\name{base.freq}
\alias{base.freq}
+\alias{GC.content}
\alias{Ftab}
\title{Base frequencies from DNA Sequences}
\description{
the four DNA bases (adenine, cytosine, guanine, and thymidine) from a
sample of sequences.
+ \code{GC.content} computes the proportion of G+C (using the previous
+ function). All missing or unknown sites are ignored.
+
\code{Ftab} computes the contingency table with the absolute
frequencies of the DNA bases from a pair of sequences.
}
\usage{
-base.freq(x, freq = FALSE)
+base.freq(x, freq = FALSE, all = FALSE)
+GC.content(x)
Ftab(x, y = NULL)
}
\arguments{
\item{y}{a vector with a single DNA sequence.}
\item{freq}{a logical specifying whether to return the proportions
(the default) or the absolute frequencies (counts).}
+ \item{all}{a logical; by default only the counts of A, C, G, and T are
+ returned. If \code{all = TRUE}, all counts of bases, ambiguous codes,
+ missing data, and alignment gaps are returned.}
}
\details{
The base frequencies are computed over all sequences in the
- sample. All missing or unknown sites are discarded from the
- computations.
+ sample.
For \code{Ftab}, if the argument \code{y} is given then both \code{x}
and \code{y} are coerced as vectors and must be of equal length. If
the two first sequences are used.
}
\value{
- A numeric vector with names \code{c("a", "c", "g", "t")}, or a four by
- four matrix with similar dimnames.
+ A numeric vector with names \code{c("a", "c", "g", "t")} (and possibly
+ \code{"r", "m", ...}, a single numeric value, or a four by four matrix
+ with similar dimnames.
}
\author{Emmanuel Paradis}
\seealso{
- \code{\link{GC.content}}, \code{\link{seg.sites}},
- \code{\link{nuc.div}}, \code{\link{DNAbin}}
+ \code{\link{seg.sites}}, \code{\link[pegas]{nuc.div}},
+ \code{\link{DNAbin}}
}
\examples{
data(woodmouse)
base.freq(woodmouse)
base.freq(woodmouse, TRUE)
+base.freq(woodmouse, TRUE, TRUE)
+GC.content(woodmouse)
Ftab(woodmouse)
Ftab(woodmouse[1, ], woodmouse[2, ]) # same than above
Ftab(woodmouse[14:15, ]) # between the last two