AMR/inst/tinytest/test-mo.R

329 lines
13 KiB
R
Raw Normal View History

2021-05-15 21:36:22 +02:00
# ==================================================================== #
# TITLE #
2022-10-05 09:12:22 +02:00
# AMR: An R Package for Working with Antimicrobial Resistance Data #
2021-05-15 21:36:22 +02:00
# #
# SOURCE #
# https://github.com/msberends/AMR #
# #
2022-10-05 09:12:22 +02:00
# CITE AS #
# Berends MS, Luz CF, Friedrich AW, Sinha BNM, Albers CJ, Glasner C #
# (2022). AMR: An R Package for Working with Antimicrobial Resistance #
# Data. Journal of Statistical Software, 104(3), 1-31. #
# doi:10.18637/jss.v104.i03 #
# #
2022-12-27 15:16:15 +01:00
# Developed at the University of Groningen and the University Medical #
# Center Groningen in The Netherlands, in collaboration with many #
# colleagues from around the world, see our website. #
2021-05-15 21:36:22 +02:00
# #
# This R package is free software; you can freely use and distribute #
# it for both personal and commercial purposes under the terms of the #
# GNU General Public License version 2.0 (GNU GPL-2), as published by #
# the Free Software Foundation. #
# We created this package for both routine data analysis and academic #
# research and it was publicly released in the hope that it will be #
# useful, but it comes WITHOUT ANY WARRANTY OR LIABILITY. #
# #
# Visit our website for the full manual and a complete tutorial about #
# how to conduct AMR data analysis: https://msberends.github.io/AMR/ #
# ==================================================================== #
MOs <- subset(microorganisms, !is.na(mo) & nchar(mo) > 3)
expect_identical(as.character(MOs$mo), as.character(as.mo(MOs$mo)))
expect_identical(
2022-10-05 09:12:22 +02:00
as.character(as.mo(c("E. coli", "H. influenzae"), keep_synonyms = FALSE)),
2022-08-28 10:31:50 +02:00
c("B_ESCHR_COLI", "B_HMPHL_INFL")
)
2021-05-15 21:36:22 +02:00
expect_equal(as.character(as.mo("Escherichia coli")), "B_ESCHR_COLI")
expect_equal(as.character(as.mo("Escherichia coli")), "B_ESCHR_COLI")
expect_equal(as.character(as.mo(112283007)), "B_ESCHR_COLI")
expect_equal(as.character(as.mo("Escherichia species")), "B_ESCHR")
expect_equal(as.character(as.mo("Escherichia")), "B_ESCHR")
2022-10-05 09:12:22 +02:00
expect_equal(as.character(as.mo("Eschr spp.")), "B_ESCHR")
2021-05-15 21:36:22 +02:00
expect_equal(as.character(as.mo(" B_ESCHR_COLI ")), "B_ESCHR_COLI")
expect_equal(as.character(as.mo("e coli")), "B_ESCHR_COLI") # not Campylobacter
expect_equal(as.character(as.mo("klpn")), "B_KLBSL_PNMN")
expect_equal(as.character(as.mo("Klebsiella")), "B_KLBSL")
2022-10-05 09:12:22 +02:00
expect_equal(as.character(as.mo("K. pneumo rhino")), "B_KLBSL_PNMN_RHNS") # K. pneumoniae subspp. rhinoscleromatis
2021-05-15 21:36:22 +02:00
expect_equal(as.character(as.mo("Bartonella")), "B_BRTNL")
expect_equal(as.character(as.mo("C. difficile")), "B_CRDDS_DFFC")
expect_equal(as.character(as.mo("L. pneumophila")), "B_LGNLL_PNMP")
expect_equal(as.character(as.mo("Streptococcus")), "B_STRPT") # not Peptostreptoccus
expect_equal(as.character(as.mo("Estreptococos grupo B")), "B_STRPT_GRPB")
expect_equal(as.character(as.mo("Group B Streptococci")), "B_STRPT_GRPB")
2022-10-05 09:12:22 +02:00
expect_equal(as.character(as.mo(c("GAS", "GBS", "haemoly strep"))), c("B_STRPT_GRPA", "B_STRPT_GRPB", "B_STRPT_HAEM"))
2021-05-15 21:36:22 +02:00
expect_equal(as.character(as.mo("S. pyo")), "B_STRPT_PYGN") # not Actinomyces pyogenes
# GLIMS
expect_equal(as.character(as.mo("bctfgr")), "B_BCTRD_FRGL")
expect_equal(as.character(as.mo("MRSE")), "B_STPHY_EPDR")
expect_equal(as.character(as.mo("VRE")), "B_ENTRC")
expect_equal(as.character(as.mo("MRPA")), "B_PSDMN_AERG")
expect_equal(as.character(as.mo("PISP")), "B_STRPT_PNMN")
expect_equal(as.character(as.mo("PRSP")), "B_STRPT_PNMN")
expect_equal(as.character(as.mo("VISP")), "B_STRPT_PNMN")
expect_equal(as.character(as.mo("VRSP")), "B_STRPT_PNMN")
expect_equal(as.character(as.mo("CNS")), "B_STPHY_CONS")
expect_equal(as.character(as.mo("CoNS")), "B_STPHY_CONS")
expect_equal(as.character(as.mo("CPS")), "B_STPHY_COPS")
expect_equal(as.character(as.mo("CoPS")), "B_STPHY_COPS")
expect_equal(as.character(as.mo("VGS")), "B_STRPT_VIRI")
expect_equal(as.character(as.mo("streptococcus milleri")), "B_STRPT_MILL")
expect_equal(as.character(as.mo(c("Gram negative", "Gram positive"))), c("B_GRAMN", "B_GRAMP"))
2022-11-17 15:23:29 +01:00
expect_warning(as.mo("Acinetobacter calcoaceticus/baumannii complex"))
2021-05-15 21:36:22 +02:00
# prevalent MO
expect_identical(
suppressWarnings(as.character(
2022-08-28 10:31:50 +02:00
as.mo(c(
2022-10-06 11:33:30 +02:00
"stau", # WHONET code
2022-08-28 10:31:50 +02:00
"STAU",
"staaur",
"S. aureus",
"S aureus",
2022-10-06 11:33:30 +02:00
"Sthafilokkockus aureus", # handles incorrect spelling
"Staphylococcus aureus (MRSA)",
"MRSA", # Methicillin Resistant S. aureus
"VISA", # Vancomycin Intermediate S. aureus
"VRSA", # Vancomycin Resistant S. aureus
115329001 # SNOMED CT code
))
2022-08-28 10:31:50 +02:00
)),
2022-10-06 11:33:30 +02:00
rep("B_STPHY_AURS", 11)
2022-08-28 10:31:50 +02:00
)
2021-05-15 21:36:22 +02:00
expect_identical(
as.character(
2022-08-28 10:31:50 +02:00
as.mo(c("EHEC", "EPEC", "EIEC", "STEC", "ATEC", "UPEC"))
),
rep("B_ESCHR_COLI", 6)
)
2021-05-15 21:36:22 +02:00
# unprevalent MO
expect_identical(
as.character(
2022-08-28 10:31:50 +02:00
as.mo(c(
"parnod",
"Paraburkholderia nodosa"
))
),
2022-12-20 22:41:39 +01:00
rep("B_PRBRK_NODS", 2)
2022-08-28 10:31:50 +02:00
)
2021-05-15 21:36:22 +02:00
# empty values
expect_identical(as.character(as.mo(c("", " ", NA, NaN))), rep(NA_character_, 4))
expect_identical(as.character(as.mo(" ")), NA_character_)
# too few characters
expect_warning(as.mo("ab"))
2023-02-12 17:10:48 +01:00
expect_identical(
2022-12-17 14:31:33 +01:00
suppressWarnings(as.character(as.mo(c("Qq species", "", "MRSA", "K. pneu rhino", "esco")))),
c("UNKNOWN", NA_character_, "B_STPHY_AURS", "B_KLBSL_PNMN_RHNS", "B_ESCHR_COLI")
2022-08-28 10:31:50 +02:00
)
2021-05-15 21:36:22 +02:00
# check for Becker classification
2022-08-28 10:31:50 +02:00
expect_identical(as.character(as.mo("S. epidermidis", Becker = FALSE)), "B_STPHY_EPDR")
expect_identical(as.character(as.mo("S. epidermidis", Becker = TRUE)), "B_STPHY_CONS")
expect_identical(as.character(as.mo("STAEPI", Becker = TRUE)), "B_STPHY_CONS")
2021-05-15 21:36:22 +02:00
expect_identical(as.character(as.mo("Sta intermedius", Becker = FALSE)), "B_STPHY_INTR")
2022-08-28 10:31:50 +02:00
expect_identical(as.character(as.mo("Sta intermedius", Becker = TRUE)), "B_STPHY_COPS")
expect_identical(as.character(as.mo("STAINT", Becker = TRUE)), "B_STPHY_COPS")
2021-05-15 21:36:22 +02:00
# aureus must only be influenced if Becker = "all"
expect_identical(as.character(as.mo("STAAUR", Becker = FALSE)), "B_STPHY_AURS")
2022-08-28 10:31:50 +02:00
expect_identical(as.character(as.mo("STAAUR", Becker = TRUE)), "B_STPHY_AURS")
2021-05-15 21:36:22 +02:00
expect_identical(as.character(as.mo("STAAUR", Becker = "all")), "B_STPHY_COPS")
# check for Lancefield classification
2022-08-28 10:31:50 +02:00
expect_identical(as.character(as.mo("S. pyogenes", Lancefield = FALSE)), "B_STRPT_PYGN")
expect_identical(as.character(as.mo("S. pyogenes", Lancefield = TRUE)), "B_STRPT_GRPA")
expect_identical(as.character(as.mo("STCPYO", Lancefield = TRUE)), "B_STRPT_GRPA") # group A
expect_identical(as.character(as.mo("S. agalactiae", Lancefield = FALSE)), "B_STRPT_AGLC")
expect_identical(as.character(as.mo("S. agalactiae", Lancefield = TRUE)), "B_STRPT_GRPB") # group B
2021-05-15 21:36:22 +02:00
expect_identical(as.character(suppressWarnings(as.mo("estreptococos grupo B"))), "B_STRPT_GRPB")
2022-10-05 09:12:22 +02:00
expect_identical(as.character(as.mo("S. equi", Lancefield = FALSE)), "B_STRPT_EQUI")
expect_identical(as.character(as.mo("S. equi", Lancefield = TRUE)), "B_STRPT_GRPC") # group C
2021-05-15 21:36:22 +02:00
# Enterococci must only be influenced if Lancefield = "all"
2022-08-28 10:31:50 +02:00
expect_identical(as.character(as.mo("E. faecium", Lancefield = FALSE)), "B_ENTRC_FACM")
expect_identical(as.character(as.mo("E. faecium", Lancefield = TRUE)), "B_ENTRC_FACM")
expect_identical(as.character(as.mo("E. faecium", Lancefield = "all")), "B_STRPT_GRPD") # group D
expect_identical(as.character(as.mo("S. anginosus", Lancefield = FALSE)), "B_STRPT_ANGN")
expect_identical(as.character(as.mo("S. anginosus", Lancefield = TRUE)), "B_STRPT_GRPF") # group F
expect_identical(as.character(as.mo("S. sanguinis", Lancefield = FALSE)), "B_STRPT_SNGN")
expect_identical(as.character(as.mo("S. sanguinis", Lancefield = TRUE)), "B_STRPT_GRPH") # group H
expect_identical(as.character(as.mo("S. salivarius", Lancefield = FALSE)), "B_STRPT_SLVR")
expect_identical(as.character(as.mo("S. salivarius", Lancefield = TRUE)), "B_STRPT_GRPK") # group K
2021-05-15 21:36:22 +02:00
2021-10-05 09:58:08 +02:00
if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0")) {
2021-05-15 21:36:22 +02:00
# select with one column
expect_identical(
2022-08-27 20:49:37 +02:00
example_isolates %>%
slice(1:10) %>%
2021-05-15 21:36:22 +02:00
left_join_microorganisms() %>%
select(genus) %>%
as.mo() %>%
as.character(),
2022-08-28 10:31:50 +02:00
c(
"B_ESCHR", "B_ESCHR", "B_STPHY", "B_STPHY", "B_STPHY",
"B_STPHY", "B_STPHY", "B_STPHY", "B_STPHY", "B_STPHY"
)
)
2021-05-15 21:36:22 +02:00
# select with two columns
expect_identical(
2022-08-27 20:49:37 +02:00
example_isolates %>%
slice(1:10) %>%
2021-05-15 21:36:22 +02:00
pull(mo),
2022-08-27 20:49:37 +02:00
example_isolates %>%
slice(1:10) %>%
2021-05-15 21:36:22 +02:00
left_join_microorganisms() %>%
select(genus, species) %>%
2022-08-28 10:31:50 +02:00
as.mo()
)
2021-05-15 21:36:22 +02:00
# too many columns
expect_error(example_isolates %>% select(1:3) %>% as.mo())
2022-08-28 10:31:50 +02:00
2021-05-15 21:36:22 +02:00
# test pull
2022-08-28 10:31:50 +02:00
expect_equal(
nrow(example_isolates %>% mutate(mo = as.mo(mo))),
2000
)
2021-05-15 21:36:22 +02:00
expect_true(example_isolates %>% pull(mo) %>% is.mo())
}
# print
expect_stdout(print(as.mo(c("B_ESCHR_COLI", NA))))
# test data.frame
2022-08-28 10:31:50 +02:00
expect_equal(
nrow(data.frame(test = as.mo("B_ESCHR_COLI"))),
1
)
2021-05-15 21:36:22 +02:00
# check empty values
2022-08-28 10:31:50 +02:00
expect_equal(
2022-10-05 09:12:22 +02:00
as.character(as.mo("")),
2022-08-28 10:31:50 +02:00
NA_character_
)
2021-05-15 21:36:22 +02:00
# check less prevalent MOs
2022-10-05 09:12:22 +02:00
expect_equal(as.character(as.mo("Actinosynnema pretiosum auranticum")), "B_ANNMA_PRTS_ARNT")
2022-12-20 22:18:50 +01:00
# expect_equal(as.character(as.mo("Actinosynnema preti aura")), "B_ANNMA_PRTS_ARNT")
# expect_equal(as.character(as.mo("A pre aur")), "B_ANNMA_PRTS_ARNT")
2022-10-05 09:12:22 +02:00
expect_equal(as.character(as.mo("Actinosynnema pretiosum")), "B_ANNMA_PRTS")
expect_equal(as.character(as.mo("Actinosynnema")), "B_ANNMA")
expect_equal(as.character(as.mo(" B_ANNMA_PRTS ")), "B_ANNMA_PRTS")
2021-05-15 21:36:22 +02:00
# check old names
expect_equal(suppressMessages(as.character(as.mo("Escherichia blattae"))), "B_SHMWL_BLTT")
expect_equal(suppressMessages(as.character(as.mo(c("E. coli", "Chlamydo psittaci")))), c("B_ESCHR_COLI", "B_CHLMY_PSTT"))
2022-03-15 17:35:02 +01:00
expect_equal(suppressMessages(mo_name("eubcom")), "Clostridium combesii")
2021-05-15 21:36:22 +02:00
# predefined reference_df
2022-08-28 10:31:50 +02:00
expect_equal(
as.character(as.mo("TestingOwnID",
reference_df = data.frame(mycol = "TestingOwnID", mo = "B_ESCHR_COLI")
)),
"B_ESCHR_COLI"
)
expect_equal(
as.character(as.mo(c("TestingOwnID", "E. coli"),
reference_df = data.frame(mycol = "TestingOwnID", mo = "B_ESCHR_COLI")
)),
c("B_ESCHR_COLI", "B_ESCHR_COLI")
)
2022-12-20 22:18:50 +01:00
# expect_warning(as.mo("TestingOwnID", reference_df = NULL))
2021-05-15 21:36:22 +02:00
expect_error(as.mo("E. coli", reference_df = data.frame(mycol = "TestingOwnID")))
# combination of existing mo and other code
2022-08-28 10:31:50 +02:00
expect_identical(
2022-10-05 09:12:22 +02:00
suppressWarnings(as.character(as.mo(c("B_ESCHR_COL", "ESCCOL")))),
2022-08-28 10:31:50 +02:00
c("B_ESCHR_COLI", "B_ESCHR_COLI")
)
2021-05-15 21:36:22 +02:00
# from different sources
2022-08-28 10:31:50 +02:00
expect_equal(
as.character(as.mo(
c("PRTMIR", "bclcer", "B_ESCHR_COLI")
)),
c("B_PROTS_MRBL", "B_BCLLS_CERS", "B_ESCHR_COLI")
)
2021-05-15 21:36:22 +02:00
# hard to find
2022-08-28 10:31:50 +02:00
expect_equal(
as.character(suppressMessages(as.mo(
c(
"Microbacterium paraoxidans",
"Streptococcus suis (bovis gr)",
"Raoultella (here some text) terrigena"
)
))),
c("B_MCRBC_PRXY", "B_STRPT_SUIS", "B_RLTLL_TRRG")
)
2021-05-15 21:36:22 +02:00
expect_stdout(print(mo_uncertainties()))
2022-10-05 09:12:22 +02:00
x <- as.mo("Sta. aur")
2021-05-15 21:36:22 +02:00
# many hits
expect_stdout(print(mo_uncertainties()))
# no viruses
2022-10-19 06:59:36 +02:00
expect_equal(suppressWarnings(as.mo("Virus")), as.mo("UNKNOWN"))
2021-05-15 21:36:22 +02:00
# summary
expect_equal(length(summary(example_isolates$mo)), 6)
# WHONET codes and NA/NaN
2022-08-28 10:31:50 +02:00
expect_equal(
as.character(as.mo(c("xxx", "na", "nan"), debug = TRUE)),
rep(NA_character_, 3)
)
2021-05-15 21:36:22 +02:00
expect_equal(as.character(as.mo("con")), "UNKNOWN")
expect_equal(as.character(as.mo("xxx")), NA_character_)
expect_equal(as.character(as.mo(c("xxx", "con", "eco"))), c(NA_character_, "UNKNOWN", "B_ESCHR_COLI"))
2022-08-28 10:31:50 +02:00
expect_equal(
2022-10-19 11:47:57 +02:00
as.character(suppressWarnings(as.mo(c("other", "none", "unknown")))),
2022-08-28 10:31:50 +02:00
rep("UNKNOWN", 3)
)
2021-05-15 21:36:22 +02:00
# ..coccus
2022-08-28 10:31:50 +02:00
expect_equal(
as.character(as.mo(c("meningococ", "gonococ", "pneumococ"))),
c("B_NESSR_MNNG", "B_NESSR_GNRR", "B_STRPT_PNMN")
)
2021-05-15 21:36:22 +02:00
# yeasts and fungi
2022-08-28 10:31:50 +02:00
expect_equal(
suppressWarnings(as.character(as.mo(c("yeasts", "fungi")))),
c("F_YEAST", "F_FUNGUS")
)
2021-05-15 21:36:22 +02:00
2021-10-05 09:58:08 +02:00
if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0")) {
2021-05-15 21:36:22 +02:00
# print tibble
expect_stdout(print(tibble(mo = as.mo("B_ESCHR_COLI"))))
}
# assigning and subsetting
x <- example_isolates$mo
expect_inherits(x[1], "mo")
expect_inherits(x[[1]], "mo")
expect_inherits(c(x[1], x[9]), "mo")
expect_warning(x[1] <- "invalid code")
expect_warning(x[[1]] <- "invalid code")
expect_warning(c(x[1], "test"))
# ignoring patterns
2023-02-12 17:10:48 +01:00
expect_identical(
2022-08-28 10:31:50 +02:00
as.character(as.mo(c("E. coli", "E. coli ignorethis"), ignore_pattern = "this")),
c("B_ESCHR_COLI", NA)
)
2021-05-15 21:36:22 +02:00
# frequency tables
2021-05-21 20:20:51 +02:00
if (AMR:::pkg_is_available("cleaner")) {
2021-05-15 21:36:22 +02:00
expect_inherits(cleaner::freq(example_isolates$mo), "freq")
}