diff --git a/DESCRIPTION b/DESCRIPTION
index 3545cce0..9d727576 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,6 +1,6 @@
Package: AMR
-Version: 1.5.0.9019
-Date: 2021-02-17
+Version: 1.5.0.9020
+Date: 2021-02-18
Title: Antimicrobial Resistance Data Analysis
Authors@R: c(
person(role = c("aut", "cre"),
diff --git a/NEWS.md b/NEWS.md
index 9a3278f5..402fb27d 100755
--- a/NEWS.md
+++ b/NEWS.md
@@ -1,5 +1,5 @@
-# AMR 1.5.0.9019
-## Last updated: 17 February 2021
+# AMR 1.5.0.9020
+## Last updated: 18 February 2021
### New
* Support for EUCAST Clinical Breakpoints v11.0 (2021), effective in the `eucast_rules()` function and in `as.rsi()` to interpret MIC and disk diffusion values. This is now the default guideline in this package.
@@ -57,6 +57,7 @@
* Updated colours of values R, S and I in tibble printing
* Functions `print()` and `summary()` on a Principal Components Analysis object (`pca()`) now print additional group info if the original data was grouped using `dplyr::group_by()`
* Improved speed and reliability of `guess_ab_col()`. As this also internally improves the reliability of `first_isolate()` and `mdro()`, this might have a slight impact on the results of those functions.
+* Fix for `mo_name()` when used in other languages than English
### Other
* Big documentation updates
diff --git a/R/mo.R b/R/mo.R
index 6ca15e83..62076bdf 100755
--- a/R/mo.R
+++ b/R/mo.R
@@ -451,528 +451,167 @@ exec_as.mo <- function(x,
x_backup_untouched <- x
x <- strip_whitespace(x, dyslexia_mode)
+ # translate 'unknown' names back to English
+ if (any(x %like% "unbekannt|onbekend|desconocid|sconosciut|iconnu|desconhecid", na.rm = TRUE)) {
+ trns <- subset(translations_file, pattern %like% "unknown" | affect_mo_name == TRUE)
+ lapply(seq_len(nrow(trns)),
+ function(i) x <<- gsub(pattern = trns$replacement[i],
+ replacement = trns$pattern[i],
+ x = x,
+ ignore.case = TRUE,
+ perl = TRUE))
+ }
+
x_backup <- x
# from here on case-insensitive
x <- tolower(x)
-
- x_backup[grepl("^(fungus|fungi)$", x)] <- "F_FUNGUS" # will otherwise become the kingdom
-
- # remove spp and species
- x <- gsub(" +(spp.?|ssp.?|sp.? |ss ?.?|subsp.?|subspecies|biovar |serovar |species)", " ", x, perl = TRUE)
- x <- gsub("(spp.?|subsp.?|subspecies|biovar|serovar|species)", "", x, perl = TRUE)
- x <- gsub("^([a-z]{2,4})(spe.?)$", "\\1", x, perl = TRUE) # when ending in SPE instead of SPP and preceded by 2-4 characters
- x <- strip_whitespace(x, dyslexia_mode)
-
- x_backup_without_spp <- x
- x_species <- paste(x, "species")
- # translate to English for supported languages of mo_property
- x <- gsub("(gruppe|groep|grupo|gruppo|groupe)", "group", x, perl = TRUE)
- # no groups and complexes as ending
- x <- gsub("(complex|group)$", "", x, perl = TRUE)
- x <- gsub("((an)?aero+b)[a-z]*", "", x, perl = TRUE)
- x <- gsub("^atyp[a-z]*", "", x, perl = TRUE)
- x <- gsub("(vergroen)[a-z]*", "viridans", x, perl = TRUE)
- x <- gsub("[a-z]*diff?erent[a-z]*", "", x, perl = TRUE)
- x <- gsub("(hefe|gist|gisten|levadura|lievito|fermento|levure)[a-z]*", "yeast", x, perl = TRUE)
- x <- gsub("(schimmels?|mofo|molde|stampo|moisissure|fungi)[a-z]*", "fungus", x, perl = TRUE)
- x <- gsub("fungus[ph|f]rya", "fungiphrya", x, perl = TRUE)
- # no contamination
- x <- gsub("(contamination|kontamination|mengflora|contaminaci.n|contamina..o)", "", x, perl = TRUE)
- # remove non-text in case of "E. coli" except dots and spaces
- x <- trimws(gsub("[^.a-zA-Z0-9/ \\-]+", " ", x, perl = TRUE))
- # but make sure that dots are followed by a space
- x <- gsub("[.] ?", ". ", x, perl = TRUE)
- # replace minus by a space
- x <- gsub("-+", " ", x, perl = TRUE)
- # replace hemolytic by haemolytic
- x <- gsub("ha?emoly", "haemoly", x, perl = TRUE)
- # place minus back in streptococci
- x <- gsub("(alpha|beta|gamma).?ha?emoly", "\\1-haemoly", x, perl = TRUE)
- # remove genus as first word
- x <- gsub("^genus ", "", x, perl = TRUE)
- # remove 'uncertain'-like texts
- x <- trimws(gsub("(uncertain|susp[ie]c[a-z]+|verdacht)", "", x, perl = TRUE))
- # allow characters that resemble others = dyslexia_mode ----
- if (dyslexia_mode == TRUE) {
- x <- tolower(x)
- x <- gsub("[iy]+", "[iy]+", x, perl = TRUE)
- x <- gsub("(c|k|q|qu|s|z|x|ks)+", "(c|k|q|qu|s|z|x|ks)+", x, perl = TRUE)
- x <- gsub("(ph|hp|f|v)+", "(ph|hp|f|v)+", x, perl = TRUE)
- x <- gsub("(th|ht|t)+", "(th|ht|t)+", x, perl = TRUE)
- x <- gsub("a+", "a+", x, perl = TRUE)
- x <- gsub("u+", "u+", x, perl = TRUE)
- # allow any ending of -um, -us, -ium, -icum, -ius, -icus, -ica, -ia and -a (needs perl for the negative backward lookup):
- x <- gsub("(u\\+\\(c\\|k\\|q\\|qu\\+\\|s\\|z\\|x\\|ks\\)\\+)(?![a-z])",
- "(u[s|m]|[iy][ck]?u[ms]|[iy]?[ck]?a)", x, perl = TRUE)
- x <- gsub("(\\[iy\\]\\+\\(c\\|k\\|q\\|qu\\+\\|s\\|z\\|x\\|ks\\)\\+a\\+)(?![a-z])",
- "(u[s|m]|[iy][ck]?u[ms]|[iy]?[ck]?a)", x, perl = TRUE)
- x <- gsub("(\\[iy\\]\\+u\\+m)(?![a-z])",
- "(u[s|m]|[iy][ck]?u[ms]|[iy]?[ck]?a)", x, perl = TRUE)
- x <- gsub("(\\[iy\\]\\+a\\+)(?![a-z])",
- "([iy]*a+|[iy]+a*)", x, perl = TRUE)
- x <- gsub("e+", "e+", x, perl = TRUE)
- x <- gsub("o+", "o+", x, perl = TRUE)
- x <- gsub("(.)\\1+", "\\1+", x, perl = TRUE)
- # allow multiplication of all other consonants
- x <- gsub("([bdgjlnrw]+)", "\\1+", x, perl = TRUE)
- # allow ending in -en or -us
- x <- gsub("e\\+n(?![a-z[])", "(e+n|u+(c|k|q|qu|s|z|x|ks)+)", x, perl = TRUE)
- # if the input is longer than 10 characters, allow any forgotten consonant between all characters, as some might just have forgotten one...
- # this will allow "Pasteurella damatis" to be correctly read as "Pasteurella dagmatis".
- consonants <- paste(letters[!letters %in% c("a", "e", "i", "o", "u")], collapse = "")
- x[nchar(x_backup_without_spp) > 10] <- gsub("[+]", paste0("+[", consonants, "]?"), x[nchar(x_backup_without_spp) > 10])
- # allow au and ou after all these regex implementations
- x <- gsub("a+[bcdfghjklmnpqrstvwxyz]?u+[bcdfghjklmnpqrstvwxyz]?", "(a+u+|o+u+)[bcdfghjklmnpqrstvwxyz]?", x, fixed = TRUE)
- x <- gsub("o+[bcdfghjklmnpqrstvwxyz]?u+[bcdfghjklmnpqrstvwxyz]?", "(a+u+|o+u+)[bcdfghjklmnpqrstvwxyz]?", x, fixed = TRUE)
- }
- x <- strip_whitespace(x, dyslexia_mode)
- # make sure to remove regex overkill (will lead to errors)
- x <- gsub("++", "+", x, fixed = TRUE)
- x <- gsub("?+", "?", x, fixed = TRUE)
-
- x_trimmed <- x
- x_trimmed_species <- paste(x_trimmed, "species")
- x_trimmed_without_group <- gsub(" gro.u.p$", "", x_trimmed, perl = TRUE)
- # remove last part from "-" or "/"
- x_trimmed_without_group <- gsub("(.*)[-/].*", "\\1", x_trimmed_without_group)
- # replace space and dot by regex sign
- x_withspaces <- gsub("[ .]+", ".* ", x, perl = TRUE)
- x <- gsub("[ .]+", ".*", x, perl = TRUE)
- # add start en stop regex
- x <- paste0("^", x, "$")
-
- x_withspaces_start_only <- paste0("^", x_withspaces)
- x_withspaces_end_only <- paste0(x_withspaces, "$")
- x_withspaces_start_end <- paste0("^", x_withspaces, "$")
-
- if (isTRUE(debug)) {
- cat(paste0(font_blue("x"), ' "', x, '"\n'))
- cat(paste0(font_blue("x_species"), ' "', x_species, '"\n'))
- cat(paste0(font_blue("x_withspaces_start_only"), ' "', x_withspaces_start_only, '"\n'))
- cat(paste0(font_blue("x_withspaces_end_only"), ' "', x_withspaces_end_only, '"\n'))
- cat(paste0(font_blue("x_withspaces_start_end"), ' "', x_withspaces_start_end, '"\n'))
- cat(paste0(font_blue("x_backup"), ' "', x_backup, '"\n'))
- cat(paste0(font_blue("x_backup_without_spp"), ' "', x_backup_without_spp, '"\n'))
- cat(paste0(font_blue("x_trimmed"), ' "', x_trimmed, '"\n'))
- cat(paste0(font_blue("x_trimmed_species"), ' "', x_trimmed_species, '"\n'))
- cat(paste0(font_blue("x_trimmed_without_group"), ' "', x_trimmed_without_group, '"\n'))
- }
-
- if (initial_search == TRUE) {
- progress <- progress_ticker(n = length(x), n_min = 25) # start if n >= 25
- on.exit(close(progress))
- }
-
- for (i in seq_len(length(x))) {
-
+
+ x_backup[x %like_case% "^(fungus|fungi)$"] <- "(unknown fungus)" # will otherwise become the kingdom
+ x_backup[x_backup_untouched == "Fungi"] <- "Fungi" # is literally the kingdom
+
+ # Fill in fullnames and MO codes at once
+ known_names <- x_backup %in% MO_lookup$fullname
+ x[known_names] <- MO_lookup[match(x_backup[known_names], MO_lookup$fullname), property, drop = TRUE]
+ known_codes <- x_backup %in% MO_lookup$mo
+ x[known_codes] <- MO_lookup[match(x_backup[known_codes], MO_lookup$mo), property, drop = TRUE]
+ already_known <- known_names | known_codes
+
+ # now only continue where the right taxonomic output is not already known
+ if (any(!already_known)) {
+ x_known <- x[already_known]
+
+ # remove spp and species
+ x <- gsub(" +(spp.?|ssp.?|sp.? |ss ?.?|subsp.?|subspecies|biovar |serovar |species)", " ", x, perl = TRUE)
+ x <- gsub("(spp.?|subsp.?|subspecies|biovar|serovar|species)", "", x, perl = TRUE)
+ x <- gsub("^([a-z]{2,4})(spe.?)$", "\\1", x, perl = TRUE) # when ending in SPE instead of SPP and preceded by 2-4 characters
+ x <- strip_whitespace(x, dyslexia_mode)
+
+ x_backup_without_spp <- x
+ x_species <- paste(x, "species")
+ # translate to English for supported languages of mo_property
+ x <- gsub("(gruppe|groep|grupo|gruppo|groupe)", "group", x, perl = TRUE)
+ # no groups and complexes as ending
+ x <- gsub("(complex|group)$", "", x, perl = TRUE)
+ x <- gsub("(^|[^a-z])((an)?aero+b)[a-z]*", "", x, perl = TRUE)
+ x <- gsub("^atyp[a-z]*", "", x, perl = TRUE)
+ x <- gsub("(vergroen)[a-z]*", "viridans", x, perl = TRUE)
+ x <- gsub("[a-z]*diff?erent[a-z]*", "", x, perl = TRUE)
+ x <- gsub("(hefe|gist|gisten|levadura|lievito|fermento|levure)[a-z]*", "yeast", x, perl = TRUE)
+ x <- gsub("(schimmels?|mofo|molde|stampo|moisissure|fungi)[a-z]*", "fungus", x, perl = TRUE)
+ x <- gsub("fungus[ph|f]rya", "fungiphrya", x, perl = TRUE)
+ # no contamination
+ x <- gsub("(contamination|kontamination|mengflora|contaminaci.n|contamina..o)", "", x, perl = TRUE)
+ # remove non-text in case of "E. coli" except dots and spaces
+ x <- trimws(gsub("[^.a-zA-Z0-9/ \\-]+", " ", x, perl = TRUE))
+ # but make sure that dots are followed by a space
+ x <- gsub("[.] ?", ". ", x, perl = TRUE)
+ # replace minus by a space
+ x <- gsub("-+", " ", x, perl = TRUE)
+ # replace hemolytic by haemolytic
+ x <- gsub("ha?emoly", "haemoly", x, perl = TRUE)
+ # place minus back in streptococci
+ x <- gsub("(alpha|beta|gamma).?ha?emoly", "\\1-haemoly", x, perl = TRUE)
+ # remove genus as first word
+ x <- gsub("^genus ", "", x, perl = TRUE)
+ # remove 'uncertain'-like texts
+ x <- trimws(gsub("(uncertain|susp[ie]c[a-z]+|verdacht)", "", x, perl = TRUE))
+ # allow characters that resemble others = dyslexia_mode ----
+ if (dyslexia_mode == TRUE) {
+ x <- tolower(x)
+ x <- gsub("[iy]+", "[iy]+", x, perl = TRUE)
+ x <- gsub("(c|k|q|qu|s|z|x|ks)+", "(c|k|q|qu|s|z|x|ks)+", x, perl = TRUE)
+ x <- gsub("(ph|hp|f|v)+", "(ph|hp|f|v)+", x, perl = TRUE)
+ x <- gsub("(th|ht|t)+", "(th|ht|t)+", x, perl = TRUE)
+ x <- gsub("a+", "a+", x, perl = TRUE)
+ x <- gsub("u+", "u+", x, perl = TRUE)
+ # allow any ending of -um, -us, -ium, -icum, -ius, -icus, -ica, -ia and -a (needs perl for the negative backward lookup):
+ x <- gsub("(u\\+\\(c\\|k\\|q\\|qu\\+\\|s\\|z\\|x\\|ks\\)\\+)(?![a-z])",
+ "(u[s|m]|[iy][ck]?u[ms]|[iy]?[ck]?a)", x, perl = TRUE)
+ x <- gsub("(\\[iy\\]\\+\\(c\\|k\\|q\\|qu\\+\\|s\\|z\\|x\\|ks\\)\\+a\\+)(?![a-z])",
+ "(u[s|m]|[iy][ck]?u[ms]|[iy]?[ck]?a)", x, perl = TRUE)
+ x <- gsub("(\\[iy\\]\\+u\\+m)(?![a-z])",
+ "(u[s|m]|[iy][ck]?u[ms]|[iy]?[ck]?a)", x, perl = TRUE)
+ x <- gsub("(\\[iy\\]\\+a\\+)(?![a-z])",
+ "([iy]*a+|[iy]+a*)", x, perl = TRUE)
+ x <- gsub("e+", "e+", x, perl = TRUE)
+ x <- gsub("o+", "o+", x, perl = TRUE)
+ x <- gsub("(.)\\1+", "\\1+", x, perl = TRUE)
+ # allow multiplication of all other consonants
+ x <- gsub("([bdgjlnrw]+)", "\\1+", x, perl = TRUE)
+ # allow ending in -en or -us
+ x <- gsub("e\\+n(?![a-z[])", "(e+n|u+(c|k|q|qu|s|z|x|ks)+)", x, perl = TRUE)
+ # if the input is longer than 10 characters, allow any forgotten consonant between all characters, as some might just have forgotten one...
+ # this will allow "Pasteurella damatis" to be correctly read as "Pasteurella dagmatis".
+ consonants <- paste(letters[!letters %in% c("a", "e", "i", "o", "u")], collapse = "")
+ x[nchar(x_backup_without_spp) > 10] <- gsub("[+]", paste0("+[", consonants, "]?"), x[nchar(x_backup_without_spp) > 10])
+ # allow au and ou after all these regex implementations
+ x <- gsub("a+[bcdfghjklmnpqrstvwxyz]?u+[bcdfghjklmnpqrstvwxyz]?", "(a+u+|o+u+)[bcdfghjklmnpqrstvwxyz]?", x, fixed = TRUE)
+ x <- gsub("o+[bcdfghjklmnpqrstvwxyz]?u+[bcdfghjklmnpqrstvwxyz]?", "(a+u+|o+u+)[bcdfghjklmnpqrstvwxyz]?", x, fixed = TRUE)
+ }
+ x <- strip_whitespace(x, dyslexia_mode)
+ # make sure to remove regex overkill (will lead to errors)
+ x <- gsub("++", "+", x, fixed = TRUE)
+ x <- gsub("?+", "?", x, fixed = TRUE)
+
+ x_trimmed <- x
+ x_trimmed_species <- paste(x_trimmed, "species")
+ x_trimmed_without_group <- gsub(" gro.u.p$", "", x_trimmed, perl = TRUE)
+ # remove last part from "-" or "/"
+ x_trimmed_without_group <- gsub("(.*)[-/].*", "\\1", x_trimmed_without_group)
+ # replace space and dot by regex sign
+ x_withspaces <- gsub("[ .]+", ".* ", x, perl = TRUE)
+ x <- gsub("[ .]+", ".*", x, perl = TRUE)
+ # add start en stop regex
+ x <- paste0("^", x, "$")
+
+ x_withspaces_start_only <- paste0("^", x_withspaces)
+ x_withspaces_end_only <- paste0(x_withspaces, "$")
+ x_withspaces_start_end <- paste0("^", x_withspaces, "$")
+
+ if (isTRUE(debug)) {
+ cat(paste0(font_blue("x"), ' "', x, '"\n'))
+ cat(paste0(font_blue("x_species"), ' "', x_species, '"\n'))
+ cat(paste0(font_blue("x_withspaces_start_only"), ' "', x_withspaces_start_only, '"\n'))
+ cat(paste0(font_blue("x_withspaces_end_only"), ' "', x_withspaces_end_only, '"\n'))
+ cat(paste0(font_blue("x_withspaces_start_end"), ' "', x_withspaces_start_end, '"\n'))
+ cat(paste0(font_blue("x_backup"), ' "', x_backup, '"\n'))
+ cat(paste0(font_blue("x_backup_without_spp"), ' "', x_backup_without_spp, '"\n'))
+ cat(paste0(font_blue("x_trimmed"), ' "', x_trimmed, '"\n'))
+ cat(paste0(font_blue("x_trimmed_species"), ' "', x_trimmed_species, '"\n'))
+ cat(paste0(font_blue("x_trimmed_without_group"), ' "', x_trimmed_without_group, '"\n'))
+ }
+
if (initial_search == TRUE) {
- progress$tick()
- }
-
- # valid MO code ----
- found <- lookup(mo == toupper(x_backup[i]))
- if (!is.na(found)) {
- x[i] <- found[1L]
- next
- }
-
- # valid fullname ----
- found <- lookup(fullname_lower %in% gsub("[^a-zA-Z0-9_. -]", "", tolower(c(x_backup[i], x_backup_without_spp[i])), perl = TRUE))
- # added the gsub() for "(unknown fungus)", since fullname_lower does not contain brackets
- if (!is.na(found)) {
- x[i] <- found[1L]
- next
- }
-
- # old fullname ----
- found <- lookup(fullname_lower %in% tolower(c(x_backup[i], x_backup_without_spp[i])),
- column = NULL, # all columns
- haystack = MO.old_lookup)
- if (!all(is.na(found))) {
- # when property is "ref" (which is the case in mo_ref, mo_authors and mo_year), return the old value, so:
- # mo_ref() of "Chlamydia psittaci" will be "Page, 1968" (with warning)
- # mo_ref() of "Chlamydophila psittaci" will be "Everett et al., 1999"
- if (property == "ref") {
- x[i] <- found["ref"]
- } else {
- x[i] <- lookup(fullname == found["fullname_new"], haystack = MO_lookup)
- }
- pkg_env$mo_renamed_last_run <- found["fullname"]
- was_renamed(name_old = found["fullname"],
- name_new = lookup(fullname == found["fullname_new"], "fullname", haystack = MO_lookup),
- ref_old = found["ref"],
- ref_new = lookup(fullname == found["fullname_new"], "ref", haystack = MO_lookup),
- mo = lookup(fullname == found["fullname_new"], "mo", haystack = MO_lookup))
- next
- }
-
- if (x_backup[i] %like_case% "\\(unknown [a-z]+\\)" | tolower(x_backup_without_spp[i]) %in% c("other", "none", "unknown")) {
- # empty and nonsense values, ignore without warning
- x[i] <- lookup(mo == "UNKNOWN")
- next
- }
-
- # exact SNOMED code ----
- if (x_backup[i] %like% "^[0-9]+$") {
- snomed_found <- unlist(lapply(reference_data_to_use$snomed,
- function(s) if (x_backup[i] %in% s) {
- TRUE
- } else {
- FALSE
- }))
- if (sum(snomed_found, na.rm = TRUE) > 0) {
- found <- reference_data_to_use[snomed_found == TRUE, property][[1]]
- if (!is.na(found)) {
- x[i] <- found[1L]
- next
- }
- }
- }
-
- # very probable: is G. species ----
- found <- lookup(g_species %in% gsub("[^a-z0-9/ \\-]+", "",
- tolower(c(x_backup[i], x_backup_without_spp[i])), perl = TRUE))
- if (!is.na(found)) {
- x[i] <- found[1L]
- next
- }
-
- # WHONET and other common LIS codes ----
- found <- microorganisms.codes[which(microorganisms.codes$code %in% toupper(c(x_backup_untouched[i], x_backup[i], x_backup_without_spp[i]))), "mo", drop = TRUE][1L]
- if (!is.na(found)) {
- x[i] <- lookup(mo == found)
- next
- }
-
- # user-defined reference ----
- if (!is.null(reference_df)) {
- if (x_backup[i] %in% reference_df[, 1]) {
- # already checked integrity of reference_df, all MOs are valid
- ref_mo <- reference_df[reference_df[, 1] == x_backup[i], "mo"][[1L]]
- x[i] <- lookup(mo == ref_mo)
- next
- }
- }
-
- # WHONET: xxx = no growth
- if (tolower(as.character(paste0(x_backup_without_spp[i], ""))) %in% c("", "xxx", "na", "nan")) {
- x[i] <- NA_character_
- next
- }
-
- # check for very small input, but ignore the O antigens of E. coli
- if (nchar(gsub("[^a-zA-Z]", "", x_trimmed[i])) < 3
- & !toupper(x_backup_without_spp[i]) %like_case% "O?(26|103|104|104|111|121|145|157)") {
- # fewer than 3 chars and not looked for species, add as failure
- x[i] <- lookup(mo == "UNKNOWN")
- if (initial_search == TRUE) {
- failures <- c(failures, x_backup[i])
- }
- next
- }
-
- if (x_backup_without_spp[i] %like_case% "(virus|viridae)") {
- # there is no fullname like virus or viridae, so don't try to coerce it
- x[i] <- NA_character_
- next
- }
-
- # translate known trivial abbreviations to genus + species ----
- if (toupper(x_backup_without_spp[i]) %in% c("MRSA", "MSSA", "VISA", "VRSA", "BORSA")
- | x_backup_without_spp[i] %like_case% "(^| )(mrsa|mssa|visa|vrsa|borsa|la-?mrsa|ca-?mrsa)( |$)") {
- x[i] <- lookup(fullname == "Staphylococcus aureus", uncertainty = -1)
- next
- }
- if (toupper(x_backup_without_spp[i]) %in% c("MRSE", "MSSE")
- | x_backup_without_spp[i] %like_case% "(^| )(mrse|msse)( |$)") {
- x[i] <- lookup(fullname == "Staphylococcus epidermidis", uncertainty = -1)
- next
- }
- if (toupper(x_backup_without_spp[i]) == "VRE"
- | x_backup_without_spp[i] %like_case% "(^| )vre "
- | x_backup_without_spp[i] %like_case% "(enterococci|enterokok|enterococo)[a-z]*?$") {
- x[i] <- lookup(genus == "Enterococcus", uncertainty = -1)
- next
- }
- # support for:
- # - 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)
- # - UPEC (Uropathogenic E. coli)
- if (toupper(x_backup_without_spp[i]) %in% c("AIEC", "ATEC", "DAEC", "EAEC", "EHEC", "EIEC", "EPEC", "ETEC", "NMEC", "STEC", "UPEC")
- # also support O-antigens of E. coli: O26, O103, O104, O111, O121, O145, O157
- | x_backup_without_spp[i] %like_case% "o?(26|103|104|111|121|145|157)") {
- x[i] <- lookup(fullname == "Escherichia coli", uncertainty = -1)
- next
- }
- if (toupper(x_backup_without_spp[i]) == "MRPA"
- | x_backup_without_spp[i] %like_case% "(^| )mrpa( |$)") {
- # multi resistant P. aeruginosa
- x[i] <- lookup(fullname == "Pseudomonas aeruginosa", uncertainty = -1)
- next
- }
- if (toupper(x_backup_without_spp[i]) == "CRSM") {
- # co-trim resistant S. maltophilia
- x[i] <- lookup(fullname == "Stenotrophomonas maltophilia", uncertainty = -1)
- next
- }
- if (toupper(x_backup_without_spp[i]) %in% c("PISP", "PRSP", "VISP", "VRSP")
- | x_backup_without_spp[i] %like_case% "(^| )(pisp|prsp|visp|vrsp)( |$)") {
- # peni I, peni R, vanco I, vanco R: S. pneumoniae
- x[i] <- lookup(fullname == "Streptococcus pneumoniae", uncertainty = -1)
- next
- }
- if (x_backup_without_spp[i] %like_case% "^g[abcdfghk]s$") {
- # Streptococci, like GBS = Group B Streptococci (B_STRPT_GRPB)
- x[i] <- lookup(mo == toupper(gsub("g([abcdfghk])s",
- "B_STRPT_GRP\\1",
- x_backup_without_spp[i])), uncertainty = -1)
- next
- }
- if (x_backup_without_spp[i] %like_case% "(streptococ|streptokok).* [abcdfghk]$") {
- # Streptococci in different languages, like "estreptococos grupo B"
- x[i] <- lookup(mo == toupper(gsub(".*(streptococ|streptokok|estreptococ).* ([abcdfghk])$",
- "B_STRPT_GRP\\2",
- x_backup_without_spp[i])), uncertainty = -1)
- next
- }
- if (x_backup_without_spp[i] %like_case% "group [abcdfghk] (streptococ|streptokok|estreptococ)") {
- # Streptococci in different languages, like "Group A Streptococci"
- x[i] <- lookup(mo == toupper(gsub(".*group ([abcdfghk]) (streptococ|streptokok|estreptococ).*",
- "B_STRPT_GRP\\1",
- x_backup_without_spp[i])), uncertainty = -1)
- next
- }
- if (x_backup_without_spp[i] %like_case% "haemoly.*strep") {
- # Haemolytic streptococci in different languages
- x[i] <- lookup(mo == "B_STRPT_HAEM", uncertainty = -1)
- next
- }
- # CoNS/CoPS in different languages (support for German, Dutch, Spanish, Portuguese)
- if (x_backup_without_spp[i] %like_case% "[ck]oagulas[ea] negatie?[vf]"
- | x_trimmed[i] %like_case% "[ck]oagulas[ea] negatie?[vf]"
- | x_backup_without_spp[i] %like_case% "[ck]o?ns[^a-z]?$") {
- # coerce S. coagulase negative
- x[i] <- lookup(mo == "B_STPHY_CONS", uncertainty = -1)
- next
- }
- if (x_backup_without_spp[i] %like_case% "[ck]oagulas[ea] positie?[vf]"
- | x_trimmed[i] %like_case% "[ck]oagulas[ea] positie?[vf]"
- | x_backup_without_spp[i] %like_case% "[ck]o?ps[^a-z]?$") {
- # coerce S. coagulase positive
- x[i] <- lookup(mo == "B_STPHY_COPS", uncertainty = -1)
- next
- }
- # streptococcal groups: milleri and viridans
- if (x_trimmed[i] %like_case% "strepto.* mil+er+i"
- | x_backup_without_spp[i] %like_case% "strepto.* mil+er+i"
- | x_backup_without_spp[i] %like_case% "mgs[^a-z]?$") {
- # Milleri Group Streptococcus (MGS)
- x[i] <- lookup(mo == "B_STRPT_MILL", uncertainty = -1)
- next
- }
- if (x_trimmed[i] %like_case% "strepto.* viridans"
- | x_backup_without_spp[i] %like_case% "strepto.* viridans"
- | x_backup_without_spp[i] %like_case% "vgs[^a-z]?$") {
- # Viridans Group Streptococcus (VGS)
- x[i] <- lookup(mo == "B_STRPT_VIRI", uncertainty = -1)
- next
- }
- if (x_backup_without_spp[i] %like_case% "gram[ -]?neg.*"
- | x_backup_without_spp[i] %like_case% "negatie?[vf]"
- | x_trimmed[i] %like_case% "gram[ -]?neg.*") {
- # coerce Gram negatives
- x[i] <- lookup(mo == "B_GRAMN", uncertainty = -1)
- next
- }
- if (x_backup_without_spp[i] %like_case% "gram[ -]?pos.*"
- | x_backup_without_spp[i] %like_case% "positie?[vf]"
- | x_trimmed[i] %like_case% "gram[ -]?pos.*") {
- # coerce Gram positives
- x[i] <- lookup(mo == "B_GRAMP", uncertainty = -1)
- next
- }
- if (x_backup_without_spp[i] %like_case% "mycoba[ck]teri.[nm]?$") {
- # coerce mycobacteria in multiple languages
- x[i] <- lookup(genus == "Mycobacterium", uncertainty = -1)
- next
- }
-
- if (x_backup_without_spp[i] %like_case% "salmonella [a-z]+ ?.*") {
- if (x_backup_without_spp[i] %like_case% "salmonella group") {
- # Salmonella Group A to Z, just return S. species for now
- x[i] <- lookup(genus == "Salmonella", uncertainty = -1)
- next
- } else if (grepl("[sS]almonella [A-Z][a-z]+ ?.*", x_backup[i], ignore.case = FALSE) &
- !x_backup[i] %like% "t[iy](ph|f)[iy]") {
- # Salmonella with capital letter species like "Salmonella Goettingen" - they're all S. enterica
- # except for S. typhi, S. paratyphi, S. typhimurium
- x[i] <- lookup(fullname == "Salmonella enterica", uncertainty = -1)
- uncertainties <- rbind(uncertainties,
- format_uncertainty_as_df(uncertainty_level = 1,
- input = x_backup[i],
- result_mo = lookup(fullname == "Salmonella enterica", "mo", uncertainty = -1)),
- stringsAsFactors = FALSE)
- next
- }
- }
-
- # trivial names known to the field:
- if ("meningococcus" %like_case% x_trimmed[i]) {
- # coerce Neisseria meningitidis
- x[i] <- lookup(fullname == "Neisseria meningitidis", uncertainty = -1)
- next
- }
- if ("gonococcus" %like_case% x_trimmed[i]) {
- # coerce Neisseria gonorrhoeae
- x[i] <- lookup(fullname == "Neisseria gonorrhoeae", uncertainty = -1)
- next
- }
- if ("pneumococcus" %like_case% x_trimmed[i]) {
- # coerce Streptococcus penumoniae
- x[i] <- lookup(fullname == "Streptococcus pneumoniae", uncertainty = -1)
- next
+ progress <- progress_ticker(n = length(x[!already_known]), n_min = 25) # start if n >= 25
+ on.exit(close(progress))
}
- if (x_backup[i] %in% pkg_env$mo_failed) {
- # previously failed already in this session ----
- # (at this point the latest reference_df has also be checked)
- x[i] <- lookup(mo == "UNKNOWN")
+ for (i in which(!already_known)) {
+
if (initial_search == TRUE) {
- failures <- c(failures, x_backup[i])
- }
- next
- }
-
- # NOW RUN THROUGH DIFFERENT PREVALENCE LEVELS
- check_per_prevalence <- function(data_to_check,
- data.old_to_check,
- a.x_backup,
- b.x_trimmed,
- c.x_trimmed_without_group,
- d.x_withspaces_start_end,
- e.x_withspaces_start_only,
- f.x_withspaces_end_only,
- g.x_backup_without_spp,
- h.x_species,
- i.x_trimmed_species) {
-
- # FIRST TRY FULLNAMES AND CODES ----
- # if only genus is available, return only genus
-
- if (all(!c(x[i], b.x_trimmed) %like_case% " ")) {
- found <- lookup(fullname_lower %in% c(h.x_species, i.x_trimmed_species),
- haystack = data_to_check)
- if (!is.na(found)) {
- x[i] <- found[1L]
- return(x[i])
- }
- if (nchar(g.x_backup_without_spp) >= 6) {
- found <- lookup(fullname_lower %like_case% paste0("^", unregex(g.x_backup_without_spp), "[a-z]+"),
- haystack = data_to_check)
- if (!is.na(found)) {
- x[i] <- found[1L]
- return(x[i])
- }
- }
- # rest of genus only is in allow_uncertain part.
- }
-
- # allow no codes less than 4 characters long, was already checked for WHONET earlier
- if (nchar(g.x_backup_without_spp) < 4) {
- x[i] <- lookup(mo == "UNKNOWN")
- if (initial_search == TRUE) {
- failures <- c(failures, a.x_backup)
- }
- return(x[i])
- }
-
- # try probable: trimmed version of fullname ----
- found <- lookup(fullname_lower %in% tolower(g.x_backup_without_spp),
- haystack = data_to_check)
- if (!is.na(found)) {
- return(found[1L])
- }
-
- # try any match keeping spaces ----
- if (nchar(g.x_backup_without_spp) >= 6) {
- found <- lookup(fullname_lower %like_case% d.x_withspaces_start_end,
- haystack = data_to_check)
- if (!is.na(found)) {
- return(found[1L])
- }
- }
-
- # try any match keeping spaces, not ending with $ ----
- found <- lookup(fullname_lower %like_case% paste0(trimws(e.x_withspaces_start_only), " "),
- haystack = data_to_check)
- if (!is.na(found)) {
- return(found[1L])
- }
- if (nchar(g.x_backup_without_spp) >= 6) {
- found <- lookup(fullname_lower %like_case% e.x_withspaces_start_only,
- haystack = data_to_check)
- if (!is.na(found)) {
- return(found[1L])
- }
- }
-
- # try any match keeping spaces, not start with ^ ----
- found <- lookup(fullname_lower %like_case% paste0(" ", trimws(f.x_withspaces_end_only)),
- haystack = data_to_check)
- if (!is.na(found)) {
- return(found[1L])
- }
-
- # try a trimmed version
- if (nchar(g.x_backup_without_spp) >= 6) {
- found <- lookup(fullname_lower %like_case% b.x_trimmed |
- fullname_lower %like_case% c.x_trimmed_without_group,
- haystack = data_to_check)
- if (!is.na(found)) {
- return(found[1L])
- }
+ progress$tick()
}
-
- # try splitting of characters in the middle and then find ID ----
- # only when text length is 6 or lower
- # like esco = E. coli, klpn = K. pneumoniae, stau = S. aureus, staaur = S. aureus
- if (nchar(g.x_backup_without_spp) <= 6) {
- x_length <- nchar(g.x_backup_without_spp)
- x_split <- paste0("^",
- g.x_backup_without_spp %pm>% substr(1, x_length / 2),
- ".* ",
- g.x_backup_without_spp %pm>% substr((x_length / 2) + 1, x_length))
- found <- lookup(fullname_lower %like_case% x_split,
- haystack = data_to_check)
- if (!is.na(found)) {
- return(found[1L])
- }
- }
-
- # try fullname without start and without nchar limit of >= 6 ----
- # like "K. pneu rhino" >> "Klebsiella pneumoniae (rhinoscleromatis)" = KLEPNERH
- found <- lookup(fullname_lower %like_case% e.x_withspaces_start_only,
- haystack = data_to_check)
+ # valid MO code ----
+ found <- lookup(mo == toupper(x_backup[i]))
if (!is.na(found)) {
- return(found[1L])
+ x[i] <- found[1L]
+ next
}
-
- # MISCELLANEOUS ----
-
- # look for old taxonomic names ----
- found <- lookup(fullname_lower %like_case% e.x_withspaces_start_only,
+
+ # valid fullname ----
+ found <- lookup(fullname_lower %in% gsub("[^a-zA-Z0-9_. -]", "", tolower(c(x_backup[i], x_backup_without_spp[i])), perl = TRUE))
+ # added the gsub() for "(unknown fungus)", since fullname_lower does not contain brackets
+ if (!is.na(found)) {
+ x[i] <- found[1L]
+ next
+ }
+
+ # old fullname ----
+ found <- lookup(fullname_lower %in% tolower(c(x_backup[i], x_backup_without_spp[i])),
column = NULL, # all columns
- haystack = data.old_to_check)
+ haystack = MO.old_lookup)
if (!all(is.na(found))) {
# when property is "ref" (which is the case in mo_ref, mo_authors and mo_year), return the old value, so:
# mo_ref() of "Chlamydia psittaci" will be "Page, 1968" (with warning)
@@ -988,351 +627,461 @@ exec_as.mo <- function(x,
ref_old = found["ref"],
ref_new = lookup(fullname == found["fullname_new"], "ref", haystack = MO_lookup),
mo = lookup(fullname == found["fullname_new"], "mo", haystack = MO_lookup))
- return(x[i])
+ next
}
-
- # check for uncertain results ----
- uncertain_fn <- function(a.x_backup,
- b.x_trimmed,
- d.x_withspaces_start_end,
- e.x_withspaces_start_only,
- f.x_withspaces_end_only,
- g.x_backup_without_spp,
- uncertain.reference_data_to_use) {
-
- if (uncertainty_level == 0) {
- # do not allow uncertainties
- return(NA_character_)
- }
-
- # UNCERTAINTY LEVEL 1 ----
- if (uncertainty_level >= 1) {
- now_checks_for_uncertainty_level <- 1
-
- # (1) look again for old taxonomic names, now for G. species ----
- if (isTRUE(debug)) {
- cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (1) look again for old taxonomic names, now for G. species\n"))
- }
- if (isTRUE(debug)) {
- message("Running '", d.x_withspaces_start_end, "' and '", e.x_withspaces_start_only, "'")
- }
- found <- lookup(fullname_lower %like_case% d.x_withspaces_start_end |
- fullname_lower %like_case% e.x_withspaces_start_only,
- column = NULL, # all columns
- haystack = data.old_to_check)
- if (!all(is.na(found)) & nchar(g.x_backup_without_spp) >= 6) {
- if (property == "ref") {
- # when property is "ref" (which is the case in mo_ref, mo_authors and mo_year), return the old value, so:
- # mo_ref("Chlamydia psittaci") = "Page, 1968" (with warning)
- # mo_ref("Chlamydophila psittaci") = "Everett et al., 1999"
- x <- found["ref"]
- } else {
- x <- lookup(fullname == found["fullname_new"], haystack = MO_lookup)
- }
- was_renamed(name_old = found["fullname"],
- name_new = lookup(fullname == found["fullname_new"], "fullname", haystack = MO_lookup),
- ref_old = found["ref"],
- ref_new = lookup(fullname == found["fullname_new"], "ref", haystack = MO_lookup),
- mo = lookup(fullname == found["fullname_new"], "mo", haystack = MO_lookup))
- pkg_env$mo_renamed_last_run <- found["fullname"]
- uncertainties <<- rbind(uncertainties,
- format_uncertainty_as_df(uncertainty_level = now_checks_for_uncertainty_level,
- input = a.x_backup,
- result_mo = lookup(fullname == found["fullname_new"], "mo", haystack = MO_lookup)),
- stringsAsFactors = FALSE)
- return(x)
- }
-
- # (2) Try with misspelled input ----
- # just rerun with dyslexia_mode = TRUE will used the extensive regex part above
- if (isTRUE(debug)) {
- cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (2) Try with misspelled input\n"))
- }
- if (isTRUE(debug)) {
- message("Running '", a.x_backup, "'")
- }
- # first try without dyslexia mode
- found <- suppressMessages(suppressWarnings(exec_as.mo(a.x_backup, initial_search = FALSE, dyslexia_mode = FALSE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 1, actual_input = a.x_backup)))
- if (empty_result(found)) {
- # then with dyslexia mode
- found <- suppressMessages(suppressWarnings(exec_as.mo(a.x_backup, initial_search = FALSE, dyslexia_mode = TRUE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 1, actual_input = a.x_backup)))
- }
- if (!empty_result(found)) {
- found_result <- found
- uncertainties <<- rbind(uncertainties,
- attr(found, which = "uncertainties", exact = TRUE),
- stringsAsFactors = FALSE)
- found <- lookup(mo == found)
- return(found)
+
+ if (x_backup[i] %like_case% "\\(unknown [a-z]+\\)" | tolower(x_backup_without_spp[i]) %in% c("other", "none", "unknown")) {
+ # empty and nonsense values, ignore without warning
+ x[i] <- lookup(mo == "UNKNOWN")
+ next
+ }
+
+ # exact SNOMED code ----
+ if (x_backup[i] %like_case% "^[0-9]+$") {
+ snomed_found <- unlist(lapply(reference_data_to_use$snomed,
+ function(s) if (x_backup[i] %in% s) {
+ TRUE
+ } else {
+ FALSE
+ }))
+ if (sum(snomed_found, na.rm = TRUE) > 0) {
+ found <- reference_data_to_use[snomed_found == TRUE, property][[1]]
+ if (!is.na(found)) {
+ x[i] <- found[1L]
+ next
}
}
-
- # UNCERTAINTY LEVEL 2 ----
- if (uncertainty_level >= 2) {
- now_checks_for_uncertainty_level <- 2
-
- # (3) look for genus only, part of name ----
- if (isTRUE(debug)) {
- cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (3) look for genus only, part of name\n"))
- }
- if (nchar(g.x_backup_without_spp) > 4 & !b.x_trimmed %like_case% " ") {
- if (!grepl("^[A-Z][a-z]+", b.x_trimmed, ignore.case = FALSE)) {
- if (isTRUE(debug)) {
- message("Running '", paste(b.x_trimmed, "species"), "'")
- }
- # not when input is like Genustext, because then Neospora would lead to Actinokineospora
- found <- lookup(fullname_lower %like_case% paste(b.x_trimmed, "species"),
- haystack = uncertain.reference_data_to_use)
- if (!is.na(found)) {
- found_result <- found
- found <- lookup(mo == found)
- uncertainties <<- rbind(uncertainties,
- format_uncertainty_as_df(uncertainty_level = now_checks_for_uncertainty_level,
- input = a.x_backup,
- result_mo = found_result),
- stringsAsFactors = FALSE)
- return(found)
- }
- }
- }
-
- # (4) strip values between brackets ----
- if (isTRUE(debug)) {
- cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (4) strip values between brackets\n"))
- }
- a.x_backup_stripped <- gsub("( *[(].*[)] *)", " ", a.x_backup, perl = TRUE)
- a.x_backup_stripped <- trimws(gsub(" +", " ", a.x_backup_stripped, perl = TRUE))
- if (isTRUE(debug)) {
- message("Running '", a.x_backup_stripped, "'")
- }
- # first try without dyslexia mode
- found <- suppressMessages(suppressWarnings(exec_as.mo(a.x_backup_stripped, initial_search = FALSE, dyslexia_mode = FALSE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
- if (empty_result(found)) {
- # then with dyslexia mode
- found <- suppressMessages(suppressWarnings(exec_as.mo(a.x_backup_stripped, initial_search = FALSE, dyslexia_mode = TRUE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
- }
- if (!empty_result(found) & nchar(g.x_backup_without_spp) >= 6) {
- found_result <- found
- uncertainties <<- rbind(uncertainties,
- attr(found, which = "uncertainties", exact = TRUE),
- stringsAsFactors = FALSE)
- found <- lookup(mo == found)
- return(found)
- }
-
- # (5) inverse input ----
- if (isTRUE(debug)) {
- cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (5) inverse input\n"))
- }
- a.x_backup_inversed <- paste(rev(unlist(strsplit(a.x_backup, split = " "))), collapse = " ")
- if (isTRUE(debug)) {
- message("Running '", a.x_backup_inversed, "'")
- }
-
- # first try without dyslexia mode
- found <- suppressMessages(suppressWarnings(exec_as.mo(a.x_backup_inversed, initial_search = FALSE, dyslexia_mode = FALSE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
- if (empty_result(found)) {
- # then with dyslexia mode
- found <- suppressMessages(suppressWarnings(exec_as.mo(a.x_backup_inversed, initial_search = FALSE, dyslexia_mode = TRUE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
- }
- if (!empty_result(found) & nchar(g.x_backup_without_spp) >= 6) {
- found_result <- found
- uncertainties <<- rbind(uncertainties,
- attr(found, which = "uncertainties", exact = TRUE),
- stringsAsFactors = FALSE)
- found <- lookup(mo == found)
- return(found)
- }
-
- # (6) try to strip off half an element from end and check the remains ----
- if (isTRUE(debug)) {
- cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (6) try to strip off half an element from end and check the remains\n"))
- }
- x_strip <- a.x_backup %pm>% strsplit("[ .]") %pm>% unlist()
- if (length(x_strip) > 1) {
- for (i in seq_len(length(x_strip) - 1)) {
- lastword <- x_strip[length(x_strip) - i + 1]
- lastword_half <- substr(lastword, 1, as.integer(nchar(lastword) / 2))
- # remove last half of the second term
- x_strip_collapsed <- paste(c(x_strip[seq_len(length(x_strip) - i)], lastword_half), collapse = " ")
- if (nchar(x_strip_collapsed) >= 4 & nchar(lastword_half) > 2) {
- if (isTRUE(debug)) {
- message("Running '", x_strip_collapsed, "'")
- }
- # first try without dyslexia mode
- found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = FALSE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
- if (empty_result(found)) {
- # then with dyslexia mode
- found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = TRUE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
- }
- if (!empty_result(found)) {
- found_result <- found
- uncertainties <<- rbind(uncertainties,
- attr(found, which = "uncertainties", exact = TRUE),
- stringsAsFactors = FALSE)
- found <- lookup(mo == found)
- return(found)
- }
- }
- }
- }
- # (7) try to strip off one element from end and check the remains ----
- if (isTRUE(debug)) {
- cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (7) try to strip off one element from end and check the remains\n"))
- }
- if (length(x_strip) > 1) {
- for (i in seq_len(length(x_strip) - 1)) {
- x_strip_collapsed <- paste(x_strip[seq_len(length(x_strip) - i)], collapse = " ")
- if (nchar(x_strip_collapsed) >= 6) {
- if (isTRUE(debug)) {
- message("Running '", x_strip_collapsed, "'")
- }
- # first try without dyslexia mode
- found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = FALSE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
- if (empty_result(found)) {
- # then with dyslexia mode
- found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = TRUE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
- }
-
- if (!empty_result(found)) {
- found_result <- found
- uncertainties <<- rbind(uncertainties,
- attr(found, which = "uncertainties", exact = TRUE),
- stringsAsFactors = FALSE)
- found <- lookup(mo == found)
- return(found)
- }
- }
- }
- }
- # (8) check for unknown yeasts/fungi ----
- if (isTRUE(debug)) {
- cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (8) check for unknown yeasts/fungi\n"))
- }
- if (b.x_trimmed %like_case% "yeast") {
- found <- "F_YEAST"
- found_result <- found
- found <- lookup(mo == found)
- uncertainties <<- rbind(uncertainties,
- format_uncertainty_as_df(uncertainty_level = now_checks_for_uncertainty_level,
- input = a.x_backup,
- result_mo = found_result),
- stringsAsFactors = FALSE)
- return(found)
- }
- if (b.x_trimmed %like_case% "(fungus|fungi)" & !b.x_trimmed %like_case% "fungiphrya") {
- found <- "F_FUNGUS"
- found_result <- found
- found <- lookup(mo == found)
- uncertainties <<- rbind(uncertainties,
- format_uncertainty_as_df(uncertainty_level = now_checks_for_uncertainty_level,
- input = a.x_backup,
- result_mo = found_result),
- stringsAsFactors = FALSE)
- return(found)
- }
- # (9) try to strip off one element from start and check the remains (only allow >= 2-part name outcome) ----
- if (isTRUE(debug)) {
- cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (9) try to strip off one element from start and check the remains (only allow >= 2-part name outcome)\n"))
- }
- x_strip <- a.x_backup %pm>% strsplit("[ .]") %pm>% unlist()
- if (length(x_strip) > 1 & nchar(g.x_backup_without_spp) >= 6) {
- for (i in 2:(length(x_strip))) {
- x_strip_collapsed <- paste(x_strip[i:length(x_strip)], collapse = " ")
- if (isTRUE(debug)) {
- message("Running '", x_strip_collapsed, "'")
- }
- # first try without dyslexia mode
- found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = FALSE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
- if (empty_result(found)) {
- # then with dyslexia mode
- found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = TRUE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
- }
- if (!empty_result(found)) {
- found_result <- found
- # uncertainty level 2 only if searched part contains a space (otherwise it will be found with lvl 3)
- if (x_strip_collapsed %like_case% " ") {
- uncertainties <<- rbind(uncertainties,
- attr(found, which = "uncertainties", exact = TRUE),
- stringsAsFactors = FALSE)
- found <- lookup(mo == found)
- return(found)
- }
- }
- }
- }
+ }
+
+ # very probable: is G. species ----
+ found <- lookup(g_species %in% gsub("[^a-z0-9/ \\-]+", "",
+ tolower(c(x_backup[i], x_backup_without_spp[i])), perl = TRUE))
+ if (!is.na(found)) {
+ x[i] <- found[1L]
+ next
+ }
+
+ # WHONET and other common LIS codes ----
+ found <- microorganisms.codes[which(microorganisms.codes$code %in% toupper(c(x_backup_untouched[i], x_backup[i], x_backup_without_spp[i]))), "mo", drop = TRUE][1L]
+ if (!is.na(found)) {
+ x[i] <- lookup(mo == found)
+ next
+ }
+
+ # user-defined reference ----
+ if (!is.null(reference_df)) {
+ if (x_backup[i] %in% reference_df[, 1]) {
+ # already checked integrity of reference_df, all MOs are valid
+ ref_mo <- reference_df[reference_df[, 1] == x_backup[i], "mo"][[1L]]
+ x[i] <- lookup(mo == ref_mo)
+ next
}
-
- # UNCERTAINTY LEVEL 3 ----
- if (uncertainty_level >= 3) {
- now_checks_for_uncertainty_level <- 3
-
- # (10) try to strip off one element from start and check the remains (any text size) ----
- if (isTRUE(debug)) {
- cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (10) try to strip off one element from start and check the remains (any text size)\n"))
- }
- x_strip <- a.x_backup %pm>% strsplit("[ .]") %pm>% unlist()
- if (length(x_strip) > 1 & nchar(g.x_backup_without_spp) >= 6) {
- for (i in 2:(length(x_strip))) {
- x_strip_collapsed <- paste(x_strip[i:length(x_strip)], collapse = " ")
- if (isTRUE(debug)) {
- message("Running '", x_strip_collapsed, "'")
- }
- # first try without dyslexia mode
- found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = FALSE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 3, actual_input = a.x_backup)))
- if (empty_result(found)) {
- # then with dyslexia mode
- found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = TRUE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 3, actual_input = a.x_backup)))
- }
- if (!empty_result(found)) {
- found_result <- found
- uncertainties <<- rbind(uncertainties,
- attr(found, which = "uncertainties", exact = TRUE),
- stringsAsFactors = FALSE)
- found <- lookup(mo == found)
- return(found)
- }
- }
- }
- # (11) try to strip off one element from end and check the remains (any text size) ----
- # (this is in fact 7 but without nchar limit of >=6)
- if (isTRUE(debug)) {
- cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (11) try to strip off one element from end and check the remains (any text size)\n"))
- }
- if (length(x_strip) > 1) {
- for (i in seq_len(length(x_strip) - 1)) {
- x_strip_collapsed <- paste(x_strip[seq_len(length(x_strip) - i)], collapse = " ")
- if (isTRUE(debug)) {
- message("Running '", x_strip_collapsed, "'")
- }
- # first try without dyslexia mode
- found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = FALSE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 3, actual_input = a.x_backup)))
- if (empty_result(found)) {
- # then with dyslexia mode
- found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = TRUE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 3, actual_input = a.x_backup)))
- }
- if (!empty_result(found)) {
- found_result <- found
- uncertainties <<- rbind(uncertainties,
- attr(found, which = "uncertainties", exact = TRUE),
- stringsAsFactors = FALSE)
- found <- lookup(mo == found)
- return(found)
- }
- }
- }
-
- # (12) part of a name (very unlikely match) ----
- if (isTRUE(debug)) {
- cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (12) part of a name (very unlikely match)\n"))
- }
- if (isTRUE(debug)) {
- message("Running '", f.x_withspaces_end_only, "'")
+ }
+
+ # WHONET: xxx = no growth
+ if (tolower(as.character(paste0(x_backup_without_spp[i], ""))) %in% c("", "xxx", "na", "nan")) {
+ x[i] <- NA_character_
+ next
+ }
+
+ # check for very small input, but ignore the O antigens of E. coli
+ if (nchar(gsub("[^a-zA-Z]", "", x_trimmed[i])) < 3
+ & !toupper(x_backup_without_spp[i]) %like_case% "O?(26|103|104|104|111|121|145|157)") {
+ # fewer than 3 chars and not looked for species, add as failure
+ x[i] <- lookup(mo == "UNKNOWN")
+ if (initial_search == TRUE) {
+ failures <- c(failures, x_backup[i])
+ }
+ next
+ }
+
+ if (x_backup_without_spp[i] %like_case% "(virus|viridae)") {
+ # there is no fullname like virus or viridae, so don't try to coerce it
+ x[i] <- NA_character_
+ next
+ }
+
+ # translate known trivial abbreviations to genus + species ----
+ if (toupper(x_backup_without_spp[i]) %in% c("MRSA", "MSSA", "VISA", "VRSA", "BORSA")
+ | x_backup_without_spp[i] %like_case% "(^| )(mrsa|mssa|visa|vrsa|borsa|la-?mrsa|ca-?mrsa)( |$)") {
+ x[i] <- lookup(fullname == "Staphylococcus aureus", uncertainty = -1)
+ next
+ }
+ if (toupper(x_backup_without_spp[i]) %in% c("MRSE", "MSSE")
+ | x_backup_without_spp[i] %like_case% "(^| )(mrse|msse)( |$)") {
+ x[i] <- lookup(fullname == "Staphylococcus epidermidis", uncertainty = -1)
+ next
+ }
+ if (toupper(x_backup_without_spp[i]) == "VRE"
+ | x_backup_without_spp[i] %like_case% "(^| )vre "
+ | x_backup_without_spp[i] %like_case% "(enterococci|enterokok|enterococo)[a-z]*?$") {
+ x[i] <- lookup(genus == "Enterococcus", uncertainty = -1)
+ next
+ }
+ # support for:
+ # - 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)
+ # - UPEC (Uropathogenic E. coli)
+ if (toupper(x_backup_without_spp[i]) %in% c("AIEC", "ATEC", "DAEC", "EAEC", "EHEC", "EIEC", "EPEC", "ETEC", "NMEC", "STEC", "UPEC")
+ # also support O-antigens of E. coli: O26, O103, O104, O111, O121, O145, O157
+ | x_backup_without_spp[i] %like_case% "o?(26|103|104|111|121|145|157)") {
+ x[i] <- lookup(fullname == "Escherichia coli", uncertainty = -1)
+ next
+ }
+ if (toupper(x_backup_without_spp[i]) == "MRPA"
+ | x_backup_without_spp[i] %like_case% "(^| )mrpa( |$)") {
+ # multi resistant P. aeruginosa
+ x[i] <- lookup(fullname == "Pseudomonas aeruginosa", uncertainty = -1)
+ next
+ }
+ if (toupper(x_backup_without_spp[i]) == "CRSM") {
+ # co-trim resistant S. maltophilia
+ x[i] <- lookup(fullname == "Stenotrophomonas maltophilia", uncertainty = -1)
+ next
+ }
+ if (toupper(x_backup_without_spp[i]) %in% c("PISP", "PRSP", "VISP", "VRSP")
+ | x_backup_without_spp[i] %like_case% "(^| )(pisp|prsp|visp|vrsp)( |$)") {
+ # peni I, peni R, vanco I, vanco R: S. pneumoniae
+ x[i] <- lookup(fullname == "Streptococcus pneumoniae", uncertainty = -1)
+ next
+ }
+ if (x_backup_without_spp[i] %like_case% "^g[abcdfghk]s$") {
+ # Streptococci, like GBS = Group B Streptococci (B_STRPT_GRPB)
+ x[i] <- lookup(mo == toupper(gsub("g([abcdfghk])s",
+ "B_STRPT_GRP\\1",
+ x_backup_without_spp[i])), uncertainty = -1)
+ next
+ }
+ if (x_backup_without_spp[i] %like_case% "(streptococ|streptokok).* [abcdfghk]$") {
+ # Streptococci in different languages, like "estreptococos grupo B"
+ x[i] <- lookup(mo == toupper(gsub(".*(streptococ|streptokok|estreptococ).* ([abcdfghk])$",
+ "B_STRPT_GRP\\2",
+ x_backup_without_spp[i])), uncertainty = -1)
+ next
+ }
+ if (x_backup_without_spp[i] %like_case% "group [abcdfghk] (streptococ|streptokok|estreptococ)") {
+ # Streptococci in different languages, like "Group A Streptococci"
+ x[i] <- lookup(mo == toupper(gsub(".*group ([abcdfghk]) (streptococ|streptokok|estreptococ).*",
+ "B_STRPT_GRP\\1",
+ x_backup_without_spp[i])), uncertainty = -1)
+ next
+ }
+ if (x_backup_without_spp[i] %like_case% "haemoly.*strep") {
+ # Haemolytic streptococci in different languages
+ x[i] <- lookup(mo == "B_STRPT_HAEM", uncertainty = -1)
+ next
+ }
+ # CoNS/CoPS in different languages (support for German, Dutch, Spanish, Portuguese)
+ if (x_backup_without_spp[i] %like_case% "[ck]oagulas[ea] negatie?[vf]"
+ | x_trimmed[i] %like_case% "[ck]oagulas[ea] negatie?[vf]"
+ | x_backup_without_spp[i] %like_case% "[ck]o?ns[^a-z]?$") {
+ # coerce S. coagulase negative
+ x[i] <- lookup(mo == "B_STPHY_CONS", uncertainty = -1)
+ next
+ }
+ if (x_backup_without_spp[i] %like_case% "[ck]oagulas[ea] positie?[vf]"
+ | x_trimmed[i] %like_case% "[ck]oagulas[ea] positie?[vf]"
+ | x_backup_without_spp[i] %like_case% "[ck]o?ps[^a-z]?$") {
+ # coerce S. coagulase positive
+ x[i] <- lookup(mo == "B_STPHY_COPS", uncertainty = -1)
+ next
+ }
+ # streptococcal groups: milleri and viridans
+ if (x_trimmed[i] %like_case% "strepto.* mil+er+i"
+ | x_backup_without_spp[i] %like_case% "strepto.* mil+er+i"
+ | x_backup_without_spp[i] %like_case% "mgs[^a-z]?$") {
+ # Milleri Group Streptococcus (MGS)
+ x[i] <- lookup(mo == "B_STRPT_MILL", uncertainty = -1)
+ next
+ }
+ if (x_trimmed[i] %like_case% "strepto.* viridans"
+ | x_backup_without_spp[i] %like_case% "strepto.* viridans"
+ | x_backup_without_spp[i] %like_case% "vgs[^a-z]?$") {
+ # Viridans Group Streptococcus (VGS)
+ x[i] <- lookup(mo == "B_STRPT_VIRI", uncertainty = -1)
+ next
+ }
+ if (x_backup_without_spp[i] %like_case% "gram[ -]?neg.*"
+ | x_backup_without_spp[i] %like_case% "negatie?[vf]"
+ | x_trimmed[i] %like_case% "gram[ -]?neg.*") {
+ # coerce Gram negatives
+ x[i] <- lookup(mo == "B_GRAMN", uncertainty = -1)
+ next
+ }
+ if (x_backup_without_spp[i] %like_case% "gram[ -]?pos.*"
+ | x_backup_without_spp[i] %like_case% "positie?[vf]"
+ | x_trimmed[i] %like_case% "gram[ -]?pos.*") {
+ # coerce Gram positives
+ x[i] <- lookup(mo == "B_GRAMP", uncertainty = -1)
+ next
+ }
+ if (x_backup_without_spp[i] %like_case% "mycoba[ck]teri.[nm]?$") {
+ # coerce mycobacteria in multiple languages
+ x[i] <- lookup(genus == "Mycobacterium", uncertainty = -1)
+ next
+ }
+
+ if (x_backup_without_spp[i] %like_case% "salmonella [a-z]+ ?.*") {
+ if (x_backup_without_spp[i] %like_case% "salmonella group") {
+ # Salmonella Group A to Z, just return S. species for now
+ x[i] <- lookup(genus == "Salmonella", uncertainty = -1)
+ next
+ } else if (grepl("[sS]almonella [A-Z][a-z]+ ?.*", x_backup[i], ignore.case = FALSE) &
+ !x_backup[i] %like% "t[iy](ph|f)[iy]") {
+ # Salmonella with capital letter species like "Salmonella Goettingen" - they're all S. enterica
+ # except for S. typhi, S. paratyphi, S. typhimurium
+ x[i] <- lookup(fullname == "Salmonella enterica", uncertainty = -1)
+ uncertainties <- rbind(uncertainties,
+ format_uncertainty_as_df(uncertainty_level = 1,
+ input = x_backup[i],
+ result_mo = lookup(fullname == "Salmonella enterica", "mo", uncertainty = -1)),
+ stringsAsFactors = FALSE)
+ next
+ }
+ }
+
+ # trivial names known to the field:
+ if ("meningococcus" %like_case% x_trimmed[i]) {
+ # coerce Neisseria meningitidis
+ x[i] <- lookup(fullname == "Neisseria meningitidis", uncertainty = -1)
+ next
+ }
+ if ("gonococcus" %like_case% x_trimmed[i]) {
+ # coerce Neisseria gonorrhoeae
+ x[i] <- lookup(fullname == "Neisseria gonorrhoeae", uncertainty = -1)
+ next
+ }
+ if ("pneumococcus" %like_case% x_trimmed[i]) {
+ # coerce Streptococcus penumoniae
+ x[i] <- lookup(fullname == "Streptococcus pneumoniae", uncertainty = -1)
+ next
+ }
+
+ if (x_backup[i] %in% pkg_env$mo_failed) {
+ # previously failed already in this session ----
+ # (at this point the latest reference_df has also been checked)
+ x[i] <- lookup(mo == "UNKNOWN")
+ if (initial_search == TRUE) {
+ failures <- c(failures, x_backup[i])
+ }
+ next
+ }
+
+ # NOW RUN THROUGH DIFFERENT PREVALENCE LEVELS
+ check_per_prevalence <- function(data_to_check,
+ data.old_to_check,
+ a.x_backup,
+ b.x_trimmed,
+ c.x_trimmed_without_group,
+ d.x_withspaces_start_end,
+ e.x_withspaces_start_only,
+ f.x_withspaces_end_only,
+ g.x_backup_without_spp,
+ h.x_species,
+ i.x_trimmed_species) {
+
+ # FIRST TRY FULLNAMES AND CODES ----
+ # if only genus is available, return only genus
+
+ if (all(!c(x[i], b.x_trimmed) %like_case% " ")) {
+ found <- lookup(fullname_lower %in% c(h.x_species, i.x_trimmed_species),
+ haystack = data_to_check)
+ if (!is.na(found)) {
+ x[i] <- found[1L]
+ return(x[i])
}
if (nchar(g.x_backup_without_spp) >= 6) {
- found <- lookup(fullname_lower %like_case% f.x_withspaces_end_only, column = "mo")
+ found <- lookup(fullname_lower %like_case% paste0("^", unregex(g.x_backup_without_spp), "[a-z]+"),
+ haystack = data_to_check)
if (!is.na(found)) {
- found_result <- lookup(mo == found)
+ x[i] <- found[1L]
+ return(x[i])
+ }
+ }
+ # rest of genus only is in allow_uncertain part.
+ }
+
+ # allow no codes less than 4 characters long, was already checked for WHONET earlier
+ if (nchar(g.x_backup_without_spp) < 4) {
+ x[i] <- lookup(mo == "UNKNOWN")
+ if (initial_search == TRUE) {
+ failures <- c(failures, a.x_backup)
+ }
+ return(x[i])
+ }
+
+ # try probable: trimmed version of fullname ----
+ found <- lookup(fullname_lower %in% tolower(g.x_backup_without_spp),
+ haystack = data_to_check)
+ if (!is.na(found)) {
+ return(found[1L])
+ }
+
+ # try any match keeping spaces ----
+ if (nchar(g.x_backup_without_spp) >= 6) {
+ found <- lookup(fullname_lower %like_case% d.x_withspaces_start_end,
+ haystack = data_to_check)
+ if (!is.na(found)) {
+ return(found[1L])
+ }
+ }
+
+ # try any match keeping spaces, not ending with $ ----
+ found <- lookup(fullname_lower %like_case% paste0(trimws(e.x_withspaces_start_only), " "),
+ haystack = data_to_check)
+ if (!is.na(found)) {
+ return(found[1L])
+ }
+ if (nchar(g.x_backup_without_spp) >= 6) {
+ found <- lookup(fullname_lower %like_case% e.x_withspaces_start_only,
+ haystack = data_to_check)
+ if (!is.na(found)) {
+ return(found[1L])
+ }
+ }
+
+ # try any match keeping spaces, not start with ^ ----
+ found <- lookup(fullname_lower %like_case% paste0(" ", trimws(f.x_withspaces_end_only)),
+ haystack = data_to_check)
+ if (!is.na(found)) {
+ return(found[1L])
+ }
+
+ # try a trimmed version
+ if (nchar(g.x_backup_without_spp) >= 6) {
+ found <- lookup(fullname_lower %like_case% b.x_trimmed |
+ fullname_lower %like_case% c.x_trimmed_without_group,
+ haystack = data_to_check)
+ if (!is.na(found)) {
+ return(found[1L])
+ }
+ }
+
+
+ # try splitting of characters in the middle and then find ID ----
+ # only when text length is 6 or lower
+ # like esco = E. coli, klpn = K. pneumoniae, stau = S. aureus, staaur = S. aureus
+ if (nchar(g.x_backup_without_spp) <= 6) {
+ x_length <- nchar(g.x_backup_without_spp)
+ x_split <- paste0("^",
+ g.x_backup_without_spp %pm>% substr(1, x_length / 2),
+ ".* ",
+ g.x_backup_without_spp %pm>% substr((x_length / 2) + 1, x_length))
+ found <- lookup(fullname_lower %like_case% x_split,
+ haystack = data_to_check)
+ if (!is.na(found)) {
+ return(found[1L])
+ }
+ }
+
+ # try fullname without start and without nchar limit of >= 6 ----
+ # like "K. pneu rhino" >> "Klebsiella pneumoniae (rhinoscleromatis)" = KLEPNERH
+ found <- lookup(fullname_lower %like_case% e.x_withspaces_start_only,
+ haystack = data_to_check)
+ if (!is.na(found)) {
+ return(found[1L])
+ }
+
+ # MISCELLANEOUS ----
+
+ # look for old taxonomic names ----
+ found <- lookup(fullname_lower %like_case% e.x_withspaces_start_only,
+ column = NULL, # all columns
+ haystack = data.old_to_check)
+ if (!all(is.na(found))) {
+ # when property is "ref" (which is the case in mo_ref, mo_authors and mo_year), return the old value, so:
+ # mo_ref() of "Chlamydia psittaci" will be "Page, 1968" (with warning)
+ # mo_ref() of "Chlamydophila psittaci" will be "Everett et al., 1999"
+ if (property == "ref") {
+ x[i] <- found["ref"]
+ } else {
+ x[i] <- lookup(fullname == found["fullname_new"], haystack = MO_lookup)
+ }
+ pkg_env$mo_renamed_last_run <- found["fullname"]
+ was_renamed(name_old = found["fullname"],
+ name_new = lookup(fullname == found["fullname_new"], "fullname", haystack = MO_lookup),
+ ref_old = found["ref"],
+ ref_new = lookup(fullname == found["fullname_new"], "ref", haystack = MO_lookup),
+ mo = lookup(fullname == found["fullname_new"], "mo", haystack = MO_lookup))
+ return(x[i])
+ }
+
+ # check for uncertain results ----
+ uncertain_fn <- function(a.x_backup,
+ b.x_trimmed,
+ d.x_withspaces_start_end,
+ e.x_withspaces_start_only,
+ f.x_withspaces_end_only,
+ g.x_backup_without_spp,
+ uncertain.reference_data_to_use) {
+
+ if (uncertainty_level == 0) {
+ # do not allow uncertainties
+ return(NA_character_)
+ }
+
+ # UNCERTAINTY LEVEL 1 ----
+ if (uncertainty_level >= 1) {
+ now_checks_for_uncertainty_level <- 1
+
+ # (1) look again for old taxonomic names, now for G. species ----
+ if (isTRUE(debug)) {
+ cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (1) look again for old taxonomic names, now for G. species\n"))
+ }
+ if (isTRUE(debug)) {
+ message("Running '", d.x_withspaces_start_end, "' and '", e.x_withspaces_start_only, "'")
+ }
+ found <- lookup(fullname_lower %like_case% d.x_withspaces_start_end |
+ fullname_lower %like_case% e.x_withspaces_start_only,
+ column = NULL, # all columns
+ haystack = data.old_to_check)
+ if (!all(is.na(found)) & nchar(g.x_backup_without_spp) >= 6) {
+ if (property == "ref") {
+ # when property is "ref" (which is the case in mo_ref, mo_authors and mo_year), return the old value, so:
+ # mo_ref("Chlamydia psittaci") = "Page, 1968" (with warning)
+ # mo_ref("Chlamydophila psittaci") = "Everett et al., 1999"
+ x <- found["ref"]
+ } else {
+ x <- lookup(fullname == found["fullname_new"], haystack = MO_lookup)
+ }
+ was_renamed(name_old = found["fullname"],
+ name_new = lookup(fullname == found["fullname_new"], "fullname", haystack = MO_lookup),
+ ref_old = found["ref"],
+ ref_new = lookup(fullname == found["fullname_new"], "ref", haystack = MO_lookup),
+ mo = lookup(fullname == found["fullname_new"], "mo", haystack = MO_lookup))
+ pkg_env$mo_renamed_last_run <- found["fullname"]
+ uncertainties <<- rbind(uncertainties,
+ format_uncertainty_as_df(uncertainty_level = now_checks_for_uncertainty_level,
+ input = a.x_backup,
+ result_mo = lookup(fullname == found["fullname_new"], "mo", haystack = MO_lookup)),
+ stringsAsFactors = FALSE)
+ return(x)
+ }
+
+ # (2) Try with misspelled input ----
+ # just rerun with dyslexia_mode = TRUE will used the extensive regex part above
+ if (isTRUE(debug)) {
+ cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (2) Try with misspelled input\n"))
+ }
+ if (isTRUE(debug)) {
+ message("Running '", a.x_backup, "'")
+ }
+ # first try without dyslexia mode
+ found <- suppressMessages(suppressWarnings(exec_as.mo(a.x_backup, initial_search = FALSE, dyslexia_mode = FALSE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 1, actual_input = a.x_backup)))
+ if (empty_result(found)) {
+ # then with dyslexia mode
+ found <- suppressMessages(suppressWarnings(exec_as.mo(a.x_backup, initial_search = FALSE, dyslexia_mode = TRUE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 1, actual_input = a.x_backup)))
+ }
+ if (!empty_result(found)) {
+ found_result <- found
uncertainties <<- rbind(uncertainties,
attr(found, which = "uncertainties", exact = TRUE),
stringsAsFactors = FALSE)
@@ -1340,110 +1089,377 @@ exec_as.mo <- function(x,
return(found)
}
}
+
+ # UNCERTAINTY LEVEL 2 ----
+ if (uncertainty_level >= 2) {
+ now_checks_for_uncertainty_level <- 2
+
+ # (3) look for genus only, part of name ----
+ if (isTRUE(debug)) {
+ cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (3) look for genus only, part of name\n"))
+ }
+ if (nchar(g.x_backup_without_spp) > 4 & !b.x_trimmed %like_case% " ") {
+ if (!grepl("^[A-Z][a-z]+", b.x_trimmed, ignore.case = FALSE)) {
+ if (isTRUE(debug)) {
+ message("Running '", paste(b.x_trimmed, "species"), "'")
+ }
+ # not when input is like Genustext, because then Neospora would lead to Actinokineospora
+ found <- lookup(fullname_lower %like_case% paste(b.x_trimmed, "species"),
+ haystack = uncertain.reference_data_to_use)
+ if (!is.na(found)) {
+ found_result <- found
+ found <- lookup(mo == found)
+ uncertainties <<- rbind(uncertainties,
+ format_uncertainty_as_df(uncertainty_level = now_checks_for_uncertainty_level,
+ input = a.x_backup,
+ result_mo = found_result),
+ stringsAsFactors = FALSE)
+ return(found)
+ }
+ }
+ }
+
+ # (4) strip values between brackets ----
+ if (isTRUE(debug)) {
+ cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (4) strip values between brackets\n"))
+ }
+ a.x_backup_stripped <- gsub("( *[(].*[)] *)", " ", a.x_backup, perl = TRUE)
+ a.x_backup_stripped <- trimws(gsub(" +", " ", a.x_backup_stripped, perl = TRUE))
+ if (isTRUE(debug)) {
+ message("Running '", a.x_backup_stripped, "'")
+ }
+ # first try without dyslexia mode
+ found <- suppressMessages(suppressWarnings(exec_as.mo(a.x_backup_stripped, initial_search = FALSE, dyslexia_mode = FALSE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
+ if (empty_result(found)) {
+ # then with dyslexia mode
+ found <- suppressMessages(suppressWarnings(exec_as.mo(a.x_backup_stripped, initial_search = FALSE, dyslexia_mode = TRUE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
+ }
+ if (!empty_result(found) & nchar(g.x_backup_without_spp) >= 6) {
+ found_result <- found
+ uncertainties <<- rbind(uncertainties,
+ attr(found, which = "uncertainties", exact = TRUE),
+ stringsAsFactors = FALSE)
+ found <- lookup(mo == found)
+ return(found)
+ }
+
+ # (5) inverse input ----
+ if (isTRUE(debug)) {
+ cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (5) inverse input\n"))
+ }
+ a.x_backup_inversed <- paste(rev(unlist(strsplit(a.x_backup, split = " "))), collapse = " ")
+ if (isTRUE(debug)) {
+ message("Running '", a.x_backup_inversed, "'")
+ }
+
+ # first try without dyslexia mode
+ found <- suppressMessages(suppressWarnings(exec_as.mo(a.x_backup_inversed, initial_search = FALSE, dyslexia_mode = FALSE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
+ if (empty_result(found)) {
+ # then with dyslexia mode
+ found <- suppressMessages(suppressWarnings(exec_as.mo(a.x_backup_inversed, initial_search = FALSE, dyslexia_mode = TRUE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
+ }
+ if (!empty_result(found) & nchar(g.x_backup_without_spp) >= 6) {
+ found_result <- found
+ uncertainties <<- rbind(uncertainties,
+ attr(found, which = "uncertainties", exact = TRUE),
+ stringsAsFactors = FALSE)
+ found <- lookup(mo == found)
+ return(found)
+ }
+
+ # (6) try to strip off half an element from end and check the remains ----
+ if (isTRUE(debug)) {
+ cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (6) try to strip off half an element from end and check the remains\n"))
+ }
+ x_strip <- a.x_backup %pm>% strsplit("[ .]") %pm>% unlist()
+ if (length(x_strip) > 1) {
+ for (i in seq_len(length(x_strip) - 1)) {
+ lastword <- x_strip[length(x_strip) - i + 1]
+ lastword_half <- substr(lastword, 1, as.integer(nchar(lastword) / 2))
+ # remove last half of the second term
+ x_strip_collapsed <- paste(c(x_strip[seq_len(length(x_strip) - i)], lastword_half), collapse = " ")
+ if (nchar(x_strip_collapsed) >= 4 & nchar(lastword_half) > 2) {
+ if (isTRUE(debug)) {
+ message("Running '", x_strip_collapsed, "'")
+ }
+ # first try without dyslexia mode
+ found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = FALSE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
+ if (empty_result(found)) {
+ # then with dyslexia mode
+ found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = TRUE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
+ }
+ if (!empty_result(found)) {
+ found_result <- found
+ uncertainties <<- rbind(uncertainties,
+ attr(found, which = "uncertainties", exact = TRUE),
+ stringsAsFactors = FALSE)
+ found <- lookup(mo == found)
+ return(found)
+ }
+ }
+ }
+ }
+ # (7) try to strip off one element from end and check the remains ----
+ if (isTRUE(debug)) {
+ cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (7) try to strip off one element from end and check the remains\n"))
+ }
+ if (length(x_strip) > 1) {
+ for (i in seq_len(length(x_strip) - 1)) {
+ x_strip_collapsed <- paste(x_strip[seq_len(length(x_strip) - i)], collapse = " ")
+ if (nchar(x_strip_collapsed) >= 6) {
+ if (isTRUE(debug)) {
+ message("Running '", x_strip_collapsed, "'")
+ }
+ # first try without dyslexia mode
+ found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = FALSE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
+ if (empty_result(found)) {
+ # then with dyslexia mode
+ found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = TRUE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
+ }
+
+ if (!empty_result(found)) {
+ found_result <- found
+ uncertainties <<- rbind(uncertainties,
+ attr(found, which = "uncertainties", exact = TRUE),
+ stringsAsFactors = FALSE)
+ found <- lookup(mo == found)
+ return(found)
+ }
+ }
+ }
+ }
+ # (8) check for unknown yeasts/fungi ----
+ if (isTRUE(debug)) {
+ cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (8) check for unknown yeasts/fungi\n"))
+ }
+ if (b.x_trimmed %like_case% "yeast") {
+ found <- "F_YEAST"
+ found_result <- found
+ found <- lookup(mo == found)
+ uncertainties <<- rbind(uncertainties,
+ format_uncertainty_as_df(uncertainty_level = now_checks_for_uncertainty_level,
+ input = a.x_backup,
+ result_mo = found_result),
+ stringsAsFactors = FALSE)
+ return(found)
+ }
+ if (b.x_trimmed %like_case% "(fungus|fungi)" & !b.x_trimmed %like_case% "fungiphrya") {
+ found <- "F_FUNGUS"
+ found_result <- found
+ found <- lookup(mo == found)
+ uncertainties <<- rbind(uncertainties,
+ format_uncertainty_as_df(uncertainty_level = now_checks_for_uncertainty_level,
+ input = a.x_backup,
+ result_mo = found_result),
+ stringsAsFactors = FALSE)
+ return(found)
+ }
+ # (9) try to strip off one element from start and check the remains (only allow >= 2-part name outcome) ----
+ if (isTRUE(debug)) {
+ cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (9) try to strip off one element from start and check the remains (only allow >= 2-part name outcome)\n"))
+ }
+ x_strip <- a.x_backup %pm>% strsplit("[ .]") %pm>% unlist()
+ if (length(x_strip) > 1 & nchar(g.x_backup_without_spp) >= 6) {
+ for (i in 2:(length(x_strip))) {
+ x_strip_collapsed <- paste(x_strip[i:length(x_strip)], collapse = " ")
+ if (isTRUE(debug)) {
+ message("Running '", x_strip_collapsed, "'")
+ }
+ # first try without dyslexia mode
+ found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = FALSE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
+ if (empty_result(found)) {
+ # then with dyslexia mode
+ found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = TRUE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 2, actual_input = a.x_backup)))
+ }
+ if (!empty_result(found)) {
+ found_result <- found
+ # uncertainty level 2 only if searched part contains a space (otherwise it will be found with lvl 3)
+ if (x_strip_collapsed %like_case% " ") {
+ uncertainties <<- rbind(uncertainties,
+ attr(found, which = "uncertainties", exact = TRUE),
+ stringsAsFactors = FALSE)
+ found <- lookup(mo == found)
+ return(found)
+ }
+ }
+ }
+ }
+ }
+
+ # UNCERTAINTY LEVEL 3 ----
+ if (uncertainty_level >= 3) {
+ now_checks_for_uncertainty_level <- 3
+
+ # (10) try to strip off one element from start and check the remains (any text size) ----
+ if (isTRUE(debug)) {
+ cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (10) try to strip off one element from start and check the remains (any text size)\n"))
+ }
+ x_strip <- a.x_backup %pm>% strsplit("[ .]") %pm>% unlist()
+ if (length(x_strip) > 1 & nchar(g.x_backup_without_spp) >= 6) {
+ for (i in 2:(length(x_strip))) {
+ x_strip_collapsed <- paste(x_strip[i:length(x_strip)], collapse = " ")
+ if (isTRUE(debug)) {
+ message("Running '", x_strip_collapsed, "'")
+ }
+ # first try without dyslexia mode
+ found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = FALSE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 3, actual_input = a.x_backup)))
+ if (empty_result(found)) {
+ # then with dyslexia mode
+ found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = TRUE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 3, actual_input = a.x_backup)))
+ }
+ if (!empty_result(found)) {
+ found_result <- found
+ uncertainties <<- rbind(uncertainties,
+ attr(found, which = "uncertainties", exact = TRUE),
+ stringsAsFactors = FALSE)
+ found <- lookup(mo == found)
+ return(found)
+ }
+ }
+ }
+ # (11) try to strip off one element from end and check the remains (any text size) ----
+ # (this is in fact 7 but without nchar limit of >=6)
+ if (isTRUE(debug)) {
+ cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (11) try to strip off one element from end and check the remains (any text size)\n"))
+ }
+ if (length(x_strip) > 1) {
+ for (i in seq_len(length(x_strip) - 1)) {
+ x_strip_collapsed <- paste(x_strip[seq_len(length(x_strip) - i)], collapse = " ")
+ if (isTRUE(debug)) {
+ message("Running '", x_strip_collapsed, "'")
+ }
+ # first try without dyslexia mode
+ found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = FALSE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 3, actual_input = a.x_backup)))
+ if (empty_result(found)) {
+ # then with dyslexia mode
+ found <- suppressMessages(suppressWarnings(exec_as.mo(x_strip_collapsed, initial_search = FALSE, dyslexia_mode = TRUE, allow_uncertain = FALSE, debug = debug, reference_data_to_use = uncertain.reference_data_to_use, actual_uncertainty = 3, actual_input = a.x_backup)))
+ }
+ if (!empty_result(found)) {
+ found_result <- found
+ uncertainties <<- rbind(uncertainties,
+ attr(found, which = "uncertainties", exact = TRUE),
+ stringsAsFactors = FALSE)
+ found <- lookup(mo == found)
+ return(found)
+ }
+ }
+ }
+
+ # (12) part of a name (very unlikely match) ----
+ if (isTRUE(debug)) {
+ cat(font_bold("\n[ UNCERTAINTY LEVEL", now_checks_for_uncertainty_level, "] (12) part of a name (very unlikely match)\n"))
+ }
+ if (isTRUE(debug)) {
+ message("Running '", f.x_withspaces_end_only, "'")
+ }
+ if (nchar(g.x_backup_without_spp) >= 6) {
+ found <- lookup(fullname_lower %like_case% f.x_withspaces_end_only, column = "mo")
+ if (!is.na(found)) {
+ found_result <- lookup(mo == found)
+ uncertainties <<- rbind(uncertainties,
+ attr(found, which = "uncertainties", exact = TRUE),
+ stringsAsFactors = FALSE)
+ found <- lookup(mo == found)
+ return(found)
+ }
+ }
+ }
+
+
+ # didn't found in uncertain results too
+ return(NA_character_)
}
-
-
- # didn't found in uncertain results too
+
+ # uncertain results
+ x[i] <- uncertain_fn(a.x_backup = a.x_backup,
+ b.x_trimmed = b.x_trimmed,
+ d.x_withspaces_start_end = d.x_withspaces_start_end,
+ e.x_withspaces_start_only = e.x_withspaces_start_only,
+ f.x_withspaces_end_only = f.x_withspaces_end_only,
+ g.x_backup_without_spp = g.x_backup_without_spp,
+ uncertain.reference_data_to_use = MO_lookup)
+ if (!empty_result(x[i])) {
+ return(x[i])
+ }
+
+ # didn't found any
return(NA_character_)
}
-
- # uncertain results
- x[i] <- uncertain_fn(a.x_backup = a.x_backup,
- b.x_trimmed = b.x_trimmed,
- d.x_withspaces_start_end = d.x_withspaces_start_end,
- e.x_withspaces_start_only = e.x_withspaces_start_only,
- f.x_withspaces_end_only = f.x_withspaces_end_only,
- g.x_backup_without_spp = g.x_backup_without_spp,
- uncertain.reference_data_to_use = MO_lookup) # MO_lookup[which(MO_lookup$prevalence %in% c(1, 2)), ])
+
+ # CHECK ALL IN ONE GO ----
+ x[i] <- check_per_prevalence(data_to_check = MO_lookup,
+ data.old_to_check = MO.old_lookup,
+ a.x_backup = x_backup[i],
+ b.x_trimmed = x_trimmed[i],
+ c.x_trimmed_without_group = x_trimmed_without_group[i],
+ d.x_withspaces_start_end = x_withspaces_start_end[i],
+ e.x_withspaces_start_only = x_withspaces_start_only[i],
+ f.x_withspaces_end_only = x_withspaces_end_only[i],
+ g.x_backup_without_spp = x_backup_without_spp[i],
+ h.x_species = x_species[i],
+ i.x_trimmed_species = x_trimmed_species[i])
if (!empty_result(x[i])) {
- return(x[i])
+ next
+ }
+
+
+ # no results found: make them UNKNOWN ----
+ x[i] <- lookup(mo == "UNKNOWN", uncertainty = -1)
+ if (initial_search == TRUE) {
+ failures <- c(failures, x_backup[i])
}
- # x[i] <- uncertain_fn(a.x_backup = a.x_backup,
- # b.x_trimmed = b.x_trimmed,
- # d.x_withspaces_start_end = d.x_withspaces_start_end,
- # e.x_withspaces_start_only = e.x_withspaces_start_only,
- # f.x_withspaces_end_only = f.x_withspaces_end_only,
- # g.x_backup_without_spp = g.x_backup_without_spp,
- # uncertain.reference_data_to_use = MO_lookup[which(MO_lookup$prevalence == 3), ])
- # if (!empty_result(x[i])) {
- # return(x[i])
- # }
-
- # didn't found any
- return(NA_character_)
}
-
- # CHECK ALL IN ONE GO ----
- x[i] <- check_per_prevalence(data_to_check = MO_lookup,
- data.old_to_check = MO.old_lookup,
- a.x_backup = x_backup[i],
- b.x_trimmed = x_trimmed[i],
- c.x_trimmed_without_group = x_trimmed_without_group[i],
- d.x_withspaces_start_end = x_withspaces_start_end[i],
- e.x_withspaces_start_only = x_withspaces_start_only[i],
- f.x_withspaces_end_only = x_withspaces_end_only[i],
- g.x_backup_without_spp = x_backup_without_spp[i],
- h.x_species = x_species[i],
- i.x_trimmed_species = x_trimmed_species[i])
- if (!empty_result(x[i])) {
- next
- }
-
-
- # no results found: make them UNKNOWN ----
- x[i] <- lookup(mo == "UNKNOWN", uncertainty = -1)
+
if (initial_search == TRUE) {
- failures <- c(failures, x_backup[i])
+ close(progress)
}
- }
-
- if (initial_search == TRUE) {
- close(progress)
+
+
+ # handling failures ----
+ failures <- failures[!failures %in% c(NA, NULL, NaN)]
+ if (length(failures) > 0 & initial_search == TRUE) {
+ pkg_env$mo_failures <- sort(unique(failures))
+ pkg_env$mo_failed <- c(pkg_env$mo_failed, pkg_env$mo_failures)
+ plural <- c("value", "it", "was")
+ if (pm_n_distinct(failures) > 1) {
+ plural <- c("values", "them", "were")
+ }
+ x_input_clean <- trimws2(x_input)
+ total_failures <- length(x_input_clean[as.character(x_input_clean) %in% as.character(failures) & !x_input %in% c(NA, NULL, NaN)])
+ total_n <- length(x_input[!x_input %in% c(NA, NULL, NaN)])
+ msg <- paste0(nr2char(pm_n_distinct(failures)), " unique ", plural[1],
+ " (covering ", percentage(total_failures / total_n),
+ ") could not be coerced and ", plural[3], " considered 'unknown'")
+ if (pm_n_distinct(failures) <= 10) {
+ msg <- paste0(msg, ": ", vector_and(failures, quotes = TRUE))
+ }
+ msg <- paste0(msg,
+ ".\nUse `mo_failures()` to review ", plural[2], ". Edit the `allow_uncertain` argument if needed (see ?as.mo).\n",
+ "You can also use your own reference data with set_mo_source() or directly, e.g.:\n",
+ ' as.mo("mycode", reference_df = data.frame(own = "mycode", mo = "', MO_lookup$mo[match("Escherichia coli", MO_lookup$fullname)], '"))\n',
+ ' mo_name("mycode", reference_df = data.frame(own = "mycode", mo = "', MO_lookup$mo[match("Escherichia coli", MO_lookup$fullname)], '"))\n')
+ warning_(paste0("\n", msg),
+ add_fn = font_red,
+ call = FALSE,
+ immediate = TRUE) # thus will always be shown, even if >= warnings
+ }
+ # handling uncertainties ----
+ if (NROW(uncertainties) > 0 & initial_search == TRUE) {
+ uncertainties <- as.list(pm_distinct(uncertainties, input, .keep_all = TRUE))
+ pkg_env$mo_uncertainties <- uncertainties
+
+ plural <- c("", "it", "was")
+ if (length(uncertainties$input) > 1) {
+ plural <- c("s", "them", "were")
+ }
+ msg <- paste0("Translation to ", nr2char(length(uncertainties$input)), " microorganism", plural[1],
+ " was guessed with uncertainty. Use mo_uncertainties() to review ", plural[2], ".")
+ message_(msg)
+ }
+ x[already_known] <- x_known
}
}
-
- # handling failures ----
- failures <- failures[!failures %in% c(NA, NULL, NaN)]
- if (length(failures) > 0 & initial_search == TRUE) {
- pkg_env$mo_failures <- sort(unique(failures))
- pkg_env$mo_failed <- c(pkg_env$mo_failed, pkg_env$mo_failures)
- plural <- c("value", "it", "was")
- if (pm_n_distinct(failures) > 1) {
- plural <- c("values", "them", "were")
- }
- x_input_clean <- trimws2(x_input)
- total_failures <- length(x_input_clean[as.character(x_input_clean) %in% as.character(failures) & !x_input %in% c(NA, NULL, NaN)])
- total_n <- length(x_input[!x_input %in% c(NA, NULL, NaN)])
- msg <- paste0(nr2char(pm_n_distinct(failures)), " unique ", plural[1],
- " (covering ", percentage(total_failures / total_n),
- ") could not be coerced and ", plural[3], " considered 'unknown'")
- if (pm_n_distinct(failures) <= 10) {
- msg <- paste0(msg, ": ", vector_and(failures, quotes = TRUE))
- }
- msg <- paste0(msg,
- ".\nUse mo_failures() to review ", plural[2], ". Edit the `allow_uncertain` argument if needed (see ?as.mo).\n",
- "You can also use your own reference data with set_mo_source() or directly, e.g.:\n",
- ' as.mo("mycode", reference_df = data.frame(own = "mycode", mo = "', MO_lookup$mo[match("Escherichia coli", MO_lookup$fullname)], '"))\n',
- ' mo_name("mycode", reference_df = data.frame(own = "mycode", mo = "', MO_lookup$mo[match("Escherichia coli", MO_lookup$fullname)], '"))\n')
- warning_(paste0("\n", msg),
- add_fn = font_red,
- call = FALSE,
- immediate = TRUE) # thus will always be shown, even if >= warnings
- }
- # handling uncertainties ----
- if (NROW(uncertainties) > 0 & initial_search == TRUE) {
- uncertainties <- as.list(pm_distinct(uncertainties, input, .keep_all = TRUE))
- pkg_env$mo_uncertainties <- uncertainties
-
- plural <- c("", "it", "was")
- if (length(uncertainties$input) > 1) {
- plural <- c("s", "them", "were")
- }
- msg <- paste0("Translation to ", nr2char(length(uncertainties$input)), " microorganism", plural[1],
- " was guessed with uncertainty. Use mo_uncertainties() to review ", plural[2], ".")
- message_(msg)
- }
-
+
# Becker ----
if (Becker == TRUE | Becker == "all") {
# warn when species found that are not in:
diff --git a/R/mo_property.R b/R/mo_property.R
index 12758d5a..b7e459aa 100755
--- a/R/mo_property.R
+++ b/R/mo_property.R
@@ -172,7 +172,10 @@ mo_name <- function(x, language = get_locale(), ...) {
meet_criteria(x, allow_NA = TRUE)
meet_criteria(language, has_length = 1, is_in = c(LANGUAGES_SUPPORTED, ""), allow_NULL = TRUE, allow_NA = TRUE)
- translate_AMR(mo_validate(x = x, property = "fullname", language = language, ...), language = language, only_unknown = FALSE)
+ translate_AMR(mo_validate(x = x, property = "fullname", language = language, ...),
+ language = language,
+ only_unknown = FALSE,
+ affect_mo_name = TRUE)
}
#' @rdname mo_property
@@ -214,7 +217,7 @@ mo_shortname <- function(x, language = get_locale(), ...) {
shortnames[is.na(x.mo)] <- NA_character_
load_mo_failures_uncertainties_renamed(metadata)
- translate_AMR(shortnames, language = language, only_unknown = FALSE)
+ translate_AMR(shortnames, language = language, only_unknown = FALSE, affect_mo_name = TRUE)
}
#' @rdname mo_property
diff --git a/R/sysdata.rda b/R/sysdata.rda
index 9dccb9eb..f9f314f8 100644
Binary files a/R/sysdata.rda and b/R/sysdata.rda differ
diff --git a/R/translate.R b/R/translate.R
index 2ad6b02f..579fa8aa 100755
--- a/R/translate.R
+++ b/R/translate.R
@@ -123,7 +123,7 @@ coerce_language_setting <- function(lang) {
}
# translate strings based on inst/translations.tsv
-translate_AMR <- function(from, language = get_locale(), only_unknown = FALSE) {
+translate_AMR <- function(from, language = get_locale(), only_unknown = FALSE, affect_mo_name = FALSE) {
if (is.null(language)) {
return(from)
@@ -146,10 +146,13 @@ translate_AMR <- function(from, language = get_locale(), only_unknown = FALSE) {
if (only_unknown == TRUE) {
df_trans <- subset(df_trans, pattern %like% "unknown")
}
+ if (affect_mo_name == TRUE) {
+ df_trans <- subset(df_trans, affect_mo_name == TRUE)
+ }
- # default case sensitive if value if 'ignore.case' is missing:
+ # default: case sensitive if value if 'ignore.case' is missing:
df_trans$ignore.case[is.na(df_trans$ignore.case)] <- FALSE
- # default not using regular expressions (fixed = TRUE) if 'fixed' is missing:
+ # default: not using regular expressions (fixed = TRUE) if 'fixed' is missing:
df_trans$fixed[is.na(df_trans$fixed)] <- TRUE
# check if text to look for is in one of the patterns
@@ -167,7 +170,8 @@ translate_AMR <- function(from, language = get_locale(), only_unknown = FALSE) {
replacement = df_trans$replacement[i],
x = from_unique_translated,
ignore.case = df_trans$ignore.case[i],
- fixed = df_trans$fixed[i]))
+ fixed = df_trans$fixed[i],
+ perl = !df_trans$fixed[i]))
# force UTF-8 for diacritics
from_unique_translated <- enc2utf8(from_unique_translated)
diff --git a/README.md b/README.md
index d4d1592f..3dd3d815 100755
--- a/README.md
+++ b/README.md
@@ -10,7 +10,7 @@
-The latest built **source package** (`AMR_x.x.x.tar.gz`) can be found in folder [/data-raw/](data-raw).
+The latest built **source package** (`AMR_latest.tar.gz`) can be found in folder [/data-raw/](data-raw).
`AMR` is a free, open-source and independent R package 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 antimicrobial resistance data analysis, that can therefore empower epidemiological analyses to continuously enable surveillance and treatment evaluation in any setting.
diff --git a/data-raw/AMR_1.5.0.9019.tar.gz b/data-raw/AMR_latest.tar.gz
similarity index 59%
rename from data-raw/AMR_1.5.0.9019.tar.gz
rename to data-raw/AMR_latest.tar.gz
index 1b685946..ee737731 100644
Binary files a/data-raw/AMR_1.5.0.9019.tar.gz and b/data-raw/AMR_latest.tar.gz differ
diff --git a/data-raw/reproduction_of_microorganisms.R b/data-raw/reproduction_of_microorganisms.R
index 7bacef5b..977fce7f 100644
--- a/data-raw/reproduction_of_microorganisms.R
+++ b/data-raw/reproduction_of_microorganisms.R
@@ -31,8 +31,9 @@
# Data retrieved from the Global Biodiversity Information Facility (GBIF):
# https://doi.org/10.15468/rffz4x
#
-# And from the Leibniz Institute: German Collection of Microorganisms and Cell Cultures (DSMZ)
-# (register first at https://bacdive.dsmz.de/api/pnu/registration/register/ and use API as done below)
+# And from the List of Prokaryotic names with Standing in Nomenclature (LPSN)
+# (register first) https://lpsn.dsmz.de/downloads
+# download the latest CSV file.
library(dplyr)
library(AMR)
diff --git a/data-raw/translations.tsv b/data-raw/translations.tsv
index d6c9ada5..30380082 100644
--- a/data-raw/translations.tsv
+++ b/data-raw/translations.tsv
@@ -1,407 +1,412 @@
-lang pattern replacement fixed ignore.case
-de Coagulase-negative Staphylococcus Koagulase-negative Staphylococcus FALSE FALSE
-de Coagulase-positive Staphylococcus Koagulase-positive Staphylococcus FALSE FALSE
-de Beta-haemolytic Streptococcus Beta-hämolytischer Streptococcus FALSE FALSE
-de unknown Gram-negatives unbekannte Gramnegativen FALSE FALSE
-de unknown Gram-positives unbekannte Grampositiven FALSE FALSE
-de unknown name unbekannte Name FALSE FALSE
-de unknown kingdom unbekanntes Reich FALSE FALSE
-de unknown phylum unbekannter Stamm FALSE FALSE
-de unknown class unbekannte Klasse FALSE FALSE
-de unknown order unbekannte Ordnung FALSE FALSE
-de unknown family unbekannte Familie FALSE FALSE
-de unknown genus unbekannte Gattung FALSE FALSE
-de unknown species unbekannte Art FALSE FALSE
-de unknown subspecies unbekannte Unterart FALSE FALSE
-de unknown rank unbekannter Rang FALSE FALSE
-de CoNS KNS TRUE FALSE
-de CoPS KPS TRUE FALSE
-de Gram-negative Gramnegativ FALSE FALSE
-de Gram-positive Grampositiv FALSE FALSE
-de Bacteria Bakterien FALSE FALSE
-de Fungi Pilze FALSE FALSE
-de Yeasts Hefen FALSE FALSE
-de Protozoa Protozoen FALSE FALSE
-de biogroup Biogruppe FALSE FALSE
-de biotype Biotyp FALSE FALSE
-de vegetative vegetativ FALSE FALSE
-de ([([ ]*?)group \\1Gruppe FALSE FALSE
-de ([([ ]*?)Group \\1Gruppe FALSE FALSE
-de no .*growth keine? .*wachstum FALSE TRUE
-de no|not keine? FALSE TRUE
-
-nl Coagulase-negative Staphylococcus Coagulase-negatieve Staphylococcus FALSE FALSE
-nl Coagulase-positive Staphylococcus Coagulase-positieve Staphylococcus FALSE FALSE
-nl Beta-haemolytic Streptococcus Beta-hemolytische Streptococcus FALSE FALSE
-nl unknown Gram-negatives onbekende Gram-negatieven FALSE FALSE
-nl unknown Gram-positives onbekende Gram-positieven FALSE FALSE
-nl unknown name onbekende naam FALSE FALSE
-nl unknown kingdom onbekend koninkrijk FALSE FALSE
-nl unknown phylum onbekend fylum FALSE FALSE
-nl unknown class onbekende klasse FALSE FALSE
-nl unknown order onbekende orde FALSE FALSE
-nl unknown family onbekende familie FALSE FALSE
-nl unknown genus onbekend geslacht FALSE FALSE
-nl unknown species onbekende soort FALSE FALSE
-nl unknown subspecies onbekende ondersoort FALSE FALSE
-nl unknown rank onbekende rang FALSE FALSE
-nl CoNS CNS TRUE FALSE
-nl CoPS CPS TRUE FALSE
-nl Gram-negative Gram-negatief FALSE FALSE
-nl Gram-positive Gram-positief FALSE FALSE
-nl Bacteria Bacteriën FALSE FALSE
-nl Fungi Schimmels FALSE FALSE
-nl Yeasts Gisten FALSE FALSE
-nl Protozoa Protozoën FALSE FALSE
-nl biogroup biogroep FALSE FALSE
-nl vegetative vegetatief FALSE FALSE
-nl ([([ ]*?)group \\1groep FALSE FALSE
-nl ([([ ]*?)Group \\1Groep FALSE FALSE
-nl antibiotic antibioticum FALSE FALSE
-nl Antibiotic Antibioticum FALSE FALSE
-nl Drug Middel FALSE FALSE
-nl drug middel FALSE FALSE
-nl no .*growth geen .*groei FALSE TRUE
-nl no|not geen|niet FALSE TRUE
-
-es Coagulase-negative Staphylococcus Staphylococcus coagulasa negativo FALSE FALSE
-es Coagulase-positive Staphylococcus Staphylococcus coagulasa positivo FALSE FALSE
-es Beta-haemolytic Streptococcus Streptococcus Beta-hemolítico FALSE FALSE
-es unknown Gram-negatives Gram negativos desconocidos FALSE FALSE
-es unknown Gram-positives Gram positivos desconocidos FALSE FALSE
-es unknown name nombre desconocido FALSE FALSE
-es unknown kingdom reino desconocido FALSE FALSE
-es unknown phylum filo desconocido FALSE FALSE
-es unknown class clase desconocida FALSE FALSE
-es unknown order orden desconocido FALSE FALSE
-es unknown family familia desconocida FALSE FALSE
-es unknown genus género desconocido FALSE FALSE
-es unknown species especie desconocida FALSE FALSE
-es unknown subspecies subespecie desconocida FALSE FALSE
-es unknown rank rango desconocido FALSE FALSE
-es CoNS SCN TRUE FALSE
-es CoPS SCP TRUE FALSE
-es Gram-negative Gram negativo FALSE FALSE
-es Gram-positive Gram positivo FALSE FALSE
-es Bacteria Bacterias FALSE FALSE
-es Fungi Hongos FALSE FALSE
-es Yeasts Levaduras FALSE FALSE
-es Protozoa Protozoarios FALSE FALSE
-es biogroup biogrupo FALSE FALSE
-es biotype biotipo FALSE FALSE
-es vegetative vegetativo FALSE FALSE
-es ([([ ]*?)group \\1grupo FALSE FALSE
-es ([([ ]*?)Group \\1Grupo FALSE FALSE
-es no .*growth no .*crecimientonon FALSE TRUE
-es no|not no|sin FALSE TRUE
-
-it Coagulase-negative Staphylococcus Staphylococcus negativo coagulasi FALSE FALSE
-it Coagulase-positive Staphylococcus Staphylococcus positivo coagulasi FALSE FALSE
-it Beta-haemolytic Streptococcus Streptococcus Beta-emolitico FALSE FALSE
-it unknown Gram-negatives Gram negativi sconosciuti FALSE FALSE
-it unknown Gram-positives Gram positivi sconosciuti FALSE FALSE
-it unknown name nome sconosciuto FALSE FALSE
-it unknown kingdom regno sconosciuto FALSE FALSE
-it unknown phylum phylum sconosciuto FALSE FALSE
-it unknown class classe sconosciuta FALSE FALSE
-it unknown order ordine sconosciuto FALSE FALSE
-it unknown family famiglia sconosciuta FALSE FALSE
-it unknown genus genere sconosciuto FALSE FALSE
-it unknown species specie sconosciute FALSE FALSE
-it unknown subspecies sottospecie sconosciute FALSE FALSE
-it unknown rank grado sconosciuto FALSE FALSE
-it Gram-negative Gram negativo FALSE FALSE
-it Gram-positive Gram positivo FALSE FALSE
-it Bacteria Batteri FALSE FALSE
-it Fungi Funghi FALSE FALSE
-it Yeasts Lieviti FALSE FALSE
-it Protozoa Protozoi FALSE FALSE
-it biogroup biogruppo FALSE FALSE
-it biotype biotipo FALSE FALSE
-it vegetative vegetativo FALSE FALSE
-it ([([ ]*?)group \\1gruppo FALSE FALSE
-it ([([ ]*?)Group \\1Gruppo FALSE FALSE
-it no .*growth sem .*crescimento FALSE TRUE
-it no|not sem FALSE TRUE
-
-fr Coagulase-negative Staphylococcus Staphylococcus à coagulase négative FALSE FALSE
-fr Coagulase-positive Staphylococcus Staphylococcus à coagulase positif FALSE FALSE
-fr Beta-haemolytic Streptococcus Streptococcus Bêta-hémolytique FALSE FALSE
-fr unknown Gram-negatives Gram négatifs inconnus FALSE FALSE
-fr unknown Gram-positives Gram positifs inconnus FALSE FALSE
-fr unknown name nom inconnu FALSE FALSE
-fr unknown kingdom règme inconnu FALSE FALSE
-fr unknown phylum embranchement inconnu FALSE FALSE
-fr unknown class classe inconnue FALSE FALSE
-fr unknown order ordre inconnu FALSE FALSE
-fr unknown family famille inconnue FALSE FALSE
-fr unknown genus genre inconnu FALSE FALSE
-fr unknown species espèce inconnue FALSE FALSE
-fr unknown subspecies sous-espèce inconnue FALSE FALSE
-fr unknown rank rang inconnu FALSE FALSE
-fr Gram-negative Gram négatif FALSE FALSE
-fr Gram-positive Gram positif FALSE FALSE
-fr Bacteria Bactéries FALSE FALSE
-fr Fungi Champignons FALSE FALSE
-fr Yeasts Levures FALSE FALSE
-fr Protozoa Protozoaires FALSE FALSE
-fr biogroup biogroupe FALSE FALSE
-fr vegetative végétatif FALSE FALSE
-fr ([([ ]*?)group \\1groupe FALSE FALSE
-fr ([([ ]*?)Group \\1Groupe FALSE FALSE
-fr no .*growth pas .*croissance FALSE TRUE
-fr no|not non FALSE TRUE
-
-pt Coagulase-negative Staphylococcus Staphylococcus coagulase negativo FALSE FALSE
-pt Coagulase-positive Staphylococcus Staphylococcus coagulase positivo FALSE FALSE
-pt Beta-haemolytic Streptococcus Streptococcus Beta-hemolítico FALSE FALSE
-pt unknown Gram-negatives Gram negativos desconhecidos FALSE FALSE
-pt unknown Gram-positives Gram positivos desconhecidos FALSE FALSE
-pt unknown name nome desconhecido FALSE FALSE
-pt unknown kingdom reino desconhecido FALSE FALSE
-pt unknown phylum filo desconhecido FALSE FALSE
-pt unknown class classe desconhecida FALSE FALSE
-pt unknown order ordem desconhecido FALSE FALSE
-pt unknown family família desconhecida FALSE FALSE
-pt unknown genus gênero desconhecido FALSE FALSE
-pt unknown species espécies desconhecida FALSE FALSE
-pt unknown subspecies subespécies desconhecida FALSE FALSE
-pt unknown rank classificação desconhecido FALSE FALSE
-pt Gram-negative Gram negativo FALSE FALSE
-pt Gram-positive Gram positivo FALSE FALSE
-pt Bacteria Bactérias FALSE FALSE
-pt Fungi Fungos FALSE FALSE
-pt Yeasts Leveduras FALSE FALSE
-pt Protozoa Protozoários FALSE FALSE
-pt biogroup biogrupo FALSE FALSE
-pt biotype biótipo FALSE FALSE
-pt vegetative vegetativo FALSE FALSE
-pt ([([ ]*?)group \\1grupo FALSE FALSE
-pt ([([ ]*?)Group \\1Grupo FALSE FALSE
-pt no .*growth sem .*crescimento FALSE TRUE
-pt no|not sem FALSE TRUE
-
-de clavulanic acid Clavulansäure FALSE TRUE
-
-nl 4-aminosalicylic acid 4-aminosalicylzuur
-nl Adefovir dipivoxil Adefovir
-nl Aldesulfone sodium Aldesulfon
-nl Amikacin Amikacine
-nl Amoxicillin Amoxicilline
-nl Amoxicillin/beta-lactamase inhibitor Amoxicilline/enzymremmer
-nl Amphotericin B Amfotericine B
-nl Ampicillin Ampicilline
-nl Ampicillin/beta-lactamase inhibitor Ampicilline/enzymremmer
-nl Anidulafungin Anidulafungine
-nl Azidocillin Azidocilline
-nl Azithromycin Azitromycine
-nl Azlocillin Azlocilline
-nl Bacampicillin Bacampicilline
-nl Bacitracin Bacitracine
-nl Benzathine benzylpenicillin Benzylpenicillinebenzathine
-nl Benzathine phenoxymethylpenicillin Fenoxymethylpenicillinebenzathine
-nl Benzylpenicillin Benzylpenicilline
-nl Calcium aminosalicylate Aminosalicylzuur
-nl Capreomycin Capreomycine
-nl Carbenicillin Carbenicilline
-nl Carindacillin Carindacilline
-nl Caspofungin Caspofungine
-nl Ce(f|ph)acetrile Cefacetril FALSE
-nl Ce(f|ph)alexin Cefalexine FALSE FALSE
-nl Ce(f|ph)alotin Cefalotine FALSE
-nl Ce(f|ph)amandole Cefamandol FALSE
-nl Ce(f|ph)apirin Cefapirine FALSE
-nl Ce(f|ph)azedone Cefazedon FALSE
-nl Ce(f|ph)azolin Cefazoline FALSE
-nl Ce(f|ph)alothin Cefalotine FALSE
-nl Ce(f|ph)alexin Cefalexine FALSE
-nl Ce(f|ph)epime Cefepim FALSE
-nl Ce(f|ph)ixime Cefixim FALSE
-nl Ce(f|ph)menoxime Cefmenoxim FALSE
-nl Ce(f|ph)metazole Cefmetazol FALSE
-nl Ce(f|ph)odizime Cefodizim FALSE
-nl Ce(f|ph)onicid Cefonicide FALSE
-nl Ce(f|ph)operazone Cefoperazon FALSE
-nl Ce(f|ph)operazone/beta-lactamase inhibitor Cefoperazon/enzymremmer FALSE
-nl Ce(f|ph)otaxime Cefotaxim FALSE
-nl Ce(f|ph)oxitin Cefoxitine FALSE
-nl Ce(f|ph)pirome Cefpirom FALSE
-nl Ce(f|ph)podoxime Cefpodoxim FALSE
-nl Ce(f|ph)radine Cefradine FALSE
-nl Ce(f|ph)sulodin Cefsulodine FALSE
-nl Ce(f|ph)tazidime Ceftazidim FALSE
-nl Ce(f|ph)tezole Ceftezol FALSE
-nl Ce(f|ph)tizoxime Ceftizoxim FALSE
-nl Ce(f|ph)triaxone Ceftriaxon FALSE
-nl Ce(f|ph)uroxime Cefuroxim FALSE
-nl Ce(f|ph)uroxime/metronidazole Cefuroxim/andere antibacteriele middelen FALSE
-nl Chloramphenicol Chlooramfenicol
-nl Chlortetracycline Chloortetracycline
-nl Cinoxacin Cinoxacine
-nl Ciprofloxacin Ciprofloxacine
-nl Clarithromycin Claritromycine
-nl Clavulanic acid Clavulaanzuur
-nl clavulanic acid clavulaanzuur
-nl Clindamycin Clindamycine
-nl Clometocillin Clometocilline
-nl Clotrimazole Clotrimazol
-nl Cloxacillin Cloxacilline
-nl Colistin Colistine
-nl Dapsone Dapson
-nl Daptomycin Daptomycine
-nl Dibekacin Dibekacine
-nl Dicloxacillin Dicloxacilline
-nl Dirithromycin Diritromycine
-nl Econazole Econazol
-nl Enoxacin Enoxacine
-nl Epicillin Epicilline
-nl Erythromycin Erytromycine
-nl Ethambutol/isoniazid Ethambutol/isoniazide
-nl Fleroxacin Fleroxacine
-nl Flucloxacillin Flucloxacilline
-nl Fluconazole Fluconazol
-nl Flucytosine Fluorocytosine
-nl Flurithromycin Fluritromycine
-nl Fosfomycin Fosfomycine
-nl Fusidic acid Fusidinezuur
-nl Gatifloxacin Gatifloxacine
-nl Gemifloxacin Gemifloxacine
-nl Gentamicin Gentamicine
-nl Grepafloxacin Grepafloxacine
-nl Hachimycin Hachimycine
-nl Hetacillin Hetacilline
-nl Imipenem/cilastatin Imipenem/enzymremmer
-nl Inosine pranobex Inosiplex
-nl Isepamicin Isepamicine
-nl Isoconazole Isoconazol
-nl Isoniazid Isoniazide
-nl Itraconazole Itraconazol
-nl Josamycin Josamycine
-nl Kanamycin Kanamycine
-nl Ketoconazole Ketoconazol
-nl Levofloxacin Levofloxacine
-nl Lincomycin Lincomycine
-nl Lomefloxacin Lomefloxacine
-nl Lysozyme Lysozym
-nl Mandelic acid Amandelzuur
-nl Metampicillin Metampicilline
-nl Meticillin Meticilline
-nl Metisazone Metisazon
-nl Metronidazole Metronidazol
-nl Mezlocillin Mezlocilline
-nl Micafungin Micafungine
-nl Miconazole Miconazol
-nl Midecamycin Midecamycine
-nl Miocamycin Miocamycine
-nl Moxifloxacin Moxifloxacine
-nl Mupirocin Mupirocine
-nl Nalidixic acid Nalidixinezuur
-nl Neomycin Neomycine
-nl Netilmicin Netilmicine
-nl Nitrofurantoin Nitrofurantoine
-nl Norfloxacin Norfloxacine
-nl Novobiocin Novobiocine
-nl Nystatin Nystatine
-nl Ofloxacin Ofloxacine
-nl Oleandomycin Oleandomycine
-nl Ornidazole Ornidazol
-nl Oxacillin Oxacilline
-nl Oxolinic acid Oxolinezuur
-nl Oxytetracycline Oxytetracycline
-nl Pazufloxacin Pazufloxacine
-nl Pefloxacin Pefloxacine
-nl Penamecillin Penamecilline
-nl Penicillin Penicilline
-nl Pheneticillin Feneticilline
-nl Phenoxymethylpenicillin Fenoxymethylpenicilline
-nl Pipemidic acid Pipemidinezuur
-nl Piperacillin Piperacilline
-nl Piperacillin/beta-lactamase inhibitor Piperacilline/enzymremmer
-nl Piromidic acid Piromidinezuur
-nl Pivampicillin Pivampicilline
-nl Polymyxin B Polymyxine B
-nl Posaconazole Posaconazol
-nl Pristinamycin Pristinamycine
-nl Procaine benzylpenicillin Benzylpenicillineprocaine
-nl Propicillin Propicilline
-nl Prulifloxacin Prulifloxacine
-nl Quinupristin/dalfopristin Quinupristine/dalfopristine
-nl Ribostamycin Ribostamycine
-nl Rifabutin Rifabutine
-nl Rifampicin Rifampicine
-nl Rifampicin/pyrazinamide/ethambutol/isoniazid Rifampicine/pyrazinamide/ethambutol/isoniazide
-nl Rifampicin/pyrazinamide/isoniazid Rifampicine/pyrazinamide/isoniazide
-nl Rifampicin/isoniazid Rifampicine/isoniazide
-nl Rifamycin Rifamycine
-nl Rifaximin Rifaximine
-nl Rokitamycin Rokitamycine
-nl Rosoxacin Rosoxacine
-nl Roxithromycin Roxitromycine
-nl Rufloxacin Rufloxacine
-nl Sisomicin Sisomicine
-nl Sodium aminosalicylate Aminosalicylzuur
-nl Sparfloxacin Sparfloxacine
-nl Spectinomycin Spectinomycine
-nl Spiramycin Spiramycine
-nl Spiramycin/metronidazole Spiramycine/metronidazol
-nl Staphylococcus immunoglobulin Stafylokokkenimmunoglobuline
-nl Streptoduocin Streptoduocine
-nl Streptomycin Streptomycine
-nl Streptomycin/isoniazid Streptomycine/isoniazide
-nl Sulbenicillin Sulbenicilline
-nl Sulfadiazine/tetroxoprim Sulfadiazine/tetroxoprim
-nl Sulfadiazine/trimethoprim Sulfadiazine/trimethoprim
-nl Sulfadimidine/trimethoprim Sulfadimidine/trimethoprim
-nl Sulfafurazole Sulfafurazol
-nl Sulfaisodimidine Sulfisomidine
-nl Sulfalene Sulfaleen
-nl Sulfamazone Sulfamazon
-nl Sulfamerazine/trimethoprim Sulfamerazine/trimethoprim
-nl Sulfamethizole Sulfamethizol
-nl Sulfamethoxazole Sulfamethoxazol
-nl Sulfamethoxazole/trimethoprim Sulfamethoxazol/trimethoprim
-nl Sulfametoxydiazine Sulfamethoxydiazine
-nl Sulfametrole/trimethoprim Sulfametrol/trimethoprim
-nl Sulfamoxole Sulfamoxol
-nl Sulfamoxole/trimethoprim Sulfamoxol/trimethoprim
-nl Sulfaperin Sulfaperine
-nl Sulfaphenazole Sulfafenazol
-nl Sulfathiazole Sulfathiazol
-nl Sulfathiourea Sulfathioureum
-nl Sultamicillin Sultamicilline
-nl Talampicillin Talampicilline
-nl Teicoplanin Teicoplanine
-nl Telithromycin Telitromycine
-nl Temafloxacin Temafloxacine
-nl Temocillin Temocilline
-nl Tenofovir disoproxil Tenofovir
-nl Terizidone Terizidon
-nl Thiamphenicol Thiamfenicol
-nl Thioacetazone/isoniazid Thioacetazon/isoniazide
-nl Ticarcillin Ticarcilline
-nl Ticarcillin/beta-lactamase inhibitor Ticarcilline/enzymremmer
-nl Ticarcillin/clavulanic acid Ticarcilline/clavulaanzuur
-nl Tinidazole Tinidazol
-nl Tobramycin Tobramycine
-nl Trimethoprim/sulfamethoxazole Cotrimoxazol
-nl Troleandomycin Troleandomycine
-nl Trovafloxacin Trovafloxacine
-nl Vancomycin Vancomycine
-nl Voriconazole Voriconazol
-nl Aminoglycosides Aminoglycosiden TRUE FALSE
-nl Amphenicols Amfenicolen TRUE FALSE
-nl Antifungals/antimycotics Antifungica/antimycotica TRUE FALSE
-nl Antimycobacterials Antimycobacteriele middelen TRUE FALSE
-nl Beta-lactams/penicillins Beta-lactams/penicillines TRUE FALSE
-nl Cephalosporins (1st gen.) Cefalosporines (1e gen.) TRUE FALSE
-nl Cephalosporins (2nd gen.) Cefalosporines (2e gen.) TRUE FALSE
-nl Cephalosporins (3rd gen.) Cefalosporines (3e gen.) TRUE FALSE
-nl Cephalosporins (4th gen.) Cefalosporines (4e gen.) TRUE FALSE
-nl Cephalosporins (5th gen.) Cefalosporines (5e gen.) TRUE FALSE
-nl Cephalosporins (unclassified gen.) Cefalosporines (ongeclassificeerd) TRUE FALSE
-nl Cephalosporins Cefalosporines TRUE FALSE
-nl Glycopeptides Glycopeptiden TRUE FALSE
-nl Macrolides/lincosamides Macroliden/lincosamiden TRUE FALSE
-nl Other antibacterials Overige antibiotica TRUE FALSE
-nl Polymyxins Polymyxines TRUE FALSE
-nl Quinolones Quinolonen TRUE FALSE
+lang pattern replacement fixed ignore.case affect_mo_name
+de Coagulase-negative Staphylococcus Koagulase-negative Staphylococcus FALSE FALSE TRUE
+de Coagulase-positive Staphylococcus Koagulase-positive Staphylococcus FALSE FALSE TRUE
+de Beta-haemolytic Streptococcus Beta-hämolytischer Streptococcus FALSE FALSE TRUE
+de unknown Gram-negatives unbekannte Gramnegativen FALSE FALSE TRUE
+de unknown Gram-positives unbekannte Grampositiven FALSE FALSE TRUE
+de unknown fungus unbekannter Pilze FALSE FALSE TRUE
+de unknown yeast unbekannte Hefe FALSE FALSE TRUE
+de unknown name unbekannte Name FALSE FALSE TRUE
+de unknown kingdom unbekanntes Reich FALSE FALSE TRUE
+de unknown phylum unbekannter Stamm FALSE FALSE TRUE
+de unknown class unbekannte Klasse FALSE FALSE TRUE
+de unknown order unbekannte Ordnung FALSE FALSE TRUE
+de unknown family unbekannte Familie FALSE FALSE TRUE
+de unknown genus unbekannte Gattung FALSE FALSE TRUE
+de unknown species unbekannte Art FALSE FALSE TRUE
+de unknown subspecies unbekannte Unterart FALSE FALSE TRUE
+de unknown rank unbekannter Rang FALSE FALSE TRUE
+de CoNS KNS TRUE FALSE TRUE
+de CoPS KPS TRUE FALSE TRUE
+de Gram-negative Gramnegativ FALSE FALSE FALSE
+de Gram-positive Grampositiv FALSE FALSE FALSE
+de ^Bacteria$ Bakterien FALSE FALSE FALSE
+de ^Fungi$ Pilze FALSE FALSE FALSE
+de ^Yeasts$ Hefen FALSE FALSE FALSE
+de ^Protozoa$ Protozoen FALSE FALSE FALSE
+de biogroup Biogruppe FALSE FALSE FALSE
+de biotype Biotyp FALSE FALSE FALSE
+de vegetative vegetativ FALSE FALSE FALSE
+de ([([ ]*?)group \\1Gruppe FALSE FALSE FALSE
+de ([([ ]*?)Group \\1Gruppe FALSE FALSE FALSE
+de no .*growth keine? .*wachstum FALSE TRUE FALSE
+de (^| )no|not keine? FALSE TRUE FALSE
+nl Coagulase-negative Staphylococcus Coagulase-negatieve Staphylococcus FALSE FALSE TRUE
+nl Coagulase-positive Staphylococcus Coagulase-positieve Staphylococcus FALSE FALSE TRUE
+nl Beta-haemolytic Streptococcus Beta-hemolytische Streptococcus FALSE FALSE TRUE
+nl unknown Gram-negatives onbekende Gram-negatieven FALSE FALSE TRUE
+nl unknown Gram-positives onbekende Gram-positieven FALSE FALSE TRUE
+nl unknown fungus onbekende schimmel FALSE FALSE TRUE
+nl unknown yeast onbekende gist FALSE FALSE TRUE
+nl unknown name onbekende naam FALSE FALSE TRUE
+nl unknown kingdom onbekend koninkrijk FALSE FALSE TRUE
+nl unknown phylum onbekend fylum FALSE FALSE TRUE
+nl unknown class onbekende klasse FALSE FALSE TRUE
+nl unknown order onbekende orde FALSE FALSE TRUE
+nl unknown family onbekende familie FALSE FALSE TRUE
+nl unknown genus onbekend geslacht FALSE FALSE TRUE
+nl unknown species onbekende soort FALSE FALSE TRUE
+nl unknown subspecies onbekende ondersoort FALSE FALSE TRUE
+nl unknown rank onbekende rang FALSE FALSE TRUE
+nl CoNS CNS TRUE FALSE TRUE
+nl CoPS CPS TRUE FALSE TRUE
+nl Gram-negative Gram-negatief FALSE FALSE FALSE
+nl Gram-positive Gram-positief FALSE FALSE FALSE
+nl ^Bacteria$ Bacteriën FALSE FALSE FALSE
+nl ^Fungi$ Schimmels FALSE FALSE FALSE
+nl ^Yeasts$ Gisten FALSE FALSE FALSE
+nl ^Protozoa$ Protozoën FALSE FALSE FALSE
+nl biogroup biogroep FALSE FALSE FALSE
+nl vegetative vegetatief FALSE FALSE FALSE
+nl ([([ ]*?)group \\1groep FALSE FALSE FALSE
+nl ([([ ]*?)Group \\1Groep FALSE FALSE FALSE
+nl antibiotic antibioticum FALSE FALSE FALSE
+nl Antibiotic Antibioticum FALSE FALSE FALSE
+nl Drug Middel FALSE FALSE FALSE
+nl drug middel FALSE FALSE FALSE
+nl no .*growth geen .*groei FALSE TRUE FALSE
+nl no|not geen|niet FALSE TRUE FALSE
+es Coagulase-negative Staphylococcus Staphylococcus coagulasa negativo FALSE FALSE TRUE
+es Coagulase-positive Staphylococcus Staphylococcus coagulasa positivo FALSE FALSE TRUE
+es Beta-haemolytic Streptococcus Streptococcus Beta-hemolítico FALSE FALSE TRUE
+es unknown Gram-negatives Gram negativos desconocidos FALSE FALSE TRUE
+es unknown Gram-positives Gram positivos desconocidos FALSE FALSE TRUE
+es unknown fungus hongo desconocido FALSE FALSE TRUE
+es unknown yeast levadura desconocida FALSE FALSE TRUE
+es unknown name nombre desconocido FALSE FALSE TRUE
+es unknown kingdom reino desconocido FALSE FALSE TRUE
+es unknown phylum filo desconocido FALSE FALSE TRUE
+es unknown class clase desconocida FALSE FALSE TRUE
+es unknown order orden desconocido FALSE FALSE TRUE
+es unknown family familia desconocida FALSE FALSE TRUE
+es unknown genus género desconocido FALSE FALSE TRUE
+es unknown species especie desconocida FALSE FALSE TRUE
+es unknown subspecies subespecie desconocida FALSE FALSE TRUE
+es unknown rank rango desconocido FALSE FALSE TRUE
+es CoNS SCN TRUE FALSE TRUE
+es CoPS SCP TRUE FALSE TRUE
+es Gram-negative Gram negativo FALSE FALSE FALSE
+es Gram-positive Gram positivo FALSE FALSE FALSE
+es ^Bacteria$ Bacterias FALSE FALSE FALSE
+es ^Fungi$ Hongos FALSE FALSE FALSE
+es ^Yeasts$ Levaduras FALSE FALSE FALSE
+es ^Protozoa$ Protozoarios FALSE FALSE FALSE
+es biogroup biogrupo FALSE FALSE FALSE
+es biotype biotipo FALSE FALSE FALSE
+es vegetative vegetativo FALSE FALSE FALSE
+es ([([ ]*?)group \\1grupo FALSE FALSE FALSE
+es ([([ ]*?)Group \\1Grupo FALSE FALSE FALSE
+es no .*growth no .*crecimientonon FALSE TRUE FALSE
+es no|not no|sin FALSE TRUE FALSE
+it Coagulase-negative Staphylococcus Staphylococcus negativo coagulasi FALSE FALSE TRUE
+it Coagulase-positive Staphylococcus Staphylococcus positivo coagulasi FALSE FALSE TRUE
+it Beta-haemolytic Streptococcus Streptococcus Beta-emolitico FALSE FALSE TRUE
+it unknown Gram-negatives Gram negativi sconosciuti FALSE FALSE TRUE
+it unknown Gram-positives Gram positivi sconosciuti FALSE FALSE TRUE
+it unknown fungus fungo sconosciuto FALSE FALSE TRUE
+it unknown yeast lievito sconosciuto FALSE FALSE TRUE
+it unknown name nome sconosciuto FALSE FALSE TRUE
+it unknown kingdom regno sconosciuto FALSE FALSE TRUE
+it unknown phylum phylum sconosciuto FALSE FALSE TRUE
+it unknown class classe sconosciuta FALSE FALSE TRUE
+it unknown order ordine sconosciuto FALSE FALSE TRUE
+it unknown family famiglia sconosciuta FALSE FALSE TRUE
+it unknown genus genere sconosciuto FALSE FALSE TRUE
+it unknown species specie sconosciute FALSE FALSE TRUE
+it unknown subspecies sottospecie sconosciute FALSE FALSE TRUE
+it unknown rank grado sconosciuto FALSE FALSE TRUE
+it Gram-negative Gram negativo FALSE FALSE FALSE
+it Gram-positive Gram positivo FALSE FALSE FALSE
+it ^Bacteria$ Batteri FALSE FALSE FALSE
+it ^Fungi$ Funghi FALSE FALSE FALSE
+it ^Yeasts$ Lieviti FALSE FALSE FALSE
+it ^Protozoa$ Protozoi FALSE FALSE FALSE
+it biogroup biogruppo FALSE FALSE FALSE
+it biotype biotipo FALSE FALSE FALSE
+it vegetative vegetativo FALSE FALSE FALSE
+it ([([ ]*?)group \\1gruppo FALSE FALSE FALSE
+it ([([ ]*?)Group \\1Gruppo FALSE FALSE FALSE
+it no .*growth sem .*crescimento FALSE TRUE FALSE
+it no|not sem FALSE TRUE FALSE
+fr Coagulase-negative Staphylococcus Staphylococcus à coagulase négative FALSE FALSE TRUE
+fr Coagulase-positive Staphylococcus Staphylococcus à coagulase positif FALSE FALSE TRUE
+fr Beta-haemolytic Streptococcus Streptococcus Bêta-hémolytique FALSE FALSE TRUE
+fr unknown Gram-negatives Gram négatifs inconnus FALSE FALSE TRUE
+fr unknown Gram-positives Gram positifs inconnus FALSE FALSE TRUE
+fr unknown fungus champignon inconnu FALSE FALSE TRUE
+fr unknown yeast levure inconnue FALSE FALSE TRUE
+fr unknown name nom inconnu FALSE FALSE TRUE
+fr unknown kingdom règme inconnu FALSE FALSE TRUE
+fr unknown phylum embranchement inconnu FALSE FALSE TRUE
+fr unknown class classe inconnue FALSE FALSE TRUE
+fr unknown order ordre inconnu FALSE FALSE TRUE
+fr unknown family famille inconnue FALSE FALSE TRUE
+fr unknown genus genre inconnu FALSE FALSE TRUE
+fr unknown species espèce inconnue FALSE FALSE TRUE
+fr unknown subspecies sous-espèce inconnue FALSE FALSE TRUE
+fr unknown rank rang inconnu FALSE FALSE TRUE
+fr Gram-negative Gram négatif FALSE FALSE FALSE
+fr Gram-positive Gram positif FALSE FALSE FALSE
+fr ^Bacteria$ Bactéries FALSE FALSE FALSE
+fr ^Fungi$ Champignons FALSE FALSE FALSE
+fr ^Yeasts$ Levures FALSE FALSE FALSE
+fr ^Protozoa$ Protozoaires FALSE FALSE FALSE
+fr biogroup biogroupe FALSE FALSE FALSE
+fr vegetative végétatif FALSE FALSE FALSE
+fr ([([ ]*?)group \\1groupe FALSE FALSE FALSE
+fr ([([ ]*?)Group \\1Groupe FALSE FALSE FALSE
+fr no .*growth pas .*croissance FALSE TRUE FALSE
+fr no|not non FALSE TRUE FALSE
+pt Coagulase-negative Staphylococcus Staphylococcus coagulase negativo FALSE FALSE TRUE
+pt Coagulase-positive Staphylococcus Staphylococcus coagulase positivo FALSE FALSE TRUE
+pt Beta-haemolytic Streptococcus Streptococcus Beta-hemolítico FALSE FALSE TRUE
+pt unknown Gram-negatives Gram negativos desconhecidos FALSE FALSE TRUE
+pt unknown Gram-positives Gram positivos desconhecidos FALSE FALSE TRUE
+pt unknown fungus fungo desconhecido FALSE FALSE TRUE
+pt unknown yeast levedura desconhecida FALSE FALSE TRUE
+pt unknown name nome desconhecido FALSE FALSE TRUE
+pt unknown kingdom reino desconhecido FALSE FALSE TRUE
+pt unknown phylum filo desconhecido FALSE FALSE TRUE
+pt unknown class classe desconhecida FALSE FALSE TRUE
+pt unknown order ordem desconhecido FALSE FALSE TRUE
+pt unknown family família desconhecida FALSE FALSE TRUE
+pt unknown genus gênero desconhecido FALSE FALSE TRUE
+pt unknown species espécies desconhecida FALSE FALSE TRUE
+pt unknown subspecies subespécies desconhecida FALSE FALSE TRUE
+pt unknown rank classificação desconhecido FALSE FALSE TRUE
+pt Gram-negative Gram negativo FALSE FALSE FALSE
+pt Gram-positive Gram positivo FALSE FALSE FALSE
+pt ^Bacteria$ Bactérias FALSE FALSE FALSE
+pt ^Fungi$ Fungos FALSE FALSE FALSE
+pt ^Yeasts$ Leveduras FALSE FALSE FALSE
+pt ^Protozoa$ Protozoários FALSE FALSE FALSE
+pt biogroup biogrupo FALSE FALSE FALSE
+pt biotype biótipo FALSE FALSE FALSE
+pt vegetative vegetativo FALSE FALSE FALSE
+pt ([([ ]*?)group \\1grupo FALSE FALSE FALSE
+pt ([([ ]*?)Group \\1Grupo FALSE FALSE FALSE
+pt no .*growth sem .*crescimento FALSE TRUE FALSE
+pt no|not sem FALSE TRUE FALSE
+de clavulanic acid Clavulansäure FALSE TRUE FALSE
+nl 4-aminosalicylic acid 4-aminosalicylzuur TRUE FALSE FALSE
+nl Adefovir dipivoxil Adefovir TRUE FALSE FALSE
+nl Aldesulfone sodium Aldesulfon TRUE FALSE FALSE
+nl Amikacin Amikacine TRUE FALSE FALSE
+nl Amoxicillin Amoxicilline TRUE FALSE FALSE
+nl Amoxicillin/beta-lactamase inhibitor Amoxicilline/enzymremmer TRUE FALSE FALSE
+nl Amphotericin B Amfotericine B TRUE FALSE FALSE
+nl Ampicillin Ampicilline TRUE FALSE FALSE
+nl Ampicillin/beta-lactamase inhibitor Ampicilline/enzymremmer TRUE FALSE FALSE
+nl Anidulafungin Anidulafungine TRUE FALSE FALSE
+nl Azidocillin Azidocilline TRUE FALSE FALSE
+nl Azithromycin Azitromycine TRUE FALSE FALSE
+nl Azlocillin Azlocilline TRUE FALSE FALSE
+nl Bacampicillin Bacampicilline TRUE FALSE FALSE
+nl Bacitracin Bacitracine TRUE FALSE FALSE
+nl Benzathine benzylpenicillin Benzylpenicillinebenzathine TRUE FALSE FALSE
+nl Benzathine phenoxymethylpenicillin Fenoxymethylpenicillinebenzathine TRUE FALSE FALSE
+nl Benzylpenicillin Benzylpenicilline TRUE FALSE FALSE
+nl Calcium aminosalicylate Aminosalicylzuur TRUE FALSE FALSE
+nl Capreomycin Capreomycine TRUE FALSE FALSE
+nl Carbenicillin Carbenicilline TRUE FALSE FALSE
+nl Carindacillin Carindacilline TRUE FALSE FALSE
+nl Caspofungin Caspofungine TRUE FALSE FALSE
+nl Ce(f|ph)acetrile Cefacetril FALSE FALSE FALSE
+nl Ce(f|ph)alexin Cefalexine FALSE FALSE FALSE
+nl Ce(f|ph)alotin Cefalotine FALSE FALSE FALSE
+nl Ce(f|ph)amandole Cefamandol FALSE FALSE FALSE
+nl Ce(f|ph)apirin Cefapirine FALSE FALSE FALSE
+nl Ce(f|ph)azedone Cefazedon FALSE FALSE FALSE
+nl Ce(f|ph)azolin Cefazoline FALSE FALSE FALSE
+nl Ce(f|ph)alothin Cefalotine FALSE FALSE FALSE
+nl Ce(f|ph)alexin Cefalexine FALSE FALSE FALSE
+nl Ce(f|ph)epime Cefepim FALSE FALSE FALSE
+nl Ce(f|ph)ixime Cefixim FALSE FALSE FALSE
+nl Ce(f|ph)menoxime Cefmenoxim FALSE FALSE FALSE
+nl Ce(f|ph)metazole Cefmetazol FALSE FALSE FALSE
+nl Ce(f|ph)odizime Cefodizim FALSE FALSE FALSE
+nl Ce(f|ph)onicid Cefonicide FALSE FALSE FALSE
+nl Ce(f|ph)operazone Cefoperazon FALSE FALSE FALSE
+nl Ce(f|ph)operazone/beta-lactamase inhibitor Cefoperazon/enzymremmer FALSE FALSE FALSE
+nl Ce(f|ph)otaxime Cefotaxim FALSE FALSE FALSE
+nl Ce(f|ph)oxitin Cefoxitine FALSE FALSE FALSE
+nl Ce(f|ph)pirome Cefpirom FALSE FALSE FALSE
+nl Ce(f|ph)podoxime Cefpodoxim FALSE FALSE FALSE
+nl Ce(f|ph)radine Cefradine FALSE FALSE FALSE
+nl Ce(f|ph)sulodin Cefsulodine FALSE FALSE FALSE
+nl Ce(f|ph)tazidime Ceftazidim FALSE FALSE FALSE
+nl Ce(f|ph)tezole Ceftezol FALSE FALSE FALSE
+nl Ce(f|ph)tizoxime Ceftizoxim FALSE FALSE FALSE
+nl Ce(f|ph)triaxone Ceftriaxon FALSE FALSE FALSE
+nl Ce(f|ph)uroxime Cefuroxim FALSE FALSE FALSE
+nl Ce(f|ph)uroxime/metronidazole Cefuroxim/andere antibacteriele middelen FALSE FALSE FALSE
+nl Chloramphenicol Chlooramfenicol TRUE FALSE FALSE
+nl Chlortetracycline Chloortetracycline TRUE FALSE FALSE
+nl Cinoxacin Cinoxacine TRUE FALSE FALSE
+nl Ciprofloxacin Ciprofloxacine TRUE FALSE FALSE
+nl Clarithromycin Claritromycine TRUE FALSE FALSE
+nl Clavulanic acid Clavulaanzuur TRUE FALSE FALSE
+nl clavulanic acid clavulaanzuur TRUE FALSE FALSE
+nl Clindamycin Clindamycine TRUE FALSE FALSE
+nl Clometocillin Clometocilline TRUE FALSE FALSE
+nl Clotrimazole Clotrimazol TRUE FALSE FALSE
+nl Cloxacillin Cloxacilline TRUE FALSE FALSE
+nl Colistin Colistine TRUE FALSE FALSE
+nl Dapsone Dapson TRUE FALSE FALSE
+nl Daptomycin Daptomycine TRUE FALSE FALSE
+nl Dibekacin Dibekacine TRUE FALSE FALSE
+nl Dicloxacillin Dicloxacilline TRUE FALSE FALSE
+nl Dirithromycin Diritromycine TRUE FALSE FALSE
+nl Econazole Econazol TRUE FALSE FALSE
+nl Enoxacin Enoxacine TRUE FALSE FALSE
+nl Epicillin Epicilline TRUE FALSE FALSE
+nl Erythromycin Erytromycine TRUE FALSE FALSE
+nl Ethambutol/isoniazid Ethambutol/isoniazide TRUE FALSE FALSE
+nl Fleroxacin Fleroxacine TRUE FALSE FALSE
+nl Flucloxacillin Flucloxacilline TRUE FALSE FALSE
+nl Fluconazole Fluconazol TRUE FALSE FALSE
+nl Flucytosine Fluorocytosine TRUE FALSE FALSE
+nl Flurithromycin Fluritromycine TRUE FALSE FALSE
+nl Fosfomycin Fosfomycine TRUE FALSE FALSE
+nl Fusidic acid Fusidinezuur TRUE FALSE FALSE
+nl Gatifloxacin Gatifloxacine TRUE FALSE FALSE
+nl Gemifloxacin Gemifloxacine TRUE FALSE FALSE
+nl Gentamicin Gentamicine TRUE FALSE FALSE
+nl Grepafloxacin Grepafloxacine TRUE FALSE FALSE
+nl Hachimycin Hachimycine TRUE FALSE FALSE
+nl Hetacillin Hetacilline TRUE FALSE FALSE
+nl Imipenem/cilastatin Imipenem/enzymremmer TRUE FALSE FALSE
+nl Inosine pranobex Inosiplex TRUE FALSE FALSE
+nl Isepamicin Isepamicine TRUE FALSE FALSE
+nl Isoconazole Isoconazol TRUE FALSE FALSE
+nl Isoniazid Isoniazide TRUE FALSE FALSE
+nl Itraconazole Itraconazol TRUE FALSE FALSE
+nl Josamycin Josamycine TRUE FALSE FALSE
+nl Kanamycin Kanamycine TRUE FALSE FALSE
+nl Ketoconazole Ketoconazol TRUE FALSE FALSE
+nl Levofloxacin Levofloxacine TRUE FALSE FALSE
+nl Lincomycin Lincomycine TRUE FALSE FALSE
+nl Lomefloxacin Lomefloxacine TRUE FALSE FALSE
+nl Lysozyme Lysozym TRUE FALSE FALSE
+nl Mandelic acid Amandelzuur TRUE FALSE FALSE
+nl Metampicillin Metampicilline TRUE FALSE FALSE
+nl Meticillin Meticilline TRUE FALSE FALSE
+nl Metisazone Metisazon TRUE FALSE FALSE
+nl Metronidazole Metronidazol TRUE FALSE FALSE
+nl Mezlocillin Mezlocilline TRUE FALSE FALSE
+nl Micafungin Micafungine TRUE FALSE FALSE
+nl Miconazole Miconazol TRUE FALSE FALSE
+nl Midecamycin Midecamycine TRUE FALSE FALSE
+nl Miocamycin Miocamycine TRUE FALSE FALSE
+nl Moxifloxacin Moxifloxacine TRUE FALSE FALSE
+nl Mupirocin Mupirocine TRUE FALSE FALSE
+nl Nalidixic acid Nalidixinezuur TRUE FALSE FALSE
+nl Neomycin Neomycine TRUE FALSE FALSE
+nl Netilmicin Netilmicine TRUE FALSE FALSE
+nl Nitrofurantoin Nitrofurantoine TRUE FALSE FALSE
+nl Norfloxacin Norfloxacine TRUE FALSE FALSE
+nl Novobiocin Novobiocine TRUE FALSE FALSE
+nl Nystatin Nystatine TRUE FALSE FALSE
+nl Ofloxacin Ofloxacine TRUE FALSE FALSE
+nl Oleandomycin Oleandomycine TRUE FALSE FALSE
+nl Ornidazole Ornidazol TRUE FALSE FALSE
+nl Oxacillin Oxacilline TRUE FALSE FALSE
+nl Oxolinic acid Oxolinezuur TRUE FALSE FALSE
+nl Oxytetracycline Oxytetracycline TRUE FALSE FALSE
+nl Pazufloxacin Pazufloxacine TRUE FALSE FALSE
+nl Pefloxacin Pefloxacine TRUE FALSE FALSE
+nl Penamecillin Penamecilline TRUE FALSE FALSE
+nl Penicillin Penicilline TRUE FALSE FALSE
+nl Pheneticillin Feneticilline TRUE FALSE FALSE
+nl Phenoxymethylpenicillin Fenoxymethylpenicilline TRUE FALSE FALSE
+nl Pipemidic acid Pipemidinezuur TRUE FALSE FALSE
+nl Piperacillin Piperacilline TRUE FALSE FALSE
+nl Piperacillin/beta-lactamase inhibitor Piperacilline/enzymremmer TRUE FALSE FALSE
+nl Piromidic acid Piromidinezuur TRUE FALSE FALSE
+nl Pivampicillin Pivampicilline TRUE FALSE FALSE
+nl Polymyxin B Polymyxine B TRUE FALSE FALSE
+nl Posaconazole Posaconazol TRUE FALSE FALSE
+nl Pristinamycin Pristinamycine TRUE FALSE FALSE
+nl Procaine benzylpenicillin Benzylpenicillineprocaine TRUE FALSE FALSE
+nl Propicillin Propicilline TRUE FALSE FALSE
+nl Prulifloxacin Prulifloxacine TRUE FALSE FALSE
+nl Quinupristin/dalfopristin Quinupristine/dalfopristine TRUE FALSE FALSE
+nl Ribostamycin Ribostamycine TRUE FALSE FALSE
+nl Rifabutin Rifabutine TRUE FALSE FALSE
+nl Rifampicin Rifampicine TRUE FALSE FALSE
+nl Rifampicin/pyrazinamide/ethambutol/isoniazid Rifampicine/pyrazinamide/ethambutol/isoniazide TRUE FALSE FALSE
+nl Rifampicin/pyrazinamide/isoniazid Rifampicine/pyrazinamide/isoniazide TRUE FALSE FALSE
+nl Rifampicin/isoniazid Rifampicine/isoniazide TRUE FALSE FALSE
+nl Rifamycin Rifamycine TRUE FALSE FALSE
+nl Rifaximin Rifaximine TRUE FALSE FALSE
+nl Rokitamycin Rokitamycine TRUE FALSE FALSE
+nl Rosoxacin Rosoxacine TRUE FALSE FALSE
+nl Roxithromycin Roxitromycine TRUE FALSE FALSE
+nl Rufloxacin Rufloxacine TRUE FALSE FALSE
+nl Sisomicin Sisomicine TRUE FALSE FALSE
+nl Sodium aminosalicylate Aminosalicylzuur TRUE FALSE FALSE
+nl Sparfloxacin Sparfloxacine TRUE FALSE FALSE
+nl Spectinomycin Spectinomycine TRUE FALSE FALSE
+nl Spiramycin Spiramycine TRUE FALSE FALSE
+nl Spiramycin/metronidazole Spiramycine/metronidazol TRUE FALSE FALSE
+nl Staphylococcus immunoglobulin Stafylokokkenimmunoglobuline TRUE FALSE FALSE
+nl Streptoduocin Streptoduocine TRUE FALSE FALSE
+nl Streptomycin Streptomycine TRUE FALSE FALSE
+nl Streptomycin/isoniazid Streptomycine/isoniazide TRUE FALSE FALSE
+nl Sulbenicillin Sulbenicilline TRUE FALSE FALSE
+nl Sulfadiazine/tetroxoprim Sulfadiazine/tetroxoprim TRUE FALSE FALSE
+nl Sulfadiazine/trimethoprim Sulfadiazine/trimethoprim TRUE FALSE FALSE
+nl Sulfadimidine/trimethoprim Sulfadimidine/trimethoprim TRUE FALSE FALSE
+nl Sulfafurazole Sulfafurazol TRUE FALSE FALSE
+nl Sulfaisodimidine Sulfisomidine TRUE FALSE FALSE
+nl Sulfalene Sulfaleen TRUE FALSE FALSE
+nl Sulfamazone Sulfamazon TRUE FALSE FALSE
+nl Sulfamerazine/trimethoprim Sulfamerazine/trimethoprim TRUE FALSE FALSE
+nl Sulfamethizole Sulfamethizol TRUE FALSE FALSE
+nl Sulfamethoxazole Sulfamethoxazol TRUE FALSE FALSE
+nl Sulfamethoxazole/trimethoprim Sulfamethoxazol/trimethoprim TRUE FALSE FALSE
+nl Sulfametoxydiazine Sulfamethoxydiazine TRUE FALSE FALSE
+nl Sulfametrole/trimethoprim Sulfametrol/trimethoprim TRUE FALSE FALSE
+nl Sulfamoxole Sulfamoxol TRUE FALSE FALSE
+nl Sulfamoxole/trimethoprim Sulfamoxol/trimethoprim TRUE FALSE FALSE
+nl Sulfaperin Sulfaperine TRUE FALSE FALSE
+nl Sulfaphenazole Sulfafenazol TRUE FALSE FALSE
+nl Sulfathiazole Sulfathiazol TRUE FALSE FALSE
+nl Sulfathiourea Sulfathioureum TRUE FALSE FALSE
+nl Sultamicillin Sultamicilline TRUE FALSE FALSE
+nl Talampicillin Talampicilline TRUE FALSE FALSE
+nl Teicoplanin Teicoplanine TRUE FALSE FALSE
+nl Telithromycin Telitromycine TRUE FALSE FALSE
+nl Temafloxacin Temafloxacine TRUE FALSE FALSE
+nl Temocillin Temocilline TRUE FALSE FALSE
+nl Tenofovir disoproxil Tenofovir TRUE FALSE FALSE
+nl Terizidone Terizidon TRUE FALSE FALSE
+nl Thiamphenicol Thiamfenicol TRUE FALSE FALSE
+nl Thioacetazone/isoniazid Thioacetazon/isoniazide TRUE FALSE FALSE
+nl Ticarcillin Ticarcilline TRUE FALSE FALSE
+nl Ticarcillin/beta-lactamase inhibitor Ticarcilline/enzymremmer TRUE FALSE FALSE
+nl Ticarcillin/clavulanic acid Ticarcilline/clavulaanzuur TRUE FALSE FALSE
+nl Tinidazole Tinidazol TRUE FALSE FALSE
+nl Tobramycin Tobramycine TRUE FALSE FALSE
+nl Trimethoprim/sulfamethoxazole Cotrimoxazol TRUE FALSE FALSE
+nl Troleandomycin Troleandomycine TRUE FALSE FALSE
+nl Trovafloxacin Trovafloxacine TRUE FALSE FALSE
+nl Vancomycin Vancomycine TRUE FALSE FALSE
+nl Voriconazole Voriconazol TRUE FALSE FALSE
+nl Aminoglycosides Aminoglycosiden TRUE FALSE FALSE
+nl Amphenicols Amfenicolen TRUE FALSE FALSE
+nl Antifungals/antimycotics Antifungica/antimycotica TRUE FALSE FALSE
+nl Antimycobacterials Antimycobacteriele middelen TRUE FALSE FALSE
+nl Beta-lactams/penicillins Beta-lactams/penicillines TRUE FALSE FALSE
+nl Cephalosporins (1st gen.) Cefalosporines (1e gen.) TRUE FALSE FALSE
+nl Cephalosporins (2nd gen.) Cefalosporines (2e gen.) TRUE FALSE FALSE
+nl Cephalosporins (3rd gen.) Cefalosporines (3e gen.) TRUE FALSE FALSE
+nl Cephalosporins (4th gen.) Cefalosporines (4e gen.) TRUE FALSE FALSE
+nl Cephalosporins (5th gen.) Cefalosporines (5e gen.) TRUE FALSE FALSE
+nl Cephalosporins (unclassified gen.) Cefalosporines (ongeclassificeerd) TRUE FALSE FALSE
+nl Cephalosporins Cefalosporines TRUE FALSE FALSE
+nl Glycopeptides Glycopeptiden TRUE FALSE FALSE
+nl Macrolides/lincosamides Macroliden/lincosamiden TRUE FALSE FALSE
+nl Other antibacterials Overige antibiotica TRUE FALSE FALSE
+nl Polymyxins Polymyxines TRUE FALSE FALSE
+nl Quinolones Quinolonen TRUE FALSE FALSE
diff --git a/docs/404.html b/docs/404.html
index 43c4fad1..17888f86 100644
--- a/docs/404.html
+++ b/docs/404.html
@@ -81,7 +81,7 @@
AMR (for R)
- 1.5.0.9019
+ 1.5.0.9020
diff --git a/docs/LICENSE-text.html b/docs/LICENSE-text.html
index 6d5d1e4f..adc8ceba 100644
--- a/docs/LICENSE-text.html
+++ b/docs/LICENSE-text.html
@@ -81,7 +81,7 @@
AMR (for R)
- 1.5.0.9019
+ 1.5.0.9020
diff --git a/docs/articles/index.html b/docs/articles/index.html
index e05b9bd2..422c81e8 100644
--- a/docs/articles/index.html
+++ b/docs/articles/index.html
@@ -81,7 +81,7 @@
AMR (for R)
- 1.5.0.9019
+ 1.5.0.9020
diff --git a/docs/authors.html b/docs/authors.html
index 8d83429d..824b29ee 100644
--- a/docs/authors.html
+++ b/docs/authors.html
@@ -81,7 +81,7 @@
AMR (for R)
- 1.5.0.9019
+ 1.5.0.9020
diff --git a/docs/index.html b/docs/index.html
index 7b6fc433..01de6418 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -43,7 +43,7 @@
AMR (for R)
- 1.5.0.9019
+ 1.5.0.9020
@@ -395,8 +395,9 @@ Since you are one of our users, we would like to know how you use the package an
The latest and unpublished development version can be installed from GitHub using:
+You can also download the latest build from our repository: https://github.com/msberends/AMR/raw/master/data-raw/AMR_latest.tar.gz
diff --git a/docs/news/index.html b/docs/news/index.html
index bff725b8..becdfb44 100644
--- a/docs/news/index.html
+++ b/docs/news/index.html
@@ -81,7 +81,7 @@
AMR (for R)
- 1.5.0.9019
+ 1.5.0.9020
NEWS.md
-
-