# HG changeset patch # User testtool # Date 1484752399 18000 # Node ID 556ebcea69894e0b3244755d5bfd3095d62bc3ac # Parent 1ab7612c510753c2c46e87f103e5fddc645462ba Uploaded diff -r 1ab7612c5107 -r 556ebcea6989 getGEO.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/getGEO.R Wed Jan 18 10:13:19 2017 -0500 @@ -0,0 +1,52 @@ +require("BiocGenerics", quietly = TRUE) +require("data.table", quietly = TRUE) +require("GEOquery", quietly = TRUE) +require("rtracklayer", quietly = TRUE) +require("FDb.InfiniumMethylation.hg19", quietly = TRUE) + +options(warn = -1) +args <- commandArgs(trailingOnly = TRUE) +GSMTable = args[1] +MetaTable = args[2] +IlmnTable = args[3] +gmTable = args[4] + +TAB = fread(GSMTable) + +if (is.null(TAB)) { + stop("Must specify input files") +} else { + GEODataTable <- getGEO(TAB$ID[1], getGPL = FALSE) + IlmnIDTable <- Table(GEODataTable) + MetaData <- data.frame(Meta(GEODataTable)) + + + write.csv(MetaData, MetaTable, row.names = FALSE, sep = "\t") +} + +hm450.hg19 <- getPlatform() + +IlmnInfo <- + data.table( + IlmnID = names(hm450.hg19), + CHR = as.data.frame(hm450.hg19@seqnames)$value, + BP = as.numeric(hm450.hg19@elementMetadata$probeStart) + ) + + +write.csv(IlmnInfo, IlmnTable, row.names = FALSE, sep = "\t") + + +if (length(TAB$ID) > 1) { + mysamples <- + do.call("data.table", lapply(TAB$ID[-1], function(x) + Table(getGEO(x, getGPL = FALSE))[, -1])) + + gmSet <- data.table(IlmnIDTable[, -1], mysamples) + +} else { + gmSet <- Table(getGEO(TAB$ID, getGPL = FALSE)) +} + + +write.csv(gmSet, gmTable, row.names = FALSE, sep = "\t")