Upload 5 files

0.IntegrateData.R

@@ -0,0 +1,82 @@
+#20230909尝试整合mPFC rAAV与V1 RV数据
+
+RV_Infected<-RV_infected_mock_intergreted[,RV_infected_mock_intergreted$sample%in%"RV_infected"]
+RV_MOCK<-RV_infected_mock_intergreted[,RV_infected_mock_intergreted$sample%in%"MOCK"]
+
+rAAV_Infected<-all.Adult[,all.Adult$BC_label%in%"Barcoded"]
+rAAV_MOCK<-all.Adult[,all.Adult$BC_label%in%"Unbarcoded"]
+
+VIRUS_LIST<-list(RV_Infected,RV_MOCK,rAAV_Infected,rAAV_MOCK)
+virus_sample_name<- c('RV_infected', 'RV_MOCK',"rAAV_infected","rAAV_MOCK")
+
+for (i in 1:length(VIRUS_LIST)){
+  VIRUS_LIST[[i]]@meta.data$sample <- virus_sample_name[[i]]}
+
+p <- list()
+for (i in 1:4){
+  p[[i]] <- DimPlot(VIRUS_LIST[[i]], reduction = 'tsne') + 
+    labs(title = virus_sample_name[i]) +
+    guides(colour=guide_legend(ncol=2, override.aes = list(size=2)))
+}
+plot_grid(plotlist = p, ncol =2)
+
+#整合
+features <- SelectIntegrationFeatures(object.list = VIRUS_LIST)
+adult.anchors <- FindIntegrationAnchors(object.list = VIRUS_LIST, 
+                                        anchor.features = features)
+adult.inte <- IntegrateData(anchorset = adult.anchors)
+adult.inte <- ScaleData(adult.inte, verbose = FALSE)
+adult.inte <- RunPCA(adult.inte, npcs = 10, verbose = FALSE)
+adult.inte <- FindNeighbors(adult.inte, reduction = "pca", dims = 1:10)
+adult.inte <- FindClusters(adult.inte, resolution = 1)
+adult.inte <- RunUMAP(adult.inte, reduction = "pca", dims = 1:10)
+adult.inte <- RunTSNE(adult.inte, reduction = "pca", dims = 1:10)
+adult.inte <-rAAV_RV.inte
+adult.inte$seurat_clusters
+VlnPlot(adult.inte,
+        features = c("Snap25",'Gad1',"Sox6","Col23a1","Pvalb","Sst","Prox1","Vip","Lamp5","Slc17a7",
+                     "Rorb","Foxp2","Bcl6","Ctss","Slc1a3","Mog","Cux2","Rorb","Deptor","Etv1","Pou3f1",'Oprk1','Foxp2',"Syt6","Tshz2"),stack = TRUE, flip = TRUE,  assay = 'RNA') + 
+  NoLegend()
+VlnPlot(adult.inte,
+        features = c("Snap25",'Gad1','Gad2',"Bcl11b","Sox6",
+                     "Col23a1","Pvalb","Sst","Prox1","Vip","Lamp5","Slc17a7",
+                     "Rorb","Foxp2","Bcl6","Ctss","Slc1a3","Mog","Cux2",
+                     "Rorb","Deptor","Etv1","Pou3f1",'Oprk1','Foxp2',"Syt6","Tshz2"),
+        stack = TRUE, flip = TRUE,  assay = 'RNA') + NoLegend()
+
+VlnPlot(adult.inte,
+        features = c("Snap25",'Gad1','Gad2',"Sox6",
+                     "Pvalb","Sst","Prox1","Vip","Lamp5","Aldoc", "Slc1a3", "Aqp4","Slc17a6","Slc17a7",
+                     'Calb1','Otof','Hap1','Cux2','Rorb','Tnnc1','Rspo1','Bdnf',
+                     'Ptn','Sema3d','Cpne7','Fstl5','Slc24a2','Oprk1','Penk',"Col23a1",
+                     'Syt6','Pcp4','Pou3f1','S100b','Etv1','Scn4b','Adamts2','Dlk1','Npr3',
+                     'Tshz2','Cbln2','Grp',"Pdgfra", "C1ql1", "Olig2", "Olig1","Fcrls", "Trem2"),
+        stack = TRUE, flip = TRUE,  assay = 'RNA') + NoLegend()
+level_maintype<-c( "Pvalb","Sst","Vip/Lamp5","Astro","Oligo","Microglia","L2/3IT","L4/5IT","L6IT","L5NP","L6CT","L5ET")
+Idents(adult.inte) <- factor(Idents(adult.inte),levels=level_maintype)
+levels(Idents(adult.inte))
+adult.inte$Maintype <- as.character(adult.inte$seurat_clusters)
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(9))] <- "Pvalb"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(11))] <- "Sst"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(13))] <- "Vip/Lamp5"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(0,1,6,9))] <- "L2/3IT"#cux2
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(5,21,22))] <- "L4/5IT"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(3,18))] <- "L6IT"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(2,22))] <- "L6CT"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(12,17))] <- "L5ET"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(8,15))] <- "L5NP"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(10,14,19))] <- "Microglia"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(4,16,17))] <- "Astro"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(7,20))] <- "Oligo"
+Idents(adult.inte) <- 'Maintype'
+VlnPlot(adult.inte,
+        features = c('Gad1',"Sox6","Pvalb","Sst","Prox1","Vip","Lamp5","Slc17a7","Col23a1",
+                     "Rorb","Foxp2","Bcl6","Ctss","Slc1a3","Mog"),group.by = "Maintype",stack = TRUE, flip = TRUE, fill.by="ident", assay = 'RNA') + 
+  NoLegend()
+
+DimPlot(adult.inte, split.by = 'sample', reduction = 'tsne', label = T, ncol = 2) +
+  theme(axis.line = element_blank(), axis.ticks = element_blank(), 
+        axis.text = element_blank(), plot.title = element_text(size = 30)) +
+  labs(x='', y='')
+saveRDS(adult.inte,"H:/Project1_RV Receptor Projection/FIG1.皮层单细胞RV rAAV感染数据分析/rAAV_RV.inte2.RDS")
+ 

1.Maintype2.R

@@ -0,0 +1,86 @@
+#20230909尝试整合mPFC rAAV与V1 RV数据
+install.packages("ape")
+RV_Infected<-RV_infected_mock_intergreted[,RV_infected_mock_intergreted$sample%in%"RV_infected"]
+RV_MOCK<-RV_infected_mock_intergreted[,RV_infected_mock_intergreted$sample%in%"MOCK"]
+
+rAAV_Infected<-all.Adult[,all.Adult$BC_label%in%"Barcoded"]
+rAAV_MOCK<-all.Adult[,all.Adult$BC_label%in%"Unbarcoded"]
+
+VIRUS_LIST<-list(RV_Infected,RV_MOCK,rAAV_Infected,rAAV_MOCK)
+virus_sample_name<- c('RV_infected', 'RV_MOCK',"rAAV_infected","rAAV_MOCK")
+
+for (i in 1:length(VIRUS_LIST)){
+  VIRUS_LIST[[i]]@meta.data$sample <- virus_sample_name[[i]]}
+
+p <- list()
+for (i in 1:4){
+  p[[i]] <- DimPlot(VIRUS_LIST[[i]], reduction = 'tsne') + 
+    labs(title = virus_sample_name[i]) +
+    guides(colour=guide_legend(ncol=2, override.aes = list(size=2)))
+}
+plot_grid(plotlist = p, ncol =2)
+
+#整合
+features <- SelectIntegrationFeatures(object.list = VIRUS_LIST)
+adult.anchors <- FindIntegrationAnchors(object.list = VIRUS_LIST, 
+                                        anchor.features = features)
+adult.inte <- IntegrateData(anchorset = adult.anchors)
+adult.inte <- ScaleData(adult.inte, verbose = FALSE)
+adult.inte <- RunPCA(adult.inte, npcs = 10, verbose = FALSE)
+adult.inte <- FindNeighbors(adult.inte, reduction = "pca", dims = 1:20)
+adult.inte <- FindClusters(adult.inte, resolution = 1)
+adult.inte <- RunUMAP(adult.inte, reduction = "pca", dims = 1:10)
+adult.inte <- RunTSNE(adult.inte, reduction = "pca", dims = 1:10)
+
+adult.inte$seurat_clusters
+
+VlnPlot(adult.inte,
+        features = c("Snap25",'Gad1','Gad2',"Sox6",
+                     "Pvalb","Sst","Prox1","Vip",
+                     "Aldoc", "Slc1a3", "Aqp4", "Olig2", "Olig1","Pdgfra", "C1ql1","Fcrls", "Trem2",
+                     "Slc17a7",'Calb1','Cux2','Rorb','Bdnf',
+                     'Ptn',"Col23a1",
+                     'Tshz2','Cbln2','Grp',"Syt6",
+                     'Pou3f1','Etv1','Adamts2','Dlk1','Npr3'),
+        stack = TRUE, flip = TRUE,  assay = 'RNA') + NoLegend()
+level_maintype<-c( "Pvalb","Sst","Vip/Lamp5","Astro","Oligo","Microglia","L2/3IT","L4/5IT","L6IT","L5NP","L6CT","L5ET")
+Idents(adult.inte) <- factor(Idents(adult.inte),levels=level_maintype)
+levels(Idents(adult.inte))
+
+Idents(adult.inte) <- 'seurat_clusters'
+Idents(adult.inte) <- 'Maintype'
+adult.inte<- BuildClusterTree(object = adult.inte, dims=1:10)
+phy <- Tool(object = adult.inte, slot = 'BuildClusterTree')
+plot(phy)
+
+adult.inte$Maintype <- as.character(adult.inte$seurat_clusters)
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(8))] <- "Pvalb"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(9))] <- "Sst"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(13,27))] <- "Vip/Lamp5"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(2,14))] <- "L2/3IT"#cux2
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(0,6))] <- "L4/5IT"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(3,4,23,25,19))] <- "L6IT"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(1))] <- "L6CT"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(11))] <- "L5ET"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(16))] <- "L5NP"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(10,15,21))] <- "Microglia"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(5,17,24,7))] <- "Astro"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(12,18,20,22,26))] <- "Oligo"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(7))] <- "7"
+adult.inte$Maintype[which(adult.inte$Maintype %in% c(19))] <- "19"
+Idents(adult.inte) <- 'Maintype'
+VlnPlot(adult.inte,
+        features = c('Gad1',"Sox6","Pvalb","Sst","Prox1","Vip","Lamp5","Slc17a7","Col23a1",
+                     "Rorb","Foxp2","Bcl6","Ctss","Slc1a3","Mog"),group.by = "Maintype",stack = TRUE, flip = TRUE, fill.by="ident", assay = 'RNA') + 
+  NoLegend()
+DimPlot(adult.inte,  reduction = 'umap', label = T, ncol = 2)
+DimPlot(adult.inte, split.by = 'sample', reduction = 'tsne', label = T, ncol = 2) +
+  theme(axis.line = element_blank(), axis.ticks = element_blank(), 
+        axis.text = element_blank(), plot.title = element_text(size = 30)) +
+  labs(x='', y='')
+saveRDS(adult.inte,"H:/Project1_RV Receptor Projection/FIG1.皮层单细胞RV rAAV感染数据分析/rAAV_RV.inte2.RDS")
+
+
+table(SLQ_IPC$predicted.id)
+SLQ_IPC$`ACB-I`
+SLQ_IPC$`BLA-I`

2.Dimplot.R

@@ -0,0 +1,19 @@
+library(Seurat)
+DimPlot(rAAV_RV.inte,)
+table(rAAV_RV.inte$sample)
+FeaturePlot(rAAV_RV.inte,
+            reduction = 'tsne',
+            c('rAAV_infected','RV_infected','Syt6','Tshz2'),
+            ncol = 2,
+            cols=c("lightgrey", "red"),
+            min.cutoff='q1')
+Idents(rAAV_RV.inte) <- rAAV_RV.inte$sample  # 设定细胞身份
+
+DimPlot(rAAV_RV.inte, reduction = "tsne", group.by = "sample",
+        cols = c("#00bfc4", "lightgrey","red", "grey"), pt.size = 0.5) +
+  ggtitle("t-SNE Visualization of Infected Cells")
+
+Idents(rAAV_RV.inte) <- rAAV_RV.inte$Maintype  # 设定细胞身份
+DimPlot(rAAV_RV.inte, reduction = "umap", pt.size = 0.5) +
+  ggtitle("t-SNE Visualization of Infected Cells")
+table(rAAV_RV.inte$Maintype,rAAV_RV.inte$sample)

3.MetaNeighbor.R

@@ -0,0 +1,82 @@
+adult.inte$maintype_sample <- paste(adult.inte$Maintype, adult.inte$sample, sep = "|")
+library(dplyr)
+table(adult.inte$sample)
+adult.inte$sample <- recode(adult.inte$sample, 
+                            "rAAV_MOCK" = "control_PFC", 
+                            "RV_MOCK" = "Control_V1")
+Idents(adult.inte) <- 'maintype_sample'
+
+#build the tree
+adult.inte<- BuildClusterTree(object = adult.inte, dims=1:10)
+phy <- Tool(object = adult.inte, slot = 'BuildClusterTree')
+p5<-plot(phy)
+p5
+unique(adult.inte$maintype_sample)
+
+#MetaNeighbor
+library(SingleCellExperiment)
+library(MetaNeighbor)
+
+# 创建 colData
+new_colData <- data.frame(
+  study_id = adult.inte$sample,
+  cell_type = adult.inte$Maintype # 确保 row.names 对齐
+)
+new_colData$study_id <- as.character(new_colData$study_id)
+new_colData$study_id[which(new_colData$study_id %in% c("Control_V1","RV_infected"))] <- "VISp"
+new_colData$study_id[which(new_colData$study_id %in% c("control_PFC","rAAV_infected"))] <- "PFC"
+
+dat <- SingleCellExperiment(adult.inte@assays$integrated@data,
+  colData = new_colData
+)
+var_genes <- VariableFeatures(adult.inte)  # 替换为实际的高变基因获取方式
+# 运行 MetaNeighbor
+celltype_NV = MetaNeighborUS(
+  var_genes = var_genes, 
+  dat = dat, # 确保 dat 是矩阵
+  study_id = dat$study_id,
+  cell_type = dat$cell_type,
+  fast_version = TRUE
+)
+
+library(pheatmap)
+pheatmap(celltype_NV, cluster_rows=T, cluster_cols=F, display_numbers=T)
+
+cor_inter<-celltype_NV[grep('VISp|PFC',rownames(celltype_NV),value = T),
+                       grep('VISp|PFC',rownames(celltype_NV),value = T)]
+p<-pheatmap(cor_inter, cluster_rows=T, cluster_cols=T, display_numbers=T,fontsize_number = 5,silent = T)
+cluster_order <- rownames(cor_inter)[p$tree_row$order] 
+
+pheatmap(cor_inter, cluster_rows=T, cluster_cols=T, display_numbers=T, 
+         fontsize_number=5, fontsize_row=8, fontsize_col=8)
+p5<-pheatmap(cor_inter[cluster_order, cluster_order], 
+         cluster_rows=F, cluster_cols=F, display_numbers=T, fontsize_number=5)
+
+cluster_order<-c("PFC|Pvalb" ,"VISp|Pvalb","PFC|Vip/Lamp5","VISp|Vip/Lamp5","PFC|Sst" ,"VISp|Sst",
+                 "PFC|Microglia","VISp|Microglia","PFC|Oligo"  ,"VISp|Oligo","PFC|Astro","VISp|Astro",
+                  "VISp|L2/3IT" ,"PFC|L2/3IT","VISp|L4/5IT", "PFC|L4/5IT","PFC|L6IT","VISp|L6IT" , "VISp|L5ET","PFC|L5ET","PFC|L6CT", "VISp|L6CT","PFC|L5NP","VISp|L5NP") 
+ggsave("H:/Project1_RV Receptor Projection/FIG1.皮层单细胞RV rAAV感染数据分析/p5_MetaNeighbor.pdf", 
+       plot = p5, width =8, height = 8, dpi = 300)
+
+
+
+
+# 提取所有共有细胞类型（PFC和VISp共有的类型）
+common_types <- sub("PFC\\|", "", grep("PFC\\|", rownames(cor_inter), value = TRUE))
+common_types <- common_types[common_types %in% sub("VISp\\|", "", grep("VISp\\|", rownames(cor_inter), value = TRUE))]
+
+# 提取PFC与VISp同类型细胞的相似性得分（单向即可，因矩阵对称）
+scores <- sapply(common_types, function(type) {
+  cor_inter[paste0("PFC|", type), paste0("VISp|", type)]
+})
+
+# 输出所有配对得分
+print(data.frame(CellType = common_types, AUROC = scores))
+
+# 计算平均相似性得分（假设理想情况下应接近1）
+mean_score <- mean(scores)
+cat(sprintf("\nMean AUROC between matched cell types: %.2f\n", mean_score))
+
+# 显著性检验：判断得分是否显著高于随机预期（假设随机预期为0.5）
+t_test_result <- t.test(scores, mu = 0.5, alternative = "greater")
+cat(sprintf("t-test p-value vs. random expectation (0.5): %.1e\n", t_test_result$p.value))

4.Percentage of infected.R

@@ -0,0 +1,121 @@
+library(dplyr)
+library(ggplot2)
+RAAV_RV.INTE<-readRDS("H:/Project1_RV Receptor Projection/FIG1.皮层单细胞RV rAAV感染数据分析/adult.inte.RDS")
+Idents(RAAV_RV.INTE) <- 'sample'
+Idents(RAAV_RV.INTE) <- factor(Idents(RAAV_RV.INTE), 
+                               levels = c("RV_infected", "rAAV_infected", "rAAV_MOCK", "RV_MOCK"))
+nMaintype <- RAAV_RV.INTE@meta.data$Maintype
+nsample <- RAAV_RV.INTE@meta.data$sample
+nMaintype
+
+custom_order <- c('Pvalb','Sst','Vip/Lamp5',"Astro","Microglia",'Oligo','L2/3IT','L4/5IT','L6IT','L5NP','L6CT','L5ET')
+nMaintype <- factor(nMaintype, levels = custom_order)
+# 转换为data.frame对象
+data <- data.frame(nMaintype, nsample)
+
+levels(data)
+
+# 计算每个nMaintype中nsample1和nsample2的数量
+summary_data <- data %>%
+  group_by(nMaintype, nsample) %>%
+  summarise(count = n()) %>%
+  ungroup()
+summary_data_3 <- summary_data %>%
+  filter(nsample %in% c("rAAV_infected", "RV_infected"))
+# 计算百分比
+percent_data <- summary_data %>%
+  group_by(nMaintype) %>%
+  mutate(percentage = count / sum(count))
+
+percent_data$nMaintype
+library(dplyr)
+
+percent_data_3 <- summary_data_3 %>%
+  group_by(nMaintype) %>%
+  mutate(percentage = count / sum(count))
+
+#不同亚群占比
+p1<- ggplot(percent_data, aes(x = nMaintype, y = percentage, fill = nsample)) +
+  geom_bar(stat = "identity") +
+  scale_fill_manual(values = c("#f8766d","#f8766d","#00bfc4", '#eade5e')) +
+  ylab("Percentage") +
+  theme_bw() +
+  labs(
+    title = "Percentage of RV rAAV infected cells",  # 设置标题
+    x = "Cluster Type",  # 设置x轴标签
+    y = "Percentage of virus infected cells"
+  ) +
+  theme(
+    plot.title = element_text(size = 20, hjust = 0.5),  # 设置标题大小为20，居中对齐
+    axis.title.x = element_text(size = 14),  # 设置x轴标签大小为14
+    axis.title.y = element_text(size = 14),  # 设置y轴标签大小为14
+    axis.text.x = element_text(angle = 45, hjust = 1,size = 14,color ='black'),  # 横坐标倾斜45度
+    legend.text = element_text(size = 14))
+
+# 过滤掉 "rAAV_MOCK" 和 "RV_MOCK"
+filtered_data <- data %>%
+  filter(nsample %in% c("RV_infected", "rAAV_infected")) %>%  # 只保留 RV_infected 和 rAAV_infected
+  filter(!nMaintype %in% c("Pvalb", "Sst", "Vip/Lamp5"))  # 去掉这几类细胞
+
+
+# 重新绘制柱状图
+p2<- ggplot(filtered_data, aes(x = nMaintype, fill = nsample)) +
+  geom_bar() +
+  scale_fill_manual(values = c("#00bfc4", '#eade5e')) +  # 仅保留 RV_infected 和 rAAV_infected 的颜色
+  theme_bw() +
+  labs(
+    title = "Number of Virus infected cells",
+    x = " ",
+    y = "Cell Numbers"
+  ) +
+  theme(
+    plot.title = element_text(size = 20, hjust = 0.5),
+    axis.title.x = element_text(size = 14),
+    axis.title.y = element_text(size = 14),
+    axis.text.x = element_text(angle = 45, hjust = 1, size = 14, color ='black'),
+    legend.text = element_text(size = 14)
+  )
+
+print(p2)
+#Virus Percentage===RV/rAAV
+# 计算每个nMaintype中nsample1和nsample2的数量
+summary_data <- filtered_data%>%
+  group_by(nMaintype, nsample) %>%
+  summarise(count = n()) %>%
+  ungroup()
+summary_data_3 <- summary_data %>%
+  filter(nsample %in% c("rAAV_infected", "RV_infected"))
+
+percent_data_3 <- summary_data_3 %>%
+  group_by(nMaintype) %>%
+  mutate(percentage = count / sum(count))
+
+p3 <- ggplot(percent_data_3, aes(x = nMaintype, y = percentage, fill = nsample)) +
+  geom_bar(stat = "identity") +
+  scale_fill_manual(values = c("#00bfc4", '#eade5e')) +
+  ylab("Percentage") +
+  theme_bw() +
+  labs(
+    title = "Percentage of RV rAAV infected cells",  # 设置标题
+    x = "Cluster Type",  # 设置x轴标签
+    y = "Percentage of virus infected cells"
+  ) +
+  theme(
+    plot.title = element_text(size = 20, hjust = 0.5),  # 设置标题大小为20，居中对齐
+    axis.title.x = element_text(size = 14),  # 设置x轴标签大小为14
+    axis.title.y = element_text(size = 14),  # 设置y轴标签大小为14
+    axis.text.x = element_text(angle = 45, hjust = 1,size = 14,color ='black')  # 横坐标倾斜45度
+  )
+
+p3
+
+
+p1
+p2
+p3
+ggsave("H:/Project1_RV Receptor Projection/FIG1.皮层单细胞RV rAAV感染数据分析/p6.Percentage of virus infected cells.pdf", 
+       plot = p1, width =7, height = 8, dpi = 300)
+ggsave("H:/Project1_RV Receptor Projection/FIG1.皮层单细胞RV rAAV感染数据分析/p7.Percentage of virus infected cells.pdf", 
+       plot = p2, width =6, height = 8, dpi = 300)
+ggsave("H:/Project1_RV Receptor Projection/FIG1.皮层单细胞RV rAAV感染数据分析/p8.Percentage of virus infected cells.pdf", 
+       plot = p3, width =6, height = 8, dpi = 300)