AMR/R/key_antibiotics.R

340 lines
14 KiB
R
Raw Normal View History

2018-07-17 13:02:05 +02:00
# ==================================================================== #
# TITLE #
# Antimicrobial Resistance (AMR) Analysis #
# #
2019-01-02 23:24:07 +01:00
# SOURCE #
# https://gitlab.com/msberends/AMR #
2018-07-17 13:02:05 +02:00
# #
# LICENCE #
# (c) 2018-2020 Berends MS, Luz CF et al. #
2018-07-17 13:02:05 +02:00
# #
2019-01-02 23:24:07 +01:00
# This R package is free software; you can freely use and distribute #
# it for both personal and commercial purposes under the terms of the #
# GNU General Public License version 2.0 (GNU GPL-2), as published by #
# the Free Software Foundation. #
# #
# We created this package for both routine data analysis and academic #
# research and it was publicly released in the hope that it will be #
# useful, but it comes WITHOUT ANY WARRANTY OR LIABILITY. #
2019-04-05 18:47:39 +02:00
# Visit our website for more info: https://msberends.gitlab.io/AMR. #
2018-07-17 13:02:05 +02:00
# ==================================================================== #
#' Key antibiotics for first *weighted* isolates
2018-07-17 13:02:05 +02:00
#'
#' These function can be used to determine first isolates (see [first_isolate()]). Using key antibiotics to determine first isolates is more reliable than without key antibiotics. These selected isolates will then be called first *weighted* isolates.
#' @inheritSection lifecycle Stable lifecycle
#' @param x table with antibiotics coloms, like `AMX` or `amox`
2019-05-23 17:35:58 +02:00
#' @param y,z characters to compare
2018-07-17 13:02:05 +02:00
#' @inheritParams first_isolate
#' @param universal_1,universal_2,universal_3,universal_4,universal_5,universal_6 column names of **broad-spectrum** antibiotics, case-insensitive. At default, the columns containing these antibiotics will be guessed with [guess_ab_col()].
#' @param GramPos_1,GramPos_2,GramPos_3,GramPos_4,GramPos_5,GramPos_6 column names of antibiotics for **Gram-positives**, case-insensitive. At default, the columns containing these antibiotics will be guessed with [guess_ab_col()].
#' @param GramNeg_1,GramNeg_2,GramNeg_3,GramNeg_4,GramNeg_5,GramNeg_6 column names of antibiotics for **Gram-negatives**, case-insensitive. At default, the columns containing these antibiotics will be guessed with [guess_ab_col()].
2018-07-23 10:35:39 +02:00
#' @param warnings give warning about missing antibiotic columns, they will anyway be ignored
2018-12-22 22:39:34 +01:00
#' @param ... other parameters passed on to function
2020-05-16 13:05:47 +02:00
#' @details The function [key_antibiotics()] returns a character vector with 12 antibiotic results for every isolate. These isolates can then be compared using [key_antibiotics_equal()], to check if two isolates have generally the same antibiogram. Missing and invalid values are replaced with a dot (`"."`) by [key_antibiotics()] and ignored by [key_antibiotics_equal()].
#'
#' The [first_isolate()] function only uses this function on the same microbial species from the same patient. Using this, e.g. an MRSA will be included after a susceptible *S. aureus* (MSSA) is found within the same patient episode. Without key antibiotic comparison it would not. See [first_isolate()] for more info.
2018-07-17 13:02:05 +02:00
#'
#' At default, the antibiotics that are used for **Gram-positive bacteria** are:
#' - Amoxicillin
#' - Amoxicillin/clavulanic acid
#' - Cefuroxime
#' - Piperacillin/tazobactam
#' - Ciprofloxacin
#' - Trimethoprim/sulfamethoxazole
#' - Vancomycin
#' - Teicoplanin
#' - Tetracycline
#' - Erythromycin
#' - Oxacillin
#' - Rifampin
2018-07-17 13:02:05 +02:00
#'
#' At default the antibiotics that are used for **Gram-negative bacteria** are:
#' - Amoxicillin
#' - Amoxicillin/clavulanic acid
#' - Cefuroxime
#' - Piperacillin/tazobactam
#' - Ciprofloxacin
#' - Trimethoprim/sulfamethoxazole
#' - Gentamicin
#' - Tobramycin
#' - Colistin
#' - Cefotaxime
#' - Ceftazidime
#' - Meropenem
#'
#' The function [key_antibiotics_equal()] checks the characters returned by [key_antibiotics()] for equality, and returns a [`logical`] vector.
2018-07-17 13:02:05 +02:00
#' @inheritSection first_isolate Key antibiotics
#' @rdname key_antibiotics
#' @export
#' @seealso [first_isolate()]
2019-01-02 23:24:07 +01:00
#' @inheritSection AMR Read more on our website!
2018-07-17 13:02:05 +02:00
#' @examples
#' # `example_isolates` is a dataset available in the AMR package.
#' # See ?example_isolates.
2019-06-11 14:18:25 +02:00
#'
2020-05-16 21:40:50 +02:00
#' \dontrun{
#' library(dplyr)
2018-07-17 13:02:05 +02:00
#' # set key antibiotics to a new variable
#' my_patients <- example_isolates %>%
#' mutate(keyab = key_antibiotics(.)) %>%
#' mutate(
#' # now calculate first isolates
2018-12-22 22:39:34 +01:00
#' first_regular = first_isolate(., col_keyantibiotics = FALSE),
#' # and first WEIGHTED isolates
2018-12-22 22:39:34 +01:00
#' first_weighted = first_isolate(., col_keyantibiotics = "keyab")
#' )
2018-07-17 13:02:05 +02:00
#'
#' # Check the difference, in this data set it results in 7% more isolates:
#' sum(my_patients$first_regular, na.rm = TRUE)
#' sum(my_patients$first_weighted, na.rm = TRUE)
2020-05-16 21:40:50 +02:00
#' }
2018-07-23 10:35:39 +02:00
#'
#' # output of the `key_antibiotics` function could be like this:
#' strainA <- "SSSRR.S.R..S"
#' strainB <- "SSSIRSSSRSSS"
#'
#' key_antibiotics_equal(strainA, strainB)
2018-12-22 22:39:34 +01:00
#' # TRUE, because I is ignored (as well as missing values)
2018-07-23 10:35:39 +02:00
#'
#' key_antibiotics_equal(strainA, strainB, ignore_I = FALSE)
#' # FALSE, because I is not ignored and so the 4th value differs
2019-05-23 16:58:59 +02:00
key_antibiotics <- function(x,
2018-12-22 22:39:34 +01:00
col_mo = NULL,
2019-06-11 14:18:25 +02:00
universal_1 = guess_ab_col(x, "amoxicillin"),
universal_2 = guess_ab_col(x, "amoxicillin/clavulanic acid"),
universal_3 = guess_ab_col(x, "cefuroxime"),
universal_4 = guess_ab_col(x, "piperacillin/tazobactam"),
universal_5 = guess_ab_col(x, "ciprofloxacin"),
universal_6 = guess_ab_col(x, "trimethoprim/sulfamethoxazole"),
GramPos_1 = guess_ab_col(x, "vancomycin"),
GramPos_2 = guess_ab_col(x, "teicoplanin"),
GramPos_3 = guess_ab_col(x, "tetracycline"),
GramPos_4 = guess_ab_col(x, "erythromycin"),
GramPos_5 = guess_ab_col(x, "oxacillin"),
GramPos_6 = guess_ab_col(x, "rifampin"),
GramNeg_1 = guess_ab_col(x, "gentamicin"),
GramNeg_2 = guess_ab_col(x, "tobramycin"),
GramNeg_3 = guess_ab_col(x, "colistin"),
GramNeg_4 = guess_ab_col(x, "cefotaxime"),
GramNeg_5 = guess_ab_col(x, "ceftazidime"),
GramNeg_6 = guess_ab_col(x, "meropenem"),
2018-08-31 13:36:19 +02:00
warnings = TRUE,
2018-12-22 22:39:34 +01:00
...) {
2020-05-16 13:05:47 +02:00
dots <- unlist(list(...))
if (length(dots) != 0) {
# backwards compatibility with old parameters
dots.names <- dots %>% names()
if ("info" %in% dots.names) {
warnings <- dots[which(dots.names == "info")]
}
}
2018-07-17 13:02:05 +02:00
2018-12-22 22:39:34 +01:00
# try to find columns based on type
# -- mo
2019-01-15 12:45:24 +01:00
if (is.null(col_mo)) {
2019-05-23 16:58:59 +02:00
col_mo <- search_type_in_df(x = x, type = "mo")
2018-08-31 13:36:19 +02:00
}
2018-12-22 22:39:34 +01:00
if (is.null(col_mo)) {
stop("`col_mo` must be set.", call. = FALSE)
2018-07-17 13:02:05 +02:00
}
# check columns
2018-07-19 15:11:23 +02:00
col.list <- c(universal_1, universal_2, universal_3, universal_4, universal_5, universal_6,
GramPos_1, GramPos_2, GramPos_3, GramPos_4, GramPos_5, GramPos_6,
GramNeg_1, GramNeg_2, GramNeg_3, GramNeg_4, GramNeg_5, GramNeg_6)
2020-05-16 13:05:47 +02:00
check_available_columns <- function(x, col.list, warnings = TRUE) {
2019-05-10 16:44:59 +02:00
# check columns
col.list <- col.list[!is.na(col.list) & !is.null(col.list)]
names(col.list) <- col.list
col.list.bak <- col.list
# are they available as upper case or lower case then?
2019-10-11 17:21:02 +02:00
for (i in seq_len(length(col.list))) {
2019-05-10 16:44:59 +02:00
if (is.null(col.list[i]) | isTRUE(is.na(col.list[i]))) {
col.list[i] <- NA
2019-05-23 16:58:59 +02:00
} else if (toupper(col.list[i]) %in% colnames(x)) {
2019-05-10 16:44:59 +02:00
col.list[i] <- toupper(col.list[i])
2019-05-23 16:58:59 +02:00
} else if (tolower(col.list[i]) %in% colnames(x)) {
2019-05-10 16:44:59 +02:00
col.list[i] <- tolower(col.list[i])
2019-05-23 16:58:59 +02:00
} else if (!col.list[i] %in% colnames(x)) {
2019-05-10 16:44:59 +02:00
col.list[i] <- NA
}
}
2019-05-23 16:58:59 +02:00
if (!all(col.list %in% colnames(x))) {
2020-05-16 13:05:47 +02:00
if (warnings == TRUE) {
2019-10-11 17:21:02 +02:00
warning("Some columns do not exist and will be ignored: ",
2019-05-23 16:58:59 +02:00
col.list.bak[!(col.list %in% colnames(x))] %>% toString(),
2019-10-11 17:21:02 +02:00
".\nTHIS MAY STRONGLY INFLUENCE THE OUTCOME.",
2019-05-10 16:44:59 +02:00
immediate. = TRUE,
call. = FALSE)
}
}
col.list
}
2020-05-16 13:05:47 +02:00
col.list <- check_available_columns(x = x, col.list = col.list, warnings = warnings)
2018-07-19 15:11:23 +02:00
universal_1 <- col.list[universal_1]
universal_2 <- col.list[universal_2]
universal_3 <- col.list[universal_3]
universal_4 <- col.list[universal_4]
universal_5 <- col.list[universal_5]
universal_6 <- col.list[universal_6]
GramPos_1 <- col.list[GramPos_1]
GramPos_2 <- col.list[GramPos_2]
GramPos_3 <- col.list[GramPos_3]
GramPos_4 <- col.list[GramPos_4]
GramPos_5 <- col.list[GramPos_5]
GramPos_6 <- col.list[GramPos_6]
GramNeg_1 <- col.list[GramNeg_1]
GramNeg_2 <- col.list[GramNeg_2]
GramNeg_3 <- col.list[GramNeg_3]
GramNeg_4 <- col.list[GramNeg_4]
GramNeg_5 <- col.list[GramNeg_5]
GramNeg_6 <- col.list[GramNeg_6]
2018-07-17 13:02:05 +02:00
2018-07-19 15:11:23 +02:00
universal <- c(universal_1, universal_2, universal_3,
universal_4, universal_5, universal_6)
2019-10-11 17:21:02 +02:00
gram_positive <- c(universal,
2018-07-19 15:11:23 +02:00
GramPos_1, GramPos_2, GramPos_3,
GramPos_4, GramPos_5, GramPos_6)
2019-01-03 23:56:19 +01:00
gram_positive <- gram_positive[!is.null(gram_positive)]
2019-05-10 16:44:59 +02:00
gram_positive <- gram_positive[!is.na(gram_positive)]
if (length(gram_positive) < 12) {
2019-06-11 14:18:25 +02:00
warning("only using ", length(gram_positive), " different antibiotics as key antibiotics for Gram-positives. See ?key_antibiotics.", call. = FALSE)
2019-05-10 16:44:59 +02:00
}
2018-07-17 13:02:05 +02:00
2019-10-11 17:21:02 +02:00
gram_negative <- c(universal,
2018-07-19 15:11:23 +02:00
GramNeg_1, GramNeg_2, GramNeg_3,
GramNeg_4, GramNeg_5, GramNeg_6)
2019-01-03 23:56:19 +01:00
gram_negative <- gram_negative[!is.null(gram_negative)]
2019-05-10 16:44:59 +02:00
gram_negative <- gram_negative[!is.na(gram_negative)]
if (length(gram_negative) < 12) {
2019-06-11 14:18:25 +02:00
warning("only using ", length(gram_negative), " different antibiotics as key antibiotics for Gram-negatives. See ?key_antibiotics.", call. = FALSE)
2019-05-10 16:44:59 +02:00
}
2018-07-17 13:02:05 +02:00
2018-12-22 22:39:34 +01:00
# join to microorganisms data set
2020-05-16 13:05:47 +02:00
x <- x %>% as.data.frame(stringsAsFactors = FALSE)
x[, col_mo] <- as.mo(x[, col_mo, drop = TRUE])
x$gramstain <- mo_gramstain(x[, col_mo, drop = TRUE], language = NULL)
2020-05-16 13:05:47 +02:00
x$key_ab <- NA_character_
2020-05-16 20:08:21 +02:00
2018-07-17 13:02:05 +02:00
# Gram +
2020-05-16 13:05:47 +02:00
x$key_ab <- if_else(x$gramstain == "Gram-positive",
tryCatch(apply(X = x[, gram_positive],
MARGIN = 1,
FUN = function(x) paste(x, collapse = "")),
error = function(e) paste0(rep(".", 12), collapse = "")),
x$key_ab)
2018-07-17 13:02:05 +02:00
# Gram -
2020-05-16 13:05:47 +02:00
x$key_ab <- if_else(x$gramstain == "Gram-negative",
tryCatch(apply(X = x[, gram_negative],
MARGIN = 1,
FUN = function(x) paste(x, collapse = "")),
error = function(e) paste0(rep(".", 12), collapse = "")),
x$key_ab)
2018-07-17 13:02:05 +02:00
# format
2020-05-16 13:05:47 +02:00
key_abs <- toupper(gsub("[^SIR]", ".", gsub("(NA|NULL)", ".", x$key_ab)))
if (n_distinct(key_abs) == 1) {
warning("No distinct key antibiotics determined.", call. = FALSE)
}
2018-07-17 13:02:05 +02:00
key_abs
}
#' @rdname key_antibiotics
#' @export
2019-05-23 17:35:58 +02:00
key_antibiotics_equal <- function(y,
z,
2018-07-17 13:02:05 +02:00
type = c("keyantibiotics", "points"),
ignore_I = TRUE,
points_threshold = 2,
info = FALSE) {
2019-05-23 17:35:58 +02:00
# y is active row, z is lag
x <- y
y <- z
2018-07-17 13:02:05 +02:00
type <- type[1]
if (length(x) != length(y)) {
2019-10-11 17:21:02 +02:00
stop("Length of `x` and `y` must be equal.")
2018-07-17 13:02:05 +02:00
}
# only show progress bar on points or when at least 5000 isolates
info_needed <- info == TRUE & (type == "points" | length(x) > 5000)
2018-07-17 13:02:05 +02:00
result <- logical(length(x))
2018-07-23 10:35:39 +02:00
if (info_needed == TRUE) {
2020-03-14 14:05:43 +01:00
p <- progress_estimated(length(x))
2020-05-16 13:05:47 +02:00
on.exit(close(p))
}
2018-07-17 19:51:09 +02:00
2019-10-11 17:21:02 +02:00
for (i in seq_len(length(x))) {
2018-07-17 13:02:05 +02:00
if (info_needed == TRUE) {
2020-05-16 13:05:47 +02:00
p$tick()
2018-07-17 19:51:09 +02:00
}
if (is.na(x[i])) {
2019-10-11 17:21:02 +02:00
x[i] <- ""
}
if (is.na(y[i])) {
2019-10-11 17:21:02 +02:00
y[i] <- ""
2018-07-17 13:02:05 +02:00
}
if (x[i] == y[i]) {
2018-07-17 13:02:05 +02:00
result[i] <- TRUE
2018-07-17 13:02:05 +02:00
} else if (nchar(x[i]) != nchar(y[i])) {
2018-07-17 13:02:05 +02:00
result[i] <- FALSE
2018-07-17 13:02:05 +02:00
} else {
2018-07-17 13:02:05 +02:00
x_split <- strsplit(x[i], "")[[1]]
y_split <- strsplit(y[i], "")[[1]]
2018-07-17 13:02:05 +02:00
2019-10-11 17:21:02 +02:00
if (type == "keyantibiotics") {
2018-07-17 13:02:05 +02:00
if (ignore_I == TRUE) {
x_split[x_split == "I"] <- "."
y_split[y_split == "I"] <- "."
}
2018-07-17 13:02:05 +02:00
y_split[x_split == "."] <- "."
x_split[y_split == "."] <- "."
2018-07-17 13:02:05 +02:00
result[i] <- all(x_split == y_split)
2019-10-11 17:21:02 +02:00
} else if (type == "points") {
2018-07-17 19:51:09 +02:00
# count points for every single character:
# - no change is 0 points
# - I <-> S|R is 0.5 point
# - S|R <-> R|S is 1 point
# use the levels of as.rsi (S = 1, I = 2, R = 3)
2018-07-17 13:02:05 +02:00
suppressWarnings(x_split <- x_split %>% as.rsi() %>% as.double())
suppressWarnings(y_split <- y_split %>% as.rsi() %>% as.double())
points <- (x_split - y_split) %>% abs() %>% sum(na.rm = TRUE) / 2
result[i] <- points >= points_threshold
2018-07-17 13:02:05 +02:00
} else {
2019-10-11 17:21:02 +02:00
stop("`", type, '` is not a valid value for type, must be "points" or "keyantibiotics". See ?key_antibiotics')
2018-07-17 13:02:05 +02:00
}
}
}
if (info_needed == TRUE) {
2019-10-11 17:21:02 +02:00
cat("\n")
}
result
2018-07-17 13:02:05 +02:00
}