checked composition of entire data

Author: yifand64

Diff for: .DS_Store

@@ -0,0 +1,75 @@
+---
+title: "mature neuron"
+author: "Yifan Duan"
+date: "2024-09-10"
+output: html_document
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE)
+```
+
+
+```{r}
+library(Seurat)
+library(BPCells)
+library(dplyr)
+library(ggplot2)
+library(ggrepel)
+library(patchwork)
+library(Matrix)
+library(cowplot)
+library(irlba)
+```
+
+
+```{r visualizing composition change over time, eval=FALSE}
+# just ignore this one, this is diagnostic for composition
+flu_obj <- readRDS("data/flu.Rds")
+View(flu_obj)
+
+levels(flu_obj$cell_type__ontology_label)
+
+flu_obj$simple_label <- case_when(
+  flu_obj$cell_type__ontology_label %in% c("neural progenitor cell", "vomeronasal sensory neuron", "olfactory receptor cell") ~ "Neuron",
+  flu_obj$cell_type__ontology_label %in% c("basal cell", "brush cell", "ciliated epithelial cell", "epithelial cell", "glandular epithelial cell", "goblet cell", "ionocyte", "serous secreting cell") ~ "Epithelial",
+  flu_obj$cell_type__ontology_label %in% c("alpha-beta T cell", "B cell", "CD4-positive, alpha-beta T cell", "CD8-positive, alpha-beta T cell", "dendritic cell", "gamma-delta T cell", "granulocyte monocyte progenitor cell", "group 2 innate lymphoid cell", "group 3 innate lymphoid cell", "macrophage", "mast cell", "monocyte", "natural killer cell", "neutrophil", "precursor B cell", "hematopoietic stem cell", "plasmacytoid dendritic cell", "plasma cell") ~ "Immune",
+  TRUE ~ "Other")
+
+flu_obj$simple_label <- as.factor(flu_obj$simple_label)
+
+# list of "other" celltype
+# chondrocyte
+# endothelial cell
+# fibroblast
+# stromal cell
+# smooth muscle cell
+# pericyte
+# osteoclast
+# osteoblast
+# smooth muscle cell
+
+lng_obj <- subset(flu_obj, subset = Tissue.Region == "LNG")
+
+comp_change <- as.data.frame(table(lng_obj$simple_label, lng_obj$Time.Point))
+colnames(comp_change) <- c("Celltype", "Timepoint", "Counts")
+comp_change <- comp_change |>
+  mutate(Timepoint = factor(Timepoint, levels = c("Naive", "2 dpi", "5 dpi", "8 dpi", "14 dpi"))) 
+
+
+# need to get the proportion of celltype per timepoint
+total_count <- comp_change |> group_by(Timepoint) |> summarise(total = sum(Counts)) |> ungroup()
+total_count |> ggplot(aes(x = Timepoint, y = total)) + 
+  geom_bar(stat = "identity") + theme_cowplot()
+
+comp_change |> group_by(Timepoint, Celltype) |> summarise(avg_count = Counts) |> ungroup() |> mutate(total_count = rep(total_count$total, each = 4)) |> mutate(prop = avg_count / total_count) |>
+  ggplot(aes(x = Timepoint, y = prop, fill = Celltype)) + 
+  geom_bar(stat = "identity") + theme_cowplot() + 
+  theme(legend.position = "top", axis.text.x = element_text(angle = 90, hjust = 1)) 
+```
+
+
+```{r}
+
+```
+

Diff for: figure/DE_genes_grp6.pdf

@@ -89,11 +89,12 @@ for (res in resolutions) {
                              algorithm = 4) # leiden
   
   # Store the clustering results with a label corresponding to the resolution
-  cluster_column <- paste0("RNA_snn_res.", res)
-  [email protected][[paste0("clusters_res_", res)]] <- [email protected][[cluster_column]]
+  #cluster_column <- paste0("RNA_snn_res.", res)
 }
 
-DimPlot(neuron_obj, reduction = "umap", group.by = "clusters_res_0.2")
+DimPlot(neuron_obj, reduction = "umap", group.by = "cell_type__ontology_label")
+DimPlot(neuron_obj, reduction = "umap", group.by = "donor_id")
+
 ```
 
 
@@ -102,8 +103,50 @@ DimPlot(neuron_obj, reduction = "umap", group.by = "clusters_res_0.2")
 neuron_obj[["RNA"]]$data <- neuron_obj[["RNA"]]$counts
 
 Idents(neuron_obj) <- "RNA_snn_res.0.2"
-FindMarkers(neuron_obj, ident.1 = "1", assay = "RNA")
+#FindMarkers(neuron_obj, ident.1 = "6", assay = "RNA")
 
 dim(neuron_obj[["RNA"]]$counts)
+
+FeaturePlot(neuron_obj, features = c("Omp", "Stoml3", "Cnga2", "Adcy3"))
+```
+
+
+```{r investigating doublet}
+# 1. higher counts than the rest
+# 2. mixture of markers 
+grp6_marker <- FindMarkers(neuron_obj, ident.1 = "6", assay = "RNA")
+doublet_obj <- subset(neuron_obj, subset = RNA_snn_res.0.2 == "6")
+
+library(EnhancedVolcano)
+pdf("figure/DE_genes_grp6.pdf")
+EnhancedVolcano(grp6_marker, 
+                rownames(grp6_marker),
+                x ="avg_log2FC", 
+                y ="p_val_adj")
+dev.off()
+
+DimPlot(doublet_obj, reduction = "umap", group.by = "Cluster.Label")
+cluster_table <- table(doublet_obj$Cluster.Label)
+cluster_table <- cluster_table[cluster_table != 0]
+
+VlnPlot(neuron_obj, features = "nCount_RNA", group.by = "seurat_clusters")
+VlnPlot(neuron_obj, features = "nFeature_RNA", group.by = "seurat_clusters")
+
+library(DoubletFinder)
+neuron_obj <- doubletFinder_v3(neuron_obj, PCs = 1:10, pN = 0.25, pK = best_pK, nExp = 500)
+
+
+```
+
+
+```{r}
+saveRDS(neuron_obj, file = "data/neuron.Rds")
+
+FeaturePlot(neuron_obj, features = c("Nqo1","Acsm4", "Nfix", "Ncam2"))
+# dorsal acsm4, nqo1
+# ventral nfix, ncam2
+
+mature_neuron_obj <- subset(neuron_obj, subset = RNA_snn_res.0.2 == c("1", "2", "4", "6"))
+saveRDS(mature_neuron_obj, "data/mature_neuron.Rds")
 ```