前些天，实验室里的同事，为了补充计算几个比较组合的差异分析，花了几千元，真够冤枉的。但碍于我们实验室对生信技术的鄙夷，我也懒得理睬。这里简单介绍一下如何使用edgeR进行差异基因的计算。文末附上完整代码，直接复制粘贴更改名称即可使用。
1. 安装
if (!requireNamespace("BiocManager", quietly = TRUE))
install.packages("BiocManager")
BiocManager::install("edgeR")
2. 读取数据
使用edgeR计算差异基因，使用的是readcount数据。我们这里使用最简单的双处理三重复数据进行举例。
OS = read.table("readcounts.txt",sep = "\t",header = T)
rownames(OS)=OS$GeneID
OS = OS[,2:7]
head(OS)
数据格式
3.构建DGEList
Treat = factor(substring(colnames(OS),1,2))
Treat = relevel(Treat, ref = "MM")
Time = factor(substring(colnames(OS),3,3))
#构建DEGList
y = DGEList(counts = OS, group = Treat)
Treat是指处理，利用substring(object, start, end),来指定处理名称，及去掉数字的部分，这里使用start和end确定处理的名字的位置，两位字节，即MM和CM。ref来确定对照。Time是指重复，这里的start和end则定位重复的标记，即1,2和3。这里MM1, CM1等，数字出现在第三位，因此start=3, end=3。
使用DEGList直接构建。
4. 过滤和标准化
部分readcount太低的需要去除。
keep = filterByExpr(y)
table(keep)
y = y[keep,,keep.lib.sizes = FALSE]
y = calcNormFactors(y)
y$samples
使用filterByExpr()来过滤，过滤掉372个基因。结果如下：
过滤
使用
calcNormFactors()进行标准化，结果如下：
标准化
5. 设计矩阵和估计离散值
我们直接用GLM方法来计算
design = model.matrix(~Time+Treat)
rownames(design) = colnames(y)
设计的矩阵如下：
接着计算离散值：
y = estimateDisp(y, design, robust=TRUE)
y$common.dispersion
plotBCV(y)
BCV
fit = glmQLFit(y, design, robust = TRUE)
plotQLDisp(fit)
image.png
6. 计算差异值
qlf = glmQLFTest(fit)
topTags(qlf)
展示FDR最低的十个基因
top = rownames(topTags(qlf))
cpm(y)[top,]
readcount中间值
summary(decideTests(qlf))
plotMD(qlf)
abline(h = c(-1,1), col = "blue")
上下调基因概述
FDR<0.05的基因
7. 提取结果
output = topTags(qlf, n =9000) n大于基因总数就行
top2 = rownames(output)
cpm2 = cpm(y)[top2,]
output2 = as.data.frame(output)
cpm3 = as.data.frame(cpm2)
output_all = cbind(cpm3,output2)
output_DEG = output_all[(output_all$FDR < 0.05 & output_all$logFC > 1) | (output_all$FDR < 0.05 & output_all$logFC < -1),]
output_Up = output_all[output_all$FDR < 0.05 & output_all$logFC > 1,]
output_Down = output_all[output_all$FDR < 0.05 & output_all$logFC < -1,]
write.table(output_all, file = "All.txt", row.names = T, sep = "\t", quote = F)
write.table(output_DEG, file = "DEG.txt", row.names = T, sep = "\t", quote = F)
write.table(output_Up, file = "Up.txt", row.names = T, sep = "\t", quote = F)
write.table(output_Down, file = "Down.txt",, row.names = T, sep = "\t", quote = F)
这里分别提取所有基因，差异基因，上调基因和下调基因的readcount中间值，FC和FDR值。
完整代码
最后附上所有代码：
setwd("...")
library(edgeR)
OS = read.table("readcounts.txt",sep = "\t",header = T)
rownames(OS)=OS$GeneID
OS = OS[,2:7]
head(OS)
Treat = factor(substring(colnames(OS),1,2))
Treat = relevel(Treat, ref = "MM")
Time = factor(substring(colnames(OS),3,3))
y = DGEList(counts = OS, group = Treat)
keep = filterByExpr(y)
table(keep)
y = y[keep,,keep.lib.sizes = FALSE]
y = calcNormFactors(y)
y$samples
design = model.matrix(~Time+Treat)
rownames(design) = colnames(y)
design
y = estimateDisp(y, design, robust=TRUE)
y$common.dispersion
plotBCV(y)
fit = glmQLFit(y, design, robust = TRUE)
plotQLDisp(fit)
qlf = glmQLFTest(fit)
topTags(qlf)
top = rownames(topTags(qlf))
cpm(y)[top,]
summary(decideTests(qlf))
plotMD(qlf)
abline(h = c(-1,1), col = "blue")
output = topTags(qlf, n =100000)
top2 = rownames(output)
cpm2 = cpm(y)[top2,]
output2 = as.data.frame(output)
cpm3 = as.data.frame(cpm2)
output_all = cbind(cpm3,output2)
output_DEG = output_all[(output_all$FDR < 0.05 & output_all$logFC > 1) | (output_all$FDR < 0.05 & output_all$logFC < -1),]
output_Up = output_all[output_all$FDR < 0.05 & output_all$logFC > 1,]
output_Down = output_all[output_all$FDR < 0.05 & output_all$logFC < -1,]
write.table(output_all, file = "All.txt", row.names = T, sep = "\t", quote = F)
write.table(output_DEG, file = "DEG.txt", row.names = T, sep = "\t", quote = F)
write.table(output_Up, file = "Up.txt", row.names = T, sep = "\t", quote = F)
write.table(output_Down, file = "Down.txt",, row.names = T, sep = "\t", quote = F)
参考：Bioconductor-edgeR