\name{geneHuman}
\Rdversion{1.1}
\alias{geneHuman}
\docType{data}
\title{UCSC Gene Predictions for hg18}
\description{
  
Gene coordinates and annotations for H. sapiens from UCSC. Coordinates are
relative to the hg18 build and are in nucleotides from the 5' end of the
positive \code{"+"} strand. Each \dQuote{gene}, or row in the dataset,
corresponds to a unique combination of transcript (TSS, TES and exons)
and coding sequence (start and end).

}

\usage{data(geneHuman)}
\format{
  A data frame with 56722 observations on the following 12
  variables.
  \describe{
    \item{\code{name}}{The name of the gene.}
    \item{\code{chrom}}{The name of the chromosome the gene is located on.}
    \item{\code{strand}}{The strand the gene is coded on, \code{"+"}, or 
         \code{"-"}.}
    \item{\code{txStart}}{Transcription start site.}
    \item{\code{txEnd}}{Transcription stop site.}
    \item{\code{cdsStart}}{Start position of the coding sequence.}
    \item{\code{cdsEnd}}{End position of the coding sequence.}
    \item{\code{exonCount}}{The number of exons.}
    \item{\code{exonStarts}}{A comma separated list of the exon start positions.}
    \item{\code{exonEnds}}{A comma separated list of exon stop positions.}
    \item{\code{proteinID}}{An ID for the protein produced, missing values
      are coded as NA}.
    \item{\code{alignID}}{Unique identifier of each gene and RNA
      alignment pair, apparently redundant with \code{name}.}
  }
}
\details{
For genes coded on the negative strand the \code{txStart} is really the end,
and similarly for the coding regions.
}

\source{
This table was taken directly from the knownGene table in the UCSC
database for hg18, see \url{http://genome.ucsc.edu/cgi-bin/hgTables} and
Hsu F, Kent WJ, Clawson H, Kuhn RM, Diekhans M, Haussler D. The UCSC
Known Genes. Bioinformatics. 2006 May 1;22(9):1036-46.
} 
\examples{
data(geneHuman)
str(geneHuman)
transcripts(geneHuman)
}
\keyword{datasets}