@@ -83,7 +83,7 @@

   U. Bodenhofer, E. Bonatesta, C. Horejs-Kainrath, and S. Hochreiter

   (2015). msa: an R package for multiple sequence alignment. 

   \emph{Bioinformatics} \bold{31}(24):3997-3999. DOI:

-  \href{http://dx.doi.org/10.1093/bioinformatics/btv494}{10.1093/bioinformatics/btv494}.

+  \doi{10.1093/bioinformatics/btv494}.

   \url{http://www.clustal.org/omega/README}

@@ -92,7 +92,7 @@

   and Higgins, D. G. (2011) Fast, scalable generation of high-quality

   protein multiple sequence alignments using Clustal Omega.

   \emph{Mol. Syst. Biol.} \bold{7}:539. DOI:

-  \href{http://dx.doi.org/10.1038/msb.2011.75}{10.1038/msb.2011.75}.

+  \doi{10.1038/msb.2011.75}.

 }

 \seealso{\code{\link{msa}}, \code{\linkS4class{MsaAAMultipleAlignment}},

   \code{\linkS4class{MsaDNAMultipleAlignment}},

@@ -82,7 +82,7 @@

   U. Bodenhofer, E. Bonatesta, C. Horejs-Kainrath, and S. Hochreiter

   (2015). msa: an R package for multiple sequence alignment. 

-  \emph{Bioinformatics} (accepted). DOI:

+  \emph{Bioinformatics} \bold{31}(24):3997-3999. DOI:

   \href{http://dx.doi.org/10.1093/bioinformatics/btv494}{10.1093/bioinformatics/btv494}.

   \url{http://www.clustal.org/omega/README}

@@ -27,12 +27,11 @@

   \item{maxiters}{maximum number of iterations; the default value is 0

     (no limitation). In the original ClustalOmega implementation, this

     parameter is called \code{iterations}.}

-  \item{substitutionMatrix}{substitution matrix for scoring matches and

-    mismatches; can be a real matrix, a file name, or the name of a

-    built-in substitution matrix. In the latter case, the choices

+  \item{substitutionMatrix}{name of substitution matrix for scoring matches and

+    mismatches; can be one of the choices

     \code{"BLOSUM30"}, \code{"BLOSUM40"}, \code{"BLOSUM50"},

-    \code{"BLOSUM65"}, \code{"BLOSUM80"}, and \code{"Gonnet"} are

-    supported.  This parameter is a new feature - the original ClustalOmega

+    \code{"BLOSUM65"}, \code{"BLOSUM80"}, and \code{"Gonnet"}.

+    This parameter is a new feature - the original ClustalOmega

     implementation does not allow for using a custom substitution matrix.}

   \item{type}{type of the input sequences \code{inputSeqs};

     see \code{\link{msa}}.}

@@ -59,6 +58,10 @@

   specific to ClustalOmega can be passed to ClustalOmega via additional

   arguments (see argument \code{help} above).

+  Since ClustalOmega only allows for using built-in amino acid

+  substitution matrices, it is hardly useful for multiple alignments

+  of nucleotide sequences.

+

   For a note on the order of output sequences and direct reading from

   FASTA files, see \code{\link{msa}}.

 }

@@ -76,6 +79,11 @@

 }

 \references{

   \url{http://www.bioinf.jku.at/software/msa}

+  

+  U. Bodenhofer, E. Bonatesta, C. Horejs-Kainrath, and S. Hochreiter

+  (2015). msa: an R package for multiple sequence alignment. 

+  \emph{Bioinformatics} (accepted). DOI:

+  \href{http://dx.doi.org/10.1093/bioinformatics/btv494}{10.1093/bioinformatics/btv494}.

   \url{http://www.clustal.org/omega/README}

@@ -9,38 +9,36 @@

     msaClustalOmega(inputSeqs, cluster="default",

                     gapOpening="default", gapExtension="default",

                     maxiters="default",  substitutionMatrix="default",

-                    type="default", verbose=FALSE, help=FALSE,

-                    ...) 

+                    type="default", order=c("aligned", "input"),

+                    verbose=FALSE, help=FALSE, ...) 

 }

 \arguments{

   \item{inputSeqs}{input sequences; see \code{\link{msa}}.

     In the original ClustalOmega implementation, this

-    parameter is called \code{-infile}.}

+    parameter is called \code{infile}.}

   \item{cluster}{The cluster size which should be used. The default is 100.  

     In the original ClustalOmega implementation, this parameter is called 

-    \code{--cluster-size}.}

-  \item{gapOpening}{gap opening penalty; the default value is -6.0.

-    In order to standardize interfaces,

-    all algorithms consistently use negative values for the gap open

-    penalty. This parameter is a new feature - the original ClustalOmega

-    implementation does not allow for customizing gap penalties.}

-  \item{gapExtension}{gap extension penalty; the default value is -1.0.

-    In order to standardize interfaces,

-    all algorithms consistently use negative values for the gap open

-    penalty. This parameter is a new feature - the original ClustalOmega

-    implementation does not allow for customizing gap penalties.}

+    \code{cluster-size}.}

+  \item{gapOpening,gapExtension}{ClustalOmega currently does

+    not allow to adjust gap penalties; these arguments are only for

+    future extensions and consistency with the other algorithms

+    and \code{\link{msa}}. However, setting these parameters to values

+    other than \code{"default"} will result in a warning.}

   \item{maxiters}{maximum number of iterations; the default value is 0

     (no limitation). In the original ClustalOmega implementation, this

-    parameter is called \code{--iterations}.}

+    parameter is called \code{iterations}.}

   \item{substitutionMatrix}{substitution matrix for scoring matches and

     mismatches; can be a real matrix, a file name, or the name of a

     built-in substitution matrix. In the latter case, the choices

-    \code{"blosum30"}, \code{"blosum40"}, \code{"blosum50"},

-    \code{"blosum65"}, \code{"blosum80"}, and \code{"gonnet"} are

+    \code{"BLOSUM30"}, \code{"BLOSUM40"}, \code{"BLOSUM50"},

+    \code{"BLOSUM65"}, \code{"BLOSUM80"}, and \code{"Gonnet"} are

     supported.  This parameter is a new feature - the original ClustalOmega

     implementation does not allow for using a custom substitution matrix.}

   \item{type}{type of the input sequences \code{inputSeqs};

     see \code{\link{msa}}.}

+  \item{order}{how the sequences should be ordered in the output object

+    (see \code{\link{msa}}); in the original ClustalW implementation, this

+    parameter is called \code{output-order}.}

   \item{verbose}{if \code{TRUE}, the algorithm displays detailed

     information and progress messages.}

   \item{help}{if \code{TRUE}, information about algorithm-specific

@@ -102,8 +100,7 @@ mySeqs <- readAAStringSet(filepath)

 msaClustalOmega(mySeqs)

 ## call msaClustalOmega with custom parameters

-msaClustalOmega(mySeqs, gapOpening=-6, gapExtension=-1, auto=FALSE,

-                cluster=120, dealign=FALSE, useKimura=FALSE,

-                verbose=FALSE)

+msaClustalOmega(mySeqs, auto=FALSE, cluster=120, dealign=FALSE,

+                useKimura=FALSE, order="input", verbose=FALSE)

 }

 \keyword{manip}

new file mode 100644

@@ -0,0 +1,109 @@

+\name{msaClustalOmega}

+\alias{msaClustalOmega}

+\title{Multiple Sequence Alignment with ClustalOmega}

+\description{

+  This function calls the multiple sequence alignment

+  algorithm ClustalOmega.

+}

+\usage{

+    msaClustalOmega(inputSeqs, cluster="default",

+                    gapOpening="default", gapExtension="default",

+                    maxiters="default",  substitutionMatrix="default",

+                    type="default", verbose=FALSE, help=FALSE,

+                    ...) 

+}

+\arguments{

+  \item{inputSeqs}{input sequences; see \code{\link{msa}}.

+    In the original ClustalOmega implementation, this

+    parameter is called \code{-infile}.}

+  \item{cluster}{The cluster size which should be used. The default is 100.  

+    In the original ClustalOmega implementation, this parameter is called 

+    \code{--cluster-size}.}

+  \item{gapOpening}{gap opening penalty; the default value is -6.0.

+    In order to standardize interfaces,

+    all algorithms consistently use negative values for the gap open

+    penalty. This parameter is a new feature - the original ClustalOmega

+    implementation does not allow for customizing gap penalties.}

+  \item{gapExtension}{gap extension penalty; the default value is -1.0.

+    In order to standardize interfaces,

+    all algorithms consistently use negative values for the gap open

+    penalty. This parameter is a new feature - the original ClustalOmega

+    implementation does not allow for customizing gap penalties.}

+  \item{maxiters}{maximum number of iterations; the default value is 0

+    (no limitation). In the original ClustalOmega implementation, this

+    parameter is called \code{--iterations}.}

+  \item{substitutionMatrix}{substitution matrix for scoring matches and

+    mismatches; can be a real matrix, a file name, or the name of a

+    built-in substitution matrix. In the latter case, the choices

+    \code{"blosum30"}, \code{"blosum40"}, \code{"blosum50"},

+    \code{"blosum65"}, \code{"blosum80"}, and \code{"gonnet"} are

+    supported.  This parameter is a new feature - the original ClustalOmega

+    implementation does not allow for using a custom substitution matrix.}

+  \item{type}{type of the input sequences \code{inputSeqs};

+    see \code{\link{msa}}.}

+  \item{verbose}{if \code{TRUE}, the algorithm displays detailed

+    information and progress messages.}

+  \item{help}{if \code{TRUE}, information about algorithm-specific

+    parameters is displayed. In this case, no multiple sequence

+    alignment is performed and the function quits after displaying

+    the additional help information.}

+  \item{...}{further parameters specific to ClustalOmega;

+    An overview of parameters that are available in this interface

+    is shown when calling \code{msaClustalOmega} with \code{help=TRUE}.

+    For more details, see also the documentation of ClustalOmega.}

+}

+\details{This is a function providing the ClustalOmega multiple alignment

+  algorithm as an R function. It can be used for various types of

+  sequence data (see \code{inputSeqs} argument above). Parameters that

+  are common to all multiple sequences alignments provided by the

+  \pkg{msa} package are explicitly provided by the function and named

+  in the same for all algorithms. Most other parameters that are

+  specific to ClustalOmega can be passed to ClustalOmega via additional

+  arguments (see argument \code{help} above).

+

+  For a note on the order of output sequences and direct reading from

+  FASTA files, see \code{\link{msa}}.

+}

+\value{

+   Depending on the type of sequences for which it was called,

+   \code{msaClustalOmega} returns a

+   \code{\linkS4class{MsaAAMultipleAlignment}}, 

+   \code{\linkS4class{MsaDNAMultipleAlignment}}, or

+   \code{\linkS4class{MsaRNAMultipleAlignment}} object.

+   If called with \code{help=TRUE}, \code{msaClustalOmega} returns

+   an invisible \code{NULL}.

+}

+\author{Enrico Bonatesta and Christoph Horejs-Kainrath

+  <msa@bioinf.jku.at>

+}

+\references{

+  \url{http://www.bioinf.jku.at/software/msa}

+

+  \url{http://www.clustal.org/omega/README}

+  

+  Sievers, F., Wilm, A., Dineen, D., Gibson, T. J., Karplus, K., Li, W.,

+  Lopez, R., McWilliam, H., Remmert, M., Soeding, J., Thompson, J. D.,

+  and Higgins, D. G. (2011) Fast, scalable generation of high-quality

+  protein multiple sequence alignments using Clustal Omega.

+  \emph{Mol. Syst. Biol.} \bold{7}:539. DOI:

+  \href{http://dx.doi.org/10.1038/msb.2011.75}{10.1038/msb.2011.75}.

+}

+\seealso{\code{\link{msa}}, \code{\linkS4class{MsaAAMultipleAlignment}},

+  \code{\linkS4class{MsaDNAMultipleAlignment}},

+  \code{\linkS4class{MsaRNAMultipleAlignment}},

+  \code{\linkS4class{MsaMetaData}}

+}

+\examples{

+## read sequences

+filepath <- system.file("examples", "exampleAA.fasta", package="msa")

+mySeqs <- readAAStringSet(filepath)

+

+## call msaClustalOmega with default values

+msaClustalOmega(mySeqs)

+

+## call msaClustalOmega with custom parameters

+msaClustalOmega(mySeqs, gapOpening=-6, gapExtension=-1, auto=FALSE,

+                cluster=120, dealign=FALSE, useKimura=FALSE,

+                verbose=FALSE)

+}

+\keyword{manip}