hg19 {rCGH}R Documentation

Hg19 Chromosome Lengths and Centromere Locations

Description

A data set containing lengths and centromere locations for each of the 24 chromosomes, according to Hg19.

Usage

hg19

Format

A data set with 24 rows and 5 columns:

Value

a data set.

Author(s)

Frederic Commo

Source

These data derived from the Hg19 gap UCSC table, freely available at: UCSC
Access date: 1-31-2014
Within the browser, select:
group: All Tables
database: hg19
table: gap

Examples

# For users convenience, we provide a prebuilt dataset
# containing the Hg19 chr lengths, and centromeres location.
hg19

# The same dataset can be obtained as follow:
## Not run: 
library(BSgenome)
library(rtracklayer)

getChrLength <- function(genome = "BSgenome.Hsapiens.UCSC.hg19"){
    g <- getBSgenome(genome, masked=FALSE)
    data.frame(chrom=1:24, length=seqlengths(g)[1:24])
}
.chrAsNum <- function(tbl){
    tbl$chrom <- gsub("chr", "", tbl$chrom)
    tbl$chrom[tbl$chrom=="X"] <- 23
    tbl$chrom[tbl$chrom=="Y"] <- 24
    tbl$chrom <- as.numeric(tbl$chrom)
    tbl[order(tbl$chrom),]
}
getCentromeres <- function( genome="hg19" ){
    mySession <- try(browserSession("UCSC"), silent=TRUE)
    # In case of failure, try another mirror
    if(inherits(mySession, "try-error"))
        mySession <- browserSession("UCSC",
                                    url="http://genome-euro.ucsc.edu/cgi-bin/")
    genome(mySession) <- genome
    obj <- ucscTableQuery(mySession, table="gap")
    tbl <- getTable(obj)
    tbl <- tbl[tbl$type=="centromere", c("chrom", "chromStart", "chromEnd")]
    colnames(tbl)[2:3] <- c("centromerStart", "centromerEnd")
    .chrAsNum(tbl)
}
makeHg19 <- function(){
    tbl <- merge(getChrLength(), getCentromeres(), by="chrom")
    cumlen <- c(0, cumsum(as.numeric(tbl$length))[-nrow(tbl)])
    cbind.data.frame(tbl, cumlen=cumlen)    
}
hg19 <- makeHg19()
hg19

## End(Not run)

[Package rCGH version 1.20.0 Index]