From 446d631c35f7ca63b2803505b4c6c6b9ef7431db Mon Sep 17 00:00:00 2001
From: ammichalowski <michaloa@mail.nih.gov>
Date: Thu, 1 Dec 2022 05:17:32 -0800
Subject: [PATCH] add SampleNames .R and .Rd files

---
 R/Sample_Names.R   | 63 ++++++++++++++++++++++++++++++++++++++++++++++
 man/SampleNames.Rd | 20 +++++++++++++++
 2 files changed, 83 insertions(+)
 create mode 100644 R/Sample_Names.R
 create mode 100644 man/SampleNames.Rd

diff --git a/R/Sample_Names.R b/R/Sample_Names.R
new file mode 100644
index 0000000..cfa4ef5
--- /dev/null
+++ b/R/Sample_Names.R
@@ -0,0 +1,63 @@
+# This code comes from NIDAP 'Metadata Table [scRNA-seq][CCBR]' code template https://nidap.nih.gov/workspace/vector/templates/ri.vector.main.template.51ea15ce-2be0-415f-902b-3c86175eb6cd
+# Documentation https://nidap.nih.gov/workspace/notepad/view/ri.notepad.main.notepad.53192624-dba0-4e63-9cbb-9bec776ede47
+# Example https://nidap.nih.gov/workspace/vector/view/ri.vector.main.workbook.00e7a393-4cd7-4f20-bdd2-1c1c0cfd1ea2?branch=master
+
+
+#' Extracting cell identities from the meta.data slot of Seurat-class object
+#' 
+#' Returns tabulation of cell identities present in the orig_ident column
+#' 
+#' It is recommended to run this function after doing SingleR annotations and before doing any visualizations/downstream analysis that requires inputting sample names.
+#' 
+#' @param SO Seurat-class object
+#' 
+#'   
+#' @export
+#' @return A table (data.frame) with the number of cells per each sample name (column names)
+
+
+SampleNames <- function(SO) {
+  # extract metadata table and sample names
+  
+  cat("\n Extracting Sample Names from metadata table: ")
+  if ("meta.data" %in% slotNames(SO)) {
+    if ("orig.ident" %in% colnames(SO@meta.data)) {
+      dim.df <-
+        as.data.frame(t(as.matrix(table(
+          SO@meta.data$orig.ident
+        ))))
+    } else {
+      dim.df <-
+        as.data.frame(t(as.matrix(table(
+          SO@meta.data$orig_ident
+        ))))
+    }
+    colnames(dim.df) <-
+      lapply(colnames(dim.df), function(x)
+        gsub(".h5", "", x))
+  } else {
+    if ("orig.ident" %in% colnames(SO$RNA@meta.data)) {
+      dim.df <-
+        as.data.frame(t(as.matrix(
+          table(SO$RNA@meta.data$orig.ident)
+        )))
+    } else {
+      dim.df <-
+        as.data.frame(t(as.matrix(
+          table(SO$RNA@meta.data$orig_ident)
+        )))
+    }
+    dim.df <-
+      as.data.frame(t(as.matrix(table(
+        SO$RNA@meta.data$orig.ident
+      ))))
+    colnames(dim.df) <-
+      lapply(colnames(dim.df), function(x)
+        gsub(".h5", "", x))
+  }
+  
+  # output data.frame
+  cat(sprintf("%g sample names returned", ncol(dim.df)))
+  return(dim.df)
+  
+}
\ No newline at end of file
diff --git a/man/SampleNames.Rd b/man/SampleNames.Rd
new file mode 100644
index 0000000..e740bb5
--- /dev/null
+++ b/man/SampleNames.Rd
@@ -0,0 +1,20 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/Sample_Names.R
+\name{SampleNames}
+\alias{SampleNames}
+\title{Extracting cell identities from the meta.data slot of Seurat-class object}
+\usage{
+SampleNames(SO)
+}
+\arguments{
+\item{SO}{Seurat-class object}
+}
+\value{
+A table (data.frame) with the number of cells per each sample name (column names)
+}
+\description{
+Returns tabulation of cell identities present in the orig_ident column
+}
+\details{
+It is recommended to run this function after doing SingleR annotations and before doing any visualizations/downstream analysis that requires inputting sample names.
+}