\name{Mmulatta}
\docType{package}

\alias{BSgenome.Mmulatta.UCSC.rheMac2-package}
\alias{BSgenome.Mmulatta.UCSC.rheMac2}
\alias{Mmulatta}


\title{Macaca mulatta (Rhesus) full genome (UCSC version rheMac2)}

\description{
  Macaca mulatta (Rhesus) full genome as provided by UCSC (rheMac2, Jan. 2006) and stored in Biostrings objects.  NOTE: In most assemblies available at UCSC, Tandem Repeats Finder repeats were filtered to retain only the repeats with period <= 12.  However, the filtering was omitted for this assembly, so the TRF masks contain all Tandem Repeats Finder results.
}

\details{
  
}

\note{
  This BSgenome data package was made from the following source data files:
  \preformatted{
sequences: chromFa.tar.gz, upstream1000.fa.gz, upstream2000.fa.gz, upstream5000.fa.gz
from http://hgdownload.cse.ucsc.edu/goldenPath/rheMac2/bigZips/
AGAPS masks: gap.txt.gz from http://hgdownload.cse.ucsc.edu/goldenPath/rheMac2/database/
RM and TRF masks: chromOut.tar.gz and chromTrf.tar.gz
from http://hgdownload.cse.ucsc.edu/goldenPath/rheMac2/bigZips/
  }
  See \code{?\link[BSgenome]{BSgenomeForge}} and the BSgenomeForge
  vignette (\code{vignette("BSgenomeForge")}) in the BSgenome software
  package for how to make a BSgenome data package.
}

\author{The Bioconductor Dev Team}

\seealso{
  \link[BSgenome]{BSgenome-class},
  \link[Biostrings]{DNAString-class},
  \code{\link[BSgenome]{available.genomes}},
  \link[BSgenome]{BSgenomeForge}
}

\examples{
Mmulatta
seqlengths(Mmulatta)
Mmulatta$chr1  # same as Mmulatta[["chr1"]]
## NOTE: In most assemblies available at UCSC, Tandem Repeats
## Finder repeats were filtered to retain only the repeats
## with period <= 12.  However, the filtering was omitted for
## this assembly, so, despite the description being displayed
## for this mask, it contains all the Tandem Repeats Finder
## results.
masks(Mmulatta$chr1)$TRF
## To get rid of the masks altogether:
unmasked(Mmulatta$chr1)

if ("AGAPS" \%in\% masknames(Mmulatta)) {

  ## Check that the assembly gaps contain only Ns:
  checkOnlyNsInGaps <- function(seq)
  {
    ## Replace all masks by the inverted AGAPS mask
    masks(seq) <- gaps(masks(seq)["AGAPS"])
    unique_letters <- uniqueLetters(seq)
    if (any(unique_letters != "N"))
        stop("assembly gaps contain more than just Ns")
  }

  ## A message will be printed each time a sequence is removed
  ## from the cache:
  options(verbose=TRUE)

  for (seqname in seqnames(Mmulatta)) {
    cat("Checking sequence", seqname, "... ")
    seq <- Mmulatta[[seqname]]
    checkOnlyNsInGaps(seq)
    cat("OK\n")
  }
}

## See the GenomeSearching vignette in the BSgenome software
## package for some examples of genome-wide motif searching using
## Biostrings and the BSgenome data packages:
if (interactive())
    vignette("GenomeSearching", package="BSgenome")
}

\keyword{package}
\keyword{data}