针对测序数据和芯片数据,目前常用差异分析的R包有edgeR、limma、DESeq2,做一简单比较,方便平时分析。内容多为搬运,主要方便下次寻找。
1. 三种分析方法的比较
三种packages的比较
1.limma包做差异分析要求数据满足正态分布或近似正态分布,如基因芯片、TPM格式的高通量测序数据。
2.通常认为Count数据不符合正态分布而服从泊松分布。对于count数据来说,用limma包做差异分析,误差较大
3.DESeq2、和 EdgeR都是基于count,然后两个都是NB(negative binomial)但是在估计dispersion parameter的方法上面不一样。
4.limma,edgeR,DESeq2三大包基本是做转录组差异分析的金标准,大多数转录组的文章都是用这三个R包进行差异分析。
5.edgeR差异分析速度快,得到的基因数目比较多,假阳性高(实际不差异,结果差异)。DESeq2差异分析速度慢,得到的基因数目比较少,假阴性高(实际差异,结果不差异)。
6.需要注意的是制作分组信息的因子向量是,因子水平的前后顺序,在R的很多模型中,默认将因子向量的第一个水平看作对照组。
2.实战
2.1数据准备
rm(list = ls())
library("DESeq2")
library("limma")
library("edgeR")
expr = read.csv("mRNA_exprSet.csv",sep = ',',header=T)
head(expr)
读取的基因矩阵文件,行为基因名,列为样本名
2.2 表达数据整理
# 对重复基因名取平均表达量,然后将基因名作为行名
expr = avereps(expr[,-1],ID = expr$X) # 自定义
# 去除低表达的基因
expr = expr[rowMeans(expr)>1,] # 自定义
# 表达矩阵分组(癌症组织和癌旁组织)
library(stringr)
tumor <- colnames(expr)[as.integer(substr(colnames(expr),14,15)) < 10]
normal <- colnames(expr)[as.integer(substr(colnames(expr),14,15)) >= 10]
tumor_sample <- expr[,tumor]
normal_sample <- expr[,normal]
exprSet_by_group <- cbind(tumor_sample,normal_sample)
group_list <- c(rep('tumor',ncol(tumor_sample)),rep('normal',ncol(normal_sample)))
save(exprSet_by_group, group_list, file = 'exprSet_by_group_list.Rdata')
2.3 edgeR包进行差异分析
# 表达矩阵
data = exprSet_by_group
# 分组矩阵
group_list = factor(group_list)
design <- model.matrix(~0+group_list)
rownames(design) = colnames(data)
colnames(design) <- levels(group_list)
# 差异表达矩阵
DGElist <- DGEList( counts = data, group = group_list)
## Counts per Million or Reads per Kilobase per Million
keep_gene <- rowSums( cpm(DGElist) > 1 ) >= 2 ## 自定义
table(keep_gene)
DGElist <- DGElist[ keep_gene, , keep.lib.sizes = FALSE ]
DGElist <- calcNormFactors( DGElist )
DGElist <- estimateGLMCommonDisp(DGElist, design)
DGElist <- estimateGLMTrendedDisp(DGElist, design)
DGElist <- estimateGLMTagwiseDisp(DGElist, design)
fit <- glmFit(DGElist, design)
results <- glmLRT(fit, contrast = c(-1, 1))
nrDEG_edgeR <- topTags(results, n = nrow(DGElist))
nrDEG_edgeR <- as.data.frame(nrDEG_edgeR)
head(nrDEG_edgeR)
# 提取基因差异显著的差异矩阵
padj = 0.01 # 自定义
foldChange= 2 # 自定义
nrDEG_edgeR_signif = nrDEG_edgeR[(nrDEG_edgeR$FDR < padj &
(nrDEG_edgeR$logFC>foldChange | nrDEG_edgeR$logFC<(-foldChange))),]
nrDEG_edgeR_signif = nrDEG_edgeR_signif[order(nrDEG_edgeR_signif$logFC),]
save(nrDEG_edgeR_signif,file = 'nrDEG_edgeR_signif.Rdata')
2.4 DESeq2包做差异表达
data = exprSet_by_group
# 分组矩阵
condition = factor(group_list)
coldata <- data.frame(row.names = colnames(data), condition)
dds <- DESeqDataSetFromMatrix(countData = data,
colData = coldata,
design = ~condition)
dds$condition<- relevel(dds$condition, ref = "normal") # 指定哪一组作为对照组
# 差异表达矩阵
dds <- DESeq(dds)
allDEG2 <- as.data.frame(results(dds))
# 提取基因差异显著的差异矩阵
padj = 0.01 # 自定义
foldChange= 2 # 自定义
nrDEG_DESeq2_signif = allDEG2[(allDEG2$padj < padj &
(allDEG2$log2FoldChange>foldChange | allDEG2$log2FoldChange<(-foldChange))),]
nrDEG_DESeq2_signif = nrDEG_DESeq2_signif[order(nrDEG_DESeq2_signif$log2FoldChange),]
save(nrDEG_DESeq2_signif, file = 'nrDEG_DESeq2_signif.Rdata')
2.5 limma包分析过程
# 表达矩阵
data = exprSet_by_group
# 分组矩阵
group_list = factor(group_list)
design <- model.matrix(~0+group_list)
rownames(design) = colnames(data)
colnames(design) <- levels(group_list)
# 差异表达矩阵
DGElist <- DGEList( counts = data, group = group_list )
keep_gene <- rowSums( cpm(DGElist) > 1 ) >= 2 # 自定义
table(keep_gene)
DGElist <- DGElist[ keep_gene, , keep.lib.sizes = FALSE ]
DGElist <- calcNormFactors( DGElist )
v <- voom(DGElist, design, plot = TRUE, normalize = "quantile")
fit <- lmFit(v, design)
cont.matrix <- makeContrasts(contrasts = c('tumor-normal'), levels = design)
fit2 <- contrasts.fit(fit, cont.matrix)
fit2 <- eBayes(fit2)
nrDEG_limma_voom = topTable(fit2, coef = 'tumor-normal', n = Inf)
nrDEG_limma_voom = na.omit(nrDEG_limma_voom)
head(nrDEG_limma_voom)
# 提取基因差异显著的差异矩阵
padj = 0.01 # 自定义
foldChange= 2 # 自定义
nrDEG_limma_voom_signif = nrDEG_limma_voom[(nrDEG_limma_voom$adj.P.Val < padj &
(nrDEG_limma_voom$logFC>foldChange | nrDEG_limma_voom$logFC<(-foldChange))),]
nrDEG_limma_voom_signif = nrDEG_limma_voom_signif[order(nrDEG_limma_voom_signif$logFC),]
save(nrDEG_limma_voom_signif, file = 'nrDEG_limma_voom_signif.RDATA')
最后,参考文档也很重要。可以翻阅这三个包的说明文档
参考:
//www.greatytc.com/p/cf2ec58e5361
https://blog.csdn.net/weixin_43700050/article/details/98085127