Created
March 3, 2016 22:39
-
-
Save katwre/d2a3f070da63e8abcb53 to your computer and use it in GitHub Desktop.
UCSC table to GRanges object (only chrom, start and end)
This file contains hidden or 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
uniform_tfbs = data.frame(cell.line=c("GM12878" ,"H1-hESC" ,"K562", "HeLa-S3", "HepG2", "HUVEC", "A549", "IMR-90", "MCF-7"), | |
schema=c("wgEncodeAwgTfbsUtaGm12878CtcfUniPk", "wgEncodeAwgTfbsUtaH1hescCtcfUniPk", "wgEncodeAwgTfbsUtaK562CtcfUniPk", "wgEncodeAwgTfbsUtaHelas3CtcfUniPk", | |
"wgEncodeAwgTfbsUtaHepg2CtcfUniPk", "wgEncodeAwgTfbsUtaHuvecCtcfUniPk", "wgEncodeAwgTfbsHaibA549Ctcfsc5916Pcr1xDex100nmUniPk", | |
"wgEncodeAwgTfbsSydhImr90CtcfbIggrabUniPk", "wgEncodeAwgTfbsUtaMcf7CtcfSerumstimUniPk"), | |
stringsAsFactors = FALSE) | |
#' UCSC table to GRanges object (only chrom, start and end) | |
#' | |
#' @param table UCSC table | |
#' @param assembly genome assembly | |
UCSCtable2Granges = function(table, assembly="hg19"){ | |
require(RMySQL) | |
require(GenomicRanges) | |
con <- dbConnect(MySQL(),user="genome",db=assembly,host="genome-mysql.cse.ucsc.edu") | |
query = dbSendQuery(con, paste0("SELECT chrom, chromStart, chromEnd FROM ", assembly, ".", table)); | |
res = fetch(query, n=-1); # n = -1 to retrieve all pending records. | |
dbClearResult(query) | |
dbDisconnect(con) | |
makeGRangesFromDataFrame(res, | |
seqnames.field="chrom", start.field="chromStart", end.field="chromEnd") | |
} | |
uniform_tfbs_schemas_gr = mclapply(uniform_tfbs$schema, | |
function(table){ | |
print(table) | |
UCSCtable2Granges(table, "hg19") | |
}, | |
mc.cores=9) | |
names(uniform_tfbs_schemas_gr) = uniform_tfbs$cell.line |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment