- - + Home
-
-
+
How to
@@ -105,77 +105,77 @@
- - + Conduct AMR analysis
- - + Predict antimicrobial resistance
- - + Data sets for download / own use
- - + Conduct principal component analysis for AMR
- - + Determine multi-drug resistance (MDR)
- - + Work with WHONET data
- - + Import data from SPSS/SAS/Stata
- - + Apply EUCAST rules
- - + Get properties of a microorganism
- - + Get properties of an antibiotic
- - + Other: benchmarks @@ -184,21 +184,21 @@
- - + Manual
- - + Authors
-
-
+
Changelog
@@ -207,14 +207,14 @@
- - + Source Code
-
-
+
Survey
diff --git a/docs/LICENSE-text.html b/docs/LICENSE-text.html
index f5ccbf8e5..5677604b3 100644
--- a/docs/LICENSE-text.html
+++ b/docs/LICENSE-text.html
@@ -81,7 +81,7 @@
@@ -89,14 +89,14 @@
- - + Home
-
-
+
How to
@@ -105,77 +105,77 @@
- - + Conduct AMR analysis
- - + Predict antimicrobial resistance
- - + Data sets for download / own use
- - + Conduct principal component analysis for AMR
- - + Determine multi-drug resistance (MDR)
- - + Work with WHONET data
- - + Import data from SPSS/SAS/Stata
- - + Apply EUCAST rules
- - + Get properties of a microorganism
- - + Get properties of an antibiotic
- - + Other: benchmarks @@ -184,21 +184,21 @@
- - + Manual
- - + Authors
-
-
+
Changelog
@@ -207,14 +207,14 @@
- - + Source Code
-
-
+
Survey
diff --git a/docs/articles/AMR.html b/docs/articles/AMR.html
index 0147c806f..72631b3ec 100644
--- a/docs/articles/AMR.html
+++ b/docs/articles/AMR.html
@@ -39,7 +39,7 @@
@@ -47,14 +47,14 @@
- - + Home
-
-
+
How to
@@ -63,77 +63,77 @@
- - + Conduct AMR analysis
- - + Predict antimicrobial resistance
- - + Data sets for download / own use
- - + Conduct principal component analysis for AMR
- - + Determine multi-drug resistance (MDR)
- - + Work with WHONET data
- - + Import data from SPSS/SAS/Stata
- - + Apply EUCAST rules
- - + Get properties of a microorganism
- - + Get properties of an antibiotic
- - + Other: benchmarks @@ -142,21 +142,21 @@
- - + Manual
- - + Authors
-
-
+
Changelog
@@ -165,14 +165,14 @@
- - + Source Code
-
-
+
Survey
@@ -187,13 +187,14 @@
- + +@@ -1553,50 +1519,48 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/@@ -47,14 +47,14 @@diff --git a/docs/articles/AMR_files/anchor-sections-1.0/anchor-sections.css b/docs/articles/AMR_files/anchor-sections-1.0/anchor-sections.css new file mode 100644 index 000000000..07aee5fcb --- /dev/null +++ b/docs/articles/AMR_files/anchor-sections-1.0/anchor-sections.css @@ -0,0 +1,4 @@ +/* Styles for section anchors */ +a.anchor-section {margin-left: 10px; visibility: hidden; color: inherit;} +a.anchor-section::before {content: '#';} +.hasAnchor:hover a.anchor-section {visibility: visible;} diff --git a/docs/articles/AMR_files/anchor-sections-1.0/anchor-sections.js b/docs/articles/AMR_files/anchor-sections-1.0/anchor-sections.js new file mode 100644 index 000000000..570f99a0a --- /dev/null +++ b/docs/articles/AMR_files/anchor-sections-1.0/anchor-sections.js @@ -0,0 +1,33 @@ +// Anchor sections v1.0 written by Atsushi Yasumoto on Oct 3rd, 2020. +document.addEventListener('DOMContentLoaded', function() { + // Do nothing if AnchorJS is used + if (typeof window.anchors === 'object' && anchors.hasOwnProperty('hasAnchorJSLink')) { + return; + } + + const h = document.querySelectorAll('h1, h2, h3, h4, h5, h6'); + + // Do nothing if sections are already anchored + if (Array.from(h).some(x => x.classList.contains('hasAnchor'))) { + return null; + } + + // Use section id when pandoc runs with --section-divs + const section_id = function(x) { + return ((x.classList.contains('section') || (x.tagName === 'SECTION')) + ? x.id : ''); + }; + + // Add anchors + h.forEach(function(x) { + const id = x.id || section_id(x.parentElement); + if (id === '') { + return null; + } + let anchor = document.createElement('a'); + anchor.href = '#' + id; + anchor.classList = ['anchor-section']; + x.classList.add('hasAnchor'); + x.appendChild(anchor); + }); +}); diff --git a/docs/articles/AMR_files/figure-html/disk_plots-1.png b/docs/articles/AMR_files/figure-html/disk_plots-1.png index d7c00b2c0..6bcac66f3 100644 Binary files a/docs/articles/AMR_files/figure-html/disk_plots-1.png and b/docs/articles/AMR_files/figure-html/disk_plots-1.png differ diff --git a/docs/articles/AMR_files/figure-html/disk_plots_mo_ab-1.png b/docs/articles/AMR_files/figure-html/disk_plots_mo_ab-1.png index 7559c2f5f..95f398e1e 100644 Binary files a/docs/articles/AMR_files/figure-html/disk_plots_mo_ab-1.png and b/docs/articles/AMR_files/figure-html/disk_plots_mo_ab-1.png differ diff --git a/docs/articles/AMR_files/figure-html/mic_plots-1.png b/docs/articles/AMR_files/figure-html/mic_plots-1.png index 3efa76392..3b1cc0a75 100644 Binary files a/docs/articles/AMR_files/figure-html/mic_plots-1.png and b/docs/articles/AMR_files/figure-html/mic_plots-1.png differ diff --git a/docs/articles/AMR_files/figure-html/mic_plots-2.png b/docs/articles/AMR_files/figure-html/mic_plots-2.png index 7a2461a94..35e3bcb13 100644 Binary files a/docs/articles/AMR_files/figure-html/mic_plots-2.png and b/docs/articles/AMR_files/figure-html/mic_plots-2.png differ diff --git a/docs/articles/AMR_files/figure-html/mic_plots_mo_ab-1.png b/docs/articles/AMR_files/figure-html/mic_plots_mo_ab-1.png index c863f5da7..05aa3890a 100644 Binary files a/docs/articles/AMR_files/figure-html/mic_plots_mo_ab-1.png and b/docs/articles/AMR_files/figure-html/mic_plots_mo_ab-1.png differ diff --git a/docs/articles/AMR_files/figure-html/mic_plots_mo_ab-2.png b/docs/articles/AMR_files/figure-html/mic_plots_mo_ab-2.png index bb86218ea..0ddd0f84f 100644 Binary files a/docs/articles/AMR_files/figure-html/mic_plots_mo_ab-2.png and b/docs/articles/AMR_files/figure-html/mic_plots_mo_ab-2.png differ diff --git a/docs/articles/AMR_files/figure-html/plot 1-1.png b/docs/articles/AMR_files/figure-html/plot 1-1.png index b40a568cc..97c68a9cf 100644 Binary files a/docs/articles/AMR_files/figure-html/plot 1-1.png and b/docs/articles/AMR_files/figure-html/plot 1-1.png differ diff --git a/docs/articles/AMR_files/figure-html/plot 3-1.png b/docs/articles/AMR_files/figure-html/plot 3-1.png index bdf38bef2..3e2a6e77d 100644 Binary files a/docs/articles/AMR_files/figure-html/plot 3-1.png and b/docs/articles/AMR_files/figure-html/plot 3-1.png differ diff --git a/docs/articles/AMR_files/figure-html/plot 4-1.png b/docs/articles/AMR_files/figure-html/plot 4-1.png index dabc0b45c..73d0ca8f7 100644 Binary files a/docs/articles/AMR_files/figure-html/plot 4-1.png and b/docs/articles/AMR_files/figure-html/plot 4-1.png differ diff --git a/docs/articles/AMR_files/figure-html/plot 5-1.png b/docs/articles/AMR_files/figure-html/plot 5-1.png index f1c786d05..6f8d63a04 100644 Binary files a/docs/articles/AMR_files/figure-html/plot 5-1.png and b/docs/articles/AMR_files/figure-html/plot 5-1.png differ diff --git a/docs/articles/EUCAST.html b/docs/articles/EUCAST.html index ce5e1e906..3d86dd96b 100644 --- a/docs/articles/EUCAST.html +++ b/docs/articles/EUCAST.html @@ -39,7 +39,7 @@
How to conduct AMR data analysis
Matthijs S. Berends
-04 March 2021
+27 April 2021
Source:vignettes/AMR.Rmd@@ -202,7 +203,7 @@ -AMR.RmdNote: values on this page will change with every website update since they are based on randomly created values and the page was written in R Markdown. However, the methodology remains unchanged. This page was generated on 04 March 2021.
+Note: values on this page will change with every website update since they are based on randomly created values and the page was written in R Markdown. However, the methodology remains unchanged. This page was generated on 27 April 2021.
Introduction
@@ -233,21 +234,21 @@- 2021-03-04 +2021-04-27 abcd Escherichia coli S S - 2021-03-04 +2021-04-27 abcd Escherichia coli S R - @@ -995,10 +994,10 @@ Longest: 242021-03-04 +2021-04-27 efgh Escherichia coli R @@ -260,14 +261,14 @@ Needed R packagesAs with many uses in R, we need some additional packages for AMR data analysis. Our package works closely together with the tidyverse packages
dplyrandggplot2by RStudio. The tidyverse tremendously improves the way we conduct data science - it allows for a very natural way of writing syntaxes and creating beautiful plots in R.We will also use the
-cleanerpackage, that can be used for cleaning data and creating frequency tables.-
library(dplyr) ++# install.packages(c("dplyr", "ggplot2", "AMR", "cleaner"))+library(dplyr) library(ggplot2) library(AMR) library(cleaner) # (if not yet installed, install with:) -# install.packages(c("dplyr", "ggplot2", "AMR", "cleaner"))
@@ -279,37 +280,37 @@Patients
To start with patients, we need a unique list of patients.
- +The
-LETTERSobject is available in R - it’s a vector with 26 characters:AtoZ. Thepatientsobject we just created is now a vector of length 260, with values (patient IDs) varying fromA1toZ10. Now we we also set the gender of our patients, by putting the ID and the gender in a table:-
patients_table <- data.frame(patient_id = patients, ++ rep("F", 125)))+patients_table <- data.frame(patient_id = patients, gender = c(rep("M", 135), - rep("F", 125)))
The first 135 patient IDs are now male, the other 125 are female.
Dates
Let’s pretend that our data consists of blood cultures isolates from between 1 January 2010 and 1 January 2018.
- +This
datesobject now contains all days in our date range.Microorganisms
For this tutorial, we will uses four different microorganisms: Escherichia coli, Staphylococcus aureus, Streptococcus pneumoniae, and Klebsiella pneumoniae:
-+-
bacteria <- c("Escherichia coli", "Staphylococcus aureus", - "Streptococcus pneumoniae", "Klebsiella pneumoniae")+bacteria <- c("Escherichia coli", "Staphylococcus aureus", + "Streptococcus pneumoniae", "Klebsiella pneumoniae")
Put everything together
Using the
-sample()function, we can randomly select items from all objects we defined earlier. To let our fake data reflect reality a bit, we will also approximately define the probabilities of bacteria and the antibiotic results, using therandom_rsi()function.-
sample_size <- 20000 ++ GEN = random_rsi(sample_size, prob_RSI = c(0.08, 0.92, 0.00)))+sample_size <- 20000 data <- data.frame(date = sample(dates, size = sample_size, replace = TRUE), patient_id = sample(patients, size = sample_size, replace = TRUE), hospital = sample(c("Hospital A", @@ -323,13 +324,13 @@ AMX = random_rsi(sample_size, prob_RSI = c(0.35, 0.60, 0.05)), AMC = random_rsi(sample_size, prob_RSI = c(0.15, 0.75, 0.10)), CIP = random_rsi(sample_size, prob_RSI = c(0.20, 0.80, 0.00)), - GEN = random_rsi(sample_size, prob_RSI = c(0.08, 0.92, 0.00)))
Using the
-left_join()function from thedplyrpackage, we can ‘map’ the gender to the patient ID using thepatients_tableobject we created earlier:+-
data <- data %>% left_join(patients_table)+data <- data %>% left_join(patients_table)
The resulting data set contains 20,000 blood culture isolates. With the
-head()function we can preview the first 6 rows of this data set:+-
head(data)+head(data)
date @@ -344,20 +345,42 @@- +2016-09-27 -F2 -Hospital C -Escherichia coli +2016-05-26 +M10 +Hospital D +Staphylococcus aureus +S S R S +M ++ +2014-05-22 +K4 +Hospital B +Staphylococcus aureus +R +S +S +S +M ++ 2012-07-31 +I4 +Hospital D +Streptococcus pneumoniae +R +S +S S M - 2012-07-08 -R4 -Hospital D +2011-03-22 +V6 +Hospital C Staphylococcus aureus S S @@ -366,46 +389,24 @@F - -2017-04-12 -X9 -Hospital A -Escherichia coli -S -S -S -S -F -- -2012-09-29 -I9 +2012-04-09 +G7 Hospital B Escherichia coli -S -S -S -S -M -- 2011-06-11 -G6 -Hospital C -Streptococcus pneumoniae I -I -R -R +S +S +S M - @@ -419,8 +420,8 @@ Cleaning the data2010-10-11 -X6 -Hospital D -Streptococcus pneumoniae +2015-08-25 +Z3 +Hospital C +Staphylococcus aureus +S S S -R S F We also created a package dedicated to data cleaning and checking, called the
cleanerpackage. Itfreq()function can be used to create frequency tables.For example, for the
-gendervariable:+-
data %>% freq(gender)+data %>% freq(gender)
Frequency table
Class: character
Length: 20,000
@@ -441,16 +442,16 @@ Longest: 11 M -10,367 -51.84% -10,367 -51.84% +10,477 +52.39% +10,477 +52.39% 2 F -9,633 -48.17% +9,523 +47.62% 20,000 100.00% So, we can draw at least two conclusions immediately. From a data scientists perspective, the data looks clean: only values
MandF. From a researchers perspective: there are slightly more men. Nothing we didn’t already know.The data is already quite clean, but we still need to transform some variables. The
- +bacteriacolumn now consists of text, and we want to add more variables based on microbial IDs later on. So, we will transform this column to valid IDs. Themutate()function of thedplyrpackage makes this really easy:We also want to transform the antibiotics, because in real life data we don’t know if they are really clean. The
- +as.rsi()function ensures reliability and reproducibility in these kind of variables. Themutate_at()will run theas.rsi()function on defined variables:Finally, we will apply EUCAST rules on our antimicrobial results. In Europe, most medical microbiological laboratories already apply these rules. Our package features their latest insights on intrinsic resistance and exceptional phenotypes. Moreover, the
eucast_rules()function can also apply additional rules, like forcingampicillin = R whenamoxicillin/clavulanic acid = R.Because the amoxicillin (column
-AMX) and amoxicillin/clavulanic acid (columnAMC) in our data were generated randomly, some rows will undoubtedly contain AMX = S and AMC = R, which is technically impossible. Theeucast_rules()fixes this:+-
data <- eucast_rules(data, col_mo = "bacteria", rules = "all")+data <- eucast_rules(data, col_mo = "bacteria", rules = "all")
Adding new variables
Now that we have the microbial ID, we can add some taxonomic properties:
--
data <- data %>% ++ species = mo_species(bacteria))+data <- data %>% mutate(gramstain = mo_gramstain(bacteria), genus = mo_genus(bacteria), - species = mo_species(bacteria))
First isolates
@@ -489,25 +490,25 @@ Longest: 1(…) When preparing a cumulative antibiogram to guide clinical decisions about empirical antimicrobial therapy of initial infections, only the first isolate of a given species per patient, per analysis period (eg, one year) should be included, irrespective of body site, antimicrobial susceptibility profile, or other phenotypical characteristics (eg, biotype). The first isolate is easily identified, and cumulative antimicrobial susceptibility test data prepared using the first isolate are generally comparable to cumulative antimicrobial susceptibility test data calculated by other methods, providing duplicate isolates are excluded.
M39-A4 Analysis and Presentation of Cumulative Antimicrobial Susceptibility Test Data, 4th Edition. CLSI, 2014. Chapter 6.4This
-AMRpackage includes this methodology with thefirst_isolate()function. It adopts the episode of a year (can be changed by user) and it starts counting days after every selected isolate. This new variable can easily be added to our data:+-
data <- data %>% +-+data <- data %>% mutate(first = first_isolate()) -# NOTE: Using column 'bacteria' as input for `col_mo`. -# NOTE: Using column 'date' as input for `col_date`. -# NOTE: Using column 'patient_id' as input for `col_patient_id`.
So only 28.4% is suitable for resistance analysis! We can now filter on it with the
-filter()function, also from thedplyrpackage:+# ℹ Using column 'bacteria' as input for `col_mo`. +# ℹ Using column 'date' as input for `col_date`. +# ℹ Using column 'patient_id' as input for `col_patient_id`.-
data_1st <- data %>% - filter(first == TRUE)So only 53.1% is suitable for resistance analysis! We can now filter on it with the
+filter()function, also from thedplyrpackage:+data_1st <- data %>% + filter(first == TRUE)
For future use, the above two syntaxes can be shortened with the
-filter_first_isolate()function:+-
data_1st <- data %>% - filter_first_isolate()+data_1st <- data %>% + filter_first_isolate()
First weighted isolates
-We made a slight twist to the CLSI algorithm, to take into account the antimicrobial susceptibility profile. Have a look at all E. coli isolates of patient V8, sorted on date:
+We made a slight twist to the CLSI algorithm, to take into account the antimicrobial susceptibility profile. Have a look at all E. coli isolates of patient C8, sorted on date:
-isolate @@ -523,8 +524,8 @@ Longest: 11 -2010-01-25 -V8 +2010-02-15 +C8 B_ESCHR_COLI S S @@ -534,63 +535,52 @@ Longest: 12 -2010-03-27 -V8 +2010-03-23 +C8 B_ESCHR_COLI R S -R +S S FALSE 3 -2010-05-28 -V8 +2010-05-20 +C8 B_ESCHR_COLI -R -I +S +S S S FALSE 4 -2010-07-06 -V8 +2011-01-07 +C8 B_ESCHR_COLI -S -S -S R +S +S +S FALSE 5 -2010-10-18 -V8 +2011-01-09 +C8 B_ESCHR_COLI +R S S R -S FALSE 6 -2010-11-04 -V8 -B_ESCHR_COLI -R -S -S -S -FALSE -- -7 -2011-04-06 -V8 +2011-01-25 +C8 B_ESCHR_COLI S S @@ -598,10 +588,10 @@ Longest: 1S TRUE - 8 -2011-06-22 -V8 ++ -7 +2011-02-09 +C8 B_ESCHR_COLI S S @@ -609,38 +599,47 @@ Longest: 1S FALSE - 9 -2011-06-27 -V8 ++ +8 +2011-03-09 +C8 B_ESCHR_COLI S S S +S +TRUE ++ 9 +2011-04-04 +C8 +B_ESCHR_COLI R +S +S +S FALSE 10 -2011-09-25 -V8 +2011-09-26 +C8 B_ESCHR_COLI -S -S +R +I S S FALSE Only 2 isolates are marked as ‘first’ according to CLSI guideline. But when reviewing the antibiogram, it is obvious that some isolates are absolutely different strains and should be included too. This is why we weigh isolates, based on their antibiogram. The
+key_antibiotics()function adds a vector with 18 key antibiotics: 6 broad spectrum ones, 6 small spectrum for Gram negatives and 6 small spectrum for Gram positives. These can be defined by the user.Only 3 isolates are marked as ‘first’ according to CLSI guideline. But when reviewing the antibiogram, it is obvious that some isolates are absolutely different strains and should be included too. This is why we weigh isolates, based on their antibiogram. The
key_antibiotics()function adds a vector with 18 key antibiotics: 6 broad spectrum ones, 6 small spectrum for Gram negatives and 6 small spectrum for Gram positives. These can be defined by the user.If a column exists with a name like ‘key(…)ab’ the
-first_isolate()function will automatically use it and determine the first weighted isolates. Mind the NOTEs in below output:+-
data <- data %>% - mutate(keyab = key_antibiotics()) %>% - mutate(first_weighted = first_isolate()) -# NOTE: Using column 'keyab' as input for `col_keyantibiotics`. Use -# col_keyantibiotics = FALSE to prevent this.+data <- data %>% + mutate(keyab = key_antibiotics()) %>% + mutate(first_weighted = first_isolate())
-isolate @@ -657,8 +656,8 @@ Longest: 11 -2010-01-25 -V8 +2010-02-15 +C8 B_ESCHR_COLI S S @@ -669,127 +668,127 @@ Longest: 12 -2010-03-27 -V8 +2010-03-23 +C8 B_ESCHR_COLI R S +S +S +FALSE +FALSE ++ +3 +2010-05-20 +C8 +B_ESCHR_COLI +S +S +S +S +FALSE +FALSE ++ +4 +2011-01-07 +C8 +B_ESCHR_COLI +R +S +S +S +FALSE +FALSE ++ +5 +2011-01-09 +C8 +B_ESCHR_COLI +R +S +S +R +FALSE +FALSE ++ +6 +2011-01-25 +C8 +B_ESCHR_COLI +S +S +S +S +TRUE +TRUE ++ +7 +2011-02-09 +C8 +B_ESCHR_COLI +S +S R S FALSE +FALSE ++ 8 +2011-03-09 +C8 +B_ESCHR_COLI +S +S +S +S +TRUE TRUE - +3 -2010-05-28 -V8 +9 +2011-04-04 +C8 +B_ESCHR_COLI +R +S +S +S +FALSE +FALSE ++ -10 +2011-09-26 +C8 B_ESCHR_COLI R I S S FALSE -TRUE -- -4 -2010-07-06 -V8 -B_ESCHR_COLI -S -S -S -R FALSE -TRUE -- -5 -2010-10-18 -V8 -B_ESCHR_COLI -S -S -R -S -FALSE -TRUE -- -6 -2010-11-04 -V8 -B_ESCHR_COLI -R -S -S -S -FALSE -TRUE -- -7 -2011-04-06 -V8 -B_ESCHR_COLI -S -S -S -S -TRUE -TRUE -- -8 -2011-06-22 -V8 -B_ESCHR_COLI -S -S -R -S -FALSE -TRUE -- -9 -2011-06-27 -V8 -B_ESCHR_COLI -S -S -S -R -FALSE -TRUE -- 10 -2011-09-25 -V8 -B_ESCHR_COLI -S -S -S -S -FALSE -TRUE Instead of 2, now 10 isolates are flagged. In total, 78.2% of all isolates are marked ‘first weighted’ - 49.9% more than when using the CLSI guideline. In real life, this novel algorithm will yield 5-10% more isolates than the classic CLSI guideline.
+Instead of 3, now 3 isolates are flagged. In total, 53.1% of all isolates are marked ‘first weighted’ - 0% more than when using the CLSI guideline. In real life, this novel algorithm will yield 5-10% more isolates than the classic CLSI guideline.
As with
-filter_first_isolate(), there’s a shortcut for this new algorithm too:--
data_1st <- data %>% - filter_first_weighted_isolate()So we end up with 15,645 isolates for analysis.
+++data_1st <- data %>% + filter_first_weighted_isolate()
So we end up with 10,622 isolates for analysis.
We can remove unneeded columns:
- +Now our data looks like:
-+-
head(data_1st)+head(data_1st)
@@ -825,44 +824,44 @@ Longest: 1 - -1 -2016-09-27 -F2 -Hospital C -B_ESCHR_COLI -R +2 +2014-05-22 +K4 +Hospital B +B_STPHY_AURS R S S +S M -Gram-negative -Escherichia -coli -TRUE -- +2 -2012-07-08 -R4 -Hospital D -B_STPHY_AURS -S -S -R -S -F Gram-positive Staphylococcus aureus TRUE + 3 +2012-07-31 +I4 +Hospital D +B_STRPT_PNMN +R +R +S +R +M +Gram-positive +Streptococcus +pneumoniae +TRUE +- 4 -2012-09-29 -I9 +5 +2012-04-09 +G7 Hospital B B_ESCHR_COLI -S +I S S S @@ -873,53 +872,53 @@ Longest: 1TRUE - 5 -2011-06-11 -G6 -Hospital C -B_STRPT_PNMN -I -I -R +9 +2010-04-07 +K8 +Hospital B +B_ESCHR_COLI R +S +S +S M -Gram-positive -Streptococcus -pneumoniae +Gram-negative +Escherichia +coli TRUE - -6 -2010-10-11 -X6 -Hospital D -B_STRPT_PNMN -S -S -R -R -F -Gram-positive -Streptococcus -pneumoniae -TRUE -- +7 -2012-02-27 -L9 +11 +2015-04-22 +U6 Hospital D B_ESCHR_COLI +R +R +R S -S -S -S -M +F Gram-negative Escherichia coli TRUE + 14 +2012-10-27 +U5 +Hospital A +B_KLBSL_PNMN +R +S +R +S +F +Gram-negative +Klebsiella +pneumoniae +TRUE +Time for the analysis!
@@ -934,15 +933,15 @@ Longest: 1 Dispersion of speciesTo just get an idea how the species are distributed, create a frequency table with our
freq()function. We created thegenusandspeciescolumn earlier based on the microbial ID. Withpaste(), we can concatenate them together.The
- +freq()function can be used like the base R language was intended:Or can be used like the
-dplyrway, which is easier readable:+-
data_1st %>% freq(genus, species)+data_1st %>% freq(genus, species)
Frequency table
Class: character
-Length: 15,645
-Available: 15,645 (100%, NA: 0 = 0%)
+Length: 10,622
+Available: 10,622 (100%, NA: 0 = 0%)
Unique: 4Shortest: 16
@@ -959,33 +958,33 @@ Longest: 24
Longest: 241 Escherichia coli -7,799 -49.85% -7,799 -49.85% +4,606 +43.36% +4,606 +43.36% 2 Staphylococcus aureus -3,935 -25.15% -11,734 -75.00% +2,710 +25.51% +7,316 +68.88% 3 Streptococcus pneumoniae -2,271 -14.52% -14,005 -89.52% +2,131 +20.06% +9,447 +88.94% 4 Klebsiella pneumoniae -1,640 -10.48% -15,645 +1,175 +11.06% +10,622 100.00% Overview of different bug/drug combinations
If you want to get a quick glance of the number of isolates in different bug/drug combinations, you can use the
-bug_drug_combinations()function:-
data_1st %>% ++ head() # show first 6 rows+data_1st %>% bug_drug_combinations() %>% - head() # show first 6 rows
mo @@ -1012,58 +1011,58 @@ Longest: 24E. coli AMX -3722 -253 -3824 -7799 +2158 +150 +2298 +4606 E. coli AMC -6174 -320 -1305 -7799 +3349 +191 +1066 +4606 E. coli CIP -5974 +3327 0 -1825 -7799 +1279 +4606 E. coli GEN -7009 +4059 0 -790 -7799 +547 +4606 K. pneumoniae AMX 0 0 -1640 -1640 +1175 +1175 K. pneumoniae AMC -1259 -58 -323 -1640 +927 +46 +202 +1175 Using Tidyverse selections, you can also select columns based on the antibiotic class they are in:
--
data_1st %>% ++ bug_drug_combinations()+data_1st %>% select(bacteria, fluoroquinolones()) %>% - bug_drug_combinations()
# Selecting fluoroquinolones: column 'CIP' (ciprofloxacin)
@@ -1116,14 +1115,14 @@ Longest: 24 Resistance percentages@@ -1078,34 +1077,34 @@ Longest: 24 E. coli CIP -5974 +3327 0 -1825 -7799 +1279 +4606 K. pneumoniae CIP -1243 +917 0 -397 -1640 +258 +1175 S. aureus CIP -2994 +2035 0 -941 -3935 +675 +2710 S. pneumoniae CIP -1758 +1698 0 -513 -2271 +433 +2131 The functions
resistance()andsusceptibility()can be used to calculate antimicrobial resistance or susceptibility. For more specific analyses, the functionsproportion_S(),proportion_SI(),proportion_I(),proportion_IR()andproportion_R()can be used to determine the proportion of a specific antimicrobial outcome.As per the EUCAST guideline of 2019, we calculate resistance as the proportion of R (
-proportion_R(), equal toresistance()) and susceptibility as the proportion of S and I (proportion_SI(), equal tosusceptibility()). These functions can be used on their own:+-
data_1st %>% resistance(AMX) -# [1] 0.536721+data_1st %>% resistance(AMX) +# [1] 0.5462248
Or can be used in conjuction with
-group_by()andsummarise(), both from thedplyrpackage:-
data_1st %>% ++ summarise(amoxicillin = resistance(AMX))+data_1st %>% group_by(hospital) %>% - summarise(amoxicillin = resistance(AMX))
# `summarise()` ungrouping output (override with `.groups` argument)@@ -1133,28 +1132,28 @@ Longest: 24 Hospital A -0.5446167 +0.5469388 Hospital B -0.5282637 +0.5456022 Hospital C -0.5516212 +0.5451654 Hospital D -0.5281008 +0.5470046 Of course it would be very convenient to know the number of isolates responsible for the percentages. For that purpose the
-n_rsi()can be used, which works exactly liken_distinct()from thedplyrpackage. It counts all isolates available for every group (i.e. values S, I or R):-
data_1st %>% ++ available = n_rsi(AMX))+data_1st %>% group_by(hospital) %>% summarise(amoxicillin = resistance(AMX), - available = n_rsi(AMX))
# `summarise()` ungrouping output (override with `.groups` argument)@@ -1165,33 +1164,33 @@ Longest: 24 Hospital A -0.5446167 -4774 +0.5469388 +3185 Hospital B -0.5282637 -5431 +0.5456022 +3695 Hospital C -0.5516212 -2344 +0.5451654 +1572 Hospital D -0.5281008 -3096 +0.5470046 +2170 These functions can also be used to get the proportion of multiple antibiotics, to calculate empiric susceptibility of combination therapies very easily:
--
data_1st %>% ++ amoxiclav_genta = susceptibility(AMC, GEN))+data_1st %>% group_by(genus) %>% summarise(amoxiclav = susceptibility(AMC), gentamicin = susceptibility(GEN), - amoxiclav_genta = susceptibility(AMC, GEN))
# `summarise()` ungrouping output (override with `.groups` argument)@@ -1203,33 +1202,33 @@ Longest: 24 Escherichia -0.8326709 -0.8987050 -0.9860238 +0.7685627 +0.8812419 +0.9789405 Klebsiella -0.8030488 -0.8993902 -0.9786585 +0.8280851 +0.8919149 +0.9838298 Staphylococcus -0.8320203 -0.9263024 -0.9878018 +0.7952030 +0.8892989 +0.9826568 Streptococcus -0.5482166 +0.5405913 0.0000000 -0.5482166 +0.5405913 To make a transition to the next part, let’s see how this difference could be plotted:
--
data_1st %>% ++# `summarise()` ungrouping output (override with `.groups` argument)+data_1st %>% group_by(genus) %>% summarise("1. Amoxi/clav" = susceptibility(AMC), "2. Gentamicin" = susceptibility(GEN), @@ -1240,15 +1239,15 @@ Longest: 24 y = value, fill = antibiotic)) + geom_col(position = "dodge2") -# `summarise()` ungrouping output (override with `.groups` argument)
@@ -1368,8 +1370,8 @@ Longest: 24 Independence testPlots
To show results in plots, most R users would nowadays use the
-ggplot2package. This package lets you create plots in layers. You can read more about it on their website. A quick example would look like these syntaxes:-
ggplot(data = a_data_set, ++ geom_bar(aes(year))+ggplot(data = a_data_set, mapping = aes(x = year, y = value)) + geom_col() + @@ -1259,16 +1258,16 @@ Longest: 24 # or as short as: ggplot(a_data_set) + - geom_bar(aes(year))
The
- +AMRpackage contains functions to extend thisggplot2package, for examplegeom_rsi(). It automatically transforms data withcount_df()orproportion_df()and show results in stacked bars. Its simplest and shortest example:
Omit the
translate_ab = FALSEto have the antibiotic codes (AMX, AMC, CIP, GEN) translated to official WHO names (amoxicillin, amoxicillin/clavulanic acid, ciprofloxacin, gentamicin).If we group on e.g. the
-genuscolumn and add some additional functions from our package, we can create this:-
# group the data on `genus` ++ theme(axis.text.y = element_text(face = "italic"))+# group the data on `genus` ggplot(data_1st %>% group_by(genus)) + # create bars with genus on x axis # it looks for variables with class `rsi`, @@ -1287,79 +1286,82 @@ Longest: 24 subtitle = "(this is fake data)") + # and print genus in italic to follow our convention # (is now y axis because we turned the plot) - theme(axis.text.y = element_text(face = "italic"))
To simplify this, we also created the
-ggplot_rsi()function, which combines almost all above functions:-
data_1st %>% ++ coord_flip()+data_1st %>% group_by(genus) %>% ggplot_rsi(x = "genus", facet = "antibiotic", breaks = 0:4 * 25, datalabels = FALSE) + - coord_flip()
Plotting MIC and disk diffusion values
The AMR package also extends the
plot()andggplot()functions for plotting minimum inhibitory concentrations (MIC, created withas.mic()) and disk diffusion diameters (created withas.disk()).With the
-random_mic()andrandom_disk()functions, we can generate sampled values for the new data types (S3 classes)<mic>and<disk>:+-
mic_values <- random_mic(size = 100) +-+mic_values <- random_mic(size = 100) mic_values # Class <mic> -# [1] 0.25 0.25 8 0.25 256 64 2 1 16 2 -# [11] 0.125 2 0.125 16 0.125 0.25 0.5 0.125 64 0.25 -# [21] 32 0.125 0.125 0.5 0.125 0.25 0.25 0.0625 0.5 0.5 -# [31] 2 0.5 0.5 0.25 128 0.25 128 0.5 0.125 0.25 -# [41] 4 4 128 0.125 0.125 2 0.25 0.125 4 256 -# [51] 128 128 128 2 1 32 16 2 0.25 8 -# [61] 2 32 64 0.125 32 128 0.125 0.0625 8 2 -# [71] 0.0625 64 0.5 0.5 128 2 8 1 16 0.5 -# [81] 256 128 0.125 0.125 64 1 0.5 4 4 0.125 -# [91] 0.25 0.125 0.0625 2 256 1 256 0.5 0.125 32
+# [1] 16 512 256 16 512 1 256 512 +# [9] 2 16 1 16 <=0.0625 1 0.5 <=0.0625 +# [17] 8 128 16 0.125 0.125 1 1 4 +# [25] 0.5 0.125 8 128 2 <=0.0625 <=0.0625 128 +# [33] 0.5 64 512 0.25 32 32 1 4 +# [41] 4 256 32 1 1 0.5 512 128 +# [49] 0.125 0.25 8 128 8 8 <=0.0625 0.5 +# [57] 8 2 64 0.25 8 16 512 4 +# [65] 2 512 0.25 0.5 8 128 2 512 +# [73] 16 1 128 2 512 32 <=0.0625 0.125 +# [81] 128 16 512 0.125 64 128 0.25 1 +# [89] 0.25 64 <=0.0625 0.25 128 2 0.5 8 +# [97] <=0.0625 <=0.0625 <=0.0625 0.25-
# base R: -plot(mic_values)+# base R: +plot(mic_values)
-
+-
# ggplot2: -ggplot(mic_values)+# ggplot2: +ggplot(mic_values)
But we could also be more specific, by generating MICs that are likely to be found in E. coli for ciprofloxacin:
-+-
mic_values <- random_mic(size = 100, mo = "E. coli", ab = "cipro")+mic_values <- random_mic(size = 100, mo = "E. coli", ab = "cipro")
For the
plot()andggplot()function, we can define the microorganism and an antimicrobial agent the same way. This will add the interpretation of those values according to a chosen guidelines (defaults to the latest EUCAST guideline).Default colours are colour-blind friendly, while maintaining the convention that e.g. ‘susceptible’ should be green and ‘resistant’ should be red:
-+-
# base R: -plot(mic_values, mo = "E. coli", ab = "cipro")+# base R: +plot(mic_values, mo = "E. coli", ab = "cipro")
-
+-
# ggplot2: -ggplot(mic_values, mo = "E. coli", ab = "cipro")+# ggplot2: +ggplot(mic_values, mo = "E. coli", ab = "cipro")
For disk diffusion values, there is not much of a difference in plotting:
-+-
disk_values <- random_disk(size = 100, mo = "E. coli", ab = "cipro") -# NOTE: Translation to one microorganism was guessed with uncertainty. Use -# `mo_uncertainties()` to review it. +-+disk_values <- random_disk(size = 100, mo = "E. coli", ab = "cipro") +# ℹ Translation is uncertain of one microorganism. Use `mo_uncertainties()` +# to review it. disk_values # Class <disk> -# [1] 23 25 18 24 23 20 18 29 21 19 29 22 21 25 25 23 19 30 26 30 24 22 29 21 28 -# [26] 20 18 31 17 28 31 17 28 29 24 24 23 29 27 20 31 26 23 26 17 26 25 30 24 29 -# [51] 24 19 20 20 30 29 26 29 28 18 30 18 20 31 26 30 28 22 19 22 31 25 23 21 23 -# [76] 20 20 17 23 21 29 26 27 27 31 27 26 26 30 24 20 28 29 28 18 29 26 25 22 30
+# [1] 25 22 17 30 26 27 24 22 30 23 31 26 21 29 19 27 27 23 22 18 26 30 28 30 28 +# [26] 18 20 22 20 22 21 22 24 22 21 25 18 31 26 18 21 24 31 17 22 17 31 19 31 25 +# [51] 19 21 28 24 18 27 23 19 26 26 20 18 19 30 23 20 19 30 24 27 21 17 31 30 23 +# [76] 19 29 23 27 28 21 17 27 20 23 28 31 28 29 31 27 24 18 19 29 31 18 29 17 28-
# base R: -plot(disk_values, mo = "E. coli", ab = "cipro")+# base R: +plot(disk_values, mo = "E. coli", ab = "cipro")
And when using the
-ggplot2package, but now choosing the latest implemented CLSI guideline (notice that the EUCAST-specific term “Incr. exposure” has changed to “Intermediate”):-
ggplot(disk_values, ++ guideline = "CLSI")+ggplot(disk_values, mo = "E. coli", ab = "cipro", - guideline = "CLSI")
The next example uses the
example_isolatesdata set. This is a data set included with this package and contains 2,000 microbial isolates with their full antibiograms. It reflects reality and can be used to practice AMR data analysis.We will compare the resistance to fosfomycin (column
-FOS) in hospital A and D. The input for thefisher.test()can be retrieved with a transformation like this:-
# use package 'tidyr' to pivot data: ++# [2,] 24 33+# use package 'tidyr' to pivot data: library(tidyr) check_FOS <- example_isolates %>% @@ -1385,10 +1387,10 @@ Longest: 24 check_FOS # A D # [1,] 25 77 -# [2,] 24 33
We can apply the test now with:
--
# do Fisher's Exact Test ++# 0.4488318+# do Fisher's Exact Test fisher.test(check_FOS) # # Fisher's Exact Test for Count Data @@ -1400,7 +1402,7 @@ Longest: 24 # 0.2111489 0.9485124 # sample estimates: # odds ratio -# 0.4488318
As can be seen, the p value is 0.031, which means that the fosfomycin resistance found in isolates from patients in hospital A and D are really different.
- - + Home
-
-
+
How to
@@ -63,77 +63,77 @@
- - + Conduct AMR analysis
- - + Predict antimicrobial resistance
- - + Data sets for download / own use
- - + Conduct principal component analysis for AMR
- - + Determine multi-drug resistance (MDR)
- - + Work with WHONET data
- - + Import data from SPSS/SAS/Stata
- - + Apply EUCAST rules
- - + Get properties of a microorganism
- - + Get properties of an antibiotic
- - + Other: benchmarks @@ -142,21 +142,21 @@
- - + Manual
- - + Authors
-
-
+
Changelog
@@ -165,14 +165,14 @@
- - + Source Code
-
-
+
Survey
@@ -187,7 +187,8 @@
- + +@@ -1360,23 +1335,22 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/@@ -1235,8 +1212,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/@@ -1101,8 +1083,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/@@ -47,14 +47,14 @@
How to apply EUCAST rules
@@ -215,8 +216,8 @@ ExamplesThese rules can be used to discard impossible bug-drug combinations in your data. For example, Klebsiella produces beta-lactamase that prevents ampicillin (or amoxicillin) from working against it. In other words, practically every strain of Klebsiella is resistant to ampicillin.
Sometimes, laboratory data can still contain such strains with ampicillin being susceptible to ampicillin. This could be because an antibiogram is available before an identification is available, and the antibiogram is then not re-interpreted based on the identification (namely, Klebsiella). EUCAST expert rules solve this, that can be applied using
-eucast_rules():-
oops <- data.frame(mo = c("Klebsiella", ++# 2 Escherichia S+oops <- data.frame(mo = c("Klebsiella", "Escherichia"), ampicillin = "S") oops @@ -227,19 +228,19 @@ eucast_rules(oops, info = FALSE) # mo ampicillin # 1 Klebsiella R -# 2 Escherichia S
A more convenient function is
-mo_is_intrinsic_resistant()that uses the same guideline, but allows to check for one or more specific microorganisms or antibiotics:-
mo_is_intrinsic_resistant(c("Klebsiella", "Escherichia"), ++# [1] TRUE FALSE+mo_is_intrinsic_resistant(c("Klebsiella", "Escherichia"), "ampicillin") # [1] TRUE FALSE mo_is_intrinsic_resistant("Klebsiella", c("ampicillin", "kanamycin")) -# [1] TRUE FALSE
EUCAST rules can not only be used for correction, they can also be used for filling in known resistance and susceptibility based on results of other antimicrobials drugs. This process is called interpretive reading, is basically a form of imputation, and is part of the
-eucast_rules()function as well:+-
data <- data.frame(mo = c("Staphylococcus aureus", +-+data <- data.frame(mo = c("Staphylococcus aureus", "Enterococcus faecalis", "Escherichia coli", "Klebsiella pneumoniae", @@ -251,9 +252,9 @@ CXM = "-", # Cefuroxime PEN = "S", # Benzylenicillin FOX = "S", # Cefoxitin - stringsAsFactors = FALSE)
+ stringsAsFactors = FALSE)-
data+data
-mo @@ -318,8 +319,8 @@+-
eucast_rules(data)+eucast_rules(data)
mo diff --git a/docs/articles/EUCAST_files/anchor-sections-1.0/anchor-sections.css b/docs/articles/EUCAST_files/anchor-sections-1.0/anchor-sections.css new file mode 100644 index 000000000..07aee5fcb --- /dev/null +++ b/docs/articles/EUCAST_files/anchor-sections-1.0/anchor-sections.css @@ -0,0 +1,4 @@ +/* Styles for section anchors */ +a.anchor-section {margin-left: 10px; visibility: hidden; color: inherit;} +a.anchor-section::before {content: '#';} +.hasAnchor:hover a.anchor-section {visibility: visible;} diff --git a/docs/articles/EUCAST_files/anchor-sections-1.0/anchor-sections.js b/docs/articles/EUCAST_files/anchor-sections-1.0/anchor-sections.js new file mode 100644 index 000000000..570f99a0a --- /dev/null +++ b/docs/articles/EUCAST_files/anchor-sections-1.0/anchor-sections.js @@ -0,0 +1,33 @@ +// Anchor sections v1.0 written by Atsushi Yasumoto on Oct 3rd, 2020. +document.addEventListener('DOMContentLoaded', function() { + // Do nothing if AnchorJS is used + if (typeof window.anchors === 'object' && anchors.hasOwnProperty('hasAnchorJSLink')) { + return; + } + + const h = document.querySelectorAll('h1, h2, h3, h4, h5, h6'); + + // Do nothing if sections are already anchored + if (Array.from(h).some(x => x.classList.contains('hasAnchor'))) { + return null; + } + + // Use section id when pandoc runs with --section-divs + const section_id = function(x) { + return ((x.classList.contains('section') || (x.tagName === 'SECTION')) + ? x.id : ''); + }; + + // Add anchors + h.forEach(function(x) { + const id = x.id || section_id(x.parentElement); + if (id === '') { + return null; + } + let anchor = document.createElement('a'); + anchor.href = '#' + id; + anchor.classList = ['anchor-section']; + x.classList.add('hasAnchor'); + x.appendChild(anchor); + }); +}); diff --git a/docs/articles/MDR.html b/docs/articles/MDR.html index 0e86071eb..d2eeeaf53 100644 --- a/docs/articles/MDR.html +++ b/docs/articles/MDR.html @@ -39,7 +39,7 @@ @@ -47,14 +47,14 @@For another example, I will create a data set to determine multi-drug resistant TB:
--
# random_rsi() is a helper function to generate ++ kanamycin = random_rsi(5000))+# random_rsi() is a helper function to generate # a random vector with values S, I and R my_TB_data <- data.frame(rifampicin = random_rsi(5000), isoniazid = random_rsi(5000), @@ -325,44 +326,44 @@ Unique: 2 ethambutol = random_rsi(5000), pyrazinamide = random_rsi(5000), moxifloxacin = random_rsi(5000), - kanamycin = random_rsi(5000))
Because all column names are automatically verified for valid drug names or codes, this would have worked exactly the same:
--
my_TB_data <- data.frame(RIF = random_rsi(5000), ++ KAN = random_rsi(5000))+my_TB_data <- data.frame(RIF = random_rsi(5000), INH = random_rsi(5000), GAT = random_rsi(5000), ETH = random_rsi(5000), PZA = random_rsi(5000), MFX = random_rsi(5000), - KAN = random_rsi(5000))
The data set now looks like this:
--
head(my_TB_data) ++# 6 I+head(my_TB_data) # rifampicin isoniazid gatifloxacin ethambutol pyrazinamide moxifloxacin -# 1 S R S S S I -# 2 S I R R R R -# 3 R S S I S I -# 4 I S S S I S -# 5 I I I S I R -# 6 S I S R S S +# 1 S S S S R R +# 2 R S S S I R +# 3 R R I R I R +# 4 R R S S R I +# 5 R R R I I I +# 6 R I R R I I # kanamycin -# 1 R -# 2 I -# 3 R -# 4 S +# 1 I +# 2 R +# 3 I +# 4 I # 5 S -# 6 R
We can now add the interpretation of MDR-TB to our data set. You can use:
-+-
mdro(my_TB_data, guideline = "TB")+mdro(my_TB_data, guideline = "TB")
or its shortcut
-mdr_tb():+-
my_TB_data$mdr <- mdr_tb(my_TB_data) -# NOTE: No column found as input for `col_mo`, assuming all records -# containMycobacterium tuberculosis.+my_TB_data$mdr <- mdr_tb(my_TB_data) +# ℹ No column found as input for `col_mo`, assuming all records +# containMycobacterium tuberculosis.
Create a frequency table of the results:
-+-
freq(my_TB_data$mdr)+freq(my_TB_data$mdr)
Frequency table
Class: factor > ordered (numeric)
Length: 5,000
@@ -382,40 +383,40 @@ Unique: 51 Mono-resistant -3246 -64.92% -3246 -64.92% +3165 +63.30% +3165 +63.30% 2 Negative -976 -19.52% -4222 -84.44% +1000 +20.00% +4165 +83.30% 3 Multi-drug-resistant -467 -9.34% -4689 -93.78% +463 +9.26% +4628 +92.56% 4 Poly-resistant -230 -4.60% -4919 -98.38% +255 +5.10% +4883 +97.66% 5 Extensively drug-resistant -81 -1.62% +117 +2.34% 5000 100.00% - - + Home
-
-
+
How to
@@ -63,77 +63,77 @@
- - + Conduct AMR analysis
- - + Predict antimicrobial resistance
- - + Data sets for download / own use
- - + Conduct principal component analysis for AMR
- - + Determine multi-drug resistance (MDR)
- - + Work with WHONET data
- - + Import data from SPSS/SAS/Stata
- - + Apply EUCAST rules
- - + Get properties of a microorganism
- - + Get properties of an antibiotic
- - + Other: benchmarks @@ -142,21 +142,21 @@
- - + Manual
- - + Authors
-
-
+
Changelog
@@ -165,14 +165,14 @@
- - + Source Code
-
-
+
Survey
@@ -187,7 +187,8 @@
- + +@@ -887,25 +880,23 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/@@ -47,14 +47,14 @@diff --git a/docs/articles/PCA_files/figure-html/unnamed-chunk-5-1.png b/docs/articles/PCA_files/figure-html/unnamed-chunk-5-1.png index 8ef396021..a848f2529 100644 Binary files a/docs/articles/PCA_files/figure-html/unnamed-chunk-5-1.png and b/docs/articles/PCA_files/figure-html/unnamed-chunk-5-1.png differ diff --git a/docs/articles/PCA_files/figure-html/unnamed-chunk-6-1.png b/docs/articles/PCA_files/figure-html/unnamed-chunk-6-1.png index b6de2dee5..17b94b5d4 100644 Binary files a/docs/articles/PCA_files/figure-html/unnamed-chunk-6-1.png and b/docs/articles/PCA_files/figure-html/unnamed-chunk-6-1.png differ diff --git a/docs/articles/PCA_files/figure-html/unnamed-chunk-7-1.png b/docs/articles/PCA_files/figure-html/unnamed-chunk-7-1.png index 0ad9620c8..07b34b06e 100644 Binary files a/docs/articles/PCA_files/figure-html/unnamed-chunk-7-1.png and b/docs/articles/PCA_files/figure-html/unnamed-chunk-7-1.png differ diff --git a/docs/articles/SPSS.html b/docs/articles/SPSS.html index ce7e6d7cc..5a517fe1b 100644 --- a/docs/articles/SPSS.html +++ b/docs/articles/SPSS.html @@ -39,7 +39,7 @@
How to conduct principal component analysis (PCA) for AMR
@@ -209,8 +210,8 @@Transforming
For PCA, we need to transform our AMR data first. This is what the
-example_isolatesdata set in this package looks like:-
library(AMR) ++# $ RIF <rsi> R, R, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, R, R, R…+library(AMR) library(dplyr) glimpse(example_isolates) # Rows: 2,000 @@ -263,10 +264,10 @@ # $ CHL <rsi> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N… # $ COL <rsi> NA, NA, R, R, R, R, R, R, R, R, R, R, NA, NA, NA, R, … # $ MUP <rsi> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N… -# $ RIF <rsi> R, R, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, R, R, R…
Now to transform this to a data set with only resistance percentages per taxonomic order and genus:
--
resistance_data <- example_isolates %>% ++# # Groups: order [5] +# order genus AMC CXM CTX CAZ GEN TOB TMP SXT +# <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> +# 1 (unknown order) (unknown gen… NA NA NA NA NA NA NA NA +# 2 Actinomycetales Schaalia NA NA NA NA NA NA NA NA +# 3 Bacteroidales Bacteroides NA NA NA NA NA NA NA NA +# 4 Campylobacteral… Campylobacter NA NA NA NA NA NA NA NA +# 5 Caryophanales Gemella NA NA NA NA NA NA NA NA +# 6 Caryophanales Listeria NA NA NA NA NA NA NA NA+resistance_data <- example_isolates %>% group_by(order = mo_order(mo), # group on anything, like order genus = mo_genus(mo)) %>% # and genus as we do here summarise_if(is.rsi, resistance) %>% # then get resistance of all drugs @@ -275,48 +276,52 @@ head(resistance_data) # # A tibble: 6 x 10 -# # Groups: order [2] -# order genus AMC CXM CTX CAZ GEN TOB TMP SXT -# <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> -# 1 (unknown order) (unknown genu… NA NA NA NA NA NA NA NA -# 2 Actinomycetales Corynebacteri… NA NA NA NA NA NA NA NA -# 3 Actinomycetales Cutibacterium NA NA NA NA NA NA NA NA -# 4 Actinomycetales Dermabacter NA NA NA NA NA NA NA NA -# 5 Actinomycetales Micrococcus NA NA NA NA NA NA NA NA -# 6 Actinomycetales Rothia NA NA NA NA NA NA NA NA
Perform principal component analysis
The new
-pca()function will automatically filter on rows that contain numeric values in all selected variables, so we now only need to do:+-
pca_result <- pca(resistance_data) -# NOTE: Columns selected for PCA: AMC CXM CTX CAZ GEN TOB TMP SXT. Total -# observations available: 7.+pca_result <- pca(resistance_data) +# ℹ Columns selected for PCA: "AMC", "CAZ", "CTX", "CXM", "GEN", "SXT", "TMP" +# and "TOB". Total observations available: 7.
The result can be reviewed with the good old
-summary()function:+-
summary(pca_result) ++# PC1 PC2 PC3 PC4 PC5 PC6 PC7 +# Standard deviation 2.1539 1.6807 0.6138 0.33879 0.20808 0.03140 5.121e-17 +# Proportion of Variance 0.5799 0.3531 0.0471 0.01435 0.00541 0.00012 0.000e+00 +# Cumulative Proportion 0.5799 0.9330 0.9801 0.99446 0.99988 1.00000 1.000e+00+summary(pca_result) +# Groups (n=4, named as 'order'): +# [1] "Caryophanales" "Enterobacterales" "Lactobacillales" "Pseudomonadales" # Importance of components: -# PC1 PC2 PC3 PC4 PC5 PC6 PC7 -# Standard deviation 2.154 1.6807 0.61365 0.33902 0.20757 0.03136 1.733e-16 -# Proportion of Variance 0.580 0.3531 0.04707 0.01437 0.00539 0.00012 0.000e+00 -# Cumulative Proportion 0.580 0.9331 0.98012 0.99449 0.99988 1.00000 1.000e+00
# Groups (n=4, named as 'order'): +# [1] "Caryophanales" "Enterobacterales" "Lactobacillales" "Pseudomonadales"Good news. The first two components explain a total of 93.3% of the variance (see the PC1 and PC2 values of the Proportion of Variance. We can create a so-called biplot with the base R
biplot()function, to see which antimicrobial resistance per drug explain the difference per microorganism.Plotting the results
-+-
biplot(pca_result)+biplot(pca_result)
But we can’t see the explanation of the points. Perhaps this works better with our new
-ggplot_pca()function, that automatically adds the right labels and even groups:+-
ggplot_pca(pca_result)+ggplot_pca(pca_result)
You can also print an ellipse per group, and edit the appearance:
-+-
ggplot_pca(pca_result, ellipse = TRUE) + - ggplot2::labs(title = "An AMR/PCA biplot!")+ggplot_pca(pca_result, ellipse = TRUE) + + ggplot2::labs(title = "An AMR/PCA biplot!")
- - + Home
-
-
+
How to
@@ -63,77 +63,77 @@
- - + Conduct AMR analysis
- - + Predict antimicrobial resistance
- - + Data sets for download / own use
- - + Conduct principal component analysis for AMR
- - + Determine multi-drug resistance (MDR)
- - + Work with WHONET data
- - + Import data from SPSS/SAS/Stata
- - + Apply EUCAST rules
- - + Get properties of a microorganism
- - + Get properties of an antibiotic
- - + Other: benchmarks @@ -142,21 +142,21 @@
- - + Manual
- - + Authors
-
-
+
Changelog
@@ -165,14 +165,14 @@
- - + Source Code
-
-
+
Survey
@@ -187,13 +187,14 @@
- + +@@ -752,9 +746,9 @@@@ -47,14 +47,14 @@diff --git a/docs/articles/WHONET.html b/docs/articles/WHONET.html index 8073149bd..ee102265f 100644 --- a/docs/articles/WHONET.html +++ b/docs/articles/WHONET.html @@ -39,7 +39,7 @@
How to import data from SPSS / SAS / Stata
Matthijs S. Berends
-02 February 2021
+27 April 2021
Source:vignettes/SPSS.Rmd@@ -228,7 +229,7 @@SPSS.RmdR has a huge community.
-Many R users just ask questions on websites like StackOverflow.com, the largest online community for programmers. At the time of writing, 385,525 R-related questions have already been asked on this platform (that covers questions and answers for any programming language). In my own experience, most questions are answered within a couple of minutes.
+Many R users just ask questions on websites like StackOverflow.com, the largest online community for programmers. At the time of writing, 398,952 R-related questions have already been asked on this platform (that covers questions and answers for any programming language). In my own experience, most questions are answered within a couple of minutes.
R understands any data type, including SPSS/SAS/Stata.
@@ -247,8 +248,8 @@To demonstrate the first point:
--
# not all values are valid MIC values: ++# [1] "J01CF05"+# not all values are valid MIC values: as.mic(0.125) # Class <mic> # [1] 0.125 @@ -279,7 +280,7 @@ # [4] "fluclox" "flucloxacilina" "flucloxacillin" # [7] "flucloxacilline" "flucloxacillinum" "fluorochloroxacillin" ab_atc("floxapen") -# [1] "J01CF05"
@@ -295,8 +296,8 @@
If you want named variables to be imported as factors so it resembles SPSS more, use
as_factor().The difference is this:
--
SPSS_data ++# # … with 4,193 more rows+SPSS_data # # A tibble: 4,203 x 4 # v001 sex status statusage # <dbl> <dbl+lbl> <dbl+lbl> <dbl> @@ -326,74 +327,74 @@ # 8 10011 Male alive 73.1 # 9 10017 Male alive 56.7 # 10 10018 Female alive 66.6 -# # … with 4,193 more rows
Base R
To import data from SPSS, SAS or Stata, you can use the great
-havenpackage yourself:-
# download and install the latest version: ++library(haven)+# download and install the latest version: install.packages("haven") # load the package you just installed: -library(haven)
You can now import files as follows:
SPSS
To read files from SPSS into R:
--
# read any SPSS file based on file extension (best way): ++read_por(file = "path/to/file")+# read any SPSS file based on file extension (best way): read_spss(file = "path/to/file") # read .sav or .zsav file: read_sav(file = "path/to/file") # read .por file: -read_por(file = "path/to/file")
Do not forget about
as_factor(), as mentioned above.To export your R objects to the SPSS file format:
-SAS
To read files from SAS into R:
--
# read .sas7bdat + .sas7bcat files: ++read_xpt(file = "path/to/file")+# read .sas7bdat + .sas7bcat files: read_sas(data_file = "path/to/file", catalog_file = NULL) # read SAS transport files (version 5 and version 8): -read_xpt(file = "path/to/file")
To export your R objects to the SAS file format:
--
# save as regular SAS file: ++write_xpt(data = yourdata, path = "path/to/file", version = 8)+# save as regular SAS file: write_sas(data = yourdata, path = "path/to/file") # the SAS transport format is an open format # (required for submission of the data to the FDA) -write_xpt(data = yourdata, path = "path/to/file", version = 8)
Stata
To read files from Stata into R:
--
# read .dta file: ++read_dta(file = "/path/to/file")+# read .dta file: read_stata(file = "/path/to/file") # works exactly the same: -read_dta(file = "/path/to/file")
To export your R objects to the Stata file format:
-- - + Home
-
-
+
How to
@@ -63,77 +63,77 @@
- - + Conduct AMR analysis
- - + Predict antimicrobial resistance
- - + Data sets for download / own use
- - + Conduct principal component analysis for AMR
- - + Determine multi-drug resistance (MDR)
- - + Work with WHONET data
- - + Import data from SPSS/SAS/Stata
- - + Apply EUCAST rules
- - + Get properties of a microorganism
- - + Get properties of an antibiotic
- - + Other: benchmarks @@ -142,21 +142,21 @@
- - + Manual
- - + Authors
-
-
+
Changelog
@@ -165,14 +165,14 @@
- - + Source Code
-
-
+
Survey
@@ -187,7 +187,8 @@
- + +@@ -692,18 +688,15 @@@@ -47,14 +47,14 @@diff --git a/docs/articles/WHONET_files/figure-html/unnamed-chunk-7-1.png b/docs/articles/WHONET_files/figure-html/unnamed-chunk-7-1.png index e54294f06..9a306e5de 100644 Binary files a/docs/articles/WHONET_files/figure-html/unnamed-chunk-7-1.png and b/docs/articles/WHONET_files/figure-html/unnamed-chunk-7-1.png differ diff --git a/docs/articles/benchmarks.html b/docs/articles/benchmarks.html index 9f4c250ff..0fa355754 100644 --- a/docs/articles/benchmarks.html +++ b/docs/articles/benchmarks.html @@ -39,7 +39,7 @@
How to work with WHONET data
@@ -205,38 +206,38 @@ Import of dataThis tutorial assumes you already imported the WHONET data with e.g. the
readxlpackage. In RStudio, this can be done using the menu button ‘Import Dataset’ in the tab ‘Environment’. Choose the option ‘From Excel’ and select your exported file. Make sure date fields are imported correctly.An example syntax could look like this:
-+-
library(readxl) -data <- read_excel(path = "path/to/your/file.xlsx")+library(readxl) +data <- read_excel(path = "path/to/your/file.xlsx")
This package comes with an example data set
WHONET. We will use it for this analysis.Preparation
First, load the relevant packages if you did not yet did this. I use the tidyverse for all of my analyses. All of them. If you don’t know it yet, I suggest you read about it on their website: https://www.tidyverse.org/.
--
library(dplyr) # part of tidyverse ++library(cleaner) # to create frequency tables+library(dplyr) # part of tidyverse library(ggplot2) # part of tidyverse library(AMR) # this package -library(cleaner) # to create frequency tables
We will have to transform some variables to simplify and automate the analysis:
- Microorganisms should be transformed to our own microorganism IDs (called an
mo) using our Catalogue of Life reference data set, which contains all ~70,000 microorganisms from the taxonomic kingdoms Bacteria, Fungi and Protozoa. We do the tranformation withas.mo(). This function also recognises almost all WHONET abbreviations of microorganisms. - Antimicrobial results or interpretations have to be clean and valid. In other words, they should only contain values
"S","I"or"R". That is exactly where theas.rsi()function is for.
-
# transform variables ++ mutate_at(vars(AMP_ND10:CIP_EE), as.rsi)+# transform variables data <- WHONET %>% # get microbial ID based on given organism mutate(mo = as.mo(Organism)) %>% # transform everything from "AMP_ND10" to "CIP_EE" to the new `rsi` class - mutate_at(vars(AMP_ND10:CIP_EE), as.rsi)
No errors or warnings, so all values are transformed succesfully.
We also created a package dedicated to data cleaning and checking, called the
cleanerpackage. Itsfreq()function can be used to create frequency tables.So let’s check our data, with a couple of frequency tables:
-+-
# our newly created `mo` variable, put in the mo_name() function -data %>% freq(mo_name(mo), nmax = 10)+# our newly created `mo` variable, put in the mo_name() function +data %>% freq(mo_name(mo), nmax = 10)
Frequency table
Class: character
Length: 500
@@ -337,10 +338,10 @@ Longest: 40(omitted 27 entries, n = 56 [11.20%])
--
# our transformed antibiotic columns ++data %>% freq(AMC_ND2)+# our transformed antibiotic columns # amoxicillin/clavulanic acid (J01CR02) as an example -data %>% freq(AMC_ND2)
Frequency table
Class: factor > ordered > rsi (numeric)
Length: 500
@@ -391,11 +392,11 @@ Drug group: Beta-lactams/penicillins
A first glimpse at results
An easy
-ggplotwill already give a lot of information, using the includedggplot_rsi()function:-
data %>% ++ ggplot_rsi(translate_ab = 'ab', facet = "Country", datalabels = FALSE)+data %>% group_by(Country) %>% select(Country, AMP_ND2, AMC_ED20, CAZ_ED10, CIP_ED5) %>% - ggplot_rsi(translate_ab = 'ab', facet = "Country", datalabels = FALSE)
- - + Home
-
-
+
How to
@@ -63,77 +63,77 @@
- - + Conduct AMR analysis
- - + Predict antimicrobial resistance
- - + Data sets for download / own use
- - + Conduct principal component analysis for AMR
- - + Determine multi-drug resistance (MDR)
- - + Work with WHONET data
- - + Import data from SPSS/SAS/Stata
- - + Apply EUCAST rules
- - + Get properties of a microorganism
- - + Get properties of an antibiotic
- - + Other: benchmarks @@ -142,21 +142,21 @@
- - + Manual
- - + Authors
-
-
+
Changelog
@@ -165,14 +165,14 @@
- - + Source Code
-
-
+
Survey
@@ -187,7 +187,8 @@
- + +-@@ -47,14 +47,14 @@diff --git a/docs/articles/benchmarks_files/figure-html/unnamed-chunk-4-1.png b/docs/articles/benchmarks_files/figure-html/unnamed-chunk-4-1.png index 766c4fa43..63db8360f 100644 Binary files a/docs/articles/benchmarks_files/figure-html/unnamed-chunk-4-1.png and b/docs/articles/benchmarks_files/figure-html/unnamed-chunk-4-1.png differ diff --git a/docs/articles/datasets.html b/docs/articles/datasets.html index 8fb9a0a88..83a910ce6 100644 --- a/docs/articles/datasets.html +++ b/docs/articles/datasets.html @@ -39,7 +39,7 @@
Benchmarks
@@ -202,15 +203,15 @@One of the most important features of this package is the complete microbial taxonomic database, supplied by the Catalogue of Life (CoL) and the List of Prokaryotic names with Standing in Nomenclature (LPSN). We created a function
as.mo()that transforms any user input value to a valid microbial ID by using intelligent rules combined with the microbial taxonomy.Using the
-microbenchmarkpackage, we can review the calculation performance of this function. Its functionmicrobenchmark()runs different input expressions independently of each other and measures their time-to-result.-
library(microbenchmark) + +library(dplyr)In the next test, we try to ‘coerce’ different input values into the microbial code of Staphylococcus aureus. Coercion is a computational process of forcing output based on an input. For microorganism names, coercing user input to taxonomically valid microorganism names is crucial to ensure correct interpretation and to enable grouping based on taxonomic properties.
The actual result is the same every time: it returns its microorganism code
B_STPHY_AURS(B stands for Bacteria, its taxonomic kingdom).But the calculation time differs a lot:
--
S.aureus <- microbenchmark( ++# expr min lq mean median uq max neval +# as.mo("sau") 25.0 25.0 30 26.0 26.0 83 25 +# as.mo("stau") 120.0 130.0 150 130.0 180.0 390 25 +# as.mo("STAU") 120.0 130.0 150 130.0 180.0 190 25 +# as.mo("staaur") 25.0 26.0 33 26.0 26.0 83 25 +# as.mo("STAAUR") 25.0 26.0 33 26.0 26.0 83 25 +# as.mo("S. aureus") 66.0 66.0 89 67.0 120.0 150 25 +# as.mo("S aureus") 66.0 66.0 74 66.0 67.0 120 25 +# as.mo("Staphylococcus aureus") 6.8 6.9 14 6.9 7.5 63 25 +# as.mo("Staphylococcus aureus (MRSA)") 550.0 550.0 560 550.0 560.0 620 25 +# as.mo("Sthafilokkockus aaureuz") 410.0 420.0 430 420.0 420.0 620 25 +# as.mo("MRSA") 25.0 26.0 31 26.0 26.0 83 25 +# as.mo("VISA") 46.0 47.0 65 47.0 98.0 110 25+S.aureus <- microbenchmark( as.mo("sau"), # WHONET code as.mo("stau"), as.mo("STAU"), @@ -224,21 +225,21 @@ as.mo("MRSA"), # Methicillin Resistant S. aureus as.mo("VISA"), # Vancomycin Intermediate S. aureus times = 25) -print(S.aureus, unit = "ms", signif = 2) +print(S.aureus, unit = "ms", signif = 2) # Unit: milliseconds -# expr min lq mean median uq max neval -# as.mo("sau") 9.9 11.0 13.0 11.0 12.0 43 25 -# as.mo("stau") 52.0 55.0 68.0 58.0 86.0 95 25 -# as.mo("STAU") 53.0 56.0 73.0 62.0 93.0 100 25 -# as.mo("staaur") 10.0 11.0 17.0 11.0 12.0 48 25 -# as.mo("STAAUR") 10.0 11.0 14.0 11.0 13.0 48 25 -# as.mo("S. aureus") 27.0 28.0 41.0 33.0 60.0 73 25 -# as.mo("S aureus") 27.0 28.0 49.0 34.0 64.0 160 25 -# as.mo("Staphylococcus aureus") 2.9 3.2 4.8 3.4 3.7 36 25 -# as.mo("Staphylococcus aureus (MRSA)") 250.0 260.0 270.0 270.0 280.0 320 25 -# as.mo("Sthafilokkockus aaureuz") 170.0 200.0 210.0 210.0 210.0 310 25 -# as.mo("MRSA") 10.0 11.0 16.0 12.0 12.0 50 25 -# as.mo("VISA") 19.0 20.0 27.0 21.0 23.0 60 25
In the table above, all measurements are shown in milliseconds (thousands of seconds). A value of 5 milliseconds means it can determine 200 input values per second. It case of 200 milliseconds, this is only 5 input values per second. It is clear that accepted taxonomic names are extremely fast, but some variations are up to 200 times slower to determine.
To improve performance, we implemented two important algorithms to save unnecessary calculations: repetitive results and already precalculated results.
@@ -247,8 +248,8 @@ Repetitive resultsRepetitive results are values that are present more than once in a vector. Unique values will only be calculated once by
as.mo(). So runningas.mo(c("E. coli", "E. coli"))will check the value"E. coli"only once.To prove this, we will use
-mo_name()for testing - a helper function that returns the full microbial name (genus, species and possibly subspecies) which usesas.mo()internally.+-
# start with the example_isolates data set +-+# start with the example_isolates data set x <- example_isolates %>% # take all MO codes from the 'mo' column pull(mo) %>% @@ -260,8 +261,8 @@ # what do these values look like? They are of class <mo>: head(x) # Class <mo> -# [1] B_STRPT_PYGN B_STPHY_HMNS B_STPHY_CONS B_STRPT_SLVR B_ENTRBC_CLOC -# [6] B_STPHY_CONS +# [1] B_STPHY_EPDR B_STPHY_EPDR B_STPHY_CONS B_STPHY_CONS B_STPHY_EPDR +# [6] B_ESCHR_COLI # as the example_isolates data set has 2,000 rows, we should have 2 million items length(x) @@ -274,30 +275,30 @@ # now let's see: run_it <- microbenchmark(mo_name(x), times = 10) -print(run_it, unit = "ms", signif = 3) +print(run_it, unit = "ms", signif = 3) # Unit: milliseconds # expr min lq mean median uq max neval -# mo_name(x) 161 194 224 204 229 368 10
So getting official taxonomic names of 2,000,000 (!!) items consisting of 90 unique values only takes 0.204 seconds. That is 102 nanoseconds on average. You only lose time on your unique input values.
+# mo_name(x) 321 378 443 410 438 713 10So getting official taxonomic names of 2,000,000 (!!) items consisting of 90 unique values only takes 0.41 seconds. That is 205 nanoseconds on average. You only lose time on your unique input values.
Precalculated results
What about precalculated results? If the input is an already precalculated result of a helper function such as
-mo_name(), it almost doesn’t take any time at all. In other words, if you runmo_name()on a valid taxonomic name, it will return the results immediately (see ‘C’ below):-
run_it <- microbenchmark(A = mo_name("STAAUR"), +-+run_it <- microbenchmark(A = mo_name("STAAUR"), B = mo_name("S. aureus"), C = mo_name("Staphylococcus aureus"), times = 10) -print(run_it, unit = "ms", signif = 3) +print(run_it, unit = "ms", signif = 3) # Unit: milliseconds -# expr min lq mean median uq max neval -# A 7.45 7.84 12.70 8.62 9.16 51.10 10 -# B 23.80 24.50 30.60 26.30 28.80 70.20 10 -# C 1.66 1.74 1.85 1.79 1.92 2.24 10
So going from
-mo_name("Staphylococcus aureus")to"Staphylococcus aureus"takes 0.0018 seconds - it doesn’t even start calculating if the result would be the same as the expected resulting value. That goes for all helper functions:+-
run_it <- microbenchmark(A = mo_species("aureus"), +# expr min lq mean median uq max neval +# A 17.00 17.1 17.10 17.10 17.20 17.20 10 +# B 57.20 57.3 68.90 57.60 58.40 117.00 10 +# C 3.66 3.7 3.74 3.74 3.77 3.89 10So going from
+mo_name("Staphylococcus aureus")to"Staphylococcus aureus"takes 0.0037 seconds - it doesn’t even start calculating if the result would be the same as the expected resulting value. That goes for all helper functions:+# A 3.70 3.71 3.81 3.74 3.82 4.14 10 +# B 3.66 3.67 3.76 3.69 3.76 4.10 10 +# C 3.66 3.70 3.72 3.72 3.73 3.76 10 +# D 3.63 3.67 3.77 3.71 3.88 4.09 10 +# E 3.62 3.67 3.75 3.70 3.78 4.07 10 +# F 3.62 3.64 3.66 3.65 3.65 3.74 10 +# G 3.63 3.64 3.67 3.67 3.68 3.75 10 +# H 3.63 3.64 3.74 3.67 3.84 4.07 10+run_it <- microbenchmark(A = mo_species("aureus"), B = mo_genus("Staphylococcus"), C = mo_name("Staphylococcus aureus"), D = mo_family("Staphylococcaceae"), @@ -306,25 +307,25 @@ G = mo_phylum("Firmicutes"), H = mo_kingdom("Bacteria"), times = 10) -print(run_it, unit = "ms", signif = 3) +print(run_it, unit = "ms", signif = 3) # Unit: milliseconds # expr min lq mean median uq max neval -# A 1.59 1.60 1.91 1.97 2.15 2.28 10 -# B 1.58 1.61 1.87 1.86 1.96 2.39 10 -# C 1.55 1.57 1.64 1.63 1.69 1.79 10 -# D 1.57 1.60 1.83 1.72 1.92 2.73 10 -# E 1.50 1.74 1.86 1.86 2.03 2.24 10 -# F 1.49 1.55 1.75 1.67 1.90 2.24 10 -# G 1.54 1.59 1.69 1.65 1.77 1.95 10 -# H 1.57 1.58 1.75 1.72 1.78 2.21 10
Of course, when running
mo_phylum("Firmicutes")the function has zero knowledge about the actual microorganism, namely S. aureus. But since the result would be"Firmicutes"anyway, there is no point in calculating the result. And because this package contains all phyla of all known bacteria, it can just return the initial value immediately.Results in other languages
When the system language is non-English and supported by this
-AMRpackage, some functions will have a translated result. This almost does’t take extra time:-
mo_name("CoNS", language = "en") # or just mo_name("CoNS") on an English system ++# en 43.15 43.49 48.88 43.66 43.81 122.3 100 +# de 79.59 80.39 88.27 80.89 81.11 135.8 100 +# nl 79.69 80.45 87.16 80.81 81.07 136.6 100 +# es 79.28 80.12 89.84 80.51 81.02 159.5 100 +# it 51.74 52.20 55.59 52.39 52.61 109.1 100 +# fr 51.43 51.88 54.83 52.05 52.29 105.5 100 +# pt 51.58 51.93 59.25 52.28 52.55 111.8 100+mo_name("CoNS", language = "en") # or just mo_name("CoNS") on an English system # [1] "Coagulase-negative Staphylococcus (CoNS)" mo_name("CoNS", language = "es") # or just mo_name("CoNS") on a Spanish system @@ -341,16 +342,16 @@ fr = mo_name("CoNS", language = "fr"), pt = mo_name("CoNS", language = "pt"), times = 100) -print(run_it, unit = "ms", signif = 4) +print(run_it, unit = "ms", signif = 4) # Unit: milliseconds # expr min lq mean median uq max neval -# en 17.33 18.21 21.97 19.06 20.40 68.32 100 -# de 20.44 21.37 30.49 22.33 24.97 78.42 100 -# nl 25.13 26.10 31.91 27.11 28.50 86.00 100 -# es 20.28 21.16 26.37 22.03 23.67 74.74 100 -# it 20.06 21.00 26.05 21.95 23.42 94.16 100 -# fr 19.90 20.63 24.40 21.85 22.82 69.07 100 -# pt 20.22 21.03 25.63 21.89 23.24 76.63 100
Currently supported non-English languages are German, Dutch, Spanish, Italian, French and Portuguese.
- - + Home
-
-
+
How to
@@ -63,77 +63,77 @@
- - + Conduct AMR analysis
- - + Predict antimicrobial resistance
- - + Data sets for download / own use
- - + Conduct principal component analysis for AMR
- - + Determine multi-drug resistance (MDR)
- - + Work with WHONET data
- - + Import data from SPSS/SAS/Stata
- - + Apply EUCAST rules
- - + Get properties of a microorganism
- - + Get properties of an antibiotic
- - + Other: benchmarks @@ -142,21 +142,21 @@
- - + Manual
- - + Authors
-
-
+
Changelog
@@ -165,14 +165,14 @@
- - + Source Code
-
-
+
Survey
@@ -187,12 +187,13 @@
- + +@@ -89,14 +89,14 @@diff --git a/docs/news/index.html b/docs/news/index.html index 88718de9c..d02a0f82a 100644 --- a/docs/news/index.html +++ b/docs/news/index.html @@ -81,7 +81,7 @@@@ -47,14 +47,14 @@@@ -89,14 +89,14 @@
Data sets for download / own use
-11 March 2021
+27 April 2021
Source:vignettes/datasets.Rmd@@ -211,7 +212,7 @@ If you are reading this page from within R, please Microorganisms (currently accepted names)datasets.RmdA data set with 70,026 rows and 16 columns, containing the following column names:
mo, fullname, kingdom, phylum, class, order, family, genus, species, subspecies, rank, ref, species_id, source, prevalence and snomed.This data set is in R available as
-microorganisms, after you load theAMRpackage.It was last updated on 11 March 2021 20:59:32 UTC. Find more info about the structure of this data set here.
+It was last updated on 27 April 2021 08:12:46 UTC. Find more info about the structure of this data set here.
Direct download links:
- Download as R file (2.2 MB)
@@ -432,7 +433,7 @@ If you are reading this page from within R, please here. +It was last updated on 27 April 2021 08:12:46 UTC. Find more info about the structure of this data set here.
Direct download links:
- Download as R file (0.2 MB)
@@ -497,7 +498,7 @@ If you are reading this page from within R, please Antibiotic agentsA data set with 456 rows and 14 columns, containing the following column names:
ab, atc, cid, name, group, atc_group1, atc_group2, abbreviations, synonyms, oral_ddd, oral_units, iv_ddd, iv_units and loinc.This data set is in R available as
-antibiotics, after you load theAMRpackage.It was last updated on 11 March 2021 20:59:32 UTC. Find more info about the structure of this data set here.
+It was last updated on 27 April 2021 08:12:46 UTC. Find more info about the structure of this data set here.
Direct download links:
- Download as R file (32 kB)
@@ -665,7 +666,7 @@ If you are reading this page from within R, please Antiviral agentsA data set with 102 rows and 9 columns, containing the following column names:
atc, cid, name, atc_group, synonyms, oral_ddd, oral_units, iv_ddd and iv_units.This data set is in R available as
-antivirals, after you load theAMRpackage.It was last updated on 29 August 2020 19:53:07 UTC. Find more info about the structure of this data set here.
+It was last updated on 27 April 2021 08:12:46 UTC. Find more info about the structure of this data set here.
Direct download links:
- Download as R file (5 kB)
@@ -792,7 +793,7 @@ If you are reading this page from within R, please Intrinsic bacterial resistanceA data set with 93,892 rows and 2 columns, containing the following column names:
microorganism and antibiotic.This data set is in R available as
-intrinsic_resistant, after you load theAMRpackage.It was last updated on 5 March 2021 09:46:55 UTC. Find more info about the structure of this data set here.
+It was last updated on 27 April 2021 08:12:46 UTC. Find more info about the structure of this data set here.
Direct download links:
- Download as R file (69 kB)
@@ -1007,7 +1008,7 @@ If you are reading this page from within R, please Interpretation from MIC values / disk diameters to R/SIA data set with 20,486 rows and 10 columns, containing the following column names:
guideline, method, site, mo, ab, ref_tbl, disk_dose, breakpoint_S, breakpoint_R and uti.This data set is in R available as
-rsi_translation, after you load theAMRpackage.It was last updated on 5 March 2021 09:46:55 UTC. Find more info about the structure of this data set here.
+It was last updated on 27 April 2021 08:12:46 UTC. Find more info about the structure of this data set here.
Direct download links:
- Download as R file (34 kB)
@@ -1137,7 +1138,7 @@ If you are reading this page from within R, please Dosage guidelines from EUCASTA data set with 169 rows and 9 columns, containing the following column names:
ab, name, type, dose, dose_times, administration, notes, original_txt and eucast_version.This data set is in R available as
-dosage, after you load theAMRpackage.It was last updated on 25 January 2021 20:58:20 UTC. Find more info about the structure of this data set here.
+It was last updated on 27 April 2021 08:12:46 UTC. Find more info about the structure of this data set here.
Direct download links:
- Download as R file (3 kB)
diff --git a/docs/articles/datasets_files/anchor-sections-1.0/anchor-sections.css b/docs/articles/datasets_files/anchor-sections-1.0/anchor-sections.css new file mode 100644 index 000000000..07aee5fcb --- /dev/null +++ b/docs/articles/datasets_files/anchor-sections-1.0/anchor-sections.css @@ -0,0 +1,4 @@ +/* Styles for section anchors */ +a.anchor-section {margin-left: 10px; visibility: hidden; color: inherit;} +a.anchor-section::before {content: '#';} +.hasAnchor:hover a.anchor-section {visibility: visible;} diff --git a/docs/articles/datasets_files/anchor-sections-1.0/anchor-sections.js b/docs/articles/datasets_files/anchor-sections-1.0/anchor-sections.js new file mode 100644 index 000000000..570f99a0a --- /dev/null +++ b/docs/articles/datasets_files/anchor-sections-1.0/anchor-sections.js @@ -0,0 +1,33 @@ +// Anchor sections v1.0 written by Atsushi Yasumoto on Oct 3rd, 2020. +document.addEventListener('DOMContentLoaded', function() { + // Do nothing if AnchorJS is used + if (typeof window.anchors === 'object' && anchors.hasOwnProperty('hasAnchorJSLink')) { + return; + } + + const h = document.querySelectorAll('h1, h2, h3, h4, h5, h6'); + + // Do nothing if sections are already anchored + if (Array.from(h).some(x => x.classList.contains('hasAnchor'))) { + return null; + } + + // Use section id when pandoc runs with --section-divs + const section_id = function(x) { + return ((x.classList.contains('section') || (x.tagName === 'SECTION')) + ? x.id : ''); + }; + + // Add anchors + h.forEach(function(x) { + const id = x.id || section_id(x.parentElement); + if (id === '') { + return null; + } + let anchor = document.createElement('a'); + anchor.href = '#' + id; + anchor.classList = ['anchor-section']; + x.classList.add('hasAnchor'); + x.appendChild(anchor); + }); +}); diff --git a/docs/articles/index.html b/docs/articles/index.html index be382c4e6..35a7040fd 100644 --- a/docs/articles/index.html +++ b/docs/articles/index.html @@ -81,7 +81,7 @@
- Download as R file (3 kB)
- Download as R file (34 kB)
- Download as R file (69 kB)
- Download as R file (5 kB)
- Download as R file (32 kB)
- Download as R file (0.2 MB)
- - + Home
-
-
+
How to
@@ -63,77 +63,77 @@
- - + Conduct AMR analysis
- - + Predict antimicrobial resistance
- - + Data sets for download / own use
- - + Conduct principal component analysis for AMR
- - + Determine multi-drug resistance (MDR)
- - + Work with WHONET data
- - + Import data from SPSS/SAS/Stata
- - + Apply EUCAST rules
- - + Get properties of a microorganism
- - + Get properties of an antibiotic
- - + Other: benchmarks @@ -142,21 +142,21 @@
- - + Manual
- - + Authors
-
-
+
Changelog
@@ -165,14 +165,14 @@
- - + Source Code
-
-
+
Survey
@@ -187,7 +187,8 @@
- + +@@ -47,14 +47,14 @@diff --git a/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-4-1.png b/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-4-1.png index 4447b94f2..11ba40d18 100644 Binary files a/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-4-1.png and b/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-4-1.png differ diff --git a/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-5-1.png b/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-5-1.png index 89246a48b..e1f60e479 100644 Binary files a/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-5-1.png and b/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-5-1.png differ diff --git a/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-5-2.png b/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-5-2.png index acc8ac2b5..d8364ea63 100644 Binary files a/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-5-2.png and b/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-5-2.png differ diff --git a/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-6-1.png b/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-6-1.png index b1a473d3e..ea4faf456 100644 Binary files a/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-6-1.png and b/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-6-1.png differ diff --git a/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-7-1.png b/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-7-1.png index 6fcbbfea8..262b5432d 100644 Binary files a/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-7-1.png and b/docs/articles/resistance_predict_files/figure-html/unnamed-chunk-7-1.png differ diff --git a/docs/articles/welcome_to_AMR.html b/docs/articles/welcome_to_AMR.html index 24991a11b..a256e685c 100644 --- a/docs/articles/welcome_to_AMR.html +++ b/docs/articles/welcome_to_AMR.html @@ -39,7 +39,7 @@
How to predict antimicrobial resistance
@@ -205,37 +206,37 @@ Needed R packagesAs with many uses in R, we need some additional packages for AMR data analysis. Our package works closely together with the tidyverse packages
dplyrandggplot2by Dr Hadley Wickham. The tidyverse tremendously improves the way we conduct data science - it allows for a very natural way of writing syntaxes and creating beautiful plots in R.Our
-AMRpackage depends on these packages and even extends their use and functions.Prediction analysis
Our package contains a function
resistance_predict(), which takes the same input as functions for other AMR data analysis. Based on a date column, it calculates cases per year and uses a regression model to predict antimicrobial resistance.It is basically as easy as:
-+# resistance prediction of piperacillin/tazobactam (TZP): -resistance_predict(tbl = example_isolates, col_date = "date", col_ab = "TZP", model = "binomial") - -# or: -example_isolates %>% - resistance_predict(col_ab = "TZP", - model "binomial") - -# to bind it to object 'predict_TZP' for example: -predict_TZP <- example_isolates %>% - resistance_predict(col_ab = "TZP", - model = "binomial")# resistance prediction of piperacillin/tazobactam (TZP): +resistance_predict(tbl = example_isolates, col_date = "date", col_ab = "TZP", model = "binomial") + +# or: +example_isolates %>% + resistance_predict(col_ab = "TZP", + model "binomial") + +# to bind it to object 'predict_TZP' for example: +predict_TZP <- example_isolates %>% + resistance_predict(col_ab = "TZP", + model = "binomial")The function will look for a date column itself if
col_dateis not set.When running any of these commands, a summary of the regression model will be printed unless using
-resistance_predict(..., info = FALSE).
+# NOTE: Using column 'date' as input for `col_date`.# ℹ Using column 'date' as input for `col_date`.This text is only a printed summary - the actual result (output) of the function is a
-data.framecontaining for each year: the number of observations, the actual observed resistance, the estimated resistance and the standard error below and above the estimation:-
predict_TZP ++# 30 2031 0.51109592 0.3973697 0.6248221 NA NA 0.51109592+predict_TZP # year value se_min se_max observations observed estimated # 1 2002 0.20000000 NA NA 15 0.20000000 0.05616378 # 2 2003 0.06250000 NA NA 32 0.06250000 0.06163839 @@ -266,30 +267,30 @@ # 27 2028 0.43730688 0.3418075 0.5328063 NA NA 0.43730688 # 28 2029 0.46175755 0.3597639 0.5637512 NA NA 0.46175755 # 29 2030 0.48639359 0.3782932 0.5944939 NA NA 0.48639359 -# 30 2031 0.51109592 0.3973697 0.6248221 NA NA 0.51109592
The function
-plotis available in base R, and can be extended by other packages to depend the output based on the type of input. We extended its function to cope with resistance predictions:+-
plot(predict_TZP)+plot(predict_TZP)
This is the fastest way to plot the result. It automatically adds the right axes, error bars, titles, number of available observations and type of model.
We also support the
-ggplot2package with our custom functionggplot_rsi_predict()to create more appealing plots:+-
ggplot_rsi_predict(predict_TZP)+ggplot_rsi_predict(predict_TZP)
-
-
++ggplot_rsi_predict(predict_TZP, ribbon = FALSE)+ # choose for error bars instead of a ribbon -ggplot_rsi_predict(predict_TZP, ribbon = FALSE)
Choosing the right model
Resistance is not easily predicted; if we look at vancomycin resistance in Gram-positive bacteria, the spread (i.e. standard error) is enormous:
--
example_isolates %>% ++ ggplot_rsi_predict()+example_isolates %>% filter(mo_gramstain(mo, language = NULL) == "Gram-positive") %>% resistance_predict(col_ab = "VAN", year_min = 2010, info = FALSE, model = "binomial") %>% - ggplot_rsi_predict()
Vancomycin resistance could be 100% in ten years, but might also stay around 0%.
You can define the model with the
@@ -330,16 +331,16 @@modelparameter. The model chosen above is a generalised linear regression model using a binomial distribution, assuming that a period of zero resistance was followed by a period of increasing resistance leading slowly to more and more resistance.For the vancomycin resistance in Gram-positive bacteria, a linear model might be more appropriate since no binomial distribution is to be expected based on the observed years:
--
example_isolates %>% ++ ggplot_rsi_predict()+example_isolates %>% filter(mo_gramstain(mo, language = NULL) == "Gram-positive") %>% resistance_predict(col_ab = "VAN", year_min = 2010, info = FALSE, model = "linear") %>% - ggplot_rsi_predict()
This seems more likely, doesn’t it?
The model itself is also available from the object, as an
-attribute:-
model <- attributes(predict_TZP)$model ++# year 0.09883005 0.02295317 4.305725 1.664395e-05+model <- attributes(predict_TZP)$model summary(model)$family # @@ -349,7 +350,7 @@ summary(model)$coefficients # Estimate Std. Error z value Pr(>|z|) # (Intercept) -200.67944891 46.17315349 -4.346237 1.384932e-05 -# year 0.09883005 0.02295317 4.305725 1.664395e-05
- - + Home
-
-
+
How to
@@ -63,77 +63,77 @@
- - + Conduct AMR analysis
- - + Predict antimicrobial resistance
- - + Data sets for download / own use
- - + Conduct principal component analysis for AMR
- - + Determine multi-drug resistance (MDR)
- - + Work with WHONET data
- - + Import data from SPSS/SAS/Stata
- - + Apply EUCAST rules
- - + Get properties of a microorganism
- - + Get properties of an antibiotic
- - + Other: benchmarks @@ -142,21 +142,21 @@
- - + Manual
- - + Authors
-
-
+
Changelog
@@ -165,14 +165,14 @@
- - + Source Code
-
-
+
Survey
@@ -187,7 +187,8 @@
- + +@@ -389,9 +389,9 @@ Latest development version@@ -379,8 +379,8 @@ Latest released version@@ -50,14 +50,14 @@@@ -89,14 +89,14 @@
Welcome to the AMR package
diff --git a/docs/authors.html b/docs/authors.html index 4ee11444b..09a1da093 100644 --- a/docs/authors.html +++ b/docs/authors.html @@ -81,7 +81,7 @@- - + Home
-
-
+
How to
@@ -66,77 +66,77 @@
- - + Conduct AMR analysis
- - + Predict antimicrobial resistance
- - + Data sets for download / own use
- - + Conduct principal component analysis for AMR
- - + Determine multi-drug resistance (MDR)
- - + Work with WHONET data
- - + Import data from SPSS/SAS/Stata
- - + Apply EUCAST rules
- - + Get properties of a microorganism
- - + Get properties of an antibiotic
- - + Other: benchmarks @@ -145,21 +145,21 @@
- - + Manual
- - + Authors
-
-
+
Changelog
@@ -168,14 +168,14 @@
- - + Source Code
-
-
+
Survey
@@ -212,8 +212,8 @@
With
-AMR(for R), there’s always a knowledgeable microbiologist by your side!-
# AMR works great with dplyr, but it's not required or neccesary ++#> Selecting carbapenems: columns 'IPM' (imipenem) and 'MEM' (meropenem)+# AMR works great with dplyr, but it's not required or neccesary library(AMR) library(dplyr) @@ -227,7 +227,7 @@ #> 'EUCAST Intrinsic Resistance and Unusual Phenotypes' v3.2 (2020). #> Selecting aminoglycosides: columns 'AMK' (amikacin), 'GEN' (gentamicin), #> 'KAN' (kanamycin) and 'TOB' (tobramycin) -#> Selecting carbapenems: columns 'IPM' (imipenem) and 'MEM' (meropenem)
With only having defined a row filter on Gram-negative bacteria with intrinsic resistance to cefotaxime (
mo_is_gram_negative()andmo_is_intrinsic_resistant()) and a column selection on two antibiotic groups (aminoglycosides()andcarbapenems()), the reference data about all microorganisms and all antibiotics in theAMRpackage make sure you get what you meant:@@ -333,18 +333,18 @@ A base R equivalent would be, giving the exact same results:
--
example_isolates$bacteria <- mo_fullname(example_isolates$mo) ++ c("bacteria", aminoglycosides(), carbapenems())]+example_isolates$bacteria <- mo_fullname(example_isolates$mo) example_isolates[which(mo_is_gram_negative() & mo_is_intrinsic_resistant(ab = "cefotax")), - c("bacteria", aminoglycosides(), carbapenems())]
This package is available here on the official R network (CRAN), which has a peer-reviewed submission process. Install this package in R from CRAN by using the command:
-+-
install.packages("AMR")+install.packages("AMR")
It will be downloaded and installed automatically. For RStudio, click on the menu Tools > Install Packages… and then type in “AMR” and press Install.
Note: Not all functions on this website may be available in this latest release. To use all functions and data sets mentioned on this website, install the latest development version.
The latest and unpublished development version can be installed from GitHub using:
-+-
install.packages("remotes") # if you haven't already -remotes::install_github("msberends/AMR")+install.packages("remotes") # if you haven't already +remotes::install_github("msberends/AMR")
You can also download the latest build from our repository: https://github.com/msberends/AMR/raw/master/data-raw/AMR_latest.tar.gz
- Download as R file (2.2 MB)
-@@ -666,23 +661,24 @@-AMR 1.6.0.9010 Unreleased +
+@@ -584,57 +578,57 @@+AMR 1.6.0.9011 Unreleased
-+@@ -562,21 +556,21 @@@@ -466,9 +460,8 @@-Last updated: 26 April 2021 +Last updated: 27 April 2021
@@ -398,7 +393,7 @@@@ -283,16 +283,15 @@
- Printing of microbial codes in a
data.frameortibblenow gives a warning if the data contains old microbial codes (from a previous AMR package version)- Extended the
like()functions:-
-
Now checks if
patternis a valid regular expression
+- Now checks if
patternis a valid regular expression -
Added
-%unlike%and%unlike_case%(as negations of the existing%like%and%like_case%). This greatly improves readability:-
++if (guideline %unlike% "EUCAST") ...if (!grepl("EUCAST", guideline)) ... # same: -if (guideline %unlike% "EUCAST") ...
- Altered the RStudio addin, so it now iterates over
%like%->%unlike%->%like_case%->%unlike_case%if you keep pressing your keyboard shortcut
+- Altered the RStudio addin, so it now iterates over
%like%->%unlike%->%like_case%->%unlike_case%if you keep pressing your keyboard shortcut
- Fixed an installation error on R-3.0
@@ -310,16 +309,14 @@New
-
-
-
-
Support for EUCAST Clinical Breakpoints v11.0 (2021), effective in the
+eucast_rules()function and inas.rsi()to interpret MIC and disk diffusion values. This is now the default guideline in this package. - Support for EUCAST Clinical Breakpoints v11.0 (2021), effective in the
eucast_rules()function and inas.rsi()to interpret MIC and disk diffusion values. This is now the default guideline in this package.- Added function
eucast_dosage()to get adata.framewith advised dosages of a certain bug-drug combination, which is based on the newdosagedata set - Added data set
dosageto fuel the neweucast_dosage()function and to make this data available in a structured way - Existing data set
example_isolatesnow reflects the latest EUCAST rules
- - Added function
-
-
Added argument
+only_rsi_columnsfor some functions, which defaults toFALSE, to indicate if the functions must only be applied to columns that are of class<rsi>(i.e., transformed withas.rsi()). This increases speed since automatic determination of antibiotic columns is not needed anymore. Affected functions are: - Added argument
only_rsi_columnsfor some functions, which defaults toFALSE, to indicate if the functions must only be applied to columns that are of class<rsi>(i.e., transformed withas.rsi()). This increases speed since automatic determination of antibiotic columns is not needed anymore. Affected functions are:- All antibiotic selector functions (
ab_class()and its wrappers, such asaminoglycosides(),carbapenems(),penicillins()) - All antibiotic filter functions (
filter_ab_class()and its wrappers, such asfilter_aminoglycosides(),filter_carbapenems(),filter_penicillins())
@@ -331,21 +328,21 @@
- All antibiotic selector functions (
-
Functions
-oxazolidinones()(an antibiotic selector function) andfilter_oxazolidinones()(an antibiotic filter function) to select/filter on e.g. linezolid and tedizolid+-
++#> Filtering on oxazolidinones: value in column `LNZ` (linezolid) is either "R", "S" or "I"library(dplyr) x <- example_isolates %>% select(date, hospital_id, oxazolidinones()) #> Selecting oxazolidinones: column 'LNZ' (linezolid) x <- example_isolates %>% filter_oxazolidinones() -#> Filtering on oxazolidinones: value in column `LNZ` (linezolid) is either "R", "S" or "I"
+ - Support for custom MDRO guidelines, using the new
custom_mdro_guideline()function, please seemdro()for additional info
+ -
+
ggplot()generics for classes<mic>and<disk>
- Support for custom MDRO guidelines, using the new
custom_mdro_guideline()function, please seemdro()for additional info
-ggplot()generics for classes<mic>and<disk>-
Function
-mo_is_yeast(), which determines whether a microorganism is a member of the taxonomic class Saccharomycetes or the taxonomic order Saccharomycetales:-
++example_isolates %>% filter(mo_is_yeast()) # dplyrmo_kingdom(c("Aspergillus", "Candida")) #> [1] "Fungi" "Fungi" @@ -354,20 +351,18 @@ # usage for filtering data: example_isolates[which(mo_is_yeast()), ] # base R -example_isolates %>% filter(mo_is_yeast()) # dplyr
The
-mo_type()function has also been updated to reflect this change:
- Added Pretomanid (PMD, J04AK08) to the
antibioticsdata set
+- Added Pretomanid (PMD, J04AK08) to the
antibioticsdata set -
MIC values (see
-as.mic()) can now be used in any mathematical processing, such as usage inside functionsmin(),max(),range(), and with binary operators (+,-, etc.). This allows for easy distribution analysis and fast filtering on MIC values:-
++#> [1] -3 8x <- random_mic(10) x #> Class <mic> @@ -378,7 +373,7 @@ range(x) #> [1] 0.125 256.000 range(log2(x)) -#> [1] -3 8
- Plotting of MIC and disk diffusion values now support interpretation colouring if you supply the microorganism and antimicrobial agent
- All colours were updated to colour-blind friendly versions for values R, S and I for all plot methods (also applies to tibble printing)
- Interpretation of MIC and disk diffusion values to R/SI will now be translated if the system language is German, Dutch or Spanish (see
-translate)- Plotting is now possible with base R using
+plot()and with ggplot2 usingggplot()on any vector of MIC and disk diffusion values- Plotting is now possible with base R using
plot()and with ggplot2 usingggplot()on any vector of MIC and disk diffusion values- Updated SNOMED codes to US Edition of SNOMED CT from 1 September 2020 and added the source to the help page of the
@@ -415,7 +410,7 @@microorganismsdata setis.rsi.eligible()now detects if the column name resembles an antibiotic name or code and now returnsTRUEimmediately if the input contains any of the values “R”, “S” or “I”. This drastically improves speed, also for a lot of other functions that rely on automatic determination of antibiotic columns.- Functions
get_episode()andis_new_episode()now support less than a day as value for argumentepisode_days(e.g., to include one patient/test per hour)- Argument
-ampc_cephalosporin_resistanceineucast_rules()now also applies to value “I” (not only “S”)- Functions
print()andsummary()on a Principal Components Analysis object (pca()) now print additional group info if the original data was grouped usingdplyr::group_by()+- Functions
print()andsummary()on a Principal Components Analysis object (pca()) now print additional group info if the original data was grouped usingdplyr::group_by()- Improved speed and reliability of
guess_ab_col(). As this also internally improves the reliability offirst_isolate()andmdro(), this might have a slight impact on the results of those functions.- Fix for
@@ -450,15 +445,14 @@mo_name()when used in other languages than English-
Functions
-get_episode()andis_new_episode()to determine (patient) episodes which are not necessarily based on microorganisms. Theget_episode()function returns the index number of the episode per group, while theis_new_episode()function returns valuesTRUE/FALSEto indicate whether an item in a vector is the start of a new episode. They also supportdplyrs grouping (i.e. usinggroup_by()):-
++ filter(is_new_episode(date, episode_days = 60))library(dplyr) example_isolates %>% group_by(patient_id, hospital_id) %>% - filter(is_new_episode(date, episode_days = 60))
- Functions
mo_is_gram_negative()andmo_is_gram_positive()as wrappers aroundmo_gramstain(). They always returnTRUEorFALSE(except when the input isNAor the MO code isUNKNOWN), thus always returnFALSEfor species outside the taxonomic kingdom of Bacteria.
-Function
mo_is_intrinsic_resistant()to test for intrinsic resistance, based on EUCAST Intrinsic Resistance and Unusual Phenotypes v3.2 from 2020.
+- Functions
mo_is_gram_negative()andmo_is_gram_positive()as wrappers aroundmo_gramstain(). They always returnTRUEorFALSE(except when the input isNAor the MO code isUNKNOWN), thus always returnFALSEfor species outside the taxonomic kingdom of Bacteria.
+ - Function
mo_is_intrinsic_resistant()to test for intrinsic resistance, based on EUCAST Intrinsic Resistance and Unusual Phenotypes v3.2 from 2020. Functions
random_mic(),random_disk()andrandom_rsi()for random value generation. The functionsrandom_mic()andrandom_disk()take microorganism names and antibiotic names as input to make generation more realistic.
Changed
-
-
New argument
ampc_cephalosporin_resistanceineucast_rules()to correct for AmpC de-repressed cephalosporin-resistant mutants
--
-
Interpretation of antimicrobial resistance -
+as.rsi(): - New argument
ampc_cephalosporin_resistanceineucast_rules()to correct for AmpC de-repressed cephalosporin-resistant mutants
+ - Interpretation of antimicrobial resistance -
as.rsi():- Reference data used for
as.rsi()can now be set by the user, using thereference_dataargument. This allows for using own interpretation guidelines. The user-set data must have the same structure asrsi_translation. - Better determination of disk zones and MIC values when running
as.rsi()on a data.frame
@@ -479,14 +472,13 @@
- Fix for using
as.rsi()on adata.framethat only contains one column for antibiotic interpretations
- - Reference data used for
-
-
Some functions are now context-aware when used inside
+dplyrverbs, such asfilter(),mutate()andsummarise(). This means that then the data argument does not need to be set anymore. This is the case for the new functions: - Some functions are now context-aware when used inside
dplyrverbs, such asfilter(),mutate()andsummarise(). This means that then the data argument does not need to be set anymore. This is the case for the new functions: -… and for the existing functions:
+… and for the existing functions:-
first_isolate(),
@@ -504,38 +496,40 @@
mdr_cmi2012(), -
eucast_exceptional_phenotypes()
-
++ as_tibble()# to select first isolates that are Gram-negative # and view results of cephalosporins and aminoglycosides: library(dplyr) example_isolates %>% filter(first_isolate(), mo_is_gram_negative()) %>% select(mo, cephalosporins(), aminoglycosides()) %>% - as_tibble()
For antibiotic selection functions (such as
-cephalosporins(),aminoglycosides()) to select columns based on a certain antibiotic group, the dependency on thetidyselectpackage was removed, meaning that they can now also be used without the need to have this package installed and now also work in base R function calls (they rely on R 3.2 or later):+-
++ c("mo", cephalosporins(), aminoglycosides())]# above example in base R: example_isolates[which(first_isolate() & mo_is_gram_negative()), - c("mo", cephalosporins(), aminoglycosides())]
- For all function arguments in the code, it is now defined what the exact type of user input should be (inspired by the
+typedpackage). If the user input for a certain function does not meet the requirements for a specific argument (such as the class or length), an informative error will be thrown. This makes the package more robust and the use of it more reproducible and reliable. In total, more than 420 arguments were defined.- Fix for
+set_mo_source(), that previously would not remember the file location of the original file- Deprecated function
+p_symbol()that not really fits the scope of this package. It will be removed in a future version. See here for the source code to preserve it.- Updated coagulase-negative staphylococci determination with Becker et al. 2020 (PMID 32056452), meaning that the species S. argensis, S. caeli, S. debuckii, S. edaphicus and S. pseudoxylosus are now all considered CoNS
+- Fix for using argument
+reference_dfinas.mo()andmo_*()functions that contain old microbial codes (from previous package versions)- Fixed a bug where
+mo_uncertainties()would not return the results based on the MO matching score- Fixed a bug where
+as.mo()would not return results for known laboratory codes for microorganisms- Fixed a bug where
+as.ab()would sometimes fail- Better tibble printing for MIC values
+- Fix for plotting MIC values with
+plot()+- Added
+plot()generic to class<disk>+- LA-MRSA and CA-MRSA are now recognised as an abbreviation for Staphylococcus aureus, meaning that e.g.
+mo_genus("LA-MRSA")will return"Staphylococcus"andmo_is_gram_positive("LA-MRSA")will returnTRUE.- Fix for printing class
+in tibbles when all values are +NA- Fix for
-mo_shortname()when the input containsNAFor all function arguments in the code, it is now defined what the exact type of user input should be (inspired by the
typedpackage). If the user input for a certain function does not meet the requirements for a specific argument (such as the class or length), an informative error will be thrown. This makes the package more robust and the use of it more reproducible and reliable. In total, more than 420 arguments were defined.Fix for
set_mo_source(), that previously would not remember the file location of the original fileDeprecated function
p_symbol()that not really fits the scope of this package. It will be removed in a future version. See here for the source code to preserve it.Updated coagulase-negative staphylococci determination with Becker et al. 2020 (PMID 32056452), meaning that the species S. argensis, S. caeli, S. debuckii, S. edaphicus and S. pseudoxylosus are now all considered CoNS
Fix for using argument
reference_dfinas.mo()andmo_*()functions that contain old microbial codes (from previous package versions)Fixed a bug where
mo_uncertainties()would not return the results based on the MO matching scoreFixed a bug where
as.mo()would not return results for known laboratory codes for microorganismsFixed a bug where
as.ab()would sometimes failBetter tibble printing for MIC values
Fix for plotting MIC values with
plot()Added
plot()generic to class<disk>LA-MRSA and CA-MRSA are now recognised as an abbreviation for Staphylococcus aureus, meaning that e.g.
mo_genus("LA-MRSA")will return"Staphylococcus"andmo_is_gram_positive("LA-MRSA")will returnTRUE.Fix for printing class
in tibbles when all values are NAFix for
mo_shortname()when the input containsNAIf
as.mo()takes more than 30 seconds, some suggestions will be done to improve speedNew
-
-
Support for ‘EUCAST Expert Rules’ / ‘EUCAST Intrinsic Resistance and Unusual Phenotypes’ version 3.2 of May 2020. With this addition to the previously implemented version 3.1 of 2016, the
eucast_rules()function can now correct for more than 180 different antibiotics and themdro()function can determine multidrug resistance based on more than 150 different antibiotics. All previously implemented versions of the EUCAST rules are now maintained and kept available in this package. Theeucast_rules()function consequently gained the argumentsversion_breakpoints(at the moment defaults to v10.0, 2020) andversion_expertrules(at the moment defaults to v3.2, 2020). Theexample_isolatesdata set now also reflects the change from v3.1 to v3.2. Themdro()function now acceptsguideline == "EUCAST3.1"andguideline == "EUCAST3.2".
-A new vignette and website page with info about all our public and freely available data sets, that can be downloaded as flat files or in formats for use in R, SPSS, SAS, Stata and Excel: https://msberends.github.io/AMR/articles/datasets.html
+- Support for ‘EUCAST Expert Rules’ / ‘EUCAST Intrinsic Resistance and Unusual Phenotypes’ version 3.2 of May 2020. With this addition to the previously implemented version 3.1 of 2016, the
eucast_rules()function can now correct for more than 180 different antibiotics and themdro()function can determine multidrug resistance based on more than 150 different antibiotics. All previously implemented versions of the EUCAST rules are now maintained and kept available in this package. Theeucast_rules()function consequently gained the argumentsversion_breakpoints(at the moment defaults to v10.0, 2020) andversion_expertrules(at the moment defaults to v3.2, 2020). Theexample_isolatesdata set now also reflects the change from v3.1 to v3.2. Themdro()function now acceptsguideline == "EUCAST3.1"andguideline == "EUCAST3.2".
+ - A new vignette and website page with info about all our public and freely available data sets, that can be downloaded as flat files or in formats for use in R, SPSS, SAS, Stata and Excel: https://msberends.github.io/AMR/articles/datasets.html +
-
Data set
intrinsic_resistant. This data set contains all bug-drug combinations where the ‘bug’ is intrinsic resistant to the ‘drug’ according to the latest EUCAST insights. It contains just two columns:microorganismandantibiotic.Curious about which enterococci are actually intrinsic resistant to vancomycin?
-
- Support for veterinary ATC codes
+- Support for veterinary ATC codes
Support for skimming classes
<rsi>,<mic>,<disk>and<mo>with theskimrpackage
Changed
-
-
Although advertised that this package should work under R 3.0.0, we still had a dependency on R 3.6.0. This is fixed, meaning that our package should now work under R 3.0.0.
--
-
Improvements for
+as.rsi(): - Although advertised that this package should work under R 3.0.0, we still had a dependency on R 3.6.0. This is fixed, meaning that our package should now work under R 3.0.0. +
- Improvements for
as.rsi():-
Support for using
-dplyr’sacross()to interpret MIC values or disk zone diameters, which also automatically determines the column with microorganism names or codes.
- Cleaning columns in a data.frame now allows you to specify those columns with tidy selection, e.g.
as.rsi(df, col1:col9)
-Big speed improvement for interpreting MIC values and disk zone diameters. When interpreting 5,000 MIC values of two antibiotics (10,000 values in total), our benchmarks showed a total run time going from 80.7-85.1 seconds to 1.8-2.0 seconds.
-Added argument ‘add_intrinsic_resistance’ (defaults to
FALSE), that considers intrinsic resistance according to EUCAST
-Fixed a bug where in EUCAST rules the breakpoint for R would be interpreted as “>=” while this should have been “<”
+- Cleaning columns in a data.frame now allows you to specify those columns with tidy selection, e.g.
as.rsi(df, col1:col9)+
+ - Big speed improvement for interpreting MIC values and disk zone diameters. When interpreting 5,000 MIC values of two antibiotics (10,000 values in total), our benchmarks showed a total run time going from 80.7-85.1 seconds to 1.8-2.0 seconds. +
- Added argument ‘add_intrinsic_resistance’ (defaults to
FALSE), that considers intrinsic resistance according to EUCAST
+ - Fixed a bug where in EUCAST rules the breakpoint for R would be interpreted as “>=” while this should have been “<”
-
-
Added intelligent data cleaning to
-as.disk(), so numbers can also be extracted from text and decimal numbers will always be rounded up:
- -
-
Improvements for
+as.mo(): - Improvements for
as.mo():- A completely new matching score for ambiguous user input, using
mo_matching_score(). Any user input value that could mean more than one taxonomic entry is now considered ‘uncertain’. Instead of a warning, a message will be thrown and the accompanyingmo_uncertainties()has been changed completely; it now prints all possible candidates with their matching score. - Big speed improvement for already valid microorganism ID. This also means an significant speed improvement for using
mo_*functions likemo_name()on microoganism IDs. - Added argument
ignore_patterntoas.mo()which can also be given tomo_*functions likemo_name(), to exclude known non-relevant input from analysing. This can also be set with the optionAMR_ignore_pattern.
- - A completely new matching score for ambiguous user input, using
get_locale()now uses at defaultSys.getenv("LANG")or, ifLANGis not set,Sys.getlocale(). This can be overwritten by setting the optionAMR_locale.
-Big speed improvement for
eucast_rules()
-Overall speed improvement by tweaking joining functions
-Function
mo_shortname()now returns the genus for input where the species is unknown
-BORSA is now recognised as an abbreviation for Staphylococcus aureus, meaning that e.g.
mo_genus("BORSA")will return “Staphylococcus”
-Added a feature from AMR 1.1.0 and earlier again, but now without other package dependencies:
tibbleprinting support for classes<rsi>,<mic>,<disk>,<ab>and<mo>. When usingtibbles containing antimicrobial columns (class<rsi>), “S” will print in green, “I” will print in yellow and “R” will print in red. Microbial IDs (class<mo>) will emphasise on the genus and species, not on the kingdom.
-Names of antiviral agents in data set
antiviralsnow have a starting capital letter, like it is the case in theantibioticsdata set
-Updated the documentation of the
WHONETdata set to clarify that all patient names are fictitious
-Small
as.ab()algorithm improvements
-Fix for combining MIC values with raw numbers, i.e.
c(as.mic(2), 2)previously failed but now returns a valid MIC class
-ggplot_rsi()andgeom_rsi()gained argumentsminimumandlanguage, to influence the internal use ofrsi_df()-
-
Changes in the
+antibioticsdata set:get_locale()now uses at defaultSys.getenv("LANG")or, ifLANGis not set,Sys.getlocale(). This can be overwritten by setting the optionAMR_locale.
+ - Big speed improvement for
eucast_rules()+
+ - Overall speed improvement by tweaking joining functions +
- Function
mo_shortname()now returns the genus for input where the species is unknown
+ - BORSA is now recognised as an abbreviation for Staphylococcus aureus, meaning that e.g.
mo_genus("BORSA")will return “Staphylococcus”
+ - Added a feature from AMR 1.1.0 and earlier again, but now without other package dependencies:
tibbleprinting support for classes<rsi>,<mic>,<disk>,<ab>and<mo>. When usingtibbles containing antimicrobial columns (class<rsi>), “S” will print in green, “I” will print in yellow and “R” will print in red. Microbial IDs (class<mo>) will emphasise on the genus and species, not on the kingdom.
+ - Names of antiviral agents in data set
antiviralsnow have a starting capital letter, like it is the case in theantibioticsdata set
+ - Updated the documentation of the
WHONETdata set to clarify that all patient names are fictitious
+ - Small
as.ab()algorithm improvements
+ - Fix for combining MIC values with raw numbers, i.e.
c(as.mic(2), 2)previously failed but now returns a valid MIC class
+ -
+
ggplot_rsi()andgeom_rsi()gained argumentsminimumandlanguage, to influence the internal use ofrsi_df()+
+ - Changes in the
antibioticsdata set:- Updated oral and parental DDDs from the WHOCC
- Added abbreviation “piptazo” to ‘Piperacillin/tazobactam’ (TZP) @@ -643,7 +637,8 @@
- The group name (
antibiotics$group) of ‘Linezolid’ (LNZ), ‘Cycloserine’ (CYC), ‘Tedizolid’ (TZD) and ‘Thiacetazone’ (THA) is now “Oxazolidinones” instead of “Other antibacterials”
- Added support for using
unique()on classes<rsi>,<mic>,<disk>,<ab>and<mo>
+- Added support for using
unique()on classes<rsi>,<mic>,<disk>,<ab>and<mo>+ Added argument
excessto thekurtosis()function (defaults toFALSE), to return the excess kurtosis, defined as the kurtosis minus three.
New
-
-
Function
ab_from_text()to retrieve antimicrobial drug names, doses and forms of administration from clinical texts in e.g. health care records, which also corrects for misspelling since it usesas.ab()internally
+- Function
ab_from_text()to retrieve antimicrobial drug names, doses and forms of administration from clinical texts in e.g. health care records, which also corrects for misspelling since it usesas.ab()internally -
Tidyverse selection helpers for antibiotic classes, that help to select the columns of antibiotics that are of a specific antibiotic class, without the need to define the columns or antibiotic abbreviations. They can be used in any function that allows selection helpers, like
-dplyr::select()andtidyr::pivot_longer():-
++#> Selecting carbapenems: `IPM` (imipenem), `MEM` (meropenem)library(dplyr) # Columns 'IPM' and 'MEM' are in the example_isolates data set example_isolates %>% select(carbapenems()) -#> Selecting carbapenems: `IPM` (imipenem), `MEM` (meropenem)
- Added
mo_domain()as an alias tomo_kingdom()
-Added function
filter_penicillins()to filter isolates on a specific result in any column with a name in the antimicrobial ‘penicillins’ class (more specific: ATC subgroup Beta-lactam antibacterials, penicillins)
-Added official antimicrobial names to all
filter_ab_class()functions, such asfilter_aminoglycosides()
-Added antibiotics code “FOX1” for cefoxitin screening (abbreviation “cfsc”) to the
antibioticsdata set
-Added Monuril as trade name for fosfomycin
+- Added
mo_domain()as an alias tomo_kingdom()+
+ - Added function
filter_penicillins()to filter isolates on a specific result in any column with a name in the antimicrobial ‘penicillins’ class (more specific: ATC subgroup Beta-lactam antibacterials, penicillins)
+ - Added official antimicrobial names to all
filter_ab_class()functions, such asfilter_aminoglycosides()+
+ - Added antibiotics code “FOX1” for cefoxitin screening (abbreviation “cfsc”) to the
antibioticsdata set
+ - Added Monuril as trade name for fosfomycin
Added argument
conserve_capped_valuestoas.rsi()for interpreting MIC values - it makes sure that values starting with “<” (but not “<=”) will always return “S” and values starting with “>” (but not “>=”) will always return “R”. The default behaviour ofas.rsi()has not changed, so you need to specifically doas.rsi(..., conserve_capped_values = TRUE).
-
Big speed improvement for using any function on microorganism codes from earlier package versions (prior to
-AMRv1.2.0), such asas.mo(),mo_name(),first_isolate(),eucast_rules(),mdro(), etc.As a consequence, very old microbial codes (from
-AMRv0.5.0 and lower) are not supported anymore. Useas.mo()on your microorganism names or codes to transform them to current abbreviations used in this package.
- -
-
Improvements for
+As a consequence, very old microbial codes (fromsusceptibility()andresistance()and allcount_*(),proportion_*()functions:AMRv0.5.0 and lower) are not supported anymore. Useas.mo()on your microorganism names or codes to transform them to current abbreviations used in this package.
+ - Improvements for
susceptibility()andresistance()and allcount_*(),proportion_*()functions:- 95% speed improvement by using other base R functions for calculation
- Using unexisting columns wil now return an error instead of dropping them silently
- Using variables for column names (as well as selectors like
dplyr::all_of()) now works again
- -
-
Improvements for
+as.ab(): - Improvements for
as.ab():- Dramatic improvement of the algorithm behind
as.ab(), making many more input errors translatable, such as digitalised health care records, using too few or too many vowels or consonants and many more - Added progress bar @@ -711,25 +704,26 @@
- The
as.ab()function will now throw a note if more than 1 antimicrobial drug could be retrieved from a single input value.
- - Dramatic improvement of the algorithm behind
Fixed a bug where
eucast_rules()would not work on a tibble when thetibbleordplyrpackage was loaded
-Fixed a bug for CLSI 2019 guidelines (using
as.rsi()), that also included results for animals. It now only contains interpretation guidelines for humans.
-All
*_join_microorganisms()functions andbug_drug_combinations()now return the original data class (e.g.tibbles anddata.tables)
--
-
For functions
+rsi_df(),proportion_df()andcount_df(): - Fixed a bug where
eucast_rules()would not work on a tibble when thetibbleordplyrpackage was loaded
+ - Fixed a bug for CLSI 2019 guidelines (using
as.rsi()), that also included results for animals. It now only contains interpretation guidelines for humans.
+ - All
*_join_microorganisms()functions andbug_drug_combinations()now return the original data class (e.g.tibbles anddata.tables)
+ - For functions
rsi_df(),proportion_df()andcount_df():- Fixed a bug for using grouped versions
- Fixed a bug where not all different antimicrobial results were added as rows
- Fixed a bug when only calculating counts (
count_df()) when all antibiotics in the data set have onlyNAs
- Improved auto-determination for columns of types
<mo>and<Date>
-Fixed a bug in
bug_drug_combinations()for when only one antibiotic was in the input data
-Changed the summary for class
<rsi>, to highlight the %SI vs. %R
-Improved error handling, giving more useful info when functions return an error
-Any progress bar will now only show in interactive mode (i.e. not in R Markdown)
-Speed improvement for
mdro()andfilter_ab_class()
-New option
arrows_textangledforggplot_pca()to indicate whether the text at the end of the arrows should be angled (defaults toTRUE, as it was in previous versions)
-Added parenteral DDD to benzylpenicillin
+- Improved auto-determination for columns of types
<mo>and<Date>+
+ - Fixed a bug in
bug_drug_combinations()for when only one antibiotic was in the input data
+ - Changed the summary for class
<rsi>, to highlight the %SI vs. %R
+ - Improved error handling, giving more useful info when functions return an error +
- Any progress bar will now only show in interactive mode (i.e. not in R Markdown) +
- Speed improvement for
mdro()andfilter_ab_class()+
+ - New option
arrows_textangledforggplot_pca()to indicate whether the text at the end of the arrows should be angled (defaults toTRUE, as it was in previous versions)
+ - Added parenteral DDD to benzylpenicillin
Fixed a bug where
as.mic()could not handle dots without a leading zero (like"<=.25)
- Microorganisms should be transformed to our own microorganism IDs (called an
-
Removed code dependency on all other R packages, making this package fully independent of the development process of others. This is a major code change, but will probably not be noticeable by most users.
Making this package independent of especially the tidyverse (e.g. packages
-dplyrandtidyr) tremendously increases sustainability on the long term, since tidyverse functions change quite often. Good for users, but hard for package maintainers. Most of our functions are replaced with versions that only rely on base R, which keeps this package fully functional for many years to come, without requiring a lot of maintenance to keep up with other packages anymore. Another upside it that this package can now be used with all versions of R since R-3.0.0 (April 2013). Our package is being used in settings where the resources are very limited. Fewer dependencies on newer software is helpful for such settings.Negative effects of this change are:
+Negative effects of this change are:-
-
- Function
freq()that was borrowed from thecleanerpackage was removed. Usecleaner::freq(), or runlibrary("cleaner")before you usefreq().
+ - Function
freq()that was borrowed from thecleanerpackage was removed. Usecleaner::freq(), or runlibrary("cleaner")before you usefreq(). Printing values of classmoorrsiin a tibble will no longer be in colour and printingrsiin a tibble will show the class<ord>, not<rsi>anymore. This is purely a visual effect.All functions from themo_*family (likemo_name()andmo_gramstain()) are noticeably slower when running on hundreds of thousands of rows.- For developers: classes
moandabnow both also inherit classcharacter, to support any data transformation. This change invalidates code that checks for class length == 1.
@@ -855,19 +849,18 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
Fixed important floating point error for some MIC comparisons in EUCAST 2020 guideline
+- Fixed important floating point error for some MIC comparisons in EUCAST 2020 guideline
-
Interpretation from MIC values (and disk zones) to R/SI can now be used with
-mutate_at()of thedplyrpackage:
- Added antibiotic abbreviations for a laboratory manufacturer (GLIMS) for cefuroxime, cefotaxime, ceftazidime, cefepime, cefoxitin and trimethoprim/sulfamethoxazole
-Added
uti(as abbreviation of urinary tract infections) as argument toas.rsi(), so interpretation of MIC values and disk zones can be made dependent on isolates specifically from UTIs
+- Added antibiotic abbreviations for a laboratory manufacturer (GLIMS) for cefuroxime, cefotaxime, ceftazidime, cefepime, cefoxitin and trimethoprim/sulfamethoxazole +
- Added
uti(as abbreviation of urinary tract infections) as argument toas.rsi(), so interpretation of MIC values and disk zones can be made dependent on isolates specifically from UTIs Info printing in functions
eucast_rules(),first_isolate(),mdro()andresistance_predict()will now at default only print when R is in an interactive mode (i.e. not in RMarkdown)
Changed
-
-
- Function
-
Support for LOINC codes in the
-antibioticsdata set. Useab_loinc()to retrieve LOINC codes, or use a LOINC code for input in anyab_*function: -
Support for SNOMED CT codes in the
-microorganismsdata set. Usemo_snomed()to retrieve SNOMED codes, or use a SNOMED code for input in anymo_*function:-
++#> [1] "Gram-positive"mo_snomed("S. aureus") #> [1] 115329001 3092008 113961008 mo_name(115329001) #> [1] "Staphylococcus aureus" mo_gramstain(115329001) -#> [1] "Gram-positive"
@@ -963,13 +954,11 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
-
If you were dependent on the old Enterobacteriaceae family e.g. by using in your code:
-+-
-if (mo_family(somebugs) == "Enterobacteriaceae") ...+if (mo_family(somebugs) == "Enterobacteriaceae") ...
then please adjust this to:
-+-
-if (mo_order(somebugs) == "Enterobacterales") ...+if (mo_order(somebugs) == "Enterobacterales") ...
@@ -981,17 +970,15 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
-
Functions
-susceptibility()andresistance()as aliases ofproportion_SI()andproportion_R(), respectively. These functions were added to make it more clear that “I” should be considered susceptible and not resistant.
- -
-
Support for a new MDRO guideline: Magiorakos AP, Srinivasan A et al. “Multidrug-resistant, extensively drug-resistant and pandrug-resistant bacteria: an international expert proposal for interim standard definitions for acquired resistance.” Clinical Microbiology and Infection (2012).
+ - Support for a new MDRO guideline: Magiorakos AP, Srinivasan A et al. “Multidrug-resistant, extensively drug-resistant and pandrug-resistant bacteria: an international expert proposal for interim standard definitions for acquired resistance.” Clinical Microbiology and Infection (2012).
- This is now the new default guideline for the
mdro()function - The new Verbose mode (
mdro(...., verbose = TRUE)) returns an informative data set where the reason for MDRO determination is given for every isolate, and an list of the resistant antimicrobial agents
@@ -1006,12 +993,11 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
- Improvements to algorithm in
as.mo():-
-
Now allows “ou” where “au” should have been used and vice versa
-More intelligent way of coping with some consonants like “l” and “r”
+- Now allows “ou” where “au” should have been used and vice versa +
- More intelligent way of coping with some consonants like “l” and “r”
-
Added a score (a certainty percentage) to
-mo_uncertainties(), that is calculated using the Levenshtein distance:-
++#> "staphylokok aureuz" -> Staphylococcus aureus (B_STPHY_AURS, score: 85.7%)as.mo(c("Stafylococcus aureus", "staphylokok aureuz")) #> Warning: @@ -1021,7 +1007,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/ mo_uncertainties() #> "Stafylococcus aureus" -> Staphylococcus aureus (B_STPHY_AURS, score: 95.2%) -#> "staphylokok aureuz" -> Staphylococcus aureus (B_STPHY_AURS, score: 85.7%)
@@ -1069,15 +1055,12 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
-
Determination of first isolates now excludes all ‘unknown’ microorganisms at default, i.e. microbial code
-"UNKNOWN". They can be included with the new argumentinclude_unknown:--
-first_isolate(..., include_unknown = TRUE)For WHONET users, this means that all records/isolates with organism code
-"con"(contamination) will be excluded at default, sinceas.mo("con") = "UNKNOWN". The function always shows a note with the number of ‘unknown’ microorganisms that were included or excluded.
+
+For WHONET users, this means that all records/isolates with organism code+first_isolate(..., include_unknown = TRUE)
"con"(contamination) will be excluded at default, sinceas.mo("con") = "UNKNOWN". The function always shows a note with the number of ‘unknown’ microorganisms that were included or excluded. - This is now the new default guideline for the
-
For code consistency, classes
-abandmowill now be preserved in any subsetting or assignment. For the sake of data integrity, this means that invalid assignments will now result inNA:+This is important, because a value like-
+-# how it works in base R: x <- factor("A") x[1] <- "B" @@ -1088,10 +1071,9 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/ x <- as.mo("E. coli") x[1] <- "testvalue" #> Warning message: -#> invalid microorganism code, NA generated
This is important, because a value like
- -"testvalue"could never be understood by e.g.mo_name(), although the class would suggest a valid microbial code.Function
freq()has moved to a new package,clean(CRAN link), since creating frequency tables actually does not fit the scope of this package. Thefreq()function still works, since it is re-exported from thecleanpackage (which will be installed automatically upon updating thisAMRpackage)."testvalue"could never be understood by e.g.mo_name(), although the class would suggest a valid microbial code.
+ - Function
freq()has moved to a new package,clean(CRAN link), since creating frequency tables actually does not fit the scope of this package. Thefreq()function still works, since it is re-exported from thecleanpackage (which will be installed automatically upon updating thisAMRpackage). Renamed data set
septic_patientstoexample_isolates
-
Function
-bug_drug_combinations()to quickly get adata.framewith the results of all bug-drug combinations in a data set. The column containing microorganism codes is guessed automatically and its input is transformed withmo_shortname()at default:-
++#> NOTE: Use 'format()' on this result to get a publicable/printable format.x <- bug_drug_combinations(example_isolates) #> NOTE: Using column `mo` as input for `col_mo`. x[1:4, ] @@ -1122,16 +1103,14 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/ #> 2 Gram-negative AMK 251 0 2 253 #> 3 Gram-negative AMP 227 0 405 632 #> 4 Gram-negative AMX 227 0 405 632 -#> NOTE: Use 'format()' on this result to get a publicable/printable format.
You can format this to a printable format, ready for reporting or exporting to e.g. Excel with the base R
-format()function:+-
-format(x, combine_IR = FALSE)+format(x, combine_IR = FALSE)
-
Additional way to calculate co-resistance, i.e. when using multiple antimicrobials as input for
-portion_*functions orcount_*functions. This can be used to determine the empiric susceptibility of a combination therapy. A new argumentonly_all_tested(which defaults toFALSE) replaces the oldalso_single_testedand can be used to select one of the two methods to count isolates and calculate portions. The difference can be seen in this example table (which is also on theportionandcounthelp pages), where the %SI is being determined:+Since this is a major change, usage of the old-
+-# -------------------------------------------------------------------- # only_all_tested = FALSE only_all_tested = TRUE # ----------------------- ----------------------- @@ -1147,18 +1126,16 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/ # S or I <NA> X X - - # R <NA> - - - - # <NA> <NA> - - - - -# --------------------------------------------------------------------
Since this is a major change, usage of the old
- +# --------------------------------------------------------------------also_single_testedwill throw an informative error that it has been replaced byonly_all_tested.also_single_testedwill throw an informative error that it has been replaced byonly_all_tested. -
-tibbleprinting support for classesrsi,mic,disk,abmo. When usingtibbles containing antimicrobial columns, valuesSwill print in green, valuesIwill print in yellow and valuesRwill print in red. Microbial IDs (classmo) will emphasise on the genus and species, not on the kingdom.
-
Function
-rsi_df()to transform adata.frameto a data set containing only the microbial interpretation (S, I, R), the antibiotic, the percentage of S/I/R and the number of available isolates. This is a convenient combination of the existing functionscount_df()andportion_df()to immediately show resistance percentages and number of available isolates:-
++# 4 Ciprofloxacin R 0.1618169 228septic_patients %>% select(AMX, CIP) %>% rsi_df() @@ -1244,7 +1220,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/ # 1 Amoxicillin SI 0.4442636 546 # 2 Amoxicillin R 0.5557364 683 # 3 Ciprofloxacin SI 0.8381831 1181 -# 4 Ciprofloxacin R 0.1618169 228
-
Support for all scientifically published pathotypes of E. coli to date (that we could find). Supported are:
@@ -1262,16 +1238,15 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/ - UPEC (Uropathogenic E. coli)
All these lead to the microbial ID of E. coli:
---
++# "Gram-negative"as.mo("UPEC") # B_ESCHR_COL mo_name("UPEC") # "Escherichia coli" mo_gramstain("EHEC") -# "Gram-negative"
Function
mo_info()as an analogy toab_info(). Themo_info()prints a list with the full taxonomy, authors, and the URL to the online database of a microorganism- Function
mo_info()as an analogy toab_info(). Themo_info()prints a list with the full taxonomy, authors, and the URL to the online database of a microorganismFunction
mo_synonyms()to get all previously accepted taxonomic names of a microorganism - The
age()function gained a new argumentexactto determine ages with decimals - Removed deprecated functions
guess_mo(),guess_atc(),EUCAST_rules(),interpretive_reading(),rsi()
- - Frequency tables (
freq()): + - Frequency tables (
freq()):-
-
speed improvement for microbial IDs
-fixed factor level names for R Markdown
-when all values are unique it now shows a message instead of a warning
+- speed improvement for microbial IDs +
- fixed factor level names for R Markdown +
- when all values are unique it now shows a message instead of a warning
-
support for boxplots:
-
@@ -1385,7 +1359,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
- Added ceftazidim intrinsic resistance to Streptococci
- Changed default settings for
age_groups(), to let groups of fives and tens end with 100+ instead of 120+
- - Fix for
freq()for when all values areNA+ - Fix for
freq()for when all values areNA - Fix for
first_isolate()for when dates are missing - Improved speed of
guess_ab_col()@@ -1435,25 +1409,23 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/New
-
-
BREAKING: removed deprecated functions, arguments and references to ‘bactid’. Use
as.mo()to identify an MO code.-
-
Catalogue of Life as a new taxonomic source for data about microorganisms, which also contains all ITIS data we used previously. The
+BREAKING: removed deprecated functions, arguments and references to ‘bactid’. Usemicroorganismsdata set now contains:as.mo()to identify an MO code.
+ - Catalogue of Life as a new taxonomic source for data about microorganisms, which also contains all ITIS data we used previously. The
microorganismsdata set now contains:-
-
All ~55,000 (sub)species from the kingdoms of Archaea, Bacteria and Protozoa
-All ~3,000 (sub)species from these orders of the kingdom of Fungi: Eurotiales, Onygenales, Pneumocystales, Saccharomycetales and Schizosaccharomycetales (covering at least like all species of Aspergillus, Candida, 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 ~15,000 previously accepted names of included (sub)species that have been taxonomically renamed
+- All ~55,000 (sub)species from the kingdoms of Archaea, Bacteria and Protozoa +
- All ~3,000 (sub)species from these orders of the kingdom of Fungi: Eurotiales, Onygenales, Pneumocystales, Saccharomycetales and Schizosaccharomycetales (covering at least like all species of Aspergillus, Candida, 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 ~15,000 previously accepted names of included (sub)species that have been taxonomically renamed
-
The responsible author(s) and year of scientific publication
-This data is updated annually - check the included version with the new function
-catalogue_of_life_version().
- Due to this change, some
mocodes changed (e.g. Streptococcus changed fromB_STRPTCtoB_STRPT). A translation table is used internally to support older microorganism IDs, so users will not notice this difference.
-New function
mo_rank()for the taxonomic rank (genus, species, infraspecies, etc.)
-New function
mo_url()to get the direct URL of a species from the Catalogue of Life
+This data is updated annually - check the included version with the new function
catalogue_of_life_version().
+ - Due to this change, some
mocodes changed (e.g. Streptococcus changed fromB_STRPTCtoB_STRPT). A translation table is used internally to support older microorganism IDs, so users will not notice this difference.
+ - New function
mo_rank()for the taxonomic rank (genus, species, infraspecies, etc.)
+ - New function
mo_url()to get the direct URL of a species from the Catalogue of Life
- -
-
Support for data from WHONET and EARS-Net (European Antimicrobial Resistance Surveillance Network):
+ - Support for data from WHONET and EARS-Net (European Antimicrobial Resistance Surveillance Network):
- Exported files from WHONET can be read and used in this package. For functions like
first_isolate()andeucast_rules(), all arguments will be filled in automatically. - This package now knows all antibiotic abbrevations by EARS-Net (which are also being used by WHONET) - the
antibioticsdata set now contains a columnears_net.
@@ -1462,8 +1434,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
- Exported files from WHONET can be read and used in this package. For functions like
-
New filters for antimicrobial classes. Use these functions to filter isolates on results in one of more antibiotics from a specific class:
--
++filter_tetracyclines()filter_aminoglycosides() filter_carbapenems() filter_cephalosporins() @@ -1474,60 +1445,55 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/ filter_fluoroquinolones() filter_glycopeptides() filter_macrolides() -filter_tetracyclines()
The
-antibioticsdata set will be searched, after which the input data will be checked for column names with a value in any abbreviations, codes or official names found in theantibioticsdata set. For example:-
++# Filtering on glycopeptide antibacterials: all of `vanc` and `teic` is Rseptic_patients %>% filter_glycopeptides(result = "R") # Filtering on glycopeptide antibacterials: any of `vanc` or `teic` is R septic_patients %>% filter_glycopeptides(result = "R", scope = "all") -# Filtering on glycopeptide antibacterials: all of `vanc` and `teic` is R
-
All
-ab_*functions are deprecated and replaced byatc_*functions:+These functions use-
+-ab_property -> atc_property() ab_name -> atc_name() ab_official -> atc_official() ab_trivial_nl -> atc_trivial_nl() ab_certe -> atc_certe() ab_umcg -> atc_umcg() -ab_tradenames -> atc_tradenames()
These functions use
- -as.atc()internally. The oldatc_propertyhas been renamedatc_online_property(). This is done for two reasons: firstly, not all ATC codes are of antibiotics (ab) but can also be of antivirals or antifungals. Secondly, the input must have classatcor must be coerable to this class. Properties of these classes should start with the same class name, analogous toas.mo()and e.g.mo_genus.New functions
set_mo_source()andget_mo_source()to use your own predefined MO codes as input foras.mo()and consequently allmo_*functionsSupport for the upcoming
dplyrversion 0.8.0New function
guess_ab_col()to find an antibiotic column in a tableNew function
mo_failures()to review values that could not be coerced to a valid MO code, usingas.mo(). This latter function will now only show a maximum of 10 uncoerced values and will refer tomo_failures().New function
mo_uncertainties()to review values that could be coerced to a valid MO code usingas.mo(), but with uncertainty.New function
mo_renamed()to get a list of all returned values fromas.mo()that have had taxonomic renamingNew function
age()to calculate the (patients) age in yearsNew function
age_groups()to split ages into custom or predefined groups (like children or elderly). This allows for easier demographic AMR data analysis per age group.as.atc()internally. The oldatc_propertyhas been renamedatc_online_property(). This is done for two reasons: firstly, not all ATC codes are of antibiotics (ab) but can also be of antivirals or antifungals. Secondly, the input must have classatcor must be coerable to this class. Properties of these classes should start with the same class name, analogous toas.mo()and e.g.mo_genus.
+ - New functions
set_mo_source()andget_mo_source()to use your own predefined MO codes as input foras.mo()and consequently allmo_*functions
+ - Support for the upcoming
dplyrversion 0.8.0
+ - New function
guess_ab_col()to find an antibiotic column in a table
+ - New function
mo_failures()to review values that could not be coerced to a valid MO code, usingas.mo(). This latter function will now only show a maximum of 10 uncoerced values and will refer tomo_failures().
+ - New function
mo_uncertainties()to review values that could be coerced to a valid MO code usingas.mo(), but with uncertainty.
+ - New function
mo_renamed()to get a list of all returned values fromas.mo()that have had taxonomic renaming
+ - New function
age()to calculate the (patients) age in years
+ - New function
age_groups()to split ages into custom or predefined groups (like children or elderly). This allows for easier demographic AMR data analysis per age group. -
New function
-ggplot_rsi_predict()as well as the base Rplot()function can now be used for resistance prediction calculated withresistance_predict():-
++ggplot_rsi_predict(x)x <- resistance_predict(septic_patients, col_ab = "amox") plot(x) -ggplot_rsi_predict(x)
-
Functions
-filter_first_isolate()andfilter_first_weighted_isolate()to shorten and fasten filtering on data sets with antimicrobial results, e.g.:-
++filter_first_isolate(septic_patients, ...)septic_patients %>% filter_first_isolate(...) # or -filter_first_isolate(septic_patients, ...)
is equal to:
-+-
++ select(-only_firsts)septic_patients %>% mutate(only_firsts = first_isolate(septic_patients, ...)) %>% filter(only_firsts == TRUE) %>% - select(-only_firsts)
+ - New function
availability()to check the number of available (non-empty) results in adata.frame
- New function
availability()to check the number of available (non-empty) results in adata.frameNew vignettes about how to conduct AMR analysis, predict antimicrobial resistance, use the G-test and more. These are also available (and even easier readable) on our website: https://msberends.gitlab.io/AMR.
-
Now handles incorrect spelling, like
-iinstead ofyandfinstead ofph:-
++#> [1] "Staphylococcus kloosii"# mo_fullname() uses as.mo() internally mo_fullname("Sthafilokockus aaureuz") #> [1] "Staphylococcus aureus" mo_fullname("S. klossi") -#> [1] "Staphylococcus kloosii"
-
Uncertainty of the algorithm is now divided into four levels, 0 to 3, where the default
-allow_uncertain = TRUEis equal to uncertainty level 2. Run?as.mofor more info about these levels.+Using-
+-# equal: as.mo(..., allow_uncertain = TRUE) as.mo(..., allow_uncertain = 2) # also equal: as.mo(..., allow_uncertain = FALSE) -as.mo(..., allow_uncertain = 0)
Using
+as.mo(..., allow_uncertain = 0)as.mo(..., allow_uncertain = 3)could lead to very unreliable results.as.mo(..., allow_uncertain = 3)could lead to very unreliable results.
+ - Implemented the latest publication of Becker et al. (2019), for categorising coagulase-negative Staphylococci -
Implemented the latest publication of Becker et al. (2019), for categorising coagulase-negative Staphylococci
-All microbial IDs that found are now saved to a local file
~/.Rhistory_mo. Use the new functionclean_mo_history()to delete this file, which resets the algorithms.
+- All microbial IDs that found are now saved to a local file
~/.Rhistory_mo. Use the new functionclean_mo_history()to delete this file, which resets the algorithms. -
Incoercible results will now be considered ‘unknown’, MO code
-UNKNOWN. On foreign systems, properties of these will be translated to all languages already previously supported: German, Dutch, French, Italian, Spanish and Portuguese:-
++#> [1] "(género desconocido)"mo_genus("qwerty", language = "es") # Warning: # one unique value (^= 100.0%) could not be coerced and is considered 'unknown': "qwerty". Use mo_failures() to review it. -#> [1] "(género desconocido)"
- Fix for vector containing only empty values
-Finds better results when input is in other languages
-Better handling for subspecies
-Better handling for Salmonellae, especially the ‘city like’ serovars like Salmonella London
-Understanding of highly virulent E. coli strains like EIEC, EPEC and STEC
-There will be looked for uncertain results at default - these results will be returned with an informative warning
-Manual (help page) now contains more info about the algorithms
-Progress bar will be shown when it takes more than 3 seconds to get results
-Support for formatted console text
-Console will return the percentage of uncoercable input
+- Fix for vector containing only empty values +
- Finds better results when input is in other languages +
- Better handling for subspecies +
- Better handling for Salmonellae, especially the ‘city like’ serovars like Salmonella London + +
- Understanding of highly virulent E. coli strains like EIEC, EPEC and STEC +
- There will be looked for uncertain results at default - these results will be returned with an informative warning +
- Manual (help page) now contains more info about the algorithms +
- Progress bar will be shown when it takes more than 3 seconds to get results +
- Support for formatted console text +
- Console will return the percentage of uncoercable input
- Function
first_isolate(): @@ -1626,35 +1590,36 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
- - Frequency tables (
freq()function): + - Frequency tables (
freq()function):-
Support for tidyverse quasiquotation! Now you can create frequency tables of function outcomes:
--
++ freq(mo_genus(mo))# Determine genus of microorganisms (mo) in `septic_patients` data set: # OLD WAY septic_patients %>% mutate(genus = mo_genus(mo)) %>% - freq(genus) + freq(genus) # NEW WAY septic_patients %>% - freq(mo_genus(mo)) + freq(mo_genus(mo)) # Even supports grouping variables: septic_patients %>% group_by(gender) %>% - freq(mo_genus(mo))
- Header info is now available as a list, with the
headerfunction
-The argument
headeris now set toTRUEat default, even for markdown
-Added header info for class
moto show unique count of families, genera and species
-Now honours the
decimal.marksetting, which just likeformatdefaults togetOption("OutDec")
-The new
big.markargument will at default be","whendecimal.mark = "."and"."otherwise
-Fix for header text where all observations are
NA
-New argument
droplevelsto exclude empty factor levels when input is a factor
-Factor levels will be in header when present in input data (maximum of 5)
-Fix for using
select()on frequency tables
+- Header info is now available as a list, with the
headerfunction
+ - The argument
headeris now set toTRUEat default, even for markdown
+ - Added header info for class
moto show unique count of families, genera and species
+ - Now honours the
decimal.marksetting, which just likeformatdefaults togetOption("OutDec")+
+ - The new
big.markargument will at default be","whendecimal.mark = "."and"."otherwise
+ - Fix for header text where all observations are
NA+
+ - New argument
droplevelsto exclude empty factor levels when input is a factor
+ - Factor levels will be in header when present in input data (maximum of 5) +
- Fix for using
select()on frequency tables
-
- Function
scale_y_percent()now contains thelimitsargument
@@ -1694,10 +1659,11 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
Functions
MDRO,BRMO,MRGNandEUCAST_exceptional_phenotypeswere renamed tomdro,brmo,mrgnandeucast_exceptional_phenotypes
-EUCAST_ruleswas renamed toeucast_rules, the old function still exists as a deprecated function
+- Functions
MDRO,BRMO,MRGNandEUCAST_exceptional_phenotypeswere renamed tomdro,brmo,mrgnandeucast_exceptional_phenotypes+ -
-
Big changes to the
+eucast_rulesfunction:EUCAST_ruleswas renamed toeucast_rules, the old function still exists as a deprecated function
+ - Big changes to the
eucast_rulesfunction:- Now also applies rules from the EUCAST ‘Breakpoint tables for bacteria’, version 8.1, 2018, https://www.eucast.org/clinical_breakpoints/ (see Source of the function)
- New argument
rulesto specify which rules should be applied (expert rules, breakpoints, others or all)
@@ -1709,61 +1675,64 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
- Small fixes to EUCAST clinical breakpoint rules
- Added column
kingdomto the microorganisms data set, and functionmo_kingdomto look up values
-Tremendous speed improvement for
as.mo(and subsequently allmo_*functions), as empty values wil be ignored a priori
-Fewer than 3 characters as input for
as.mowill return NA
+- Added column
kingdomto the microorganisms data set, and functionmo_kingdomto look up values
+ - Tremendous speed improvement for
as.mo(and subsequently allmo_*functions), as empty values wil be ignored a priori +
+ - Fewer than 3 characters as input for
as.mowill return NA -
Function
-as.mo(and allmo_*wrappers) now supports genus abbreviations with “species” attached-
++mo_fullname("S. species") # "Staphylococcus species"as.mo("E. species") # B_ESCHR mo_fullname("E. spp.") # "Escherichia species" as.mo("S. spp") # B_STPHY -mo_fullname("S. species") # "Staphylococcus species"
- Added argument
combine_IR(TRUE/FALSE) to functionsportion_dfandcount_df, to indicate that all values of I and R must be merged into one, so the output only consists of S vs. IR (susceptible vs. non-susceptible)
-Fix for
portion_*(..., as_percent = TRUE)when minimal number of isolates would not be met
-Added argument
also_single_testedforportion_*andcount_*functions to also include cases where not all antibiotics were tested but at least one of the tested antibiotics includes the target antimicribial interpretation, see?portion
-Using
portion_*functions now throws a warning when total available isolate is below argumentminimum
-Functions
as.mo,as.rsi,as.mic,as.atcandfreqwill not set package name as attribute anymore
--
-
Frequency tables -
+freq(): - Added argument
combine_IR(TRUE/FALSE) to functionsportion_dfandcount_df, to indicate that all values of I and R must be merged into one, so the output only consists of S vs. IR (susceptible vs. non-susceptible)
+ - Fix for
portion_*(..., as_percent = TRUE)when minimal number of isolates would not be met
+ - Added argument
also_single_testedforportion_*andcount_*functions to also include cases where not all antibiotics were tested but at least one of the tested antibiotics includes the target antimicribial interpretation, see?portion+
+ - Using
portion_*functions now throws a warning when total available isolate is below argumentminimum+
+ - Functions
as.mo,as.rsi,as.mic,as.atcandfreqwill not set package name as attribute anymore
+ - Frequency tables -
freq():-
Support for grouping variables, test with:
- -
Support for (un)selecting columns:
-
- Check for
hms::is.hms
-Now prints in markdown at default in non-interactive sessions
-No longer adds the factor level column and sorts factors on count again
-Support for class
difftime
-New argument
na, to choose which character to print for empty values
-New argument
headerto turn the header info off (default whenmarkdown = TRUE)
-New argument
titleto manually setbthe title of the frequency table
+- Check for
hms::is.hms+
+ - Now prints in markdown at default in non-interactive sessions +
- No longer adds the factor level column and sorts factors on count again +
- Support for class
difftime+
+ - New argument
na, to choose which character to print for empty values
+ - New argument
headerto turn the header info off (default whenmarkdown = TRUE)
+ - New argument
titleto manually setbthe title of the frequency table
- -
first_isolatenow tries to find columns to use as input when arguments are left blank
-Improvements for MDRO algorithm (function
mdro)
-Data set
septic_patientsis now adata.frame, not a tibble anymore
-Removed diacritics from all authors (columns
microorganisms$refandmicroorganisms.old$ref) to comply with CRAN policy to only allow ASCII characters
-Fix for
mo_propertynot working properly
-Fix for
eucast_ruleswhere some Streptococci would become ceftazidime R in EUCAST rule 4.5
-Support for named vectors of class
mo, useful fortop_freq()
-ggplot_rsiandscale_y_percenthavebreaksargument-
-
AI improvements for
+as.mo:first_isolatenow tries to find columns to use as input when arguments are left blank
+ - Improvements for MDRO algorithm (function
mdro)
+ - Data set
septic_patientsis now adata.frame, not a tibble anymore
+ - Removed diacritics from all authors (columns
microorganisms$refandmicroorganisms.old$ref) to comply with CRAN policy to only allow ASCII characters
+ - Fix for
mo_propertynot working properly
+ - Fix for
eucast_ruleswhere some Streptococci would become ceftazidime R in EUCAST rule 4.5
+ - Support for named vectors of class
mo, useful fortop_freq()+
+ -
+
ggplot_rsiandscale_y_percenthavebreaksargument
+ - AI improvements for
as.mo:-
"CRS"-> Stenotrophomonas maltophilia @@ -1779,11 +1748,12 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
- -
Fix for
joinfunctions
-Speed improvement for
is.rsi.eligible, now 15-20 times faster
-In
g.test, whensum(x)is below 1000 or any of the expected values is below 5, Fisher’s Exact Test will be suggested
-ab_namewill try to fall back onas.atcwhen no results are found
-Removed the addin to view data sets
+- Fix for
joinfunctions
+ - Speed improvement for
is.rsi.eligible, now 15-20 times faster
+ - In
g.test, whensum(x)is below 1000 or any of the expected values is below 5, Fisher’s Exact Test will be suggested
+ -
+
ab_namewill try to fall back onas.atcwhen no results are found
+ - Removed the addin to view data sets
Percentages will now will rounded more logically (e.g. in
freqfunction)The data set
microorganismsnow contains all microbial taxonomic data from ITIS (kingdoms Bacteria, Fungi and Protozoa), the Integrated Taxonomy Information System, available via https://itis.gov. The data set now contains more than 18,000 microorganisms with all known bacteria, fungi and protozoa according ITIS with genus, species, subspecies, family, order, class, phylum and subkingdom. The new data setmicroorganisms.oldcontains all previously known taxonomic names from those kingdoms.
--
-
New functions based on the existing function
+mo_property: - The data set
microorganismsnow contains all microbial taxonomic data from ITIS (kingdoms Bacteria, Fungi and Protozoa), the Integrated Taxonomy Information System, available via https://itis.gov. The data set now contains more than 18,000 microorganisms with all known bacteria, fungi and protozoa according ITIS with genus, species, subspecies, family, order, class, phylum and subkingdom. The new data setmicroorganisms.oldcontains all previously known taxonomic names from those kingdoms.
+ - New functions based on the existing function
mo_property:- Taxonomic names:
mo_phylum,mo_class,mo_order,mo_family,mo_genus,mo_species,mo_subspecies
@@ -1819,8 +1788,7 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
- Taxonomic names:
Changed
-
-
New
-
-
They also come with support for German, Dutch, French, Italian, Spanish and Portuguese:
--
++# [1] "Streptococcus grupo A"mo_gramstain("E. coli") # [1] "Gram negative" mo_gramstain("E. coli", language = "de") # German @@ -1828,43 +1796,39 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/ mo_gramstain("E. coli", language = "es") # Spanish # [1] "Gram negativo" mo_fullname("S. group A", language = "pt") # Portuguese -# [1] "Streptococcus grupo A"
Furthermore, former taxonomic names will give a note about the current taxonomic name:
--
++# [1] "Gram negative"mo_gramstain("Esc blattae") # Note: 'Escherichia blattae' (Burgess et al., 1973) was renamed 'Shimwellia blattae' (Priest and Barker, 2010) -# [1] "Gram negative"
- -
-
Functions
+count_R,count_IR,count_I,count_SIandcount_Sto selectively count resistant or susceptible isolates - Functions
count_R,count_IR,count_I,count_SIandcount_Sto selectively count resistant or susceptible isolates- Extra function
count_df(which works likeportion_df) to get all counts of S, I and R of a data set with antibiotic columns, with support for grouped variables
- - Extra function
Function
is.rsi.eligibleto check for columns that have valid antimicrobial results, but do not have thersiclass yet. Transform the columns of your raw data with:data %>% mutate_if(is.rsi.eligible, as.rsi)
+- Function
is.rsi.eligibleto check for columns that have valid antimicrobial results, but do not have thersiclass yet. Transform the columns of your raw data with:data %>% mutate_if(is.rsi.eligible, as.rsi)+ -
Functions
-as.moandis.moas replacements foras.bactidandis.bactid(since themicrooganismsdata set not only contains bacteria). These last two functions are deprecated and will be removed in a future release. Theas.mofunction determines microbial IDs using intelligent rules:-
++# [1] B_STRPTC_GRAas.mo("E. coli") # [1] B_ESCHR_COL as.mo("MRSA") # [1] B_STPHY_AUR as.mo("S group A") -# [1] B_STRPTC_GRA
And with great speed too - on a quite regular Linux server from 2007 it takes us less than 0.02 seconds to transform 25,000 items:
--
++# 0.01817717 0.01843957 0.03878077 100thousands_of_E_colis <- rep("E. coli", 25000) microbenchmark::microbenchmark(as.mo(thousands_of_E_colis), unit = "s") # Unit: seconds # min median max neval -# 0.01817717 0.01843957 0.03878077 100
- Added argument
reference_dfforas.mo, so users can supply their own microbial IDs, name or codes as a reference table
--
-
Renamed all previous references to
+bactidtomo, like: - Added argument
reference_dfforas.mo, so users can supply their own microbial IDs, name or codes as a reference table
+ - Renamed all previous references to
bactidtomo, like:- Column names inputs of
EUCAST_rules,first_isolateandkey_antibiotics
@@ -1873,11 +1837,12 @@ This works for all drug combinations, such as ampicillin/sulbactam, ceftazidime/
- All old syntaxes will still work with this version, but will throw warnings
- - Column names inputs of
Function
labels_rsi_countto print datalabels on a RSIggplot2model
+- Function
labels_rsi_countto print datalabels on a RSIggplot2model Functions
as.atcandis.atcto transform/look up antibiotic ATC codes as defined by the WHO. The existing functionguess_atcis now an alias ofas.atc.
-Function
ab_propertyand its aliases:ab_name,ab_tradenames,ab_certe,ab_umcgandab_trivial_nl
-Introduction to AMR as a vignette
-Removed clipboard functions as it violated the CRAN policy
+- Function
ab_propertyand its aliases:ab_name,ab_tradenames,ab_certe,ab_umcgandab_trivial_nl+
+ - Introduction to AMR as a vignette +
- Removed clipboard functions as it violated the CRAN policy
Renamed
septic_patients$sextoseptic_patients$gender
Changed
-
-
Added three antimicrobial agents to the
antibioticsdata set: Terbinafine (D01BA02), Rifaximin (A07AA11) and Isoconazole (D01AC05)
+- Added three antimicrobial agents to the
antibioticsdata set: Terbinafine (D01BA02), Rifaximin (A07AA11) and Isoconazole (D01AC05) -
Added 163 trade names to the
-antibioticsdata set, it now contains 298 different trade names in total, e.g.:+-
++# [1] "R01AX06" "J01CA04" "J01FA10" "J01CF05"ab_official("Bactroban") # [1] "Mupirocin" ab_name(c("Bactroban", "Amoxil", "Zithromax", "Floxapen")) # [1] "Mupirocin" "Amoxicillin" "Azithromycin" "Flucloxacillin" ab_atc(c("Bactroban", "Amoxil", "Zithromax", "Floxapen")) -# [1] "R01AX06" "J01CA04" "J01FA10" "J01CF05"
+ - For
first_isolate, rows will be ignored when there’s no species available
+ - Function
ratiois now deprecated and will be removed in a future release, as it is not really the scope of this package
+ - Fix for
as.micfor values ending in zeroes after a real number
+ - Small fix where B. fragilis would not be found in the
microorganisms.umcgdata set
+ - Added
prevalencecolumn to themicroorganismsdata set
+ - Added arguments
minimumandas_percenttoportion_df
- For
first_isolate, rows will be ignored when there’s no species available
-Function
ratiois now deprecated and will be removed in a future release, as it is not really the scope of this package
-Fix for
as.micfor values ending in zeroes after a real number
-Small fix where B. fragilis would not be found in the
microorganisms.umcgdata set
-Added
prevalencecolumn to themicroorganismsdata set
-Added arguments
minimumandas_percenttoportion_df-
Support for quasiquotation in the functions series
- +count_*andportions_*, andn_rsi. This allows to check for more than 2 vectors or columns.
+ - Edited
ggplot_rsiandgeom_rsiso they can cope withcount_df. The newfunargument has valueportion_dfat default, but can be set tocount_df.
+ - Fix for
ggplot_rsiwhen theggplot2package was not loaded
+ - Added datalabels function
labels_rsi_counttoggplot_rsi+
+ - Added possibility to set any argument to
geom_rsi(andggplot_rsi) so you can set your own preferences
+ - Fix for joins, where predefined suffices would not be honoured +
- Added argument
quoteto thefreqfunction
+ - Added generic function
difffor frequency tables
+ - Added longest en shortest character length in the frequency table (
freq) header of classcharacter
- Edited
ggplot_rsiandgeom_rsiso they can cope withcount_df. The newfunargument has valueportion_dfat default, but can be set tocount_df.
-Fix for
ggplot_rsiwhen theggplot2package was not loaded
-Added datalabels function
labels_rsi_counttoggplot_rsi
-Added possibility to set any argument to
geom_rsi(andggplot_rsi) so you can set your own preferences
-Fix for joins, where predefined suffices would not be honoured
-Added argument
quoteto thefreqfunction
-Added generic function
difffor frequency tables
-Added longest en shortest character length in the frequency table (
freq) header of classcharacter-
Support for types (classes) list and matrix for
-freq-
+ +freq(my_matrix)For lists, subsetting is possible:
-
- A vignette to explain its usage
- Support for
rsi(antimicrobial resistance) to use as input
- - Support for
tableto use as input:freq(table(x, y))+ - Support for
tableto use as input:freq(table(x, y)) - Support for existing functions
histandplotto use a frequency table as input:hist(freq(df$age)) - Support for
as.vector,as.data.frame,as_tibbleandformat
- - Support for quasiquotation:
freq(mydata, mycolumn)is the same asmydata %>% freq(mycolumn)+ - Support for quasiquotation:
freq(mydata, mycolumn)is the same asmydata %>% freq(mycolumn) - Function
top_freqfunction to return the top/below n items as vector - Header of frequency tables now also show Mean Absolute Deviaton (MAD) and Interquartile Range (IQR) diff --git a/docs/pkgdown.yml b/docs/pkgdown.yml index 6096a690a..8446a7354 100644 --- a/docs/pkgdown.yml +++ b/docs/pkgdown.yml @@ -1,4 +1,4 @@ -pandoc: 2.11.2 +pandoc: '2.6' pkgdown: 1.6.1 pkgdown_sha: ~ articles: @@ -12,7 +12,7 @@ articles: datasets: datasets.html resistance_predict: resistance_predict.html welcome_to_AMR: welcome_to_AMR.html -last_built: 2021-04-26T21:56Z +last_built: 2021-04-27T08:22Z urls: reference: https://msberends.github.io/AMR//reference article: https://msberends.github.io/AMR//articles diff --git a/docs/reference/AMR.html b/docs/reference/AMR.html index a3a499ee9..8ee6c8f57 100644 --- a/docs/reference/AMR.html +++ b/docs/reference/AMR.html @@ -82,7 +82,7 @@ @@ -90,14 +90,14 @@
