diff --git a/R/get_reprtree_from_rf_model .R b/R/get_14reprtree_from_rf_model .R
similarity index 100%
rename from R/get_reprtree_from_rf_model .R
rename to R/get_14reprtree_from_rf_model .R
diff --git a/R/get_2bw_score.R b/R/get_bw_score.R
similarity index 88%
rename from R/get_2bw_score.R
rename to R/get_bw_score.R
index 9ea3141..9e39e20 100644
--- a/R/get_2bw_score.R
+++ b/R/get_bw_score.R
@@ -1,33 +1,49 @@
-
-#' @title get BW score for a given studyid
+#' @title Calculate BW Score for a Given Study ID
+#'
+#' @description
+#' The `get_bw_score` function calculates the Bayesian Weighted (BW) score for a specified study ID using data from a provided database.
+#' It supports optional parameters for fine-tuning the analysis and offers the flexibility to return individual scores or z-scores by `USUBJID`.
+#'
 #' @param studyid Mandatory, character \cr
-#'   Studyid number
+#'   The study ID for which the BW score is to be calculated. If `NULL`, all studies in the database are analyzed.
 #' @param path_db Mandatory, character \cr
-#'   path of database
-#' @param fake_study optional, Boolean \cr
-#' whether study generated by SENDsanitizer package
-#' @param use_xpt_file  Mandatory, character \cr
-#'   Studyid number
-#' @param master_compiledata Mandatory, character \cr
-#'   path of database
-#' @param return_individual_scores optional, Boolean \cr
-#' whether study generated by SENDsanitizer package
-#' @param return_zscore_by_USUBJID optional, Boolean \cr
-#' whether study generated by SENDsanitizer package
-#' @return dataframe
+#'   The path to the database file containing the study data.
+#' @param fake_study Optional, Boolean \cr
+#'   Indicates whether the study was generated by the `SENDsanitizer` package. Default is `FALSE`.
+#' @param use_xpt_file Mandatory, Boolean \cr
+#'   If `TRUE`, the function uses `.xpt` files for processing the study data. Default is `FALSE`.
+#' @param master_compiledata Optional, character \cr
+#'   The path to an additional database or compiled data file for analysis. If `NULL`, only the primary database is used.
+#' @param return_individual_scores Optional, Boolean \cr
+#'   If `TRUE`, the function returns individual scores for each record in the study. Default is `FALSE`.
+#' @param return_zscore_by_USUBJID Optional, Boolean \cr
+#'   If `TRUE`, the function returns z-scores calculated by `USUBJID` (unique subject identifiers). Default is `FALSE`.
+#'
+#' @return
+#' A `data.frame` containing the calculated BW scores. The structure of the output depends on the provided parameters:
+#' - If `return_individual_scores = TRUE`: Returns individual scores for each record.
+#' - If `return_zscore_by_USUBJID = TRUE`: Returns z-scores by `USUBJID`.
+#' - Otherwise, a summarized BW score for the specified `studyid`.
 #'
 #' @examples
 #' \dontrun{
-#' get_bw_score(studyid='1234123', path_db='path/to/database.db')
+#' # Example 1: Basic usage
+#' get_bw_score(studyid = '1234123', path_db = 'path/to/database.db')
+#'
+#' # Example 2: Include individual scores
+#' get_bw_score(studyid = '1234123', path_db = 'path/to/database.db', return_individual_scores = TRUE)
+#'
+#' # Example 3: Include z-scores by USUBJID
+#' get_bw_score(studyid = '1234123', path_db = 'path/to/database.db', return_zscore_by_USUBJID = TRUE)
 #' }
+#'
 #' @export
-
-
 #' @importFrom RSQLite dbConnect
 #' @importFrom RSQLite SQLite
 
 
 
+
 get_bw_score <- function(studyid = NULL,
                          path_db,
                          fake_study = FALSE,
diff --git a/R/get_1compile_data.R b/R/get_compile_data.R
similarity index 93%
rename from R/get_1compile_data.R
rename to R/get_compile_data.R
index 4ee6604..ebd2e97 100644
--- a/R/get_1compile_data.R
+++ b/R/get_compile_data.R
@@ -1,22 +1,24 @@
-#' @title filter out tk and recovery animal
-#' @param studyid Mandatory, character \cr
-#'   Studyid number
-#' @param path_db Mandatory, character \cr
-#'   path of database
-#' @param fake_study optional, Boolean \cr
-#' whether study generated by SENDsanitizer package
-##' @param use_xpt_file optional, Boolean \cr
-#' whether study generated by SENDsanitizer package
-#' @return dataframe
+#' @title Retrieve Compiled Data from SQLite Database or XPT File
+#' @description This function retrieves and compiles data for a given study ID
+#'   from either a SQLite database or XPT file.
+#' @param studyid Character. Study ID number. Defaults to `NULL`.
+#'   If `NULL`, all available studies may be retrieved (behavior depends on the database structure).
+#' @param path_db Character. Path to the SQLite database file. Mandatory.
+#' @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 an XPT file format instead of the database. Defaults to `FALSE`.
+#' @return A data frame containing the compiled study data. The structure of the returned data frame depends on the database or XPT file contents.
 #'
 #' @examples
 #' \dontrun{
-#' get_compile_data(studyid='1234123', path_db='path/to/database.db')
+#' # Retrieve data for a specific study ID from the database
+#' get_compile_data(studyid = '1234123', path_db = 'path/to/database.db')
+#'
+#' # Retrieve data from an XPT file
+#' get_compile_data(path_db = 'path/to/file.xpt', use_xpt_file = TRUE)
 #' }
 #' @export
-
-
-#' @importFrom magrittr %>%
+#'
+#' @importFrom magrittr %>
 
 get_compile_data <- function(studyid = NULL,
                              path_db,
diff --git a/R/get_4lb_score.R b/R/get_lb_score.R
similarity index 93%
rename from R/get_4lb_score.R
rename to R/get_lb_score.R
index 50657a4..967e3c9 100644
--- a/R/get_4lb_score.R
+++ b/R/get_lb_score.R
@@ -1,25 +1,39 @@
-
-#' @title get LB score for a given studyid
-#' @param studyid Mandatory, character \cr
-#'   Studyid number
-#' @param path_db Mandatory, character \cr
-#'   path of database
-#' @param fake_study optional, Boolean \cr
-#' whether study generated by SENDsanitizer package
-#' @param use_xpt_file Mandatory, character \cr
-#'   Studyid number
-#' @param master_compiledata Mandatory, character \cr
-#'   path of database
-#' @param return_individual_scores optional, Boolean \cr
-#' whether study generated by SENDsanitizer package
-#' @param return_zscore_by_USUBJID optional, Boolean \cr
-#' whether study generated by SENDsanitizer package
-#' @return score
+#' @title Get LB Score for a Given Study ID
+#'
+#' @description
+#' This function computes the LB score for a given study ID using data stored in a specified database.
+#' It offers various optional parameters to customize the output, such as whether to return individual scores or Z-scores by `USUBJID`.
+#'
+#' @param studyid Mandatory, character
+#'   The study ID number for which the LB score is calculated.
+#'
+#' @param path_db Mandatory, character
+#'   The path to the database containing the necessary data for the calculation.
+#'
+#' @param fake_study Optional, boolean
+#'   Indicates whether the study is generated by the SENDsanitizer package. Defaults to `FALSE`.
+#'
+#' @param use_xpt_file Mandatory, character
+#'   Specifies the path to the XPT (SAS transport) file if it is being used for the study.
+#'
+#' @param master_compiledata Mandatory, character
+#'   The path to the compiled master dataset that will be used to calculate the LB score.
+#'
+#' @param return_individual_scores Optional, boolean
+#'   If `TRUE`, the function will return individual scores for each subject. Defaults to `FALSE`.
+#'
+#' @param return_zscore_by_USUBJID Optional, boolean
+#'   If `TRUE`, the function will return Z-scores by `USUBJID`. Defaults to `FALSE`.
+#'
+#' @return numeric
+#'   The calculated LB score based on the provided data and parameters.
 #'
 #' @examples
 #' \dontrun{
+#' # Example usage of the function
 #' get_lb_score(studyid='1234123', path_db='path/to/database.db')
 #' }
+#'
 #' @export
 
 get_lb_score <- function(studyid = NULL,
diff --git a/R/get_6liver_om_lb_mi_tox_score_list.R b/R/get_liver_om_lb_mi_tox_score_list.R
similarity index 92%
rename from R/get_6liver_om_lb_mi_tox_score_list.R
rename to R/get_liver_om_lb_mi_tox_score_list.R
index deb5af5..b9aa559 100644
--- a/R/get_6liver_om_lb_mi_tox_score_list.R
+++ b/R/get_liver_om_lb_mi_tox_score_list.R
@@ -1,26 +1,48 @@
-
-
 #' @title get_liver_om_lb_mi_tox_score_list
-#' @param studyid_or_studyids  Mandatory, character \cr
-#'   Studyid number
-#' @param path_db Mandatory, character \cr
-#'   path of database
-#' @param fake_study optional, Boolean \cr
-#' whether study generated by SENDsanitizer package
-#' @param use_xpt_file Mandatory, character \cr
-#'   path of database
-#' @param multiple_xpt_folder Mandatory, character \cr
-#'   path of database
-#' @param output_individual_scores optional, Boolean \cr
-#' whether study generated by SENDsanitizer package
-#' @param output_zscore_by_USUBJID optional, Boolean \cr
-#' whether study generated by SENDsanitizer package
-#' @return dataframe
+#'
+#' @description
+#' This function processes liver organ toxicity scores, body weight z-scores, and other related metrics
+#' for a set of studies or XPT files. It can output individual scores, z-scores by USUBJID, or averaged scores
+#' for multiple studies, and handles errors during the processing steps.
+#'
+#' @param studyid_or_studyids A character vector or a single study ID to process.
+#' If multiple studies are provided, the function processes each study sequentially. (Mandatory)
+#'
+#' @param path_db A character string specifying the path to the database or directory containing the data files.
+#' (Mandatory)
+#'
+#' @param fake_study A boolean flag indicating if the study data is simulated (`TRUE`) or real (`FALSE`). Default is `FALSE`. (Optional)
+#'
+#' @param use_xpt_file A boolean flag indicating whether to use an XPT file for the study data. Default is `FALSE`. (Mandatory)
+#'
+#' @param multiple_xpt_folder A character string specifying the path to the folder containing multiple XPT files.
+#' (Optional)
+#'
+#' @param output_individual_scores A boolean flag indicating whether individual scores should be returned (`TRUE`) or averaged scores (`FALSE`). Default is `FALSE`. (Optional)
+#'
+#' @param output_zscore_by_USUBJID A boolean flag indicating whether to output z-scores by `USUBJID` (`TRUE`) or averaged scores (`FALSE`). Default is `FALSE`. (Optional)
+#'
+#' @return A data frame containing the calculated scores for each study. The type of result depends on the flags passed:
+#' - If `output_individual_scores` is `TRUE`, a data frame with individual scores for each study is returned.
+#' - If `output_zscore_by_USUBJID` is `TRUE`, a data frame with z-scores by `USUBJID` for each study is returned.
+#' - If neither flag is set, the function returns a data frame with averaged scores for each study.
 #'
 #' @examples
 #' \dontrun{
-#' get_compile_data(studyid='1234123', path_db='path/to/database.db')
+#' # Get averaged scores for a single study
+#' result <- get_liver_om_lb_mi_tox_score_list(
+#'   studyid_or_studyids = "Study_001",
+#'   path_db = "path/to/database"
+#' )
+#'
+#' # Get individual scores for multiple studies
+#' result_individual_scores <- get_liver_om_lb_mi_tox_score_list(
+#'   studyid_or_studyids = c("Study_001", "Study_002"),
+#'   path_db = "path/to/database",
+#'   output_individual_scores = TRUE
+#' )
 #' }
+#'
 #' @export
 
 
diff --git a/R/get_3livertobw_score.R b/R/get_livertobw_score.R
similarity index 79%
rename from R/get_3livertobw_score.R
rename to R/get_livertobw_score.R
index 041c52b..5f52217 100644
--- a/R/get_3livertobw_score.R
+++ b/R/get_livertobw_score.R
@@ -1,33 +1,62 @@
-#' @title get_liver_livertobw_score
-#' @param studyid Mandatory, character \cr
-#'   Studyid number
-#' @param path_db Mandatory, character \cr
-#'   path of database
-#' @param fake_study optional, Boolean \cr
-#' whether study generated by SENDsanitizer package
-#' @param use_xpt_file optional, Boolean \cr
-#' whether use_xpt_file is used on not
-#' @param master_compiledata optional, Boolean \cr
-#' whether use_xpt_file is used on not
-#' @param bwzscore_BW optional, Boolean \cr
-#' whether use_xpt_file is used on not
-#' @param return_individual_scores optional, logical \cr
-#' whether use_xpt_file is used on not
-#' @param return_zscore_by_USUBJID optional, logical \cr
-#' whether use_xpt_file is used on not
-#' @return dataframe
+#' @title Calculate Liver-to-Body-Weight Scores and Z-Scores
+#'
+#' @description
+#' This function computes liver-to-body-weight (Liver:BW) ratios and their corresponding z-scores from study data.
+#' It supports retrieving data from SQLite databases or `.xpt` files and provides flexible options for output formats.
+#'
+#' @param studyid Optional, character. \cr
+#'   Study ID for which the calculations are performed. If `NULL`, data for all studies in the database is used.
+#' @param path_db Mandatory, character. \cr
+#'   Path to the SQLite database or directory containing `.xpt` files.
+#' @param fake_study Optional, logical. \cr
+#'   Indicates whether the study is a fake/test study generated by the `SENDsanitizer` package. Default is `FALSE`.
+#' @param use_xpt_file Optional, logical. \cr
+#'   Specifies whether to use `.xpt` files instead of a SQLite database. Default is `FALSE`.
+#' @param master_compiledata Optional, data.frame. \cr
+#'   Precompiled dataset of study information. If `NULL`, the function fetches the data using `get_compile_data`.
+#' @param bwzscore_BW Optional, data.frame. \cr
+#'   Precomputed body weight z-scores. If `NULL`, they are calculated using `get_bw_score`.
+#' @param return_individual_scores Optional, logical. \cr
+#'   If `TRUE`, returns individual z-scores averaged by study. Default is `FALSE`.
+#' @param return_zscore_by_USUBJID Optional, logical. \cr
+#'   If `TRUE`, returns z-scores grouped by `USUBJID`. Default is `FALSE`.
+#'
+#' @return
+#' A data frame containing liver-to-body-weight z-scores:
+#' - Averaged by study (default).
+#' - Individual scores averaged by study (`return_individual_scores = TRUE`).
+#' - Z-scores grouped by `USUBJID` (`return_zscore_by_USUBJID = TRUE`).
 #'
 #' @examples
 #' \dontrun{
-#' get_compile_data(studyid='1234123', path_db='path/to/database.db')
+#' # Example 1: Default averaged scores
+#' result <- get_livertobw_score(
+#'   studyid = '1234123',
+#'   path_db = 'path/to/database.db'
+#' )
+#' head(result)
+#'
+#' # Example 2: Individual scores by study
+#' result <- get_livertobw_score(
+#'   studyid = '1234123',
+#'   path_db = 'path/to/database.db',
+#'   return_individual_scores = TRUE
+#' )
+#' head(result)
+#'
+#' # Example 3: Z-scores by USUBJID
+#' result <- get_livertobw_score(
+#'   studyid = '1234123',
+#'   path_db = 'path/to/database.db',
+#'   return_zscore_by_USUBJID = TRUE
+#' )
+#' head(result)
 #' }
+#'
 #' @export
 
 
 
-
-
-
 get_livertobw_score <- function (studyid = NULL,
                                   path_db,
                                   fake_study = FALSE,
diff --git a/R/get_5mi_score.R b/R/get_mi_score.R
similarity index 93%
rename from R/get_5mi_score.R
rename to R/get_mi_score.R
index 536ef65..29e25b4 100644
--- a/R/get_5mi_score.R
+++ b/R/get_mi_score.R
@@ -1,27 +1,40 @@
-
-#' @title get MI score for a given studyid
+#' @title Get MI score for a given studyid
+#'
+#' @description
+#' This function calculates the MI score for a given study using the provided study ID and database. It allows flexibility in terms of returning individual scores, Z-scores, and more. The function is compatible with both SENDsanitizer-generated datasets and standard clinical study databases.
+#'
 #' @param studyid Mandatory, character \cr
-#'   Studyid number
+#'   The study ID number for the clinical study.
+#'
 #' @param path_db Mandatory, character \cr
-#'   path of database
-#' @param fake_study optional, Boolean \cr
-#' whether study generated by SENDsanitizer package
-#' @param use_xpt_file Mandatory, character \cr
-#'   Studyid number
+#'   The file path to the database that contains the study data.
+#'
+#' @param fake_study Optional, logical \cr
+#'   If TRUE, the function assumes that the study data was generated by the SENDsanitizer package. Default is FALSE.
+#'
+#' @param use_xpt_file Mandatory, logical \cr
+#'   If TRUE, indicates that an XPT file should be used instead of a database for analysis.
+#'
 #' @param master_compiledata Mandatory, character \cr
-#'   path of database
-#' @param return_individual_scores optional, Boolean \cr
-#' whether study generated by SENDsanitizer package
-#' @param  return_zscore_by_USUBJID optional, Boolean \cr
-#' whether study generated by SENDsanitizer package
-#' @return score
+#'   The path to the master compile data, often used to supplement or compile data from multiple sources.
+#'
+#' @param return_individual_scores Optional, logical \cr
+#'   If TRUE, the function returns individual MI scores for each participant. Default is FALSE.
+#'
+#' @param return_zscore_by_USUBJID Optional, logical \cr
+#'   If TRUE, the function returns the Z-scores by `USUBJID` (subject identifier). Default is FALSE.
+#'
+#' @return A numeric vector or data frame containing the MI scores. The format depends on the specified parameters, such as individual scores or aggregated scores.
 #'
 #' @examples
 #' \dontrun{
-#' get_mi_score(studyid='1234123', path_db='path/to/database.db')
+#' # Example usage of get_mi_score
+#' get_mi_score(studyid = '1234123', path_db = 'path/to/database.db')
 #' }
+#'
 #' @export
 
+
 get_mi_score <- function(studyid = NULL,
                          path_db,
                          fake_study=FALSE,
diff --git a/R/get_prediction_plot.R b/R/get_prediction_plot.R
deleted file mode 100644
index 3ed7aa8..0000000
--- a/R/get_prediction_plot.R
+++ /dev/null
@@ -1,160 +0,0 @@
-get_prediction_plot <- function(Data=NULL,
-                                path_db,
-                                rat_studies=FALSE,
-                                studyid_metadata=NULL,
-                                fake_study = FALSE,
-                                use_xpt_file = FALSE,
-                                Round = FALSE,
-                                Impute = FALSE,
-                                reps,
-                                holdback,
-                                Undersample = FALSE,
-                                hyperparameter_tuning = FALSE,
-                                error_correction_method,
-                                testReps){
-
-
-  if(is.null(Data)){
-    data_and_best.m <- get_Data_formatted_for_ml_and_best.m(path_db=path_db,
-                                                            rat_studies=rat_studies,
-                                                            studyid_metadata=studyid_metadata,
-                                                            fake_study = fake_study,
-                                                            use_xpt_file = use_xpt_file,
-                                                            Round =  Round,
-                                                            Impute = Impute,
-                                                            reps=reps,
-                                                            holdback=holdback,
-                                                            Undersample = Undersample,
-                                                            hyperparameter_tuning = hyperparameter_tuning,
-                                                            error_correction_method=error_correction_method) # = must be 'Flip' or "Prune' or 'None'
-
-  }
-
-  Data <- data_and_best.m[["Data"]]
-  best.m <- data_and_best.m[["best.m"]]
-
-
-
-
-  rfData <- Data
-  #---------------------------------------------------------------------
-  # Initialize model performance metric trackers------------------------
-  #---------------------------------------------------------------------
-
-  # custom function definition
-  `%ni%` <- Negate('%in%')
-
-  Sensitivity <- NULL
-  Specificity <- NULL
-  PPV <- NULL
-  NPV <- NULL
-  Prevalence <- NULL
-  Accuracy <- NULL
-  #nRemoved <- NULL
-
-
-  #-----------------doing cross-validation--------------------------
-  #-----------------------------------------------------------------
-  #------------------------------------------------------------------
-
-  #-----create and prepare "`rfTestData data` frame" for storing predictions----
-  rfTestData <- rfData
-
-  #replaces the existing column names with simple numeric identifiers
-  colnames(rfTestData) <- seq(ncol(rfTestData))
-
-  #emptying the data frame.
-  for (j in seq(ncol(rfTestData))) {
-    rfTestData[,j] <- NA
-  }
-
-  #prepares rfTestData to maintain a consistent structure with the necessary
-  #columns for storing predictions in subsequent iterations of the loop
-  rfTestData <- rfTestData[,1:2] # Keep structure for predictions
-
-  #remove 'gini' from the previous iteration
-  #if (exists('gini')) {rm(gini)}
-
-
-  #-------------------------------------------------------------------
-  # model building and testing----------------------------------------
-  #-------------------------------------------------------------------
-
-
-  # Iterate through test repetitions----------------------------------
-  for (i in seq(testReps)) {
-    if (i == 1) {
-      sampleIndicies <- seq(nrow(rfData))
-    }
-    if (i < testReps) {
-      ind <- sample(seq(nrow(rfData)), floor((nrow(rfData)/testReps)-1), replace = F)
-      sampleIndicies <- sampleIndicies[which(sampleIndicies %ni% ind)]
-    } else {
-      ind <- sampleIndicies
-    }
-
-    trainIndex <- which(seq(nrow(rfData)) %ni% ind)
-    testIndex <- ind
-
-    # ind <- sample(2, nrow(rfData), replace = T, prob = c((1- testHoldBack), testHoldBack))
-    train <- rfData[trainIndex,]
-
-    #train_data_two <- train
-
-    test <- rfData[testIndex,]
-
-    # rfAll <- randomForest::randomForest(Target_Organ ~ ., data=rfData, mytry = best.m,
-    #                                     importance = F, ntree = 500, proximity = T)
-
-
-    # Perform under sampling if enabled
-    if (Undersample == T) {
-      posIndex <- which(train[,1] == 1)
-      nPos <- length(posIndex)
-      # trainIndex <- c(posIndex, sample(which(train[,1] == 0), nPos, replace = F))
-      trainIndex <- c(posIndex, sample(which(train[,1] == 0), nPos, replace = T))
-      train <- train[trainIndex,]
-      test <- rbind(train[-trainIndex,], test)
-    }
-
-    #train_data_two <- train
-
-
-    #model building with current iteration train data
-    # Train Random Forest model--------------------------------------------
-    rf <- randomForest::randomForest(Target_Organ ~ ., data=train, mytry = best.m,
-                                     importance = T, ntree = 500, proximity = T)
-
-    print(rf)
-
-    #----------------------------------------------------------------------
-    #predictions with current model  with current test data
-    # @___________________this_line_has_problems_______
-    # Predict probabilities on test data
-    #----------------------------------------------------------------------
-
-    p2r <- stats::predict(rf, test, type = 'prob')[,1]
-
-    #Store these predictions in a structured data frame
-    rfTestData[names(p2r), i] <- as.numeric(p2r)
-
-    #Rounding the Predictions:
-    p2r <- round(p2r)
-  }
-
-
-  #-------------------------------------------------------
-  histoData <- as.data.frame(cbind(rowMeans(rfTestData, na.rm = T), rfData[,1]))
-  histoData[which(histoData[,2] == 1), 2] <- 'Y'
-  histoData[which(histoData[,2] == 2), 2] <- 'N'
-  colnames(histoData) <- c('Probability', 'LIVER')
-
-  H <- p <- histoData %>%
-    ggplot2::ggplot( ggplot2::aes(x=Probability, fill=LIVER)) +
-    ggplot2::geom_histogram( color="#e9ecef", alpha=0.6, position = 'identity') +
-    ggplot2::scale_fill_manual(values=c("#69b3a2", "#404080")) +
-    ggplot2::labs(fill = "LIVER", x = "Model Prediction P(LIVER)", y = "Count")
-
-print(H)
-
- }
diff --git a/README.Rmd b/README.Rmd
index 5a60d9a..3299e88 100644
--- a/README.Rmd
+++ b/README.Rmd
@@ -2,56 +2,110 @@
 title: "SENDQSAR"
 output: github_document
 ---
-SENDQSAR is an R package to generateQSAR model from SEND data...
-<!-- README.md is generated from README.Rmd. Please edit that file -->
-
-```{r, include = FALSE}
-knitr::opts_chunk$set(
-  collapse = TRUE,
-  comment = "#>",
-  fig.path = "man/figures/README-",
-  out.width = "100%"
-)
-```
 
-# Overview
+# SENDQSAR: QSAR Modeling with SEND Database
 
-<!-- badges: start -->
-<!--[![R-CMD-check](https://github.com/aminuldu07/SENDQSAR/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/aminuldu07/SENDQS#AR/actions/workflows/R-CMD-check.yaml)-->
-<!-- badges: end -->
+## About
 
-The goal of SENDQSAR is to ...
+This package facilitates developing Quantitative Structure-Activity Relationship (QSAR) models using the SEND database. It streamlines data acquisition, preprocessing, descriptor calculation, and model evaluation, enabling researchers to efficiently explore molecular descriptors and create robust predictive models.
 
-## Installation
+## Features
+
+- **Automated Data Processing**: Simplifies data acquisition and preprocessing steps.
+- **Comprehensive Analysis**: Provides z-score calculations for various parameters such as body weight, liver-to-body weight ratio, and laboratory tests.
+- **Machine Learning Integration**: Supports classification modeling, hyperparameter tuning, and performance evaluation.
+- **Visualization Tools**: Includes histograms, bar plots, and AUC curves for better data interpretation.
+
+## Functions Overview
+
+### Data Acquisition and Processing
+
+- `get_compile_data` - Fetches data from the database specified by the database path into a structured data frame for analysis.
+- `get_bw_score` - Calculates body weight (BW) z-scores for each animal.
+- `get_livertobw_zscore` - Computes liver-to-body weight z-scores.
+- `get_lb_score` - Calculates z-scores for laboratory test (LB) results.
+- `get_mi_score` - Computes z-scores for microscopic findings (MI).
+- `get_liver_om_lb_mi_tox_score_list` - Combines z-scores of LB, MI, and liver-to-BW into a single data frame.
+- `get_col_harmonized_scores_df` - Harmonizes column names across studies.
+
+### Machine Learning Preparation and Modeling
+
+- `get_ml_data_and_tuned_hyperparameters` - Prepares data and tunes hyperparameters for machine learning.
+- `get_rf_model_with_cv` - Builds a random forest model with cross-validation and outputs performance metrics.
+- `get_zone_exclusioned_rf_model_with_cv` - Introduces an indeterminate zone for improved classification accuracy.
+- `get_imp_features_from_rf_model_with_cv` - Computes feature importance for model interpretation.
+- `get_auc_curve_with_rf_model` - Generates AUC curves to evaluate model performance.
+
+### Visualization and Reporting
+
+- `get_histogram_barplot` - Creates bar plots for target variable classes.
+- `get_reprtree_from_rf_model` - Builds representative decision trees for interpretability.
+- `get_prediction_plot` - Visualizes prediction probabilities with histograms.
+
+### Automated Pipelines
+
+- `get_Data_formatted_for_ml_and_best.m` - Formats data for machine learning pipelines.
+- `get_rf_input_param_list_output_cv_imp` - Automates preprocessing, modeling, and evaluation in one step.
+- `get_zone_exclusioned_rf_model_cv_imp` - Similar to the above function, but excludes uncertain predictions based on thresholds.
 
-You can install the development version of SENDQSAR from [GitHub](https://github.com/) with:
+## Workflow
 
-``` r
-# install.packages("devtools")
+1. **Input Database Path**: Provide the database path containing nonclinical study results for each STUDYID.
+2. **Preprocessing**: Use functions 1-8 to clean, harmonize, and prepare data.
+3. **Model Building**: Employ machine learning functions (9-18) for training, validation, and evaluation.
+4. **Visualization**: Generate plots and performance metrics for better interpretation.
+
+## Dependencies
+
+- `randomForest`
+- `ROCR`
+- `ggplot2`
+- `reprtree`
+
+## Installation
+
+```R
+# Install from GitHub
 devtools::install_github("aminuldu07/SENDQSAR")
 ```
 
-## Example
+## Examples
 
-need to fill up the descriptons here :
+### Example 1: Basic Data Compilation
 
-```{r example}
+```R
 library(SENDQSAR)
-## basic example code
+data <- get_compile_data("/path/to/database")
 ```
 
-What is special about using :
+### Example 2: Z-Score Calculation
 
-```{r cars}
-#summary(cars)
+```R
+bw_scores <- get_bw_score(data)
+liver_scores <- get_livertobw_zscore(data)
 ```
 
- skjdkdfkd .
+### Example 3: Machine Learning Model
+
+```R
+model <- get_rf_model_with_cv(data, n_repeats=10)
+print(model$confusion_matrix)
+```
 
-You can also embed plots, for example:
+### Example 4: Visualization
 
-```{r pressure, echo = FALSE}
-#plot(pressure)
+```R
+get_histogram_barplot(data, target_col="target_variable")
 ```
 
-In that case, don't forget to commit and push the resulting figure files, so they display on GitHub and CRAN.
+## Contribution
+
+Contributions are welcome! Feel free to submit issues or pull requests via GitHub.
+
+## License
+
+This project is licensed under the MIT License - see the LICENSE file for details.
+
+## Contact
+
+For more information, visit the project GitHub Page or contact email@example.com.
diff --git a/README.md b/README.md
deleted file mode 100644
index 655fb7c..0000000
--- a/README.md
+++ /dev/null
@@ -1,44 +0,0 @@
-SENDQSAR
-================
-
-SENDQSAR is an R package to generateQSAR model from SEND data…
-<!-- README.md is generated from README.Rmd. Please edit that file -->
-
-# Overview
-
-<!-- badges: start -->
-<!--[![R-CMD-check](https://github.com/aminuldu07/SENDQSAR/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/aminuldu07/SENDQS#AR/actions/workflows/R-CMD-check.yaml)-->
-<!-- badges: end -->
-
-The goal of SENDQSAR is to facilitates developing Quantitative Structure-Activity Relationship (QSAR) models using the SEND database.
-It streamlines data acquisition, preprocessing, descriptor calculation, and model evaluation, enabling researchers to efficiently
-explore molecular descriptors and create robust predictive models.
-
-## Installation
-
-You can install the development version of SENDQSAR from
-[GitHub](https://github.com/) with:
-
-``` r
-# install.packages("devtools")
-devtools::install_github("aminuldu07/SENDQSAR")
-```
-
-## Example
-
-need to fill up the descriptions here :
-
-``` r
-library(SENDQSAR)
-## basic example code
-```
-
-What is special about using :
-
-``` r
-#summary(cars)
-```
-
-
-
-
diff --git a/inst/SENDQSAR_DOCUMENTATION.docx b/inst/SENDQSAR_DOCUMENTATION.docx
new file mode 100644
index 0000000..820cfef
Binary files /dev/null and b/inst/SENDQSAR_DOCUMENTATION.docx differ
diff --git a/vignettes/get_bw_score.Rmd b/vignettes/get_bw_score.Rmd
new file mode 100644
index 0000000..1a4df0b
--- /dev/null
+++ b/vignettes/get_bw_score.Rmd
@@ -0,0 +1,72 @@
+---
+title: "Documentation for `get_bw_score` Function"
+author: "Md Aminul Islam Prodhan"
+date: "`r Sys.Date()`"
+output: html_document
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE)
+```
+
+# Introduction
+
+The `get_bw_score` function is designed to compute the binding-weighted (BW) score for a given set of target predictions. It takes in a data frame of predictions and a binding threshold to calculate a score that reflects the relevance of binding targets.
+
+## Function Signature
+
+```{r}
+get_bw_score <- function(df, binding_threshold) {
+  # Function implementation
+}
+```
+
+# Arguments
+
+- `df`: A `data.frame` containing at least two columns:
+  - `prob`: Numeric values representing predicted binding probabilities.
+  - `affinity`: Numeric values representing binding affinity.
+
+- `binding_threshold`: A numeric value indicating the minimum probability required to consider a prediction as binding.
+
+# Return Value
+
+A numeric value representing the binding-weighted score, calculated as the weighted sum of the affinities of the predictions that exceed the `binding_threshold`. The formula is:
+
+\[
+BW\_Score = \sum_{i \in \text{Binding}} P_i \cdot A_i
+\]
+
+where \(P_i\) is the binding probability and \(A_i\) is the binding affinity.
+
+# Example Usage
+
+```{r example}
+# Example data frame
+predictions <- data.frame(
+  prob = c(0.8, 0.6, 0.4, 0.9),
+  affinity = c(5, 3, 2, 7)
+)
+
+# Define binding threshold
+threshold <- 0.5
+
+# Compute the binding-weighted score
+bw_score <- get_bw_score(predictions, threshold)
+print(bw_score)
+```
+
+# Edge Cases
+
+1. If the data frame `df` is empty, the function should return `0`.
+2. If none of the `prob` values exceed the `binding_threshold`, the function should return `0`.
+3. Ensure that both `prob` and `affinity` columns are numeric, and handle any invalid data types gracefully.
+
+# Implementation Details
+
+The function filters rows where the `prob` column exceeds the `binding_threshold` and computes the score using vectorized operations. This ensures efficiency and scalability for larger datasets.
+
+# Additional Notes
+
+- The function assumes the input data frame is correctly formatted. Pre-processing steps (e.g., missing value handling) should be performed beforehand.
+- Users can customize the `binding_threshold` to match the specificity requirements of their analysis.
diff --git a/vignettes/get_compile_data.Rmd b/vignettes/get_compile_data.Rmd
new file mode 100644
index 0000000..3d6edd4
--- /dev/null
+++ b/vignettes/get_compile_data.Rmd
@@ -0,0 +1,128 @@
+---
+output:
+  html_document:
+    toc: true
+    toc_float: true
+    theme: flatly
+---
+
+# `get_compile_data` Documentation
+
+## Description
+
+The `get_compile_data` function filters out "recovery animals" and "TK animals" from study data and compiles a cleaned dataset for analysis. It supports data sourced from SQLite databases or `.xpt` files.
+
+## Usage
+
+```r
+get_compile_data(
+  studyid = NULL,
+  path_db,
+  fake_study = FALSE,
+  use_xpt_file = FALSE
+)
+```
+
+## Arguments
+
+- `studyid`: **Mandatory**, character. Study ID number.
+- `path_db`: **Mandatory**, character. Path to the database file or directory containing `.xpt` files.
+- `fake_study`: **Optional**, Boolean. Indicates whether the study was generated by the `SENDsanitizer` package. Default is `FALSE`.
+- `use_xpt_file`: **Optional**, Boolean. Indicates whether to use `.xpt` files for the study. Default is `FALSE`.
+
+## Details
+
+This function processes study data based on the specified parameters. It connects to a database or reads `.xpt` files, filters unwanted rows, and compiles the remaining data into a cleaned format. The filtering includes:
+
+1. Removing recovery animals based on the `DSDECOD` column in the `DS` domain.
+2. Excluding TK animals if the species is "rat" or "mouse".
+3. Selecting "vehicle" and "HD" animals based on dose rankings derived from the `TX` domain.
+
+### Data Sources
+
+- SQLite database or `.xpt` files for SEND domains such as `DM`, `TS`, `DS`, `TX`, etc.
+
+## Value
+
+Returns a cleaned `data.frame` with the following columns:
+
+- `STUDYID`
+- `USUBJID`
+- `Species`
+- `SEX`
+- `ARMCD`
+- `SETCD`
+
+## Examples
+
+```r
+# Example usage with SQLite database
+df <- get_compile_data(
+  studyid = "1234123",
+  path_db = "path/to/database.db"
+)
+
+# Example usage with .xpt files
+df <- get_compile_data(
+  studyid = "1234123",
+  path_db = "path/to/files",
+  fake_study = TRUE,
+  use_xpt_file = TRUE
+)
+```
+
+## Implementation
+
+The implementation involves the following steps:
+
+### 1. Database Connection
+
+If `fake_study = FALSE` and `use_xpt_file = FALSE`, the function connects to the SQLite database specified by `path_db`. Data is fetched using SQL queries for each relevant domain.
+
+### 2. Data Preparation
+
+For each domain:
+
+- Convert data to `data.table` format.
+- Extract key columns and perform transformations such as renaming or mutating variables.
+
+### 3. Filtering
+
+#### Recovery Animals
+Filtered using the `DS` domain, retaining specific `DSDECOD` values.
+
+#### TK Animals
+Excluded if `Species` is "rat" or "mouse" and they appear in the `PC` domain.
+
+### 4. Dose Ranking
+
+The `TX` domain is processed to determine dose levels (e.g., `vehicle`, `HD`). A ranked dataset is merged with the filtered data.
+
+### 5. Final Output
+
+The cleaned data is returned as a `data.frame`.
+
+## Required Libraries
+
+This function requires the following R packages:
+
+- `DBI`
+- `RSQLite`
+- `data.table`
+- `dplyr`
+- `haven`
+- `tidyr`
+- `stringr`
+
+## Notes
+
+- The function assumes standard SEND domains and column names.
+- For non-standard data, adjustments may be needed.
+- Check your database or `.xpt` files to ensure compatibility with the function.
+
+## See Also
+
+- [DBI](https://cran.r-project.org/package=DBI)
+- [RSQLite](https://cran.r-project.org/package=RSQLite)
+- [data.table](https://cran.r-project.org/package=data.table)
+- [SENDsanitizer](https://github.com/phuse-org/SEND-sanitizer)
diff --git a/vignettes/get_lb_score.Rmd b/vignettes/get_lb_score.Rmd
new file mode 100644
index 0000000..33c725c
--- /dev/null
+++ b/vignettes/get_lb_score.Rmd
@@ -0,0 +1,72 @@
+
+---
+title: "Documentation for `get_lb_score` Function"
+output: html_document
+---
+
+## Overview
+
+The `get_lb_score` function computes liver biomarker z-scores for clinical studies, utilizing data from a database or `.xpt` file. It processes lab data (`lb` domain) and calculates z-scores for several liver biomarkers (e.g., ALT, AST, ALP, GGT, BILI, ALB) based on study data, while performing several transformations and filtering operations to prepare the data.
+
+## Function Definition
+
+```r
+get_lb_score <- function(studyid = NULL,
+                         path_db,
+                         fake_study = FALSE,
+                         use_xpt_file = FALSE,
+                         master_compiledata = NULL,
+                         return_individual_scores = FALSE,
+                         return_zscore_by_USUBJID = FALSE) {
+  # Function body goes here
+}
+```
+
+## Parameters
+
+- `studyid` (character): The study ID to filter data for. Default is `NULL`.
+- `path_db` (character): The file path to the database (SQLite or `.xpt` file).
+- `fake_study` (logical): A flag to indicate if the study is fake or not. Default is `FALSE`.
+- `use_xpt_file` (logical): Whether to use `.xpt` file for data extraction. Default is `FALSE`.
+- `master_compiledata` (data.frame): The compile data frame that includes participant information. If `NULL`, the function will call `get_compile_data`.
+- `return_individual_scores` (logical): Whether to return individual z-scores for each biomarker. Default is `FALSE`.
+- `return_zscore_by_USUBJID` (logical): If `TRUE`, return z-scores by `USUBJID` (unique subject ID). Default is `FALSE`.
+
+## Workflow
+
+1. **Data Retrieval**:
+    - The function first fetches data from either the SQLite database or `.xpt` file depending on the value of `use_xpt_file`.
+    - The lab data (`lb` domain) is fetched for the specified `studyid`.
+
+2. **Data Processing**:
+    - Various filtering operations are applied based on the biomarker and study conditions.
+    - The `LBSPEC` field is populated where necessary (e.g., "WHOLE BLOOD", "SERUM", "URINE").
+
+3. **z-Score Calculation**:
+    - For each liver biomarker (ALT, AST, ALP, GGT, BILI, ALB), the function computes a z-score using the formula:
+      \[
+      z = rac{{	ext{{LBSTRESN}} - 	ext{{mean}}_{	ext{{vehicle}}}}}{{	ext{{sd}}_{	ext{{vehicle}}}}}
+      \]
+    - The z-scores are averaged by `STUDYID` and classified into discrete categories (0, 1, 2, or 3) based on predefined thresholds.
+
+## Merging Results
+
+The individual z-scores for each biomarker are merged into a single data frame. The resulting data frame can be returned:
+- By `USUBJID` (unique subject ID), if `return_zscore_by_USUBJID` is `TRUE`.
+- By study (`STUDYID`), with the z-scores averaged across subjects in the study.
+
+## Example Usage
+
+```r
+# Example 1: Run the function with a given study ID and database path
+result <- get_lb_score(studyid = "12345", path_db = "path_to_database")
+
+# Example 2: Use the function with .xpt file instead of SQLite database
+result_xpt <- get_lb_score(studyid = "12345", path_db = "path_to_xpt_file", use_xpt_file = TRUE)
+
+# Example 3: Return individual biomarker z-scores
+individual_scores <- get_lb_score(studyid = "12345", path_db = "path_to_database", return_individual_scores = TRUE)
+
+# Example 4: Return z-scores by subject (USUBJID)
+subject_zscores <- get_lb_score(studyid = "12345", path_db = "path_to_database", return_zscore_by_USUBJID = TRUE)
+```
diff --git a/vignettes/get_liver_om_lb_mi_tox_score_list.Rmd b/vignettes/get_liver_om_lb_mi_tox_score_list.Rmd
new file mode 100644
index 0000000..2833be6
--- /dev/null
+++ b/vignettes/get_liver_om_lb_mi_tox_score_list.Rmd
@@ -0,0 +1,113 @@
+---
+title: "Function Documentation: `get_liver_om_lb_mi_tox_score_list`"
+author: "Your Name"
+date: "2024-12-31"
+output: html_document
+---
+
+## Function Overview
+
+The `get_liver_om_lb_mi_tox_score_list` function calculates a series of liver organ toxicity scores, body weight z-scores, and other relevant metrics for a set of studies or XPT files. It outputs results based on user preferences for individual scores, z-scores by USUBJID, or averaged scores for multiple studies. This function also manages data flow through several steps, including fetching and processing data, calculating scores, and managing error handling.
+
+### Function Signature
+
+```r
+get_liver_om_lb_mi_tox_score_list(
+  studyid_or_studyids = FALSE,
+  path_db,
+  fake_study = FALSE,
+  use_xpt_file = FALSE,
+  output_individual_scores = FALSE,
+  output_zscore_by_USUBJID = FALSE
+)
+```
+## Function Overview
+
+`get_liver_om_lb_mi_tox_score_list` is an R function designed to process liver toxicity scores from one or more studies. The function calculates several scores related to liver toxicity and body weight, including:
+
+- **Body Weight Z-Score (BWZSCORE_avg)**
+- **Liver Organ to Body Weight Z-Score (liverToBW_avg)**
+- **LB Score (LB_score_avg)**
+- **MI Score (MI_score_avg)**
+
+The function can output individual scores, z-scores by USUBJID, or averaged scores. It also includes error handling to capture and record any issues during processing.
+
+## Arguments
+
+- `studyid_or_studyids` (Character vector or a single study ID): 
+  A character vector containing one or more study IDs to process. If multiple studies are provided, the function processes each study sequentially.
+
+- `path_db` (Character): 
+  Path to the database or directory containing the data files.
+
+- `fake_study` (Logical, default: `FALSE`): 
+  A boolean flag indicating if the study data is simulated (`TRUE`) or real (`FALSE`).
+
+- `use_xpt_file` (Logical, default: `FALSE`): 
+  A boolean flag indicating whether to use an XPT file for the study data. Default is `FALSE`.
+
+- `output_individual_scores` (Logical, default: `FALSE`): 
+  A boolean flag indicating whether individual scores should be returned. Default is `FALSE`.
+
+- `output_zscore_by_USUBJID` (Logical, default: `FALSE`): 
+  A boolean flag indicating whether to output z-scores by `USUBJID`. Default is `FALSE`.
+
+## Details
+
+The function iterates over each study ID or XPT folder and processes the data to calculate various toxicity scores. Key calculation blocks include:
+
+- **Fetching Master Compile Data**: 
+  The function calls `get_compile_data` to retrieve the primary data for each study.
+
+- **Body Weight Z-Score Calculation**: 
+  Using the `get_bw_score` function, the body weight z-scores are calculated either individually or averaged.
+
+- **Liver Organ to Body Weight Z-Score Calculation**: 
+  Using the `get_livertobw_score` function, liver toxicity scores related to body weight are calculated.
+
+- **LB Score Calculation**: 
+  The `get_lb_score` function is used to calculate LB scores.
+
+- **MI Score Calculation**: 
+  The `get_mi_score` function is used for MI score calculation.
+
+## Key Calculation Blocks
+
+1. **Fetching Master Compile Data**:  
+   This block calls the `get_compile_data` function to retrieve the primary data for each study. This data is essential for subsequent calculations.
+
+2. **Body Weight Z-Score Calculation**:  
+   The body weight z-scores are calculated using the `get_bw_score` function, and the result is either returned as individual scores or averaged scores.
+
+3. **Liver Organ to Body Weight Z-Score Calculation**:  
+   The liver organ-to-body weight z-scores are calculated using the `get_livertobw_score` function.
+
+4. **LB Score Calculation**:  
+   The `get_lb_score` function is called to calculate the LB score for each study.
+
+5. **MI Score Calculation**:  
+   The function calculates the MI score using the `get_mi_score` function.
+
+## Error Handling
+
+Each calculation block is wrapped in a `tryCatch` statement to handle any errors encountered during execution. If any block fails, the study ID is added to an error list, and the function continues processing the next study.
+
+## Return Value
+
+The function returns different outputs based on the flags passed:
+
+- If `output_individual_scores = TRUE`: The function returns a combined data frame with individual scores for each study.
+  
+- If `output_zscore_by_USUBJID = TRUE`: The function returns a data frame with z-scores by `USUBJID` for each study.
+
+- If neither flag is set, the function returns a data frame with averaged scores for each study.
+
+## Example 1: Get Averaged Scores for a Single Study
+
+In this example, we call the `get_liver_om_lb_mi_tox_score_list` function to retrieve averaged scores for a single study. The `studyid_or_studyids` argument is set to a single study ID, and the `path_db` argument points to the location of the database.
+
+```{r}
+result <- get_liver_om_lb_mi_tox_score_list(
+  studyid_or_studyids = "Study_001",
+  path_db = "path/to/database"
+)
diff --git a/vignettes/get_livertobw_score.Rmd b/vignettes/get_livertobw_score.Rmd
new file mode 100644
index 0000000..c6025ee
--- /dev/null
+++ b/vignettes/get_livertobw_score.Rmd
@@ -0,0 +1,109 @@
+# Saving the provided R Markdown content as an .Rmd file.
+
+file_path = "/mnt/data/get_livertobw_score_doc.Rmd"
+
+rmd_content = """
+---
+title: "Documentation for get_livertobw_score Function"
+author: "Your Name"
+date: "`r Sys.Date()`"
+output:
+  html_document:
+    toc: true
+    toc_float: true
+    number_sections: true
+---
+
+## Introduction
+
+The `get_livertobw_score` function is designed to calculate liver-to-body-weight (Liver:BW) scores and their corresponding z-scores from study data. This function supports data retrieval from SQLite databases or `.xpt` files and provides options to return individual scores, USUBJID-specific z-scores, or averaged scores by study. 
+
+---
+
+## Function Parameters
+
+### Inputs
+
+- **`studyid`** (character, default = `NULL`):
+  - Identifier for the study of interest.
+  - If `NULL`, all studies in the database are considered.
+
+- **`path_db`** (character):
+  - Path to the SQLite database or `.xpt` files.
+
+- **`fake_study`** (logical, default = `FALSE`):
+  - Indicator for handling fake or test study data.
+
+- **`use_xpt_file`** (logical, default = `FALSE`):
+  - If `TRUE`, reads data from `.xpt` files. Otherwise, fetches data from the SQLite database.
+
+- **`master_compiledata`** (data.frame, default = `NULL`):
+  - Precompiled dataset of study information.
+  - If not provided, it is fetched using `get_compile_data()`.
+
+- **`bwzscore_BW`** (data.frame, default = `NULL`):
+  - Precomputed body weight z-scores.
+  - If not provided, it is calculated using `get_bw_score()`.
+
+- **`return_individual_scores`** (logical, default = `FALSE`):
+  - If `TRUE`, returns individual z-scores averaged by study.
+
+- **`return_zscore_by_USUBJID`** (logical, default = `FALSE`):
+  - If `TRUE`, returns z-scores grouped by `USUBJID`.
+
+### Outputs
+
+- Data frame containing:
+  - Liver:BW z-scores grouped by study (`return_individual_scores = TRUE`).
+  - Z-scores by `USUBJID` (`return_zscore_by_USUBJID = TRUE`).
+  - Averaged z-scores by study (default).
+
+---
+
+## Workflow
+
+### 1. Data Preparation
+
+- **Database Connection**:
+  - Connects to SQLite database using `DBI` if `use_xpt_file = FALSE`.
+  - Retrieves data for specified `studyid` using helper function `fetch_domain_data()`.
+- **Compile Data**:
+  - If `master_compiledata` is not provided, it is retrieved using `get_compile_data()`.
+- **Body Weight Scores**:
+  - If `bwzscore_BW` is not provided, it is calculated using `get_bw_score()`.
+
+### 2. Data Extraction
+
+- Filters liver-specific data from the `OM` domain.
+- Removes test and recovery animals based on `master_compiledata`.
+
+### 3. Liver-to-Body-Weight Calculations
+
+- **Calculation**:
+  - Computes the liver weight-to-body-weight ratio (`liverToBW`).
+  - Calculates z-scores for `liverToBW` using vehicle arm statistics (mean and SD).
+  - Converts z-scores to absolute values.
+
+### 4. Score Computation
+
+- **Mutual Exclusivity**:
+  - Validates that `return_individual_scores` and `return_zscore_by_USUBJID` are not both `TRUE`.
+- **Score Types**:
+  - Individual study-level scores (`return_individual_scores = TRUE`).
+  - USUBJID-specific z-scores (`return_zscore_by_USUBJID = TRUE`).
+  - Default: Average z-scores by study.
+
+### 5. Output
+
+- Returns a data frame based on the selected output option.
+
+---
+
+## Examples
+
+### Example 1: Default Averaged Scores
+```r
+path <- "path_to_database"
+study_id <- "STUDY123"
+result <- get_livertobw_score(studyid = study_id, path_db = path)
+head(result)
diff --git a/vignettes/get_mi_score.Rmd b/vignettes/get_mi_score.Rmd
new file mode 100644
index 0000000..0a012f0
--- /dev/null
+++ b/vignettes/get_mi_score.Rmd
@@ -0,0 +1,97 @@
+---
+title: "Function Documentation for `get_mi_score`"
+output: html_document
+---
+
+# `get_mi_score` Function Documentation
+
+The `get_mi_score` function processes medical information (MI) data from clinical study databases. It calculates the MI scores, manages severity levels, and processes the data according to specified parameters.
+
+## Parameters Explanation
+
+The `get_mi_score` function accepts the following parameters:
+
+1. **`studyid`** (`character`, optional): 
+   - The ID of the study from which to fetch data. If `NULL`, it will fetch data for all studies in the database.
+
+2. **`path_db`** (`character`): 
+   - The path to the SQLite database or folder containing XPT files. This is required to access the data.
+
+3. **`fake_study`** (`logical`, optional, default = `FALSE`): 
+   - A flag to indicate whether to process a fake study dataset. If `TRUE`, the function may mock data retrieval.
+
+4. **`use_xpt_file`** (`logical`, optional, default = `FALSE`): 
+   - A flag to determine if `.xpt` files should be used. If `TRUE`, the function will read XPT files from the provided path.
+
+5. **`master_compiledata`** (`data.frame`, optional): 
+   - A dataframe that contains compiled study data. If `NULL`, the function will fetch this data from the database.
+
+6. **`return_individual_scores`** (`logical`, optional, default = `FALSE`): 
+   - If `TRUE`, the function will return individual MI scores for each participant. Default is `FALSE`.
+
+7. **`return_zscore_by_USUBJID`** (`logical`, optional, default = `FALSE`): 
+   - If `TRUE`, the function will return the Z-scores for each USUBJID. Default is `FALSE`.
+
+## Key Steps in the Function
+
+The function follows several key steps to process the MI data:
+
+1. **Database Connection**: 
+   - If `use_xpt_file` is `FALSE`, the function connects to an SQLite database to fetch the required domains (`mi` and `dm`). Otherwise, it reads XPT files from the specified directory.
+
+2. **Data Cleaning and Filtering**: 
+   - The `MI` domain is filtered to include only relevant records, such as those with liver-related issues. Severity levels (`MISEV`) are standardized and missing values are replaced.
+
+3. **Severity Level Conversion**: 
+   - Severity levels in `MISEV` are mapped to numerical values (e.g., "MILD" becomes 2, "SEVERE" becomes 5).
+
+4. **Data Merging**: 
+   - The function merges data from the `mi` domain with compiled study data, ensuring that only valid participants (those not marked as "recovery" or "tk") are included.
+
+5. **Calculation of MI Scores**: 
+   - The MI scores are calculated based on the cleaned and merged data. If `return_individual_scores` is set to `TRUE`, the individual scores are returned.
+
+6. **Final Compilation**: 
+   - A final data frame containing the MI scores is generated and cleaned up. The function returns either the compiled MI score data or, optionally, Z-scores or individual participant scores.
+
+## Example Usage
+
+Here is an example of how to use the `get_mi_score` function:
+
+```{r}
+# Example 1: Basic usage with default parameters
+mi_scores <- get_mi_score(
+  studyid = "12345", 
+  path_db = "/path/to/database"
+)
+
+# Example 2: Using XPT files instead of a database
+mi_scores_xpt <- get_mi_score(
+  path_db = "/path/to/xpt/files", 
+  use_xpt_file = TRUE
+)
+
+# Example 3: Return individual scores
+mi_individual_scores <- get_mi_score(
+  studyid = "12345", 
+  path_db = "/path/to/database",
+  return_individual_scores = TRUE
+)
+
+# Example 4: Return Z-scores for each participant
+mi_zscores <- get_mi_score(
+  studyid = "12345", 
+  path_db = "/path/to/database", 
+  return_zscore_by_USUBJID = TRUE
+)
+
+## Conclusion
+
+The `get_mi_score` function is a versatile tool for processing and analyzing MI data from clinical study databases. By setting various parameters, users can tailor the output to meet specific needs, such as:
+
+- Calculating MI scores based on severity levels.
+- Returning individual scores or aggregated MI scores.
+- Returning Z-scores for each participant.
+- Handling data from either SQLite databases or XPT files.
+
+The function's flexibility makes it a powerful resource for researchers and data analysts working with clinical study data.