
||||
# for the returned genera without species, add species ----
|
||||
# like "ESC" -> "ESCSPP", but only where the input contained it
|
||||
indices <- nchar(unique(x)) == 3 & !x %like% "[A-Z]{3}SPP" & !x %in% c("GNR", "GPR", "GNC", "GPC",
|
||||
"GNS", "GPS", "GNK", "GPK")
|
||||
indices <- indices[!is.na(indices)]
|
||||
x[indices] <- paste0(x[indices], 'SPP')
|
||||
|
||||
# left join the found results to the original input values (x_input)
|
||||
df_found <- data.frame(input = as.character(unique(x_input)),
|
||||
found = x,
|
||||
@@ -392,9 +572,11 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE) {
|
||||
|
||||
class(x) <- "mo"
|
||||
attr(x, 'package') <- 'AMR'
|
||||
attr(x, 'ITIS') <- TRUE
|
||||
x
|
||||
}
|
||||
|
||||
|
||||
#' @rdname as.mo
|
||||
#' @export
|
||||
is.mo <- function(x) {
|
||||
|
||||
174
R/mo_property.R
174
R/mo_property.R
@@ -22,21 +22,17 @@
|
||||
#' @param x any (vector of) text that can be coerced to a valid microorganism code with \code{\link{as.mo}}
|
||||
#' @param property one of the column names of one of the \code{\link{microorganisms}} data set, like \code{"mo"}, \code{"bactsys"}, \code{"family"}, \code{"genus"}, \code{"species"}, \code{"fullname"}, \code{"gramstain"} and \code{"aerobic"}
|
||||
#' @inheritParams as.mo
|
||||
#' @param language language of the returned text, defaults to the systems language. Either one of \code{"en"} (English), \code{"de"} (German), \code{"nl"} (Dutch), \code{"es"} (Spanish) or \code{"pt"} (Portuguese).
|
||||
#' @source
|
||||
#' [1] Becker K \emph{et al.} \strong{Coagulase-Negative Staphylococci}. 2014. Clin Microbiol Rev. 27(4): 870–926. \url{https://dx.doi.org/10.1128/CMR.00109-13}
|
||||
#'
|
||||
#' [2] Lancefield RC \strong{A serological differentiation of human and other groups of hemolytic streptococci}. 1933. J Exp Med. 57(4): 571–95. \url{https://dx.doi.org/10.1084/jem.57.4.571}
|
||||
#'
|
||||
#' [3] Integrated Taxonomic Information System (ITIS) on-line database, \url{https://www.itis.gov}.
|
||||
#' @param language language of the returned text, defaults to the systems language but can also be set with \code{\link{getOption}("AMR_locale")}. Either one of \code{"en"} (English), \code{"de"} (German), \code{"nl"} (Dutch), \code{"es"} (Spanish) or \code{"pt"} (Portuguese).
|
||||
#' @inheritSection as.mo ITIS
|
||||
#' @inheritSection as.mo Source
|
||||
#' @rdname mo_property
|
||||
#' @name mo_property
|
||||
#' @return A logical (in case of \code{mo_aerobic}), a list (in case of \code{mo_taxonomy}), a character otherwise
|
||||
#' @export
|
||||
#' @importFrom dplyr %>% left_join pull
|
||||
#' @seealso \code{\link{microorganisms}}
|
||||
#' @examples
|
||||
#' # All properties
|
||||
#' mo_subkingdom("E. coli") # "Negibacteria"
|
||||
#' mo_phylum("E. coli") # "Proteobacteria"
|
||||
#' mo_class("E. coli") # "Gammaproteobacteria"
|
||||
#' mo_order("E. coli") # "Enterobacteriales"
|
||||
@@ -46,42 +42,30 @@
|
||||
#' mo_subspecies("E. coli") # ""
|
||||
#' mo_fullname("E. coli") # "Escherichia coli"
|
||||
#' mo_shortname("E. coli") # "E. coli"
|
||||
#' mo_gramstain("E. coli") # "Gram negative"
|
||||
#' mo_TSN("E. coli") # 285
|
||||
#' mo_type("E. coli") # "Bacteria"
|
||||
#' mo_gramstain("E. coli") # "Negative rods"
|
||||
#' mo_aerobic("E. coli") # TRUE
|
||||
#'
|
||||
#'
|
||||
#' # Abbreviations known in the field
|
||||
#' mo_genus("MRSA") # "Staphylococcus"
|
||||
#' mo_species("MRSA") # "aureus"
|
||||
#' mo_shortname("MRSA") # "S. aureus"
|
||||
#' mo_gramstain("MRSA") # "Positive cocci"
|
||||
#' mo_gramstain("MRSA") # "Gram positive"
|
||||
#'
|
||||
#' mo_genus("VISA") # "Staphylococcus"
|
||||
#' mo_species("VISA") # "aureus"
|
||||
#'
|
||||
#'
|
||||
#' # Known subspecies
|
||||
#' mo_genus("EHEC") # "Escherichia"
|
||||
#' mo_species("EHEC") # "coli"
|
||||
#' mo_subspecies("EHEC") # "EHEC"
|
||||
#' mo_fullname("EHEC") # "Escherichia coli (EHEC)"
|
||||
#' mo_shortname("EHEC") # "E. coli"
|
||||
#'
|
||||
#' mo_genus("doylei") # "Campylobacter"
|
||||
#' mo_species("doylei") # "jejuni"
|
||||
#' mo_fullname("doylei") # "Campylobacter jejuni (doylei)"
|
||||
#' mo_fullname("doylei") # "Campylobacter jejuni doylei"
|
||||
#'
|
||||
#' mo_fullname("K. pneu rh") # "Klebsiella pneumoniae (rhinoscleromatis)"
|
||||
#' mo_fullname("K. pneu rh") # "Klebsiella pneumoniae rhinoscleromatis"
|
||||
#' mo_shortname("K. pneu rh") # "K. pneumoniae"
|
||||
#'
|
||||
#'
|
||||
#' # Anaerobic bacteria
|
||||
#' mo_genus("B. fragilis") # "Bacteroides"
|
||||
#' mo_species("B. fragilis") # "fragilis"
|
||||
#' mo_aerobic("B. fragilis") # FALSE
|
||||
#'
|
||||
#'
|
||||
#' # Becker classification, see ?as.mo
|
||||
#' mo_fullname("S. epi") # "Staphylococcus epidermidis"
|
||||
#' mo_fullname("S. epi", Becker = TRUE) # "Coagulase Negative Staphylococcus (CoNS)"
|
||||
@@ -99,10 +83,9 @@
|
||||
#' mo_type("E. coli", language = "de") # "Bakterium"
|
||||
#' mo_type("E. coli", language = "nl") # "Bacterie"
|
||||
#' mo_type("E. coli", language = "es") # "Bakteria"
|
||||
#' mo_gramstain("E. coli", language = "de") # "Negative Staebchen"
|
||||
#' mo_gramstain("E. coli", language = "nl") # "Negatieve staven"
|
||||
#' mo_gramstain("E. coli", language = "es") # "Bacilos negativos"
|
||||
#' mo_gramstain("Giardia", language = "pt") # "Parasitas"
|
||||
#' mo_gramstain("E. coli", language = "de") # "Gramnegativ"
|
||||
#' mo_gramstain("E. coli", language = "nl") # "Gram-negatief"
|
||||
#' mo_gramstain("E. coli", language = "es") # "Gram negativo"
|
||||
#'
|
||||
#' mo_fullname("S. pyogenes",
|
||||
#' Lancefield = TRUE,
|
||||
@@ -112,7 +95,7 @@
|
||||
#' language = "nl") # "Streptococcus groep A"
|
||||
#'
|
||||
#'
|
||||
#' # Complete taxonomy up to Phylum, returns a list
|
||||
#' # Complete taxonomy up to Subkingdom, returns a list
|
||||
#' mo_taxonomy("E. coli")
|
||||
mo_fullname <- function(x, Becker = FALSE, Lancefield = FALSE, language = NULL) {
|
||||
mo_property(x, "fullname", Becker = Becker, Lancefield = Lancefield, language = language)
|
||||
@@ -191,12 +174,24 @@ mo_phylum <- function(x) {
|
||||
mo_property(x, "phylum")
|
||||
}
|
||||
|
||||
#' @rdname mo_property
|
||||
#' @export
|
||||
mo_subkingdom <- function(x) {
|
||||
mo_property(x, "subkingdom")
|
||||
}
|
||||
|
||||
#' @rdname mo_property
|
||||
#' @export
|
||||
mo_type <- function(x, language = NULL) {
|
||||
mo_property(x, "type", language = language)
|
||||
}
|
||||
|
||||
#' @rdname mo_property
|
||||
#' @export
|
||||
mo_TSN <- function(x) {
|
||||
mo_property(x, "tsn")
|
||||
}
|
||||
|
||||
#' @rdname mo_property
|
||||
#' @export
|
||||
mo_gramstain <- function(x, language = NULL) {
|
||||
@@ -204,28 +199,32 @@ mo_gramstain <- function(x, language = NULL) {
|
||||
}
|
||||
|
||||
#' @rdname mo_property
|
||||
#' @export
|
||||
mo_aerobic <- function(x) {
|
||||
mo_property(x, "aerobic")
|
||||
}
|
||||
|
||||
#' @rdname mo_property
|
||||
#' @importFrom data.table data.table as.data.table setkey
|
||||
#' @export
|
||||
mo_property <- function(x, property = 'fullname', Becker = FALSE, Lancefield = FALSE, language = NULL) {
|
||||
property <- tolower(property[1])
|
||||
if (!property %in% colnames(AMR::microorganisms)) {
|
||||
stop("invalid property: ", property, " - use a column name of the `microorganisms` data set")
|
||||
}
|
||||
result1 <- as.mo(x = x, Becker = Becker, Lancefield = Lancefield) # this will give a warning if x cannot be coerced
|
||||
result2 <- suppressWarnings(
|
||||
data.frame(mo = result1, stringsAsFactors = FALSE) %>%
|
||||
left_join(AMR::microorganisms, by = "mo") %>%
|
||||
pull(property)
|
||||
)
|
||||
if (property != "aerobic") {
|
||||
if (Becker == TRUE | Lancefield == TRUE | !is.mo(x)) {
|
||||
# this will give a warning if x cannot be coerced
|
||||
result1 <- AMR::as.mo(x = x, Becker = Becker, Lancefield = Lancefield)
|
||||
} else {
|
||||
result1 <- x
|
||||
}
|
||||
A <- data.table(mo = result1, stringsAsFactors = FALSE)
|
||||
B <- as.data.table(AMR::microorganisms)
|
||||
setkey(B, mo)
|
||||
result2 <- B[A, on = 'mo', ..property][[1]]
|
||||
|
||||
if (property == "tsn") {
|
||||
result2 <- as.integer(result2)
|
||||
} else {
|
||||
# will else not retain `logical` class
|
||||
result2[x %in% c("", NA) | result2 %in% c("", NA, "(no MO)")] <- ""
|
||||
result2 <- mo_translate(result2, language = language)
|
||||
if (property %in% c("fullname", "shortname", "genus", "species", "subspecies", "type", "gramstain")) {
|
||||
result2 <- mo_translate(result2, language = language)
|
||||
}
|
||||
}
|
||||
result2
|
||||
}
|
||||
@@ -234,7 +233,8 @@ mo_property <- function(x, property = 'fullname', Becker = FALSE, Lancefield = F
|
||||
#' @export
|
||||
mo_taxonomy <- function(x) {
|
||||
x <- as.mo(x)
|
||||
base::list(phylum = mo_phylum(x),
|
||||
base::list(subkingdom = mo_subkingdom(x),
|
||||
phylum = mo_phylum(x),
|
||||
class = mo_class(x),
|
||||
order = mo_order(x),
|
||||
family = mo_family(x),
|
||||
@@ -266,15 +266,11 @@ mo_translate <- function(x, language) {
|
||||
gsub("Coagulase Positive Staphylococcus","Koagulase-positive Staphylococcus", ., fixed = TRUE) %>%
|
||||
gsub("Beta-haemolytic Streptococcus", "Beta-h\u00e4molytischer Streptococcus", ., fixed = TRUE) %>%
|
||||
gsub("(no MO)", "(kein MO)", ., fixed = TRUE) %>%
|
||||
gsub("Negative rods", "Negative St\u00e4bchen", ., fixed = TRUE) %>%
|
||||
gsub("Negative cocci", "Negative Kokken", ., fixed = TRUE) %>%
|
||||
gsub("Positive rods", "Positive St\u00e4bchen", ., fixed = TRUE) %>%
|
||||
gsub("Positive cocci", "Positive Kokken", ., fixed = TRUE) %>%
|
||||
gsub("Parasites", "Parasiten", ., fixed = TRUE) %>%
|
||||
gsub("Fungi and yeasts", "Pilze und Hefen", ., fixed = TRUE) %>%
|
||||
gsub("Bacteria", "Bakterium", ., fixed = TRUE) %>%
|
||||
gsub("Fungus/yeast", "Pilz/Hefe", ., fixed = TRUE) %>%
|
||||
gsub("Parasite", "Parasit", ., fixed = TRUE) %>%
|
||||
gsub("Gram negative", "Gramnegativ", ., fixed = TRUE) %>%
|
||||
gsub("Gram positive", "Grampositiv", ., fixed = TRUE) %>%
|
||||
gsub("Bacteria", "Bakterien", ., fixed = TRUE) %>%
|
||||
gsub("Fungi", "Hefen/Pilze", ., fixed = TRUE) %>%
|
||||
gsub("Protozoa", "Protozoen", ., fixed = TRUE) %>%
|
||||
gsub("biogroup", "Biogruppe", ., fixed = TRUE) %>%
|
||||
gsub("biotype", "Biotyp", ., fixed = TRUE) %>%
|
||||
gsub("vegetative", "vegetativ", ., fixed = TRUE) %>%
|
||||
@@ -287,15 +283,11 @@ mo_translate <- function(x, language) {
|
||||
gsub("Coagulase Positive Staphylococcus","Coagulase-positieve Staphylococcus", ., fixed = TRUE) %>%
|
||||
gsub("Beta-haemolytic Streptococcus", "Beta-hemolytische Streptococcus", ., fixed = TRUE) %>%
|
||||
gsub("(no MO)", "(geen MO)", ., fixed = TRUE) %>%
|
||||
gsub("Negative rods", "Negatieve staven", ., fixed = TRUE) %>%
|
||||
gsub("Negative cocci", "Negatieve kokken", ., fixed = TRUE) %>%
|
||||
gsub("Positive rods", "Positieve staven", ., fixed = TRUE) %>%
|
||||
gsub("Positive cocci", "Positieve kokken", ., fixed = TRUE) %>%
|
||||
gsub("Parasites", "Parasieten", ., fixed = TRUE) %>%
|
||||
gsub("Fungi and yeasts", "Schimmels en gisten", ., fixed = TRUE) %>%
|
||||
gsub("Bacteria", "Bacterie", ., fixed = TRUE) %>%
|
||||
gsub("Fungus/yeast", "Schimmel/gist", ., fixed = TRUE) %>%
|
||||
gsub("Parasite", "Parasiet", ., fixed = TRUE) %>%
|
||||
gsub("Gram negative", "Gram-negatief", ., fixed = TRUE) %>%
|
||||
gsub("Gram positive", "Gram-positief", ., fixed = TRUE) %>%
|
||||
gsub("Bacteria", "Bacteri\u00ebn", ., fixed = TRUE) %>%
|
||||
gsub("Fungi", "Schimmels/gisten", ., fixed = TRUE) %>%
|
||||
gsub("Protozoa", "protozo\u00ebn", ., fixed = TRUE) %>%
|
||||
gsub("biogroup", "biogroep", ., fixed = TRUE) %>%
|
||||
# gsub("biotype", "biotype", ., fixed = TRUE) %>%
|
||||
gsub("vegetative", "vegetatief", ., fixed = TRUE) %>%
|
||||
@@ -308,15 +300,11 @@ mo_translate <- function(x, language) {
|
||||
gsub("Coagulase Positive Staphylococcus","Staphylococcus coagulasa positivo", ., fixed = TRUE) %>%
|
||||
gsub("Beta-haemolytic Streptococcus", "Streptococcus Beta-hemol\u00edtico", ., fixed = TRUE) %>%
|
||||
gsub("(no MO)", "(sin MO)", ., fixed = TRUE) %>%
|
||||
gsub("Negative rods", "Bacilos negativos", ., fixed = TRUE) %>%
|
||||
gsub("Negative cocci", "Cocos negativos", ., fixed = TRUE) %>%
|
||||
gsub("Positive rods", "Bacilos positivos", ., fixed = TRUE) %>%
|
||||
gsub("Positive cocci", "Cocos positivos", ., fixed = TRUE) %>%
|
||||
gsub("Parasites", "Par\u00e1sitos", ., fixed = TRUE) %>%
|
||||
gsub("Fungi and yeasts", "Hongos y levaduras", ., fixed = TRUE) %>%
|
||||
# gsub("Bacteria", "Bacteria", ., fixed = TRUE) %>%
|
||||
gsub("Fungus/yeast", "Hongo/levadura", ., fixed = TRUE) %>%
|
||||
gsub("Parasite", "Par\u00e1sito", ., fixed = TRUE) %>%
|
||||
gsub("Gram negative", "Gram negativo", ., fixed = TRUE) %>%
|
||||
gsub("Gram positive", "Gram positivo", ., fixed = TRUE) %>%
|
||||
gsub("Bacteria", "Bacterias", ., fixed = TRUE) %>%
|
||||
gsub("Fungi", "Hongos", ., fixed = TRUE) %>%
|
||||
gsub("Protozoa", "Protozoarios", ., fixed = TRUE) %>%
|
||||
gsub("biogroup", "biogrupo", ., fixed = TRUE) %>%
|
||||
gsub("biotype", "biotipo", ., fixed = TRUE) %>%
|
||||
gsub("vegetative", "vegetativo", ., fixed = TRUE) %>%
|
||||
@@ -329,15 +317,11 @@ mo_translate <- function(x, language) {
|
||||
gsub("Coagulase Positive Staphylococcus","Staphylococcus coagulase positivo", ., fixed = TRUE) %>%
|
||||
gsub("Beta-haemolytic Streptococcus", "Streptococcus Beta-hemol\u00edtico", ., fixed = TRUE) %>%
|
||||
gsub("(no MO)", "(sem MO)", ., fixed = TRUE) %>%
|
||||
gsub("Negative rods", "Bacilos negativos", ., fixed = TRUE) %>%
|
||||
gsub("Negative cocci", "Cocos negativos", ., fixed = TRUE) %>%
|
||||
gsub("Positive rods", "Bacilos positivos", ., fixed = TRUE) %>%
|
||||
gsub("Positive cocci", "Cocos positivos", ., fixed = TRUE) %>%
|
||||
gsub("Parasites", "Parasitas", ., fixed = TRUE) %>%
|
||||
gsub("Fungi and yeasts", "Cogumelos e leveduras", ., fixed = TRUE) %>%
|
||||
gsub("Bacteria", "Bact\u00e9ria", ., fixed = TRUE) %>%
|
||||
gsub("Fungus/yeast", "Cogumelo/levedura", ., fixed = TRUE) %>%
|
||||
gsub("Parasite", "Parasita", ., fixed = TRUE) %>%
|
||||
gsub("Gram negative", "Gram negativo", ., fixed = TRUE) %>%
|
||||
gsub("Gram positive", "Gram positivo", ., fixed = TRUE) %>%
|
||||
gsub("Bacteria", "Bact\u00e9rias", ., fixed = TRUE) %>%
|
||||
gsub("Fungi", "Fungos", ., fixed = TRUE) %>%
|
||||
gsub("Protozoa", "Protozo\u00e1rios", ., fixed = TRUE) %>%
|
||||
gsub("biogroup", "biogrupo", ., fixed = TRUE) %>%
|
||||
gsub("biotype", "bi\u00f3tipo", ., fixed = TRUE) %>%
|
||||
gsub("vegetative", "vegetativo", ., fixed = TRUE) %>%
|
||||
@@ -350,15 +334,11 @@ mo_translate <- function(x, language) {
|
||||
gsub("Coagulase Positive Staphylococcus","Staphylococcus positivo coagulasi", ., fixed = TRUE) %>%
|
||||
gsub("Beta-haemolytic Streptococcus", "Streptococcus Beta-emolitico", ., fixed = TRUE) %>%
|
||||
gsub("(no MO)", "(non MO)", ., fixed = TRUE) %>%
|
||||
gsub("Negative rods", "Bastoncini Gram-negativi", ., fixed = TRUE) %>%
|
||||
gsub("Negative cocci", "Cocchi Gram-negativi", ., fixed = TRUE) %>%
|
||||
gsub("Positive rods", "Bastoncini Gram-positivi", ., fixed = TRUE) %>%
|
||||
gsub("Positive cocci", "Cocchi Gram-positivi", ., fixed = TRUE) %>%
|
||||
gsub("Parasites", "Parassiti", ., fixed = TRUE) %>%
|
||||
gsub("Fungi and yeasts", "Funghi e lieviti", ., fixed = TRUE) %>%
|
||||
gsub("Bacteria", "Batterio", ., fixed = TRUE) %>%
|
||||
gsub("Fungus/yeast", "Fungo/lievito", ., fixed = TRUE) %>%
|
||||
gsub("Parasite", "Parassita", ., fixed = TRUE) %>%
|
||||
gsub("Gram negative", "Gram negativo", ., fixed = TRUE) %>%
|
||||
gsub("Gram positive", "Gram positivo", ., fixed = TRUE) %>%
|
||||
gsub("Bacteria", "Batteri", ., fixed = TRUE) %>%
|
||||
gsub("Fungi", "Fungo", ., fixed = TRUE) %>%
|
||||
gsub("Protozoa", "Protozoi", ., fixed = TRUE) %>%
|
||||
gsub("biogroup", "biogruppo", ., fixed = TRUE) %>%
|
||||
gsub("biotype", "biotipo", ., fixed = TRUE) %>%
|
||||
gsub("vegetative", "vegetativo", ., fixed = TRUE) %>%
|
||||
@@ -371,15 +351,11 @@ mo_translate <- function(x, language) {
|
||||
gsub("Coagulase Positive Staphylococcus","Staphylococcus \u00e0 coagulase positif", ., fixed = TRUE) %>%
|
||||
gsub("Beta-haemolytic Streptococcus", "Streptococcus B\u00eata-h\u00e9molytique", ., fixed = TRUE) %>%
|
||||
gsub("(no MO)", "(pas MO)", ., fixed = TRUE) %>%
|
||||
gsub("Negative rods", "Bacilles n\u00e9gatif", ., fixed = TRUE) %>%
|
||||
gsub("Negative cocci", "Cocci n\u00e9gatif", ., fixed = TRUE) %>%
|
||||
gsub("Positive rods", "Bacilles positif", ., fixed = TRUE) %>%
|
||||
gsub("Positive cocci", "Cocci positif", ., fixed = TRUE) %>%
|
||||
# gsub("Parasites", "Parasites", ., fixed = TRUE) %>%
|
||||
gsub("Fungi and yeasts", "Champignons et levures", ., fixed = TRUE) %>%
|
||||
gsub("Bacteria", "Bact\u00e9rie", ., fixed = TRUE) %>%
|
||||
gsub("Fungus/yeast", "Champignon/levure", ., fixed = TRUE) %>%
|
||||
# gsub("Parasite", "Parasite", ., fixed = TRUE) %>%
|
||||
gsub("Gram negative", "Gram n\u00e9gatif", ., fixed = TRUE) %>%
|
||||
gsub("Gram positive", "Gram positif", ., fixed = TRUE) %>%
|
||||
gsub("Bacteria", "Bact\u00e9ries", ., fixed = TRUE) %>%
|
||||
gsub("Fungi", "Champignons", ., fixed = TRUE) %>%
|
||||
gsub("Protozoa", "Protozoaires", ., fixed = TRUE) %>%
|
||||
gsub("biogroup", "biogroupe", ., fixed = TRUE) %>%
|
||||
# gsub("biotype", "biotype", ., fixed = TRUE) %>%
|
||||
gsub("vegetative", "v\u00e9g\u00e9tatif", ., fixed = TRUE) %>%
|
||||
|
||||
Reference in New Issue
Block a user