From 84ef3293d3073b1f8f6db67f33a025117f416ea7 Mon Sep 17 00:00:00 2001 From: ixxmu Date: Thu, 16 May 2024 01:08:30 +0000 Subject: [PATCH] A custom message for the commit --- ...70\270\347\224\250\345\221\275\344\273\244.md" | 15 --------------- 1 file changed, 15 deletions(-) delete mode 100644 "docs/2024-05/scRNA_seq\346\225\260\346\215\256\345\210\206\346\236\220_seurat_v5___\345\270\270\347\224\250\345\221\275\344\273\244.md" diff --git "a/docs/2024-05/scRNA_seq\346\225\260\346\215\256\345\210\206\346\236\220_seurat_v5___\345\270\270\347\224\250\345\221\275\344\273\244.md" "b/docs/2024-05/scRNA_seq\346\225\260\346\215\256\345\210\206\346\236\220_seurat_v5___\345\270\270\347\224\250\345\221\275\344\273\244.md" deleted file mode 100644 index f0801fa7..00000000 --- "a/docs/2024-05/scRNA_seq\346\225\260\346\215\256\345\210\206\346\236\220_seurat_v5___\345\270\270\347\224\250\345\221\275\344\273\244.md" +++ /dev/null @@ -1,15 +0,0 @@ ---- -title: "scRNA-seq数据分析（seurat v5）——常用命令" -date: 2024-05-16T01:07:17Z -draft: ["false"] -tags: [ - "fetched", - "被炸熟的虾" -] -categories: ["Acdemic"] ---- -scRNA-seq数据分析（seurat v5）——常用命令 by 被炸熟的虾 ------- -

哈喽小伙伴们，seurat官网整理了一些常用命令，方便我们调用。一起来看看吧！

https://github.com/satijalab/seurat/blob/HEAD/vignettes/essential_commands.Rmd

Contents

一、Seurat标准工作流程

pbmc <- NormalizeData(object = pbmc)pbmc <- FindVariableFeatures(object = pbmc)pbmc <- ScaleData(object = pbmc)pbmc <- RunPCA(object = pbmc)pbmc <- FindNeighbors(object = pbmc, dims = 1:30)pbmc <- FindClusters(object = pbmc)pbmc <- RunUMAP(object = pbmc, dims = 1:30)DimPlot(object = pbmc, reduction = "umap")

 SCtransform 版本

pbmc <- SCTransform(object = pbmc)pbmc <- RunPCA(object = pbmc)pbmc <- FindNeighbors(object = pbmc, dims = 1:30)pbmc <- FindClusters(object = pbmc)pbmc <- RunUMAP(object = pbmc, dims = 1:30)DimPlot(object = pbmc, reduction = "umap")
#可以使用%>%将多个命令链接在一起pbmc <- SCTransform(pbmc) %>%    RunPCA() %>%    FindNeighbors(dims = 1:30) %>%    FindClusters() %>%    RunUMAP(dims = 1:30)

二、Seurat对象数据访问

 1. 细胞、基因和layer名称

#获取细胞和基因名以及总数的多种方法colnames(pbmc)Cells(pbmc)
#基因名称Features(pbmc)rownames(pbmc)
#细胞/基因的数量num_cells <- ncol(pbmc)num_features <- nrow(pbmc)
#对象层列表Layers(pbmc)
#使用多模态对象列表分析Assays(cbmc)
#检测特异性特征(基因/ADT)Features(cbmc[["RNA"]])Features(cbmc[["ADT"]])
#可变基因名称VariableFeatures(pbmc)
#设置可变基因VariableFeatures(cbmc) <- var.gene.names
#设置一个特定的assayVariableFeatures(cbmc[["ADT"]]) <- var.gene.names

  2. 确定分类标签

#设置和检索细胞标识#将标识类设置为metadata中的现有列Idents(object = pbmc) <- "seurat_annotations"#查看细胞标识，获取汇总表Idents(pbmc)table(Idents(pbmc))
#将所有细胞的标识设置为CD4 T细胞Idents(pbmc) <- "CD4 T cells"
#为选定的细胞组设置pbmc.cells <- Cells(pbmc)Idents(object = pbmc, cells = pbmc.cells[1:10]) <- "CD4 T cells"
#获取细胞标识类Idents(object = pbmc)levels(x = pbmc)
#将细胞标识类存储在metadata中pbmc[["old.ident"]] <- Idents(object = pbmc)pbmc <- StashIdent(object = pbmc, save.name = "old.ident")
#重命名标识类pbmc <- RenameIdents(object = pbmc, `CD4 T cells` = "T Helper cells")

 3. 细胞metadata

#查看存储在object@meta.data中的meta.data数据框pbmc[[]]
#从metadata中检索特定的值pbmc$nCount_RNApbmc[[c("percent.mito", "nFeature_RNA")]]
#添加metadata，参见?AddMetaDatarandom_group_labels <- sample(x = c("g1", "g2"), size = ncol(x = pbmc), replace = TRUE)pbmc$groups <- random_group_labels

 4. 表达式数据（在 Seurat v5 中作为layers存储）

#检索表达矩阵RNA计数矩阵中的数据pbmc[["RNA"]]$counts
#具有相同结果的备用函数LayerData(pbmc, assay = "RNA", layer = "counts")
#仍然支持来自Seurat v4的GetAssayDataGetAssayData(object = pbmc, assay = "RNA", slot = "counts")
#ADT计数矩阵(多模态对象)cbmc[["ADT"]]$counts
#设置表达式数据假设为new.data 是一种新的表达式矩阵pbmc[["RNA"]]$counts <- new.data
#具有相同结果的备用setter函数LayerData(pbmc, assay = "RNA", layer = "counts") <- new.data
#仍然支持来自Seurat v4的SetAssayDatapbmc <- SetAssayData(object = pbmc, slot = "counts", new.data = new.data

 5. 降维

#获取存储在pbmc上的细胞嵌入和基因加载[['pca']]@cell.embeddingsEmbeddings(pbmc, reduction = "pca")
#存储在pbmc[['pca]]@feature.loadings中Loadings(pbmc, reduction = "pca")#创建自定义尺寸缩减加载矩阵是可选的new_reduction <- CreateDimReducObject(embeddings = new.embeddings, loadings = new.loadings, key = "custom_pca")pbmc[["custom_pca"]] <- new_reduction

 6. FetchData （获取数据）

#FetchData可以访问表达式矩阵、细胞嵌入或metadata中的任何内容#使用FetchData访问单个/小组变量FetchData(object = pbmc, vars = c("PC_1", "nFeature_RNA", "MS4A1"), layer = "counts")

三、子集和合并

 1. Seurat对象的子集

#基于标识类的子集Seurat对象，参见?SubsetDatasubset(x = pbmc, idents = "B")subset(x = pbmc, idents = c("Naive CD4 T", "CD8 T"), invert = TRUE)
#基因/特征表达水平上的子集subset(x = pbmc, subset = MS4A1 > 2.5)
#标准的组合上的子集subset(x = pbmc, subset = MS4A1 > 2.5 & PC_1 > 5)subset(x = pbmc, subset = MS4A1 > 2.5, idents = "B")
#对象metadata中的子集subset(x = pbmc, subset = groups == "g1")
#下采样每个标识类的细胞数量subset(x = pbmc, downsample = 100)

 2. 分层

#在Seurat v5中，用户现在可以将对象直接拆分为不同的层，将表达式数据保留在一个对象中，但是#将多个样本拆分成层后可以直接进入整合工作流程ifnb[["RNA"]] <- split(ifnb[["RNA"]], f = ifnb$stim)Layers(ifnb)
#如果需要，例如在整合之后，这些层可以再次连接在一起ifnb <- JoinLayers(ifnb)

 3. 拆分对象

#可以根据metadata将对象拆分为多个对象的列表#创建两个对象的列表ifnb_list <- SplitObject(ifnb, split.by = "stim")ifnb_list$CTRLifnb_list$STIM

 4. 合并对象（没有integration）

在Seurat v5 中，合并会创建一个对象，但会将表达式信息拆分为不同的层进行integration。如果不继续integration，请在合并后重新加入layers。
#合并两个Seurat对象merged_obj <- merge(x = ifnb_list$CTRL, y = ifnb_list$STIM)merged_obj[["RNA"]] <- JoinLayers(merged_obj)
#合并两个以上的Seurat对象merge(x = pbmc1, y = list(pbmc2, pbmc3))

 5. 合并对象（有integration）

https://satijalab.org/seurat/articles/integration_introduction

merged_obj <- merge(x = ifnb_list$CTRL, y = ifnb_list$STIM)merged_obj <- NormalizeData(merged_obj)merged_obj <- FindVariableFeatures(merged_obj)merged_obj <- ScaleData(merged_obj)merged_obj <- RunPCA(merged_obj)merged_obj <- IntegrateLayers(object = obj, method = RPCAIntegration, orig.reduction = "pca", new.reduction = "integrated.rpca",    verbose = FALSE)
#现在整合已经完成，重新加入layersmerged_obj[["RNA"]] <- JoinLayers(merged_obj)

四、Pseudobulk分析





为了从高通量单细胞mRNA数据中增加基因数量和基因表达相关性，我们从同一细胞群中的多个细胞中收集数据，制作假细胞（Pseudocell）用于网络解释。看来这个Pseudocell概念是为了弥补稀疏矩阵在计算相关性上的缺陷，毕竟零值太多，影响相关性的计算。

在高通量单细胞转录组数据上应用bulk RNA 的分析方法的时候，采用这种局部bulk的方法还是有必要的，一方面是维度缩减，一方面是提高模型的适应性。





 基于多个类别将细胞分组在一起

有关如何将列添加到metadata的信息，请参阅https://satijalab.org/seurat/articles/de_vignette。donor_id

#pseudobulk细胞仅按细胞类型区分bulk <- AggregateExpression(ifnb, group.by = "seurat_annotations", return.seurat = TRUE)Cells(bulk)
#pseudobulk细胞受刺激条件和细胞类型的影响bulk <- AggregateExpression(ifnb, group.by = c("stim", "seurat_annotations"), return.seurat = TRUE)Cells(bulk)
#pseudobulk细胞与刺激条件、细胞类型和供体有关bulk <- AggregateExpression(ifnb, group.by = c("stim", "seurat_annotations", "donor_id"), return.seurat = TRUE)Cells(bulk)

五、Seurat的可视化

Seurat 有一个庞大的、基于 ggplot2 的绘图库。默认情况下，所有绘图函数都将返回一个 ggplot2 绘图，从而允许使用 ggplot2 轻松自定义。

#降维图DimPlot(object = pbmc, reduction = "pca")
#维度缩减图 细胞由定量特征着色 如果可用，默认为UMAPFeaturePlot(object = pbmc, features = "MS4A1")
#单个细胞的散点图FeatureScatter(object = pbmc, feature1 = "MS4A1", feature2 = "PC_1")FeatureScatter(object = pbmc, feature1 = "MS4A1", feature2 = "CD3D")
#散点图跨越各个特征 取代CellPlotCellScatter(object = pbmc, cell1 = "AGTCTACTAGGGTG", cell2 = "CACAGATGGTTTCT")
VariableFeaturePlot(object = pbmc)
#小提琴和山脊图VlnPlot(object = pbmc, features = c("LYZ", "CCL5", "IL32"))RidgePlot(object = pbmc, feature = c("LYZ", "CCL5", "IL32"))
#热图(可视化scale.data) DimHeatmap(object = pbmc, reduction = "pca", cells = 200)
#标准工作流程pbmc <- ScaleData(pbmc, features = heatmap_markers)DoHeatmap(object = pbmc, features = heatmap_markers)
#sctransform工作流程pbmc <- GetResidual(pbmc, features = heatmap_markers)DoHeatmap(object = pbmc, features = heatmap_markers)
#热图 每组最多100个细胞DoHeatmap(pbmc, heatmap_markers, cells = subset(pbmc, downsample = 100)
#尝试新事物!注意，绘图函数现在返回ggplot2对象#因此可以向其添加主题、标题和选项VlnPlot(object = pbmc, features = "MS4A1", split.by = "groups")DotPlot(object = pbmc, features = c("LYZ", "CCL5", "IL32"), split.by = "groups")FeaturePlot(object = pbmc, features = c("MS4A1", "CD79A"), blend = TRUE)DimPlot(object = pbmc) + DarkTheme()DimPlot(object = pbmc) + labs(title = "2,700 PBMCs clustered using Seurat and viewed\non a two-dimensional UMAP")

Seurat 提供了许多预构建的主题，可以添加到 ggplot2 绘图中以便快速自定义。

主题功能
DarkTheme设置带有白色文本的黑色背景
FontSize设置绘图中各种元素的字体大小
NoAxes删除轴和轴文本
NoLegend删除所有图例元素
RestoreLegend删除后恢复图例
RotatedAxis旋转 x 轴标签
#绘图辅助函数用于基于ggplot2的散点图#如DimPlot, FeaturePlot, CellScatter和FeatureScatterplot <- DimPlot(object = pbmc) + NoLegend()
#HoverLocator取代了以前的`do.hover`#它还可以通过' information '参数显示额外的数据 旨在与FetchData一起顺利工作HoverLocator(plot = plot, information = FetchData(object = pbmc, vars = c("ident", "PC_1", "nFeature_RNA")))
#FeatureLocator取代了之前的`do.identify`select.cells <- FeatureLocator(plot = plot)
#在ggplot对象上标记点LabelPoints(plot = plot, points = TopCells(object = pbmc[["pca"]]), repel = TRUE)

六、多检测特性

使用Seurat，您可以轻松地在单细胞水平的不同检测方法之间切换（例如来自CITE-seq的ADT计数，或整合/批量校正的数据）。大多数函数现在都采用检测参数，但您可以设置默认检测以避免重复语句。

cbmc <- CreateSeuratObject(counts = cbmc.rna)#添加ADT数据cbmc[["ADT"]] <- CreateAssayObject(counts = cbmc.adt)#通过指定要使用的assay来运行分析NormalizeData(object = cbmc, assay = "RNA")NormalizeData(object = cbmc, assay = "ADT", method = "CLR")
#检索并设置默认assayDefaultAssay(object = cbmc)DefaultAssay(object = cbmc) <- "ADT"DefaultAssay(object = cbmc)
#使用keys从两个assays中提取特征表达式FetchData(object = cbmc, vars = c("rna_CD3E", "adt_CD3"))
#使用keys绘制来自多个assays的数据FeatureScatter(object = cbmc, feature1 = "rna_CD3E", feature2 = "adt_CD3")

七、其他资源

对 Seurat v5 中数据存储的一些技术更改特别感兴趣的用户可以浏览以下资源：

https://mojaveazure.github.io/seurat-object/
https://satijalab.org/seurat/articles/seurat5_essential_commands

-
-原文链接