P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2024-12-26 06:46:11 +01:00
Code Releases Activity

(v2.1.1.9090) website error

Browse Source
This commit is contained in:
dr. M.S. (Matthijs) Berends 2024-10-04 16:08:41 +02:00
parent 0736ac7a7e
commit 325664f5aa
4 changed files with 51 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
DESCRIPTION
View File

@ -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)

2
NEWS.md
View File

@ -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).)*

1
_pkgdown.yml
View File

@ -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:

35
data-raw/reproduction_of_antibiotics.R
View File

@ -263,11 +263,28 @@ get_synonyms <- function(CID, clean = TRUE) {
next
}
# 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/fastsimilarity_2d/cid/",
CID[i],
"/cids/TXT?Threshold=96&MaxRecords=5"
),
sep = "\n",
showProgress = FALSE
)[[1]],
error = function(e) NA_character_
)
all_cids <- unique(c(CID[i], similar_cids))
# for each one, we are getting the synonyms
current_syns <- character(0)
for (j in seq_len(length(all_cids))) {
synonyms_txt <- tryCatch(
data.table::fread(
paste0(
"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/fastidentity/cid/",
CID[i],
all_cids[j],
"/synonyms/TXT"
),
sep = "\n",
@ -276,7 +293,7 @@ get_synonyms <- function(CID, clean = TRUE) {
error = function(e) NA_character_
)
Sys.sleep(0.1)
Sys.sleep(0.05)
if (clean == TRUE) {
# remove text between brackets
@ -291,14 +308,20 @@ get_synonyms <- function(CID, clean = TRUE) {
)
))
synonyms_txt <- gsub("Co-", "Co", synonyms_txt, fixed = TRUE)
synonyms_txt <- gsub(" ?(mono)?sodium ?", "", ignore.case = TRUE, synonyms_txt)
synonyms_txt <- gsub(" ?injection ?", "", 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 <- synonyms_txt[nchar(synonyms_txt) %in% c(6:20) &
synonyms_txt <- synonyms_txt[nchar(synonyms_txt) %in% c(5:20) &
!grepl("[-&{},_0-9/:]", synonyms_txt) &
grepl("^[A-Z]", synonyms_txt, ignore.case = FALSE)]
synonyms_txt <- unlist(strsplit(synonyms_txt, ";", fixed = TRUE))
}
synonyms_txt <- unique(trimws(synonyms_txt[tolower(synonyms_txt) %in% unique(tolower(synonyms_txt))]))
synonyms[i] <- list(sort(synonyms_txt))
current_syns <- c(current_syns, 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]