rCGH (version 1.2.0)

hg38: Hg38 Chromosome Lengths and Centromere Locations

Description

A data set containing lengths and centromere locations for each of the 24 chromosomes, according to Hg38.

Usage

hg38

Value

Format

A data set with 24 rows and 5 columns:

• chrom: chromosome number.
• length: chromosome length.
• centromerStart: centromere start position.
• centromerEnd: centromere start position.
• cumlen: cumulative length (where the previous chromosome ends).

Source

These data derived from the Hg38 gap UCSC table, freely available at: UCSC Access date: 10-10-2015 Within the browser, select: group: All Tables database: hg38 table: gap

Examples

# For users convenience, we provide a prebuilt dataset
# containing the Hg38 chr lengths, and centromeres location.
hg38

# The same dataset can be obtained as follow:
## Not run: 
# library(BSgenome)
# library(rtracklayer)
# 
# getChrLength <- function(genome){
#     genome <- sprintf("BSgenome.Hsapiens.UCSC.
#     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$chrom),]
# }
# getCentromeres <- function(genome){
#     mySession <- try(browserSession("UCSC"), silent=TRUE)
#     # In case it fails, use another mirror
#     if(inherits(mySession, "try-error"))
#         mySession <- browserSession("UCSC",
#                                     url="http://genome-euro.ucsc.edu/cgi-bin/")
#     genome(mySession) <- genome
#     obj <- ucscTableQuery(mySession, table="gap")
#     tbl <- getTable(obj)
#     if(!"centromere" 
#         return(NULL)
#     tbl <- tbl[tbl$type=="centromere", c("chrom", "chromStart", "chromEnd")]
#     colnames(tbl)[2:3] <- c("centromerStart", "centromerEnd")
#     .chrAsNum(tbl)
# }
# makeHg <- function(genome){
#     chrL <- getChrLength(genome)
#     ctm <- getCentromeres(genome)
#     # Notice that, in case of Hg38, centromeres locations are in Hg19.
#     if(is.null(ctm))
#         ctm <- getCentromeres("hg19")
#     tbl <- merge(chrL, ctm, by="chrom")
#     cumlen <- c(0, cumsum(as.numeric(tbl$length))[-nrow(tbl)])
#     cbind.data.frame(tbl, cumlen=cumlen)    
# }
# hg38 <- makeHg("hg38")
# hg38
# ## End(Not run)