a bunch of new stuff (see ChangeLog)

[ape.git] / man / clustal.Rd

diff --git a/man/clustal.Rd b/man/clustal.Rd
new file mode 100644 (file)
index 0000000..8bb5cfb
--- /dev/null
+++ b/man/clustal.Rd
@@ -0,0 +1,86 @@
+\name{clustal}
+\alias{clustal}
+\alias{muscle}
+\alias{tcoffee}
+\title{Multiple Sequence Alignment with External Applications}
+\description{
+  These functions call their respective program from \R to align a set of
+  nucleotide sequences of class \code{"DNAbin"}.
+}
+\usage{
+clustal(x, pw.gapopen = 10, pw.gapext = 0.1,
+        gapopen = 10, gapext = 0.2, exec = NULL,
+        MoreArgs = "", quiet = TRUE)
+muscle(x, exec = "muscle", MoreArgs = "", quiet = TRUE)
+tcoffee(x, exec = "t_coffee", MoreArgs = "", quiet = TRUE)
+}
+\arguments{
+  \item{x}{an object of class \code{"DNAbin"}.}
+  \item{pw.gapopen, pw.gapext}{gap opening and gap extension penalties
+    used by Clustal during pairwise alignments.}
+  \item{gapopen, gapext}{idem for global alignment.}
+  \item{exec}{a character string giving the name of the program, with
+    its path if necessary. \code{clustal} tries to guess it depending on
+    the operating system (see details).}
+  \item{MoreArgs}{a character string giving additional options.}
+  \item{quiet}{a logical: the default is to not print on \R's console the
+    messages from the external program.}
+}
+\details{
+  \code{clustal} tries to guess the name of the executable program
+  depending on the operating system. Specifically, the followings are
+  used: ``clustalw'' under Linux, ``clustalw2'' under MacOS, or
+  ``C:/Program Files/ClustalW2/clustalw2'' under Windows.
+
+  The calculations are done in a temporary directory which is deleted
+  when \R is quit. So it is possible to find the files created by the
+  last call in the directory printed by \code{tempdir()}.
+
+  When called without arguments (i.e., \code{clustal()}, \dots), the
+  function prints the options of the program which may be passed to
+  \code{MoreArgs}.
+}
+\value{
+  an object of class \code{"DNAbin"} with the aligned sequences.
+}
+\references{
+  Chenna, R., Sugawara, H., Koike, T., Lopez, R., Gibson, T. J.,
+  Higgins, D. G. and Thompson, J. D. (2003) Multiple sequence alignment
+  with the Clustal series of programs. \emph{Nucleic Acids Research}
+  \bold{31}, 3497--3500.
+
+  \url{http://www.clustal.org/}
+
+  Edgar, R. C. (2004) MUSCLE: Multiple sequence alignment with high
+  accuracy and high throughput. \emph{Nucleic Acids Research},
+  \bold{32}, 1792--1797.
+
+  \url{http://www.drive5.com/muscle/muscle_userguide3.8.html}
+
+  Notredame, C., Higgins, D. and Heringa, J. (2000) T-Coffee: A novel
+  method for multiple sequence alignments. \emph{Journal of Molecular
+  Biology}, \bold{302}, 205--217.
+
+  \url{http://www.tcoffee.org/Documentation/t_coffee/t_coffee_technical.htm}
+}
+\author{Emmanuel Paradis}
+\seealso{
+  \code{\link{image.DNAbin}}, \code{\link{del.gaps}}
+
+  The package \pkg{phyloch} which has similar functions for the MAFFT
+  and Prank.
+}
+\examples{
+\dontrun{
+### display the options:
+clustal()
+muscle()
+tcoffee()
+
+data(woodmouse)
+### open gaps more easily:
+clustal(woodmouse, pw.gapopen = 1, pw.gapext = 1)
+### T-Coffee requires negative values (quite slow; muscle is much faster):
+tcoffee(woodmouse,  MoreArgs = "-gapopen=-10 -gapext=-2")
+}}
+\keyword{manip}