(v2.1.1.9090) website error

DESCRIPTION

@@ -1,5 +1,5 @@
 Package: AMR
-Version: 2.1.1.9089
+Version: 2.1.1.9090
 Date: 2024-10-04
 Title: Antimicrobial Resistance Data Analysis
 Description: Functions to simplify and standardise antimicrobial resistance (AMR)

NEWS.md

@@ -1,4 +1,4 @@
-# AMR 2.1.1.9089
+# AMR 2.1.1.9090
 
 *(this beta version will eventually become v3.0. We're happy to reach a new major milestone soon, which will be all about the new One Health support! Install this beta using [the instructions here](https://msberends.github.io/AMR/#latest-development-version).)*
 

_pkgdown.yml

@@ -59,7 +59,6 @@ home:
   sidebar:
     structure: [gpthelp, toc, links, authors]
     components:
-      <a href="https://chatgpt.com/g/g-M4UNLwFi5-amr-for-r-assistant"><img src="AMRforRGPT.svg" style="min-width: 300px; width: 10%;" /></a>
       gpthelp: '<a target="_blank" href="https://chatgpt.com/g/g-M4UNLwFi5-amr-for-r-assistant"><img src="https://github.com/msberends/AMR/raw/main/pkgdown/assets/AMRforRGPT.svg" style="width: 80%;"></a>'
 
 navbar:

data-raw/reproduction_of_antibiotics.R

@@ -262,43 +262,66 @@ get_synonyms <- function(CID, clean = TRUE) {
     if (is.na(CID[i])) {
       next
     }
-
+    
-    synonyms_txt <- tryCatch(
+    # we will now get the closest compounds with a 96% threshold
+    similar_cids <- tryCatch(
       data.table::fread(
         paste0(
-          "https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/fastidentity/cid/",
+          "https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/fastsimilarity_2d/cid/",
           CID[i],
-          "/synonyms/TXT"
+          "/cids/TXT?Threshold=96&MaxRecords=5"
         ),
         sep = "\n",
         showProgress = FALSE
       )[[1]],
       error = function(e) NA_character_
     )
-
+    all_cids <- unique(c(CID[i], similar_cids))
-    Sys.sleep(0.1)
+    # for each one, we are getting the synonyms
-
+    current_syns <- character(0)
-    if (clean == TRUE) {
+    for (j in seq_len(length(all_cids))) {
-      # remove text between brackets
+      synonyms_txt <- tryCatch(
-      synonyms_txt <- trimws(gsub(
+        data.table::fread(
-        "[(].*[)]", "",
+          paste0(
-        gsub(
+            "https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/fastidentity/cid/",
-          "[[].*[]]", "",
+            all_cids[j],
+            "/synonyms/TXT"
+          ),
+          sep = "\n",
+          showProgress = FALSE
+        )[[1]],
+        error = function(e) NA_character_
+      )
+      
+      Sys.sleep(0.05)
+      
+      if (clean == TRUE) {
+        # remove text between brackets
+        synonyms_txt <- trimws(gsub(
+          "[(].*[)]", "",
           gsub(
-            "[(].*[]]", "",
+            "[[].*[]]", "",
-            gsub("[[].*[)]", "", synonyms_txt)
+            gsub(
+              "[(].*[]]", "",
+              gsub("[[].*[)]", "", synonyms_txt)
+            )
           )
-        )
+        ))
-      ))
+        synonyms_txt <- gsub("Co-", "Co", synonyms_txt, fixed = TRUE)
-      synonyms_txt <- gsub("Co-", "Co", synonyms_txt, fixed = TRUE)
+        synonyms_txt <- gsub(" ?(mono)?sodium ?", "", ignore.case = TRUE, synonyms_txt)
-      # only length 6 to 20 and no txt with reading marks or numbers and must start with capital letter (= brand)
+        synonyms_txt <- gsub(" ?injection ?", "", ignore.case = TRUE, synonyms_txt)
-      synonyms_txt <- synonyms_txt[nchar(synonyms_txt) %in% c(6:20) &
+        # only length 6 to 20 and no txt with reading marks or numbers and must start with capital letter (= brand)
-        !grepl("[-&{},_0-9/:]", synonyms_txt) &
+        synonyms_txt <- synonyms_txt[nchar(synonyms_txt) %in% c(5:20) &
-        grepl("^[A-Z]", synonyms_txt, ignore.case = FALSE)]
+                                       !grepl("[-&{},_0-9/:]", synonyms_txt) &
-      synonyms_txt <- unlist(strsplit(synonyms_txt, ";", fixed = TRUE))
+                                       grepl("^[A-Z]", synonyms_txt, ignore.case = FALSE)]
+        synonyms_txt <- unlist(strsplit(synonyms_txt, ";", fixed = TRUE))
+      }
+      
+      current_syns <- c(current_syns, synonyms_txt)
     }
-    synonyms_txt <- unique(trimws(synonyms_txt[tolower(synonyms_txt) %in% unique(tolower(synonyms_txt))]))
+    
-    synonyms[i] <- list(sort(synonyms_txt))
+    current_syns <- unique(trimws(current_syns[tolower(current_syns) %in% unique(tolower(current_syns))]))
+    synonyms[i] <- list(sort(current_syns))
   }
   names(synonyms) <- CID
   synonyms
@@ -319,7 +342,7 @@ for (i in seq_len(length(synonyms))) {
 
 antibiotics$synonyms <- synonyms
 
-stop("remember to remove co-trimoxazole as synonyms from SXT (Sulfamethoxazole), so it only exists in SXT!")
+stop("remember to remove co-trimoxazole as synonyms from SMX (Sulfamethoxazole), so it only exists in SXT!")
 sulfa <- antibiotics[which(antibiotics$ab == "SMX"), "synonyms", drop = TRUE][[1]]
 cotrim <- antibiotics[which(antibiotics$ab == "SXT"), "synonyms", drop = TRUE][[1]]
 sulfa <- sulfa[!sulfa %in% cotrim]