updates

R/CalculatePercentage.R

@@ -1,14 +1,16 @@
-#' Calculate the percentage of cells in activation status
+#' CalculatePercentage
 #'
 #' This function calculates the percentage of cells in ON (scale > 0) and OFF (scale < 0)
 #' activation states within each group defined by `group_var`. If exactly two groups
 #' are provided, it also computes Cohen's d effect size between their activation values.
+#'
 #' @name CalculatePercentage
 #' @importFrom dplyr bind_rows
 #' @importFrom effsize cohen.d
 #' @importFrom stats na.omit
 #' @param to.plot A data frame containing at least a `scale` column and a grouping column.
 #' @param group_var A string specifying the grouping variable (e.g., "genotype", "treatment").
+#'
 #' @return A data frame with the percentage of ON/OFF cells and Cohen's d (if applicable).
 #' @examples
 #' data(fake_to_plot)

R/ComputeCellData.R

@@ -1,3 +1,5 @@
+#' ComputeCellData
+#'
 #' A function computes cell status for a given pathway in single-cell RNA-seq data,
 #' based on the distance between genes in a specified pathway. The distance is computed
 #' for each batch of cells, and classical multidimensional scaling (MDS) is used to
@@ -14,7 +16,7 @@
 #'
 #' @param x A `Seurat` object containing single-cell RNA sequencing data.
 #' @param pathway A `character` string specifying the pathway name. This should match a pathway used by `LoadPathway()`.
-#' @param distance.method A `character` string specifying the distance metric to use.
+#' @param distance.method A `character` string specifying the distance metric to use.Default is "manhattan".
 #' Options include: `"manhattan"`, `"euclidean"`, `"canberra"`, `"binary"`, `"minkowski"`
 #' @param batch.size An `integer` specifying the number of cells to process per batch. Default is 1000.
 #' @param scale.data A `logical` indicating whether to use scaled data (`scale.data = TRUE`) or normalized data. Default is `TRUE`.
@@ -53,8 +55,15 @@ ComputeCellData <- function(x, pathway, distance.method, batch.size = batch.size
  shuffled_cell_id <- sample(cell_id)
 
  # Split shuffled indices into batches
+ # Check if batch.size is provided; if not, set default and message
+ if (missing(batch.size) || is.null(batch.size)) {
+ message("Parameter 'batch.size' is missing or NULL. Setting default batch size to 1000.")
+ batch.size <- 1000
+ }
+
  # Define batch size
  batch_size <- batch.size
+
  batches <- split(shuffled_cell_id, ceiling(seq_along(shuffled_cell_id) / batch.size))
 
  # Subset expression data into chunks based on sampled indices
@@ -82,6 +91,12 @@ ComputeCellData <- function(x, pathway, distance.method, batch.size = batch.size
  next
  }
 
+ # Check if distance.method is provided; if not, set default and message
+ if (missing(distance.method) || is.null(distance.method)) {
+ message("Parameter 'distance.method' is missing or NULL. Setting default distance.method to 'manhattan'.")
+ distance.method <- "manhattan"
+ }
+
  # Distance calculation
  message("Computing distance...")
  d <- dist(t(pathwaytempdata), method = distance.method)

R/LoadPathway.R

@@ -1,6 +1,7 @@
-## Pathway Data Extraction from Exceldataset
+#' LoadPathway
 #'
 #' This function reads pathway data from the package's built-in Excel file.
+#'
 #' @name LoadPathway
 #' @param pathway A `character` string specifying the pathway name.
 #' @return A data frame with pathway data.

R/PathwayMaxMin.R

@@ -1,4 +1,7 @@
+#' PathwayMaxMin
+#'
 #' A function to obtain the hypothetical max and min activation status of selected pathway for a given scRNA seq data set
+#'
 #' @name PathwayMaxMin
 #' @import Seurat
 #' @import tidyverse

R/PlotPathway.R

@@ -1,3 +1,5 @@
+#' PlotPathway
+#'
 #' A function to plot the Pathway activation status
 #'
 #' @name PlotPathway

README.md

@@ -37,7 +37,7 @@ library(PathwayEmbed)
 data(fake_test_object)
 
 # Compute pathway data
-mds_results <- ComputeCellData(fake_test_object, pathway = "Wnt", distance.method = "manhattan")
+mds_results <- ComputeCellData(fake_test_object, pathway = "Wnt", distance.method = "manhattan", batch.size = 100) need to add a default batch size and a end message
 
 # Prepare data for plotting
 plot_data <- PreparePlotData(fake_test_object, mds_results, group = "genotype")

R/CalculatePercentage.R

@@ -1,14 +1,16 @@
-#' Calculate the percentage of cells in activation status
+#' CalculatePercentage
 #'
 #' This function calculates the percentage of cells in ON (scale > 0) and OFF (scale < 0)
 #' activation states within each group defined by `group_var`. If exactly two groups
 #' are provided, it also computes Cohen's d effect size between their activation values.
+#'
 #' @name CalculatePercentage
 #' @importFrom dplyr bind_rows
 #' @importFrom effsize cohen.d
 #' @importFrom stats na.omit
 #' @param to.plot A data frame containing at least a `scale` column and a grouping column.
 #' @param group_var A string specifying the grouping variable (e.g., "genotype", "treatment").
+#'
 #' @return A data frame with the percentage of ON/OFF cells and Cohen's d (if applicable).
 #' @examples
 #' data(fake_to_plot)

R/ComputeCellData.R

@@ -1,3 +1,5 @@
+#' ComputeCellData
+#'
 #' A function computes cell status for a given pathway in single-cell RNA-seq data,
 #' based on the distance between genes in a specified pathway. The distance is computed
 #' for each batch of cells, and classical multidimensional scaling (MDS) is used to
@@ -14,7 +16,7 @@
 #'
 #' @param x A `Seurat` object containing single-cell RNA sequencing data.
 #' @param pathway A `character` string specifying the pathway name. This should match a pathway used by `LoadPathway()`.
-#' @param distance.method A `character` string specifying the distance metric to use.
+#' @param distance.method A `character` string specifying the distance metric to use.Default is "manhattan".
 #' Options include: `"manhattan"`, `"euclidean"`, `"canberra"`, `"binary"`, `"minkowski"`
 #' @param batch.size An `integer` specifying the number of cells to process per batch. Default is 1000.
 #' @param scale.data A `logical` indicating whether to use scaled data (`scale.data = TRUE`) or normalized data. Default is `TRUE`.
@@ -53,8 +55,15 @@ ComputeCellData <- function(x, pathway, distance.method, batch.size = batch.size
  shuffled_cell_id <- sample(cell_id)
 
  # Split shuffled indices into batches
+ # Check if batch.size is provided; if not, set default and message
+ if (missing(batch.size) || is.null(batch.size)) {
+ message("Parameter 'batch.size' is missing or NULL. Setting default batch size to 1000.")
+ batch.size <- 1000
+ }
+
  # Define batch size
  batch_size <- batch.size
+
  batches <- split(shuffled_cell_id, ceiling(seq_along(shuffled_cell_id) / batch.size))
 
  # Subset expression data into chunks based on sampled indices
@@ -82,6 +91,12 @@ ComputeCellData <- function(x, pathway, distance.method, batch.size = batch.size
  next
  }
 
+ # Check if distance.method is provided; if not, set default and message
+ if (missing(distance.method) || is.null(distance.method)) {
+ message("Parameter 'distance.method' is missing or NULL. Setting default distance.method to 'manhattan'.")
+ distance.method <- "manhattan"
+ }
+
  # Distance calculation
  message("Computing distance...")
  d <- dist(t(pathwaytempdata), method = distance.method)

R/LoadPathway.R

@@ -1,6 +1,7 @@
-## Pathway Data Extraction from Exceldataset
+#' LoadPathway
 #'
 #' This function reads pathway data from the package's built-in Excel file.
+#'
 #' @name LoadPathway
 #' @param pathway A `character` string specifying the pathway name.
 #' @return A data frame with pathway data.

R/PathwayMaxMin.R

@@ -1,4 +1,7 @@
+#' PathwayMaxMin
+#'
 #' A function to obtain the hypothetical max and min activation status of selected pathway for a given scRNA seq data set
+#'
 #' @name PathwayMaxMin
 #' @import Seurat
 #' @import tidyverse

R/PlotPathway.R

@@ -1,3 +1,5 @@
+#' PlotPathway
+#'
 #' A function to plot the Pathway activation status
 #'
 #' @name PlotPathway

README.md

@@ -37,7 +37,7 @@ library(PathwayEmbed)
 data(fake_test_object)
 
 # Compute pathway data
-mds_results <- ComputeCellData(fake_test_object, pathway = "Wnt", distance.method = "manhattan")
+mds_results <- ComputeCellData(fake_test_object, pathway = "Wnt", distance.method = "manhattan", batch.size = 100) need to add a default batch size and a end message
 
 # Prepare data for plotting
 plot_data <- PreparePlotData(fake_test_object, mds_results, group = "genotype")

R/CalculatePercentage.R

@@ -1,14 +1,16 @@
-#' Calculate the percentage of cells in activation status
+#' CalculatePercentage
 #'
 #' This function calculates the percentage of cells in ON (scale > 0) and OFF (scale < 0)
 #' activation states within each group defined by `group_var`. If exactly two groups
 #' are provided, it also computes Cohen's d effect size between their activation values.
+#'
 #' @name CalculatePercentage
 #' @importFrom dplyr bind_rows
 #' @importFrom effsize cohen.d
 #' @importFrom stats na.omit
 #' @param to.plot A data frame containing at least a `scale` column and a grouping column.
 #' @param group_var A string specifying the grouping variable (e.g., "genotype", "treatment").
+#'
 #' @return A data frame with the percentage of ON/OFF cells and Cohen's d (if applicable).
 #' @examples
 #' data(fake_to_plot)

R/ComputeCellData.R

@@ -1,3 +1,5 @@
+#' ComputeCellData
+#'
 #' A function computes cell status for a given pathway in single-cell RNA-seq data,
 #' based on the distance between genes in a specified pathway. The distance is computed
 #' for each batch of cells, and classical multidimensional scaling (MDS) is used to
@@ -14,7 +16,7 @@
 #'
 #' @param x A `Seurat` object containing single-cell RNA sequencing data.
 #' @param pathway A `character` string specifying the pathway name. This should match a pathway used by `LoadPathway()`.
-#' @param distance.method A `character` string specifying the distance metric to use.
+#' @param distance.method A `character` string specifying the distance metric to use.Default is "manhattan".
 #' Options include: `"manhattan"`, `"euclidean"`, `"canberra"`, `"binary"`, `"minkowski"`
 #' @param batch.size An `integer` specifying the number of cells to process per batch. Default is 1000.
 #' @param scale.data A `logical` indicating whether to use scaled data (`scale.data = TRUE`) or normalized data. Default is `TRUE`.
@@ -53,8 +55,15 @@ ComputeCellData <- function(x, pathway, distance.method, batch.size = batch.size
  shuffled_cell_id <- sample(cell_id)
 
  # Split shuffled indices into batches
+ # Check if batch.size is provided; if not, set default and message
+ if (missing(batch.size) || is.null(batch.size)) {
+ message("Parameter 'batch.size' is missing or NULL. Setting default batch size to 1000.")
+ batch.size <- 1000
+ }
+
  # Define batch size
  batch_size <- batch.size
+
  batches <- split(shuffled_cell_id, ceiling(seq_along(shuffled_cell_id) / batch.size))
 
  # Subset expression data into chunks based on sampled indices
@@ -82,6 +91,12 @@ ComputeCellData <- function(x, pathway, distance.method, batch.size = batch.size
  next
  }
 
+ # Check if distance.method is provided; if not, set default and message
+ if (missing(distance.method) || is.null(distance.method)) {
+ message("Parameter 'distance.method' is missing or NULL. Setting default distance.method to 'manhattan'.")
+ distance.method <- "manhattan"
+ }
+
  # Distance calculation
  message("Computing distance...")
  d <- dist(t(pathwaytempdata), method = distance.method)

R/LoadPathway.R

@@ -1,6 +1,7 @@
-## Pathway Data Extraction from Exceldataset
+#' LoadPathway
 #'
 #' This function reads pathway data from the package's built-in Excel file.
+#'
 #' @name LoadPathway
 #' @param pathway A `character` string specifying the pathway name.
 #' @return A data frame with pathway data.

R/PathwayMaxMin.R

@@ -1,4 +1,7 @@
+#' PathwayMaxMin
+#'
 #' A function to obtain the hypothetical max and min activation status of selected pathway for a given scRNA seq data set
+#'
 #' @name PathwayMaxMin
 #' @import Seurat
 #' @import tidyverse

R/PlotPathway.R

@@ -1,3 +1,5 @@
+#' PlotPathway
+#'
 #' A function to plot the Pathway activation status
 #'
 #' @name PlotPathway

README.md

@@ -37,7 +37,7 @@ library(PathwayEmbed)
 data(fake_test_object)
 
 # Compute pathway data
-mds_results <- ComputeCellData(fake_test_object, pathway = "Wnt", distance.method = "manhattan")
+mds_results <- ComputeCellData(fake_test_object, pathway = "Wnt", distance.method = "manhattan", batch.size = 100) need to add a default batch size and a end message
 
 # Prepare data for plotting
 plot_data <- PreparePlotData(fake_test_object, mds_results, group = "genotype")

R/CalculatePercentage.R

@@ -1,14 +1,16 @@
-#' Calculate the percentage of cells in activation status
+#' CalculatePercentage
 #'
 #' This function calculates the percentage of cells in ON (scale > 0) and OFF (scale < 0)
 #' activation states within each group defined by `group_var`. If exactly two groups
 #' are provided, it also computes Cohen's d effect size between their activation values.
+#'
 #' @name CalculatePercentage
 #' @importFrom dplyr bind_rows
 #' @importFrom effsize cohen.d
 #' @importFrom stats na.omit
 #' @param to.plot A data frame containing at least a `scale` column and a grouping column.
 #' @param group_var A string specifying the grouping variable (e.g., "genotype", "treatment").
+#'
 #' @return A data frame with the percentage of ON/OFF cells and Cohen's d (if applicable).
 #' @examples
 #' data(fake_to_plot)

R/ComputeCellData.R

@@ -1,3 +1,5 @@
+#' ComputeCellData
+#'
 #' A function computes cell status for a given pathway in single-cell RNA-seq data,
 #' based on the distance between genes in a specified pathway. The distance is computed
 #' for each batch of cells, and classical multidimensional scaling (MDS) is used to
@@ -14,7 +16,7 @@
 #'
 #' @param x A `Seurat` object containing single-cell RNA sequencing data.
 #' @param pathway A `character` string specifying the pathway name. This should match a pathway used by `LoadPathway()`.
-#' @param distance.method A `character` string specifying the distance metric to use.
+#' @param distance.method A `character` string specifying the distance metric to use.Default is "manhattan".
 #' Options include: `"manhattan"`, `"euclidean"`, `"canberra"`, `"binary"`, `"minkowski"`
 #' @param batch.size An `integer` specifying the number of cells to process per batch. Default is 1000.
 #' @param scale.data A `logical` indicating whether to use scaled data (`scale.data = TRUE`) or normalized data. Default is `TRUE`.
@@ -53,8 +55,15 @@ ComputeCellData <- function(x, pathway, distance.method, batch.size = batch.size
  shuffled_cell_id <- sample(cell_id)
 
  # Split shuffled indices into batches
+ # Check if batch.size is provided; if not, set default and message
+ if (missing(batch.size) || is.null(batch.size)) {
+ message("Parameter 'batch.size' is missing or NULL. Setting default batch size to 1000.")
+ batch.size <- 1000
+ }
+
  # Define batch size
  batch_size <- batch.size
+
  batches <- split(shuffled_cell_id, ceiling(seq_along(shuffled_cell_id) / batch.size))
 
  # Subset expression data into chunks based on sampled indices
@@ -82,6 +91,12 @@ ComputeCellData <- function(x, pathway, distance.method, batch.size = batch.size
  next
  }
 
+ # Check if distance.method is provided; if not, set default and message
+ if (missing(distance.method) || is.null(distance.method)) {
+ message("Parameter 'distance.method' is missing or NULL. Setting default distance.method to 'manhattan'.")
+ distance.method <- "manhattan"
+ }
+
  # Distance calculation
  message("Computing distance...")
  d <- dist(t(pathwaytempdata), method = distance.method)

R/LoadPathway.R

@@ -1,6 +1,7 @@
-## Pathway Data Extraction from Exceldataset
+#' LoadPathway
 #'
 #' This function reads pathway data from the package's built-in Excel file.
+#'
 #' @name LoadPathway
 #' @param pathway A `character` string specifying the pathway name.
 #' @return A data frame with pathway data.

R/PathwayMaxMin.R

@@ -1,4 +1,7 @@
+#' PathwayMaxMin
+#'
 #' A function to obtain the hypothetical max and min activation status of selected pathway for a given scRNA seq data set
+#'
 #' @name PathwayMaxMin
 #' @import Seurat
 #' @import tidyverse

R/PlotPathway.R

@@ -1,3 +1,5 @@
+#' PlotPathway
+#'
 #' A function to plot the Pathway activation status
 #'
 #' @name PlotPathway

README.md

@@ -37,7 +37,7 @@ library(PathwayEmbed)
 data(fake_test_object)
 
 # Compute pathway data
-mds_results <- ComputeCellData(fake_test_object, pathway = "Wnt", distance.method = "manhattan")
+mds_results <- ComputeCellData(fake_test_object, pathway = "Wnt", distance.method = "manhattan", batch.size = 100) need to add a default batch size and a end message
 
 # Prepare data for plotting
 plot_data <- PreparePlotData(fake_test_object, mds_results, group = "genotype")

R/CalculatePercentage.R

@@ -1,14 +1,16 @@
-#' Calculate the percentage of cells in activation status
+#' CalculatePercentage
 #'
 #' This function calculates the percentage of cells in ON (scale > 0) and OFF (scale < 0)
 #' activation states within each group defined by `group_var`. If exactly two groups
 #' are provided, it also computes Cohen's d effect size between their activation values.
+#'
 #' @name CalculatePercentage
 #' @importFrom dplyr bind_rows
 #' @importFrom effsize cohen.d
 #' @importFrom stats na.omit
 #' @param to.plot A data frame containing at least a `scale` column and a grouping column.
 #' @param group_var A string specifying the grouping variable (e.g., "genotype", "treatment").
+#'
 #' @return A data frame with the percentage of ON/OFF cells and Cohen's d (if applicable).
 #' @examples
 #' data(fake_to_plot)

R/ComputeCellData.R

@@ -1,3 +1,5 @@
+#' ComputeCellData
+#'
 #' A function computes cell status for a given pathway in single-cell RNA-seq data,
 #' based on the distance between genes in a specified pathway. The distance is computed
 #' for each batch of cells, and classical multidimensional scaling (MDS) is used to
@@ -14,7 +16,7 @@
 #'
 #' @param x A `Seurat` object containing single-cell RNA sequencing data.
 #' @param pathway A `character` string specifying the pathway name. This should match a pathway used by `LoadPathway()`.
-#' @param distance.method A `character` string specifying the distance metric to use.
+#' @param distance.method A `character` string specifying the distance metric to use.Default is "manhattan".
 #' Options include: `"manhattan"`, `"euclidean"`, `"canberra"`, `"binary"`, `"minkowski"`
 #' @param batch.size An `integer` specifying the number of cells to process per batch. Default is 1000.
 #' @param scale.data A `logical` indicating whether to use scaled data (`scale.data = TRUE`) or normalized data. Default is `TRUE`.
@@ -53,8 +55,15 @@ ComputeCellData <- function(x, pathway, distance.method, batch.size = batch.size
  shuffled_cell_id <- sample(cell_id)
 
  # Split shuffled indices into batches
+ # Check if batch.size is provided; if not, set default and message
+ if (missing(batch.size) || is.null(batch.size)) {
+ message("Parameter 'batch.size' is missing or NULL. Setting default batch size to 1000.")
+ batch.size <- 1000
+ }
+
  # Define batch size
  batch_size <- batch.size
+
  batches <- split(shuffled_cell_id, ceiling(seq_along(shuffled_cell_id) / batch.size))
 
  # Subset expression data into chunks based on sampled indices
@@ -82,6 +91,12 @@ ComputeCellData <- function(x, pathway, distance.method, batch.size = batch.size
  next
  }
 
+ # Check if distance.method is provided; if not, set default and message
+ if (missing(distance.method) || is.null(distance.method)) {
+ message("Parameter 'distance.method' is missing or NULL. Setting default distance.method to 'manhattan'.")
+ distance.method <- "manhattan"
+ }
+
  # Distance calculation
  message("Computing distance...")
  d <- dist(t(pathwaytempdata), method = distance.method)

R/LoadPathway.R

@@ -1,6 +1,7 @@
-## Pathway Data Extraction from Exceldataset
+#' LoadPathway
 #'
 #' This function reads pathway data from the package's built-in Excel file.
+#'
 #' @name LoadPathway
 #' @param pathway A `character` string specifying the pathway name.
 #' @return A data frame with pathway data.

R/PathwayMaxMin.R

@@ -1,4 +1,7 @@
+#' PathwayMaxMin
+#'
 #' A function to obtain the hypothetical max and min activation status of selected pathway for a given scRNA seq data set
+#'
 #' @name PathwayMaxMin
 #' @import Seurat
 #' @import tidyverse

R/PlotPathway.R

@@ -1,3 +1,5 @@
+#' PlotPathway
+#'
 #' A function to plot the Pathway activation status
 #'
 #' @name PlotPathway

README.md

@@ -37,7 +37,7 @@ library(PathwayEmbed)
 data(fake_test_object)
 
 # Compute pathway data
-mds_results <- ComputeCellData(fake_test_object, pathway = "Wnt", distance.method = "manhattan")
+mds_results <- ComputeCellData(fake_test_object, pathway = "Wnt", distance.method = "manhattan", batch.size = 100) need to add a default batch size and a end message
 
 # Prepare data for plotting
 plot_data <- PreparePlotData(fake_test_object, mds_results, group = "genotype")

R/CalculatePercentage.R

@@ -1,14 +1,16 @@
-#' Calculate the percentage of cells in activation status
+#' CalculatePercentage
 #'
 #' This function calculates the percentage of cells in ON (scale > 0) and OFF (scale < 0)
 #' activation states within each group defined by `group_var`. If exactly two groups
 #' are provided, it also computes Cohen's d effect size between their activation values.
+#'
 #' @name CalculatePercentage
 #' @importFrom dplyr bind_rows
 #' @importFrom effsize cohen.d
 #' @importFrom stats na.omit
 #' @param to.plot A data frame containing at least a `scale` column and a grouping column.
 #' @param group_var A string specifying the grouping variable (e.g., "genotype", "treatment").
+#'
 #' @return A data frame with the percentage of ON/OFF cells and Cohen's d (if applicable).
 #' @examples
 #' data(fake_to_plot)

R/ComputeCellData.R

@@ -1,3 +1,5 @@
+#' ComputeCellData
+#'
 #' A function computes cell status for a given pathway in single-cell RNA-seq data,
 #' based on the distance between genes in a specified pathway. The distance is computed
 #' for each batch of cells, and classical multidimensional scaling (MDS) is used to
@@ -14,7 +16,7 @@
 #'
 #' @param x A `Seurat` object containing single-cell RNA sequencing data.
 #' @param pathway A `character` string specifying the pathway name. This should match a pathway used by `LoadPathway()`.
-#' @param distance.method A `character` string specifying the distance metric to use.
+#' @param distance.method A `character` string specifying the distance metric to use.Default is "manhattan".
 #' Options include: `"manhattan"`, `"euclidean"`, `"canberra"`, `"binary"`, `"minkowski"`
 #' @param batch.size An `integer` specifying the number of cells to process per batch. Default is 1000.
 #' @param scale.data A `logical` indicating whether to use scaled data (`scale.data = TRUE`) or normalized data. Default is `TRUE`.
@@ -53,8 +55,15 @@ ComputeCellData <- function(x, pathway, distance.method, batch.size = batch.size
  shuffled_cell_id <- sample(cell_id)
 
  # Split shuffled indices into batches
+ # Check if batch.size is provided; if not, set default and message
+ if (missing(batch.size) || is.null(batch.size)) {
+ message("Parameter 'batch.size' is missing or NULL. Setting default batch size to 1000.")
+ batch.size <- 1000
+ }
+
  # Define batch size
  batch_size <- batch.size
+
  batches <- split(shuffled_cell_id, ceiling(seq_along(shuffled_cell_id) / batch.size))
 
  # Subset expression data into chunks based on sampled indices
@@ -82,6 +91,12 @@ ComputeCellData <- function(x, pathway, distance.method, batch.size = batch.size
  next
  }
 
+ # Check if distance.method is provided; if not, set default and message
+ if (missing(distance.method) || is.null(distance.method)) {
+ message("Parameter 'distance.method' is missing or NULL. Setting default distance.method to 'manhattan'.")
+ distance.method <- "manhattan"
+ }
+
  # Distance calculation
  message("Computing distance...")
  d <- dist(t(pathwaytempdata), method = distance.method)

R/LoadPathway.R

@@ -1,6 +1,7 @@
-## Pathway Data Extraction from Exceldataset
+#' LoadPathway
 #'
 #' This function reads pathway data from the package's built-in Excel file.
+#'
 #' @name LoadPathway
 #' @param pathway A `character` string specifying the pathway name.
 #' @return A data frame with pathway data.

R/PathwayMaxMin.R

@@ -1,4 +1,7 @@
+#' PathwayMaxMin
+#'
 #' A function to obtain the hypothetical max and min activation status of selected pathway for a given scRNA seq data set
+#'
 #' @name PathwayMaxMin
 #' @import Seurat
 #' @import tidyverse

R/PlotPathway.R

@@ -1,3 +1,5 @@
+#' PlotPathway
+#'
 #' A function to plot the Pathway activation status
 #'
 #' @name PlotPathway

README.md

@@ -37,7 +37,7 @@ library(PathwayEmbed)
 data(fake_test_object)
 
 # Compute pathway data
-mds_results <- ComputeCellData(fake_test_object, pathway = "Wnt", distance.method = "manhattan")
+mds_results <- ComputeCellData(fake_test_object, pathway = "Wnt", distance.method = "manhattan", batch.size = 100) need to add a default batch size and a end message
 
 # Prepare data for plotting
 plot_data <- PreparePlotData(fake_test_object, mds_results, group = "genotype")

R/CalculatePercentage.R

@@ -1,14 +1,16 @@
-#' Calculate the percentage of cells in activation status
+#' CalculatePercentage
 #'
 #' This function calculates the percentage of cells in ON (scale > 0) and OFF (scale < 0)
 #' activation states within each group defined by `group_var`. If exactly two groups
 #' are provided, it also computes Cohen's d effect size between their activation values.
+#'
 #' @name CalculatePercentage
 #' @importFrom dplyr bind_rows
 #' @importFrom effsize cohen.d
 #' @importFrom stats na.omit
 #' @param to.plot A data frame containing at least a `scale` column and a grouping column.
 #' @param group_var A string specifying the grouping variable (e.g., "genotype", "treatment").
+#'
 #' @return A data frame with the percentage of ON/OFF cells and Cohen's d (if applicable).
 #' @examples
 #' data(fake_to_plot)

R/ComputeCellData.R

@@ -1,3 +1,5 @@
+#' ComputeCellData
+#'
 #' A function computes cell status for a given pathway in single-cell RNA-seq data,
 #' based on the distance between genes in a specified pathway. The distance is computed
 #' for each batch of cells, and classical multidimensional scaling (MDS) is used to
@@ -14,7 +16,7 @@
 #'
 #' @param x A `Seurat` object containing single-cell RNA sequencing data.
 #' @param pathway A `character` string specifying the pathway name. This should match a pathway used by `LoadPathway()`.
-#' @param distance.method A `character` string specifying the distance metric to use.
+#' @param distance.method A `character` string specifying the distance metric to use.Default is "manhattan".
 #' Options include: `"manhattan"`, `"euclidean"`, `"canberra"`, `"binary"`, `"minkowski"`
 #' @param batch.size An `integer` specifying the number of cells to process per batch. Default is 1000.
 #' @param scale.data A `logical` indicating whether to use scaled data (`scale.data = TRUE`) or normalized data. Default is `TRUE`.
@@ -53,8 +55,15 @@ ComputeCellData <- function(x, pathway, distance.method, batch.size = batch.size
  shuffled_cell_id <- sample(cell_id)
 
  # Split shuffled indices into batches
+ # Check if batch.size is provided; if not, set default and message
+ if (missing(batch.size) || is.null(batch.size)) {
+ message("Parameter 'batch.size' is missing or NULL. Setting default batch size to 1000.")
+ batch.size <- 1000
+ }
+
  # Define batch size
  batch_size <- batch.size
+
  batches <- split(shuffled_cell_id, ceiling(seq_along(shuffled_cell_id) / batch.size))
 
  # Subset expression data into chunks based on sampled indices
@@ -82,6 +91,12 @@ ComputeCellData <- function(x, pathway, distance.method, batch.size = batch.size
  next
  }
 
+ # Check if distance.method is provided; if not, set default and message
+ if (missing(distance.method) || is.null(distance.method)) {
+ message("Parameter 'distance.method' is missing or NULL. Setting default distance.method to 'manhattan'.")
+ distance.method <- "manhattan"
+ }
+
  # Distance calculation
  message("Computing distance...")
  d <- dist(t(pathwaytempdata), method = distance.method)

R/LoadPathway.R

@@ -1,6 +1,7 @@
-## Pathway Data Extraction from Exceldataset
+#' LoadPathway
 #'
 #' This function reads pathway data from the package's built-in Excel file.
+#'
 #' @name LoadPathway
 #' @param pathway A `character` string specifying the pathway name.
 #' @return A data frame with pathway data.

R/PathwayMaxMin.R

@@ -1,4 +1,7 @@
+#' PathwayMaxMin
+#'
 #' A function to obtain the hypothetical max and min activation status of selected pathway for a given scRNA seq data set
+#'
 #' @name PathwayMaxMin
 #' @import Seurat
 #' @import tidyverse

R/PlotPathway.R

@@ -1,3 +1,5 @@
+#' PlotPathway
+#'
 #' A function to plot the Pathway activation status
 #'
 #' @name PlotPathway

README.md

@@ -37,7 +37,7 @@ library(PathwayEmbed)
 data(fake_test_object)
 
 # Compute pathway data
-mds_results <- ComputeCellData(fake_test_object, pathway = "Wnt", distance.method = "manhattan")
+mds_results <- ComputeCellData(fake_test_object, pathway = "Wnt", distance.method = "manhattan", batch.size = 100) need to add a default batch size and a end message
 
 # Prepare data for plotting
 plot_data <- PreparePlotData(fake_test_object, mds_results, group = "genotype")

R/CalculatePercentage.R

@@ -1,14 +1,16 @@
-#' Calculate the percentage of cells in activation status
+#' CalculatePercentage
 #'
 #' This function calculates the percentage of cells in ON (scale > 0) and OFF (scale < 0)
 #' activation states within each group defined by `group_var`. If exactly two groups
 #' are provided, it also computes Cohen's d effect size between their activation values.
+#'
 #' @name CalculatePercentage
 #' @importFrom dplyr bind_rows
 #' @importFrom effsize cohen.d
 #' @importFrom stats na.omit
 #' @param to.plot A data frame containing at least a `scale` column and a grouping column.
 #' @param group_var A string specifying the grouping variable (e.g., "genotype", "treatment").
+#'
 #' @return A data frame with the percentage of ON/OFF cells and Cohen's d (if applicable).
 #' @examples
 #' data(fake_to_plot)

R/ComputeCellData.R

@@ -1,3 +1,5 @@
+#' ComputeCellData
+#'
 #' A function computes cell status for a given pathway in single-cell RNA-seq data,
 #' based on the distance between genes in a specified pathway. The distance is computed
 #' for each batch of cells, and classical multidimensional scaling (MDS) is used to
@@ -14,7 +16,7 @@
 #'
 #' @param x A `Seurat` object containing single-cell RNA sequencing data.
 #' @param pathway A `character` string specifying the pathway name. This should match a pathway used by `LoadPathway()`.
-#' @param distance.method A `character` string specifying the distance metric to use.
+#' @param distance.method A `character` string specifying the distance metric to use.Default is "manhattan".
 #' Options include: `"manhattan"`, `"euclidean"`, `"canberra"`, `"binary"`, `"minkowski"`
 #' @param batch.size An `integer` specifying the number of cells to process per batch. Default is 1000.
 #' @param scale.data A `logical` indicating whether to use scaled data (`scale.data = TRUE`) or normalized data. Default is `TRUE`.
@@ -53,8 +55,15 @@ ComputeCellData <- function(x, pathway, distance.method, batch.size = batch.size
  shuffled_cell_id <- sample(cell_id)
 
  # Split shuffled indices into batches
+ # Check if batch.size is provided; if not, set default and message
+ if (missing(batch.size) || is.null(batch.size)) {
+ message("Parameter 'batch.size' is missing or NULL. Setting default batch size to 1000.")
+ batch.size <- 1000
+ }
+
  # Define batch size
  batch_size <- batch.size
+
  batches <- split(shuffled_cell_id, ceiling(seq_along(shuffled_cell_id) / batch.size))
 
  # Subset expression data into chunks based on sampled indices
@@ -82,6 +91,12 @@ ComputeCellData <- function(x, pathway, distance.method, batch.size = batch.size
  next
  }
 
+ # Check if distance.method is provided; if not, set default and message
+ if (missing(distance.method) || is.null(distance.method)) {
+ message("Parameter 'distance.method' is missing or NULL. Setting default distance.method to 'manhattan'.")
+ distance.method <- "manhattan"
+ }
+
  # Distance calculation
  message("Computing distance...")
  d <- dist(t(pathwaytempdata), method = distance.method)

R/LoadPathway.R

@@ -1,6 +1,7 @@
-## Pathway Data Extraction from Exceldataset
+#' LoadPathway
 #'
 #' This function reads pathway data from the package's built-in Excel file.
+#'
 #' @name LoadPathway
 #' @param pathway A `character` string specifying the pathway name.
 #' @return A data frame with pathway data.

R/PathwayMaxMin.R

@@ -1,4 +1,7 @@
+#' PathwayMaxMin
+#'
 #' A function to obtain the hypothetical max and min activation status of selected pathway for a given scRNA seq data set
+#'
 #' @name PathwayMaxMin
 #' @import Seurat
 #' @import tidyverse

R/PlotPathway.R

@@ -1,3 +1,5 @@
+#' PlotPathway
+#'
 #' A function to plot the Pathway activation status
 #'
 #' @name PlotPathway

README.md

@@ -37,7 +37,7 @@ library(PathwayEmbed)
 data(fake_test_object)
 
 # Compute pathway data
-mds_results <- ComputeCellData(fake_test_object, pathway = "Wnt", distance.method = "manhattan")
+mds_results <- ComputeCellData(fake_test_object, pathway = "Wnt", distance.method = "manhattan", batch.size = 100) need to add a default batch size and a end message
 
 # Prepare data for plotting
 plot_data <- PreparePlotData(fake_test_object, mds_results, group = "genotype")