diff --git a/.github/workflows/check.yaml b/.github/workflows/check.yaml
index 5fd4f193..1189e961 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 0e66d73d..aad0d6a5 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 1edb7be2..680681da 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 df9258dc..d5275305 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 8e82984e..edd135d1 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 7d4d32c9..f3e2c356 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 7a9cd5ec..58481e53 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 e79727c3..7f046d33 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 46d2da89..f45fb96e 100644
--- a/docs/404.html
+++ b/docs/404.html
@@ -81,7 +81,7 @@
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 e6c0f4aa..1cbb3040 100644 --- a/docs/index.html +++ b/docs/index.html @@ -42,7 +42,7 @@ diff --git a/docs/news/index.html b/docs/news/index.html index 886187a9..1ceaf914 100644 --- a/docs/news/index.html +++ b/docs/news/index.html @@ -81,7 +81,7 @@ @@ -236,13 +236,13 @@ Source:
NEWS.md
- 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 expressionkn 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.
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.
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.
A logical vector
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
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.
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.