@ -31,7 +31,7 @@
< a class = "navbar-brand me-2" href = "../index.html" > AMR (for R)< / a >
< small class = "nav-text text-muted me-auto" data-bs-toggle = "tooltip" data-bs-placement = "bottom" title = "" > 2.1.1.9163 < / small >
< small class = "nav-text text-muted me-auto" data-bs-toggle = "tooltip" data-bs-placement = "bottom" title = "" > 2.1.1.9182 < / small >
< button class = "navbar-toggler" type = "button" data-bs-toggle = "collapse" data-bs-target = "#navbar" aria-controls = "navbar" aria-expanded = "false" aria-label = "Toggle navigation" >
@ -127,6 +127,7 @@ train, and evaluate the model.</li>
package.< / p >
< div class = "sourceCode" id = "cb1" > < pre class = "downlit sourceCode r" >
< code class = "sourceCode R" > < span > < span class = "co" > # Load required libraries< / span > < / span >
< span > < span class = "kw" > < a href = "https://rdrr.io/r/base/library.html" class = "external-link" > library< / a > < / span > < span class = "op" > (< / span > < span class = "va" > < a href = "https://msberends.github.io/AMR/" > AMR< / a > < / span > < span class = "op" > )< / span > < span class = "co" > # For AMR data analysis< / span > < / span >
< span > < span class = "kw" > < a href = "https://rdrr.io/r/base/library.html" class = "external-link" > library< / a > < / span > < span class = "op" > (< / span > < span class = "va" > < a href = "https://tidymodels.tidymodels.org" class = "external-link" > tidymodels< / a > < / span > < span class = "op" > )< / span > < span class = "co" > # For machine learning workflows, and data manipulation (dplyr, tidyr, ...)< / span > < / span >
< span > < span class = "co" > #> ── < span style = "font-weight: bold;" > Attaching packages< / span > ────────────────────────────────────── tidymodels 1.3.0 ──< / span > < / span >
< span > < span class = "co" > #> < span style = "color: #00BB00;" > ✔< / span > < span style = "color: #0000BB;" > broom < / span > 1.0.7 < span style = "color: #00BB00;" > ✔< / span > < span style = "color: #0000BB;" > recipes < / span > 1.1.1< / span > < / span >
@ -142,7 +143,6 @@ package.</p>
< span > < span class = "co" > #> < span style = "color: #BB0000;" > ✖< / span > < span style = "color: #0000BB;" > dplyr< / span > ::< span style = "color: #00BB00;" > filter()< / span > masks < span style = "color: #0000BB;" > stats< / span > ::filter()< / span > < / span >
< span > < span class = "co" > #> < span style = "color: #BB0000;" > ✖< / span > < span style = "color: #0000BB;" > dplyr< / span > ::< span style = "color: #00BB00;" > lag()< / span > masks < span style = "color: #0000BB;" > stats< / span > ::lag()< / span > < / span >
< span > < span class = "co" > #> < span style = "color: #BB0000;" > ✖< / span > < span style = "color: #0000BB;" > recipes< / span > ::< span style = "color: #00BB00;" > step()< / span > masks < span style = "color: #0000BB;" > stats< / span > ::step()< / span > < / span >
< span > < span class = "kw" > < a href = "https://rdrr.io/r/base/library.html" class = "external-link" > library< / a > < / span > < span class = "op" > (< / span > < span class = "va" > < a href = "https://msberends.github.io/AMR/" > AMR< / a > < / span > < span class = "op" > )< / span > < span class = "co" > # For AMR data analysis< / span > < / span >
< span > < / span >
< span > < span class = "co" > # Select relevant columns for prediction< / span > < / span >
< span > < span class = "va" > data< / span > < span class = "op" > < -< / span > < span class = "va" > example_isolates< / span > < span class = "op" > < a href = "https://magrittr.tidyverse.org/reference/pipe.html" class = "external-link" > %> %< / a > < / span > < / span >
@ -201,6 +201,32 @@ three steps: preprocessing, model specification, and fitting.</p>
< span > < span class = "co" > #> < / span > < / span >
< span > < span class = "co" > #> ── Operations< / span > < / span >
< span > < span class = "co" > #> < span style = "color: #00BBBB;" > •< / span > Correlation filter on: < span style = "color: #0000BB;" > c(aminoglycosides(), betalactams())< / span > < / span > < / span > < / code > < / pre > < / div >
< p > For a recipe that includes at least one preprocessing operation, like
we have with < code > step_corr()< / code > , the necessary parameters can be
estimated from a training set using < code > prep()< / code > :< / p >
< div class = "sourceCode" id = "cb3" > < pre class = "downlit sourceCode r" >
< code class = "sourceCode R" > < span > < span class = "fu" > prep< / span > < span class = "op" > (< / span > < span class = "va" > resistance_recipe< / span > < span class = "op" > )< / span > < / span >
< span > < span class = "co" > #> < span style = "color: #0000BB;" > ℹ < / span > < span style = "color: #0000BB; background-color: #EEEEEE;" > aminoglycosides()< / span > < span style = "color: #0000BB;" > using columns '< / span > < span style = "color: #0000BB; font-weight: bold;" > GEN< / span > < span style = "color: #0000BB;" > ' (gentamicin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > TOB< / span > < span style = "color: #0000BB;" > '< / span > < / span > < / span >
< span > < span class = "co" > < span style = "color: #0000BB;" > #> (tobramycin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > AMK< / span > < span style = "color: #0000BB;" > ' (amikacin), and '< / span > < span style = "color: #0000BB; font-weight: bold;" > KAN< / span > < span style = "color: #0000BB;" > ' (kanamycin)< / span > < / span > < / span >
< span > < span class = "co" > #> < span style = "color: #0000BB;" > ℹ < / span > < span style = "color: #0000BB; background-color: #EEEEEE;" > betalactams()< / span > < span style = "color: #0000BB;" > using columns '< / span > < span style = "color: #0000BB; font-weight: bold;" > PEN< / span > < span style = "color: #0000BB;" > ' (benzylpenicillin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > OXA< / span > < span style = "color: #0000BB;" > '< / span > < / span > < / span >
< span > < span class = "co" > < span style = "color: #0000BB;" > #> (oxacillin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > FLC< / span > < span style = "color: #0000BB;" > ' (flucloxacillin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > AMX< / span > < span style = "color: #0000BB;" > ' (amoxicillin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > AMC< / span > < span style = "color: #0000BB;" > '< / span > < / span > < / span >
< span > < span class = "co" > < span style = "color: #0000BB;" > #> (amoxicillin/clavulanic acid), '< / span > < span style = "color: #0000BB; font-weight: bold;" > AMP< / span > < span style = "color: #0000BB;" > ' (ampicillin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > TZP< / span > < span style = "color: #0000BB;" > '< / span > < / span > < / span >
< span > < span class = "co" > < span style = "color: #0000BB;" > #> (piperacillin/tazobactam), '< / span > < span style = "color: #0000BB; font-weight: bold;" > CZO< / span > < span style = "color: #0000BB;" > ' (cefazolin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > FEP< / span > < span style = "color: #0000BB;" > ' (cefepime), '< / span > < span style = "color: #0000BB; font-weight: bold;" > CXM< / span > < span style = "color: #0000BB;" > '< / span > < / span > < / span >
< span > < span class = "co" > < span style = "color: #0000BB;" > #> (cefuroxime), '< / span > < span style = "color: #0000BB; font-weight: bold;" > FOX< / span > < span style = "color: #0000BB;" > ' (cefoxitin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > CTX< / span > < span style = "color: #0000BB;" > ' (cefotaxime), '< / span > < span style = "color: #0000BB; font-weight: bold;" > CAZ< / span > < span style = "color: #0000BB;" > ' (ceftazidime),< / span > < / span > < / span >
< span > < span class = "co" > < span style = "color: #0000BB;" > #> '< / span > < span style = "color: #0000BB; font-weight: bold;" > CRO< / span > < span style = "color: #0000BB;" > ' (ceftriaxone), '< / span > < span style = "color: #0000BB; font-weight: bold;" > IPM< / span > < span style = "color: #0000BB;" > ' (imipenem), and '< / span > < span style = "color: #0000BB; font-weight: bold;" > MEM< / span > < span style = "color: #0000BB;" > ' (meropenem)< / span > < / span > < / span >
< span > < span class = "co" > #> < / span > < / span >
< span > < span class = "co" > #> < span style = "color: #00BBBB;" > ──< / span > < span style = "font-weight: bold;" > Recipe< / span > < span style = "color: #00BBBB;" > ──────────────────────────────────────────────────────────────────────< / span > < / span > < / span >
< span > < span class = "co" > #> < / span > < / span >
< span > < span class = "co" > #> ── Inputs< / span > < / span >
< span > < span class = "co" > #> Number of variables by role< / span > < / span >
< span > < span class = "co" > #> outcome: 1< / span > < / span >
< span > < span class = "co" > #> predictor: 20< / span > < / span >
< span > < span class = "co" > #> < / span > < / span >
< span > < span class = "co" > #> ── Training information< / span > < / span >
< span > < span class = "co" > #> Training data contained 1968 data points and no incomplete rows.< / span > < / span >
< span > < span class = "co" > #> < / span > < / span >
< span > < span class = "co" > #> ── Operations< / span > < / span >
< span > < span class = "co" > #> < span style = "color: #00BBBB;" > •< / span > Correlation filter on: < span style = "color: #0000BB;" > AMX< / span > < span style = "color: #0000BB;" > CTX< / span > | < span style = "font-style: italic;" > Trained< / span > < / span > < / span > < / code > < / pre > < / div >
< p > < strong > Explanation:< / strong > < / p >
< ul >
< li >
@ -212,14 +238,17 @@ predictors.</li>
columns) that have a higher correlation than 90%.< / li >
< / ul >
< p > Notice how the recipe contains just the antibiotic selector functions
- no need to define the columns specifically.< / p >
- no need to define the columns specifically. In the preparation
(retrieved with < code > prep()< / code > ) we can see that the columns or
variables ‘ ’ ‘ ’
existing, other variables.< / p >
< / div >
< div class = "section level4" >
< h4 id = "specifying-the-model" > 2. Specifying the Model< a class = "anchor" aria-label = "anchor" href = "#specifying-the-model" > < / a >
< / h4 >
< p > We define a logistic regression model since resistance prediction is
a binary classification task.< / p >
< div class = "sourceCode" id = "cb3 " > < pre class = "downlit sourceCode r" >
< div class = "sourceCode" id = "cb4 " > < pre class = "downlit sourceCode r" >
< code class = "sourceCode R" > < span > < span class = "co" > # Specify a logistic regression model< / span > < / span >
< span > < span class = "va" > logistic_model< / span > < span class = "op" > < -< / span > < span class = "fu" > logistic_reg< / span > < span class = "op" > (< / span > < span class = "op" > )< / span > < span class = "op" > < a href = "https://magrittr.tidyverse.org/reference/pipe.html" class = "external-link" > %> %< / a > < / span > < / span >
< span > < span class = "fu" > set_engine< / span > < span class = "op" > (< / span > < span class = "st" > "glm"< / span > < span class = "op" > )< / span > < span class = "co" > # Use the Generalized Linear Model engine< / span > < / span >
@ -242,11 +271,25 @@ engine.</li>
< / h4 >
< p > We bundle the recipe and model together into a < code > workflow< / code > ,
which organizes the entire modeling process.< / p >
< div class = "sourceCode" id = "cb4 " > < pre class = "downlit sourceCode r" >
< div class = "sourceCode" id = "cb5 " > < pre class = "downlit sourceCode r" >
< code class = "sourceCode R" > < span > < span class = "co" > # Combine the recipe and model into a workflow< / span > < / span >
< span > < span class = "va" > resistance_workflow< / span > < span class = "op" > < -< / span > < span class = "fu" > workflow< / span > < span class = "op" > (< / span > < span class = "op" > )< / span > < span class = "op" > < a href = "https://magrittr.tidyverse.org/reference/pipe.html" class = "external-link" > %> %< / a > < / span > < / span >
< span > < span class = "fu" > add_recipe< / span > < span class = "op" > (< / span > < span class = "va" > resistance_recipe< / span > < span class = "op" > )< / span > < span class = "op" > < a href = "https://magrittr.tidyverse.org/reference/pipe.html" class = "external-link" > %> %< / a > < / span > < span class = "co" > # Add the preprocessing recipe< / span > < / span >
< span > < span class = "fu" > add_model< / span > < span class = "op" > (< / span > < span class = "va" > logistic_model< / span > < span class = "op" > )< / span > < span class = "co" > # Add the logistic regression model< / span > < / span > < / code > < / pre > < / div >
< span > < span class = "fu" > add_model< / span > < span class = "op" > (< / span > < span class = "va" > logistic_model< / span > < span class = "op" > )< / span > < span class = "co" > # Add the logistic regression model< / span > < / span >
< span > < span class = "va" > resistance_workflow< / span > < / span >
< span > < span class = "co" > #> ══ Workflow ════════════════════════════════════════════════════════════════════< / span > < / span >
< span > < span class = "co" > #> < span style = "font-style: italic;" > Preprocessor:< / span > Recipe< / span > < / span >
< span > < span class = "co" > #> < span style = "font-style: italic;" > Model:< / span > logistic_reg()< / span > < / span >
< span > < span class = "co" > #> < / span > < / span >
< span > < span class = "co" > #> ── Preprocessor ────────────────────────────────────────────────────────────────< / span > < / span >
< span > < span class = "co" > #> 1 Recipe Step< / span > < / span >
< span > < span class = "co" > #> < / span > < / span >
< span > < span class = "co" > #> • step_corr()< / span > < / span >
< span > < span class = "co" > #> < / span > < / span >
< span > < span class = "co" > #> ── Model ───────────────────────────────────────────────────────────────────────< / span > < / span >
< span > < span class = "co" > #> Logistic Regression Model Specification (classification)< / span > < / span >
< span > < span class = "co" > #> < / span > < / span >
< span > < span class = "co" > #> Computational engine: glm< / span > < / span > < / code > < / pre > < / div >
< / div >
< / div >
< div class = "section level3" >
@ -256,7 +299,7 @@ which organizes the entire modeling process.</p>
< p > To train the model, we split the data into training and testing sets.
Then, we fit the workflow on the training set and evaluate its
performance.< / p >
< div class = "sourceCode" id = "cb5 " > < pre class = "downlit sourceCode r" >
< div class = "sourceCode" id = "cb6 " > < pre class = "downlit sourceCode r" >
< code class = "sourceCode R" > < span > < span class = "co" > # Split data into training and testing sets< / span > < / span >
< span > < span class = "fu" > < a href = "https://rdrr.io/r/base/Random.html" class = "external-link" > set.seed< / a > < / span > < span class = "op" > (< / span > < span class = "fl" > 123< / span > < span class = "op" > )< / span > < span class = "co" > # For reproducibility< / span > < / span >
< span > < span class = "va" > data_split< / span > < span class = "op" > < -< / span > < span class = "fu" > initial_split< / span > < span class = "op" > (< / span > < span class = "va" > data< / span > , prop < span class = "op" > =< / span > < span class = "fl" > 0.8< / span > < span class = "op" > )< / span > < span class = "co" > # 80% training, 20% testing< / span > < / span >
@ -265,15 +308,7 @@ performance.</p>
< span > < / span >
< span > < span class = "co" > # Fit the workflow to the training data< / span > < / span >
< span > < span class = "va" > fitted_workflow< / span > < span class = "op" > < -< / span > < span class = "va" > resistance_workflow< / span > < span class = "op" > < a href = "https://magrittr.tidyverse.org/reference/pipe.html" class = "external-link" > %> %< / a > < / span > < / span >
< span > < span class = "fu" > fit< / span > < span class = "op" > (< / span > < span class = "va" > training_data< / span > < span class = "op" > )< / span > < span class = "co" > # Train the model< / span > < / span >
< span > < span class = "co" > #> < span style = "color: #0000BB;" > ℹ < / span > < span style = "color: #0000BB; background-color: #EEEEEE;" > aminoglycosides()< / span > < span style = "color: #0000BB;" > using columns '< / span > < span style = "color: #0000BB; font-weight: bold;" > GEN< / span > < span style = "color: #0000BB;" > ' (gentamicin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > TOB< / span > < span style = "color: #0000BB;" > '< / span > < / span > < / span >
< span > < span class = "co" > < span style = "color: #0000BB;" > #> (tobramycin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > AMK< / span > < span style = "color: #0000BB;" > ' (amikacin), and '< / span > < span style = "color: #0000BB; font-weight: bold;" > KAN< / span > < span style = "color: #0000BB;" > ' (kanamycin)< / span > < / span > < / span >
< span > < span class = "co" > #> < span style = "color: #0000BB;" > ℹ < / span > < span style = "color: #0000BB; background-color: #EEEEEE;" > betalactams()< / span > < span style = "color: #0000BB;" > using columns '< / span > < span style = "color: #0000BB; font-weight: bold;" > PEN< / span > < span style = "color: #0000BB;" > ' (benzylpenicillin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > OXA< / span > < span style = "color: #0000BB;" > '< / span > < / span > < / span >
< span > < span class = "co" > < span style = "color: #0000BB;" > #> (oxacillin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > FLC< / span > < span style = "color: #0000BB;" > ' (flucloxacillin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > AMX< / span > < span style = "color: #0000BB;" > ' (amoxicillin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > AMC< / span > < span style = "color: #0000BB;" > '< / span > < / span > < / span >
< span > < span class = "co" > < span style = "color: #0000BB;" > #> (amoxicillin/clavulanic acid), '< / span > < span style = "color: #0000BB; font-weight: bold;" > AMP< / span > < span style = "color: #0000BB;" > ' (ampicillin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > TZP< / span > < span style = "color: #0000BB;" > '< / span > < / span > < / span >
< span > < span class = "co" > < span style = "color: #0000BB;" > #> (piperacillin/tazobactam), '< / span > < span style = "color: #0000BB; font-weight: bold;" > CZO< / span > < span style = "color: #0000BB;" > ' (cefazolin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > FEP< / span > < span style = "color: #0000BB;" > ' (cefepime), '< / span > < span style = "color: #0000BB; font-weight: bold;" > CXM< / span > < span style = "color: #0000BB;" > '< / span > < / span > < / span >
< span > < span class = "co" > < span style = "color: #0000BB;" > #> (cefuroxime), '< / span > < span style = "color: #0000BB; font-weight: bold;" > FOX< / span > < span style = "color: #0000BB;" > ' (cefoxitin), '< / span > < span style = "color: #0000BB; font-weight: bold;" > CTX< / span > < span style = "color: #0000BB;" > ' (cefotaxime), '< / span > < span style = "color: #0000BB; font-weight: bold;" > CAZ< / span > < span style = "color: #0000BB;" > ' (ceftazidime),< / span > < / span > < / span >
< span > < span class = "co" > < span style = "color: #0000BB;" > #> '< / span > < span style = "color: #0000BB; font-weight: bold;" > CRO< / span > < span style = "color: #0000BB;" > ' (ceftriaxone), '< / span > < span style = "color: #0000BB; font-weight: bold;" > IPM< / span > < span style = "color: #0000BB;" > ' (imipenem), and '< / span > < span style = "color: #0000BB; font-weight: bold;" > MEM< / span > < span style = "color: #0000BB;" > ' (meropenem)< / span > < / span > < / span > < / code > < / pre > < / div >
< span > < span class = "fu" > fit< / span > < span class = "op" > (< / span > < span class = "va" > training_data< / span > < span class = "op" > )< / span > < span class = "co" > # Train the model< / span > < / span > < / code > < / pre > < / div >
< p > < strong > Explanation:< / strong > < / p >
< ul >
< li >
@ -286,7 +321,7 @@ testing sets.</li>
are internally called again. For training, these functions are called
since they are stored in the recipe.< / p >
< p > Next, we evaluate the model on the testing data.< / p >
< div class = "sourceCode" id = "cb6 " > < pre class = "downlit sourceCode r" >
< div class = "sourceCode" id = "cb7 " > < pre class = "downlit sourceCode r" >
< code class = "sourceCode R" > < span > < span class = "co" > # Make predictions on the testing set< / span > < / span >
< span > < span class = "va" > predictions< / span > < span class = "op" > < -< / span > < span class = "va" > fitted_workflow< / span > < span class = "op" > < a href = "https://magrittr.tidyverse.org/reference/pipe.html" class = "external-link" > %> %< / a > < / span > < / span >
< span > < span class = "fu" > < a href = "https://rdrr.io/r/stats/predict.html" class = "external-link" > predict< / a > < / span > < span class = "op" > (< / span > < span class = "va" > testing_data< / span > < span class = "op" > )< / span > < span class = "co" > # Generate predictions< / span > < / span >
@ -338,11 +373,11 @@ kappa.</li>
< p > 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:< / p >
< div class = "sourceCode" id = "cb7 " > < pre class = "downlit sourceCode r" >
< div class = "sourceCode" id = "cb8 " > < pre class = "downlit sourceCode r" >
< code class = "sourceCode R" > < span > < span class = "va" > predictions< / span > < span class = "op" > < a href = "https://magrittr.tidyverse.org/reference/pipe.html" class = "external-link" > %> %< / a > < / span > < / span >
< span > < span class = "fu" > roc_curve< / span > < span class = "op" > (< / span > < span class = "va" > mo< / span > , < span class = "va" > `.pred_Gram-negative`< / span > < span class = "op" > )< / span > < span class = "op" > < a href = "https://magrittr.tidyverse.org/reference/pipe.html" class = "external-link" > %> %< / a > < / span > < / span >
< span > < span class = "fu" > < a href = "https://ggplot2.tidyverse.org/reference/autoplot.html" class = "external-link" > autoplot< / a > < / span > < span class = "op" > (< / span > < span class = "op" > )< / span > < / span > < / code > < / pre > < / div >
< p > < img src = "AMR_with_tidymodels_files/figure-html/unnamed-chunk-7 -1.png" width = "720" > < / p >
< p > < img src = "AMR_with_tidymodels_files/figure-html/unnamed-chunk-8 -1.png" width = "720" > < / p >
< / div >
< div class = "section level3" >
< h3 id = "conclusion" >
github-actions
