version 0.1.1

DESCRIPTION

@@ -0,0 +1,36 @@
+Package: scRNAstat
+Type: Package
+Title: A Pipeline to Process Single Cell RNAseq Data
+Version: 0.1.1
+Authors@R: c(
+        person("Jianming","Zeng",
+            email = "jmzeng1314@163.com",
+            role = "aut"),
+        person(given = "Yonghe",
+           family = "Xia",
+           role = c("ctb", "cre"),
+           email = "xiayh17@gmail.com"),
+        person("Biotrainee group",role = c("cph","fnd"))
+    )
+Maintainer: Yonghe Xia <xiayh17@gmail.com>
+Description: A pipeline that can process single or multiple Single Cell RNAseq 
+    samples primarily specializes in Clustering and Dimensionality Reduction. 
+    Meanwhile we use common cell type marker genes for T cells, B cells, Myeloid cells, 
+    Epithelial cells, and stromal cells (Fiboblast, Endothelial cells, Pericyte,
+    Smooth muscle cells) to visualize the Seurat clusters, to facilitate labeling 
+    them by biological names. Once users named each cluster, they can evaluate the 
+    quality of them again and find the de novo marker genes also.
+License: AGPL (>= 3)
+Encoding: UTF-8
+LazyData: true
+RoxygenNote: 7.1.2
+Depends: R (>= 2.10)
+Imports: Seurat, ggplot2, stringr, clustree, magrittr, Matrix, dplyr,
+        patchwork
+NeedsCompilation: no
+Packaged: 2021-09-21 02:39:07 UTC; yonghe
+Author: Jianming Zeng [aut],
+  Yonghe Xia [ctb, cre],
+  Biotrainee group [cph, fnd]
+Repository: CRAN
+Date/Publication: 2021-09-22 08:10:02 UTC

MD5

@@ -0,0 +1,21 @@
+31de7f08a555dd57527ca0b08a1cd48b *DESCRIPTION
+1c9f0566fd793b5739bcd92627aa91ef *NAMESPACE
+af2aeb9cf224fb53d4feea3a132af876 *R/AJ064_small_last_sce.R
+e687f56fa7689a4b88df3b7b2de6e52c *R/AJ064_small_sce.R
+b9285b03752abf3bb29868ef423d4e39 *R/basic_filter.R
+c27cd23af10863e3092192ad60afb1ca *R/basic_find_markers.R
+d86e792691e003cff21e14e6c070e0b5 *R/basic_markers.R
+b803c51e36a9da420703bfc0a2ac6b0e *R/basic_qc.R
+7aae5c29be2039bf68dff9194953f311 *R/basic_workflow.R
+4f84b6a4364d620edfb9ac3a1ec59597 *R/global.R
+b56ff2b193ecba52f9ec7f3b10cca008 *R/utils-pipe.R
+f81552edb9b7d8ef56948d01f5db6749 *data/AJ064_small_last_sce.rda
+099afff1e9a10d71f7a5bfdd58358fa1 *data/AJ064_small_sce.rda
+b981eb1be99da48b154349b7dfb44a7d *man/AJ064_small_last_sce.Rd
+60f901b91a7ce544c2a4d96fc1962a9b *man/AJ064_small_sce.Rd
+9432069f95ceb1a1c69b88460715cc4c *man/basic_filter.Rd
+6970f9a2c2446b445d0b27c48536d733 *man/basic_find_markers.Rd
+62ac8723b7bc2f1995969a9e55aa2216 *man/basic_markers.Rd
+8f5a9658d03955eb0026bef6bf991971 *man/basic_qc.Rd
+71c7c629e288ba3a769eca273050fff5 *man/basic_workflow.Rd
+774d9de8e95aa151215efcd304549d41 *man/pipe.Rd

NAMESPACE

@@ -0,0 +1,38 @@
+# Generated by roxygen2: do not edit by hand
+
+export("%>%")
+export(basic_filter)
+export(basic_find_markers)
+export(basic_markers)
+export(basic_qc)
+export(basic_workflow)
+import(Seurat)
+import(clustree)
+import(ggplot2)
+import(patchwork)
+importFrom(Matrix,rowSums)
+importFrom(Seurat,DimPlot)
+importFrom(Seurat,FeatureScatter)
+importFrom(Seurat,FindClusters)
+importFrom(Seurat,FindNeighbors)
+importFrom(Seurat,FindVariableFeatures)
+importFrom(Seurat,GetAssay)
+importFrom(Seurat,NoLegend)
+importFrom(Seurat,NormalizeData)
+importFrom(Seurat,RunPCA)
+importFrom(Seurat,RunTSNE)
+importFrom(Seurat,RunUMAP)
+importFrom(Seurat,ScaleData)
+importFrom(Seurat,VariableFeatures)
+importFrom(Seurat,VlnPlot)
+importFrom(clustree,clustree)
+importFrom(dplyr,group_by)
+importFrom(dplyr,top_n)
+importFrom(ggplot2,coord_flip)
+importFrom(ggplot2,ggsave)
+importFrom(ggplot2,scale_y_continuous)
+importFrom(grDevices,dev.off)
+importFrom(grDevices,pdf)
+importFrom(magrittr,"%>%")
+importFrom(stringr,str_to_title)
+importFrom(utils,write.csv)

R/AJ064_small_last_sce.R

@@ -0,0 +1,4 @@
+#' Small `AJ064` Seurat Data After Processed
+#'
+#' An object of class Seurat
+"AJ064_small_last_sce"

R/AJ064_small_sce.R

@@ -0,0 +1,4 @@
+#' Small `AJ064` Seurat Data Set
+#'
+#' An object of class Seurat
+"AJ064_small_sce"

R/basic_filter.R

@@ -0,0 +1,32 @@
+#' basic_filter
+#'
+#' filter the genes which show expression less than 3 cells.
+#' filter the cells which percent_mito < 25 & percent_ribo > 3 & percent_hb < 10
+#' filter the cells which  nFeature_RNA > 300 & nFeature_RNA < 8000
+#'
+#' @param sce  An object of class Seurat
+#'
+#' @return sce.all.filt  An object of class Seurat
+#' @import Seurat
+#' @importFrom Matrix rowSums
+#' @export
+#'
+#' @examples
+#' basic_filter(AJ064_small_sce)
+#'
+basic_filter <-  function(sce){
+  if (!'percent_mito' %in% colnames(sce@meta.data)){
+    sce=basic_qc(sce,dir = tempdir())
+  }
+  selected_f <- rownames(sce)[Matrix::rowSums(sce@assays$RNA@counts > 0 ) > 3]
+  sce.all.filt <- subset(sce, features = selected_f)
+  sce.all.filt
+  sce.all.filt <- subset(sce.all.filt,
+                         percent_mito < 25 & percent_ribo > 3 & percent_hb < 10)
+
+  sce.all.filt <- subset(sce.all.filt,
+                         nFeature_RNA > 300 & nFeature_RNA < 8000  )
+  sce.all.filt
+
+  return(sce.all.filt)
+}

R/basic_find_markers.R

@@ -0,0 +1,58 @@
+#' Basic Find Markers
+#'
+#' To find de `novo` markers by `FindAllMarkers` from Seurat with default setting.
+#'
+#' @param sce An object of class Seurat
+#' @param group default:seurat_clusters, you can change it to  celltype
+#' @param dir path for saving results
+#'
+#' @return sce.markers a data.frame of markers.
+#'
+#' @import Seurat
+#' @importFrom ggplot2 ggsave coord_flip
+#' @importFrom utils write.csv
+#' @importFrom dplyr group_by top_n
+#' @export
+#'
+#' @examples
+#' \donttest{
+#' basic_find_markers(AJ064_small_last_sce,dir=tempdir())
+#' }
+basic_find_markers <-  function(sce,group='seurat_clusters',dir='.'){
+
+  Seurat::Idents(sce)= sce@meta.data[,group]
+  message( table(Seurat::Idents(sce)) )
+  n=length(table(Seurat::Idents(sce)))
+  # library(future)
+  # plan("multiprocess", workers = 8)
+  sce.markers <- Seurat::FindAllMarkers(object = sce, only.pos = TRUE, min.pct = 0.25,
+                                thresh.use = 0.25)
+  utils::write.csv(sce.markers,
+            file=file.path(dir,paste0(group,'_sce.markers.csv')))
+
+  top10 <- sce.markers %>% dplyr::group_by(cluster) %>% dplyr::top_n(10, avg_log2FC)
+  Seurat::DoHeatmap(sce,top10$gene,size=3)
+  ggplot2::ggsave(filename=file.path(dir,paste0(group,'_sce.markers_check_top10_heatmap.pdf')),
+          height = 15,width = 18)
+
+  p <- Seurat::DotPlot(sce, features = unique(top10$gene),
+               assay='RNA'  )  + coord_flip()
+
+
+  ggplot2::ggsave(file.path(dir,paste0(group,'_DotPlot_check_top10_markers_by_clusters.pdf')),
+         height = 18)
+
+  top3 <- sce.markers %>% dplyr::group_by(cluster) %>% top_n(3, avg_log2FC)
+  DoHeatmap(sce,top3$gene,size=3)
+  ggplot2::ggsave(file.path(dir,paste0(group,'_DoHeatmap_check_top3_markers_by_clusters.pdf')))
+
+
+  p <- DotPlot(sce, features = unique(top3$gene),
+               assay='RNA'  )  + coord_flip()
+
+
+  ggsave(file.path(dir,paste0(group,'_DotPlot_check_top3_markers_by_clusters.pdf')),height = 8)
+  save(sce.markers,file = file.path(dir,paste0(group,'_sce.markers.Rdata')))
+  return(sce.markers)
+
+}

R/basic_markers.R

@@ -0,0 +1,164 @@
+#' Basic Markers
+#'
+#' @param sce An object of class Seurat
+#' @param org human or mouse, default: human
+#' @param group default:`orig.ident`, you can change it to `seurat_clusters` or `celltype`
+#' @param dir the path for saving the figures by `DotPlot` with known famous markers.
+#'
+#' @return a list of figures by `DotPlot`
+#' @import ggplot2
+#' @import Seurat
+#' @import clustree
+#' @importFrom stringr str_to_title
+#' @importFrom grDevices pdf dev.off
+#' @export
+#'
+#' @examples
+#' \donttest{
+#' basic_markers(AJ064_small_last_sce,dir=tempdir())
+#' }
+basic_markers <-  function(sce,org='human',group='orig.ident',dir='.'){
+
+  # T Cells (CD3D, CD3E, CD8A),
+  # B cells (CD19, CD79A, MS4A1 [CD20]),
+  # Plasma cells (IGHG1, MZB1, SDC1, CD79A),
+  # Monocytes and macrophages (CD68, CD163, CD14),
+  # NK Cells (FGFBP2, FCG3RA, CX3CR1),
+  # Photoreceptor cells (RCVRN),
+  # Fibroblasts (FGF7, MME),
+  # Endothelial cells (PECAM1, VWF).
+  # epi or tumor (EPCAM, KRT19, PROM1, ALDH1A1, CD24).
+  #   immune (CD45+,PTPRC), epithelial/cancer (EpCAM+,EPCAM),
+  # stromal (CD10+,MME,fibo or CD31+,PECAM1,endo)
+
+  all_markers =c('PTPRC', 'CD3D', 'CD3E', 'CD4','CD8A',
+                'CD19', 'CD79A', 'MS4A1' ,
+                'IGHG1', 'MZB1', 'SDC1',
+                'CD68', 'CD163', 'CD14',
+                'TPSAB1' , 'TPSB2',  # mast cells,
+                'RCVRN','FPR1' , 'ITGAM' ,
+                'C1QA',  'C1QB',  # mac
+                'S100A9', 'S100A8', 'MMP19',# monocyte
+                'LAMP3', 'IDO1','IDO2',## DC3
+                'CD1E','CD1C', # DC2
+                'KLRB1','NCR1', # NK
+                'FGF7','MME', 'ACTA2',
+                'PECAM1', 'VWF',
+                'EPCAM' , 'KRT19', 'PROM1', 'ALDH1A1' )
+
+
+
+  # TH17 cells (C-12, CCR6+ and RORC)
+  # type 1 helper T cells (TH1; C-17, CXCR3+ and IFNG and TBX21)
+  # heterogeneous continuum of intermediate TH1/TH17 states (C-13, C-16 and C-19)
+  # with varying degrees of CXCR3, CCR6, CCR5 and CD161 surface protein expression and RORC and TBX21 expression
+  # CD161+ subset of type 2 helper T (TH2) cells (C-14),
+  # described as pathogenic, with higher expression of allergy-associated HPGDS and IL17RB
+  # naive (LEF1, SELL, TCF7),
+  # effector (IFNG),
+  # cytotoxicity (GZMB, PRF1),
+  # early and general exhaustion (PDCD1, CTLA4, ENTPD1 ) .
+  # antigen presentation (CD74, HLA-DRB1/5, HLA-DQA2)
+  # FCGR3A (FCGR3A+ Monocyte), KLRF1 (NK), FCER1A (DC), and PF4 (MP/platelets).
+
+  Tcells_markers = c('PTPRC', 'CD3D', 'CD3E', 'CD4','CD8A',
+                     'LEF1', 'SELL' , 'TCF7', # naive
+                     'FOXP3',
+                     'CCR6', 'RORC' ,  # TH17 cells
+                     'TBX21', 'CXCR3', 'IFNG', # type 1 helper T cells
+                     'CCR3','CCR4',
+                     'PDCD1',  'CTLA4','ENTPD1', # early and general exhaustion
+                     'GZMB', 'GZMK','PRF1', # cytotoxicity
+                     'IFNG',   'CCL3' ,'CXCR6' , 'ITGA1',  # effector
+                     'NKG7','KLRF1','MKI67','PF4','FCER1A','FCGR3A')
+
+  # mast cells, TPSAB1 and TPSB2
+  # B cell,  CD79A  and MS4A1 (CD20)
+  # naive B cells, such as MS4A1 (CD20), CD19, CD22, TCL1A, and CD83,
+  # plasma B cells, such as CD38, TNFRSF17 (BCMA), and IGHG1/IGHG4
+  Bcells_markers = c('CD3D','MS4A1','CD79A',
+                     'CD19', 'CD22', 'TCL1A',  'CD83', #  naive B cells
+                     'CD38','TNFRSF17','IGHG1','IGHG4', # plasma B cells,
+                     'TPSAB1' , 'TPSB2',  # mast cells,
+                     'PTPRC' )
+
+
+  Myeloid_markers =c('CD68', 'CD163', 'CD14',  'CD86','C1QA',  'C1QB',  # mac
+                    'S100A9', 'S100A8', 'MMP19',# monocyte
+                    'LAMP3', 'IDO1','IDO2',## DC3
+                    'MRC1','MSR1','ITGAE','ITGAM','ITGAX','SIGLEC7',
+                    'CD1E','CD1C', # DC2
+                    'XCR1','CLEC9A','FCER1A',# DC1
+                    'GZMB','TCF4','IRF7')
+
+  # epi or tumor (EPCAM, KRT19, PROM1, ALDH1A1, CD24).
+  # - alveolar type I cell (AT1; AGER+)
+  # - alveolar type II cell (AT2; SFTPA1)
+  # - secretory club cell (Club; SCGB1A1+)
+  # - basal airway epithelial cells (Basal; KRT17+)
+  # - ciliated airway epithelial cells (Ciliated; TPPP3+)
+
+  epi_markers = c(  'EPCAM' , 'KRT19', 'PROM1', 'ALDH1A1' ,
+                       'AGER','SFTPA1','SCGB1A1','KRT17','TPPP3',
+                       'KRT4','KRT14','KRT8','KRT18',
+                       'CD3D','PTPRC' )
+
+
+  stromal_markers = c('TEK',"PTPRC","EPCAM","PDPN","PECAM1",'PDGFRB',
+                     'CSPG4','GJB2', 'RGS5','ITGA7',
+                     'ACTA2','RBP1','CD36', 'ADGRE5','COL11A1','FGF7', 'MME')
+
+
+
+  # basal (e.g., KRT5, ACTA2, MYLK, SNAI2),
+  # luminal progenitor (TNFRSF11A (RANK), KIT),
+  # mature luminal cells (ESR1, PGR, FOXA1)
+
+  brca_markers = c(  'EPCAM' , 'KRT19', 'PROM1', 'ALDH1A1' ,
+                       'KRT5', 'ACTA2', 'MYLK', 'SNAI2', # basal
+                       'RANK', 'KIT', # luminal progenitor
+                       'ESR1', 'PGR', 'FOXA1',# mature luminal cells
+                       'KRT4','KRT14','KRT8','KRT18',
+                       'CD3D','PTPRC' )
+  if(org=='human'){
+  }else if(org=='mouse'){
+    all_markers=str_to_title(all_markers)
+    Tcells_markers=str_to_title(Tcells_markers)
+    Bcells_markers=str_to_title(Bcells_markers)
+    Myeloid_markers=str_to_title(Myeloid_markers)
+    epi_markers=str_to_title(epi_markers)
+    stromal_markers=str_to_title(stromal_markers)
+    brca_markers=str_to_title(brca_markers)
+  } else {
+    stop('So far, we only accept human and mouse')
+  }
+  genes_to_check=list(
+    all_markers=unique(all_markers),
+    Tcells_markers=unique(Tcells_markers),
+    Bcells_markers=unique(Bcells_markers),
+    Myeloid_markers=unique(Myeloid_markers),
+    epi_markers=unique(epi_markers),
+    stromal_markers=unique(stromal_markers),
+    brca_markers=unique(brca_markers)
+  )
+  # dpl: dotplot, list
+  dpl <- lapply(genes_to_check, function(cg){
+    DotPlot(sce, assay = "RNA",
+            features = cg,
+            group.by =  group  
+
+      ) + coord_flip()
+  })
+
+  pdf(file.path(dir,
+                paste0( 'markers_based_on_',group,'.pdf')))
+  lapply(1:length(genes_to_check), function(i){
+    p=names(genes_to_check)[i] 
+    print(dpl[[i]]+ggtitle(p))
+  })
+  dev.off()
+  return(dpl)
+
+}
+
+