Merge pull request #23 from spriyansh/main

Updated Documentation

R/DESeq2_estimateSizeFactorsForMatrix.R

@@ -1,8 +1,8 @@
 #' @title estimateSizeFactorsForMatrix from DESeq2
 #' @author Simon Anders
 #' Please cite as
-#' Love, M.I., Huber, W., Anders, S. Moderated estimation of fold change and dispersion for RNA-seq data with
-#' DESeq2 Genome Biology 15(12):550 (2014)
+#' Love, M.I., Huber, W., Anders, S. Moderated estimation of fold change and
+#' dispersion for RNA-seq data with DESeq2 Genome Biology 15(12):550 (2014)
 #'
 #' Low-level function to estimate size factors with robust regression.
 #'

R/ScMaSigProClass.R

@@ -20,7 +20,7 @@
 #' @slot bin_method A character string representing the algorithm used for
 #' binning.
 #' @slot path_col A character string representing the column name for branching
-#' path assignment in 'Sparse' or 'Dense'data. See `colData` from the
+#' path assignment in 'Sparse' or 'Dense' data. See `colData` from the
 #' \pkg{SingleCellExperiment} package.
 #' @slot bin_col A character string representing the name of the column in which
 #' bin labels are stored.
@@ -32,7 +32,8 @@
 #' metadata containing cell level annotations. (Default is "cell_type").
 #' @slot g Update Description..
 #' @slot p_value Significance Level.
-#' @slot min_na Minimum values needed to estimate the model.
+#' @slot min_na Minimum values needed per gene across cells to estimate the
+#' model.
 #' @slot mt_correction A character string specifying the p-value correction
 #' method.
 #' @slot epsilon Model convergence tolerance.
@@ -41,12 +42,13 @@
 #' @slot offset A logical value specifying whether to use offset during fitting.
 #' @slot log_offset A logical value specifying whether to take the logarithm of
 #' the offsets.
-#' @slot max_it Integer. Maximum number of iterations to fit the model.
-#' @slot poly_degree Integer with the polynomial degree to fit the regression. 1
-#' @slot distribution Distribution used
-#' @slot cluster_method Description
-#' @slot use_dim description
-#' @slot fill_na description
+#' @slot max_it Maximum number of iterations to fit the model.
+#' @slot poly_degree Order of the polynomial linear model.
+#' @slot distribution Distribution of the error term.
+#' @slot cluster_method Clustering method used for clustering significant genes.
+#' @slot use_dim Dimension to use for filling the missing values before
+#' clustering.
+#' @slot fill_na Method to fill the missing values.
 #'
 #' @name ParameterConfig
 #' @aliases ParameterConfig-class
@@ -100,14 +102,11 @@ setClass(
       }
     }
 
-    # Check for slot g
     if (!is.integer(object@g)) {
       stop("Slot 'g' must be an integer.")
     }
 
-    # Check for slot Q
     if (!is.numeric(object@p_value)) {
-      stop("Slot 'p_value' must be numeric.")
     }
 
     if (!is.numeric(object@epsilon)) {

R/align_pseudotime.R

@@ -11,6 +11,7 @@
 #' @importFrom scales rescale
 #' @importFrom S4Vectors DataFrame
 #'
+#' @param scmpObj description
 #' @param ptime_col A character string representing the column name
 #' for inferred Pseudotime values in 'Sparse' data. See `colData` from the
 #' \pkg{SingleCellExperiment} package. (Default is "Pseudotime")

R/create_scmp.R

@@ -41,7 +41,7 @@ create_scmp <- function(counts,
     msg = paste("Rownames of raw-counts and cell-level-metadata are different.")
   )
 
-  if (!is.null(bin_counts) | !is.null(bin_cell_data)) {
+  if (!is.null(bin_counts) || !is.null(bin_cell_data)) {
     assert_that(nrow(bin_counts) == nrow(bin_cell_data),
       msg = paste("Number of cells in bin_counts and bin_cell_data are different.")
     )

R/m3_select_path.R

@@ -194,7 +194,7 @@ m3_select_path <- function(cds,
       inputType = "Monocle3",
       ptime_col = ptime_col
     )
-  } else if (plot_purity & !all(supplied_nodes %in% anno.df[["node"]])) {
+  } else if (plot_purity && !all(supplied_nodes %in% anno.df[["node"]])) {
     # Tranfer data
     data <- anno.df
 
@@ -213,7 +213,7 @@ m3_select_path <- function(cds,
       group_by(!!sym(node), !!sym(anno)) %>%
       summarise(count = n(), .groups = "drop")
 
-    data_summary <- data_summary[data_summary$count >= (mean(data_summary$count) + sd(data_summary$count)), ]
+    data_summary <- data_summary[data_summary[[count]] >= (mean(data_summary$count) + sd(data_summary[[count]])), ]
 
     # Plotting the data
     fraction_bar <- ggplot(data_summary, aes(x = .data$node, y = .data$count, fill = .data$anno)) +

R/pb_helpers.R

@@ -474,7 +474,7 @@ optimize_bin_max <- function(bin_table, max_allowed, verbose = TRUE,
 #' cell counts. It does this by either taking the mean or sum of counts across
 #' cells in each bin, depending on the specified method.
 #'
-#' @param scmpObject object of Class scMaSigPro. See \code{\link{ScMaSigPro}}
+#' @param scmpObj object of Class scMaSigPro. See \code{\link{ScMaSigPro}}
 #' for more details.
 #' @param bin_mem_col Column name in the Dense metadata storing information
 #' about the members of the bins. (Default is 'scmp_bin_members').
@@ -502,29 +502,29 @@ optimize_bin_max <- function(bin_table, max_allowed, verbose = TRUE,
 #'
 #' @keywords internal
 
-pb_counts <- function(scmpObject,
-                      bin_mem_col = scmpObject@Parameters@bin_mem_col,
-                      bin_col = scmpObject@Parameters@bin_col,
+pb_counts <- function(scmpObj,
+                      bin_mem_col = scmpObj@Parameters@bin_mem_col,
+                      bin_col = scmpObj@Parameters@bin_col,
                       assay_name = "counts",
                       cluster_count_by = "sum") {
   # Check Object Validity
-  assert_that(is(scmpObject, "ScMaSigPro"),
+  assert_that(is(scmpObj, "ScMaSigPro"),
     msg = "Please provide object of class 'scMaSigPro'."
   )
 
   # Count slot
   assert_that(
     all(
-      assay_name %in% names(scmpObject@Sparse@assays@data@listData)
+      assay_name %in% names(scmpObj@Sparse@assays@data@listData)
     ),
-    msg = paste0("'", assay_name, "' ", "doesn't exit in scmpObject.")
+    msg = paste0("'", assay_name, "' ", "doesn't exit in scmpObj.")
   )
 
   # Get assay
-  counts <- scmpObject@Sparse@assays@data@listData[[assay_name]]
+  counts <- scmpObj@Sparse@assays@data@listData[[assay_name]]
 
   # Get Pseudobulk Profile
-  pseudo_bulk_profile <- as.data.frame(colData(scmpObject@Dense))
+  pseudo_bulk_profile <- as.data.frame(colData(scmpObj@Dense))
 
   assert_that(bin_mem_col %in% colnames(pseudo_bulk_profile),
     msg = paste0("'", bin_mem_col, "' does not exist in level.meta.data")
@@ -567,8 +567,8 @@ pb_counts <- function(scmpObject,
   colnames(pb.counts) <- meta.info[[bin_col]]
 
   # Return the counts
-  scmpObject@Dense@assays@data@listData$bulk.counts <- as(pb.counts, "dgCMatrix")
+  scmpObj@Dense@assays@data@listData$bulk.counts <- as(pb.counts, "dgCMatrix")
 
   # return
-  return(scmpObject)
+  return(scmpObj)
 }

R/plotBinTile.R

@@ -1,19 +1,23 @@
 #' @title Plot Bin Sizes Across Binned Time and Paths
 #'
 #' @description
-#' This function generates plots to visualize the dense cell metadata from a ScMaSigPro
-#' object. It produces tile plot to display the bin sizes across different
-#' binned time intervals and paths.
+#' This function generates plots to visualize the Dense slot cell metadata
+#' from a ScMaSigPro object. It produces tile plot to display the bin sizes
+#' across different binned time intervals and paths.
 #'
-#' @param scmpObj A ScMaSigPro class object with an additional slot 'Dense' that
-#' contains compression information.
-#' @param path_col Name of the column in `cell.metadata` storing information
-#' for Path.
-#' @param bin_size_col A title of the barplot
-#' @param bin_ptime_col description
+#' @param scmpObj An object of class \code{\link{ScMaSigPro}}.
+#' @param path_col A character string representing the column name for branching
+#' path assignment in 'Sparse' or 'Dense' slot.
+#' @param bin_size_col A character string representing the name of the column in
+#' which bin sizes per bin are stored. (Default is "scmp_bin_size").
+#' @param bin_ptime_col A character string representing the column name
+#' for binned Pseudotime values in 'Dense' data.
+#' (Default is "scmp_binned_pseudotime").
+#'
+#' @return ggplot2 plot object.
+#'
+#' @author Priyansh Srivastava \email{spriyansh29@@gmail.com}
 #'
-#' @return A tile plot made with `geom_tile()`, visualizing the bin sizes across
-#' different binned time and paths.
 #' @export
 plotBinTile <- function(scmpObj,
                         path_col = scmpObj@Parameters@path_col,

R/plotIntersect.R

@@ -1,22 +1,28 @@
-#' @title Generate UpSet Plot on Intersection of Significant Genes from scmpObject
+#' @title Generate UpSet Plot
 #'
-#' @param scmpObj An object of class ScMaSigPro
-#' @param min_intersection_size minimal number of observations in an intersection
+#' @description
+#' Generate UpSet Plot on Intersection of Significant Genes from scMaSigPro
+#' object. It is a wrapper around `ComplexUpset::upset`.
+#'
+#' @importFrom S4Vectors isEmpty
+#' @importFrom ComplexUpset upset intersection_matrix intersection_size upset_set_size
+#' @importFrom RColorConesa colorConesa
+#'
+#' @param scmpObj An object of class \code{\link{ScMaSigPro}}.
+#' @param min_intersection_size Minimal number of observations in an intersection
 #' for it to be included.
-#' @param width_ratio ratio of the overall set size width to intersection matrix
+#' @param width_ratio Ratio of the overall set size width to intersection matrix
 #' width.
-#' @param keep_empty_groups whether empty sets should be kept (including sets
+#' @param keep_empty_groups Whether empty sets should be kept (including sets
 #' which are only empty after filtering by size)
-#' @param show_sets_size the overall set sizes plot, e.g. from upset_set_size()
+#' @param show_sets_size The overall set sizes plot, e.g. from upset_set_size()
 #' (FALSE to hide)
 #'
-#' @return An UpSet plot visualizing the intersections of significant genes across pathways.
-#' @importFrom S4Vectors isEmpty
-#' @importFrom ComplexUpset upset intersection_matrix intersection_size upset_set_size
-#' @importFrom RColorConesa colorConesa
+#' @return ggplot2 plot object.
 #'
-#' @export
+#' @author Priyansh Srivastava \email{spriyansh29@@gmail.com}
 #'
+#' @export
 plotIntersect <- function(scmpObj, min_intersection_size = 2,
                           keep_empty_groups = TRUE,
                           width_ratio = 0.1, show_sets_size = FALSE) {