美文网首页
探索kegg库的brite子库

探索kegg库的brite子库

作者: 一只烟酒僧 | 来源:发表于2020-07-16 19:38 被阅读0次
######################################################## 
#-------------------------------------------------------
# Topic:探索kegg库的brite子库
# Author:Wang Haiquan
# Date:Thu Jul 16 17:58:03 2020
# Mail:mg1835020@smail.nju.edu.cn
#-------------------------------------------------------
########################################################



library(stringr)
library(KEGGREST)
listDatabases()
brite_list<-keggList("brite")
#对应位置:https://www.kegg.jp/kegg/brite.html
#我想获得kegg中的transporter的信息
which(brite_list=="Transporters")
transporter<-keggGet("br:ko02000")
transporter<-str_split(transporter,"\\n",simplify = T)
transporter[1:100]
#切割
index<-grep("^A",transporter)
index_1<-rep(0,time=length(transporter))
index_2<-index[-1]-1
index_2[length(index_2)+1]<-length(transporter)
for (i in 1:(length(index))) {
  index_1[index[i]:index_2[i]]<-i
}
index_1[!grepl("^A|^B|^C|^D|^E|^F|^G",transporter)]<-0
index_1
transporter<-as.character(transporter)
transporter<-split(transporter,index_1)
#整理信息
names(transporter)<-sapply(transporter,function(x){x[1]})
transporter_gene<-lapply(transporter,function(x){x[grep("K[0-9]{1,}",x)]})
transporter_gene<-transporter_gene[-1]
transporter_gene<-lapply(transporter_gene,function(x){a=x;a=str_split(a,";",simplify = T)})
transporter_gene<-lapply(transporter_gene,function(x){a=x;b=a[,1];b=gsub(", ",",",b);b=gsub(" ",":",b);b=str_split(b,":{1,}",simplify = T);cbind(b,a[,2])})
transporter_gene<-lapply(transporter_gene,function(x){x=data.frame(geneid=x[,2],
                                                                   gene_sym=x[,3],
                                                                   gene_fullname=x[,4])})
transporter_gene_list<-data.frame()
for (i in 1:length(transporter_gene)) {
  transporter_gene_list_1<-transporter_gene[[i]]
  transporter_gene_list_1$supercluster<-names(transporter_gene)[i]
  transporter_gene_list<-rbind(transporter_gene_list,transporter_gene_list_1)
}
transporter_gene_list
table(transporter_gene_list$supercluster)

 # AABC transporters, eukaryotic type  AABC transporters, prokaryotic type 
# 96                                  513 
# AMajor facilitator superfamily (MFS)                  AOther transporters 
# 183                                  722 
# APhosphotransferase system (PTS)         ASolute carrier family (SLC) 
# 85                                  317 

相关文章

网友评论

      本文标题:探索kegg库的brite子库

      本文链接:https://www.haomeiwen.com/subject/pdumhktx.html