diff --git a/.Rbuildignore b/.Rbuildignore index d20eb122..1d616f7b 100755 --- a/.Rbuildignore +++ b/.Rbuildignore @@ -13,6 +13,7 @@ ^doc$ ^docs$ ^git.sh$ +^gitmerge.sh$ ^index\.md$ ^Meta$ ^packrat/ diff --git a/.gitignore b/.gitignore index 66e5baae..abc6fc9a 100755 --- a/.gitignore +++ b/.gitignore @@ -18,5 +18,6 @@ vignettes/*.R .Rprofile ^CRAN-RELEASE$ git.sh +gitmerge.sh packrat/lib*/ packrat/src/ diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml index e24afe1d..e7873c2a 100644 --- a/.gitlab-ci.yml +++ b/.gitlab-ci.yml @@ -41,8 +41,8 @@ before_script: cache: key: "$CI_COMMIT_REF_SLUG" paths: - - /usr/local/lib/R/ - - /usr/lib/R/ + - /usr/local/lib/R/* + - /usr/lib/R/* R 3: stage: build @@ -55,6 +55,7 @@ R 3: - R CMD build . --no-build-vignettes --no-manual - PKG_FILE_NAME=$(ls -1t *.tar.gz | head -n 1) - R CMD check "${PKG_FILE_NAME}" --no-build-vignettes --no-manual --as-cran + - Rscript -e 'print(.libPaths())' artifacts: paths: - '*.Rcheck/*' diff --git a/R/globals.R b/R/globals.R index 9c131ca4..aa0d6ae2 100755 --- a/R/globals.R +++ b/R/globals.R @@ -20,6 +20,11 @@ # ==================================================================== # globalVariables(c(".", + "atc", + "certe", + "official", + "trade_name", + "umcg", "..property", "antibiotic", "Antibiotic", diff --git a/R/itis.R b/R/itis.R index 3b72285d..6b3e78fa 100644 --- a/R/itis.R +++ b/R/itis.R @@ -35,7 +35,8 @@ #' @examples #' # Get a note when a species was renamed #' mo_shortname("Chlamydia psittaci") -#' # Note: 'Chlamydia psittaci' (Page, 1968) was renamed 'Chlamydophila psittaci' (Everett et al., 1999) +#' # Note: 'Chlamydia psittaci' (Page, 1968) was renamed +#' # 'Chlamydophila psittaci' (Everett et al., 1999) #' # [1] "C. psittaci" #' #' # Get any property from the entire taxonomic tree for all included species diff --git a/docs/articles/AMR.html b/docs/articles/AMR.html index f585914e..8b3a9a1a 100644 --- a/docs/articles/AMR.html +++ b/docs/articles/AMR.html @@ -179,7 +179,7 @@ -
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 RMarkdown. However, the methodology remains unchanged. This page was generated on 02 January 2019.
+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 RMarkdown. However, the methodology remains unchanged. This page was generated on 04 January 2019.
As with many uses in R, we need some additional packages for AMR analysis. The most important one is dplyr
, which tremendously improves the way we work with data - it allows for a very natural way of writing syntaxes in R. Another important dependency is ggplot2
. This package can be used to create beautiful plots in R.
Our AMR
package depends on these packages and even extends their use and functions.
library(dplyr) # the data science package
-library(AMR) # this package, to simplify and automate AMR analysis
-library(ggplot2) # for appealing plots
library(dplyr) # the data science package
+library(AMR) # this package, to simplify and automate AMR analysis
+library(ggplot2) # for appealing plots
To start with patients, we need a unique list of patients.
- +The LETTERS
object is available in R - it’s a vector with 26 characters: A
to Z
. The patients
object we just created is now a vector of length 260, with values (patient IDs) varying from A1
to Z10
. 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,
+ gender = c(rep("M", 135),
+ rep("F", 125)))
The first 135 patient IDs are now male, the other 125 are female.
Let’s pretend that our data consists of blood cultures isolates from 1 January 2010 until 1 January 2018.
- +This dates
object now contains all days in our date range.
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")
For completeness, we can also add the hospital where the patients was admitted and we need to define valid antibmicrobial results for our randomisation:
- +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 with the prob
parameter.
data <- data.frame(date = sample(dates, 5000, replace = TRUE),
- patient_id = sample(patients, 5000, replace = TRUE),
- hospital = sample(hospitals, 5000, replace = TRUE, prob = c(0.30, 0.35, 0.15, 0.20)),
- bacteria = sample(bacteria, 5000, replace = TRUE, prob = c(0.50, 0.25, 0.15, 0.10)),
- amox = sample(ab_interpretations, 5000, replace = TRUE, prob = c(0.60, 0.05, 0.35)),
- amcl = sample(ab_interpretations, 5000, replace = TRUE, prob = c(0.75, 0.10, 0.15)),
- cipr = sample(ab_interpretations, 5000, replace = TRUE, prob = c(0.80, 0.00, 0.20)),
- gent = sample(ab_interpretations, 5000, replace = TRUE, prob = c(0.92, 0.00, 0.08))
- )
Using the left_join()
function from the dplyr
package, we can ‘map’ the gender to the patient ID using the patients_table
object we created earlier:
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 with the prob
parameter.
data <- data.frame(date = sample(dates, 5000, replace = TRUE),
+ patient_id = sample(patients, 5000, replace = TRUE),
+ hospital = sample(hospitals, 5000, replace = TRUE, prob = c(0.30, 0.35, 0.15, 0.20)),
+ bacteria = sample(bacteria, 5000, replace = TRUE, prob = c(0.50, 0.25, 0.15, 0.10)),
+ amox = sample(ab_interpretations, 5000, replace = TRUE, prob = c(0.60, 0.05, 0.35)),
+ amcl = sample(ab_interpretations, 5000, replace = TRUE, prob = c(0.75, 0.10, 0.15)),
+ cipr = sample(ab_interpretations, 5000, replace = TRUE, prob = c(0.80, 0.00, 0.20)),
+ gent = sample(ab_interpretations, 5000, replace = TRUE, prob = c(0.92, 0.00, 0.08))
+ )
Using the left_join()
function from the dplyr
package, we can ‘map’ the gender to the patient ID using the patients_table
object we created earlier:
data <- data %>% left_join(patients_table)
The resulting data set contains 5,000 blood culture isolates. With the head()
function we can preview the first 6 values of this data set:
head(data)
date | @@ -295,10 +295,10 @@|||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2017-03-28 | -D2 | -Hospital B | -Staphylococcus aureus | +2014-02-20 | +D5 | +Hospital A | +Escherichia coli | R | S | S | @@ -306,60 +306,60 @@M | ||
2010-06-26 | -O3 | +2010-06-17 | +N4 | Hospital A | Escherichia coli | S | S | +R | S | -S | -F | +M | |
2015-12-14 | -M8 | +2017-08-02 | +A6 | Hospital B | Staphylococcus aureus | -S | -S | -S | +R | +I | +R | S | M |
2013-02-26 | -C7 | -Hospital B | -Klebsiella pneumoniae | -S | +2012-11-25 | +K7 | +Hospital A | +Escherichia coli | +I | S | S | S | M |
2012-11-01 | -Y5 | -Hospital D | -Escherichia coli | -S | -S | -R | -S | -F | -|||||
2015-04-04 | -K10 | -Hospital A | +2012-06-24 | +G9 | +Hospital B | Escherichia coli | R | S | -R | +S | R | M | |
2011-05-20 | +T7 | +Hospital C | +Escherichia coli | +S | +S | +S | +S | +F | +
Now, let’s start the cleaning and the analysis!
@@ -369,7 +369,7 @@Use the frequency table function freq()
to look specifically for unique values in any variable. For example, for the gender
variable:
data %>% freq(gender) # this would be the same: freq(data$gender)
# Frequency table of `gender`
# Class: factor (numeric)
# Levels: F, M
@@ -378,67 +378,67 @@
#
# Item Count Percent Cum. Count Cum. Percent
# --- ----- ------ -------- ----------- -------------
-# 1 M 2,549 51.0% 2,549 51.0%
-# 2 F 2,451 49.0% 5,000 100.0%
+# 1 M 2,636 52.7% 2,636 52.7%
+# 2 F 2,364 47.3% 5,000 100.0%
So, we can draw at least two conclusions immediately. From a data scientist perspective, the data looks clean: only values M
and F
. From a researcher 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 bacteria
column 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. The mutate()
function of the dplyr
package 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. The mutate_at()
will run the as.rsi()
function on defined variables:
The data is already quite clean, but we still need to transform some variables. The bacteria
column 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. The mutate()
function of the dplyr
package 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. The mutate_at()
will run the as.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 forcing
Because the amoxicillin (column amox
) and amoxicillin/clavulanic acid (column amcl
) in our data were generated randomly, some rows will undoubtedly contain amox = S and amcl = R, which is technically impossible. The eucast_rules()
fixes this:
data <- eucast_rules(data, col_mo = "bacteria")
-#
-# Rules by the European Committee on Antimicrobial Susceptibility Testing (EUCAST)
-#
-# EUCAST Clinical Breakpoints (v8.1, 2018)
-# Enterobacteriales (Order) (no changes)
-# Staphylococcus (no changes)
-# Enterococcus (no changes)
-# Streptococcus groups A, B, C, G (no changes)
-# Streptococcus pneumoniae (364 changes)
-# Viridans group streptococci (no changes)
-# Haemophilus influenzae (no changes)
-# Moraxella catarrhalis (no changes)
-# Anaerobic Gram positives (no changes)
-# Anaerobic Gram negatives (no changes)
-# Pasteurella multocida (no changes)
-# Campylobacter jejuni and C. coli (no changes)
-# Aerococcus sanguinicola and A. urinae (no changes)
-# Kingella kingae (no changes)
-#
-# EUCAST Expert Rules, Intrinsic Resistance and Exceptional Phenotypes (v3.1, 2016)
-# Table 1: Intrinsic resistance in Enterobacteriaceae (303 changes)
-# Table 2: Intrinsic resistance in non-fermentative Gram-negative bacteria (no changes)
-# Table 3: Intrinsic resistance in other Gram-negative bacteria (no changes)
-# Table 4: Intrinsic resistance in Gram-positive bacteria (641 changes)
-# Table 8: Interpretive rules for B-lactam agents and Gram-positive cocci (no changes)
-# Table 9: Interpretive rules for B-lactam agents and Gram-negative rods (no changes)
-# Table 10: Interpretive rules for B-lactam agents and other Gram-negative bacteria (no changes)
-# Table 11: Interpretive rules for macrolides, lincosamides, and streptogramins (no changes)
-# Table 12: Interpretive rules for aminoglycosides (no changes)
-# Table 13: Interpretive rules for quinolones (no changes)
-#
-# Other rules
-# Non-EUCAST: ampicillin = R where amoxicillin/clav acid = R (403 changes)
-# Non-EUCAST: piperacillin = R where piperacillin/tazobactam = R (no changes)
-# Non-EUCAST: trimethoprim = R where trimethoprim/sulfa = R (no changes)
-# Non-EUCAST: amoxicillin/clav acid = S where ampicillin = S (231 changes)
-# Non-EUCAST: piperacillin/tazobactam = S where piperacillin = S (no changes)
-# Non-EUCAST: trimethoprim/sulfa = S where trimethoprim = S (no changes)
-#
-# => EUCAST rules affected 4,588 out of 5,000 rows -> changed 1,942 test results.
data <- eucast_rules(data, col_mo = "bacteria")
+#
+# Rules by the European Committee on Antimicrobial Susceptibility Testing (EUCAST)
+#
+# EUCAST Clinical Breakpoints (v8.1, 2018)
+# Enterobacteriales (Order) (no changes)
+# Staphylococcus (no changes)
+# Enterococcus (no changes)
+# Streptococcus groups A, B, C, G (no changes)
+# Streptococcus pneumoniae (no changes)
+# Viridans group streptococci (no changes)
+# Haemophilus influenzae (no changes)
+# Moraxella catarrhalis (no changes)
+# Anaerobic Gram positives (no changes)
+# Anaerobic Gram negatives (no changes)
+# Pasteurella multocida (no changes)
+# Campylobacter jejuni and C. coli (no changes)
+# Aerococcus sanguinicola and A. urinae (no changes)
+# Kingella kingae (no changes)
+#
+# EUCAST Expert Rules, Intrinsic Resistance and Exceptional Phenotypes (v3.1, 2016)
+# Table 1: Intrinsic resistance in Enterobacteriaceae (332 changes)
+# Table 2: Intrinsic resistance in non-fermentative Gram-negative bacteria (no changes)
+# Table 3: Intrinsic resistance in other Gram-negative bacteria (no changes)
+# Table 4: Intrinsic resistance in Gram-positive bacteria (658 changes)
+# Table 8: Interpretive rules for B-lactam agents and Gram-positive cocci (no changes)
+# Table 9: Interpretive rules for B-lactam agents and Gram-negative rods (no changes)
+# Table 10: Interpretive rules for B-lactam agents and other Gram-negative bacteria (no changes)
+# Table 11: Interpretive rules for macrolides, lincosamides, and streptogramins (no changes)
+# Table 12: Interpretive rules for aminoglycosides (no changes)
+# Table 13: Interpretive rules for quinolones (no changes)
+#
+# Other rules
+# Non-EUCAST: ampicillin = R where amoxicillin/clav acid = R (no changes)
+# Non-EUCAST: piperacillin = R where piperacillin/tazobactam = R (no changes)
+# Non-EUCAST: trimethoprim = R where trimethoprim/sulfa = R (no changes)
+# Non-EUCAST: amoxicillin/clav acid = S where ampicillin = S (no changes)
+# Non-EUCAST: piperacillin/tazobactam = S where piperacillin = S (no changes)
+# Non-EUCAST: trimethoprim/sulfa = S where trimethoprim = S (no changes)
+#
+# => EUCAST rules affected 1,828 out of 5,000 rows -> changed 990 test results.
Now that we have the microbial ID, we can add some taxonomic properties:
-data <- data %>%
- mutate(gramstain = mo_gramstain(bacteria),
- genus = mo_genus(bacteria),
- species = mo_species(bacteria))
data <- data %>%
+ mutate(gramstain = mo_gramstain(bacteria),
+ genus = mo_genus(bacteria),
+ species = mo_species(bacteria))
(…) 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 6.4
This AMR
package includes this methodology with the first_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 %>%
- 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`.
-# => Found 2,925 first isolates (58.5% of total)
So only 58.5% is suitable for resistance analysis! We can now filter on is with the filter()
function, also from the dplyr
package:
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`.
+# => Found 2,950 first isolates (59.0% of total)
So only 59% is suitable for resistance analysis! We can now filter on is with the filter()
function, also from the dplyr
package:
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()
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 show 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 `bacteria` as input for `col_mo`.
-# Warning: These columns do not exist and will be ignored: cfur, pita, trsu, vanc, teic, tetr, eryt, oxac, rifa, tobr, coli, cfot, cfta, mero.
-# THIS MAY STRONGLY INFLUENCE THE OUTCOME.
-# 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`.
-# NOTE: Using column `keyab` as input for `col_keyantibiotics`. Use col_keyantibiotics = FALSE to prevent this.
-# [Criterion] Inclusion based on key antibiotics, ignoring I.
-# => Found 4,390 first weighted isolates (87.8% of total)
data <- data %>%
+ mutate(keyab = key_antibiotics(.)) %>%
+ mutate(first_weighted = first_isolate(.))
+# NOTE: Using column `bacteria` as input for `col_mo`.
+# amox amcl cipr gent
+# "amox" "amcl" "cipr" "gent"
+# [1] "amox" "amcl" "cipr"
+# amox amcl cipr gent
+# "amox" "amcl" "cipr" "gent"
+# 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`.
+# NOTE: Using column `keyab` as input for `col_keyantibiotics`. Use col_keyantibiotics = FALSE to prevent this.
+# [Criterion] Inclusion based on key antibiotics, ignoring I.
+# => Found 4,430 first weighted isolates (88.6% of total)
isolate | @@ -621,11 +624,11 @@||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
1 | -2010-07-09 | -W3 | +2010-05-26 | +D5 | B_ESCHR_COL | -S | -S | +R | +R | R | S | TRUE | @@ -633,11 +636,11 @@||
2 | -2010-07-22 | -W3 | +2010-06-05 | +D5 | B_ESCHR_COL | -R | -R | +S | +S | S | S | FALSE | @@ -645,115 +648,114 @@||
3 | -2011-02-02 | -W3 | +2010-09-13 | +D5 | B_ESCHR_COL | S | S | -R | -R | +S | +S | +FALSE | FALSE | -TRUE |
4 | -2012-01-18 | -W3 | +2010-12-19 | +D5 | B_ESCHR_COL | +S | R | S | S | -S | -TRUE | +FALSE | TRUE | |
5 | -2012-07-21 | -W3 | +2012-03-01 | +D5 | B_ESCHR_COL | S | +R | S | S | -S | -FALSE | +TRUE | TRUE | |
6 | -2013-04-19 | -W3 | +2012-04-14 | +D5 | B_ESCHR_COL | -R | S | S | S | -TRUE | +S | +FALSE | TRUE | |
7 | -2013-09-01 | -W3 | +2013-01-04 | +D5 | B_ESCHR_COL | S | S | S | S | FALSE | +FALSE | +|||
8 | +2013-01-22 | +D5 | +B_ESCHR_COL | +I | +I | +R | +S | +FALSE | TRUE | |||||
8 | -2013-12-07 | -W3 | -B_ESCHR_COL | -S | -S | -S | -S | -FALSE | -FALSE | -|||||
9 | -2013-12-15 | -W3 | +2013-03-20 | +D5 | B_ESCHR_COL | -R | S | S | S | -FALSE | +S | +TRUE | TRUE | |
10 | -2014-02-03 | -W3 | +2013-09-13 | +D5 | B_ESCHR_COL | S | S | -R | S | +R | FALSE | TRUE |
Instead of 3, now 9 isolates are flagged. In total, 87.8% of all isolates are marked ‘first weighted’ - 146.3% 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 8 isolates are flagged. In total, 88.6% of all isolates are marked ‘first weighted’ - 147.6% 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:
So we end up with 4,390 isolates for analysis.
+data_1st <- data %>%
+ filter_first_weighted_isolate()
So we end up with 4,430 isolates for analysis.
We can remove unneeded columns:
- +Now our data looks like:
- +head(data_1st)
date | patient_id | hospital | @@ -770,78 +772,73 @@|||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
1 | -2017-03-28 | -D2 | -Hospital B | -B_STPHY_AUR | +2014-02-20 | +D5 | +Hospital A | +B_ESCHR_COL | R | S | S | S | M | +Gram negative | +Escherichia | +coli | +TRUE | +||||||
2010-06-17 | +N4 | +Hospital A | +B_ESCHR_COL | +S | +S | +R | +S | +M | +Gram negative | +Escherichia | +coli | +TRUE | +|||||||||||
2017-08-02 | +A6 | +Hospital B | +B_STPHY_AUR | +R | +I | +R | +S | +M | Gram positive | Staphylococcus | aureus | TRUE | |||||||||||
2 | -2010-06-26 | -O3 | +2012-11-25 | +K7 | Hospital A | B_ESCHR_COL | -S | -S | -S | -S | -F | -Gram negative | -Escherichia | -coli | -TRUE | -||||||||
4 | -2013-02-26 | -C7 | -Hospital B | -B_KLBSL_PNE | -R | +I | S | S | S | M | Gram negative | -Klebsiella | -pneumoniae | -TRUE | -|||||||||
5 | -2012-11-01 | -Y5 | -Hospital D | -B_ESCHR_COL | -S | -S | -R | -S | -F | -Gram negative | Escherichia | coli | TRUE | ||||||||||
6 | -2015-04-04 | -K10 | -Hospital A | +2012-06-24 | +G9 | +Hospital B | B_ESCHR_COL | R | S | -R | +S | R | M | Gram negative | @@ -850,19 +847,18 @@TRUE | ||||||||
7 | -2012-02-22 | -Z6 | -Hospital B | -B_STPHY_AUR | -R | -R | -R | +2011-05-20 | +T7 | +Hospital C | +B_ESCHR_COL | +S | +S | +S | S | F | -Gram positive | -Staphylococcus | -aureus | +Gram negative | +Escherichia | +coli | TRUE |
1 | Escherichia coli | -2,196 | -50.0% | -2,196 | -50.0% | +2,206 | +49.8% | +2,206 | +49.8% | ||||||||||||||
2 | Staphylococcus aureus | -1,148 | -26.2% | -3,344 | -76.2% | +1,093 | +24.7% | +3,299 | +74.5% | ||||||||||||||
3 | Streptococcus pneumoniae | -622 | -14.2% | +667 | +15.1% | 3,966 | -90.3% | +89.5% | |||||||||||||||
4 | Klebsiella pneumoniae | -424 | -9.7% | -4,390 | +464 | +10.5% | +4,430 | 100.0% |
hospital | @@ -946,27 +942,27 @@ Longest: 24||
---|---|---|
Hospital A | -0.5574018 | +0.4605873 |
Hospital B | -0.5468750 | +0.4624277 |
Hospital C | -0.5281583 | +0.4853801 |
Hospital D | -0.5406644 | +0.4659218 |
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 like n_distinct()
from the dplyr
package. It counts all isolates available for every group (i.e. values S, I or R):
data_1st %>%
- group_by(hospital) %>%
- summarise(amoxicillin = portion_IR(amox),
- available = n_rsi(amox))
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 like n_distinct()
from the dplyr
package. It counts all isolates available for every group (i.e. values S, I or R):
data_1st %>%
+ group_by(hospital) %>%
+ summarise(amoxicillin = portion_IR(amox),
+ available = n_rsi(amox))
hospital | @@ -976,32 +972,32 @@ Longest: 24||||
---|---|---|---|---|
Hospital A | -0.5574018 | -1324 | +0.4605873 | +1294 |
Hospital B | -0.5468750 | -1536 | +0.4624277 | +1557 |
Hospital C | -0.5281583 | -657 | +0.4853801 | +684 |
Hospital D | -0.5406644 | -873 | +0.4659218 | +895 |
These functions can also be used to get the portion of multiple antibiotics, to calculate co-resistance very easily:
-data_1st %>%
- group_by(genus) %>%
- summarise(amoxicillin = portion_S(amcl),
- gentamicin = portion_S(gent),
- "amox + gent" = portion_S(amcl, gent))
data_1st %>%
+ group_by(genus) %>%
+ summarise(amoxicillin = portion_S(amcl),
+ gentamicin = portion_S(gent),
+ "amox + gent" = portion_S(amcl, gent))
genus | @@ -1012,94 +1008,94 @@ Longest: 24||||||
---|---|---|---|---|---|---|
Escherichia | -0.7923497 | -0.9130237 | -0.9817851 | +0.7307344 | +0.9120580 | +0.9782412 |
Klebsiella | -0.7641509 | -0.9127358 | -0.9811321 | +0.7521552 | +0.9181034 | +0.9806034 |
Staphylococcus | -0.8040070 | -0.9224739 | -0.9834495 | +0.7419945 | +0.9268070 | +0.9798719 |
Streptococcus | -0.5643087 | +0.7256372 | 0.0000000 | -0.5643087 | +0.7256372 |
To make a transition to the next part, let’s see how this difference could be plotted:
-data_1st %>%
- group_by(genus) %>%
- summarise("1. Amoxicillin" = portion_S(amcl),
- "2. Gentamicin" = portion_S(gent),
- "3. Amox + gent" = portion_S(amcl, gent)) %>%
- tidyr::gather("Antibiotic", "S", -genus) %>%
- ggplot(aes(x = genus,
- y = S,
- fill = Antibiotic)) +
- geom_col(position = "dodge2")
data_1st %>%
+ group_by(genus) %>%
+ summarise("1. Amoxicillin" = portion_S(amcl),
+ "2. Gentamicin" = portion_S(gent),
+ "3. Amox + gent" = portion_S(amcl, gent)) %>%
+ tidyr::gather("Antibiotic", "S", -genus) %>%
+ ggplot(aes(x = genus,
+ y = S,
+ fill = Antibiotic)) +
+ geom_col(position = "dodge2")
To show results in plots, most R users would nowadays use the ggplot2
package. 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,
- mapping = aes(x = year,
- y = value)) +
- geom_col() +
- labs(title = "A title",
- subtitle = "A subtitle",
- x = "My X axis",
- y = "My Y axis")
-
-ggplot(a_data_set,
- aes(year, value) +
- geom_bar()
ggplot(data = a_data_set,
+ mapping = aes(x = year,
+ y = value)) +
+ geom_col() +
+ labs(title = "A title",
+ subtitle = "A subtitle",
+ x = "My X axis",
+ y = "My Y axis")
+
+ggplot(a_data_set,
+ aes(year, value) +
+ geom_bar()
The AMR
package contains functions to extend this ggplot2
package, for example geom_rsi()
. It automatically transforms data with count_df()
or portion_df()
and show results in stacked bars. Its simplest and shortest example:
Omit the translate_ab = FALSE
to have the antibiotic codes (amox, amcl, cipr, gent) translated to official WHO names (amoxicillin, amoxicillin and betalactamase inhibitor, ciprofloxacin, gentamicin).
If we group on e.g. the genus
column and add some additional functions from our package, we can create this:
# 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`,
- # of which we have 4 (earlier created with `as.rsi`)
- geom_rsi(x = "genus") +
- # split plots on antibiotic
- facet_rsi(facet = "Antibiotic") +
- # make R red, I yellow and S green
- scale_rsi_colours() +
- # show percentages on y axis
- scale_y_percent(breaks = 0:4 * 25) +
- # turn 90 degrees, make it bars instead of columns
- coord_flip() +
- # add labels
- labs(title = "Resistance per genus and antibiotic",
- 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"))
# 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`,
+ # of which we have 4 (earlier created with `as.rsi`)
+ geom_rsi(x = "genus") +
+ # split plots on antibiotic
+ facet_rsi(facet = "Antibiotic") +
+ # make R red, I yellow and S green
+ scale_rsi_colours() +
+ # show percentages on y axis
+ scale_y_percent(breaks = 0:4 * 25) +
+ # turn 90 degrees, make it bars instead of columns
+ coord_flip() +
+ # add labels
+ labs(title = "Resistance per genus and antibiotic",
+ 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 %>%
- group_by(genus) %>%
- ggplot_rsi(x = "genus",
- facet = "Antibiotic",
- breaks = 0:4 * 25,
- datalabels = FALSE) +
- coord_flip()
data_1st %>%
+ group_by(genus) %>%
+ ggplot_rsi(x = "genus",
+ facet = "Antibiotic",
+ breaks = 0:4 * 25,
+ datalabels = FALSE) +
+ coord_flip()
We can transform the data and apply the test in only a couple of lines:
-septic_patients %>%
- filter(hospital_id %in% c("A", "D")) %>% # filter on only hospitals A and D
- select(hospital_id, fosf) %>% # select the hospitals and fosfomycin
- group_by(hospital_id) %>% # group on the hospitals
- count_df(combine_IR = TRUE) %>% # count all isolates per group (hospital_id)
- tidyr::spread(hospital_id, Value) %>% # transform output so A and D are columns
- select(A, D) %>% # and select these only
- as.matrix() %>% # transform to good old matrix for fisher.test()
- fisher.test() # do Fisher's Exact Test
-#
-# Fisher's Exact Test for Count Data
-#
-# data: .
-# p-value = 0.03104
-# alternative hypothesis: true odds ratio is not equal to 1
-# 95 percent confidence interval:
-# 1.054283 4.735995
-# sample estimates:
-# odds ratio
-# 2.228006
septic_patients %>%
+ filter(hospital_id %in% c("A", "D")) %>% # filter on only hospitals A and D
+ select(hospital_id, fosf) %>% # select the hospitals and fosfomycin
+ group_by(hospital_id) %>% # group on the hospitals
+ count_df(combine_IR = TRUE) %>% # count all isolates per group (hospital_id)
+ tidyr::spread(hospital_id, Value) %>% # transform output so A and D are columns
+ select(A, D) %>% # and select these only
+ as.matrix() %>% # transform to good old matrix for fisher.test()
+ fisher.test() # do Fisher's Exact Test
+#
+# Fisher's Exact Test for Count Data
+#
+# data: .
+# p-value = 0.03104
+# alternative hypothesis: true odds ratio is not equal to 1
+# 95 percent confidence interval:
+# 1.054283 4.735995
+# sample estimates:
+# odds ratio
+# 2.228006
As can be seen, the p value is 0.03, which means that the fosfomycin resistances found in hospital A and D are really different.
To only show and quickly review the content of one variable, you can just select this variable in various ways. Let’s say we want to get the frequencies of the gender
variable of the septic_patients
dataset:
septic_patients %>% freq(gender)
Frequency table of gender