如果传统bulk转录组数据队列足够大也可以使用单细胞流程

library(Seurat)
# https://satijalab.org/seurat/mca.html
sce <- CreateSeuratObject(counts = sarc_choose, 
                          meta.data =clinic,
                          min.cells = 5, min.features = 1000, 
                          project = "sce")
head(sce@meta.data)  
# 步骤 ScaleData 的耗时取决于电脑系统配置（保守估计大于一分钟）
sce <- ScaleData(object = sce, 
                 vars.to.regress = c('nCount_RNA'), 
                 model.use = 'linear', 
                 use.umi = FALSE)
sce <- FindVariableFeatures(object = sce)
length(VariableFeatures(sce)) 
sce <- RunPCA(object = sce, pc.genes = VariableFeatures(sce))
# 下面只是展现不同降维算法而已，并不要求都使用一次。
sce <- RunICA(sce )
sce <- RunTSNE(sce )
#sce <- RunUMAP(sce,dims = 1:10)
#VizPCA( sce, pcs.use = 1:2)
DimPlot(object = sce, reduction = "pca") 
DimPlot(object = sce, reduction = "ica")
DimPlot(object = sce, reduction = "tsne",group.by  =  'short.histo')

# 针对PCA降维后的表达矩阵进行聚类 FindNeighbors+FindClusters 两个步骤。
sce <- FindNeighbors(object = sce, dims = 1:20, verbose = FALSE) 
sce <- FindClusters(object = sce, resolution = 0.8,verbose = FALSE)
# 继续tSNE可视化
DimPlot(object = sce, reduction = "tsne",
        group.by = 'RNA_snn_res.0.8',label = T)
table(sce@meta.data$short.histo,sce@meta.data$RNA_snn_res.0.8)

Idents(sce)=sce@meta.data$short.histo

sce.markers <- FindAllMarkers(object = sce, only.pos = TRUE, min.pct = 0.25, 
                              thresh.use = 0.25)
DT::datatable(sce.markers)
library(dplyr)
sce.markers=sce.markers[!is.infinite(sce.markers$avg_logFC),]
sce.markers %>% group_by(cluster) %>% top_n(2, avg_logFC)
topN <- sce.markers %>% group_by(cluster) %>% top_n(50, avg_logFC)
DoHeatmap(sce,topN$gene)

"wilcox" : Identifies differentially expressed genes between two groups of cells using a Wilcoxon Rank Sum test (default)
"bimod" : Likelihood-ratio test for single cell gene expression, (McDavid et al., Bioinformatics, 2013)
"roc" : Identifies 'markers' of gene expression using ROC analysis. For each gene, evaluates (using AUC) a classifier built on that gene alone, to classify between two groups of cells. An AUC value of 1 means that expression values for this gene alone can perfectly classify the two groupings (i.e. Each of the cells in cells.1 exhibit a higher level than each of the cells in cells.2). An AUC value of 0 also means there is perfect classification, but in the other direction. A value of 0.5 implies that the gene has no predictive power to classify the two groups. Returns a 'predictive power' (abs(AUC-0.5) * 2) ranked matrix of putative differentially expressed genes.
"t" : Identify differentially expressed genes between two groups of cells using the Student's t-test.
"negbinom" : Identifies differentially expressed genes between two groups of cells using a negative binomial generalized linear model. Use only for UMI-based datasets
"poisson" : Identifies differentially expressed genes between two groups of cells using a poisson generalized linear model. Use only for UMI-based datasets
"LR" : Uses a logistic regression framework to determine differentially expressed genes. Constructs a logistic regression model predicting group membership based on each feature individually and compares this to a null model with a likelihood ratio test.
"MAST" : Identifies differentially expressed genes between two groups of cells using a hurdle model tailored to scRNA-seq data. Utilizes the MAST package to run the DE testing.
"DESeq2" : Identifies differentially expressed genes between two groups of cells based on a model using DESeq2 which uses a negative binomial distribution (Love et al, Genome Biology, 2014).This test does not support pre-filtering of genes based on average difference (or percent detection rate) between cell groups. However, genes may be pre-filtered based on their minimum detection rate (min.pct) across both cell groups. To use this method, please install DESeq2, using the instructions at https://bioconductor.org/packages/release/bioc/html/DESeq2.html