EUCAST import: blocking rows, note restrictions, PK-PD and parser fixes (#310)

Make the EUCAST Clinical Breakpoint Tables import (2019-2026) fail-safe:

- Add blocking rows (NA breakpoints, reason in `note`) where EUCAST gives
  no breakpoint for an organism (IE, "-", Note, brackets, "except"
  clauses, table scope), so as.sir() no longer falls back to broader taxa
- Apply restrictions from EUCAST notes via a curated rule table with a
  completeness guard (e.g. zone diameters for E. coli only)
- Import PK-PD (non-species related) breakpoints 2019-2023, H.
  parainfluenzae MIC breakpoints, and explicit screening thresholds from
  notes (high-level aminoglycosides, cefoxitin MIC, unidentified CoNS)
- Parser fixes: lost Staphylococcus sheets 2019/2020, note keys and
  bodies, struck-through cells, hidden sheets, missing disk contents,
  organism groups, site vocabulary, MIC dilution levels, off-scale
  breakpoints stored as 0.0001
- Keep EUCAST antifungal breakpoints 2019-2025 from WHONET; code WHONET
  streptomycin as STR1 instead of STR (streptoduocin)

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Matthijs BerendsandClaude Opus 5.5 authored and GitHub committed 2026-10-02 06:01:58 +02:00
1 parent 5d9974e2b9
commit dab4c47e86
25 files changed
+83693 -58604

No files matched your search

+2 -1
View File
@@ -653,7 +653,8 @@ if (changed_md5(clin_break)) {
try(saveRDS(clin_break, "data-raw/datasets/clinical_breakpoints.rds", version = 2, compress = "xz"), silent = TRUE)
try(write.table(clinical_breakpoints, "data-raw/datasets/clinical_breakpoints.txt", sep = "\t", na = "", row.names = FALSE), silent = TRUE)
try(haven::write_sav(clin_break, "data-raw/datasets/clinical_breakpoints.sav"), silent = TRUE)
try(haven::write_dta(clin_break, "data-raw/datasets/clinical_breakpoints.dta"), silent = TRUE)
# long notes as strL, otherwise Stata's fixed-width strings make the file exceed 100 MB; a missing string is "" in Stata
try(haven::write_dta(clin_break %>% mutate(note = if_else(is.na(note), "", note)), "data-raw/datasets/clinical_breakpoints.dta", strl_threshold = 255), silent = TRUE)
try(openxlsx2::write_xlsx(clin_break, "data-raw/datasets/clinical_breakpoints.xlsx"), silent = TRUE)
try(arrow::write_feather(clin_break, "data-raw/datasets/clinical_breakpoints.feather"), silent = TRUE)
try(arrow::write_parquet(clin_break, "data-raw/datasets/clinical_breakpoints.parquet"), silent = TRUE)
@@ -282,6 +282,24 @@ breakpoints |>
breakpoints <- breakpoints |>
filter(!is.na(WHONET_ABX_CODE))
# a WHONET code can also exist in `antimicrobials` as the code of another
# agent, e.g. WHONET "STR" (streptomycin) is "STR" (streptoduocin) here, so
# compare the code with WHONET's own name of the agent:
whonet_code_check <- breakpoints |>
distinct(WHONET_ABX_CODE) |>
left_join(whonet_antibiotics_raw |> select(WHONET_ABX_CODE, ANTIBIOTIC), by = "WHONET_ABX_CODE") |>
filter(!is.na(ANTIBIOTIC)) |>
mutate(
by_code = as.ab(if_else(WHONET_ABX_CODE == "STR", "STR1", WHONET_ABX_CODE), info = FALSE),
by_name = as.ab(ANTIBIOTIC, info = FALSE)
) |>
filter(is.na(by_code) | is.na(by_name) | by_code != by_name)
# 2026-10-01: SUD (WHONET: sulbactam-durlobactam, CLSI 2024-2026) is
# sulfadimethoxine here, and sulbactam-durlobactam is not in `antimicrobials`
# yet; this must be resolved before these breakpoints can be used. This
# should otherwise be empty:
whonet_code_check
## Build new breakpoints table ----
@@ -304,7 +322,10 @@ breakpoints_new <- breakpoints |>
mo_rank(mo, keep_synonyms = TRUE) == "order" ~ 5,
TRUE ~ 6
),
ab = as.ab(WHONET_ABX_CODE),
# WHONET code "STR" is streptomycin, but in this package "STR" is
# streptoduocin (streptomycin is "STR1"), so as.ab("STR") would return
# the wrong agent
ab = as.ab(if_else(WHONET_ABX_CODE == "STR", "STR1", WHONET_ABX_CODE)),
ref_tbl = ifelse(type == "ECOFF" & is.na(REFERENCE_TABLE), "ECOFF", REFERENCE_TABLE),
disk_dose = POTENCY,
breakpoint_S = ifelse(type == "ECOFF" & is.na(S) & !is.na(ECV_ECOFF), ECV_ECOFF, S),
@@ -505,6 +526,9 @@ dim(clinical_breakpoints)
# Retrieve >= EUCAST 2019 directly from EUCAST ----
# This parses the EUCAST Clinical Breakpoint Tables in data-raw/ and creates
# `breakpoints_eucast`, `eucast_coverage` and merge_eucast_breakpoints(), used
# below to replace the WHONET-based human EUCAST rows that these tables cover
source("data-raw/_reproduction_scripts/reproduction_of_clinical_breakpoints_eucast.R")
@@ -525,8 +549,7 @@ breakpoints_new <- breakpoints_new |>
# and arrange
arrange(desc(guideline), mo, ab, type, host, method)
clinical_breakpoints <- breakpoints_new
clinical_breakpoints <- clinical_breakpoints |> dataset_UTF8_to_ASCII()
clinical_breakpoints <- merge_eucast_breakpoints(breakpoints_new, breakpoints_eucast, eucast_coverage)
usethis::use_data(clinical_breakpoints, overwrite = TRUE, compress = "xz", version = 2)
rm(clinical_breakpoints)
devtools::load_all(".")
File diff suppressed because it is too large. Load diff
File diff suppressed because it is too large. Load diff
Binary file not shown.
+1 -1
View File
@@ -1 +1 @@
634c5e23bed1e92783eeb4739c0d1486
c23b72fd46f4a08b2033b104cef0d4e1
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
File diff suppressed because it is too large. Load diff
Binary file not shown.