Antimicrobial resistance (AMR) is a global health crisis, and understanding resistance patterns is crucial for managing effective treatments. The AMR R package provides robust tools for -analysing AMR data, including convenient antibiotic selector functions -like aminoglycosides() and betalactams(). In -this post, we will explore how to use the tidymodels -framework to predict resistance patterns in the +analysing AMR data, including convenient antimicrobial selector +functions like aminoglycosides() and +betalactams(). In this post, we will explore how to use the +tidymodels framework to predict resistance patterns in the example_isolates dataset.
AMR
aminoglycosides()
betalactams()
tidymodels
example_isolates
By leveraging the power of tidymodels and the AMR package, we’ll build a reproducible machine learning @@ -147,6 +150,29 @@ package.
step_corr()
Notice how the recipe contains just the antibiotic selector functions -- no need to define the columns specifically. In the preparation -(retrieved with prep()) we can see that the columns or -variables ‘AMX’ and ‘CTX’ were removed as they correlate too much with -existing, other variables.
prep()
Notice how the recipe contains just the antimicrobial selector +functions - no need to define the columns specifically. In the +preparation (retrieved with prep()) we can see that the +columns or variables ‘AMX’ and ‘CTX’ were removed as they correlate too +much with existing, other variables.
# Specify a logistic regression model logistic_model <- logistic_reg() %>% - set_engine("glm") # Use the Generalized Linear Model engine + set_engine("glm") # Use the Generalised Linear Model engine logistic_model #> Logistic Regression Model Specification (classification) #> @@ -273,7 +299,7 @@ engine. 3. Building the Workflow We bundle the recipe and model together into a workflow, -which organizes the entire modeling process. +which organises the entire modeling process. # Combine the recipe and model into a workflow resistance_workflow <- workflow() %>% @@ -320,9 +346,9 @@ testing sets. fit() trains the workflow on the training set. -Notice how in fit(), the antibiotic selector functions -are internally called again. For training, these functions are called -since they are stored in the recipe. +Notice how in fit(), the antimicrobial selector +functions are internally called again. For training, these functions are +called since they are stored in the recipe. Next, we evaluate the model on the testing data. # Make predictions on the testing set @@ -363,7 +389,22 @@ since they are stored in the recipe. #> .metric .estimator .estimate #> <chr> <chr> <dbl> #> 1 accuracy binary 0.995 -#> 2 kap binary 0.989 +#> 2 kap binary 0.989 + + +# To assess some other model properties, you can make our own `metrics()` function +our_metrics <- metric_set(accuracy, kap, ppv, npv) # add Positive Predictive Value and Negative Predictive Value +metrics2 <- predictions %>% + our_metrics(truth = mo, estimate = .pred_class) # run again on our `our_metrics()` function + +metrics2 +#> # A tibble: 4 × 3 +#> .metric .estimator .estimate +#> <chr> <chr> <dbl> +#> 1 accuracy binary 0.995 +#> 2 kap binary 0.989 +#> 3 ppv binary 0.987 +#> 4 npv binary 1 Explanation: @@ -373,9 +414,9 @@ set. metrics() computes evaluation metrics like accuracy and kappa. -It appears we can predict the Gram based on AMR results with a 99.5% -accuracy based on AMR results of aminoglycosides and beta-lactam -antibiotics. The ROC curve looks like this: +It appears we can predict the Gram stain with a 99.5% accuracy based +on AMR results of only aminoglycosides and beta-lactam antibiotics. The +ROC curve looks like this: predictions %>% roc_curve(mo, `.pred_Gram-negative`) %>% @@ -392,9 +433,241 @@ pipeline with the tidymodels framework and the aminoglycosides() and betalactams() with tidymodels, we efficiently prepared data, trained a model, and evaluated its performance. -This workflow is extensible to other antibiotic classes and +This workflow is extensible to other antimicrobial classes and resistance patterns, empowering users to analyse AMR data systematically and reproducibly. + + +
We bundle the recipe and model together into a workflow, -which organizes the entire modeling process.
workflow
# Combine the recipe and model into a workflow resistance_workflow <- workflow() %>% @@ -320,9 +346,9 @@ testing sets. fit() trains the workflow on the training set. -Notice how in fit(), the antibiotic selector functions -are internally called again. For training, these functions are called -since they are stored in the recipe. +Notice how in fit(), the antimicrobial selector +functions are internally called again. For training, these functions are +called since they are stored in the recipe. Next, we evaluate the model on the testing data. # Make predictions on the testing set @@ -363,7 +389,22 @@ since they are stored in the recipe. #> .metric .estimator .estimate #> <chr> <chr> <dbl> #> 1 accuracy binary 0.995 -#> 2 kap binary 0.989 +#> 2 kap binary 0.989 + + +# To assess some other model properties, you can make our own `metrics()` function +our_metrics <- metric_set(accuracy, kap, ppv, npv) # add Positive Predictive Value and Negative Predictive Value +metrics2 <- predictions %>% + our_metrics(truth = mo, estimate = .pred_class) # run again on our `our_metrics()` function + +metrics2 +#> # A tibble: 4 × 3 +#> .metric .estimator .estimate +#> <chr> <chr> <dbl> +#> 1 accuracy binary 0.995 +#> 2 kap binary 0.989 +#> 3 ppv binary 0.987 +#> 4 npv binary 1
fit()
Notice how in fit(), the antibiotic selector functions -are internally called again. For training, these functions are called -since they are stored in the recipe.
Notice how in fit(), the antimicrobial selector +functions are internally called again. For training, these functions are +called since they are stored in the recipe.
Next, we evaluate the model on the testing data.
# Make predictions on the testing set @@ -363,7 +389,22 @@ since they are stored in the recipe. #> .metric .estimator .estimate #> <chr> <chr> <dbl> #> 1 accuracy binary 0.995 -#> 2 kap binary 0.989
Explanation:
metrics()
It appears we can predict the Gram based on AMR results with a 99.5% -accuracy based on AMR results of aminoglycosides and beta-lactam -antibiotics. The ROC curve looks like this:
It appears we can predict the Gram stain with a 99.5% accuracy based +on AMR results of only aminoglycosides and beta-lactam antibiotics. The +ROC curve looks like this:
predictions %>% roc_curve(mo, `.pred_Gram-negative`) %>% @@ -392,9 +433,241 @@ pipeline with the tidymodels framework and the aminoglycosides() and betalactams() with tidymodels, we efficiently prepared data, trained a model, and evaluated its performance. -This workflow is extensible to other antibiotic classes and +This workflow is extensible to other antimicrobial classes and resistance patterns, empowering users to analyse AMR data systematically and reproducibly. + +
This workflow is extensible to other antibiotic classes and +
This workflow is extensible to other antimicrobial classes and resistance patterns, empowering users to analyse AMR data systematically and reproducibly.
In this second example, we aim to predict antimicrobial resistance +(AMR) trends over time using tidymodels. We will model +resistance to three antibiotics (amoxicillin AMX, +amoxicillin-clavulanic acid AMC, and ciprofloxacin +CIP), based on historical data grouped by year and hospital +ward.
AMX
AMC
CIP
Our goal is to:
We start by transforming the example_isolates dataset +into a structured time-series format.
+# Load required libraries +library(AMR) +library(tidymodels) + +# Transform dataset +data_time <- example_isolates %>% + top_n_microorganisms(n = 10) %>% # Filter on the top #10 species + mutate(year = as.integer(format(date, "%Y")), # Extract year from date + gramstain = mo_gramstain(mo)) %>% # Get taxonomic names + group_by(year, gramstain) %>% + summarise(across(c(AMX, AMC, CIP), + function(x) resistance(x, minimum = 0), + .names = "res_{.col}"), + .groups = "drop") %>% + filter(!is.na(res_AMX) & !is.na(res_AMC) & !is.na(res_CIP)) # Drop missing values +#> ℹ Using column 'mo' as input for col_mo. + +data_time +#> # A tibble: 32 × 5 +#> year gramstain res_AMX res_AMC res_CIP +#> <int> <chr> <dbl> <dbl> <dbl> +#> 1 2002 Gram-negative 1 0.105 0.0606 +#> 2 2002 Gram-positive 0.838 0.182 0.162 +#> 3 2003 Gram-negative 1 0.0714 0 +#> 4 2003 Gram-positive 0.714 0.244 0.154 +#> 5 2004 Gram-negative 0.464 0.0938 0 +#> 6 2004 Gram-positive 0.849 0.299 0.244 +#> 7 2005 Gram-negative 0.412 0.132 0.0588 +#> 8 2005 Gram-positive 0.882 0.382 0.154 +#> 9 2006 Gram-negative 0.379 0 0.1 +#> 10 2006 Gram-positive 0.778 0.333 0.353 +#> # ℹ 22 more rows
# Load required libraries +library(AMR) +library(tidymodels) + +# Transform dataset +data_time <- example_isolates %>% + top_n_microorganisms(n = 10) %>% # Filter on the top #10 species + mutate(year = as.integer(format(date, "%Y")), # Extract year from date + gramstain = mo_gramstain(mo)) %>% # Get taxonomic names + group_by(year, gramstain) %>% + summarise(across(c(AMX, AMC, CIP), + function(x) resistance(x, minimum = 0), + .names = "res_{.col}"), + .groups = "drop") %>% + filter(!is.na(res_AMX) & !is.na(res_AMC) & !is.na(res_CIP)) # Drop missing values +#> ℹ Using column 'mo' as input for col_mo. + +data_time +#> # A tibble: 32 × 5 +#> year gramstain res_AMX res_AMC res_CIP +#> <int> <chr> <dbl> <dbl> <dbl> +#> 1 2002 Gram-negative 1 0.105 0.0606 +#> 2 2002 Gram-positive 0.838 0.182 0.162 +#> 3 2003 Gram-negative 1 0.0714 0 +#> 4 2003 Gram-positive 0.714 0.244 0.154 +#> 5 2004 Gram-negative 0.464 0.0938 0 +#> 6 2004 Gram-positive 0.849 0.299 0.244 +#> 7 2005 Gram-negative 0.412 0.132 0.0588 +#> 8 2005 Gram-positive 0.882 0.382 0.154 +#> 9 2006 Gram-negative 0.379 0 0.1 +#> 10 2006 Gram-positive 0.778 0.333 0.353 +#> # ℹ 22 more rows
Explanation: - mo_name(mo): Converts +microbial codes into proper species names. - resistance(): +Converts AMR results into numeric values (proportion of resistant +isolates). - group_by(year, ward, species): Aggregates +resistance rates by year and ward.
mo_name(mo)
resistance()
group_by(year, ward, species)
We now define the modeling workflow, which consists of a +preprocessing step, a model specification, and the fitting process.
+# Define the recipe +resistance_recipe_time <- recipe(res_AMX ~ year + gramstain, data = data_time) %>% + step_dummy(gramstain, one_hot = TRUE) %>% # Convert categorical to numerical + step_normalize(year) %>% # Normalise year for better model performance + step_nzv(all_predictors()) # Remove near-zero variance predictors + +resistance_recipe_time +#> +#> ── Recipe ────────────────────────────────────────────────────────────────────── +#> +#> ── Inputs +#> Number of variables by role +#> outcome: 1 +#> predictor: 2 +#> +#> ── Operations +#> • Dummy variables from: gramstain +#> • Centering and scaling for: year +#> • Sparse, unbalanced variable filter on: all_predictors()
# Define the recipe +resistance_recipe_time <- recipe(res_AMX ~ year + gramstain, data = data_time) %>% + step_dummy(gramstain, one_hot = TRUE) %>% # Convert categorical to numerical + step_normalize(year) %>% # Normalise year for better model performance + step_nzv(all_predictors()) # Remove near-zero variance predictors + +resistance_recipe_time +#> +#> ── Recipe ────────────────────────────────────────────────────────────────────── +#> +#> ── Inputs +#> Number of variables by role +#> outcome: 1 +#> predictor: 2 +#> +#> ── Operations +#> • Dummy variables from: gramstain +#> • Centering and scaling for: year +#> • Sparse, unbalanced variable filter on: all_predictors()
Explanation: - step_dummy(): Encodes +categorical variables (ward, species) as +numerical indicators. - step_normalize(): Normalises the +year variable. - step_nzv(): Removes near-zero +variance predictors.
step_dummy()
ward
species
step_normalize()
year
step_nzv()
We use a linear regression model to predict resistance trends.
+# Define the linear regression model +lm_model <- linear_reg() %>% + set_engine("lm") # Use linear regression + +lm_model +#> Linear Regression Model Specification (regression) +#> +#> Computational engine: lm
# Define the linear regression model +lm_model <- linear_reg() %>% + set_engine("lm") # Use linear regression + +lm_model +#> Linear Regression Model Specification (regression) +#> +#> Computational engine: lm
Explanation: - linear_reg(): Defines a +linear regression model. - set_engine("lm"): Uses R’s +built-in linear regression engine.
linear_reg()
set_engine("lm")
We combine the preprocessing recipe and model into a workflow.
+# Create workflow +resistance_workflow_time <- workflow() %>% + add_recipe(resistance_recipe_time) %>% + add_model(lm_model) + +resistance_workflow_time +#> ══ Workflow ════════════════════════════════════════════════════════════════════ +#> Preprocessor: Recipe +#> Model: linear_reg() +#> +#> ── Preprocessor ──────────────────────────────────────────────────────────────── +#> 3 Recipe Steps +#> +#> • step_dummy() +#> • step_normalize() +#> • step_nzv() +#> +#> ── Model ─────────────────────────────────────────────────────────────────────── +#> Linear Regression Model Specification (regression) +#> +#> Computational engine: lm
# Create workflow +resistance_workflow_time <- workflow() %>% + add_recipe(resistance_recipe_time) %>% + add_model(lm_model) + +resistance_workflow_time +#> ══ Workflow ════════════════════════════════════════════════════════════════════ +#> Preprocessor: Recipe +#> Model: linear_reg() +#> +#> ── Preprocessor ──────────────────────────────────────────────────────────────── +#> 3 Recipe Steps +#> +#> • step_dummy() +#> • step_normalize() +#> • step_nzv() +#> +#> ── Model ─────────────────────────────────────────────────────────────────────── +#> Linear Regression Model Specification (regression) +#> +#> Computational engine: lm
We split the data into training and testing sets, fit the model, and +evaluate performance.
+# Split the data +set.seed(123) +data_split_time <- initial_split(data_time, prop = 0.8) +train_time <- training(data_split_time) +test_time <- testing(data_split_time) + +# Train the model +fitted_workflow_time <- resistance_workflow_time %>% + fit(train_time) + +# Make predictions +predictions_time <- fitted_workflow_time %>% + predict(test_time) %>% + bind_cols(test_time) + +# Evaluate model +metrics_time <- predictions_time %>% + metrics(truth = res_AMX, estimate = .pred) + +metrics_time +#> # A tibble: 3 × 3 +#> .metric .estimator .estimate +#> <chr> <chr> <dbl> +#> 1 rmse standard 0.0774 +#> 2 rsq standard 0.711 +#> 3 mae standard 0.0704
# Split the data +set.seed(123) +data_split_time <- initial_split(data_time, prop = 0.8) +train_time <- training(data_split_time) +test_time <- testing(data_split_time) + +# Train the model +fitted_workflow_time <- resistance_workflow_time %>% + fit(train_time) + +# Make predictions +predictions_time <- fitted_workflow_time %>% + predict(test_time) %>% + bind_cols(test_time) + +# Evaluate model +metrics_time <- predictions_time %>% + metrics(truth = res_AMX, estimate = .pred) + +metrics_time +#> # A tibble: 3 × 3 +#> .metric .estimator .estimate +#> <chr> <chr> <dbl> +#> 1 rmse standard 0.0774 +#> 2 rsq standard 0.711 +#> 3 mae standard 0.0704
Explanation: - initial_split(): Splits +data into training and testing sets. - fit(): Trains the +workflow. - predict(): Generates resistance predictions. - +metrics(): Evaluates model performance.
initial_split()
predict()
We plot resistance trends over time for Amoxicillin.
+library(ggplot2) + +# Plot actual vs predicted resistance over time +ggplot(predictions_time, aes(x = year)) + + geom_point(aes(y = res_AMX, color = "Actual")) + + geom_line(aes(y = .pred, color = "Predicted")) + + labs(title = "Predicted vs Actual AMX Resistance Over Time", + x = "Year", + y = "Resistance Proportion") + + theme_minimal()
library(ggplot2) + +# Plot actual vs predicted resistance over time +ggplot(predictions_time, aes(x = year)) + + geom_point(aes(y = res_AMX, color = "Actual")) + + geom_line(aes(y = .pred, color = "Predicted")) + + labs(title = "Predicted vs Actual AMX Resistance Over Time", + x = "Year", + y = "Resistance Proportion") + + theme_minimal()
Additionally, we can visualise resistance trends in +ggplot2 and directly adding linear models there:
ggplot2
+ggplot(data_time, aes(x = year, y = res_AMX, color = gramstain)) + + geom_line() + + labs(title = "AMX Resistance Trends", + x = "Year", + y = "Resistance Proportion") + + # add a linear model directly in ggplot2: + geom_smooth(method = "lm", + formula = y ~ x, + alpha = 0.25) + + theme_minimal()
ggplot(data_time, aes(x = year, y = res_AMX, color = gramstain)) + + geom_line() + + labs(title = "AMX Resistance Trends", + x = "Year", + y = "Resistance Proportion") + + # add a linear model directly in ggplot2: + geom_smooth(method = "lm", + formula = y ~ x, + alpha = 0.25) + + theme_minimal()
In this example, we demonstrated how to analyze AMR trends over time +using tidymodels. By aggregating resistance rates by year +and hospital ward, we built a predictive model to track changes in +resistance to amoxicillin (AMX), amoxicillin-clavulanic +acid (AMC), and ciprofloxacin (CIP).
This method can be extended to other antibiotics and resistance +patterns, providing valuable insights into AMR dynamics in healthcare +settings.
vignettes/resistance_predict.Rmd
resistance_predict.Rmd
As with many uses in R, we need some additional packages for AMR data -analysis. Our package works closely together with the tidyverse packages dplyr and ggplot2. 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.
dplyr
Our AMR package depends on these packages and even -extends their use and functions.
-library(dplyr) -library(ggplot2) -library(AMR) - -# (if not yet installed, install with:) -# install.packages(c("tidyverse", "AMR"))
library(dplyr) -library(ggplot2) -library(AMR) - -# (if not yet installed, install with:) -# install.packages(c("tidyverse", "AMR"))
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.
resistance_predict()
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_date is not set.
col_date
When running any of these commands, a summary of the regression model -will be printed unless using -resistance_predict(..., info = FALSE).
resistance_predict(..., info = FALSE)
This text is only a printed summary - the actual result (output) of -the function is a data.frame containing for each year: the -number of observations, the actual observed resistance, the estimated -resistance and the standard error below and above the estimation:
data.frame
-predict_TZP -#> # A tibble: 34 × 7 -#> year value se_min se_max observations observed estimated -#> * <dbl> <dbl> <dbl> <dbl> <int> <dbl> <dbl> -#> 1 2002 0.2 NA NA 15 0.2 0.0562 -#> 2 2003 0.0625 NA NA 32 0.0625 0.0616 -#> 3 2004 0.0854 NA NA 82 0.0854 0.0676 -#> 4 2005 0.05 NA NA 60 0.05 0.0741 -#> 5 2006 0.0508 NA NA 59 0.0508 0.0812 -#> 6 2007 0.121 NA NA 66 0.121 0.0889 -#> 7 2008 0.0417 NA NA 72 0.0417 0.0972 -#> 8 2009 0.0164 NA NA 61 0.0164 0.106 -#> 9 2010 0.0566 NA NA 53 0.0566 0.116 -#> 10 2011 0.183 NA NA 93 0.183 0.127 -#> # ℹ 24 more rows
predict_TZP -#> # A tibble: 34 × 7 -#> year value se_min se_max observations observed estimated -#> * <dbl> <dbl> <dbl> <dbl> <int> <dbl> <dbl> -#> 1 2002 0.2 NA NA 15 0.2 0.0562 -#> 2 2003 0.0625 NA NA 32 0.0625 0.0616 -#> 3 2004 0.0854 NA NA 82 0.0854 0.0676 -#> 4 2005 0.05 NA NA 60 0.05 0.0741 -#> 5 2006 0.0508 NA NA 59 0.0508 0.0812 -#> 6 2007 0.121 NA NA 66 0.121 0.0889 -#> 7 2008 0.0417 NA NA 72 0.0417 0.0972 -#> 8 2009 0.0164 NA NA 61 0.0164 0.106 -#> 9 2010 0.0566 NA NA 53 0.0566 0.116 -#> 10 2011 0.183 NA NA 93 0.183 0.127 -#> # ℹ 24 more rows
The function plot is 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
-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 ggplot2 package with our custom -function ggplot_sir_predict() to create more appealing -plots:
ggplot_sir_predict()
-ggplot_sir_predict(predict_TZP)
ggplot_sir_predict(predict_TZP)
- -# choose for error bars instead of a ribbon -ggplot_sir_predict(predict_TZP, ribbon = FALSE)
-# choose for error bars instead of a ribbon -ggplot_sir_predict(predict_TZP, ribbon = FALSE)
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 %>% - filter(mo_gramstain(mo, language = NULL) == "Gram-positive") %>% - resistance_predict(col_ab = "VAN", year_min = 2010, info = FALSE, model = "binomial") %>% - ggplot_sir_predict()
example_isolates %>% - filter(mo_gramstain(mo, language = NULL) == "Gram-positive") %>% - resistance_predict(col_ab = "VAN", year_min = 2010, info = FALSE, model = "binomial") %>% - ggplot_sir_predict()
Vancomycin resistance could be 100% in ten years, but might remain -very low.
You can define the model with the model parameter. 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.
model
Valid values are:
"binomial"
"binom"
"logit"
glm(..., family = binomial)
"loglin"
"poisson"
glm(..., family = poisson)
"lin"
"linear"
lm()
For the vancomycin resistance in Gram-positive bacteria, a linear -model might be more appropriate:
-example_isolates %>% - filter(mo_gramstain(mo, language = NULL) == "Gram-positive") %>% - resistance_predict(col_ab = "VAN", year_min = 2010, info = FALSE, model = "linear") %>% - ggplot_sir_predict()
example_isolates %>% - filter(mo_gramstain(mo, language = NULL) == "Gram-positive") %>% - resistance_predict(col_ab = "VAN", year_min = 2010, info = FALSE, model = "linear") %>% - ggplot_sir_predict()
The model itself is also available from the object, as an -attribute:
attribute
-model <- attributes(predict_TZP)$model - -summary(model)$family -#> -#> Family: binomial -#> Link function: logit - -summary(model)$coefficients -#> Estimate Std. Error z value Pr(>|z|) -#> (Intercept) -200.67944891 46.17315349 -4.346237 1.384932e-05 -#> year 0.09883005 0.02295317 4.305725 1.664395e-05
model <- attributes(predict_TZP)$model - -summary(model)$family -#> -#> Family: binomial -#> Link function: logit - -summary(model)$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
(this beta version will eventually become v3.0. We’re happy to reach a new major milestone soon, which will be all about the new One Health support! Install this beta using the instructions here.)
This package now supports not only tools for AMR data analysis in clinical settings, but also for veterinary and environmental microbiology. This was made possible through a collaboration with the University of Prince Edward Island’s Atlantic Veterinary College, Canada. To celebrate this great improvement of the package, we also updated the package logo to reflect this change.
antibiotics
antimicrobials
rsi
sir
as.sir()
breakpoint_type = "animal"
host
ab
mo
uti
as.sir(..., ab = "column1", mo = "column2", uti = "column3")
.xpt
This changelog only contains changes from AMR v3.0 (March 2025) and later.
Our import and reproduction script can be found here: <https://github.com/msberends/AMR/blob/main/data-raw/reproduction scripts/reproduction_of_clinical_breakpoints.R>.
Our import and reproduction script can be found here: https://github.com/msberends/AMR/blob/main/data-raw/_reproduction_scripts/reproduction_of_clinical_breakpoints.R.
A data set containing the full microbial taxonomy (last updated: June 24th, 2024) of six kingdoms. This data set is the backbone of this AMR package. MO codes can be looked up using as.mo() and microorganism properties can be looked up using any of the mo_* functions.
as.mo()
mo_*
This data set is carefully crafted, yet made 100% reproducible from public and authoritative taxonomic sources (using this script(https://github.com/msberends/AMR/blob/main/data-raw/reproduction scripts/reproduction_of_microorganisms.R)), namely: List of Prokaryotic names with Standing in Nomenclature (LPSN) for bacteria, MycoBank for fungi, and Global Biodiversity Information Facility (GBIF) for all others taxons.
This data set is carefully crafted, yet made 100% reproducible from public and authoritative taxonomic sources (using this script), namely: List of Prokaryotic names with Standing in Nomenclature (LPSN) for bacteria, MycoBank for fungi, and Global Biodiversity Information Facility (GBIF) for all others taxons.
1 entry of Blastocystis (B. hominis), although it officially does not exist (Noel et al. 2005, PMID 15634993)
1 entry of Moraxella (M. catarrhalis), which was formally named Branhamella catarrhalis (Catlin, 1970) though this change was never accepted within the field of clinical microbiology
8 other 'undefined' entries (unknown, unknown Gram-negatives, unknown Gram-positives, unknown yeast, unknown fungus, and unknown anaerobic Gram-pos/Gram-neg bacteria)
The syntax used to transform the original data to a cleansed R format, can be found here(https://github.com/msberends/AMR/blob/main/data-raw/reproduction scripts/reproduction_of_microorganisms.R).
The syntax used to transform the original data to a cleansed R format, can be found here.