diff --git a/.gitignore b/.gitignore
index e2371544..9a2c3cb6 100755
--- a/.gitignore
+++ b/.gitignore
@@ -21,3 +21,5 @@ vignettes/*.R
packrat/lib*/
packrat/src/
cran-comments.md
+data-raw/taxon.tab
+data-raw/DSMZ_bactnames.xlsx
diff --git a/DESCRIPTION b/DESCRIPTION
index 7dc38214..2c786620 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,5 +1,5 @@
Package: AMR
-Version: 0.7.1.9032
+Version: 0.7.1.9034
Date: 2019-08-09
Title: Antimicrobial Resistance Analysis
Authors@R: c(
diff --git a/NEWS.md b/NEWS.md
index 75a89294..53104f81 100755
--- a/NEWS.md
+++ b/NEWS.md
@@ -1,4 +1,4 @@
-# AMR 0.7.1.9032
+# AMR 0.7.1.9034
### Breaking
* Function `freq()` has moved to a new package, [`clean`](https://github.com/msberends/clean) ([CRAN link](https://cran.r-project.org/package=clean)). Creating frequency tables is actually not the scope of this package (never was) and this function has matured a lot over the last two years. Therefore, a new package was created for data cleaning and checking and it perfectly fits the `freq()` function. The [`clean`](https://github.com/msberends/clean) package is available on CRAN and will be installed automatically when updating the `AMR` package, that now imports it. In a later stage, the `skewness()` and `kurtosis()` functions will be moved to the `clean` package too.
@@ -60,7 +60,8 @@
* Some misspelled input were not understood
* These new trivial names known to the field are now understood: meningococcus, gonococcus, pneumococcus
* Added support for unknown yeasts and fungi
-* Added the newest taxonomic data from the IJSEM journal (now up to date until August 2019)
+* Updated the `microorganisms` data set to contain the latest taxonomic data from the IJSEM journal (now up to date until August 2019)
+* Added almost 5,000 new fungi to the `microorganisms` data set
* Fix for using `mo_*` functions where the coercion uncertainties and failures would not be available through `mo_uncertainties()` and `mo_failures()` anymore
* Deprecated the `country` parameter of `mdro()` in favour of the already existing `guideline` parameter to support multiple guidelines within one country
* The `name` of `RIF` is now Rifampicin instead of Rifampin
diff --git a/R/catalogue_of_life.R b/R/catalogue_of_life.R
index 0ec29f8a..5c92d9e1 100755
--- a/R/catalogue_of_life.R
+++ b/R/catalogue_of_life.R
@@ -30,10 +30,10 @@
#' @section Included taxa:
#' Included are:
#' \itemize{
-#' \item{All ~55,000 (sub)species from the kingdoms of Archaea, Bacteria and Protozoa}
-#' \item{All ~3,500 (sub)species from these orders of the kingdom of Fungi: Eurotiales, Onygenales, Pneumocystales, Saccharomycetales, Schizosaccharomycetales and Tremellales. The kingdom of Fungi is a very large taxon with almost 300,000 different (sub)species, of which most are not microbial (but rather macroscopic, like mushrooms). Because of this, not all fungi fit the scope of this package and including everything would tremendously slow down our algorithms too. By only including the aforementioned taxonomic orders, the most relevant fungi are covered (like all species of \emph{Aspergillus}, \emph{Candida}, \emph{Cryptococcus}, \emph{Histplasma}, \emph{Pneumocystis}, \emph{Saccharomyces} and \emph{Trichophyton}).}
-#' \item{All ~2,000 (sub)species from ~100 other relevant genera, from the kingdoms of Animalia and Plantae (like \emph{Strongyloides} and \emph{Taenia})}
-#' \item{All ~21,000 previously accepted names of included (sub)species that have been taxonomically renamed}
+#' \item{All ~61,000 (sub)species from the kingdoms of Archaea, Bacteria, Chromista and Protozoa}
+#' \item{All ~8,500 (sub)species from these orders of the kingdom of Fungi: Eurotiales, Microascales, Mucorales, Onygenales, Pneumocystales, Saccharomycetales, Schizosaccharomycetales and Tremellales. The kingdom of Fungi is a very large taxon with almost 300,000 different (sub)species, of which most are not microbial (but rather macroscopic, like mushrooms). Because of this, not all fungi fit the scope of this package and including everything would tremendously slow down our algorithms too. By only including the aforementioned taxonomic orders, the most relevant fungi are covered (like all species of \emph{Aspergillus}, \emph{Candida}, \emph{Cryptococcus}, \emph{Histplasma}, \emph{Pneumocystis}, \emph{Saccharomyces} and \emph{Trichophyton}).}
+#' \item{All ~150 (sub)species from ~100 other relevant genera from the kingdom of Animalia (like \emph{Strongyloides} and \emph{Taenia})}
+#' \item{All ~23,000 previously accepted names of all included (sub)species (these were taxonomically renamed)}
#' \item{The complete taxonomic tree of all included (sub)species: from kingdom to subspecies}
#' \item{The responsible author(s) and year of scientific publication}
#' }
diff --git a/R/data.R b/R/data.R
index 1974ab19..b8178772 100755
--- a/R/data.R
+++ b/R/data.R
@@ -51,11 +51,11 @@
#' @seealso \code{\link{microorganisms}}
"antibiotics"
-#' Data set with ~65,000 microorganisms
+#' Data set with ~70,000 microorganisms
#'
#' A data set containing the microbial taxonomy of six kingdoms from the Catalogue of Life. MO codes can be looked up using \code{\link{as.mo}}.
#' @inheritSection catalogue_of_life Catalogue of Life
-#' @format A \code{\link{data.frame}} with 68,260 observations and 16 variables:
+#' @format A \code{\link{data.frame}} with 69,854 observations and 16 variables:
#' \describe{
#' \item{\code{mo}}{ID of microorganism as used by this package}
#' \item{\code{col_id}}{Catalogue of Life ID}
@@ -98,7 +98,7 @@ catalogue_of_life <- list(
#'
#' A data set containing old (previously valid or accepted) taxonomic names according to the Catalogue of Life. This data set is used internally by \code{\link{as.mo}}.
#' @inheritSection catalogue_of_life Catalogue of Life
-#' @format A \code{\link{data.frame}} with 21,743 observations and 4 variables:
+#' @format A \code{\link{data.frame}} with 22,932 observations and 4 variables:
#' \describe{
#' \item{\code{col_id}}{Catalogue of Life ID that was originally given}
#' \item{\code{col_id_new}}{New Catalogue of Life ID that responds to an entry in the \code{\link{microorganisms}} data set}
@@ -113,7 +113,7 @@ catalogue_of_life <- list(
#' Translation table for microorganism codes
#'
#' A data set containing commonly used codes for microorganisms, from laboratory systems and WHONET. Define your own with \code{\link{set_mo_source}}.
-#' @format A \code{\link{data.frame}} with 4,969 observations and 2 variables:
+#' @format A \code{\link{data.frame}} with 4,965 observations and 2 variables:
#' \describe{
#' \item{\code{certe}}{Commonly used code of a microorganism}
#' \item{\code{mo}}{ID of the microorganism in the \code{\link{microorganisms}} data set}
diff --git a/R/ggplot_rsi.R b/R/ggplot_rsi.R
index 40b43ccb..c54050e3 100755
--- a/R/ggplot_rsi.R
+++ b/R/ggplot_rsi.R
@@ -182,8 +182,8 @@ ggplot_rsi <- function(data,
title = NULL,
subtitle = NULL,
caption = NULL,
- x.title = NULL,
- y.title = NULL,
+ x.title = "Antimicrobial",
+ y.title = "Proportion",
...) {
stopifnot_installed_package("ggplot2")
diff --git a/data-raw/reproduction_of_microorganisms.R b/data-raw/reproduction_of_microorganisms.R
index 79b18291..fd2b5d39 100644
--- a/data-raw/reproduction_of_microorganisms.R
+++ b/data-raw/reproduction_of_microorganisms.R
@@ -11,10 +11,10 @@ library(dplyr)
library(AMR)
# unzip and extract taxon.tab (around 1.5 GB) from the CoL archive, then:
-data_col <- data.table::fread("Downloads/taxon.tab")
+data_col <- data.table::fread("data-raw/taxon.tab")
# read the xlsx file from DSMZ (only around 2.5 MB):
-data_dsmz <- readxl::read_xlsx("Downloads/DSMZ_bactnames.xlsx")
+data_dsmz <- readxl::read_xlsx("data-raw/DSMZ_bactnames.xlsx")
# the CoL data is over 3.7M rows:
data_col %>% freq(kingdom)
@@ -99,23 +99,25 @@ MOs <- data_total %>%
# and not all fungi: Aspergillus, Candida, Trichphyton and Pneumocystis are the most important,
# so only keep these orders from the fungi:
& !(kingdom == "Fungi"
- & !order %in% c("Eurotiales", "Mucorales", "Saccharomycetales", "Schizosaccharomycetales", "Tremellales", "Onygenales", "Pneumocystales"))
+ & !order %in% c("Eurotiales", "Microascales", "Mucorales", "Saccharomycetales", "Schizosaccharomycetales", "Tremellales", "Onygenales", "Pneumocystales"))
)
# or the genus has to be one of the genera we found in our hospitals last decades (Northern Netherlands, 2002-2018)
| genus %in% c("Absidia", "Acremonium", "Actinotignum", "Alternaria", "Anaerosalibacter", "Ancylostoma", "Anisakis", "Apophysomyces",
"Arachnia", "Ascaris", "Aureobacterium", "Aureobasidium", "Balantidum", "Bilophilia", "Branhamella", "Brochontrix",
"Brugia", "Calymmatobacterium", "Catabacter", "Cdc", "Chilomastix", "Chryseomonas", "Cladophialophora", "Cladosporium",
"Clonorchis", "Cordylobia", "Curvularia", "Demodex", "Dermatobia", "Diphyllobothrium", "Dracunculus", "Echinococcus",
- "Enterobius", "Euascomycetes", "Exophiala", "Fasciola", "Fusarium", "Hendersonula", "Hymenolepis", "Kloeckera",
+ "Enterobius", "Euascomycetes", "Exophiala", "Fasciola", "Fusarium", "Hendersonula", "Hymenolepis", "Hypomyces", "Kloeckera",
"Koserella", "Larva", "Leishmania", "Lelliottia", "Loa", "Lumbricus", "Malassezia", "Metagonimus", "Molonomonas",
- "Mucor", "Nattrassia", "Necator", "Novospingobium", "Onchocerca", "Opistorchis", "Paragonimus", "Paramyxovirus",
+ "Mucor", "Nattrassia", "Necator", "Nectria", "Novospingobium", "Onchocerca", "Opistorchis", "Paragonimus", "Paramyxovirus",
"Pediculus", "Phoma", "Phthirus", "Pityrosporum", "Pseudallescheria", "Pulex", "Rhizomucor", "Rhizopus", "Rhodotorula",
"Salinococcus", "Sanguibacteroides", "Schistosoma", "Scopulariopsis", "Scytalidium", "Sporobolomyces", "Stomatococcus",
- "Strongyloides", "Syncephalastraceae", "Taenia", "Torulopsis", "Trichinella", "Trichobilharzia", "Trichomonas",
+ "Strongyloides", "Syncephalastraceae", "Taenia", "Torulopsis", "Trichinella", "Trichobilharzia", "Trichoderma", "Trichomonas",
"Trichosporon", "Trichuris", "Trypanosoma", "Wuchereria")
# or the taxonomic entry is old - the species was renamed
| !is.na(col_id_new)
- )
+ ) %>%
+ # really no Plantae (e.g. Dracunculus exist both as worm and as plant)
+ filter(kingdom != "Plantae")
# filter old taxonomic names so only the ones with an existing reference will be kept
MOs <- MOs %>%
@@ -222,7 +224,7 @@ MOs <- MOs %>%
distinct(fullname, .keep_all = TRUE)
# what characters are in the fullnames?
-paste(unique(sort(unlist(strsplit(x = paste(MOs$fullname, collapse = ""), split = "")))), collapse = "")
+table(sort(unlist(strsplit(x = paste(MOs$fullname, collapse = ""), split = ""))))
# Add abbreviations so we can easily know which ones are which ones.
# These will become valid and unique microbial IDs for the AMR package.
@@ -522,12 +524,22 @@ MOs <- MOs %>%
# everything distinct?
sum(duplicated(MOs$mo))
+sum(duplicated(MOs$fullname))
colnames(MOs)
# here we welcome the new ones:
MOs %>% filter(!fullname %in% AMR::microorganisms$fullname) %>% View()
# and the ones we lost:
AMR::microorganisms %>% filter(!fullname %in% MOs$fullname) %>% View()
+# and these IDs have changed:
+MOs %>%
+ filter(fullname %in% AMR::microorganisms$fullname) %>%
+ left_join(AMR::microorganisms %>% select(mo, fullname), by = "fullname", suffix = c("_new", "_old")) %>%
+ filter(mo_new != mo_old) %>%
+ select(mo_old, mo_new, everything()) %>%
+ View()
+# and these codes are now missing (which will throw a unit test error):
+AMR::microorganisms.codes %>% filter(!mo %in% AMR::microorganisms$mo)
# set prevalence per species
MOs <- MOs %>%
diff --git a/data/microorganisms.codes.rda b/data/microorganisms.codes.rda
index bcfa993a..80c6586b 100644
Binary files a/data/microorganisms.codes.rda and b/data/microorganisms.codes.rda differ
diff --git a/data/microorganisms.old.rda b/data/microorganisms.old.rda
index 674279f6..805070c3 100644
Binary files a/data/microorganisms.old.rda and b/data/microorganisms.old.rda differ
diff --git a/data/microorganisms.rda b/data/microorganisms.rda
index b5a2d375..871cb79e 100755
Binary files a/data/microorganisms.rda and b/data/microorganisms.rda differ
diff --git a/docs/LICENSE-text.html b/docs/LICENSE-text.html
index f48faeb2..71b07b4f 100644
--- a/docs/LICENSE-text.html
+++ b/docs/LICENSE-text.html
@@ -78,7 +78,7 @@
AMR (for R)
- 0.7.1.9032
+ 0.7.1.9034
diff --git a/docs/articles/index.html b/docs/articles/index.html
index 9d070245..dbdcbf53 100644
--- a/docs/articles/index.html
+++ b/docs/articles/index.html
@@ -78,7 +78,7 @@
AMR (for R)
- 0.7.1.9032
+ 0.7.1.9034
diff --git a/docs/authors.html b/docs/authors.html
index 2f345f87..6665c28b 100644
--- a/docs/authors.html
+++ b/docs/authors.html
@@ -78,7 +78,7 @@
AMR (for R)
- 0.7.1.9032
+ 0.7.1.9034
diff --git a/docs/index.html b/docs/index.html
index 99a91fb4..76320f6d 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -42,7 +42,7 @@
AMR (for R)
- 0.7.1.9032
+ 0.7.1.9034
@@ -189,10 +189,23 @@
AMR is a free and open-source R package to simplify the analysis and prediction of Antimicrobial Resistance (AMR) and to work with microbial and antimicrobial properties by using evidence-based methods. It supports any data format, including WHONET/EARS-Net data.
We created this package for both academic research and routine analysis at the Faculty of Medical Sciences of the University of Groningen, the Netherlands, and the Medical Microbiology & Infection Prevention (MMBI) department of the University Medical Center Groningen (UMCG). This R package is actively maintained and is free software; you can freely use and distribute it for both personal and commercial (but not patent) purposes under the terms of the GNU General Public License version 2.0 (GPL-2), as published by the Free Software Foundation. Read the full license here.
+
+
+What is AMR (for R)?
+
AMR is a free and open-source R package to simplify the analysis and prediction of Antimicrobial Resistance (AMR) and to work with microbial and antimicrobial properties by using evidence-based methods. Since its first public release in early 2018, this package has been downloaded over 20,000 times from more than 40 countries (source: CRAN logs, 2019).
+
After installing this package, R knows ~70,000 microorganisms (distinct microbial species) and ~450 antibiotics by name and code, and knows all about valid RSI and MIC values. It supports any data format, including WHONET/EARS-Net data.
+
We created this package for both academic research and routine analysis at the Faculty of Medical Sciences of the University of Groningen, the Netherlands, and the Medical Microbiology & Infection Prevention (MMBI) department of the University Medical Center Groningen (UMCG). This R package is actively maintained and is free software; you can freely use and distribute it for both personal and commercial (but not patent) purposes under the terms of the GNU General Public License version 2.0 (GPL-2), as published by the Free Software Foundation. Read the full license here.
This package contains the complete taxonomic tree of almost all microorganisms from the authoritative and comprehensive Catalogue of Life (www.catalogueoflife.org).
Included are:
-
All ~55,000 (sub)species from the kingdoms of Archaea, Bacteria and Protozoa
+
All ~61,000 (sub)species from the kingdoms of Archaea, Bacteria, Chromista and Protozoa
-
All ~3,500 (sub)species from these orders of the kingdom of Fungi: Eurotiales, Onygenales, Pneumocystales, Saccharomycetales, Schizosaccharomycetales and Tremellales.
+
All ~8,500 (sub)species from these orders of the kingdom of Fungi: Eurotiales, Microascales, Mucorales, Onygenales, Pneumocystales, Saccharomycetales, Schizosaccharomycetales and Tremellales.
The kingdom of Fungi is a very large taxon with almost 300,000 different (sub)species, of which most are not microbial (but rather macroscopic, like mushrooms). Because of this, not all fungi fit the scope of this package and including everything would tremendously slow down our algorithms too. By only including the aforementioned taxonomic orders, the most relevant fungi are covered (like all species of Aspergillus, Candida, Cryptococcus, Histoplasma, Pneumocystis, Saccharomyces and Trichophyton).
-
All ~2,000 (sub)species from ~100 other relevant genera, from the kingdoms of Animalia and Plantae (like Strongyloides and Taenia)
-
All ~21,000 previously accepted names of included (sub)species that have been taxonomically renamed
+
All ~150 (sub)species from ~100 other relevant genera from the kingdom of Animalia (like Strongyloides and Taenia)
+
All ~23,000 previously accepted names of all included (sub)species (these were taxonomically renamed)
The responsible author(s) and year of scientific publication
Use mdro() (abbreviation of Multi Drug Resistant Organisms) to check your isolates for exceptional resistance with country-specific guidelines or EUCAST rules. Currently, national guidelines for Germany and the Netherlands are supported.
-
The data set microorganisms contains the complete taxonomic tree of ~65,000 microorganisms. Furthermore, some colloquial names and all Gram stains are available, which enables resistance analysis of e.g. different antibiotics per Gram stain. The package also contains functions to look up values in this data set like mo_genus(), mo_family(), mo_gramstain() or even mo_phylum(). As they use as.mo() internally, they also use the same intelligent rules for determination. For example, mo_genus("MRSA") and mo_genus("S. aureus") will both return "Staphylococcus". They also come with support for German, Dutch, Spanish, Italian, French and Portuguese. These functions can be used to add new variables to your data.
+
The data set microorganisms contains the complete taxonomic tree of ~70,000 microorganisms. Furthermore, some colloquial names and all Gram stains are available, which enables resistance analysis of e.g. different antibiotics per Gram stain. The package also contains functions to look up values in this data set like mo_genus(), mo_family(), mo_gramstain() or even mo_phylum(). As they use as.mo() internally, they also use the same intelligent rules for determination. For example, mo_genus("MRSA") and mo_genus("S. aureus") will both return "Staphylococcus". They also come with support for German, Dutch, Spanish, Italian, French and Portuguese. These functions can be used to add new variables to your data.
The data set antibiotics contains ~450 antimicrobial drugs with their EARS-Net code, ATC code, PubChem compound ID, official name, common LIS codes and DDDs of both oral and parenteral administration. It also contains all (thousands of) trade names found in PubChem. The function ab_atc() will return the ATC code of an antibiotic as defined by the WHO. Use functions like ab_name(), ab_group() and ab_tradenames() to look up values. The ab_* functions use as.ab() internally so they support the same intelligent rules to guess the most probable result. For example, ab_name("Fluclox"), ab_name("Floxapen") and ab_name("J01CF05") will all return "Flucloxacillin". These functions can again be used to add new variables to your data.
@@ -354,12 +368,6 @@
-
-
-Partners
-
The development of this package is part of, related to, or made possible by:
diff --git a/docs/reference/catalogue_of_life.html b/docs/reference/catalogue_of_life.html
index 8081bf20..a7352ec1 100644
--- a/docs/reference/catalogue_of_life.html
+++ b/docs/reference/catalogue_of_life.html
@@ -80,7 +80,7 @@
AMR (for R)
- 0.7.1.9029
+ 0.7.1.9033
@@ -246,10 +246,10 @@ This package contains the complete taxonomic tree of almost all microorganisms (
Included are:
-
All ~55,000 (sub)species from the kingdoms of Archaea, Bacteria and Protozoa
-
All ~3,500 (sub)species from these orders of the kingdom of Fungi: Eurotiales, Onygenales, Pneumocystales, Saccharomycetales, Schizosaccharomycetales and Tremellales. The kingdom of Fungi is a very large taxon with almost 300,000 different (sub)species, of which most are not microbial (but rather macroscopic, like mushrooms). Because of this, not all fungi fit the scope of this package and including everything would tremendously slow down our algorithms too. By only including the aforementioned taxonomic orders, the most relevant fungi are covered (like all species of Aspergillus, Candida, Cryptococcus, Histplasma, Pneumocystis, Saccharomyces and Trichophyton).
-
All ~2,000 (sub)species from ~100 other relevant genera, from the kingdoms of Animalia and Plantae (like Strongyloides and Taenia)
-
All ~21,000 previously accepted names of included (sub)species that have been taxonomically renamed
+
All ~61,000 (sub)species from the kingdoms of Archaea, Bacteria, Chromista and Protozoa
+
All ~8,500 (sub)species from these orders of the kingdom of Fungi: Eurotiales, Microascales, Mucorales, Onygenales, Pneumocystales, Saccharomycetales, Schizosaccharomycetales and Tremellales. The kingdom of Fungi is a very large taxon with almost 300,000 different (sub)species, of which most are not microbial (but rather macroscopic, like mushrooms). Because of this, not all fungi fit the scope of this package and including everything would tremendously slow down our algorithms too. By only including the aforementioned taxonomic orders, the most relevant fungi are covered (like all species of Aspergillus, Candida, Cryptococcus, Histplasma, Pneumocystis, Saccharomyces and Trichophyton).
+
All ~150 (sub)species from ~100 other relevant genera from the kingdom of Animalia (like Strongyloides and Taenia)
+
All ~23,000 previously accepted names of all included (sub)species (these were taxonomically renamed)
The complete taxonomic tree of all included (sub)species: from kingdom to subspecies
The responsible author(s) and year of scientific publication
diff --git a/index.md b/index.md
index 805511c1..7874f335 100644
--- a/index.md
+++ b/index.md
@@ -4,14 +4,28 @@
----
-`AMR` is a free and open-source [R package](https://www.r-project.org) to simplify the analysis and prediction of Antimicrobial Resistance (AMR) and to work with microbial and antimicrobial properties by using evidence-based methods. It supports any data format, including WHONET/EARS-Net data.
+### What is `AMR` (for R)?
-After installing this package, R knows [**~65,000 microorganisms**](./reference/microorganisms.html) and [**~450 antibiotics**](./reference/antibiotics.html) by name and code, and knows all about valid RSI and MIC values.
+`AMR` is a free and open-source [R package](https://www.r-project.org) to simplify the analysis and prediction of Antimicrobial Resistance (AMR) and to work with microbial and antimicrobial properties by using evidence-based methods. Since its first public release in early 2018, this package has been downloaded over 20,000 times from more than 40 countries (source: [CRAN logs, 2019](https://cran-logs.rstudio.com)).
-**Used to SPSS?** Read our [tutorial on how to import data from SPSS, SAS or Stata](./articles/SPSS.html) and learn in which ways R outclasses any of these statistical packages.
+After installing this package, R knows [**~70,000 microorganisms**](./reference/microorganisms.html) (distinct microbial species) and [**~450 antibiotics**](./reference/antibiotics.html) by name and code, and knows all about valid RSI and MIC values. It supports any data format, including WHONET/EARS-Net data.
We created this package for both academic research and routine analysis at the Faculty of Medical Sciences of the University of Groningen, the Netherlands, and the Medical Microbiology & Infection Prevention (MMBI) department of the University Medical Center Groningen (UMCG).
-This R package is actively maintained and is free software; you can freely use and distribute it for both personal and commercial (but **not** patent) purposes under the terms of the GNU General Public License version 2.0 (GPL-2), as published by the Free Software Foundation. Read the full license [here](./LICENSE-text.html).
+This R package is [actively maintained](./news) and is free software; you can freely use and distribute it for both personal and commercial (but **not** patent) purposes under the terms of the GNU General Public License version 2.0 (GPL-2), as published by the Free Software Foundation. Read the full license [here](./LICENSE-text.html).
+
+**Used to SPSS?** Read our [tutorial on how to import data from SPSS, SAS or Stata](./articles/SPSS.html).
+
+#### Partners
+
+The development of this package is part of, related to, or made possible by:
+
+
+
+
+
+
+
+### What can you do with this package?
This package can be used for:
@@ -23,7 +37,7 @@ This package can be used for:
* Calculating (empirical) susceptibility of both mono therapy and combination therapies ([tutorial](./articles/AMR.html))
* Predicting future antimicrobial resistance using regression models ([tutorial](./articles/resistance_predict.html))
* Getting properties for any microorganism (like Gram stain, species, genus or family) ([manual](./reference/mo_property.html))
- * Getting properties for any antibiotic (like name, ATC code, defined daily dose or trade name) ([manual](./reference/ab_property.html))
+ * Getting properties for any antibiotic (like name, EARS-Net code, ATC code, PubChem code, defined daily dose or trade name) ([manual](./reference/ab_property.html))
* Plotting antimicrobial resistance ([tutorial](./articles/AMR.html))
* Applying EUCAST expert rules ([manual](./reference/eucast_rules.html))
@@ -54,7 +68,7 @@ Developers
* Software developers
* Web application / Shiny developers
-## Get this package
+### Get this package
#### Latest released version
@@ -76,11 +90,11 @@ install.packages("devtools")
devtools::install_gitlab("msberends/AMR")
```
-## Get started
+### Get started
To find out how to conduct AMR analysis, please [continue reading here to get started](./articles/AMR.html) or click the links in the 'How to' menu.
-## Short introduction
+### Short introduction
#### Microbial (taxonomic) reference data
@@ -90,15 +104,15 @@ This package contains the complete taxonomic tree of almost all microorganisms f
Included are:
-* All ~55,000 (sub)species from the kingdoms of Archaea, Bacteria and Protozoa
+* All ~61,000 (sub)species from the kingdoms of Archaea, Bacteria, Chromista and Protozoa
-* All ~3,500 (sub)species from these orders of the kingdom of Fungi: Eurotiales, Onygenales, Pneumocystales, Saccharomycetales, Schizosaccharomycetales and Tremellales.
+* All ~8,500 (sub)species from these orders of the kingdom of Fungi: Eurotiales, Microascales, Mucorales, Onygenales, Pneumocystales, Saccharomycetales, Schizosaccharomycetales and Tremellales.
The kingdom of Fungi is a very large taxon with almost 300,000 different (sub)species, of which most are not microbial (but rather macroscopic, like mushrooms). Because of this, not all fungi fit the scope of this package and including everything would tremendously slow down our algorithms too. By only including the aforementioned taxonomic orders, the most relevant fungi are covered (like all species of *Aspergillus*, *Candida*, *Cryptococcus*, *Histoplasma*, *Pneumocystis*, *Saccharomyces* and *Trichophyton*).
-* All ~2,000 (sub)species from ~100 other relevant genera, from the kingdoms of Animalia and Plantae (like *Strongyloides* and *Taenia*)
+* All ~150 (sub)species from ~100 other relevant genera from the kingdom of Animalia (like *Strongyloides* and *Taenia*)
-* All ~21,000 previously accepted names of included (sub)species that have been taxonomically renamed
+* All ~23,000 previously accepted names of all included (sub)species (these were taxonomically renamed)
* The responsible author(s) and year of scientific publication
@@ -145,7 +159,7 @@ The `AMR` package basically does four important things:
* Use `first_isolate()` to identify the first isolates of every patient [using guidelines from the CLSI](https://clsi.org/standards/products/microbiology/documents/m39/) (Clinical and Laboratory Standards Institute).
* You can also identify first *weighted* isolates of every patient, an adjusted version of the CLSI guideline. This takes into account key antibiotics of every strain and compares them.
* Use `mdro()` (abbreviation of Multi Drug Resistant Organisms) to check your isolates for exceptional resistance with country-specific guidelines or EUCAST rules. Currently, national guidelines for Germany and the Netherlands are supported.
- * The [data set `microorganisms`](./reference/microorganisms.html) contains the complete taxonomic tree of ~65,000 microorganisms. Furthermore, some colloquial names and all Gram stains are available, which enables resistance analysis of e.g. different antibiotics per Gram stain. The package also contains functions to look up values in this data set like `mo_genus()`, `mo_family()`, `mo_gramstain()` or even `mo_phylum()`. As they use `as.mo()` internally, they also use the same intelligent rules for determination. For example, `mo_genus("MRSA")` and `mo_genus("S. aureus")` will both return `"Staphylococcus"`. They also come with support for German, Dutch, Spanish, Italian, French and Portuguese. These functions can be used to add new variables to your data.
+ * The [data set `microorganisms`](./reference/microorganisms.html) contains the complete taxonomic tree of ~70,000 microorganisms. Furthermore, some colloquial names and all Gram stains are available, which enables resistance analysis of e.g. different antibiotics per Gram stain. The package also contains functions to look up values in this data set like `mo_genus()`, `mo_family()`, `mo_gramstain()` or even `mo_phylum()`. As they use `as.mo()` internally, they also use the same intelligent rules for determination. For example, `mo_genus("MRSA")` and `mo_genus("S. aureus")` will both return `"Staphylococcus"`. They also come with support for German, Dutch, Spanish, Italian, French and Portuguese. These functions can be used to add new variables to your data.
* The [data set `antibiotics`](./reference/antibiotics.html) contains ~450 antimicrobial drugs with their EARS-Net code, ATC code, PubChem compound ID, official name, common LIS codes and DDDs of both oral and parenteral administration. It also contains all (thousands of) trade names found in PubChem. The function `ab_atc()` will return the ATC code of an antibiotic as defined by the WHO. Use functions like `ab_name()`, `ab_group()` and `ab_tradenames()` to look up values. The `ab_*` functions use `as.ab()` internally so they support the same intelligent rules to guess the most probable result. For example, `ab_name("Fluclox")`, `ab_name("Floxapen")` and `ab_name("J01CF05")` will all return `"Flucloxacillin"`. These functions can again be used to add new variables to your data.
3. It **analyses the data** with convenient functions that use well-known methods.
@@ -163,14 +177,3 @@ The `AMR` package basically does four important things:
* Results of 40 antibiotics (each antibiotic in its own column) with a total ~40,000 antimicrobial results
* Real and genuine data
* The [`WHONET` data set](./reference/WHONET.html). This data set only contains fake data, but with the exact same structure as files exported by WHONET. Read more about WHONET [on its tutorial page](./articles/WHONET.html).
-
-
-#### Partners
-
-The development of this package is part of, related to, or made possible by:
-
-
-
-
-
-
diff --git a/man/catalogue_of_life.Rd b/man/catalogue_of_life.Rd
index 7a5830d1..e8cd3324 100644
--- a/man/catalogue_of_life.Rd
+++ b/man/catalogue_of_life.Rd
@@ -18,10 +18,10 @@ This package contains the complete taxonomic tree of almost all microorganisms (
Included are:
\itemize{
- \item{All ~55,000 (sub)species from the kingdoms of Archaea, Bacteria and Protozoa}
- \item{All ~3,500 (sub)species from these orders of the kingdom of Fungi: Eurotiales, Onygenales, Pneumocystales, Saccharomycetales, Schizosaccharomycetales and Tremellales. The kingdom of Fungi is a very large taxon with almost 300,000 different (sub)species, of which most are not microbial (but rather macroscopic, like mushrooms). Because of this, not all fungi fit the scope of this package and including everything would tremendously slow down our algorithms too. By only including the aforementioned taxonomic orders, the most relevant fungi are covered (like all species of \emph{Aspergillus}, \emph{Candida}, \emph{Cryptococcus}, \emph{Histplasma}, \emph{Pneumocystis}, \emph{Saccharomyces} and \emph{Trichophyton}).}
- \item{All ~2,000 (sub)species from ~100 other relevant genera, from the kingdoms of Animalia and Plantae (like \emph{Strongyloides} and \emph{Taenia})}
- \item{All ~21,000 previously accepted names of included (sub)species that have been taxonomically renamed}
+ \item{All ~61,000 (sub)species from the kingdoms of Archaea, Bacteria, Chromista and Protozoa}
+ \item{All ~8,500 (sub)species from these orders of the kingdom of Fungi: Eurotiales, Microascales, Mucorales, Onygenales, Pneumocystales, Saccharomycetales, Schizosaccharomycetales and Tremellales. The kingdom of Fungi is a very large taxon with almost 300,000 different (sub)species, of which most are not microbial (but rather macroscopic, like mushrooms). Because of this, not all fungi fit the scope of this package and including everything would tremendously slow down our algorithms too. By only including the aforementioned taxonomic orders, the most relevant fungi are covered (like all species of \emph{Aspergillus}, \emph{Candida}, \emph{Cryptococcus}, \emph{Histplasma}, \emph{Pneumocystis}, \emph{Saccharomyces} and \emph{Trichophyton}).}
+ \item{All ~150 (sub)species from ~100 other relevant genera from the kingdom of Animalia (like \emph{Strongyloides} and \emph{Taenia})}
+ \item{All ~23,000 previously accepted names of all included (sub)species (these were taxonomically renamed)}
\item{The complete taxonomic tree of all included (sub)species: from kingdom to subspecies}
\item{The responsible author(s) and year of scientific publication}
}
diff --git a/man/ggplot_rsi.Rd b/man/ggplot_rsi.Rd
index 73e8522f..a76bcf0b 100644
--- a/man/ggplot_rsi.Rd
+++ b/man/ggplot_rsi.Rd
@@ -17,7 +17,8 @@ ggplot_rsi(data, position = NULL, x = "antibiotic",
colours = c(S = "#61a8ff", SI = "#61a8ff", I = "#61f7ff", IR =
"#ff6961", R = "#ff6961"), datalabels = TRUE, datalabels.size = 2.5,
datalabels.colour = "gray15", title = NULL, subtitle = NULL,
- caption = NULL, x.title = NULL, y.title = NULL, ...)
+ caption = NULL, x.title = "Antimicrobial", y.title = "Proportion",
+ ...)
geom_rsi(position = NULL, x = c("antibiotic", "interpretation"),
fill = "interpretation", translate_ab = "name",
diff --git a/man/microorganisms.Rd b/man/microorganisms.Rd
index 0e7ff53b..a5c496e7 100755
--- a/man/microorganisms.Rd
+++ b/man/microorganisms.Rd
@@ -3,8 +3,8 @@
\docType{data}
\name{microorganisms}
\alias{microorganisms}
-\title{Data set with ~65,000 microorganisms}
-\format{A \code{\link{data.frame}} with 68,260 observations and 16 variables:
+\title{Data set with ~70,000 microorganisms}
+\format{A \code{\link{data.frame}} with 69,854 observations and 16 variables:
\describe{
\item{\code{mo}}{ID of microorganism as used by this package}
\item{\code{col_id}}{Catalogue of Life ID}
diff --git a/man/microorganisms.codes.Rd b/man/microorganisms.codes.Rd
index 53319cd0..793d6877 100644
--- a/man/microorganisms.codes.Rd
+++ b/man/microorganisms.codes.Rd
@@ -4,7 +4,7 @@
\name{microorganisms.codes}
\alias{microorganisms.codes}
\title{Translation table for microorganism codes}
-\format{A \code{\link{data.frame}} with 4,969 observations and 2 variables:
+\format{A \code{\link{data.frame}} with 4,965 observations and 2 variables:
\describe{
\item{\code{certe}}{Commonly used code of a microorganism}
\item{\code{mo}}{ID of the microorganism in the \code{\link{microorganisms}} data set}
diff --git a/man/microorganisms.old.Rd b/man/microorganisms.old.Rd
index c685c73a..c4aa817b 100644
--- a/man/microorganisms.old.Rd
+++ b/man/microorganisms.old.Rd
@@ -4,7 +4,7 @@
\name{microorganisms.old}
\alias{microorganisms.old}
\title{Data set with previously accepted taxonomic names}
-\format{A \code{\link{data.frame}} with 21,743 observations and 4 variables:
+\format{A \code{\link{data.frame}} with 22,932 observations and 4 variables:
\describe{
\item{\code{col_id}}{Catalogue of Life ID that was originally given}
\item{\code{col_id_new}}{New Catalogue of Life ID that responds to an entry in the \code{\link{microorganisms}} data set}
