Replace RSI with SIR

data-raw/_pre_commit_hook.R

@@ -144,21 +144,6 @@ create_species_cons_cops <- function(type = c("CoNS", "CoPS")) {
     ]
   }
 }
-create_MO_fullname_lower <- function() {
-  AMR_env$MO_lookup <- AMR::microorganisms
-  # use this paste instead of `fullname` to work with Viridans Group Streptococci, etc.
-  AMR_env$MO_lookup$fullname_lower <- tolower(trimws(paste(
-    AMR_env$MO_lookup$genus,
-    AMR_env$MO_lookup$species,
-    AMR_env$MO_lookup$subspecies
-  )))
-  ind <- AMR_env$MO_lookup$genus == "" | grepl("^[(]unknown ", AMR_env$MO_lookup$fullname, perl = TRUE)
-  AMR_env$MO_lookup[ind, "fullname_lower"] <- tolower(AMR_env$MO_lookup[ind, "fullname", drop = TRUE])
-  AMR_env$MO_lookup$fullname_lower <- trimws(gsub("[^.a-z0-9/ \\-]+", "", AMR_env$MO_lookup$fullname_lower, perl = TRUE))
-  # special for Salmonella - they have cities as subspecies but not the species (enterica) in the fullname:
-  AMR_env$MO_lookup$fullname_lower[which(AMR_env$MO_lookup$subspecies %like_case% "^[A-Z]")] <- gsub(" enterica ", " ", AMR_env$MO_lookup$fullname_lower[which(AMR_env$MO_lookup$subspecies %like_case% "^[A-Z]")], fixed = TRUE)
-  AMR_env$MO_lookup$fullname_lower
-}
 MO_CONS <- create_species_cons_cops("CoNS")
 MO_COPS <- create_species_cons_cops("CoPS")
 MO_STREP_ABCG <- AMR_env$MO_lookup$mo[which(AMR_env$MO_lookup$genus == "Streptococcus" &
@@ -166,7 +151,6 @@ MO_STREP_ABCG <- AMR_env$MO_lookup$mo[which(AMR_env$MO_lookup$genus == "Streptoc
     "pyogenes", "agalactiae", "dysgalactiae", "equi", "canis",
     "group A", "group B", "group C", "group G"
   ))]
-MO_FULLNAME_LOWER <- create_MO_fullname_lower()
 MO_PREVALENT_GENERA <- c(
   "Absidia", "Acanthamoeba", "Acremonium", "Aedes", "Alternaria", "Amoeba", "Ancylostoma", "Angiostrongylus",
   "Anisakis", "Anopheles", "Apophysomyces", "Aspergillus", "Aureobasidium", "Basidiobolus", "Beauveria",
@@ -298,7 +282,6 @@ suppressMessages(usethis::use_data(EUCAST_RULES_DF,
   MO_CONS,
   MO_COPS,
   MO_STREP_ABCG,
-  MO_FULLNAME_LOWER,
   MO_PREVALENT_GENERA,
   AB_LOOKUP,
   AV_LOOKUP,
@@ -369,20 +352,20 @@ changed_md5 <- function(object) {
 }
 
 # give official names to ABs and MOs
-rsi <- rsi_translation %>%
+clin_break <- clinical_breakpoints %>%
   mutate(mo_name = mo_name(mo, language = NULL, keep_synonyms = TRUE, info = FALSE), .after = mo) %>%
   mutate(ab_name = ab_name(ab, language = NULL), .after = ab)
-if (changed_md5(rsi)) {
-  usethis::ui_info(paste0("Saving {usethis::ui_value('rsi_translation')} to {usethis::ui_value('data-raw/')}"))
-  write_md5(rsi)
-  try(saveRDS(rsi, "data-raw/rsi_translation.rds", version = 2, compress = "xz"), silent = TRUE)
-  try(write.table(rsi, "data-raw/rsi_translation.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)
-  try(haven::write_sas(rsi, "data-raw/rsi_translation.sas"), silent = TRUE)
-  try(haven::write_sav(rsi, "data-raw/rsi_translation.sav"), silent = TRUE)
-  try(haven::write_dta(rsi, "data-raw/rsi_translation.dta"), silent = TRUE)
-  try(openxlsx::write.xlsx(rsi, "data-raw/rsi_translation.xlsx"), silent = TRUE)
-  try(arrow::write_feather(rsi, "data-raw/rsi_translation.feather"), silent = TRUE)
-  try(arrow::write_parquet(rsi, "data-raw/rsi_translation.parquet"), silent = TRUE)
+if (changed_md5(clin_break)) {
+  usethis::ui_info(paste0("Saving {usethis::ui_value('clinical_breakpoints')} to {usethis::ui_value('data-raw/')}"))
+  write_md5(clin_break)
+  try(saveRDS(clin_break, "data-raw/clinical_breakpoints.rds", version = 2, compress = "xz"), silent = TRUE)
+  try(write.table(clin_break, "data-raw/clinical_breakpoints.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)
+  try(haven::write_sas(clin_break, "data-raw/clinical_breakpoints.sas"), silent = TRUE)
+  try(haven::write_sav(clin_break, "data-raw/clinical_breakpoints.sav"), silent = TRUE)
+  try(haven::write_dta(clin_break, "data-raw/clinical_breakpoints.dta"), silent = TRUE)
+  try(openxlsx::write.xlsx(clin_break, "data-raw/clinical_breakpoints.xlsx"), silent = TRUE)
+  try(arrow::write_feather(clin_break, "data-raw/clinical_breakpoints.feather"), silent = TRUE)
+  try(arrow::write_parquet(clin_break, "data-raw/clinical_breakpoints.parquet"), silent = TRUE)
 }
 
 if (changed_md5(microorganisms)) {

data-raw/microorganisms.txt

@@ -45554,7 +45554,7 @@
 "B_STRPT_ORLX"	"Streptococcus oriloxodontae"	"accepted"	"Bacteria"	"Bacillota"	"Bacilli"	"Lactobacillales"	"Streptococcaceae"	"Streptococcus"	"oriloxodontae"	""	"species"	"Shinozaki-Kuwahara et al., 2014"	"LPSN"	"792340"	"517118"					1.5	""
 "B_STRPT_ORSS"	"Streptococcus orisasini"	"accepted"	"Bacteria"	"Bacillota"	"Bacilli"	"Lactobacillales"	"Streptococcaceae"	"Streptococcus"	"orisasini"	""	"species"	"Takada et al., 2013"	"LPSN"	"790987"	"517118"					1.5	""
 "B_STRPT_ORSR"	"Streptococcus orisratti"	"accepted"	"Bacteria"	"Bacillota"	"Bacilli"	"Lactobacillales"	"Streptococcaceae"	"Streptococcus"	"orisratti"	""	"species"	"Zhu et al., 2000"	"LPSN"	"781365"	"517118"					1.5	"438034004"
-"B_STRPT_RSIS"	"Streptococcus orisuis"	"accepted"	"Bacteria"	"Bacillota"	"Bacilli"	"Lactobacillales"	"Streptococcaceae"	"Streptococcus"	"orisuis"	""	"species"	"Takada et al., 2007"	"LPSN"	"781314"	"517118"					1.5	"6441000146108"
+"B_STRPT_sirS"	"Streptococcus orisuis"	"accepted"	"Bacteria"	"Bacillota"	"Bacilli"	"Lactobacillales"	"Streptococcaceae"	"Streptococcus"	"orisuis"	""	"species"	"Takada et al., 2007"	"LPSN"	"781314"	"517118"					1.5	"6441000146108"
 "B_STRPT_OVIS"	"Streptococcus ovis"	"accepted"	"Bacteria"	"Bacillota"	"Bacilli"	"Lactobacillales"	"Streptococcaceae"	"Streptococcus"	"ovis"	""	"species"	"Collins et al., 2001"	"LPSN"	"781366"	"517118"					1.5	"438035003"
 "B_STRPT_OVBR"	"Streptococcus ovuberis"	"accepted"	"Bacteria"	"Bacillota"	"Bacilli"	"Lactobacillales"	"Streptococcaceae"	"Streptococcus"	"ovuberis"	""	"species"	"Zamora et al., 2017"	"LPSN"	"796216"	"517118"					1.5	""
 "B_STRPT_PCFC"	"Streptococcus pacificus"	"accepted"	"Bacteria"	"Bacillota"	"Bacilli"	"Lactobacillales"	"Streptococcaceae"	"Streptococcus"	"pacificus"	""	"species"	"Volokhov et al., 2021"	"LPSN"	"19573"	"517118"					1.5	""

data-raw/read_EUCAST.R

@@ -230,7 +230,7 @@ read_EUCAST <- function(sheet, file, guideline_name) {
       mo = ifelse(mo == "", mo_sheet, mo)
     ) %>%
     filter(!(is.na(breakpoint_S) & is.na(breakpoint_R))) %>%
-    # comply with rsi_translation for now
+    # comply with clinical_breakpoints for now
     transmute(guideline,
       method,
       site = case_when(
@@ -285,7 +285,7 @@ for (i in 2:length(sheets_to_analyse)) {
 }
 
 # 2021-07-12 fix for Morganellaceae (check other lines too next time)
-morg <- rsi_translation %>%
+morg <- clinical_breakpoints %>%
   as_tibble() %>%
   filter(
     ab == "IPM",
@@ -298,7 +298,7 @@ morg[which(morg$method == "MIC"), "breakpoint_R"] <- 4
 morg[which(morg$method == "DISK"), "breakpoint_S"] <- 50
 morg[which(morg$method == "DISK"), "breakpoint_R"] <- 19
 
-rsi_translation <- rsi_translation %>%
+clinical_breakpoints <- clinical_breakpoints %>%
   bind_rows(morg) %>%
   bind_rows(morg %>%
     mutate(guideline = "EUCAST 2020")) %>%

data-raw/reproduction_of_clinical_breakpoints.R

@@ -28,7 +28,7 @@
 # ==================================================================== #
 
 # This script runs in under a minute and renews all guidelines of CLSI and EUCAST!
-# Run it with source("data-raw/reproduction_of_rsi_translation.R")
+# Run it with source("data-raw/reproduction_of_clinical_breakpoints.R")
 
 library(dplyr)
 library(readr)
@@ -206,11 +206,11 @@ breakpoints_new[which(is.na(breakpoints_new$breakpoint_R)), "breakpoint_R"] <- b
 # check again
 breakpoints_new %>% filter(guideline == "EUCAST 2022", ab == "AMC", mo == "B_[ORD]_ENTRBCTR", method == "MIC")
 # compare with current version
-rsi_translation %>% filter(guideline == "EUCAST 2022", ab == "AMC", mo == "B_[ORD]_ENTRBCTR", method == "MIC")
+clinical_breakpoints %>% filter(guideline == "EUCAST 2022", ab == "AMC", mo == "B_[ORD]_ENTRBCTR", method == "MIC")
 
 # Save to package ----
 
-rsi_translation <- breakpoints_new
-usethis::use_data(rsi_translation, overwrite = TRUE, compress = "xz", version = 2)
-rm(rsi_translation)
+clinical_breakpoints <- breakpoints_new
+usethis::use_data(clinical_breakpoints, overwrite = TRUE, compress = "xz", version = 2)
+rm(clinical_breakpoints)
 devtools::load_all(".")

data-raw/reproduction_of_intrinsic_resistant.R

@@ -31,7 +31,7 @@ library(AMR)
 library(dplyr)
 int_resis <- data.frame(mo = microorganisms$mo, stringsAsFactors = FALSE)
 for (i in seq_len(nrow(antibiotics))) {
-  int_resis$new <- as.rsi("S")
+  int_resis$new <- as.sir("S")
   colnames(int_resis)[ncol(int_resis)] <- antibiotics$ab[i]
 }
 
@@ -43,7 +43,7 @@ int_resis <- eucast_rules(int_resis,
   info = FALSE
 )
 
-int_resis2 <- int_resis[, sapply(int_resis, function(x) any(!is.rsi(x) | x == "R")), drop = FALSE] %>%
+int_resis2 <- int_resis[, sapply(int_resis, function(x) any(!is.sir(x) | x == "R")), drop = FALSE] %>%
   tidyr::pivot_longer(-mo) %>%
   filter(value == "R") %>%
   select(mo, ab = name)

data-raw/reproduction_of_microorganisms.R

@@ -1333,7 +1333,7 @@ rm(microorganisms)
 
 # and check: these codes should not be missing (will otherwise throw a unit test error):
 AMR::microorganisms.codes %>% filter(!mo %in% taxonomy$mo)
-AMR::rsi_translation %>% filter(!mo %in% taxonomy$mo)
+AMR::clinical_breakpoints %>% filter(!mo %in% taxonomy$mo)
 AMR::example_isolates %>% filter(!mo %in% taxonomy$mo)
 AMR::intrinsic_resistant %>% filter(!mo %in% taxonomy$mo)
 
@@ -1342,10 +1342,10 @@ devtools::load_all(".")
 
 
 # reset previously changed mo codes
-if (!identical(rsi_translation$mo, as.mo(rsi_translation$mo, language = NULL))) {
-  rsi_translation$mo <- as.mo(rsi_translation$mo, language = NULL)
-  usethis::use_data(rsi_translation, overwrite = TRUE, version = 2, compress = "xz")
-  rm(rsi_translation)
+if (!identical(clinical_breakpoints$mo, as.mo(clinical_breakpoints$mo, language = NULL))) {
+  clinical_breakpoints$mo <- as.mo(clinical_breakpoints$mo, language = NULL)
+  usethis::use_data(clinical_breakpoints, overwrite = TRUE, version = 2, compress = "xz")
+  rm(clinical_breakpoints)
 }
 
 if (!identical(microorganisms.codes$mo, as.mo(microorganisms.codes$mo, language = NULL))) {