1 安装依赖
# scater 数据可视化
if (!requireNamespace("BiocManager", quietly = TRUE))
install.packages("BiocManager")
BiocManager::install("scater")
library("scater")
BiocManager::install("scRNAseq")
library("scRNAseq")
BioConductor
Collection of Public Single-Cell RNA-Seq Datasets
Single-Cell Analysis Toolkit for Gene Expression Data in R
2 数据获取
example_sce <- ZeiselBrainData()
example_sce
3 质控诊断
library(scater)
example_sce <-
addPerCellQC(example_sce,
subsets=list(Mito=grep("mt-", rownames(example_sce))))
plotColData(example_sce, x = "sum", y="detected", colour_by="tissue")
基因数随序列数增加而增加，点代表细胞，颜色代表组织
plotColData(example_sce, x = "sum", y="subsets_Mito_percent",
other_fields="tissue") + facet_wrap(~tissue)
单细胞中总序列数和线粒体（内参）百分比，好的细胞测序内参应较少
plotHighestExprs(example_sce, exprs_values = "counts")
top50基因在所有细胞中的表达量
example_sce <- logNormCounts(example_sce)
vars <- getVarianceExplained(example_sce,
variables=c("tissue", "total mRNA mol", "sex", "age"))
head(vars)
plotExplanatoryVariables(vars)
各变量对基因表达变异的解释程度，密度图
4 基因表达值
plotExpression(example_sce, rownames(example_sce)[1:6], x = "level1class")
其中6个基因subset的表达值
plotExpression(example_sce, rownames(example_sce)[1:6],
x = rownames(example_sce)[10])
6个基因subset的表达值与10号指标的关系图
plotExpression(example_sce, rownames(example_sce)[1:6],
x = "level1class", colour_by="tissue")
着色
plotExpression(example_sce, rownames(example_sce)[1:6])
合并基因subset
5 维度分析
- 主成分分析
example_sce <- runPCA(example_sce)
str(reducedDim(example_sce, "PCA"))
example_sce <- runPCA(example_sce, name="PCA2",
subset_row=rownames(example_sce)[1:1000],
ncomponents=25)
str(reducedDim(example_sce, "PCA2"))
- 其他降维方法
set.seed(1000)
example_sce <- runTSNE(example_sce, perplexity=10)
head(reducedDim(example_sce, "TSNE"))
set.seed(1000)
example_sce <- runTSNE(example_sce, perplexity=50,
dimred="PCA", n_dimred=10)
head(reducedDim(example_sce, "TSNE"))
- 降维可视化
plotReducedDim(example_sce, dimred = "PCA", colour_by = "level1class")
plotTSNE(example_sce, colour_by = "Snap25")
plotPCA(example_sce, colour_by="Mog")
example_sce <- runPCA(example_sce, ncomponents=20)
plotPCA(example_sce, ncomponents = 4, colour_by = "level1class")
不同组成份组合降维图
6 普通可视化
ggcells(example_sce, mapping=aes(x=level1class, y=Snap25)) +
geom_boxplot() +
facet_wrap(~tissue)
snap25在不同细胞，组织中的表达
ggcells(example_sce, mapping=aes(x=TSNE.1, y=TSNE.2, colour=Snap25)) +
geom_point() +
stat_density_2d() +
facet_wrap(~tissue) +
scale_colour_distiller(direction=1)
snap25基因在所有细胞中表达降维分布
ggcells(example_sce, mapping=aes(x=sizeFactor, y=Actb)) +
geom_point() +
geom_smooth()
尺度与actb基因表达的关系
colnames(example_sce) <- make.names(colnames(example_sce))
ggfeatures(example_sce, mapping=aes(x=featureType, y=X1772062111_E06)) +
geom_violin()
指定细胞，feature type与表达值的关系，小提琴图
更多
代码分析 | 单细胞转录组Normalization详解
Single-cell analysis toolkit for expression in R
Assigning cell types with SingleR
Hemberg-lab单细胞转录组数据分析（十一）- Scater单细胞表达谱PCA可视化
scater 文献
