Last active
December 27, 2016 06:13
-
-
Save JakeConway/d875a8504ec67a0719fd to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
setwd("/Users/jakeconway/Desktop/icgcSampleData/Set 1") | |
fileList <- list.files() | |
set1 <- data.frame(); set2 <- data.frame(); set3 <- data.frame(); | |
for(file in fileList){ | |
temp_data <- read.table(file, header=TRUE, sep="\t") | |
temp_data$Mutation.ID <- as.character(temp_data$Mutation.ID) | |
set1 <- rbind(set1, temp_data) | |
rm(temp_data) | |
} | |
setwd("/Users/jakeconway/Desktop/icgcSampleData/Set 2") | |
fileList <- list.files() | |
for(file in fileList){ | |
temp_data <- read.table(file, header=TRUE, sep="\t") | |
temp_data$Mutation.ID <- as.character(temp_data$Mutation.ID) | |
set2 <- rbind(set2, temp_data) | |
rm(temp_data) | |
} | |
setwd("/Users/jakeconway/Desktop/icgcSampleData/Set 3") | |
fileList <- list.files() | |
for(file in fileList){ | |
temp_data <- read.table(file, header=TRUE, sep="\t") | |
temp_data$Mutation.ID <- as.character(temp_data$Mutation.ID) | |
set3 <- rbind(set3, temp_data) | |
rm(temp_data) | |
} | |
set1IDs <- set1$Mutation.ID | |
set2IDs <- set2$Mutation.ID | |
set3IDs <- set3$Mutation.ID | |
data <- do.call("rbind", list(set1, set2, set3)) | |
rm(set1, set2, set3) | |
fill <- rep(0, 3*nrow(data)) | |
setMatrix <- matrix(fill, ncol = 3) | |
colnames(setMatrix) <- c("Set1", "Set2", "Set3") | |
data <- cbind(data, setMatrix) | |
data$Set1[which(data$Mutation.ID %in% set1IDs)] <- 1 | |
data$Set2[which(data$Mutation.ID %in% set2IDs)] <- 1 | |
data$Set3[which(data$Mutation.ID %in% set3IDs)] <- 1 | |
genomicData <- as.character(data$Genomic.DNA.Change) | |
genomicData <- strsplit(genomicData, ":g.") | |
chromosome <- unlist(lapply(genomicData, function(x){x <- x[1]})) | |
specificSub <- unlist(lapply(genomicData, function(x){ x <- gsub('[[:digit:]]+', '', x[2])})) | |
data$chromosome <- chromosome | |
data$specific.substitution <- specificSub | |
rm(genomicData); data$Genomic.DNA.Change <- NULL | |
cons <- as.character(data$Consequences) | |
typeAndGene <- strsplit(cons, ": ") | |
mutationType <- unlist(lapply(typeAndGene, function(x){x <- x[1]})) | |
gene <- unlist(lapply(typeAndGene, function(x){x <- strsplit(x[2], " "); x <- x[[1]][1]})) | |
data$specific.mutation.type <- mutationType | |
data$gene <- gene | |
totalDonors <- unlist(lapply(strsplit(as.character(data$Donors.Affected), "/"), function(x)x <-x[2])) | |
data$total.donors <- as.integer(totalDonors) | |
data$Consequences <- as.character(data$Consequences) | |
data$Type <- as.character(data$Type) | |
data$Donors.Affected <- as.character(data$Donors.Affected) | |
data$Projects.Mutation.Observed <- as.character(data$Projects.Mutation.Observed) | |
setwd("/Users/jakeconway/Desktop") | |
write.table(data, file = "icgcData.txt", sep = "\t") | |
jsonData <- list( | |
file = "/Users/jakeconway/Desktop", | |
name = "icgcData.txt", | |
header = 0, | |
separator = "\t", | |
skip = 0, | |
meta = list(c(type = "id", index = 0, name = "Mutation.ID"), | |
c(type = "character", index = 1, name = "Type"), | |
c(type = "character", index = 2, name = "Consequences"), | |
c(type = "character", index = 3, name = "Donors.Affected"), | |
c(type = "character", index = 4, name = "Projects.Mutation.Observed"), | |
c(type = "character", index = 8, name = "chromosome"), | |
c(type = "character", index = 9, name = "specific.substitution"), | |
c(type = "character", index = 10, name = "specific.mutation.type"), | |
c(type = "character", index = 11, name = "gene"), | |
c(type = "integer", index = 12, name = "total.donors")), | |
sets = c(format = "binary", start = 5, end = 7) | |
) | |
jsonData <- toJSON(jsonData) | |
write(jsonData, "icgcData.json") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment