Hello R users,
I am trying to create an object out of some data a colleague sent my way,
so to duplicate the following code...
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)]
###############################################
m2 = m
ll = list()
for(i in colnames(m2)){
str = strsplit(i, split = ".", fixed = T)[[1]]
if(str[4] == "11"){
}else{
ll = c(ll,i)
}
}
ll = unlist(ll)
m2 = m2[,ll]
colnames(m2) = sapply(colnames(m2), function(i){
str = strsplit(i,split = ".", fixed = T)[[1]]
p = paste(str[c(1:3)], collapse = "-")
})
clin = as.data.frame(fread(file
"/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/survival/FireHose/GBM/GBM.clin.merged.txt",
sep = "\t", header = F))
clin = t(clin)
colnames(clin) = clin[1,]
rownames(clin) = toupper(clin[,"patient.bcr_patient_barcode"])
clin = clin[2:length(clin[,1]),]
#"patient.stage_event.pathologic_stage"
clin1
clin[,c("patient.age_at_initial_pathologic_diagnosis","patient.days_to_death","patient.days_to_last_followup","patient.vital_status")]
clin1 = cbind(clin1,rep("bla",length(clin1[,1])))
clin2 = as.matrix(clin1)
colnames(clin2)[length(colnames(clin2))] = "time"
for(i in rownames(clin2)){
if(clin2[i,"patient.vital_status"] %in% c("alive")){
clin2[i,"patient.vital_status"] =0
}else if(clin2[i,"patient.vital_status"] %in% c("dead")){
clin2[i,"patient.vital_status"] =1
}else{
clin2[i,"patient.vital_status"] = "NA"
}
if(is.na(clin2[i,"patient.days_to_last_followup"])){
clin2[i,"time"] = clin2[i,"patient.days_to_death"]
}else{
clin2[i,"time"] =
clin2[i,"patient.days_to_last_followup"]
}
}
clin2 = clin2[!is.na(clin2[,"time"]),]
clin2 = clin2[!is.na(clin2[,"patient.vital_status"]),]
library(survival)
p = intersect(colnames(m2), rownames(clin2))
surv
Surv(as.numeric(clin2[p,"time"]),as.numeric(clin2[p,"patient.vital_status"]))
an_m = anno[anno$probe %in% rownames(m2),]
an_m = an[an$gene %in% rownames(exp),]
sur_z = apply(an_m, 1, function(i){
tryCatch(summary(coxph(surv ~
as.numeric(m2[as.character(i[1]),p])+as.numeric(clin2[p,"patient.age_at_initial_pathologic_diagnosis"])))$coefficients[1,c("z")],
error = function(e) NA)
})
sur_p = apply(an_m, 1, function(i){
tryCatch(summary(coxph(surv ~
as.numeric(m2[as.character(i[1]),p])+as.numeric(clin2[p,"patient.age_at_initial_pathologic_diagnosis"])))$coefficients[1,c("Pr(>|z|)")],
error = function(e) NA)
})
qsur = p.adjust(as.numeric(sur_p))
sur = cbind(sur_z,sur_p)
sur = cbind(sur,qsur)
The file is a text file
"/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt", which
is
then proceeded by another txt. file
"/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/27K/GBM.txt, which I wish to
load subsequently. However, when i tried copying the procedure above I
received the following error message..
library(data.table)> anno = as.data.frame(fread(file
"/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt", sep
="\t",
header = T))
Error in fread(file
"/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt", :
File '/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt'
does
not exist or is non-readable.
getwd()=='C:/Users/Spencer/Documents'
The file does exit so in what context is it 'unreadable' and how might I
solve this situation?
Best,
Spencer
[[alternative HTML version deleted]]
On 4/22/19 11:49 AM, Spencer Brackett wrote:> Hello R users, > > I am trying to create an object out of some data a colleague sent my way, > so to duplicate the following code... > > library(data.table) > anno = as.data.frame(fread(file > "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt", sep ="\t", > header = T))At first glance it appeared that you sent the list a rather extensive bit of code and asked us to figure something out, but after looking at the error message it instead appears the it was the first effort at reading data from disk that threw an error. So the rest of the code is at best unnecessary and at worst seriously distracting (to us and more crucially to you). You should run your code one line at a time so you and the rest of us are not completely distracted. This was the error message:> anno = as.data.frame(fread(file"/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt", sep ="\t", header = T)) Error in fread(file "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt", : File '/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt' does not exist or is non-readable. You claim this file exists, but I'm uncertain how convincing that assertion should be "scored". What do either of these show? ?list.files(pattern =".txt$") # Or "mapper.txt" %in% list.files( paste0 ( getwd(), "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K")) -- David. PS Please learn to post in plain-text. It didn't cause a problem this time but it probably will at some time in the future.> meth = read.table(file > "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/27K/GBM.txt", sep ="\t", > header = T, row.names = 1) > meth = as.matrix(meth) > """ the loop just formats the methylation column names to match format""" > colnames(meth) = sapply(colnames(meth), function(i){ > c1 = strsplit(i,split = '.', fixed = T)[[1]] > c1[4] = paste(strsplit(c1[4],split = "",fixed = T)[[1]][1:2],collapse > "") > paste(c1,collapse = ".") > }) > exp = read.table(file > "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/RNAseq/GBM.txt", sep = "\t", > header = T, row.names = 1) > exp = as.matrix(exp) > c = intersect(colnames(exp),colnames(meth)) > exp = exp[,c] > meth = meth[,c] > m = apply(meth, 1, function(i){ > log2(i/(1-i)) > }) > m = t(as.matrix(m)) > an = anno[anno$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",]$coefficient[2,c(3:4)] > ############################################### > > m2 = m > ll = list() > for(i in colnames(m2)){ > str = strsplit(i, split = ".", fixed = T)[[1]] > if(str[4] == "11"){ > > }else{ > ll = c(ll,i) > } > } > ll = unlist(ll) > m2 = m2[,ll] > colnames(m2) = sapply(colnames(m2), function(i){ > str = strsplit(i,split = ".", fixed = T)[[1]] > p = paste(str[c(1:3)], collapse = "-") > }) > > > clin = as.data.frame(fread(file > "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/survival/FireHose/GBM/GBM.clin.merged.txt", > sep = "\t", header = F)) > clin = t(clin) > colnames(clin) = clin[1,] > rownames(clin) = toupper(clin[,"patient.bcr_patient_barcode"]) > clin = clin[2:length(clin[,1]),] > #"patient.stage_event.pathologic_stage" > clin1 > clin[,c("patient.age_at_initial_pathologic_diagnosis","patient.days_to_death","patient.days_to_last_followup","patient.vital_status")] > clin1 = cbind(clin1,rep("bla",length(clin1[,1]))) > clin2 = as.matrix(clin1) > colnames(clin2)[length(colnames(clin2))] = "time" > > for(i in rownames(clin2)){ > > if(clin2[i,"patient.vital_status"] %in% c("alive")){ > clin2[i,"patient.vital_status"] =0 > }else if(clin2[i,"patient.vital_status"] %in% c("dead")){ > clin2[i,"patient.vital_status"] =1 > }else{ > clin2[i,"patient.vital_status"] = "NA" > } > > if(is.na(clin2[i,"patient.days_to_last_followup"])){ > clin2[i,"time"] = clin2[i,"patient.days_to_death"] > }else{ > clin2[i,"time"] = clin2[i,"patient.days_to_last_followup"] > } > } > > clin2 = clin2[!is.na(clin2[,"time"]),] > clin2 = clin2[!is.na(clin2[,"patient.vital_status"]),] > > library(survival) > p = intersect(colnames(m2), rownames(clin2)) > surv > Surv(as.numeric(clin2[p,"time"]),as.numeric(clin2[p,"patient.vital_status"])) > > an_m = anno[anno$probe %in% rownames(m2),] > an_m = an[an$gene %in% rownames(exp),] > > sur_z = apply(an_m, 1, function(i){ > tryCatch(summary(coxph(surv ~ > as.numeric(m2[as.character(i[1]),p])+as.numeric(clin2[p,"patient.age_at_initial_pathologic_diagnosis"])))$coefficients[1,c("z")], > error = function(e) NA) > }) > > sur_p = apply(an_m, 1, function(i){ > tryCatch(summary(coxph(surv ~ > as.numeric(m2[as.character(i[1]),p])+as.numeric(clin2[p,"patient.age_at_initial_pathologic_diagnosis"])))$coefficients[1,c("Pr(>|z|)")], > error = function(e) NA) > }) > > qsur = p.adjust(as.numeric(sur_p)) > sur = cbind(sur_z,sur_p) > sur = cbind(sur,qsur) > > > The file is a text file > "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt", which is > then proceeded by another txt. file > "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/27K/GBM.txt, which I wish to > load subsequently. However, when i tried copying the procedure above I > received the following error message.. > > library(data.table) >> anno = as.data.frame(fread(file > "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt", sep ="\t", > header = T)) > Error in fread(file > "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt", : > File '/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt' does > not exist or is non-readable. > getwd()=='C:/Users/Spencer/Documents' > > The file does exit so in what context is it 'unreadable' and how might I > solve this situation? > > Best, > > Spencer > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code.
file.info( "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt" ) would tell about the permissions on the file, if it exists (and give NA's if it did not). Bill Dunlap TIBCO Software wdunlap tibco.com On Mon, Apr 22, 2019 at 2:00 PM David Winsemius <dwinsemius at comcast.net> wrote:> > On 4/22/19 11:49 AM, Spencer Brackett wrote: > > Hello R users, > > > > I am trying to create an object out of some data a colleague sent my way, > > so to duplicate the following code... > > > > library(data.table) > > anno = as.data.frame(fread(file > > "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt", sep ="\t", > > header = T)) > > > At first glance it appeared that you sent the list a rather extensive > bit of code and asked us to figure something out, but after looking at > the error message it instead appears the it was the first effort at > reading data from disk that threw an error. So the rest of the code is > at best unnecessary and at worst seriously distracting (to us and more > crucially to you). > > You should run your code one line at a time so you and the rest of us > are not completely distracted. This was the error message: > > > anno = as.data.frame(fread(file > > "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt", sep ="\t", > header = T)) > Error in fread(file > "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt", : > File '/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt' does > not exist or is non-readable. > > You claim this file exists, but I'm uncertain how convincing that > assertion should be "scored". What do either of these show? > > list.files(pattern =".txt$") > > # Or > > "mapper.txt" %in% list.files( paste0 ( getwd(), > "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K")) > > -- > > David. > > > PS Please learn to post in plain-text. It didn't cause a problem this > time but it probably will at some time in the future. > > > 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)] > > ############################################### > > > > m2 = m > > ll = list() > > for(i in colnames(m2)){ > > str = strsplit(i, split = ".", fixed = T)[[1]] > > if(str[4] == "11"){ > > > > }else{ > > ll = c(ll,i) > > } > > } > > ll = unlist(ll) > > m2 = m2[,ll] > > colnames(m2) = sapply(colnames(m2), function(i){ > > str = strsplit(i,split = ".", fixed = T)[[1]] > > p = paste(str[c(1:3)], collapse = "-") > > }) > > > > > > clin = as.data.frame(fread(file > > > "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/survival/FireHose/GBM/GBM.clin.merged.txt", > > sep = "\t", header = F)) > > clin = t(clin) > > colnames(clin) = clin[1,] > > rownames(clin) = toupper(clin[,"patient.bcr_patient_barcode"]) > > clin = clin[2:length(clin[,1]),] > > #"patient.stage_event.pathologic_stage" > > clin1 > > > clin[,c("patient.age_at_initial_pathologic_diagnosis","patient.days_to_death","patient.days_to_last_followup","patient.vital_status")] > > clin1 = cbind(clin1,rep("bla",length(clin1[,1]))) > > clin2 = as.matrix(clin1) > > colnames(clin2)[length(colnames(clin2))] = "time" > > > > for(i in rownames(clin2)){ > > > > if(clin2[i,"patient.vital_status"] %in% c("alive")){ > > clin2[i,"patient.vital_status"] =0 > > }else if(clin2[i,"patient.vital_status"] %in% c("dead")){ > > clin2[i,"patient.vital_status"] =1 > > }else{ > > clin2[i,"patient.vital_status"] = "NA" > > } > > > > if(is.na(clin2[i,"patient.days_to_last_followup"])){ > > clin2[i,"time"] = clin2[i,"patient.days_to_death"] > > }else{ > > clin2[i,"time"] = clin2[i,"patient.days_to_last_followup"] > > } > > } > > > > clin2 = clin2[!is.na(clin2[,"time"]),] > > clin2 = clin2[!is.na(clin2[,"patient.vital_status"]),] > > > > library(survival) > > p = intersect(colnames(m2), rownames(clin2)) > > surv > > > Surv(as.numeric(clin2[p,"time"]),as.numeric(clin2[p,"patient.vital_status"])) > > > > an_m = anno[anno$probe %in% rownames(m2),] > > an_m = an[an$gene %in% rownames(exp),] > > > > sur_z = apply(an_m, 1, function(i){ > > tryCatch(summary(coxph(surv ~ > > > as.numeric(m2[as.character(i[1]),p])+as.numeric(clin2[p,"patient.age_at_initial_pathologic_diagnosis"])))$coefficients[1,c("z")], > > error = function(e) NA) > > }) > > > > sur_p = apply(an_m, 1, function(i){ > > tryCatch(summary(coxph(surv ~ > > > as.numeric(m2[as.character(i[1]),p])+as.numeric(clin2[p,"patient.age_at_initial_pathologic_diagnosis"])))$coefficients[1,c("Pr(>|z|)")], > > error = function(e) NA) > > }) > > > > qsur = p.adjust(as.numeric(sur_p)) > > sur = cbind(sur_z,sur_p) > > sur = cbind(sur,qsur) > > > > > > The file is a text file > > "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt", which is > > then proceeded by another txt. file > > "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/27K/GBM.txt, which I wish to > > load subsequently. However, when i tried copying the procedure above I > > received the following error message.. > > > > library(data.table) > >> anno = as.data.frame(fread(file > > "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt", sep ="\t", > > header = T)) > > Error in fread(file > > "/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt", : > > File '/rsrch1/bcb/kchen_group/v_mohanty/data/TCGA/450K/mapper.txt' > does > > not exist or is non-readable. > > getwd()=='C:/Users/Spencer/Documents' > > > > The file does exit so in what context is it 'unreadable' and how might I > > solve this situation? > > > > Best, > > > > Spencer > > > > [[alternative HTML version deleted]] > > > > ______________________________________________ > > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > > https://stat.ethz.ch/mailman/listinfo/r-help > > PLEASE do read the posting guide > http://www.R-project.org/posting-guide.html > > and provide commented, minimal, self-contained, reproducible code. > > ______________________________________________ > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide > http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. >[[alternative HTML version deleted]]