Ensembl_ID to gene_symbol

######################################################################
###################    Ensembl_ID转gene_symbol   #####################
######################################################################




library(BiocManager)
library(tidyverse)
library(dplyr)
library(DESeq2)
library(DESeq2)




test1=read.table("./ENS-genetype-genename.txt",sep="\t",header=T)
test2=read.table("./joined_counts.txt",sep="\t",header=T)
merge <- inner_join(test1, test2,by = "ID") %>% dplyr::select(-1)
write.table(merge,file="symbol.txt",sep="\t",quote=F,row.names=F) 



datagene<- merge[merge$Gene.type=="protein_coding",]
datalncrna<- merge[merge$Gene.type=="lncRNA",]
datamirna<- merge[merge$Gene.type=="miRNA",]
datagene<- datagene[,-1]



# 以变量x去重，返回所有变量  
avereps(datagene[,-1],ID=data1$id)                                 #重复序列取均值，前半部分为只保留矩阵，后半部分设id（基因名）列为被查找的重复列
datagene<-datagene[!duplicated(data1$id),]                         #合并删除重复序列





##用函数将Ensembl_ID转gene_symbol##
library(clusterprofiler)
library(org.Hs.eg.db)
df<-bitr(rownames(DEG),fromType="SYMBOL",toType=c("ENTREZID"),orgDb=org.Hs.eg.db