数据挖掘—GPL17586探针ID与Gene名转换

https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GPL17586&targ=self&form=text&view=data

ids <- data.table::fread("../data/GPL17586.txt",data.table = F)
colnames(ids)
probe2gene <- ids[,c(2,8)]

library(stringr)  
probe2gene$symbol=trimws(str_split(probe2gene$gene_assignment,'//',simplify = T)[,2])
plot(table(table(probe2gene$symbol)),xlim=c(1,50))
head(probe2gene)

dim(probe2gene)

ids2 <- probe2gene[,c(1,3)]
colnames(ids2)
colnames(ids2) <- c("probe_id","symbol")

ids2 <- ids2[!ids2$symbol == "---",]
head(ids2)

ids2_filtered <- subset(ids2, !grepl("^(OTTHUMG|LOC)", symbol))

ids <- ids2_filtered
dim(ids)
head(ids)