diff --git a/.github/workflows/check.yaml b/.github/workflows/check.yaml index 5fd4f1930..1189e961d 100644 --- a/.github/workflows/check.yaml +++ b/.github/workflows/check.yaml @@ -65,10 +65,10 @@ jobs: - {os: ubuntu-20.04, r: '3.6', allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"} - {os: ubuntu-20.04, r: '3.5', allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"} - {os: ubuntu-20.04, r: '3.4', allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"} - - {os: ubuntu-20.04, r: '3.3', allowfail: true, rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"} + - {os: ubuntu-20.04, r: '3.3', allowfail: false rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"} # - {os: ubuntu-20.04, r: '3.2', allowfail: true, rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"} # - {os: ubuntu-20.04, r: '3.1', allowfail: true, rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"} - - {os: ubuntu-20.04, r: '3.0', allowfail: true, rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"} + - {os: ubuntu-20.04, r: '3.0', allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/focal/latest"} - {os: ubuntu-16.04, r: 'devel', allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"} - {os: ubuntu-16.04, r: 'release', allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"} @@ -77,10 +77,10 @@ jobs: - {os: ubuntu-16.04, r: '3.6', allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"} - {os: ubuntu-16.04, r: '3.5', allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"} - {os: ubuntu-16.04, r: '3.4', allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"} - - {os: ubuntu-16.04, r: '3.3', allowfail: true, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"} + - {os: ubuntu-16.04, r: '3.3', allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"} # - {os: ubuntu-16.04, r: '3.2', allowfail: true, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"} # - {os: ubuntu-16.04, r: '3.1', allowfail: true, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"} - - {os: ubuntu-16.04, r: '3.0', allowfail: true, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"} + - {os: ubuntu-16.04, r: '3.0', allowfail: false, rspm: "https://packagemanager.rstudio.com/cran/__linux__/xenial/latest"} env: R_REMOTES_NO_ERRORS_FROM_WARNINGS: true diff --git a/DESCRIPTION b/DESCRIPTION index 0e66d73d5..aad0d6a50 100644 --- a/DESCRIPTION +++ b/DESCRIPTION @@ -1,6 +1,6 @@ Package: AMR -Version: 1.6.0.9002 -Date: 2021-04-12 +Version: 1.6.0.9003 +Date: 2021-04-16 Title: Antimicrobial Resistance Data Analysis Authors@R: c( person(role = c("aut", "cre"), diff --git a/NEWS.md b/NEWS.md index 1edb7be2f..680681da9 100755 --- a/NEWS.md +++ b/NEWS.md @@ -1,5 +1,5 @@ -# AMR 1.6.0.9002 -## Last updated: 12 April 2021 +# AMR 1.6.0.9003 +## Last updated: 16 April 2021 ### New * Function `custom_eucast_rules()` that brings support for custom AMR rules in `eucast_rules()` @@ -13,6 +13,7 @@ * Fix for minor translation errors * Printing of microbial codes in a `data.frame` or `tibble` now gives a warning if the data contains old microbial codes (from a previous AMR package version) * `first_isolate()` can now take a vector of values for `col_keyantibiotics` and can have an episode length of `Inf` +* `like()` (and `%like%`) now checks if `pattern` is a *valid* regular expression * Fixed an installation error on R-3.0 # AMR 1.6.0 diff --git a/R/aa_helper_functions.R b/R/aa_helper_functions.R index df9258dc2..d52753056 100755 --- a/R/aa_helper_functions.R +++ b/R/aa_helper_functions.R @@ -211,10 +211,20 @@ search_type_in_df <- function(x, type, info = TRUE) { found } -is_possibly_regex <- function(x) { - tryCatch(vapply(FUN.VALUE = character(1), strsplit(x, ""), - function(y) any(y %in% c("$", "(", ")", "*", "+", "-", ".", "?", "[", "]", "^", "{", "|", "}", "\\"), na.rm = TRUE)), - error = function(e) rep(TRUE, length(x))) +is_valid_regex <- function(x) { + regex_at_all <- tryCatch(vapply(FUN.VALUE = logical(1), + X = strsplit(x, ""), + FUN = function(y) any(y %in% c("$", "(", ")", "*", "+", "-", + ".", "?", "[", "]", "^", "{", + "|", "}", "\\"), + na.rm = TRUE)), + error = function(e) rep(TRUE, length(x))) + regex_valid <- vapply(FUN.VALUE = logical(1), + X = c("[.", "."), + FUN = function(y) !"try-error" %in% class(try(grepl(y, ""), + silent = TRUE)), + USE.NAMES = FALSE) + regex_at_all & regex_valid } stop_ifnot_installed <- function(package) { diff --git a/R/like.R b/R/like.R index 8e82984ec..edd135d1d 100755 --- a/R/like.R +++ b/R/like.R @@ -28,21 +28,21 @@ #' Convenient wrapper around [grepl()] to match a pattern: `x %like% pattern`. It always returns a [`logical`] vector and is always case-insensitive (use `x %like_case% pattern` for case-sensitive matching). Also, `pattern` can be as long as `x` to compare items of each index in both vectors, or they both can have the same length to iterate over all cases. #' @inheritSection lifecycle Stable Lifecycle #' @param x a character vector where matches are sought, or an object which can be coerced by [as.character()] to a character vector. -#' @param pattern a character string containing a regular expression (or [character] string for `fixed = TRUE`) to be matched in the given character vector. Coerced by [as.character()] to a character string if possible. If a [character] vector of length 2 or more is supplied, the first element is used with a warning. +#' @param pattern a character vector containing regular expressions (or a [character] string for `fixed = TRUE`) to be matched in the given character vector. Coerced by [as.character()] to a character string if possible. #' @param ignore.case if `FALSE`, the pattern matching is *case sensitive* and if `TRUE`, case is ignored during matching. #' @return A [logical] vector #' @name like #' @rdname like #' @export #' @details -#' The `%like%` function: +#' This `%like%` function: #' * Is case-insensitive (use `%like_case%` for case-sensitive matching) #' * Supports multiple patterns -#' * Checks if `pattern` is a regular expression and sets `fixed = TRUE` if not, to greatly improve speed +#' * Checks if `pattern` is a valid regular expression and sets `fixed = TRUE` if not, to greatly improve speed (vectorised over `pattern`) #' * Always uses compatibility with Perl unless `fixed = TRUE`, to greatly improve speed #' #' Using RStudio? The text `%like%` can also be directly inserted in your code from the Addins menu and can have its own Keyboard Shortcut like `Ctrl+Shift+L` or `Cmd+Shift+L` (see `Tools` > `Modify Keyboard Shortcuts...`). -#' @source Idea from the [`like` function from the `data.table` package](https://github.com/Rdatatable/data.table/blob/ec1259af1bf13fc0c96a1d3f9e84d55d8106a9a4/R/like.R) +#' @source Idea from the [`like` function from the `data.table` package](https://github.com/Rdatatable/data.table/blob/ec1259af1bf13fc0c96a1d3f9e84d55d8106a9a4/R/like.R), although altered as explained in *Details*. #' @seealso [grepl()] #' @inheritSection AMR Read more on Our Website! #' @examples @@ -79,9 +79,10 @@ like <- function(x, pattern, ignore.case = TRUE) { if (all(is.na(x))) { return(rep(FALSE, length(x))) } - - # set to fixed if no regex found - fixed <- !any(is_possibly_regex(pattern)) + + # set to fixed if no valid regex (vectorised) + fixed <- !is_valid_regex(pattern) + if (ignore.case == TRUE) { # set here, otherwise if fixed = TRUE, this warning will be thrown: argument `ignore.case = TRUE` will be ignored x <- tolower(x) @@ -91,7 +92,7 @@ like <- function(x, pattern, ignore.case = TRUE) { if (is.factor(x)) { x <- as.character(x) } - + if (length(pattern) == 1) { grepl(pattern, x, ignore.case = FALSE, fixed = fixed, perl = !fixed) } else { @@ -105,7 +106,9 @@ like <- function(x, pattern, ignore.case = TRUE) { mapply(FUN = grepl, x = x, pattern = pattern, - MoreArgs = list(ignore.case = FALSE, fixed = fixed, perl = !fixed), + fixed = fixed, + perl = !fixed, + MoreArgs = list(ignore.case = FALSE), SIMPLIFY = FALSE, USE.NAMES = FALSE) ) diff --git a/R/mo_matching_score.R b/R/mo_matching_score.R index 7d4d32c90..f3e2c356c 100755 --- a/R/mo_matching_score.R +++ b/R/mo_matching_score.R @@ -44,7 +44,7 @@ #' * \ifelse{html}{\out{pn is the human pathogenic prevalence group of n, as described below;}}{p_n is the human pathogenic prevalence group of \eqn{n}, as described below;} #' * \ifelse{html}{\out{kn is the taxonomic kingdom of n, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.}}{l_n is the taxonomic kingdom of \eqn{n}, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.} #' -#' The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. **Group 1** (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is *Enterococcus*, *Staphylococcus* or *Streptococcus*. This group consequently contains all common Gram-negative bacteria, such as *Pseudomonas* and *Legionella* and all species within the order Enterobacterales. **Group 2** consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is *Absidia*, *Acremonium*, *Actinotignum*, *Alternaria*, *Anaerosalibacter*, *Apophysomyces*, *Arachnia*, *Aspergillus*, *Aureobacterium*, *Aureobasidium*, *Bacteroides*, *Basidiobolus*, *Beauveria*, *Blastocystis*, *Branhamella*, *Calymmatobacterium*, *Candida*, *Capnocytophaga*, *Catabacter*, *Chaetomium*, *Chryseobacterium*, *Chryseomonas*, *Chrysonilia*, *Cladophialophora*, *Cladosporium*, *Conidiobolus*, *Cryptococcus*, *Curvularia*, *Exophiala*, *Exserohilum*, *Flavobacterium*, *Fonsecaea*, *Fusarium*, *Fusobacterium*, *Hendersonula*, *Hypomyces*, *Koserella*, *Lelliottia*, *Leptosphaeria*, *Leptotrichia*, *Malassezia*, *Malbranchea*, *Mortierella*, *Mucor*, *Mycocentrospora*, *Mycoplasma*, *Nectria*, *Ochroconis*, *Oidiodendron*, *Phoma*, *Piedraia*, *Pithomyces*, *Pityrosporum*, *Prevotella*, *Pseudallescheria*, *Rhizomucor*, *Rhizopus*, *Rhodotorula*, *Scolecobasidium*, *Scopulariopsis*, *Scytalidium*,*Sporobolomyces*, *Stachybotrys*, *Stomatococcus*, *Treponema*, *Trichoderma*, *Trichophyton*, *Trichosporon*, *Tritirachium* or *Ureaplasma*. **Group 3** consists of all other microorganisms. +#' The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. **Group 1** (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is *Enterococcus*, *Staphylococcus* or *Streptococcus*. This group consequently contains all common Gram-negative bacteria, such as *Pseudomonas* and *Legionella* and all species within the order Enterobacterales. **Group 2** consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is *Absidia*, *Acremonium*, *Actinotignum*, *Alternaria*, *Anaerosalibacter*, *Apophysomyces*, *Arachnia*, *Aspergillus*, *Aureobacterium*, *Aureobasidium*, *Bacteroides*, *Basidiobolus*, *Beauveria*, *Blastocystis*, *Branhamella*, *Calymmatobacterium*, *Candida*, *Capnocytophaga*, *Catabacter*, *Chaetomium*, *Chryseobacterium*, *Chryseomonas*, *Chrysonilia*, *Cladophialophora*, *Cladosporium*, *Conidiobolus*, *Cryptococcus*, *Curvularia*, *Exophiala*, *Exserohilum*, *Flavobacterium*, *Fonsecaea*, *Fusarium*, *Fusobacterium*, *Hendersonula*, *Hypomyces*, *Koserella*, *Lelliottia*, *Leptosphaeria*, *Leptotrichia*, *Malassezia*, *Malbranchea*, *Mortierella*, *Mucor*, *Mycocentrospora*, *Mycoplasma*, *Nectria*, *Ochroconis*, *Oidiodendron*, *Phoma*, *Piedraia*, *Pithomyces*, *Pityrosporum*, *Prevotella*, *Pseudallescheria*, *Rhizomucor*, *Rhizopus*, *Rhodotorula*, *Scolecobasidium*, *Scopulariopsis*, *Scytalidium*, *Sporobolomyces*, *Stachybotrys*, *Stomatococcus*, *Treponema*, *Trichoderma*, *Trichophyton*, *Trichosporon*, *Tritirachium* or *Ureaplasma*. **Group 3** consists of all other microorganisms. #' #' All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., `"E. coli"` will return the microbial ID of *Escherichia coli* (\eqn{m = `r round(mo_matching_score("E. coli", "Escherichia coli"), 3)`}, a highly prevalent microorganism found in humans) and not *Entamoeba coli* (\eqn{m = `r round(mo_matching_score("E. coli", "Entamoeba coli"), 3)`}, a less prevalent microorganism in humans), although the latter would alphabetically come first. #' @export diff --git a/R/sysdata.rda b/R/sysdata.rda index 7a9cd5ec8..58481e537 100644 Binary files a/R/sysdata.rda and b/R/sysdata.rda differ diff --git a/data-raw/AMR_latest.tar.gz b/data-raw/AMR_latest.tar.gz index e79727c35..7f046d330 100644 Binary files a/data-raw/AMR_latest.tar.gz and b/data-raw/AMR_latest.tar.gz differ diff --git a/docs/404.html b/docs/404.html index 46d2da89f..f45fb96e1 100644 --- a/docs/404.html +++ b/docs/404.html @@ -81,7 +81,7 @@ AMR (for R) - 1.6.0.9002 + 1.6.0.9003 diff --git a/docs/LICENSE-text.html b/docs/LICENSE-text.html index a4bcef621..85ccaa279 100644 --- a/docs/LICENSE-text.html +++ b/docs/LICENSE-text.html @@ -81,7 +81,7 @@ AMR (for R) - 1.6.0.9002 + 1.6.0.9003 diff --git a/docs/articles/index.html b/docs/articles/index.html index 0607f7623..9466b8146 100644 --- a/docs/articles/index.html +++ b/docs/articles/index.html @@ -81,7 +81,7 @@ AMR (for R) - 1.6.0.9002 + 1.6.0.9003 diff --git a/docs/authors.html b/docs/authors.html index ecefc12f9..42946a3d9 100644 --- a/docs/authors.html +++ b/docs/authors.html @@ -81,7 +81,7 @@ AMR (for R) - 1.6.0.9002 + 1.6.0.9003 @@ -236,13 +236,13 @@ Source: inst/CITATION -

Berends MS, Luz CF et al. (2019). AMR - An R Package for Working with Antimicrobial Resistance Data. bioRxiv, https://doi.org/10.1101/810622

+

Berends MS, Luz CF et al. (2021). AMR - An R Package for Working with Antimicrobial Resistance Data. bioRxiv, https://doi.org/10.1101/810622

@Article{,
   title = {AMR - An R Package for Working with Antimicrobial Resistance Data},
   author = {M S Berends and C F Luz and A W Friedrich and B N M Sinha and C J Albers and C Glasner},
   journal = {bioRxiv},
   publisher = {Cold Spring Harbor Laboratory},
-  year = {2019},
+  year = {2021},
   url = {https://doi.org/10.1101/810622},
 }
diff --git a/docs/index.html b/docs/index.html index e6c0f4aa7..1cbb3040e 100644 --- a/docs/index.html +++ b/docs/index.html @@ -42,7 +42,7 @@ AMR (for R) - 1.6.0.9002 + 1.6.0.9003 diff --git a/docs/news/index.html b/docs/news/index.html index 886187a98..1ceaf9140 100644 --- a/docs/news/index.html +++ b/docs/news/index.html @@ -81,7 +81,7 @@ AMR (for R) - 1.6.0.9002 + 1.6.0.9003 @@ -236,13 +236,13 @@ Source: NEWS.md -
-

-AMR 1.6.0.9002 Unreleased +
+

+AMR 1.6.0.9003 Unreleased

-
+

-Last updated: 12 April 2021 +Last updated: 16 April 2021

@@ -270,6 +270,8 @@
  • first_isolate() can now take a vector of values for col_keyantibiotics and can have an episode length of Inf
    • +
  • +like() (and %like%) now checks if pattern is a valid regular expression
  • Fixed an installation error on R-3.0

    • diff --git a/docs/pkgdown.yml b/docs/pkgdown.yml index 910f15644..30a6f11a3 100644 --- a/docs/pkgdown.yml +++ b/docs/pkgdown.yml @@ -12,7 +12,7 @@ articles: datasets: datasets.html resistance_predict: resistance_predict.html welcome_to_AMR: welcome_to_AMR.html -last_built: 2021-04-12T12:24Z +last_built: 2021-04-16T09:40Z urls: reference: https://msberends.github.io/AMR//reference article: https://msberends.github.io/AMR//articles diff --git a/docs/reference/as.mo.html b/docs/reference/as.mo.html index 4d14a013e..1b34e620f 100644 --- a/docs/reference/as.mo.html +++ b/docs/reference/as.mo.html @@ -82,7 +82,7 @@ AMR (for R) - 1.6.0 + 1.6.0.9003
    @@ -399,7 +399,7 @@ The lifecycle of this function is stable

    kn is the taxonomic kingdom of n, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.

    -

    The grouping into human pathogenic prevalence (\(p\)) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. Group 1 (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is Enterococcus, Staphylococcus or Streptococcus. This group consequently contains all common Gram-negative bacteria, such as Pseudomonas and Legionella and all species within the order Enterobacterales. Group 2 consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is Absidia, Acremonium, Actinotignum, Alternaria, Anaerosalibacter, Apophysomyces, Arachnia, Aspergillus, Aureobacterium, Aureobasidium, Bacteroides, Basidiobolus, Beauveria, Blastocystis, Branhamella, Calymmatobacterium, Candida, Capnocytophaga, Catabacter, Chaetomium, Chryseobacterium, Chryseomonas, Chrysonilia, Cladophialophora, Cladosporium, Conidiobolus, Cryptococcus, Curvularia, Exophiala, Exserohilum, Flavobacterium, Fonsecaea, Fusarium, Fusobacterium, Hendersonula, Hypomyces, Koserella, Lelliottia, Leptosphaeria, Leptotrichia, Malassezia, Malbranchea, Mortierella, Mucor, Mycocentrospora, Mycoplasma, Nectria, Ochroconis, Oidiodendron, Phoma, Piedraia, Pithomyces, Pityrosporum, Prevotella, Pseudallescheria, Rhizomucor, Rhizopus, Rhodotorula, Scolecobasidium, Scopulariopsis, Scytalidium,Sporobolomyces, Stachybotrys, Stomatococcus, Treponema, Trichoderma, Trichophyton, Trichosporon, Tritirachium or Ureaplasma. Group 3 consists of all other microorganisms.

    +

    The grouping into human pathogenic prevalence (\(p\)) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. Group 1 (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is Enterococcus, Staphylococcus or Streptococcus. This group consequently contains all common Gram-negative bacteria, such as Pseudomonas and Legionella and all species within the order Enterobacterales. Group 2 consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is Absidia, Acremonium, Actinotignum, Alternaria, Anaerosalibacter, Apophysomyces, Arachnia, Aspergillus, Aureobacterium, Aureobasidium, Bacteroides, Basidiobolus, Beauveria, Blastocystis, Branhamella, Calymmatobacterium, Candida, Capnocytophaga, Catabacter, Chaetomium, Chryseobacterium, Chryseomonas, Chrysonilia, Cladophialophora, Cladosporium, Conidiobolus, Cryptococcus, Curvularia, Exophiala, Exserohilum, Flavobacterium, Fonsecaea, Fusarium, Fusobacterium, Hendersonula, Hypomyces, Koserella, Lelliottia, Leptosphaeria, Leptotrichia, Malassezia, Malbranchea, Mortierella, Mucor, Mycocentrospora, Mycoplasma, Nectria, Ochroconis, Oidiodendron, Phoma, Piedraia, Pithomyces, Pityrosporum, Prevotella, Pseudallescheria, Rhizomucor, Rhizopus, Rhodotorula, Scolecobasidium, Scopulariopsis, Scytalidium, Sporobolomyces, Stachybotrys, Stomatococcus, Treponema, Trichoderma, Trichophyton, Trichosporon, Tritirachium or Ureaplasma. Group 3 consists of all other microorganisms.

    All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., "E. coli" will return the microbial ID of Escherichia coli (\(m = 0.688\), a highly prevalent microorganism found in humans) and not Entamoeba coli (\(m = 0.079\), a less prevalent microorganism in humans), although the latter would alphabetically come first.

    Catalogue of Life

    diff --git a/docs/reference/first_isolate.html b/docs/reference/first_isolate.html index fc71e23b0..64e276eaa 100644 --- a/docs/reference/first_isolate.html +++ b/docs/reference/first_isolate.html @@ -82,7 +82,7 @@ AMR (for R) - 1.6.0.9001 + 1.6.0.9003
    diff --git a/docs/reference/get_episode.html b/docs/reference/get_episode.html index 72becabc2..f3916185c 100644 --- a/docs/reference/get_episode.html +++ b/docs/reference/get_episode.html @@ -82,7 +82,7 @@ AMR (for R) - 1.6.0.9001 + 1.6.0.9003
    diff --git a/docs/reference/index.html b/docs/reference/index.html index 1d3b900fc..5ce5bed9c 100644 --- a/docs/reference/index.html +++ b/docs/reference/index.html @@ -81,7 +81,7 @@ AMR (for R) - 1.6.0.9002 + 1.6.0.9003

    diff --git a/docs/reference/like.html b/docs/reference/like.html index 32d4639f4..affe9389d 100644 --- a/docs/reference/like.html +++ b/docs/reference/like.html @@ -82,7 +82,7 @@ AMR (for R) - 1.6.0.9001 + 1.6.0.9003 @@ -257,7 +257,7 @@ pattern -

    a character string containing a regular expression (or character string for fixed = TRUE) to be matched in the given character vector. Coerced by as.character() to a character string if possible. If a character vector of length 2 or more is supplied, the first element is used with a warning.

    +

    a character vector containing regular expressions (or a character string for fixed = TRUE) to be matched in the given character vector. Coerced by as.character() to a character string if possible.

    ignore.case @@ -267,16 +267,16 @@

    Source

    -

    Idea from the like function from the data.table package

    +

    Idea from the like function from the data.table package, although altered as explained in Details.

    Value

    A logical vector

    Details

    -

    The %like% function:

    -

    The grouping into human pathogenic prevalence (\(p\)) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. Group 1 (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is Enterococcus, Staphylococcus or Streptococcus. This group consequently contains all common Gram-negative bacteria, such as Pseudomonas and Legionella and all species within the order Enterobacterales. Group 2 consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is Absidia, Acremonium, Actinotignum, Alternaria, Anaerosalibacter, Apophysomyces, Arachnia, Aspergillus, Aureobacterium, Aureobasidium, Bacteroides, Basidiobolus, Beauveria, Blastocystis, Branhamella, Calymmatobacterium, Candida, Capnocytophaga, Catabacter, Chaetomium, Chryseobacterium, Chryseomonas, Chrysonilia, Cladophialophora, Cladosporium, Conidiobolus, Cryptococcus, Curvularia, Exophiala, Exserohilum, Flavobacterium, Fonsecaea, Fusarium, Fusobacterium, Hendersonula, Hypomyces, Koserella, Lelliottia, Leptosphaeria, Leptotrichia, Malassezia, Malbranchea, Mortierella, Mucor, Mycocentrospora, Mycoplasma, Nectria, Ochroconis, Oidiodendron, Phoma, Piedraia, Pithomyces, Pityrosporum, Prevotella, Pseudallescheria, Rhizomucor, Rhizopus, Rhodotorula, Scolecobasidium, Scopulariopsis, Scytalidium,Sporobolomyces, Stachybotrys, Stomatococcus, Treponema, Trichoderma, Trichophyton, Trichosporon, Tritirachium or Ureaplasma. Group 3 consists of all other microorganisms.

    +

    The grouping into human pathogenic prevalence (\(p\)) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. Group 1 (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is Enterococcus, Staphylococcus or Streptococcus. This group consequently contains all common Gram-negative bacteria, such as Pseudomonas and Legionella and all species within the order Enterobacterales. Group 2 consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is Absidia, Acremonium, Actinotignum, Alternaria, Anaerosalibacter, Apophysomyces, Arachnia, Aspergillus, Aureobacterium, Aureobasidium, Bacteroides, Basidiobolus, Beauveria, Blastocystis, Branhamella, Calymmatobacterium, Candida, Capnocytophaga, Catabacter, Chaetomium, Chryseobacterium, Chryseomonas, Chrysonilia, Cladophialophora, Cladosporium, Conidiobolus, Cryptococcus, Curvularia, Exophiala, Exserohilum, Flavobacterium, Fonsecaea, Fusarium, Fusobacterium, Hendersonula, Hypomyces, Koserella, Lelliottia, Leptosphaeria, Leptotrichia, Malassezia, Malbranchea, Mortierella, Mucor, Mycocentrospora, Mycoplasma, Nectria, Ochroconis, Oidiodendron, Phoma, Piedraia, Pithomyces, Pityrosporum, Prevotella, Pseudallescheria, Rhizomucor, Rhizopus, Rhodotorula, Scolecobasidium, Scopulariopsis, Scytalidium, Sporobolomyces, Stachybotrys, Stomatococcus, Treponema, Trichoderma, Trichophyton, Trichosporon, Tritirachium or Ureaplasma. Group 3 consists of all other microorganisms.

    All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., "E. coli" will return the microbial ID of Escherichia coli (\(m = 0.688\), a highly prevalent microorganism found in humans) and not Entamoeba coli (\(m = 0.079\), a less prevalent microorganism in humans), although the latter would alphabetically come first.

    Stable Lifecycle

    diff --git a/docs/reference/mo_property.html b/docs/reference/mo_property.html index 43e826018..3e824d6a8 100644 --- a/docs/reference/mo_property.html +++ b/docs/reference/mo_property.html @@ -82,7 +82,7 @@ AMR (for R) - 1.6.0 + 1.6.0.9003 @@ -376,7 +376,7 @@ The lifecycle of this function is stable

    kn is the taxonomic kingdom of n, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.

    -

    The grouping into human pathogenic prevalence (\(p\)) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. Group 1 (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is Enterococcus, Staphylococcus or Streptococcus. This group consequently contains all common Gram-negative bacteria, such as Pseudomonas and Legionella and all species within the order Enterobacterales. Group 2 consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is Absidia, Acremonium, Actinotignum, Alternaria, Anaerosalibacter, Apophysomyces, Arachnia, Aspergillus, Aureobacterium, Aureobasidium, Bacteroides, Basidiobolus, Beauveria, Blastocystis, Branhamella, Calymmatobacterium, Candida, Capnocytophaga, Catabacter, Chaetomium, Chryseobacterium, Chryseomonas, Chrysonilia, Cladophialophora, Cladosporium, Conidiobolus, Cryptococcus, Curvularia, Exophiala, Exserohilum, Flavobacterium, Fonsecaea, Fusarium, Fusobacterium, Hendersonula, Hypomyces, Koserella, Lelliottia, Leptosphaeria, Leptotrichia, Malassezia, Malbranchea, Mortierella, Mucor, Mycocentrospora, Mycoplasma, Nectria, Ochroconis, Oidiodendron, Phoma, Piedraia, Pithomyces, Pityrosporum, Prevotella, Pseudallescheria, Rhizomucor, Rhizopus, Rhodotorula, Scolecobasidium, Scopulariopsis, Scytalidium,Sporobolomyces, Stachybotrys, Stomatococcus, Treponema, Trichoderma, Trichophyton, Trichosporon, Tritirachium or Ureaplasma. Group 3 consists of all other microorganisms.

    +

    The grouping into human pathogenic prevalence (\(p\)) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. Group 1 (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is Enterococcus, Staphylococcus or Streptococcus. This group consequently contains all common Gram-negative bacteria, such as Pseudomonas and Legionella and all species within the order Enterobacterales. Group 2 consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is Absidia, Acremonium, Actinotignum, Alternaria, Anaerosalibacter, Apophysomyces, Arachnia, Aspergillus, Aureobacterium, Aureobasidium, Bacteroides, Basidiobolus, Beauveria, Blastocystis, Branhamella, Calymmatobacterium, Candida, Capnocytophaga, Catabacter, Chaetomium, Chryseobacterium, Chryseomonas, Chrysonilia, Cladophialophora, Cladosporium, Conidiobolus, Cryptococcus, Curvularia, Exophiala, Exserohilum, Flavobacterium, Fonsecaea, Fusarium, Fusobacterium, Hendersonula, Hypomyces, Koserella, Lelliottia, Leptosphaeria, Leptotrichia, Malassezia, Malbranchea, Mortierella, Mucor, Mycocentrospora, Mycoplasma, Nectria, Ochroconis, Oidiodendron, Phoma, Piedraia, Pithomyces, Pityrosporum, Prevotella, Pseudallescheria, Rhizomucor, Rhizopus, Rhodotorula, Scolecobasidium, Scopulariopsis, Scytalidium, Sporobolomyces, Stachybotrys, Stomatococcus, Treponema, Trichoderma, Trichophyton, Trichosporon, Tritirachium or Ureaplasma. Group 3 consists of all other microorganisms.

    All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., "E. coli" will return the microbial ID of Escherichia coli (\(m = 0.688\), a highly prevalent microorganism found in humans) and not Entamoeba coli (\(m = 0.079\), a less prevalent microorganism in humans), although the latter would alphabetically come first.

    Catalogue of Life

    diff --git a/docs/survey.html b/docs/survey.html index c0da4272f..9a6bc3057 100644 --- a/docs/survey.html +++ b/docs/survey.html @@ -81,7 +81,7 @@ AMR (for R) - 1.6.0.9002 + 1.6.0.9003 diff --git a/inst/CITATION b/inst/CITATION index 66ddc1d08..e24418a17 100644 --- a/inst/CITATION +++ b/inst/CITATION @@ -6,9 +6,9 @@ citEntry( author = "M S Berends and C F Luz and A W Friedrich and B N M Sinha and C J Albers and C Glasner", journal = "bioRxiv", publisher = "Cold Spring Harbor Laboratory", - year = 2019, + year = 2021, url = "https://doi.org/10.1101/810622", - textVersion = "Berends MS, Luz CF et al. (2019). AMR - An R Package for Working with Antimicrobial Resistance Data. bioRxiv, https://doi.org/10.1101/810622" + textVersion = "Berends MS, Luz CF et al. (2021). AMR - An R Package for Working with Antimicrobial Resistance Data. bioRxiv, https://doi.org/10.1101/810622" ) -citFooter("The mentioned article is a preprinted version of a manuscript we sent to a journal. Many thanks for using our open-source method to work with microbial and antimicrobial data!") +citFooter("This preprint was accepted for publication in the Journal of Statistical Software, but we are awaiting the actual publication. Many thanks for using our open-source method to work with microbial and antimicrobial data!") diff --git a/man/as.mo.Rd b/man/as.mo.Rd index 62c259dbd..061731b96 100644 --- a/man/as.mo.Rd +++ b/man/as.mo.Rd @@ -157,7 +157,7 @@ where: \item \ifelse{html}{\out{kn is the taxonomic kingdom of n, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.}}{l_n is the taxonomic kingdom of \eqn{n}, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.} } -The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. \strong{Group 1} (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is \emph{Enterococcus}, \emph{Staphylococcus} or \emph{Streptococcus}. This group consequently contains all common Gram-negative bacteria, such as \emph{Pseudomonas} and \emph{Legionella} and all species within the order Enterobacterales. \strong{Group 2} consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is \emph{Absidia}, \emph{Acremonium}, \emph{Actinotignum}, \emph{Alternaria}, \emph{Anaerosalibacter}, \emph{Apophysomyces}, \emph{Arachnia}, \emph{Aspergillus}, \emph{Aureobacterium}, \emph{Aureobasidium}, \emph{Bacteroides}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Branhamella}, \emph{Calymmatobacterium}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Catabacter}, \emph{Chaetomium}, \emph{Chryseobacterium}, \emph{Chryseomonas}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Flavobacterium}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Fusobacterium}, \emph{Hendersonula}, \emph{Hypomyces}, \emph{Koserella}, \emph{Lelliottia}, \emph{Leptosphaeria}, \emph{Leptotrichia}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Mycoplasma}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oidiodendron}, \emph{Phoma}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Prevotella}, \emph{Pseudallescheria}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium},\emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Stomatococcus}, \emph{Treponema}, \emph{Trichoderma}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Tritirachium} or \emph{Ureaplasma}. \strong{Group 3} consists of all other microorganisms. +The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. \strong{Group 1} (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is \emph{Enterococcus}, \emph{Staphylococcus} or \emph{Streptococcus}. This group consequently contains all common Gram-negative bacteria, such as \emph{Pseudomonas} and \emph{Legionella} and all species within the order Enterobacterales. \strong{Group 2} consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is \emph{Absidia}, \emph{Acremonium}, \emph{Actinotignum}, \emph{Alternaria}, \emph{Anaerosalibacter}, \emph{Apophysomyces}, \emph{Arachnia}, \emph{Aspergillus}, \emph{Aureobacterium}, \emph{Aureobasidium}, \emph{Bacteroides}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Branhamella}, \emph{Calymmatobacterium}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Catabacter}, \emph{Chaetomium}, \emph{Chryseobacterium}, \emph{Chryseomonas}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Flavobacterium}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Fusobacterium}, \emph{Hendersonula}, \emph{Hypomyces}, \emph{Koserella}, \emph{Lelliottia}, \emph{Leptosphaeria}, \emph{Leptotrichia}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Mycoplasma}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oidiodendron}, \emph{Phoma}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Prevotella}, \emph{Pseudallescheria}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium}, \emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Stomatococcus}, \emph{Treponema}, \emph{Trichoderma}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Tritirachium} or \emph{Ureaplasma}. \strong{Group 3} consists of all other microorganisms. All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., \code{"E. coli"} will return the microbial ID of \emph{Escherichia coli} (\eqn{m = 0.688}, a highly prevalent microorganism found in humans) and not \emph{Entamoeba coli} (\eqn{m = 0.079}, a less prevalent microorganism in humans), although the latter would alphabetically come first. } diff --git a/man/like.Rd b/man/like.Rd index a07fa9cdd..9b5b3f3e7 100755 --- a/man/like.Rd +++ b/man/like.Rd @@ -6,7 +6,7 @@ \alias{\%like_case\%} \title{Vectorised Pattern Matching with Keyboard Shortcut} \source{ -Idea from the \href{https://github.com/Rdatatable/data.table/blob/ec1259af1bf13fc0c96a1d3f9e84d55d8106a9a4/R/like.R}{\code{like} function from the \code{data.table} package} +Idea from the \href{https://github.com/Rdatatable/data.table/blob/ec1259af1bf13fc0c96a1d3f9e84d55d8106a9a4/R/like.R}{\code{like} function from the \code{data.table} package}, although altered as explained in \emph{Details}. } \usage{ like(x, pattern, ignore.case = TRUE) @@ -18,7 +18,7 @@ x \%like_case\% pattern \arguments{ \item{x}{a character vector where matches are sought, or an object which can be coerced by \code{\link[=as.character]{as.character()}} to a character vector.} -\item{pattern}{a character string containing a regular expression (or \link{character} string for \code{fixed = TRUE}) to be matched in the given character vector. Coerced by \code{\link[=as.character]{as.character()}} to a character string if possible. If a \link{character} vector of length 2 or more is supplied, the first element is used with a warning.} +\item{pattern}{a character vector containing regular expressions (or a \link{character} string for \code{fixed = TRUE}) to be matched in the given character vector. Coerced by \code{\link[=as.character]{as.character()}} to a character string if possible.} \item{ignore.case}{if \code{FALSE}, the pattern matching is \emph{case sensitive} and if \code{TRUE}, case is ignored during matching.} } @@ -29,11 +29,11 @@ A \link{logical} vector Convenient wrapper around \code{\link[=grepl]{grepl()}} to match a pattern: \code{x \%like\% pattern}. It always returns a \code{\link{logical}} vector and is always case-insensitive (use \code{x \%like_case\% pattern} for case-sensitive matching). Also, \code{pattern} can be as long as \code{x} to compare items of each index in both vectors, or they both can have the same length to iterate over all cases. } \details{ -The \verb{\%like\%} function: +This \verb{\%like\%} function: \itemize{ \item Is case-insensitive (use \verb{\%like_case\%} for case-sensitive matching) \item Supports multiple patterns -\item Checks if \code{pattern} is a regular expression and sets \code{fixed = TRUE} if not, to greatly improve speed +\item Checks if \code{pattern} is a valid regular expression and sets \code{fixed = TRUE} if not, to greatly improve speed (vectorised over \code{pattern}) \item Always uses compatibility with Perl unless \code{fixed = TRUE}, to greatly improve speed } diff --git a/man/mo_matching_score.Rd b/man/mo_matching_score.Rd index 2b11fd60b..f3bd793b4 100644 --- a/man/mo_matching_score.Rd +++ b/man/mo_matching_score.Rd @@ -30,7 +30,7 @@ where: \item \ifelse{html}{\out{kn is the taxonomic kingdom of n, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.}}{l_n is the taxonomic kingdom of \eqn{n}, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.} } -The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. \strong{Group 1} (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is \emph{Enterococcus}, \emph{Staphylococcus} or \emph{Streptococcus}. This group consequently contains all common Gram-negative bacteria, such as \emph{Pseudomonas} and \emph{Legionella} and all species within the order Enterobacterales. \strong{Group 2} consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is \emph{Absidia}, \emph{Acremonium}, \emph{Actinotignum}, \emph{Alternaria}, \emph{Anaerosalibacter}, \emph{Apophysomyces}, \emph{Arachnia}, \emph{Aspergillus}, \emph{Aureobacterium}, \emph{Aureobasidium}, \emph{Bacteroides}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Branhamella}, \emph{Calymmatobacterium}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Catabacter}, \emph{Chaetomium}, \emph{Chryseobacterium}, \emph{Chryseomonas}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Flavobacterium}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Fusobacterium}, \emph{Hendersonula}, \emph{Hypomyces}, \emph{Koserella}, \emph{Lelliottia}, \emph{Leptosphaeria}, \emph{Leptotrichia}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Mycoplasma}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oidiodendron}, \emph{Phoma}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Prevotella}, \emph{Pseudallescheria}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium},\emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Stomatococcus}, \emph{Treponema}, \emph{Trichoderma}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Tritirachium} or \emph{Ureaplasma}. \strong{Group 3} consists of all other microorganisms. +The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. \strong{Group 1} (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is \emph{Enterococcus}, \emph{Staphylococcus} or \emph{Streptococcus}. This group consequently contains all common Gram-negative bacteria, such as \emph{Pseudomonas} and \emph{Legionella} and all species within the order Enterobacterales. \strong{Group 2} consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is \emph{Absidia}, \emph{Acremonium}, \emph{Actinotignum}, \emph{Alternaria}, \emph{Anaerosalibacter}, \emph{Apophysomyces}, \emph{Arachnia}, \emph{Aspergillus}, \emph{Aureobacterium}, \emph{Aureobasidium}, \emph{Bacteroides}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Branhamella}, \emph{Calymmatobacterium}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Catabacter}, \emph{Chaetomium}, \emph{Chryseobacterium}, \emph{Chryseomonas}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Flavobacterium}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Fusobacterium}, \emph{Hendersonula}, \emph{Hypomyces}, \emph{Koserella}, \emph{Lelliottia}, \emph{Leptosphaeria}, \emph{Leptotrichia}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Mycoplasma}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oidiodendron}, \emph{Phoma}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Prevotella}, \emph{Pseudallescheria}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium}, \emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Stomatococcus}, \emph{Treponema}, \emph{Trichoderma}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Tritirachium} or \emph{Ureaplasma}. \strong{Group 3} consists of all other microorganisms. All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., \code{"E. coli"} will return the microbial ID of \emph{Escherichia coli} (\eqn{m = 0.688}, a highly prevalent microorganism found in humans) and not \emph{Entamoeba coli} (\eqn{m = 0.079}, a less prevalent microorganism in humans), although the latter would alphabetically come first. } diff --git a/man/mo_property.Rd b/man/mo_property.Rd index a2dab59dd..bfc9175a7 100644 --- a/man/mo_property.Rd +++ b/man/mo_property.Rd @@ -160,7 +160,7 @@ where: \item \ifelse{html}{\out{kn is the taxonomic kingdom of n, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.}}{l_n is the taxonomic kingdom of \eqn{n}, set as Bacteria = 1, Fungi = 2, Protozoa = 3, Archaea = 4, others = 5.} } -The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. \strong{Group 1} (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is \emph{Enterococcus}, \emph{Staphylococcus} or \emph{Streptococcus}. This group consequently contains all common Gram-negative bacteria, such as \emph{Pseudomonas} and \emph{Legionella} and all species within the order Enterobacterales. \strong{Group 2} consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is \emph{Absidia}, \emph{Acremonium}, \emph{Actinotignum}, \emph{Alternaria}, \emph{Anaerosalibacter}, \emph{Apophysomyces}, \emph{Arachnia}, \emph{Aspergillus}, \emph{Aureobacterium}, \emph{Aureobasidium}, \emph{Bacteroides}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Branhamella}, \emph{Calymmatobacterium}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Catabacter}, \emph{Chaetomium}, \emph{Chryseobacterium}, \emph{Chryseomonas}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Flavobacterium}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Fusobacterium}, \emph{Hendersonula}, \emph{Hypomyces}, \emph{Koserella}, \emph{Lelliottia}, \emph{Leptosphaeria}, \emph{Leptotrichia}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Mycoplasma}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oidiodendron}, \emph{Phoma}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Prevotella}, \emph{Pseudallescheria}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium},\emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Stomatococcus}, \emph{Treponema}, \emph{Trichoderma}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Tritirachium} or \emph{Ureaplasma}. \strong{Group 3} consists of all other microorganisms. +The grouping into human pathogenic prevalence (\eqn{p}) is based on experience from several microbiological laboratories in the Netherlands in conjunction with international reports on pathogen prevalence. \strong{Group 1} (most prevalent microorganisms) consists of all microorganisms where the taxonomic class is Gammaproteobacteria or where the taxonomic genus is \emph{Enterococcus}, \emph{Staphylococcus} or \emph{Streptococcus}. This group consequently contains all common Gram-negative bacteria, such as \emph{Pseudomonas} and \emph{Legionella} and all species within the order Enterobacterales. \strong{Group 2} consists of all microorganisms where the taxonomic phylum is Proteobacteria, Firmicutes, Actinobacteria or Sarcomastigophora, or where the taxonomic genus is \emph{Absidia}, \emph{Acremonium}, \emph{Actinotignum}, \emph{Alternaria}, \emph{Anaerosalibacter}, \emph{Apophysomyces}, \emph{Arachnia}, \emph{Aspergillus}, \emph{Aureobacterium}, \emph{Aureobasidium}, \emph{Bacteroides}, \emph{Basidiobolus}, \emph{Beauveria}, \emph{Blastocystis}, \emph{Branhamella}, \emph{Calymmatobacterium}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Catabacter}, \emph{Chaetomium}, \emph{Chryseobacterium}, \emph{Chryseomonas}, \emph{Chrysonilia}, \emph{Cladophialophora}, \emph{Cladosporium}, \emph{Conidiobolus}, \emph{Cryptococcus}, \emph{Curvularia}, \emph{Exophiala}, \emph{Exserohilum}, \emph{Flavobacterium}, \emph{Fonsecaea}, \emph{Fusarium}, \emph{Fusobacterium}, \emph{Hendersonula}, \emph{Hypomyces}, \emph{Koserella}, \emph{Lelliottia}, \emph{Leptosphaeria}, \emph{Leptotrichia}, \emph{Malassezia}, \emph{Malbranchea}, \emph{Mortierella}, \emph{Mucor}, \emph{Mycocentrospora}, \emph{Mycoplasma}, \emph{Nectria}, \emph{Ochroconis}, \emph{Oidiodendron}, \emph{Phoma}, \emph{Piedraia}, \emph{Pithomyces}, \emph{Pityrosporum}, \emph{Prevotella}, \emph{Pseudallescheria}, \emph{Rhizomucor}, \emph{Rhizopus}, \emph{Rhodotorula}, \emph{Scolecobasidium}, \emph{Scopulariopsis}, \emph{Scytalidium}, \emph{Sporobolomyces}, \emph{Stachybotrys}, \emph{Stomatococcus}, \emph{Treponema}, \emph{Trichoderma}, \emph{Trichophyton}, \emph{Trichosporon}, \emph{Tritirachium} or \emph{Ureaplasma}. \strong{Group 3} consists of all other microorganisms. All matches are sorted descending on their matching score and for all user input values, the top match will be returned. This will lead to the effect that e.g., \code{"E. coli"} will return the microbial ID of \emph{Escherichia coli} (\eqn{m = 0.688}, a highly prevalent microorganism found in humans) and not \emph{Entamoeba coli} (\eqn{m = 0.079}, a less prevalent microorganism in humans), although the latter would alphabetically come first. } diff --git a/tests/testthat/test-eucast_rules.R b/tests/testthat/test-eucast_rules.R index a3e54aa5d..e881232a0 100755 --- a/tests/testthat/test-eucast_rules.R +++ b/tests/testthat/test-eucast_rules.R @@ -38,7 +38,7 @@ test_that("EUCAST rules work", { "reference.version", "note")) MOs_mentioned <- unique(eucast_rules_file$this_value) - MOs_mentioned <- sort(trimws(unlist(strsplit(MOs_mentioned[!is_possibly_regex(MOs_mentioned)], ",", fixed = TRUE)))) + MOs_mentioned <- sort(trimws(unlist(strsplit(MOs_mentioned[!is_valid_regex(MOs_mentioned)], ",", fixed = TRUE)))) MOs_test <- suppressWarnings(suppressMessages(mo_name(MOs_mentioned))) expect_length(MOs_mentioned[MOs_test != MOs_mentioned], 0)