X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=man%2Fbase.freq.Rd;h=8832fccf71001779e0290f7ae786d52d0caa6060;hb=HEAD;hp=dcb564e6329f6263eb9d1ca4f69f7708b48c7e46;hpb=21eb56120c84786502f24ff9c27b39d5badfe1f7;p=ape.git diff --git a/man/base.freq.Rd b/man/base.freq.Rd index dcb564e..8832fcc 100644 --- a/man/base.freq.Rd +++ b/man/base.freq.Rd @@ -1,32 +1,62 @@ \name{base.freq} \alias{base.freq} +\alias{GC.content} +\alias{Ftab} \title{Base frequencies from DNA Sequences} +\description{ + \code{base.freq} computes the frequencies (absolute or relative) of + 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{x}{a vector, a matrix, or a list which contains the DNA sequences.} + \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).} -} -\description{ - This function computes the relative frequencies (i.e. proportions) of - the four DNA bases (adenine, cytosine, guanine, and thymidine) from a - sample of sequences. + \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 + \code{y} is not given, \code{x} must be a matrix or a list and only + the two first sequences are used. } \value{ - A numeric vector storing the relative frequencies with names - \code{c("a", "c", "g", "t")}. + 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 } \keyword{univar} +\keyword{manip}