GEO多数据集联合分析-文献复现

rm(list = ls())
library(GEOquery)
library(stringr)
#芯片原始数据处理
BiocManager::install(c( 'oligo' ),ask = F,update = F)
library(oligo)
BiocManager::install(c( 'pd.hg.u133.plus.2' ),ask = F,update = F)
library(pd.hg.u133.plus.2)

dir='D:\\ferroptosis_diabetic_kidney\\GSE30122_RAW'
od=getwd()
setwd(dir)
celFiles <- list.celfiles(listGzipped = T)
celFiles
affyRaw <- read.celfiles( celFiles )
setwd(od)
eset <- rma(affyRaw)
eset
colnames(eset)
#列名需要修改以获取临床信息
colnames(eset) <- str_sub(colnames(eset),end = 9)
exp1 <- exprs(eset)
dim(exp1)
exp1[1:4,1:4]
#表达矩阵已取log， 不用再取log
boxplot(exp1, las = 2)
#提取临床信息
eSet1 <- getGEO("GSE30122", 
                destdir = '.', 
                getGPL = F)
pd1 <- pData(eSet1[[1]])
if(!identical(rownames(pd1),colnames(exp1))) exp1 = exp1[,match(rownames(pd1),colnames(exp1))]

#数据下载
eSet2 <- getGEO("GSE47185", 
                destdir = '.', 
                getGPL = F)
#(1)提取表达矩阵exp
exp2 <- exprs(eSet2[[1]])
exp2[1:4,1:4]
dim(exp2)
boxplot(exp2)
#(2)提取临床信息
pd2 <- pData(eSet2[[1]])
#GSE47185在文中作者提取了14个DN样本
str_detect(pd2$title,"Diabetic Nephropathy")
pd2 <- pd2[str_detect(pd2$title,"Diabetic Nephropathy"), ]
#只保留14个样本的表达矩阵
if(!identical(rownames(pd2),colnames(exp2))) exp2 = exp2[,match(rownames(pd2),colnames(exp2))]
dim(exp2)
boxplot(exp2,las = 2)

# 样本矫正
library(limma)
exp2=normalizeBetweenArrays(exp2)
boxplot(exp2,las=2)

#(3)提取芯片平台编号
gpl1 <- eSet1[[1]]@annotation
gpl2 <- eSet2[[1]]@annotation

#(4)探针注释的获取
#由于来源于不同平台的芯片数据导致表达矩阵行名不一样，
#所以先分别注释成gene symbol,再合并表达矩阵，去除批次效应
library(tinyarray)
if (!requireNamespace("BiocManager", quietly = TRUE))
  install.packages("BiocManager")
BiocManager::install("hgu133a2.db")
find_anno(gpl1)
library(hgu133a2.db);ids <- toTable(hgu133a2SYMBOL)
ids1 <- ids
#为exp数据框添加几列
exp1 <- as.data.frame(exp1)
#1.加probe_id列，把行名变成一列
library(dplyr)
exp1 = mutate(exp1,probe_id = rownames(exp1))
#2.加上探针注释
ids1 = distinct(ids1,symbol,.keep_all = T)
#其他去重方式在zz.去重方式.R
exp1 = inner_join(exp1,ids1,by="probe_id")
nrow(exp1) #如果行数为0就是你找的探针注释是错的。
rownames(exp1) <- exp1[,71]

#GSE47185数据集注释
find_anno(gpl2)
#没有相应的R包,自行从GEO网页界面下载平台注释文件并打开编辑保留所需信息
ids2 <- read.table("GPL11670_family.soft", header = T, sep = "\t")
#为exp数据框添加几列
exp2 <- as.data.frame(exp2)
#1.加probe_id列，把行名变成一列
library(dplyr)
exp2 = mutate(exp2,GeneID = rownames(exp2))
#2.加上探针注释
ids2 = distinct(ids2,ORF,.keep_all = T)
ids2 = ids2[, 2:3]
#其他去重方式在zz.去重方式.R
exp2 = inner_join(exp2,ids2,by="GeneID")
ids2$GeneID <- as.character (ids2$GeneID)
exp2 = inner_join(exp2,ids2,by="GeneID")
nrow(exp2) #如果行数为0就是你找的探针注释是错的。
rownames(exp2) <- exp2[,16]

#(4)合并表达矩阵
table(rownames(exp1) %in% rownames(exp2))
length(intersect(rownames(exp1),rownames(exp2)))
exp1 <- exp1[intersect(rownames(exp1),rownames(exp2)),]
exp2 <- exp2[intersect(rownames(exp1),rownames(exp2)),]
exp1 <- exp1[,1:69]
exp2 <- exp2[,1:14]
exp = cbind(exp1,exp2)
boxplot(exp)

Group1 = ifelse(str_detect(pd1$title,"Control"),"Normal", "DN")
Group2 = ifelse(str_detect(pd2$characteristics_ch1.1,"Diabetic Nephropathy"),"DN","Normal")
Group = c(Group1,Group2)
table(Group)
Group = factor(Group,levels = c("Normal","DN"))
save(Group,exp,file = "exp.Rdata")
dimnames <- list(rownames(exp),colnames(exp))
data <- matrix(as.numeric(as.matrix(exp)),nrow=nrow(exp),dimnames=dimnames)
dim(data)
class(data) 
group_list <- data.frame(
  sample = colnames(exp), c(rep("GSE30122",69),rep("GSE47185",14)))
rownames(group_list) <- group_list$sample
colnames(group_list)[2] <- "dataset"
group <- factor(group_list$dataset)
View(group_list)
library(FactoMineR)##没有请先安装
library(factoextra)
pdf(file = "PCA_before1.pdf",width = 7,height = 6)
pre.pca <- PCA(t(exp),graph = FALSE)
fviz_pca_ind(pre.pca,
             geom= "point",
             col.ind = group,
             addEllipses = TRUE,
             legend.title="Group"
)
dev.off()

#-------------------进行去批次------------------#
#### 使用sva包计算批次效应
library(sva)
exp_combat <- ComBat(exp, batch = group_list$dataset) # batch为批次信息
boxplot(exp_combat)
# 查看去除批次效应的结果如何
library(tinyarray)
draw_pca(exp = exp, group_list = group)

#做校正的PCA分析
pdf(file = "9_PCA_after.pdf",width = 7,height = 6)
pre.pca <- PCA(t(exp_combat),graph = FALSE)
fviz_pca_ind(pre.pca,
             geom= "point",
             col.ind = group,
             addEllipses = TRUE,
             legend.title="Group")
dev.off()

#差异分析
library(limma)
design = model.matrix(~Group)
fit = lmFit(exp,design)
fit = eBayes(fit)
deg = topTable(fit,coef = 2,number = Inf)
#3.加change列,标记上下调基因
logFC_t = 1.0
p_t = 0.05
#思考，如何使用padj而非p值
k1 = (deg$P.Value < p_t)&(deg$logFC < -logFC_t)
k2 = (deg$P.Value < p_t)&(deg$logFC > logFC_t)
deg = mutate(deg,change = ifelse(k1,"down",ifelse(k2,"up","stable")))
table(deg$change)
#火山图
library(ggplot2)
ggplot(data = deg, aes(x = logFC, y = -log10(P.Value))) +
  geom_point(alpha=0.4, size=3.5, aes(color=change)) +
  scale_color_manual(values=c("blue", "grey","red"))+
  geom_vline(xintercept=c(-logFC_t,logFC_t),lty=4,col="black",linewidth=0.8) +
  geom_hline(yintercept = -log10(p_t),lty=4,col="black",linewidth=0.8) +
  theme_bw()

#与ferroptosis- related genes (FRGs)取交集画韦恩图
#下载并读取文中FRGs文件，文中附件2即是。需整理成一列的TXT文件
deg = mutate(deg,symbol = rownames(deg))
DEG = deg$symbol[deg$change !="stable"]
FRG <- read.table("FRG.txt")
FRG <- FRG[,1]
library (VennDiagram)
venn.diagram(x= list(DEG = DEG,FRG = FRG),
             filename = "pic.png",
             height = 450, width = 450,
             resolution =300,
             imagetype="png",
             col="transparent",
             fill=c('#0099CC','#FF6666'),
             alpha = 0.50,
             cex=0.45,
             cat.cex=0.45,)

# FRDEGs热图----
# 表达矩阵行名替换为基因名
FRDEGs <- intersect(DEG,FRG)

exp = exp[deg$probe_id,]
rownames(exp) = deg$symbol
diff_gene = deg$symbol[deg$change !="stable"]

n = exp[FRDEGs,]
library(pheatmap)
annotation_col = data.frame(Group)
rownames(annotation_col) = colnames(n) 
pheatmap(n,show_colnames =F,
         show_rownames = T,
         scale = "row",
         cluster_cols = F, 
         annotation_col=annotation_col,
         breaks = seq(-3,3,length.out = 100)
) 

#4.对FRDEGs加ENTREZID列，用于富集分析（symbol转entrezid，然后inner_join）
FRDEG_gene <- deg[FRDEGs,]
library(clusterProfiler)
library(org.Hs.eg.db)
s2e = bitr(FRDEG_gene$symbol, 
           fromType = "SYMBOL",
           toType = "ENTREZID",
           OrgDb = org.Hs.eg.db)#人类,注意物种
#一部分基因没匹配上是正常的。<30%的失败都没事。
#其他物种http://bioconductor.org/packages/release/BiocViews.html#___OrgDb
nrow(FRDEG_gene)
FRDEG_gene = inner_join(FRDEG_gene,s2e,by=c("symbol"="SYMBOL"))
#多了几行少了几行都正常，SYMBOL与ENTREZID不是一对一的。
nrow(FRDEG_gene)
save(exp,Group,FRDEG_gene,logFC_t,p_t,file = "step4output.Rdata")

rm(list = ls())  
load(file = 'step4output.Rdata')
library(clusterProfiler)
library(ggthemes)
library(org.Hs.eg.db)
library(dplyr)
library(ggplot2)
library(stringr)
library(enrichplot)

#(1)输入数据
gene_diff = FRDEG_gene$ENTREZID

#(2)富集
ekk <- enrichKEGG(gene = gene_diff,organism = 'hsa')
ekk <- setReadable(ekk,OrgDb = org.Hs.eg.db,keyType = "ENTREZID")
ego <- enrichGO(gene = gene_diff,OrgDb= org.Hs.eg.db,
                ont = "ALL",readable = TRUE)
#setReadable和readable = TRUE都是把富集结果表格里的基因名称转为symbol
class(ekk)

#(3)可视化
dotplot(ego, split = "ONTOLOGY") + 
  facet_grid(ONTOLOGY ~ ., space = "free_y",scales = "free_y") 
dotplot(ekk)