[R] R Data

[Spencer Brackett]

Hello everyone,

The following is a portion of coding that a colleague sent. Given my lack
of experience in R, I am not quite sure what the significance of the
following arguments. Could anyone help me translate? For context, I am
aware of the downloading portion of the script... library(data.table) etc.,
but am not familiar with the portion pertaining to an1 .

library(data.table)
anno = as.data.frame(fread(file =
"/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt", sep ="\t",
header = T))
meth = read.table(file =
"/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/27K/GBM.txt", sep  ="\t",
header = T, row.names = 1)
meth = as.matrix(meth)
""" the loop just formats the methylation column names to match format"""
colnames(meth) = sapply(colnames(meth), function(i){
  c1 = strsplit(i,split = '.', fixed = T)[[1]]
  c1[4] = paste(strsplit(c1[4],split = "",fixed = T)[[1]][1:2],collapse =
"")
  paste(c1,collapse = ".")
})
exp = read.table(file =
"/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/RNAseq/GBM.txt", sep = "\t",
header = T, row.names = 1)
exp = as.matrix(exp)
c = intersect(colnames(exp),colnames(meth))
exp = exp[,c]
meth = meth[,c]
m = apply(meth, 1, function(i){
  log2(i/(1-i))
})
m = t(as.matrix(m))
an = anno[anno$probe %in% rownames(m),]
an = an[an$gene %in% rownames(exp),]
an = an[an$location %in% c("TSS200","TSS1500"),]

p = apply(an,1,function(i){
  tryCatch(summary(lm(exp[as.character(i[2]),] ~
m[as.character(i[1]),]))$coefficient[2,4], error= function(e)NA)
})
t = apply(an,1,function(i){
  tryCatch(summary(lm(exp[as.character(i[2]),] ~
m[as.character(i[1]),]))$coefficient[2,3], error= function(e)NA)
})
an1 =cbind(an,p)
an1 = cbind(an1,t)
an1$q = p.adjust(as.numeric(an1$p))
summary(lm(exp["MAOB",] ~ m["cg00121904",]$coefficient[2,c(3:4)]
###############################################

	[[alternative HTML version deleted]]