剔除了两个样品前后的差异分析结果没什么区别？

load( file = '../GSE193983/step1_output.Rdata')
# ~~~~~ heatmap~~~~~
cg=names(tail(sort(apply(dat,1,sd)),1000))#apply按行（'1'是按行取，'2'是按列取）取每一行的方差，从小到大排序，取最大的1000个
library(pheatmap)
pheatmap(dat[cg,],show_colnames =F,show_rownames = F) #对那些提取出来的1000个基因所在的每一行取出，组合起来为一个新的表达矩阵
n=t(scale(t(dat[cg,]))) # 'scale'可以对log-ratio数值进行归一化
n[n>2]=2 
n[n< -2]= -2
head(n)
pheatmap(n,show_colnames =F,show_rownames = F)
ac=data.frame(Group=group_list)
rownames(ac)=colnames(n)
pheatmap(n,show_colnames =T,show_rownames = F,
         annotation_col=ac)
colnames(dat)
boxplot(dat['GSTM4',]~group_list)
kp=!colnames(dat) %in% c("GSM5825026" ,"GSM5825027")
dat=dat[,kp]
group_list=group_list[kp]
table(group_list)
save(gse_number,dat,group_list,
     #  probe_exp,probe_info,pd,
     file = 'step1_output.Rdata')

rm(list = ls())
library(data.table)
raw_deg = fread(file = './GSE193983//DEG.csv',data.table = F)
remove_deg = fread(file = './remove//DEG.csv',data.table = F)

colnames(remove_deg)
rownames(raw_deg)=raw_deg$name 
rownames(remove_deg)=remove_deg$name

ids=intersect(rownames(raw_deg),
              rownames(remove_deg))
df= data.frame(
  raw_deg = raw_deg[ids,'logFC'],
  remove_deg = remove_deg[ids,'logFC']
)
library(ggpubr)
ggscatter(df, x = "raw_deg", y = "remove_deg",
          color = "black", shape = 21, size = 3, # Points color, shape and size
          add = "reg.line",  # Add regressin line
          add.params = list(color = "blue", fill = "lightgray"), # Customize reg. line
          conf.int = TRUE, # Add confidence interval
          cor.coef = TRUE, # Add correlation coefficient. see ?stat_cor
          cor.coeff.args = list(method = "pearson",  label.sep = "\n")
)

df= data.frame(
  raw_deg = raw_deg[ids,'g'],
  remove_deg = remove_deg[ids,'g']
)
table(df)
gplots::balloonplot(table(df))

symbols_list = split(ids,paste(df[,1],df[,2]))
library(clusterProfiler)
library(org.Hs.eg.db)
library(ReactomePA)
library(ggplot2)
library(stringr) 
# 首先全部的symbol 需要转为 entrezID
gcSample = lapply(symbols_list, function(y){ 
  y=as.character(na.omit(AnnotationDbi::select(org.Hs.eg.db,
                                               keys = y,
                                               columns = 'ENTREZID',
                                               keytype = 'SYMBOL')[,2])
  )
  y
})
gcSample
pro='test'
# 第1个注释是 KEGG 
xx <- compareCluster(gcSample, fun="enrichKEGG",
                     organism="hsa", pvalueCutoff=0.3)
dotplot(xx)  + theme(axis.text.x=element_text(angle=45,hjust = 1)) + 
  scale_y_discrete(labels=function(x) str_wrap(x, width=50)) 
ggsave(paste0(pro,'_kegg.pdf'),width = 10,height = 8)