I have a dataframe like below:
dput(trans_eqtl[1:3,1:10])
structure(list(Gene = c("ENSG00000132819", "ENSG00000101162",
"ENSG00000132819"), `Gene-Chr` = c(20, 20, 20), `Gene-Pos` = c(55975426,
57598009, 55975426), RsId = c("rs6084653", "rs156356", "rs1741314"
), `SNP-Chr` = c(20, 20, 20), `SNP-Pos` = c(4157072, 1819280,
4155193), start = c(57391407, 59019254, 57391407), end = c(57409333,
59025466, 57409333), Ds_cismb = c(56391407, 58019254, 56391407
), De_cismb = c(58409333, 60025466, 58409333)), row.names = c(NA,
3L), class = "data.frame")
I am trying to keep those rows only for whose columns match the following condition:
I want to filter snps based on its position: if SNP position is more than De_cismb or less than Ds_cismb consider it and add to the table trans_snp.
I tried this code but it doesn't give me the right subset:
##check for trans_Snp
trans_snp <- NULL
for(i in 1:dim(trans_eqtl)[1]){
if((trans_eqtl$`SNP-Pos`[i] > trans_eqtl$De_cismb[i])==TRUE | (trans_eqtl$`SNP-Pos`[i] < trans_eqtl$Ds_cismb[i])==TRUE){
x <- which(trans_eqtl$`SNP-Pos`[i] > trans_eqtl$De_cismb[i])
y <- which(trans_eqtl$`SNP-Pos`[i] < trans_eqtl$Ds_cismb[i])
value <- trans_eqtl[x,]
value <- trans_eqtl[y,]
}
trans_snp <- rbind(trans_snp,value)
}
This is the output dataframe that I am getting:
dput(trans_snp[1:4,1:10])
structure(list(Gene = c("ENSG00000132819", "ENSG00000132819",
"ENSG00000132819", "ENSG00000132819"), `Gene-Chr` = c(20, 20,
20, 20), `Gene-Pos` = c(55975426, 55975426, 55975426, 55975426
), RsId = c("rs6084653", "rs6084653", "rs6084653", "rs6084653"
), `SNP-Chr` = c(20, 20, 20, 20), `SNP-Pos` = c(4157072, 4157072,
4157072, 4157072), start = c(57391407, 57391407, 57391407, 57391407
), end = c(57409333, 57409333, 57409333, 57409333), Ds_cismb = c(56391407,
56391407, 56391407, 56391407), De_cismb = c(58409333, 58409333,
58409333, 58409333)), row.names = c(NA, 4L), class = "data.frame")
Its only filled with the first value of the input dataframe. Does anyone know where I am making the mistake.
In dplyr:
library(dplyr)
trans_eqtl %>%
filter(`SNP-Pos` > De_cismb | `SNP-Pos` < Ds_cismb) -> trans_snp