included quality control and filtering

R_script.R

@@ -33,3 +33,49 @@ table(seurat.combined$orig.ident)#track which sample originated from
 ##checkpt
 save(seurat.combined,file = 'seurat.combined.Rdata')
 seurat.combined=get(load(file = 'seurat.combined.Rdata'))
+
+#Quality control and making of violin plots
+#reference from https://satijalab.org/seurat/archive/v3.0/pbmc3k_tutorial.html
+seurat.combined[["percent.mt"]] <-
+  PercentageFeatureSet(seurat.combined, pattern = "^MT-")
+seurat.combined[["percent.ribo"]] <-
+  PercentageFeatureSet(seurat.combined, pattern = "^RP")
+plot1 <-
+  FeatureScatter(seurat.combined, feature1 = "nCount_RNA", feature2 = "percent.mt")
+plot2 <-
+  FeatureScatter(seurat.combined, feature1 = "nCount_RNA", feature2 = "nFeature_RNA")
+CombinePlots(plots = list(plot1, plot2))
+
+VlnPlot(
+  seurat.combined,
+  features = c("percent.ribo", "percent.mt"),
+  ncol = 2
+)
+VlnPlot(
+  seurat.combined,
+  features = c("nFeature_RNA", "nCount_RNA"),
+  ncol = 2
+)
+VlnPlot(
+  seurat.combined,
+  features = c("percent.ribo", "nCount_RNA"),
+  ncol = 2
+)
+#TODO: interpret violin plots to generate filtering parameters
+
+# Each sample, from a total of 1359 naive and 683 SR1 cells, was
+# first filtered to remove cells with low gene counts (naive, n = 92;
+# SR1, n = 37) that arise from aborted sequencing, and gene
+# expression was normalized between cells.
+##due to unknown parameter for filtering, parameters used are based on
+##https://blog.katastros.com/a?ID=af0c80dc-5f37-4a17-b7b4-31edb9e51c2b
+filtered.seurat.combined <-
+  subset(seurat.combined, subset = nFeature_RNA > 200 &
+           nCount_RNA > 1000 &
+           percent.mt < 20)
+filtered.seurat.combined
+table(filtered.seurat.combined$orig.ident)
+
+##checkpt
+save(filtered.seurat.combined, file = 'filtered.seurat.combined.Rdata')
+filtered.seurat.combined = get(load(file = 'filtered.seurat.combined.Rdata'))