diff --git a/DESCRIPTION b/DESCRIPTION
index e535bbf5..4897140e 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,6 +1,6 @@
Package: AMR
-Version: 0.7.0.9000
-Date: 2019-06-03
+Version: 0.7.0.9001
+Date: 2019-06-07
Title: Antimicrobial Resistance Analysis
Authors@R: c(
person(
diff --git a/NAMESPACE b/NAMESPACE
index 9493fb50..4983e269 100755
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -173,6 +173,8 @@ export(resistance_predict)
export(right_join_microorganisms)
export(rsi_predict)
export(scale_rsi_colours)
+export(scale_type.ab)
+export(scale_type.mo)
export(scale_y_percent)
export(semi_join_microorganisms)
export(set_mo_source)
@@ -217,6 +219,8 @@ exportMethods(print.rsi)
exportMethods(pull.ab)
exportMethods(pull.atc)
exportMethods(pull.mo)
+exportMethods(scale_type.ab)
+exportMethods(scale_type.mo)
exportMethods(select.freq)
exportMethods(skewness)
exportMethods(skewness.data.frame)
@@ -241,6 +245,7 @@ importFrom(crayon,strip_style)
importFrom(crayon,underline)
importFrom(crayon,white)
importFrom(crayon,yellow)
+importFrom(data.table,address)
importFrom(data.table,as.data.table)
importFrom(data.table,data.table)
importFrom(data.table,setkey)
@@ -302,6 +307,7 @@ importFrom(microbenchmark,microbenchmark)
importFrom(rlang,as_label)
importFrom(rlang,enquos)
importFrom(rlang,eval_tidy)
+importFrom(scales,percent)
importFrom(stats,complete.cases)
importFrom(stats,fivenum)
importFrom(stats,glm)
diff --git a/NEWS.md b/NEWS.md
index 0962111c..640e8e0a 100755
--- a/NEWS.md
+++ b/NEWS.md
@@ -1,10 +1,26 @@
-# AMR 0.7.0.9000
+# AMR 0.7.0.9001
#### New
+* Support for all scientifically published pathotypes of *E. coli* to date. Supported are: AIEC (Adherent-Invasive *E. coli*), ATEC (Atypical Entero-pathogenic *E. coli*), DAEC (Diffusely Adhering *E. coli*), EAEC (Entero-Aggresive *E. coli*), EHEC (Entero-Haemorrhagic *E. coli*), EIEC (Entero-Invasive *E. coli*), EPEC (Entero-Pathogenic *E. coli*), ETEC (Entero-Toxigenic *E. coli*), NMEC (Neonatal Meningitis‐causing *E. coli*), STEC (Shiga-toxin producing *E. coli*) and UPEC (Uropathogenic *E. coli*). All these lead to the microbial ID of *E. coli*:
+ ```r
+ as.mo("UPEC")
+ # B_ESCHR_COL
+ mo_fullname("UPEC")
+ # "Escherichia coli"
+ ```
#### Changed
+* Fixed bug in translation of microorganism names
+* Fixed bug in determining taxonomic kingdoms
+* Algorithm improvements for `as.ab()` and `as.mo()` to understand even more severe misspelled input
+* Added `ggplot2` methods for automatically determining the scale type of classes `mo` and `ab`
+* Added names of object in the header in frequency tables, even when using pipes
+* Prevented `"bacteria"` from getting coerced by `as.ab()` because Bacterial is a brand name of trimethoprim (TMP)
+* Fixed a bug where setting an antibiotic would not work for `eucast_rules()` and `mdro()`
+* Fixed a EUCAST rule for Staphylococci, where amikacin resistance would not be inferred from tobramycin
#### Other
+* Fixed a note thrown by CRAN tests
# AMR 0.7.0
diff --git a/R/ab.R b/R/ab.R
index c90c206b..b39d0e4a 100755
--- a/R/ab.R
+++ b/R/ab.R
@@ -91,6 +91,11 @@ as.ab <- function(x) {
x_unknown <- c(x_unknown, x_bak[x[i] == x_bak_clean][1])
next
}
+ # prevent "bacteria" from coercing to TMP, since Bacterial is a brand name of it
+ if (identical(tolower(x[i]), "bacteria")) {
+ x_unknown <- c(x_unknown, x_bak[x[i] == x_bak_clean][1])
+ next
+ }
# exact AB code
found <- AMR::antibiotics[which(AMR::antibiotics$ab == toupper(x[i])),]$ab
@@ -162,23 +167,20 @@ as.ab <- function(x) {
}
x_spelling <- tolower(x[i])
x_spelling <- gsub("[iy]+", "[iy]+", x_spelling)
- x_spelling <- gsub("[sz]+", "[sz]+", x_spelling)
- x_spelling <- gsub("(c|k|q|qu)+", "(c|k|q|qu)+", x_spelling)
+ x_spelling <- gsub("(c|k|q|qu|s|z|x|ks)+", "(c|k|q|qu|s|z|x|ks)+", x_spelling)
x_spelling <- gsub("(ph|f|v)+", "(ph|f|v)+", x_spelling)
x_spelling <- gsub("(th|t)+", "(th|t)+", x_spelling)
- x_spelling <- gsub("(x|ks)+", "(x|ks)+", x_spelling)
x_spelling <- gsub("a+", "a+", x_spelling)
x_spelling <- gsub("e+", "e+", x_spelling)
x_spelling <- gsub("o+", "o+", x_spelling)
- # allow start with C/S/Z
- x_spelling <- gsub("^(\\(c\\|k\\|q\\|qu\\)|\\[sz\\])", "(c|k|q|qu|s|z)", x_spelling)
- x_spelling <- gsub("(c|k|q|qu)+[sz]", "(c|k|q|qu|s|x|z)", x_spelling, fixed = TRUE)
# allow any ending of -in/-ine and -im/-ime
x_spelling <- gsub("(\\[iy\\]\\+(n|m)|\\[iy\\]\\+(n|m)e\\+)$", "[iy]+(n|m)e*", x_spelling)
# allow any ending of -ol/-ole
x_spelling <- gsub("(o\\+l|o\\+le\\+)$", "o+le*", x_spelling)
# allow any ending of -on/-one
x_spelling <- gsub("(o\\+n|o\\+ne\\+)$", "o+ne*", x_spelling)
+ # replace multiple same characters to single one with '+', like "ll" -> "l+"
+ x_spelling <- gsub("(.)\\1+", "\\1+", x_spelling)
# try if name starts with it
found <- AMR::antibiotics[which(AMR::antibiotics$name %like% paste0("^", x_spelling)),]$ab
if (length(found) > 0) {
@@ -256,3 +258,13 @@ as.data.frame.ab <- function (x, ...) {
pull.ab <- function(.data, ...) {
pull(as.data.frame(.data), ...)
}
+
+#' @exportMethod scale_type.ab
+#' @export
+#' @noRd
+scale_type.ab <- function(x) {
+ # fix for:
+ # "Don't know how to automatically pick scale for object of type ab. Defaulting to continuous."
+ # "Error: Discrete value supplied to continuous scale"
+ "discrete"
+}
diff --git a/R/amr.R b/R/amr.R
index 5351cf9d..cbff6fb2 100644
--- a/R/amr.R
+++ b/R/amr.R
@@ -67,4 +67,5 @@
#' @rdname AMR
# # prevent NOTE on R >= 3.6
#' @importFrom microbenchmark microbenchmark
+#' @importFrom scales percent
NULL
diff --git a/R/eucast_rules.R b/R/eucast_rules.R
index 9b7b82c6..e6bb0a49 100755
--- a/R/eucast_rules.R
+++ b/R/eucast_rules.R
@@ -209,6 +209,12 @@ eucast_rules <- function(x,
stop("`col_mo` must be set")
}
+ decimal.mark <- getOption("OutDec")
+ big.mark <- ifelse(decimal.mark != ",", ",", ".")
+ formatnr <- function(x) {
+ trimws(format(x, big.mark = big.mark, decimal.mark = decimal.mark))
+ }
+
warned <- FALSE
txt_error <- function() { cat("", bgRed(white(" ERROR ")), "\n") }
@@ -219,7 +225,7 @@ eucast_rules <- function(x,
if (no_of_changes == 1) {
cat(blue(" (1 new change)\n"))
} else {
- cat(blue(paste0(" (", no_of_changes, " new changes)\n")))
+ cat(blue(paste0(" (", formatnr(no_of_changes), " new changes)\n")))
}
} else {
cat(green(" (no new changes)\n"))
@@ -664,12 +670,6 @@ eucast_rules <- function(x,
verbose_info <- verbose_info %>%
arrange(row, rule_group, rule_name, col)
- decimal.mark <- getOption("OutDec")
- big.mark <- ifelse(decimal.mark != ",", ",", ".")
- formatnr <- function(x) {
- trimws(format(x, big.mark = big.mark, decimal.mark = decimal.mark))
- }
-
cat(paste0("\n", silver(strrep("-", options()$width - 1)), "\n"))
cat(bold(paste('EUCAST rules', paste0(wouldve, 'affected'),
formatnr(n_distinct(verbose_info$row)),
diff --git a/R/first_isolate.R b/R/first_isolate.R
index 49a29a82..ba95f4a1 100755
--- a/R/first_isolate.R
+++ b/R/first_isolate.R
@@ -414,15 +414,15 @@ first_isolate <- function(x,
if (length(x) == 1) {
return(TRUE)
}
- indices = integer(0)
- start = x[1]
- ind = 1
- indices[ind] = ind
+ indices <- integer(0)
+ start <- x[1]
+ ind <- 1
+ indices[ind] <- ind
for (i in 2:length(x)) {
- if (as.numeric(x[i] - start >= episode_days)) {
- ind = ind + 1
- indices[ind] = i
- start = x[i]
+ if (isTRUE(as.numeric(x[i] - start) >= episode_days)) {
+ ind <- ind + 1
+ indices[ind] <- i
+ start <- x[i]
}
}
result <- rep(FALSE, length(x))
diff --git a/R/freq.R b/R/freq.R
index 07faa5bd..a234593a 100755
--- a/R/freq.R
+++ b/R/freq.R
@@ -238,7 +238,13 @@ freq <- function(x,
x.name <- x.name %>% strsplit("%>%", fixed = TRUE) %>% unlist() %>% .[1] %>% trimws()
}
if (x.name == ".") {
- x.name <- "a data.frame"
+ # passed on with pipe
+ x.name <- get_data_source_name(x)
+ if (!is.null(x.name)) {
+ x.name <- paste0("`", x.name, "`")
+ } else {
+ x.name <- "a data.frame"
+ }
} else {
x.name <- paste0("`", x.name, "`")
}
@@ -1230,3 +1236,21 @@ format.freq <- function(x, digits = 1, ...) {
x$cum_percent <- percent(x$cum_percent, round = digits, force_zero = TRUE)
base::format.data.frame(x, ...)
}
+
+#' @importFrom data.table address
+get_data_source_name <- function(x, else_txt = NULL) {
+ obj_addr <- address(x)
+ # try global environment
+ addrs <- unlist(lapply(ls(".GlobalEnv"), function(x) address(get(x))))
+ res <- ls(".GlobalEnv")[addrs == obj_addr]
+ if (length(res) == 0) {
+ # check AMR package - some users might use our data sets for testing
+ addrs <- unlist(lapply(ls("package:AMR"), function(x) address(get(x))))
+ res <- ls("package:AMR")[addrs == obj_addr]
+ }
+ if (length(res) == 0) {
+ else_txt
+ } else {
+ res
+ }
+}
diff --git a/R/misc.R b/R/misc.R
index 799b0631..e0cf3840 100755
--- a/R/misc.R
+++ b/R/misc.R
@@ -172,16 +172,19 @@ get_column_abx <- function(x,
# get_column_abx(septic_patients %>% rename(thisone = AMX), amox = "thisone")
dots <- list(...)
if (length(dots) > 0) {
- dots <- unlist(dots)
newnames <- suppressWarnings(as.ab(names(dots)))
if (any(is.na(newnames))) {
warning("Invalid antibiotic reference(s): ", toString(names(dots)[is.na(newnames)]),
call. = FALSE, immediate. = TRUE)
}
+ # turn all NULLs to NAs
+ dots <- unlist(lapply(dots, function(x) if (is.null(x)) NA else x))
names(dots) <- newnames
dots <- dots[!is.na(names(dots))]
# merge, but overwrite automatically determined ones by 'dots'
x <- c(x[!x %in% dots & !names(x) %in% names(dots)], dots)
+ # delete NAs, this will make eucast_rules(... TMP = NULL) work to prevent TMP from being used
+ x <- x[!is.na(x)]
}
# sort on name
diff --git a/R/mo.R b/R/mo.R
index 9ba0252b..1e375073 100755
--- a/R/mo.R
+++ b/R/mo.R
@@ -485,18 +485,21 @@ exec_as.mo <- function(x,
# remove genus as first word
x <- gsub("^Genus ", "", x)
# allow characters that resemble others
- x <- gsub("[iy]+", "[iy]+", x, ignore.case = TRUE)
- x <- gsub("[sz]+", "[sz]+", x, ignore.case = TRUE)
- x <- gsub("(c|k|q|qu)+", "(c|k|q|qu)+", x, ignore.case = TRUE)
- x <- gsub("(ph|f|v)+", "(ph|f|v)+", x, ignore.case = TRUE)
- x <- gsub("(th|t)+", "(th|t)+", x, ignore.case = TRUE)
- x <- gsub("a+", "a+", x, ignore.case = TRUE)
- # allow any ending of -um, -us, -ium, -ius and -a (needs perl for the negative backward lookup):
- x <- gsub("(um|u\\[sz\\]\\+|\\[iy\\]\\+um|\\[iy\\]\\+u\\[sz\\]\\+|a\\+)(?![a-z[])",
- "(um|us|ium|ius|a)", x, ignore.case = TRUE, perl = TRUE)
- x <- gsub("e+", "e+", x, ignore.case = TRUE)
- x <- gsub("o+", "o+", x, ignore.case = TRUE)
-
+ if (initial_search == FALSE) {
+ x <- tolower(x)
+ x <- gsub("[iy]+", "[iy]+", x)
+ x <- gsub("(c|k|q|qu|s|z|x|ks)+", "(c|k|q|qu|s|z|x|ks)+", x)
+ x <- gsub("(ph|f|v)+", "(ph|f|v)+", x)
+ x <- gsub("(th|t)+", "(th|t)+", x)
+ x <- gsub("a+", "a+", x)
+ x <- gsub("u+", "u+", x)
+ # allow any ending of -um, -us, -ium, -ius and -a (needs perl for the negative backward lookup):
+ x <- gsub("(um|u\\[sz\\]\\+|\\[iy\\]\\+um|\\[iy\\]\\+u\\[sz\\]\\+|a\\+)(?![a-z[])",
+ "(um|us|ium|ius|a)", x, ignore.case = TRUE, perl = TRUE)
+ x <- gsub("e+", "e+", x, ignore.case = TRUE)
+ x <- gsub("o+", "o+", x, ignore.case = TRUE)
+ x <- gsub("(.)\\1+", "\\1+", x)
+ }
x <- strip_whitespace(x)
x_trimmed <- x
@@ -639,7 +642,7 @@ exec_as.mo <- function(x,
}
next
}
- if (toupper(x_backup_without_spp[i]) %in% c("EHEC", "EPEC", "EIEC", "STEC", "ATEC")
+ if (toupper(x_backup_without_spp[i]) %in% c("AIEC", "ATEC", "DAEC", "EAEC", "EHEC", "EIEC", "EPEC", "ETEC", "NMEC", "STEC", "UPEC")
| x_backup_without_spp[i] %like% "O?(26|103|104|104|111|121|145|157)") {
x[i] <- microorganismsDT[mo == 'B_ESCHR_COL', ..property][[1]][1L]
if (initial_search == TRUE) {
@@ -1481,3 +1484,13 @@ translate_allow_uncertain <- function(allow_uncertain) {
}
allow_uncertain
}
+
+#' @exportMethod scale_type.mo
+#' @export
+#' @noRd
+scale_type.mo <- function(x) {
+ # fix for:
+ # "Don't know how to automatically pick scale for object of type mo. Defaulting to continuous."
+ # "Error: Discrete value supplied to continuous scale"
+ "discrete"
+}
diff --git a/R/mo_property.R b/R/mo_property.R
index 3d0c6024..cb7aeb41 100755
--- a/R/mo_property.R
+++ b/R/mo_property.R
@@ -238,7 +238,8 @@ mo_kingdom <- function(x, language = get_locale(), ...) {
x <- as.mo(x, ...)
kngdm <- mo_validate(x = x, property = "kingdom", ...)
if (language != "en") {
- kngdm[x == "UNKNOWN"] <- t(kngdm[x == "UNKNOWN"], language = language)
+ # translate only unknown, so "Bacteria" (the official taxonomic name) would not change
+ kngdm[identical(x, "UNKNOWN")] <- t(kngdm[identical(x, "UNKNOWN")], language = language)
}
kngdm
}
diff --git a/R/sysdata.rda b/R/sysdata.rda
index ee6d78c5..7c43f0a4 100644
Binary files a/R/sysdata.rda and b/R/sysdata.rda differ
diff --git a/R/zzz.R b/R/zzz.R
index 9cc92b47..f21644bf 100755
--- a/R/zzz.R
+++ b/R/zzz.R
@@ -51,6 +51,31 @@
}
+
+.onAttach <- function(...) {
+ if (interactive()) {
+ console_width <- options()$width - 1
+ url <- "https://www.surveymonkey.com/r/AMR_for_R"
+ txt <- paste("Thanks for using the AMR package!",
+ "As researchers, we are interested in how and why you use this package and if there are things you're missing from it.",
+ "Please fill in our 2-minute survey at:", url)
+
+ # make it honour new lines bases on console width:
+ txt <- unlist(strsplit(txt, " "))
+ txt_new <- ""
+ total_chars <- 0
+ for (i in 1:length(txt)) {
+ total_chars <- total_chars + nchar(txt[i]) + 1
+ if (total_chars > console_width) {
+ txt_new <- paste0(txt_new, "\n")
+ total_chars <- 0
+ }
+ txt_new <- paste0(txt_new, txt[i], " ")
+ }
+ packageStartupMessage(txt_new)
+ }
+}
+
#' @importFrom data.table as.data.table setkey
make_DT <- function() {
microorganismsDT <- as.data.table(AMR::microorganisms)
diff --git a/data-raw/eucast_rules.tsv b/data-raw/eucast_rules.tsv
index 2537e598..5df26eb4 100644
--- a/data-raw/eucast_rules.tsv
+++ b/data-raw/eucast_rules.tsv
@@ -165,7 +165,7 @@ family is Enterobacteriaceae TIC, PIP R, S PIP R Table 09: Interpretive rules fo
genus is .* ERY S AZM, CLR S Table 11: Interpretive rules for macrolides, lincosamides, and streptogramins Expert Rules
genus is .* ERY I AZM, CLR I Table 11: Interpretive rules for macrolides, lincosamides, and streptogramins Expert Rules
genus is .* ERY R AZM, CLR R Table 11: Interpretive rules for macrolides, lincosamides, and streptogramins Expert Rules
-genus is Staphylococcus TOB R KAN, amik R Table 12: Interpretive rules for aminoglycosides Expert Rules
+genus is Staphylococcus TOB R KAN, AMK R Table 12: Interpretive rules for aminoglycosides Expert Rules
genus is Staphylococcus GEN R aminoglycosides R Table 12: Interpretive rules for aminoglycosides Expert Rules
family is Enterobacteriaceae GEN, TOB I, S GEN R Table 12: Interpretive rules for aminoglycosides Expert Rules
family is Enterobacteriaceae GEN, TOB R, I TOB R Table 12: Interpretive rules for aminoglycosides Expert Rules
diff --git a/data-raw/internals.R b/data-raw/internals.R
index 0c55d4aa..29396bbe 100644
--- a/data-raw/internals.R
+++ b/data-raw/internals.R
@@ -18,7 +18,7 @@ eucast_rules_file <- dplyr::arrange(
reference.rule)
# Translations -----
-translations_file <- utils::read.table(file = "data-raw/translations.tsv",
+translations_file <- utils::read.delim(file = "data-raw/translations.tsv",
sep = "\t",
stringsAsFactors = FALSE,
header = TRUE,
@@ -27,7 +27,9 @@ translations_file <- utils::read.table(file = "data-raw/translations.tsv",
strip.white = TRUE,
encoding = "UTF-8",
fileEncoding = "UTF-8",
- na.strings = c(NA, "", NULL))
+ na.strings = c(NA, "", NULL),
+ allowEscapes = TRUE, # else "\\1" will be imported as "\\\\1"
+ quote = "")
# Export to package as internal data ----
usethis::use_data(eucast_rules_file, translations_file,
diff --git a/docs/LICENSE-text.html b/docs/LICENSE-text.html
index de5cd3cd..9b3d7e15 100644
--- a/docs/LICENSE-text.html
+++ b/docs/LICENSE-text.html
@@ -78,7 +78,7 @@
AMR (for R)
- 0.7.0.9000
+ 0.7.0.9001
diff --git a/docs/articles/AMR.html b/docs/articles/AMR.html
index deb20be5..32705737 100644
--- a/docs/articles/AMR.html
+++ b/docs/articles/AMR.html
@@ -40,7 +40,7 @@
AMR (for R)
- 0.7.0
+ 0.7.0.9000
@@ -199,7 +199,7 @@
How to conduct AMR analysis
Matthijs S. Berends
-
03 June 2019
+
07 June 2019
AMR.Rmd
@@ -208,7 +208,7 @@
-
Note: values on this page will change with every website update since they are based on randomly created values and the page was written in R Markdown. However, the methodology remains unchanged. This page was generated on 03 June 2019.
+
Note: values on this page will change with every website update since they are based on randomly created values and the page was written in R Markdown. However, the methodology remains unchanged. This page was generated on 07 June 2019.
Introduction
@@ -224,21 +224,21 @@
-
2019-06-03
+
2019-06-07
abcd
Escherichia coli
S
S
-
2019-06-03
+
2019-06-07
abcd
Escherichia coli
S
R
-
2019-06-03
+
2019-06-07
efgh
Escherichia coli
R
@@ -334,19 +334,52 @@
-
2010-12-01
-
Y6
-
Hospital C
+
2010-01-26
+
S3
+
Hospital B
+
Escherichia coli
+
R
+
I
+
R
+
S
+
F
+
+
+
2010-08-26
+
G7
+
Hospital D
Escherichia coli
R
S
S
S
-
F
+
M
+
+
+
2016-05-04
+
B8
+
Hospital A
+
Escherichia coli
+
S
+
S
+
R
+
S
+
M
-
2011-05-31
-
C8
+
2016-11-19
+
E10
+
Hospital D
+
Streptococcus pneumoniae
+
S
+
S
+
S
+
S
+
M
+
+
+
2013-07-13
+
G3
Hospital A
Escherichia coli
R
@@ -355,45 +388,12 @@
S
M
-
-
2012-04-18
-
Z6
-
Hospital D
-
Escherichia coli
-
R
-
S
-
R
-
S
-
F
-
-
2011-04-24
-
W4
+
2017-05-23
+
V3
Hospital C
Staphylococcus aureus
S
-
R
-
R
-
S
-
F
-
-
-
2011-11-05
-
A9
-
Hospital C
-
Escherichia coli
-
R
-
S
-
R
-
S
-
M
-
-
-
2016-09-07
-
Y6
-
Hospital B
-
Staphylococcus aureus
-
S
S
S
S
@@ -409,7 +409,7 @@
Cleaning the data
Use the frequency table function freq() to look specifically for unique values in any variable. For example, for the gender variable:
data %>%freq(gender) # this would be the same: freq(data$gender)
-
# Frequency table of `gender` from a data.frame (20,000 x 9)
+
# Frequency table of `gender` from `data` (20,000 x 9)
#
# Class: factor (numeric)
# Length: 20,000 (of which NA: 0 = 0.00%)
@@ -418,8 +418,8 @@
#
# Item Count Percent Cum. Count Cum. Percent
# --- ----- ------- -------- ----------- -------------
-# 1 M 10,407 52.0% 10,407 52.0%
-# 2 F 9,593 48.0% 20,000 100.0%
+# 1 M 10,368 51.8% 10,368 51.8%
+# 2 F 9,632 48.2% 20,000 100.0%
So, we can draw at least two conclusions immediately. From a data scientist perspective, the data looks clean: only values M and F. From a researcher perspective: there are slightly more men. Nothing we didn’t already know.
The data is already quite clean, but we still need to transform some variables. The bacteria column now consists of text, and we want to add more variables based on microbial IDs later on. So, we will transform this column to valid IDs. The mutate() function of the dplyr package makes this really easy:
For future use, the above two syntaxes can be shortened with the filter_first_isolate() function:
@@ -536,8 +536,8 @@
1
-
2010-03-08
-
C7
+
2010-01-16
+
V9
B_ESCHR_COL
S
S
@@ -547,10 +547,10 @@
2
-
2010-04-14
-
C7
+
2010-02-23
+
V9
B_ESCHR_COL
-
R
+
S
S
S
S
@@ -558,8 +558,8 @@
3
-
2010-04-18
-
C7
+
2010-04-05
+
V9
B_ESCHR_COL
S
S
@@ -569,19 +569,19 @@
4
-
2010-04-22
-
C7
+
2010-04-28
+
V9
B_ESCHR_COL
S
S
-
R
+
S
S
FALSE
5
-
2010-05-30
-
C7
+
2010-05-20
+
V9
B_ESCHR_COL
S
S
@@ -591,19 +591,19 @@
6
-
2010-10-09
-
C7
+
2010-07-07
+
V9
B_ESCHR_COL
S
S
-
S
R
+
S
FALSE
7
-
2011-01-26
-
C7
+
2010-09-11
+
V9
B_ESCHR_COL
S
S
@@ -613,8 +613,8 @@
8
-
2011-02-19
-
C7
+
2010-09-19
+
V9
B_ESCHR_COL
S
S
@@ -624,29 +624,29 @@
9
-
2011-03-25
-
C7
+
2010-10-07
+
V9
B_ESCHR_COL
-
R
S
S
S
-
TRUE
+
S
+
FALSE
10
-
2011-04-17
-
C7
+
2011-01-14
+
V9
B_ESCHR_COL
R
S
-
R
+
S
S
FALSE
-
Only 2 isolates are marked as ‘first’ according to CLSI guideline. But when reviewing the antibiogram, it is obvious that some isolates are absolutely different strains and should be included too. This is why we weigh isolates, based on their antibiogram. The key_antibiotics() function adds a vector with 18 key antibiotics: 6 broad spectrum ones, 6 small spectrum for Gram negatives and 6 small spectrum for Gram positives. These can be defined by the user.
+
Only 1 isolates are marked as ‘first’ according to CLSI guideline. But when reviewing the antibiogram, it is obvious that some isolates are absolutely different strains and should be included too. This is why we weigh isolates, based on their antibiogram. The key_antibiotics() function adds a vector with 18 key antibiotics: 6 broad spectrum ones, 6 small spectrum for Gram negatives and 6 small spectrum for Gram positives. These can be defined by the user.
If a column exists with a name like ‘key(…)ab’ the first_isolate() function will automatically use it and determine the first weighted isolates. Mind the NOTEs in below output:
Instead of 2, now 9 isolates are flagged. In total, 75.4% of all isolates are marked ‘first weighted’ - 47.1% more than when using the CLSI guideline. In real life, this novel algorithm will yield 5-10% more isolates than the classic CLSI guideline.
+
Instead of 1, now 4 isolates are flagged. In total, 75.4% of all isolates are marked ‘first weighted’ - 46.9% more than when using the CLSI guideline. In real life, this novel algorithm will yield 5-10% more isolates than the classic CLSI guideline.
The functions portion_S(), portion_SI(), portion_I(), portion_IR() and portion_R() can be used to determine the portion of a specific antimicrobial outcome. As per the EUCAST guideline of 2019, we calculate resistance as the portion of R (portion_R()) and susceptibility as the portion of S and I (portion_SI()). These functions can be used on their own:
In the table above, all measurements are shown in milliseconds (thousands of seconds). A value of 5 milliseconds means it can determine 200 input values per second. It case of 100 milliseconds, this is only 10 input values per second. The second input is the only one that has to be looked up thoroughly. All the others are known codes (the first one is a WHONET code) or common laboratory codes, or common full organism names like the last one. Full organism names are always preferred.
To achieve this speed, the as.mo function also takes into account the prevalence of human pathogenic microorganisms. The downside is of course that less prevalent microorganisms will be determined less fast. See this example for the ID of Thermus islandicus (B_THERMS_ISL), a bug probably never found before in humans:
That takes 8.1 times as much time on average. A value of 100 milliseconds means it can only determine ~10 different input values per second. We can conclude that looking up arbitrary codes of less prevalent microorganisms is the worst way to go, in terms of calculation performance. Full names (like Thermus islandicus) are almost fast - these are the most probable input from most data sets.
That takes 8.6 times as much time on average. A value of 100 milliseconds means it can only determine ~10 different input values per second. We can conclude that looking up arbitrary codes of less prevalent microorganisms is the worst way to go, in terms of calculation performance. Full names (like Thermus islandicus) are almost fast - these are the most probable input from most data sets.
In the figure below, we compare Escherichia coli (which is very common) with Prevotella brevis (which is moderately common) and with Thermus islandicus (which is very uncommon):
So going from mo_fullname("Staphylococcus aureus") to "Staphylococcus aureus" takes 0.0018 seconds - it doesn’t even start calculating if the result would be the same as the expected resulting value. That goes for all helper functions:
So going from mo_fullname("Staphylococcus aureus") to "Staphylococcus aureus" takes 0.002 seconds - it doesn’t even start calculating if the result would be the same as the expected resulting value. That goes for all helper functions:
Of course, when running mo_phylum("Firmicutes") the function has zero knowledge about the actual microorganism, namely S. aureus. But since the result would be "Firmicutes" too, there is no point in calculating the result. And because this package ‘knows’ all phyla of all known bacteria (according to the Catalogue of Life), it can just return the initial value immediately.
Frequency table of hospital_id from a data.frame (2,000 x 49)
+
Frequency table of hospital_id from septic_patients (2,000 x 49)
Class: factor (numeric)
Length: 2,000 (of which NA: 0 = 0.00%)
Levels: 4: A, B, C, D
@@ -619,7 +619,7 @@ Unique: 4
All classes will be printed into the header. Variables with the new rsi class of this AMR package are actually ordered factors and have three classes (look at Class in the header):
Frequency table of date from a data.frame (2,000 x 49)
+
Frequency table of date from septic_patients (2,000 x 49)
Class: Date (numeric)
Length: 2,000 (of which NA: 0 = 0.00%)
Unique: 1,140
@@ -752,7 +752,7 @@ Median: 31 July 2009 (47.39%)
With the na.rm parameter you can remove NA values from the frequency table (defaults to TRUE, but the number of NA values will always be shown into the header):
Frequency table of hospital_id from a data.frame (2,000 x 49)
+
Frequency table of hospital_id from septic_patients (2,000 x 49)
Class: factor (numeric)
Length: 2,000 (of which NA: 0 = 0.00%)
Levels: 4: A, B, C, D
@@ -864,7 +864,7 @@ Unique: 4
The markdown parameter is TRUE at default in non-interactive sessions, like in reports created with R Markdown. This will always print all rows, unless nmax is set. Without markdown (like in regular R), a frequency table would print like:
Support for all scientifically published pathotypes of E. coli to date. Supported are: AIEC (Adherent-Invasive E. coli), ATEC (Atypical Entero-pathogenic E. coli), DAEC (Diffusely Adhering E. coli), EAEC (Entero-Aggresive E. coli), EHEC (Entero-Haemorrhagic E. coli), EIEC (Entero-Invasive E. coli), EPEC (Entero-Pathogenic E. coli), ETEC (Entero-Toxigenic E. coli), NMEC (Neonatal Meningitis‐causing E. coli), STEC (Shiga-toxin producing E. coli) and UPEC (Uropathogenic E. coli). All these lead to the microbial ID of E. coli:
The antibiotics data set will be searched, after which the input data will be checked for column names with a value in any abbreviations, codes or official names found in the antibiotics data set. For example:
These functions use as.atc() internally. The old atc_property has been renamed atc_online_property(). This is done for two reasons: firstly, not all ATC codes are of antibiotics (ab) but can also be of antivirals or antifungals. Secondly, the input must have class atc or must be coerable to this class. Properties of these classes should start with the same class name, analogous to as.mo() and e.g. mo_genus.
@@ -443,20 +467,20 @@ These functions use as.atc()
New function age_groups() to split ages into custom or predefined groups (like children or elderly). This allows for easier demographic antimicrobial resistance analysis per age group.
Uncertainty of the algorithm is now divided into four levels, 0 to 3, where the default allow_uncertain = TRUE is equal to uncertainty level 2. Run ?as.mo for more info about these levels.
Implemented the latest publication of Becker et al. (2019), for categorising coagulase-negative Staphylococci
All microbial IDs that found are now saved to a local file ~/.Rhistory_mo. Use the new function clean_mo_history() to delete this file, which resets the algorithms.
Incoercible results will now be considered ‘unknown’, MO code UNKNOWN. On foreign systems, properties of these will be translated to all languages already previously supported: German, Dutch, French, Italian, Spanish and Portuguese:
Added parameter combine_IR (TRUE/FALSE) to functions portion_df and count_df, to indicate that all values of I and R must be merged into one, so the output only consists of S vs. IR (susceptible vs. non-susceptible)
Fix for portion_*(..., as_percent = TRUE) when minimal number of isolates would not be met
Functions as.mo and is.mo as replacements for as.bactid and is.bactid (since the microoganisms data set not only contains bacteria). These last two functions are deprecated and will be removed in a future release. The as.mo function determines microbial IDs using intelligent rules:
Added parameter reference_df for as.mo, so users can supply their own microbial IDs, name or codes as a reference table
Renamed all previous references to bactid to mo, like:
@@ -809,12 +833,12 @@ Using as.mo(..., allow_uncertain = 3)Added three antimicrobial agents to the antibiotics data set: Terbinafine (D01BA02), Rifaximin (A07AA11) and Isoconazole (D01AC05)
Added 163 trade names to the antibiotics data set, it now contains 298 different trade names in total, e.g.: