Clean up Roxygen parametrs and descriptions

.Rhistory

@@ -67,8 +67,8 @@ complexity.limits = c(NA,NA),
 mad.complexity.limits = c(5,NA),
 topNgenes.limits = c(NA,NA),
 mad.topNgenes.limits = c(5,5),
-n.topgnes=20,
-do.doublets.fitler=T
+n.topgenes=20,
+do.doublets.filter=T
 )
 ggsave(SO_filtered$plots$PostFilterCombined, filename = "./images/QC1.png", width = 10, height = 10)
 ggsave(SO_filtered$plots$ViolinPlotCombine, filename = "./images/QC2.png", width = 10, height = 10)
@@ -315,12 +315,12 @@ dev.off()
 modScore
 MS_object=modScore(object=Anno_SO$object,
 marker.table=Marker_Table,
-use_columns = c("Macrophages","M1","M2" )
-ms_threshold=c("Macrophages .40","M1 .25","M2 .14"),
+use.columns = c("Macrophages","M1","M2" )
+ms.threshold=c("Macrophages .40","M1 .25","M2 .14"),
 MS_object=modScore(object=Anno_SO$object,
 marker.table=Marker_Table,
-use_columns = c("Macrophages","M1","M2" ),
-ms_threshold=c("Macrophages .40","M1 .25","M2 .14"),
+use.columns = c("Macrophages","M1","M2" ),
+ms.threshold=c("Macrophages .40","M1 .25","M2 .14"),
 use_assay = "SCT",
 general.class=c("Macrophages"),
 lvl.vec = c('Macrophages-M1','Macrophages-M2'),
@@ -333,8 +333,8 @@ step.size = 0.1
 modScore
 MS_object=modScore(object=Anno_SO$object,
 marker.table=Marker_Table,
-use_columns = c("Macrophages","M1","M2" ),
-ms_threshold=c("Macrophages .40","M1 .25","M2 .14"),
+use.columns = c("Macrophages","M1","M2" ),
+ms.threshold=c("Macrophages .40","M1 .25","M2 .14"),
 use_assay = "SCT",
 general.class=c("Macrophages"),
 multi.lvl = FALSE,
@@ -347,8 +347,8 @@ step.size = 0.1
 modScore
 MS_object=modScore(object=Anno_SO$object,
 marker.table=Marker_Table,
-use_columns = c("Macrophages","M1","M2" ),
-ms_threshold=c("Macrophages .40","M1 .25","M2 .14"),
+use.columns = c("Macrophages","M1","M2" ),
+ms.threshold=c("Macrophages .40","M1 .25","M2 .14"),
 general.class=c("Macrophages"),
 multi.lvl = FALSE,
 reduction = "umap",
@@ -359,8 +359,8 @@ step.size = 0.1
 )
 MS_object=modScore(object=Anno_SO$object,
 marker.table=Marker_Table,
-use_columns = c("Macrophages","M1","M2" ),
-ms_threshold=c("Macrophages .40","M1 .25","M2 .14"),
+use.columns = c("Macrophages","M1","M2" ),
+ms.threshold=c("Macrophages .40","M1 .25","M2 .14"),
 multi.lvl = FALSE,
 reduction = "umap",
 nbins = 10,
@@ -370,8 +370,8 @@ step.size = 0.1
 )
 MS_object=modScore(object=Anno_SO$object,
 marker.table=Marker_Table,
-use_columns = c("Macrophages","M1","M2" ),
-ms_threshold=c("Macrophages .40","M1 .25","M2 .14"),
+use.columns = c("Macrophages","M1","M2" ),
+ms.threshold=c("Macrophages .40","M1 .25","M2 .14"),
 general.class=c("Macrophages","M1","M2"),
 multi.lvl = FALSE,
 reduction = "umap",
@@ -383,8 +383,8 @@ step.size = 0.1
 Marker_Table
 MS_object=modScore(object=Anno_SO$object,
 marker.table=Marker_Table,
-use_columns = c("Macrophages","Monocytes","CD8_T" ),
-ms_threshold=c("Macrophages .40","Monocytes .25","CD8_T .14"),
+use.columns = c("Macrophages","Monocytes","CD8_T" ),
+ms.threshold=c("Macrophages .40","Monocytes .25","CD8_T .14"),
 general.class=c("Macrophages","Monocytes","CD8_T"),
 multi.lvl = FALSE,
 reduction = "umap",
@@ -395,8 +395,8 @@ step.size = 0.1
 )
 MS_object=modScore(object=Anno_SO$object,
 marker.table=Marker_Table,
-use_columns = c("Macrophages","Neutrophils","CD8_T" ),
-ms_threshold=c("Macrophages .40","Neutrophils .25","CD8_T .14"),
+use.columns = c("Macrophages","Neutrophils","CD8_T" ),
+ms.threshold=c("Macrophages .40","Neutrophils .25","CD8_T .14"),
 general.class=c("Macrophages","Neutrophils","CD8_T"),
 multi.lvl = FALSE,
 reduction = "umap",
@@ -407,8 +407,8 @@ step.size = 0.1
 )
 MS_object=modScore(object=Anno_SO$object,
 marker.table=Marker_Table,
-use_columns = c("Neutrophils","Macrophages","CD8_T" ),
-ms_threshold=c("Neutrophils .25","Macrophages .40","CD8_T .14"),
+use.columns = c("Neutrophils","Macrophages","CD8_T" ),
+ms.threshold=c("Neutrophils .25","Macrophages .40","CD8_T .14"),
 general.class=c("Neutrophils","Macrophages","CD8_T"),
 multi.lvl = FALSE,
 reduction = "umap",

.gitignore

@@ -16,3 +16,7 @@ inst/doc
 *.rds
 /doc/
 /Meta/
+
+.github
+.github.zip
+decision_log.md

DESCRIPTION

@@ -92,4 +92,5 @@ Imports:
     htmlwidgets,
     scDblFinder
     , BiocParallel
+    , patchwork
 Config/testthat/edition: 3

NAMESPACE

@@ -14,11 +14,11 @@ export(dotPlotMet)
 export(dualLabeling)
 export(filterQC)
 export(filterSeuratObjectByMetadata)
+export(harmonyBatchCorrect)
 export(heatmapSC)
 export(launch_module_score_app)
 export(modScore)
 export(nameClusters)
-export(object)
 export(palantir_api_call)
 export(plotMetadata)
 export(processRawData)
@@ -46,12 +46,16 @@ import(httr)
 import(jsonlite)
 import(magrittr)
 import(parallel)
+importFrom(tidyr, pivot_longer)
 import(plotly)
 import(quantmod)
 import(reshape2)
 import(rlang)
 import(scales)
+importFrom(stringr, str_split)
+import(stringr)
 import(tibble)
+import(tidyr)
 import(tidyverse)
 import(tools)
 import(utils)
@@ -135,6 +139,7 @@ importFrom(gridExtra,arrangeGrob)
 importFrom(gridExtra,tableGrob)
 importFrom(htmlwidgets,saveWidget)
 importFrom(magrittr,"%>%")
+importFrom(patchwork,plot_layout)
 importFrom(plotly,as_widget)
 importFrom(plotly,ggplotly)
 importFrom(plotly,plot_ly)

R/3D_tSNE.R

@@ -19,6 +19,20 @@
 #' @importFrom htmlwidgets saveWidget
 #'
 #' @export
+#'
+#' @return A list with a plotly 3D TSNE plot (`figure`) and TSNE coordinates
+#' (`tsne.df`).
+#'
+#' @examples
+#' \dontrun{
+#' out <- tSNE3D(
+#'   object = seurat_obj,
+#'   color.variable = "cell_type",
+#'   label.variable = "orig.ident",
+#'   npcs = 15,
+#'   save.plot = FALSE
+#' )
+#' }
 
 tSNE3D <- function(object,
                    color.variable,

R/AggregateCounts.R

@@ -1,33 +1,44 @@
-##' @title Aggregate Counts (Pseudobulk)
-##' @description Compute pseudobulk expression by averaging expression across groups
-##'              defined by one or more metadata columns, and return a tidy table.
-##' @details Uses Seurat's `AverageExpression()` on the `SCT` assay to compute
-##'          group-wise average expression for each feature. Also produces a
-##'          bar plot (via `ggplot2`/`plotly`) showing the number of cells per
-##'          pseudobulk group and warns if any group contains only one cell.
-##'
-##' @param object Seurat-class object.
-##' @param var.group Character vector of metadata column names used to define
-##'                  pseudobulk groups. When multiple columns are supplied, an
-##'                  interaction of these columns defines the groups.
-##' @param slot Character name of the assay data layer passed to
-##'             `AverageExpression()` (e.g., "data", "counts", or "scale.data").
-##'
-##' @return A data.frame of pseudobulk expression with columns `Gene` followed by
-##'         one column per pseudobulk group. Column names are sanitized to
-##'         contain only alphanumeric/underscore characters.
-##'
-##' @import Seurat
-##' @import tidyverse
-##' @import ggplot2
-##' @import plotly
-##' @importFrom dplyr select
-##'
-##' @export
+#' @title Aggregate Counts (Pseudobulk)
+#' @description Compute pseudobulk expression by averaging expression across groups
+#'              defined by one or more metadata columns, and return a tidy table.
+#' @details Uses Seurat's `AverageExpression()` on the `SCT` assay to compute
+#'          group-wise average expression for each feature. Also produces a
+#'          bar plot (via `ggplot2`/`plotly`) showing the number of cells per
+#'          pseudobulk group and warns if any group contains only one cell.
+#'
+#' @param object Seurat-class object.
+#' @param var.group Character vector of metadata column names used to define
+#'                  pseudobulk groups. When multiple columns are supplied, an
+#'                  interaction of these columns defines the groups.
+#' @param slot Character name of the assay data layer passed to
+#'             `AverageExpression()` (e.g., "data", "counts", or "scale.data").
+#' @param interactive If TRUE, draw plotly plot (default is FALSE)          
+#'
+#' @import Seurat
+#' @import tidyverse
+#' @import ggplot2
+#' @import plotly
+#' @importFrom dplyr select
+#'
+#' @export
+#'
+#' @return A data.frame of pseudobulk expression with columns `Gene` followed by
+#'         one column per pseudobulk group. Column names are sanitized to
+#'         contain only alphanumeric/underscore characters.
+#'
+#' @examples
+#' \dontrun{
+#' out <- aggregateCounts(
+#'   object = seurat_obj,
+#'   var.group = c("orig.ident", "condition"),
+#'   slot = "data"
+#' )
+#' }
 
 aggregateCounts <- function(object,
                             var.group,
-                            slot){
+                            slot="data",
+                            interactive=FALSE){
 
 
   ## --------------- ##
@@ -73,16 +84,19 @@ aggregateCounts <- function(object,
       ))
     }
 
-    p <- ggplotly(ggplot(df, aes(x = pseudobulk_group, y = Freq)) +
+    p <- ggplot(df, aes(x = pseudobulk_group, y = Freq)) +
                     geom_bar(stat = "identity", position = "stack") +
                     labs(y = "Counts", x = "Pseudobulk Groups", title = "Number of Cells in each Pseudobulk Group") +
-                    theme(axis.text.x = element_text(angle = 90, hjust = 1)))
+                    theme(axis.text.x = element_text(angle = 90, hjust = 1))
 
-    print(p)
+    if(interactive==T){
+      p <- ggplotly(p)
+    }
 
   } else {
     stop("All columns in var.group must be factors or characters")
   }
 
-  return(pseudobulk)
+  return(list(data=pseudobulk,
+              plots=p))
 }

R/Annotate_Cell_Types.R

@@ -1,8 +1,7 @@
-#' @title Annotating cell types using SingleR module
-#' @description SingleR is an automatic annotation method for single-cell
-#' RNA sequencing (scRNAseq) data (Aran et al. 2019). Given a reference dataset
-#' of samples (single-cell or bulk) with known labels, it labels new cells
-#' from a test dataset based on similarity to the reference.
+#' @title Cell Type Annotation with SingleR [CCBR] [scRNA-seq]
+#' @description Annotate the cell types of your cells using SingleR (Aran et al., 2019). This
+#' function takes a combined Seurat object after PC reduction and assigns cells
+#' to a category (for example, stem cells or T cells) based on genomic profile.
 #' @details This function is Step 5 of the basic Single-Cell RNA-seq workflow.
 #' It is the starting point for downstream visualization, subsetting, and
 #' analysis. It takes a combined seurat object as input, such as the one created
@@ -22,8 +21,7 @@
 #' Default is NULL
 #' @param use.clusters Provide cluster identities for each cell.
 #' Default is NULL
-
-
+#'
 #'
 #' @import Seurat
 #' @import cowplot
@@ -36,9 +34,17 @@
 #' @export
 #'
 #' @return a Seurat object with additional metadata
-
-
-
+#'
+#' @examples
+#' \dontrun{
+#' out <- annotateCellTypes(
+#'   object = combined_so,
+#'   species = "Human",
+#'   reduction.type = "umap"
+#' )
+#' }
+#'
+#'
 annotateCellTypes <- function(object,
                               species = "Mouse",
                               reduction.type = "umap",

R/Color_by_Gene.R

@@ -35,8 +35,17 @@
 #' @export
 #'
 #' @return a Seurat object with additional metadata or gene table and plot
-
-
+#'
+#' @examples
+#' \dontrun{
+#' out <- colorByGene(
+#'   object = anno_so,
+#'   samples.to.include = c("sample1", "sample2"),
+#'   gene = c("CD3D", "MS4A1"),
+#'   reduction.type = "umap"
+#' )
+#' }
+#'
 
 colorByGene <- function(object,
                         samples.to.include,
@@ -65,16 +74,14 @@ colorByGene <- function(object,
   ## --------------- ##
 
 
-  print(object)
   # checking for samples
-  if(any(grepl('c\\(|\\[\\]',samples))) {
-    samples = eval(parse(text = gsub('\\[\\]', 'c()', samples)))
-  }else{
-    samples=samples
+  if (is.character(samples.to.include) && length(samples.to.include) == 1 &&
+      grepl('c\\(|\\[\\]', samples.to.include)) {
+    samples.to.include <- eval(parse(text = gsub('\\[\\]', 'c()', samples.to.include)))
   }
   # if none specified, using ALL
-  if (length(samples) == 0) {
-    samples = unique(object@meta.data$orig.ident)
+  if (length(samples.to.include) == 0) {
+    samples.to.include = unique(object@meta.data$orig.ident)
   }
 
   # Fix for underscore
@@ -85,13 +92,13 @@ colorByGene <- function(object,
     names(sample.name) = names(object@active.ident)
     object@active.ident <- as.factor(vector())
     object@active.ident <- sample.name
-    object.sub = subset(object, ident = samples)
+    object.sub = subset(object, ident = samples.to.include)
   } else {
     sample.name = as.factor(object@meta.data$orig.ident)
     names(sample.name) = names(object@active.ident)
     object@active.ident <- as.factor(vector())
     object@active.ident <- sample.name
-    object.sub = subset(object, ident = samples)
+    object.sub = subset(object, ident = samples.to.include)
   }
 
   #Check input for missing genes