packages updated

NAMESPACE

@@ -1,12 +1,15 @@
 # Generated by roxygen2: do not edit by hand
 
 export(get_Data_formatted_for_ml_and_best.m)
+export(get_all_TESTCD_rf_input_param_list_output_cv_imp)
+export(get_all_lb_TESTCD_zscore)
 export(get_auc_curve_with_rf_model)
 export(get_bw_score)
 export(get_col_harmonized_scores_df)
 export(get_compile_data)
 export(get_histogram_barplot)
 export(get_imp_features_from_rf_model_with_cv)
+export(get_indiv_score_om_lb_mi_domain_df)
 export(get_lb_score)
 export(get_liver_om_lb_mi_tox_score_list)
 export(get_livertobw_score)
@@ -18,6 +21,7 @@ export(get_reprtree_from_rf_model)
 export(get_rf_input_param_list_output_cv_imp)
 export(get_rf_model_output_cv_imp)
 export(get_rf_model_with_cv)
+export(get_treatment_group_amin)
 import(DBI)
 import(ROCR)
 import(RSQLite)

R/get_bw_score.R

@@ -48,6 +48,11 @@ get_bw_score <- function(studyid = NULL,
                          return_individual_scores = FALSE,
                          return_zscore_by_USUBJID = FALSE) {
 
+  # Enforce mutual exclusivity: If both are TRUE, throw an error or handle it
+  if (return_individual_scores && return_zscore_by_USUBJID) {
+    stop("Error: Both 'return_individual_scores' and 'return_zscore_by_USUBJID' cannot be TRUE at the same time.")
+  }
+
   studyid <- as.character(studyid)
   path <- path_db
 
@@ -356,11 +361,6 @@ if (!("BWDY" %in% colnames(bw)) && !("VISITDY" %in% colnames(bw))) {
     as.data.frame(HD_BWzScore)
 
 
-    # Enforce mutual exclusivity: If both are TRUE, throw an error or handle it
-    if (return_individual_scores && return_zscore_by_USUBJID) {
-      stop("Error: Both 'return_individual_scores' and 'return_zscore_by_USUBJID' cannot be TRUE at the same time.")
-    }
-
   if (return_individual_scores){
 
     bwzscore_BW <- bwzscore_BW

R/get_compile_data.R

@@ -39,7 +39,7 @@ get_compile_data <- function(studyid = NULL,
                              path_db,
                              fake_study = FALSE,
                              use_xpt_file = FALSE) {
-browser()
+
   studyid <- as.character(studyid)
   path <- path_db
 
@@ -445,7 +445,7 @@ browser()
                                                    "DOSE_RANKING",
                                                    "SETCD")]
 
-    # Rename the "DOSE_RANKING" column to ARMCD
+      # Rename the "DOSE_RANKING" column to ARMCD
     # Rename "DOSE_RANKING" to "ARMCD" in master_compiledata
     master_compiledata <- master_compiledata1 %>%
       dplyr::rename(ARMCD = DOSE_RANKING)

R/get_treatment_group_&_dose.R

@@ -10,7 +10,7 @@
 #' @param fake_study Logical. Whether the study data is generated by the `SENDsanitizer` package. Defaults to `FALSE`.
 #' @param use_xpt_file Logical. Whether to retrieve study data from `.xpt` files instead of the SQLite database. Defaults to `FALSE`.
 #'
-#' @return
+#' @return a data frame
 #' @examples
 #'
 #' \dontrun{

README.Rmd

@@ -7,7 +7,7 @@ output:
     toc_depth: 2
 ---
 
-# SENDQSAR: QSAR Modeling with SEND Database
+# SENDQSAR: A `R Package` for `QSAR Modeling` with `SEND Database`
 
 ## About
 
@@ -23,11 +23,11 @@ output:
 
 ## Workflow
 
-- **Input Database Path**: Provide the database path containing nonclinical study results for each STUDYID.
-- **Data Pre processing**: Use functions `f1` to `f8` to clean, harmonize, and prepare data.
-- **Model Building**: Employ machine learning functions (`f9` to `f18`) for training, validation, and evaluation.
-- **Visualization**: Generate plots and performance metrics for better interpretation.
-
+- **Input Database Path**: Provide the path for database or `.xpt` files containing nonclinical study data in `SEND` format.
+- **Data Pre processing**: Use functions `f1` to `f8` to clean, harmonize, and prepare data for Machine Learning (ML).
+- **Model Building**: Employ ML functions (`f9` to `f18`) for ML model training and evaluation.
+- **Visualization**: Generate plots and performance metrics for better interpretation (`f12` to `f15`).
+- **Automated Pipelines**: Use functions `f15` to `f18` to perform the above workflows in A single step by providing the database path and a `.csv` file containing the label (TOXIC/NON-TOXIC) of the `STUDYID`. 
 
 ## Modular Functions Overview
 
@@ -53,16 +53,26 @@ output:
 
 - **Machine Learning Model Building and Performance Evaluation**:
 
-  - `f9`: `get_rf_model_with_cv` - Builds a random forest model with cross-validation (depends on `f8`).
-
-
-  - `f10`: `get_zone_exclusioned_rf_model_with_cv` - Enhances classification accuracy by excluding uncertain predictions  (depends on `f8`).
-
-  - `f11`: `get_imp_features_from_rf_model_with_cv` - Computes feature importance for model interpretation.
-
-  - `f12`: `get_auc_curve_with_rf_model`- Generates AUC curves to evaluate model performance.
-
-- **N.B** :
+  - **Model Training** 
+    - `f9`: `get_rf_model_with_cv`
+      - Builds a random forest model with cross-validation (depends on `f8`).
+
+  - **Improved Classification Accuracy**    
+    - `f10`: `get_zone_exclusioned_rf_model_with_cv`
+      - Enhances classification accuracy by excluding uncertain predictions  (depends on `f8`).
+
+  - **Feature Importance**      
+    - `f11`: `get_imp_features_from_rf_model_with_cv`
+      - Computes feature importance for model interpretation.
+
+  - **Model Performance Visualization**   
+    - `f12`: `get_auc_curve_with_rf_model`
+      - Generates AUC curves to evaluate model performance.
+
+#### Notes for MOdular Functions 
+- **Data Preparation**  
+  - Functions `f1` to `f8` must be executed sequentially to prepare the `Data` argument required by these functions.  
+  - Alternatively, the **composite function** `f18` can be used to directly generate the `Data` argument, combining the functionality of `f1` to `f8`.
   - For `f9`, `f10`, `f11`, and `f12`, Functions `f1`, `f2`, `f3`, `f4`, `f5`, `f6`, `f7`, and `f8`must be executed sequentially to prepare the `Data` argument. Alternatively, the **composite function** `f18` can be used to directly generate the `Data` argument.   
 
 ---

README.html

@@ -603,8 +603,9 @@
 
 <h1 id="sendqsar">SENDQSAR</h1>
 <ul>
-<li><a href="#sendqsar-qsar-modeling-with-send-database">SENDQSAR: QSAR
-Modeling with SEND Database</a>
+<li><a href="#sendqsar-a-r-package-for-qsar-modeling-with-send-database">SENDQSAR:
+A <code>R Package</code> for <code>QSAR Modeling</code> with
+<code>SEND Database</code></a>
 <ul>
 <li><a href="#about">About</a></li>
 <li><a href="#features">Features</a></li>
@@ -622,8 +623,9 @@ <h1 id="sendqsar">SENDQSAR</h1>
 <li><a href="#contact">Contact</a></li>
 </ul></li>
 </ul>
-<h1 id="sendqsar-qsar-modeling-with-send-database">SENDQSAR: QSAR
-Modeling with SEND Database</h1>
+<h1 id="sendqsar-a-r-package-for-qsar-modeling-with-send-database">SENDQSAR:
+A <code>R Package</code> for <code>QSAR Modeling</code> with
+<code>SEND Database</code></h1>
 <h2 id="about">About</h2>
 <ul>
 <li>This package facilitates developing Quantitative Structure-Activity
@@ -652,15 +654,22 @@ <h2 id="features">Features</h2>
 </ul>
 <h2 id="workflow">Workflow</h2>
 <ul>
-<li><strong>Input Database Path</strong>: Provide the database path
-containing nonclinical study results for each STUDYID.</li>
+<li><strong>Input Database Path</strong>: Provide the path for database
+or <code>.xpt</code> files containing nonclinical study data in
+<code>SEND</code> format.</li>
 <li><strong>Data Pre processing</strong>: Use functions <code>f1</code>
-to <code>f8</code> to clean, harmonize, and prepare data.</li>
-<li><strong>Model Building</strong>: Employ machine learning functions
-(<code>f9</code> to <code>f18</code>) for training, validation, and
+to <code>f8</code> to clean, harmonize, and prepare data for Machine
+Learning (ML).</li>
+<li><strong>Model Building</strong>: Employ ML functions
+(<code>f9</code> to <code>f18</code>) for ML model training and
 evaluation.</li>
 <li><strong>Visualization</strong>: Generate plots and performance
-metrics for better interpretation.</li>
+metrics for better interpretation (<code>f12</code> to
+<code>f15</code>).</li>
+<li><strong>Automated Pipelines</strong>: Use functions <code>f15</code>
+to <code>f18</code> to perform the above workflows in A single step by
+providing the database path and a <code>.csv</code> file containing the
+label (TOXIC/NON-TOXIC) of the <code>STUDYID</code>.</li>
 </ul>
 <h2 id="modular-functions-overview">Modular Functions Overview</h2>
 <ul>
@@ -701,21 +710,50 @@ <h2 id="modular-functions-overview">Modular Functions Overview</h2>
 <li><p><strong>Machine Learning Model Building and Performance
 Evaluation</strong>:</p>
 <ul>
-<li><p><code>f9</code>: <code>get_rf_model_with_cv</code> - Builds a
-random forest model with cross-validation (depends on
-<code>f8</code>).</p></li>
-<li><p><code>f10</code>:
-<code>get_zone_exclusioned_rf_model_with_cv</code> - Enhances
-classification accuracy by excluding uncertain predictions (depends on
-<code>f8</code>).</p></li>
-<li><p><code>f11</code>:
-<code>get_imp_features_from_rf_model_with_cv</code> - Computes feature
-importance for model interpretation.</p></li>
-<li><p><code>f12</code>: <code>get_auc_curve_with_rf_model</code>-
-Generates AUC curves to evaluate model performance.</p></li>
+<li><strong>Model Training</strong>
+<ul>
+<li><code>f9</code>: <code>get_rf_model_with_cv</code>
+<ul>
+<li>Builds a random forest model with cross-validation (depends on
+<code>f8</code>).</li>
+</ul></li>
+</ul></li>
+<li><strong>Improved Classification Accuracy</strong>
+<ul>
+<li><code>f10</code>: <code>get_zone_exclusioned_rf_model_with_cv</code>
+<ul>
+<li>Enhances classification accuracy by excluding uncertain predictions
+(depends on <code>f8</code>).</li>
+</ul></li>
+</ul></li>
+<li><strong>Feature Importance</strong>
+<ul>
+<li><code>f11</code>:
+<code>get_imp_features_from_rf_model_with_cv</code>
+<ul>
+<li>Computes feature importance for model interpretation.</li>
+</ul></li>
+</ul></li>
+<li><strong>Model Performance Visualization</strong>
+<ul>
+<li><code>f12</code>: <code>get_auc_curve_with_rf_model</code>
+<ul>
+<li>Generates AUC curves to evaluate model performance.</li>
 </ul></li>
-<li><p><strong>N.B</strong> :</p>
+</ul></li>
+</ul></li>
+</ul>
+<h4 id="notes-for-modular-functions">Notes for MOdular Functions</h4>
+<ul>
+<li><strong>Data Preparation</strong>
 <ul>
+<li>Functions <code>f1</code> to <code>f8</code> must be executed
+sequentially to prepare the <code>Data</code> argument required by these
+functions.</li>
+<li>Alternatively, the <strong>composite function</strong>
+<code>f18</code> can be used to directly generate the <code>Data</code>
+argument, combining the functionality of <code>f1</code> to
+<code>f8</code>.</li>
 <li>For <code>f9</code>, <code>f10</code>, <code>f11</code>, and
 <code>f12</code>, Functions <code>f1</code>, <code>f2</code>,
 <code>f3</code>, <code>f4</code>, <code>f5</code>, <code>f6</code>,

README.md

@@ -1,8 +1,8 @@
 SENDQSAR
 ================
 
-- [SENDQSAR: QSAR Modeling with SEND
-  Database](#sendqsar-qsar-modeling-with-send-database)
+- [SENDQSAR: A `R Package` for `QSAR Modeling` with
+  `SEND Database`](#sendqsar-a-r-package-for-qsar-modeling-with-send-database)
   - [About](#about)
   - [Features](#features)
   - [Workflow](#workflow)
@@ -16,7 +16,7 @@ SENDQSAR
   - [License](#license)
   - [Contact](#contact)
 
-# SENDQSAR: QSAR Modeling with SEND Database
+# SENDQSAR: A `R Package` for `QSAR Modeling` with `SEND Database`
 
 ## About
 
@@ -44,14 +44,17 @@ SENDQSAR
 
 ## Workflow
 
-- **Input Database Path**: Provide the database path containing
-  nonclinical study results for each STUDYID.
+- **Input Database Path**: Provide the path for database or `.xpt` files
+  containing nonclinical study data in `SEND` format.
 - **Data Pre processing**: Use functions `f1` to `f8` to clean,
-  harmonize, and prepare data.
-- **Model Building**: Employ machine learning functions (`f9` to `f18`)
-  for training, validation, and evaluation.
+  harmonize, and prepare data for Machine Learning (ML).
+- **Model Building**: Employ ML functions (`f9` to `f18`) for ML model
+  training and evaluation.
 - **Visualization**: Generate plots and performance metrics for better
-  interpretation.
+  interpretation (`f12` to `f15`).
+- **Automated Pipelines**: Use functions `f15` to `f18` to perform the
+  above workflows in A single step by providing the database path and a
+  `.csv` file containing the label (TOXIC/NON-TOXIC) of the `STUDYID`.
 
 ## Modular Functions Overview
 
@@ -87,21 +90,29 @@ SENDQSAR
 
 - **Machine Learning Model Building and Performance Evaluation**:
 
-  - `f9`: `get_rf_model_with_cv` - Builds a random forest model with
-    cross-validation (depends on `f8`).
-
-  - `f10`: `get_zone_exclusioned_rf_model_with_cv` - Enhances
-    classification accuracy by excluding uncertain predictions (depends
-    on `f8`).
-
-  - `f11`: `get_imp_features_from_rf_model_with_cv` - Computes feature
-    importance for model interpretation.
-
-  - `f12`: `get_auc_curve_with_rf_model`- Generates AUC curves to
-    evaluate model performance.
-
-- **N.B** :
-
+  - **Model Training**
+    - `f9`: `get_rf_model_with_cv`
+      - Builds a random forest model with cross-validation (depends on
+        `f8`).
+  - **Improved Classification Accuracy**
+    - `f10`: `get_zone_exclusioned_rf_model_with_cv`
+      - Enhances classification accuracy by excluding uncertain
+        predictions (depends on `f8`).
+  - **Feature Importance**
+    - `f11`: `get_imp_features_from_rf_model_with_cv`
+      - Computes feature importance for model interpretation.
+  - **Model Performance Visualization**
+    - `f12`: `get_auc_curve_with_rf_model`
+      - Generates AUC curves to evaluate model performance.
+
+#### Notes for MOdular Functions
+
+- **Data Preparation**
+  - Functions `f1` to `f8` must be executed sequentially to prepare the
+    `Data` argument required by these functions.  
+  - Alternatively, the **composite function** `f18` can be used to
+    directly generate the `Data` argument, combining the functionality
+    of `f1` to `f8`.
   - For `f9`, `f10`, `f11`, and `f12`, Functions `f1`, `f2`, `f3`, `f4`,
     `f5`, `f6`, `f7`, and `f8`must be executed sequentially to prepare
     the `Data` argument. Alternatively, the **composite function** `f18`