P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2025-10-31 01:28:17 +01:00
Code Releases Activity

remove MO_lookup from sysdata.rda

Browse Source
This commit is contained in:
dr. M.S. (Matthijs) Berends
2023-01-21 19:55:19 +01:00
parent 79c8415d3e
commit 8a92c5a869
16 changed files with 89 additions and 236 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
R/aa_amr-package.R
View File

@@ -32,7 +32,7 @@
#' @description #' @description
#' Welcome to the `AMR` package. #' Welcome to the `AMR` package.
#' #'
#' The `AMR` package is a [free and open-source](https://msberends.github.io/AMR#copyright) R package with [zero dependencies](https://en.wikipedia.org/wiki/Dependency_hell) to simplify the analysis and prediction of Antimicrobial Resistance (AMR) and to work with microbial and antimicrobial data and properties, by using evidence-based methods. **Our aim is to provide a standard** for clean and reproducible AMR data analysis, that can therefore empower epidemiological analyses to continuously enable surveillance and treatment evaluation in any setting. [Many different researchers](https://msberends.github.io/AMR/authors.html) from around the globe are continually helping us to make this a successful and durable project! #' The `AMR` package is a [free and open-source](https://msberends.github.io/AMR/#copyright) R package with [zero dependencies](https://en.wikipedia.org/wiki/Dependency_hell) to simplify the analysis and prediction of Antimicrobial Resistance (AMR) and to work with microbial and antimicrobial data and properties, by using evidence-based methods. **Our aim is to provide a standard** for clean and reproducible AMR data analysis, that can therefore empower epidemiological analyses to continuously enable surveillance and treatment evaluation in any setting. [Many different researchers](https://msberends.github.io/AMR/authors.html) from around the globe are continually helping us to make this a successful and durable project!
#' #'
#' This work was published in the Journal of Statistical Software (Volume 104(3); [DOI 10.18637/jss.v104.i03](https://doi.org/10.18637/jss.v104.i03)) and formed the basis of two PhD theses ([DOI 10.33612/diss.177417131](https://doi.org/10.33612/diss.177417131) and [DOI 10.33612/diss.192486375](https://doi.org/10.33612/diss.192486375)). #' This work was published in the Journal of Statistical Software (Volume 104(3); [DOI 10.18637/jss.v104.i03](https://doi.org/10.18637/jss.v104.i03)) and formed the basis of two PhD theses ([DOI 10.33612/diss.177417131](https://doi.org/10.33612/diss.177417131) and [DOI 10.33612/diss.192486375](https://doi.org/10.33612/diss.192486375)).
#' #'

34
R/aa_helper_functions.R
View File

@@ -225,6 +225,8 @@ search_type_in_df <- function(x, type, info = TRUE) {
# -- mo # -- mo
if (type == "mo") { if (type == "mo") {
add_MO_lookup_to_AMR_env()
if (any(vapply(FUN.VALUE = logical(1), x, is.mo))) { if (any(vapply(FUN.VALUE = logical(1), x, is.mo))) {
# take first 'mo' column # take first 'mo' column
found <- colnames(x)[vapply(FUN.VALUE = logical(1), x, is.mo)] found <- colnames(x)[vapply(FUN.VALUE = logical(1), x, is.mo)]
@@ -1379,6 +1381,38 @@ add_intrinsic_resistance_to_AMR_env <- function() {
} }
} }
add_MO_lookup_to_AMR_env <- function() {
# for all MO functions, saves a lot of time on package load and in package size
if (is.null(AMR_env$MO_lookup)) {
MO_lookup <- AMR::microorganisms
MO_lookup$kingdom_index <- NA_real_
MO_lookup[which(MO_lookup$kingdom == "Bacteria" | MO_lookup$mo == "UNKNOWN"), "kingdom_index"] <- 1
MO_lookup[which(MO_lookup$kingdom == "Fungi"), "kingdom_index"] <- 2
MO_lookup[which(MO_lookup$kingdom == "Protozoa"), "kingdom_index"] <- 3
MO_lookup[which(MO_lookup$kingdom == "Archaea"), "kingdom_index"] <- 4
# all the rest
MO_lookup[which(is.na(MO_lookup$kingdom_index)), "kingdom_index"] <- 5
# the fullname lowercase, important for the internal algorithms in as.mo()
MO_lookup$fullname_lower <- tolower(trimws(paste(
MO_lookup$genus,
MO_lookup$species,
MO_lookup$subspecies
)))
ind <- MO_lookup$genus == "" | grepl("^[(]unknown ", MO_lookup$fullname, perl = TRUE)
MO_lookup[ind, "fullname_lower"] <- tolower(MO_lookup[ind, "fullname", drop = TRUE])
MO_lookup$fullname_lower <- trimws(gsub("[^.a-z0-9/ \\-]+", "", MO_lookup$fullname_lower, perl = TRUE))
# special for Salmonella - they have cities as subspecies but not the species (enterica) in the fullname:
MO_lookup$fullname_lower[which(MO_lookup$subspecies %like_case% "^[A-Z]")] <- gsub(" enterica ", " ", MO_lookup$fullname_lower[which(MO_lookup$subspecies %like_case% "^[A-Z]")], fixed = TRUE)
MO_lookup$full_first <- substr(MO_lookup$fullname_lower, 1, 1)
MO_lookup$species_first <- tolower(substr(MO_lookup$species, 1, 1)) # tolower for groups (Streptococcus, Salmonella)
MO_lookup$subspecies_first <- tolower(substr(MO_lookup$subspecies, 1, 1)) # tolower for Salmonella serovars
AMR_env$MO_lookup <- MO_lookup
}
}
trimws2 <- function(..., whitespace = "[\u0009\u000A\u000B\u000C\u000D\u0020\u0085\u00A0\u1680\u180E\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007\u2008\u2009\u200A\u200B\u200C\u200D\u2028\u2029\u202F\u205F\u2060\u3000\uFEFF]") { trimws2 <- function(..., whitespace = "[\u0009\u000A\u000B\u000C\u000D\u0020\u0085\u00A0\u1680\u180E\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007\u2008\u2009\u200A\u200B\u200C\u200D\u2028\u2029\u202F\u205F\u2060\u3000\uFEFF]") {
# this is even faster than trimws() itself which sets " \t\n\r". # this is even faster than trimws() itself which sets " \t\n\r".
trimws(..., whitespace = whitespace) trimws(..., whitespace = whitespace)

8
R/custom_microorganisms.R
View File

@@ -124,6 +124,8 @@ add_custom_microorganisms <- function(x) {
meet_criteria(x, allow_class = "data.frame") meet_criteria(x, allow_class = "data.frame")
stop_ifnot("genus" %in% tolower(colnames(x)), paste0("`x` must contain column 'genus'.")) stop_ifnot("genus" %in% tolower(colnames(x)), paste0("`x` must contain column 'genus'."))
add_MO_lookup_to_AMR_env()
# remove any extra class/type, such as grouped tbl, or data.table: # remove any extra class/type, such as grouped tbl, or data.table:
x <- as.data.frame(x, stringsAsFactors = FALSE) x <- as.data.frame(x, stringsAsFactors = FALSE)
colnames(x) <- tolower(colnames(x)) colnames(x) <- tolower(colnames(x))
@@ -269,7 +271,11 @@ add_custom_microorganisms <- function(x) {
#' @export #' @export
clear_custom_microorganisms <- function() { clear_custom_microorganisms <- function() {
n <- nrow(AMR_env$MO_lookup) n <- nrow(AMR_env$MO_lookup)
AMR_env$MO_lookup <- create_MO_lookup()
# reset
AMR_env$MO_lookup <- NULL
add_MO_lookup_to_AMR_env()
n2 <- nrow(AMR_env$MO_lookup) n2 <- nrow(AMR_env$MO_lookup)
AMR_env$custom_mo_codes <- character(0) AMR_env$custom_mo_codes <- character(0)
AMR_env$mo_previously_coerced <- AMR_env$mo_previously_coerced[which(AMR_env$mo_previously_coerced$mo %in% AMR_env$MO_lookup$mo), , drop = FALSE] AMR_env$mo_previously_coerced <- AMR_env$mo_previously_coerced[which(AMR_env$mo_previously_coerced$mo %in% AMR_env$MO_lookup$mo), , drop = FALSE]

2
R/eucast_rules.R
View File

@@ -182,6 +182,8 @@ eucast_rules <- function(x,
meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1) meet_criteria(only_sir_columns, allow_class = "logical", has_length = 1)
meet_criteria(custom_rules, allow_class = "custom_eucast_rules", allow_NULL = TRUE) meet_criteria(custom_rules, allow_class = "custom_eucast_rules", allow_NULL = TRUE)
add_MO_lookup_to_AMR_env()
if ("custom" %in% rules && is.null(custom_rules)) { if ("custom" %in% rules && is.null(custom_rules)) {
warning_("in `eucast_rules()`: no custom rules were set with the `custom_rules` argument", warning_("in `eucast_rules()`: no custom rules were set with the `custom_rules` argument",
immediate = TRUE immediate = TRUE

2
R/italicise_taxonomy.R
View File

@@ -51,6 +51,8 @@ italicise_taxonomy <- function(string, type = c("markdown", "ansi")) {
meet_criteria(string, allow_class = "character") meet_criteria(string, allow_class = "character")
meet_criteria(type, allow_class = "character", has_length = 1, is_in = c("markdown", "ansi")) meet_criteria(type, allow_class = "character", has_length = 1, is_in = c("markdown", "ansi"))
add_MO_lookup_to_AMR_env()
if (type == "markdown") { if (type == "markdown") {
before <- "*" before <- "*"
after <- "*" after <- "*"

2
R/join_microorganisms.R
View File

@@ -127,6 +127,8 @@ anti_join_microorganisms <- function(x, by = NULL, ...) {
} }
join_microorganisms <- function(type, x, by, suffix, ...) { join_microorganisms <- function(type, x, by, suffix, ...) {
add_MO_lookup_to_AMR_env()
if (!is.data.frame(x)) { if (!is.data.frame(x)) {
if (pkg_is_available("tibble", also_load = FALSE)) { if (pkg_is_available("tibble", also_load = FALSE)) {
x <- import_fn("tibble", "tibble")(mo = x) x <- import_fn("tibble", "tibble")(mo = x)

188
R/mdro.R
View File

@@ -325,7 +325,7 @@ mdro <- function(x = NULL,
"No column found as input for `col_mo`, ", "No column found as input for `col_mo`, ",
font_bold(paste0("assuming all rows contain ", font_italic("Mycobacterium tuberculosis"), ".")) font_bold(paste0("assuming all rows contain ", font_italic("Mycobacterium tuberculosis"), "."))
) )
x$mo <- as.mo("Mycobacterium tuberculosis") # consider overkill at all times: AMR_env$MO_lookup[which(AMR_env$MO_lookup$fullname == "Mycobacterium tuberculosis"), "mo", drop = TRUE] x$mo <- as.mo("Mycobacterium tuberculosis", keep_synonyms = TRUE)
col_mo <- "mo" col_mo <- "mo"
} }
stop_if(is.null(col_mo), "`col_mo` must be set") stop_if(is.null(col_mo), "`col_mo` must be set")
@@ -382,120 +382,16 @@ mdro <- function(x = NULL,
cols_ab <- get_column_abx( cols_ab <- get_column_abx(
x = x, x = x,
soft_dependencies = c( soft_dependencies = c(
# [table] 1 (S aureus): # [table] 1 (S aureus)
"GEN", "GEN", "RIF", "CPT", "OXA", "CIP", "MFX", "SXT", "FUS", "VAN", "TEC", "TLV", "TGC", "CLI", "DAP", "ERY", "LNZ", "CHL", "FOS", "QDA", "TCY", "DOX", "MNO",
"RIF",
"CPT",
"OXA",
"CIP",
"MFX",
"SXT",
"FUS",
"VAN",
"TEC",
"TLV",
"TGC",
"CLI",
"DAP",
"ERY",
"LNZ",
"CHL",
"FOS",
"QDA",
"TCY",
"DOX",
"MNO",
# [table] 2 (Enterococcus) # [table] 2 (Enterococcus)
"GEH", "GEH", "STH", "IPM", "MEM", "DOR", "CIP", "LVX", "MFX", "VAN", "TEC", "TGC", "DAP", "LNZ", "AMP", "QDA", "DOX", "MNO",
"STH",
"IPM",
"MEM",
"DOR",
"CIP",
"LVX",
"MFX",
"VAN",
"TEC",
"TGC",
"DAP",
"LNZ",
"AMP",
"QDA",
"DOX",
"MNO",
# [table] 3 (Enterobacteriaceae) # [table] 3 (Enterobacteriaceae)
"GEN", "GEN", "TOB", "AMK", "NET", "CPT", "TCC", "TZP", "ETP", "IPM", "MEM", "DOR", "CZO", "CXM", "CTX", "CAZ", "FEP", "FOX", "CTT", "CIP", "SXT", "TGC", "ATM", "AMP", "AMC", "SAM", "CHL", "FOS", "COL", "TCY", "DOX", "MNO",
"TOB",
"AMK",
"NET",
"CPT",
"TCC",
"TZP",
"ETP",
"IPM",
"MEM",
"DOR",
"CZO",
"CXM",
"CTX",
"CAZ",
"FEP",
"FOX",
"CTT",
"CIP",
"SXT",
"TGC",
"ATM",
"AMP",
"AMC",
"SAM",
"CHL",
"FOS",
"COL",
"TCY",
"DOX",
"MNO",
# [table] 4 (Pseudomonas) # [table] 4 (Pseudomonas)
"GEN", "GEN", "TOB", "AMK", "NET", "IPM", "MEM", "DOR", "CAZ", "FEP", "CIP", "LVX", "TCC", "TZP", "ATM", "FOS", "COL", "PLB",
"TOB",
"AMK",
"NET",
"IPM",
"MEM",
"DOR",
"CAZ",
"FEP",
"CIP",
"LVX",
"TCC",
"TZP",
"ATM",
"FOS",
"COL",
"PLB",
# [table] 5 (Acinetobacter) # [table] 5 (Acinetobacter)
"GEN", "GEN", "TOB", "AMK", "NET", "IPM", "MEM", "DOR", "CIP", "LVX", "TZP", "TCC", "CTX", "CRO", "CAZ", "FEP", "SXT", "SAM", "COL", "PLB", "TCY", "DOX", "MNO"
"TOB",
"AMK",
"NET",
"IPM",
"MEM",
"DOR",
"CIP",
"LVX",
"TZP",
"TCC",
"CTX",
"CRO",
"CAZ",
"FEP",
"SXT",
"SAM",
"COL",
"PLB",
"TCY",
"DOX",
"MNO"
), ),
verbose = verbose, verbose = verbose,
info = info, info = info,
@@ -506,30 +402,7 @@ mdro <- function(x = NULL,
} else if (guideline$code == "eucast3.2") { } else if (guideline$code == "eucast3.2") {
cols_ab <- get_column_abx( cols_ab <- get_column_abx(
x = x, x = x,
soft_dependencies = c( soft_dependencies = c("AMP", "AMX", "CIP", "DAL", "DAP", "ERV", "FDX", "GEN", "LNZ", "MEM", "MTR", "OMC", "ORI", "PEN", "QDA", "RIF", "TEC", "TGC", "TLV", "TOB", "TZD", "VAN"),
"AMP",
"AMX",
"CIP",
"DAL",
"DAP",
"ERV",
"FDX",
"GEN",
"LNZ",
"MEM",
"MTR",
"OMC",
"ORI",
"PEN",
"QDA",
"RIF",
"TEC",
"TGC",
"TLV",
"TOB",
"TZD",
"VAN"
),
verbose = verbose, verbose = verbose,
info = info, info = info,
only_sir_columns = only_sir_columns, only_sir_columns = only_sir_columns,
@@ -539,30 +412,7 @@ mdro <- function(x = NULL,
} else if (guideline$code == "eucast3.3") { } else if (guideline$code == "eucast3.3") {
cols_ab <- get_column_abx( cols_ab <- get_column_abx(
x = x, x = x,
soft_dependencies = c( soft_dependencies = c("AMP", "AMX", "CIP", "DAL", "DAP", "ERV", "FDX", "GEN", "LNZ", "MEM", "MTR", "OMC", "ORI", "PEN", "QDA", "RIF", "TEC", "TGC", "TLV", "TOB", "TZD", "VAN"),
"AMP",
"AMX",
"CIP",
"DAL",
"DAP",
"ERV",
"FDX",
"GEN",
"LNZ",
"MEM",
"MTR",
"OMC",
"ORI",
"PEN",
"QDA",
"RIF",
"TEC",
"TGC",
"TLV",
"TOB",
"TZD",
"VAN"
),
verbose = verbose, verbose = verbose,
info = info, info = info,
only_sir_columns = only_sir_columns, only_sir_columns = only_sir_columns,
@@ -572,16 +422,7 @@ mdro <- function(x = NULL,
} else if (guideline$code == "tb") { } else if (guideline$code == "tb") {
cols_ab <- get_column_abx( cols_ab <- get_column_abx(
x = x, x = x,
soft_dependencies = c( soft_dependencies = c("CAP", "ETH", "GAT", "INH", "PZA", "RIF", "RIB", "RFP"),
"CAP",
"ETH",
"GAT",
"INH",
"PZA",
"RIF",
"RIB",
"RFP"
),
verbose = verbose, verbose = verbose,
info = info, info = info,
only_sir_columns = only_sir_columns, only_sir_columns = only_sir_columns,
@@ -591,14 +432,7 @@ mdro <- function(x = NULL,
} else if (guideline$code == "mrgn") { } else if (guideline$code == "mrgn") {
cols_ab <- get_column_abx( cols_ab <- get_column_abx(
x = x, x = x,
soft_dependencies = c( soft_dependencies = c("PIP", "CTX", "CAZ", "IPM", "MEM", "CIP"),
"PIP",
"CTX",
"CAZ",
"IPM",
"MEM",
"CIP"
),
verbose = verbose, verbose = verbose,
info = info, info = info,
only_sir_columns = only_sir_columns, only_sir_columns = only_sir_columns,

12
R/mo.R
View File

@@ -164,6 +164,8 @@ as.mo <- function(x,
language <- validate_language(language) language <- validate_language(language)
meet_criteria(info, allow_class = "logical", has_length = 1) meet_criteria(info, allow_class = "logical", has_length = 1)
add_MO_lookup_to_AMR_env()
if (tryCatch(all(x %in% c(AMR_env$MO_lookup$mo, NA)) && if (tryCatch(all(x %in% c(AMR_env$MO_lookup$mo, NA)) &&
isFALSE(Becker) && isFALSE(Becker) &&
isFALSE(Lancefield), error = function(e) FALSE)) { isFALSE(Lancefield), error = function(e) FALSE)) {
@@ -492,6 +494,7 @@ mo_uncertainties <- function() {
#' @rdname as.mo #' @rdname as.mo
#' @export #' @export
mo_renamed <- function() { mo_renamed <- function() {
add_MO_lookup_to_AMR_env()
x <- AMR_env$mo_renamed x <- AMR_env$mo_renamed
x$new <- synonym_mo_to_accepted_mo(x$old) x$new <- synonym_mo_to_accepted_mo(x$old)
@@ -547,6 +550,7 @@ mo_cleaning_regex <- function() {
# will be exported using s3_register() in R/zzz.R # will be exported using s3_register() in R/zzz.R
pillar_shaft.mo <- function(x, ...) { pillar_shaft.mo <- function(x, ...) {
add_MO_lookup_to_AMR_env()
out <- format(x) out <- format(x)
# grey out the kingdom (part until first "_") # grey out the kingdom (part until first "_")
out[!is.na(x)] <- gsub("^([A-Z]+_)(.*)", paste0(font_subtle("\\1"), "\\2"), out[!is.na(x)], perl = TRUE) out[!is.na(x)] <- gsub("^([A-Z]+_)(.*)", paste0(font_subtle("\\1"), "\\2"), out[!is.na(x)], perl = TRUE)
@@ -664,6 +668,7 @@ get_skimmers.mo <- function(column) {
#' @export #' @export
#' @noRd #' @noRd
print.mo <- function(x, print.shortnames = FALSE, ...) { print.mo <- function(x, print.shortnames = FALSE, ...) {
add_MO_lookup_to_AMR_env()
cat("Class 'mo'\n") cat("Class 'mo'\n")
x_names <- names(x) x_names <- names(x)
if (is.null(x_names) & print.shortnames == TRUE) { if (is.null(x_names) & print.shortnames == TRUE) {
@@ -704,6 +709,7 @@ summary.mo <- function(object, ...) {
#' @export #' @export
#' @noRd #' @noRd
as.data.frame.mo <- function(x, ...) { as.data.frame.mo <- function(x, ...) {
add_MO_lookup_to_AMR_env()
if (!all(x %in% c(AMR_env$MO_lookup$mo, NA))) { if (!all(x %in% c(AMR_env$MO_lookup$mo, NA))) {
warning_( warning_(
"The data contains old MO codes (from a previous AMR package version). ", "The data contains old MO codes (from a previous AMR package version). ",
@@ -741,6 +747,7 @@ as.data.frame.mo <- function(x, ...) {
y <- NextMethod() y <- NextMethod()
attributes(y) <- attributes(i) attributes(y) <- attributes(i)
# must only contain valid MOs # must only contain valid MOs
add_MO_lookup_to_AMR_env()
return_after_integrity_check(y, "microorganism code", as.character(AMR_env$MO_lookup$mo)) return_after_integrity_check(y, "microorganism code", as.character(AMR_env$MO_lookup$mo))
} }
#' @method [[<- mo #' @method [[<- mo
@@ -750,6 +757,7 @@ as.data.frame.mo <- function(x, ...) {
y <- NextMethod() y <- NextMethod()
attributes(y) <- attributes(i) attributes(y) <- attributes(i)
# must only contain valid MOs # must only contain valid MOs
add_MO_lookup_to_AMR_env()
return_after_integrity_check(y, "microorganism code", as.character(AMR_env$MO_lookup$mo)) return_after_integrity_check(y, "microorganism code", as.character(AMR_env$MO_lookup$mo))
} }
#' @method c mo #' @method c mo
@@ -759,6 +767,7 @@ c.mo <- function(...) {
x <- list(...)[[1L]] x <- list(...)[[1L]]
y <- NextMethod() y <- NextMethod()
attributes(y) <- attributes(x) attributes(y) <- attributes(x)
add_MO_lookup_to_AMR_env()
return_after_integrity_check(y, "microorganism code", as.character(AMR_env$MO_lookup$mo)) return_after_integrity_check(y, "microorganism code", as.character(AMR_env$MO_lookup$mo))
} }
@@ -789,6 +798,8 @@ print.mo_uncertainties <- function(x, ...) {
return(invisible(NULL)) return(invisible(NULL))
} }
add_MO_lookup_to_AMR_env()
cat(word_wrap("Matching scores are based on the resemblance between the input and the full taxonomic name, and the pathogenicity in humans. See `?mo_matching_score`.\n\n", add_fn = font_blue)) cat(word_wrap("Matching scores are based on the resemblance between the input and the full taxonomic name, and the pathogenicity in humans. See `?mo_matching_score`.\n\n", add_fn = font_blue))
if (has_colour()) { if (has_colour()) {
cat(word_wrap("Colour keys: ", cat(word_wrap("Colour keys: ",
@@ -1049,6 +1060,7 @@ replace_old_mo_codes <- function(x, property) {
# B_ESCH_COL (AMR v0.5.0) -> B_ESCHR_COLI # B_ESCH_COL (AMR v0.5.0) -> B_ESCHR_COLI
ind <- x %like_case% "^[A-Z]_[A-Z_]+$" & !x %in% AMR_env$MO_lookup$mo ind <- x %like_case% "^[A-Z]_[A-Z_]+$" & !x %in% AMR_env$MO_lookup$mo
if (any(ind, na.rm = TRUE)) { if (any(ind, na.rm = TRUE)) {
add_MO_lookup_to_AMR_env()
# get the ones that match # get the ones that match
affected <- x[ind] affected <- x[ind]
affected_unique <- unique(affected) affected_unique <- unique(affected)

2
R/mo_matching_score.R
View File

@@ -84,6 +84,8 @@ mo_matching_score <- function(x, n) {
meet_criteria(x, allow_class = c("character", "data.frame", "list")) meet_criteria(x, allow_class = c("character", "data.frame", "list"))
meet_criteria(n, allow_class = "character") meet_criteria(n, allow_class = "character")
add_MO_lookup_to_AMR_env()
x <- parse_and_convert(x) x <- parse_and_convert(x)
# no dots and other non-whitespace characters # no dots and other non-whitespace characters
x <- gsub("[^a-zA-Z0-9 \\(\\)]+", "", x) x <- gsub("[^a-zA-Z0-9 \\(\\)]+", "", x)

9
R/mo_property.R
View File

@@ -417,6 +417,8 @@ mo_pathogenicity <- function(x, language = get_AMR_locale(), keep_synonyms = get
language <- validate_language(language) language <- validate_language(language)
meet_criteria(keep_synonyms, allow_class = "logical", has_length = 1) meet_criteria(keep_synonyms, allow_class = "logical", has_length = 1)
add_MO_lookup_to_AMR_env()
x.mo <- as.mo(x, language = language, keep_synonyms = keep_synonyms, ...) x.mo <- as.mo(x, language = language, keep_synonyms = keep_synonyms, ...)
metadata <- get_mo_uncertainties() metadata <- get_mo_uncertainties()
@@ -726,6 +728,8 @@ mo_synonyms <- function(x, language = get_AMR_locale(), keep_synonyms = getOptio
language <- validate_language(language) language <- validate_language(language)
meet_criteria(keep_synonyms, allow_class = "logical", has_length = 1) meet_criteria(keep_synonyms, allow_class = "logical", has_length = 1)
add_MO_lookup_to_AMR_env()
x.mo <- as.mo(x, language = language, keep_synonyms = keep_synonyms, ...) x.mo <- as.mo(x, language = language, keep_synonyms = keep_synonyms, ...)
metadata <- get_mo_uncertainties() metadata <- get_mo_uncertainties()
@@ -812,6 +816,8 @@ mo_url <- function(x, open = FALSE, language = get_AMR_locale(), keep_synonyms =
language <- validate_language(language) language <- validate_language(language)
meet_criteria(keep_synonyms, allow_class = "logical", has_length = 1) meet_criteria(keep_synonyms, allow_class = "logical", has_length = 1)
add_MO_lookup_to_AMR_env()
x.mo <- as.mo(x = x, language = language, keep_synonyms = keep_synonyms, ... = ...) x.mo <- as.mo(x = x, language = language, keep_synonyms = keep_synonyms, ... = ...)
metadata <- get_mo_uncertainties() metadata <- get_mo_uncertainties()
@@ -847,7 +853,7 @@ mo_property <- function(x, property = "fullname", language = get_AMR_locale(), k
x <- find_mo_col(fn = "mo_property") x <- find_mo_col(fn = "mo_property")
} }
meet_criteria(x, allow_NA = TRUE) meet_criteria(x, allow_NA = TRUE)
meet_criteria(property, allow_class = "character", has_length = 1, is_in = colnames(AMR_env$MO_lookup)) meet_criteria(property, allow_class = "character", has_length = 1, is_in = colnames(AMR::microorganisms))
language <- validate_language(language) language <- validate_language(language)
meet_criteria(keep_synonyms, allow_class = "logical", has_length = 1) meet_criteria(keep_synonyms, allow_class = "logical", has_length = 1)
@@ -855,6 +861,7 @@ mo_property <- function(x, property = "fullname", language = get_AMR_locale(), k
} }
mo_validate <- function(x, property, language, keep_synonyms = keep_synonyms, ...) { mo_validate <- function(x, property, language, keep_synonyms = keep_synonyms, ...) {
add_MO_lookup_to_AMR_env()
# try to catch an error when inputting an invalid argument # try to catch an error when inputting an invalid argument
# so the 'call.' can be set to FALSE # so the 'call.' can be set to FALSE

2
R/mo_source.R
View File

@@ -261,6 +261,8 @@ get_mo_source <- function(destination = getOption("AMR_mo_source", "~/mo_source.
} }
check_validity_mo_source <- function(x, refer_to_name = "`reference_df`", stop_on_error = TRUE) { check_validity_mo_source <- function(x, refer_to_name = "`reference_df`", stop_on_error = TRUE) {
add_MO_lookup_to_AMR_env()
if (paste(deparse(substitute(x)), collapse = "") == "get_mo_source()") { if (paste(deparse(substitute(x)), collapse = "") == "get_mo_source()") {
return(TRUE) return(TRUE)
} }

BIN
R/sysdata.rda
View File

Binary file not shown.

1
R/vctrs.R
View File

@@ -95,6 +95,7 @@ vec_cast.character.mo <- function(x, to, ...) {
as.character(x) as.character(x)
} }
vec_cast.mo.character <- function(x, to, ...) { vec_cast.mo.character <- function(x, to, ...) {
add_MO_lookup_to_AMR_env()
return_after_integrity_check(x, "microorganism code", as.character(AMR_env$MO_lookup$mo)) return_after_integrity_check(x, "microorganism code", as.character(AMR_env$MO_lookup$mo))
} }

40
R/zzz.R
View File

@@ -181,11 +181,10 @@ if (utf8_supported && !is_latex) {
try(loadNamespace("tibble"), silent = TRUE) try(loadNamespace("tibble"), silent = TRUE)
} }
# reference data - they have additional columns compared to `antibiotics` and `microorganisms` to improve speed # reference data - they have additional to improve algorithm speed
# they cannot be part of R/sysdata.rda since CRAN thinks it would make the package too large (+3 MB) # they cannot be part of R/sysdata.rda since CRAN thinks it would make the package too large (+3 MB)
AMR_env$AB_lookup <- create_AB_lookup() AMR_env$AB_lookup <- cbind(AMR::antibiotics, AB_LOOKUP)
AMR_env$AV_lookup <- create_AV_lookup() AMR_env$AV_lookup <- cbind(AMR::antivirals, AV_LOOKUP)
AMR_env$MO_lookup <- create_MO_lookup()
} }
.onAttach <- function(lib, pkg) { .onAttach <- function(lib, pkg) {
@@ -208,36 +207,3 @@ if (utf8_supported && !is_latex) {
}, error = function(e) packageStartupMessage("Failed: ", e$message)) }, error = function(e) packageStartupMessage("Failed: ", e$message))
} }
} }
# Helper functions --------------------------------------------------------
create_AB_lookup <- function() {
cbind(AMR::antibiotics, AB_LOOKUP)
}
create_AV_lookup <- function() {
cbind(AMR::antivirals, AV_LOOKUP)
}
create_MO_lookup <- function() {
MO_lookup <- AMR::microorganisms
MO_lookup$kingdom_index <- NA_real_
MO_lookup[which(MO_lookup$kingdom == "Bacteria" | MO_lookup$mo == "UNKNOWN"), "kingdom_index"] <- 1
MO_lookup[which(MO_lookup$kingdom == "Fungi"), "kingdom_index"] <- 2
MO_lookup[which(MO_lookup$kingdom == "Protozoa"), "kingdom_index"] <- 3
MO_lookup[which(MO_lookup$kingdom == "Archaea"), "kingdom_index"] <- 4
# all the rest
MO_lookup[which(is.na(MO_lookup$kingdom_index)), "kingdom_index"] <- 5
if (length(MO_FULLNAME_LOWER) != nrow(MO_lookup)) {
packageStartupMessage("fullname_lower not same size - applied tolower(), update sysdata.rda!")
MO_lookup$fullname_lower <- tolower(MO_lookup$fullname)
} else {
MO_lookup$fullname_lower <- MO_FULLNAME_LOWER
}
MO_lookup$full_first <- substr(MO_lookup$fullname_lower, 1, 1)
MO_lookup$species_first <- tolower(substr(MO_lookup$species, 1, 1)) # tolower for groups (Streptococcus, Salmonella)
MO_lookup$subspecies_first <- tolower(substr(MO_lookup$subspecies, 1, 1)) # tolower for Salmonella serovars
MO_lookup
}

17
data-raw/_pre_commit_hook.R
View File

@@ -144,21 +144,6 @@ create_species_cons_cops <- function(type = c("CoNS", "CoPS")) {
] ]
} }
} }
create_MO_fullname_lower <- function() {
AMR_env$MO_lookup <- AMR::microorganisms
# use this paste instead of `fullname` to work with Viridans Group Streptococci, etc.
AMR_env$MO_lookup$fullname_lower <- tolower(trimws(paste(
AMR_env$MO_lookup$genus,
AMR_env$MO_lookup$species,
AMR_env$MO_lookup$subspecies
)))
ind <- AMR_env$MO_lookup$genus == "" | grepl("^[(]unknown ", AMR_env$MO_lookup$fullname, perl = TRUE)
AMR_env$MO_lookup[ind, "fullname_lower"] <- tolower(AMR_env$MO_lookup[ind, "fullname", drop = TRUE])
AMR_env$MO_lookup$fullname_lower <- trimws(gsub("[^.a-z0-9/ \\-]+", "", AMR_env$MO_lookup$fullname_lower, perl = TRUE))
# special for Salmonella - they have cities as subspecies but not the species (enterica) in the fullname:
AMR_env$MO_lookup$fullname_lower[which(AMR_env$MO_lookup$subspecies %like_case% "^[A-Z]")] <- gsub(" enterica ", " ", AMR_env$MO_lookup$fullname_lower[which(AMR_env$MO_lookup$subspecies %like_case% "^[A-Z]")], fixed = TRUE)
AMR_env$MO_lookup$fullname_lower
}
MO_CONS <- create_species_cons_cops("CoNS") MO_CONS <- create_species_cons_cops("CoNS")
MO_COPS <- create_species_cons_cops("CoPS") MO_COPS <- create_species_cons_cops("CoPS")
MO_STREP_ABCG <- AMR_env$MO_lookup$mo[which(AMR_env$MO_lookup$genus == "Streptococcus" & MO_STREP_ABCG <- AMR_env$MO_lookup$mo[which(AMR_env$MO_lookup$genus == "Streptococcus" &
@@ -166,7 +151,6 @@ MO_STREP_ABCG <- AMR_env$MO_lookup$mo[which(AMR_env$MO_lookup$genus == "Streptoc
"pyogenes", "agalactiae", "dysgalactiae", "equi", "canis", "pyogenes", "agalactiae", "dysgalactiae", "equi", "canis",
"group A", "group B", "group C", "group G" "group A", "group B", "group C", "group G"
))] ))]
MO_FULLNAME_LOWER <- create_MO_fullname_lower()
MO_PREVALENT_GENERA <- c( MO_PREVALENT_GENERA <- c(
"Absidia", "Acanthamoeba", "Acremonium", "Aedes", "Alternaria", "Amoeba", "Ancylostoma", "Angiostrongylus", "Absidia", "Acanthamoeba", "Acremonium", "Aedes", "Alternaria", "Amoeba", "Ancylostoma", "Angiostrongylus",
"Anisakis", "Anopheles", "Apophysomyces", "Aspergillus", "Aureobasidium", "Basidiobolus", "Beauveria", "Anisakis", "Anopheles", "Apophysomyces", "Aspergillus", "Aureobasidium", "Basidiobolus", "Beauveria",
@@ -298,7 +282,6 @@ suppressMessages(usethis::use_data(EUCAST_RULES_DF,
MO_CONS, MO_CONS,
MO_COPS, MO_COPS,
MO_STREP_ABCG, MO_STREP_ABCG,
MO_FULLNAME_LOWER,
MO_PREVALENT_GENERA, MO_PREVALENT_GENERA,
AB_LOOKUP, AB_LOOKUP,
AV_LOOKUP, AV_LOOKUP,

2
man/AMR.Rd
View File

@@ -28,7 +28,7 @@ A BibTeX entry for LaTeX users is:
\description{ \description{
Welcome to the \code{AMR} package. Welcome to the \code{AMR} package.
The \code{AMR} package is a \href{https://msberends.github.io/AMR#copyright}{free and open-source} R package with \href{https://en.wikipedia.org/wiki/Dependency_hell}{zero dependencies} to simplify the analysis and prediction of Antimicrobial Resistance (AMR) and to work with microbial and antimicrobial data and properties, by using evidence-based methods. \strong{Our aim is to provide a standard} for clean and reproducible AMR data analysis, that can therefore empower epidemiological analyses to continuously enable surveillance and treatment evaluation in any setting. \href{https://msberends.github.io/AMR/authors.html}{Many different researchers} from around the globe are continually helping us to make this a successful and durable project! The \code{AMR} package is a \href{https://msberends.github.io/AMR/#copyright}{free and open-source} R package with \href{https://en.wikipedia.org/wiki/Dependency_hell}{zero dependencies} to simplify the analysis and prediction of Antimicrobial Resistance (AMR) and to work with microbial and antimicrobial data and properties, by using evidence-based methods. \strong{Our aim is to provide a standard} for clean and reproducible AMR data analysis, that can therefore empower epidemiological analyses to continuously enable surveillance and treatment evaluation in any setting. \href{https://msberends.github.io/AMR/authors.html}{Many different researchers} from around the globe are continually helping us to make this a successful and durable project!
This work was published in the Journal of Statistical Software (Volume 104(3); \href{https://doi.org/10.18637/jss.v104.i03}{DOI 10.18637/jss.v104.i03}) and formed the basis of two PhD theses (\href{https://doi.org/10.33612/diss.177417131}{DOI 10.33612/diss.177417131} and \href{https://doi.org/10.33612/diss.192486375}{DOI 10.33612/diss.192486375}). This work was published in the Journal of Statistical Software (Volume 104(3); \href{https://doi.org/10.18637/jss.v104.i03}{DOI 10.18637/jss.v104.i03}) and formed the basis of two PhD theses (\href{https://doi.org/10.33612/diss.177417131}{DOI 10.33612/diss.177417131} and \href{https://doi.org/10.33612/diss.192486375}{DOI 10.33612/diss.192486375}).