From ec11283d0bb9ac35f712d56176ebdc8e649ccdc9 Mon Sep 17 00:00:00 2001 From: Petar Petrov Date: Fri, 22 May 2020 23:39:23 +0700 Subject: academic/muscle: Update script and added manual page. Signed-off-by: Willy Sudiarto Raharjo --- academic/muscle/README | 30 +++++++-- academic/muscle/muscle.1 | 135 ++++++++++++++++++++++++++++++++++++++ academic/muscle/muscle.SlackBuild | 16 ++++- academic/muscle/muscle.info | 8 ++- academic/muscle/slack-desc | 4 +- 5 files changed, 183 insertions(+), 10 deletions(-) create mode 100644 academic/muscle/muscle.1 (limited to 'academic') diff --git a/academic/muscle/README b/academic/muscle/README index 4db82130b5..2a8b2c538d 100644 --- a/academic/muscle/README +++ b/academic/muscle/README @@ -3,7 +3,29 @@ nucleotide sequences. A range of options is provided that give you the choice of optimizing accuracy, speed, or some compromise between the two. -For details and citation: -Edgar, R.C. (2004) MUSCLE: multiple sequence alignment with high -accuracy and high throughput. Nucleic Acids Res. 32(5):1792-1797. -doi:10.1093/nar/gkh340 +Fast, accurate and easy to use +MUSCLE is one of the best-performing multiple alignment programs +according to published benchmark tests, with accuracy and speed that +are consistently better than CLUSTALW. MUSCLE can align hundreds of +sequences in seconds. Most users learn everything they need to know +about MUSCLE in a few minutes—only a handful of command-line options +are needed to perform common alignment tasks. + +NOTE about the "-stable" option no longer being supported: +The "-stable" option had a bug, which sometimes resulted in incorrect +alignments to be produced. The author has created a python script to +be used as a workaround. The SlackBuild includes it and its usage is: + + python muscle-stable.py input.fasta aligned.fasta > stable.fasta + +Papers +There are two papers. The first (NAR) introduced the algorithm, and is +the primary citation if you use the program. The second (in BMC Bio- +informatics) gives more technical details, including descriptions of +non-default options. + +Edgar, R.C. (2004) MUSCLE: multiple sequence alignment with high +accuracy and high throughput. Nucleic Acids Res. 32(5):1792-1797 + +Edgar, R.C. (2004) MUSCLE: a multiple sequence alignment method with +reduced time and space complexity BMC Bioinformatics, (5) 113 diff --git a/academic/muscle/muscle.1 b/academic/muscle/muscle.1 new file mode 100644 index 0000000000..057c81da47 --- /dev/null +++ b/academic/muscle/muscle.1 @@ -0,0 +1,135 @@ +.\" Title: MUSCLE +.\" Author: Robert Elgar +.\" Generator: DocBook XSL Stylesheets v1.73.2 +.\" Date: 02/06/2008 +.\" Manual: Muscle Manual +.\" Source: muscle 3.7 +.\" +.TH "MUSCLE" "1" "02/06/2008" "muscle 3.7" "Muscle Manual" +.\" disable hyphenation +.nh +.\" disable justification (adjust text to left margin only) +.ad l +.SH "NAME" +muscle - Multiple Protein Sequence Alignment +.SH "SYNOPSIS" +.HP 7 +\fBmuscle\fR \fB\-in\ \fR\fB\fIinput\ file\ (fasta)\fR\fR [\fB\-out\ \fR\fB\fIoutput\ file\ (default\ fasta)\fR\fR] [\fB\-diags\fR] [\fB\-log\ \fR\fB\fIlog\ file\fR\fR] [\fB\-maxiters\ \fR\fB\fIn\fR\fR] [\fB\-maxhours\ \fR\fB\fIn\fR\fR] [\fB\-maxmb\ \fR\fB\fIm\fR\fR] [\fB\-html\fR] [\fB\-msf\fR] [\fB\-clw\fR] [\fB\-clwstrict\fR] [\fB\-log[a]\ \fR\fB\fIlogfile\fR\fR] [\fB\-quiet\fR] [\fB\-stable\fR] [\fB\-group\fR] [\fB\-version\fR] +.SH "DESCRIPTION" +.PP +This manual page documents briefly the +\fBmuscle\fR +command\. +.PP +\fBmuscle\fR +aligns protein sequences and is considered superior and faster than Clustal\ W\. +.SH "OPTIONS" +.PP +\fB\-in \fR\fB\fIinput file\fR\fR +.RS 4 +Path to FASTA formatted input file +.RE +.PP +\fB\-out \fR\fB\fIoutput file\fR\fR +.RS 4 +Path to output file, FASTA formatted by default +.RE +.PP +\fB\-diags\fR +.RS 4 +Find diagonals (faster for similar sequences) +.RE +.PP +\fB\-maxiters \fR\fB\fIn\fR\fR +.RS 4 +Maximum number of iterations (integer, default 16) +.RE +.PP +\fB\-maxhours \fR\fB\fIn\fR\fR +.RS 4 +Maximum time to iterate in hours (default no limit) +.RE +.PP +\fB\-maxmb \fR\fB\fIm\fR\fR +.RS 4 +Maximum memory to allocate in Mb (default 80% of RAM) +.RE +.PP +\fB\-html\fR +.RS 4 +Write output in HTML format (default FASTA) +.RE +.PP +\fB\-msf\fR +.RS 4 +Write output in MSF format (default FASTA) +.RE +.PP +\fB\-clw\fR +.RS 4 +Write output in Clustal\ W format (default FASTA) +.RE +.PP +\fB\-clwstrict\fR +.RS 4 +As \-clw, with \'CLUSTAL W (1\.81)\' header +.RE +.PP +\fB\-log[a] \fR\fB\fIlogfile\fR\fR +.RS 4 +Log to file (append if \-loga, overwrite if \-log) +.RE +.PP +\fB\-quiet\fR +.RS 4 +Do not write progress messages to stderr +.RE +.PP +\fB\-stable\fR +.RS 4 +Output sequences in input order (default is \-group) +.RE +.PP +\fB\-group\fR +.RS 4 +Group sequences by similarity (this is the default) +.RE +.PP +\fB\-version\fR +.RS 4 +Display version information and exit +.RE +.SH "SEE ALSO" +.PP + +\fBclustalw\fR(1), +\fBseaview\fR(1), +\fBt_coffee\fR(1)\. +.SH "AUTHORS" +.PP +\fBRobert Elgar\fR +.sp -1n +.IP "" 4 +Wrote Muscle\. +.PP +\fBSteffen Moeller\fR <\&moeller@debian\.org\&> +.sp -1n +.IP "" 4 +Wrote this manpage\. +.PP +\fBCharles Plessy\fR <\&charles\-debian\-nospam@plessy\.org\&> +.sp -1n +.IP "" 4 +Updated this manpage\. +.SH "COPYRIGHT" +Copyright \(co 2003, 2004 Steffen Moeller (manpage) +.br +Copyright \(co 2007, 2008 Charles Plessy (manpage) +.br +.PP +Muscle is in the public domain, and therefore not subjected to copyright\. +.PP +This manual page was written by Steffen Moeller moeller@debian\.org for the +Debian(TM) +system (but may be used by others)\. Permission is granted to copy, distribute and/or modify this document as if it were in public domain\. +.sp diff --git a/academic/muscle/muscle.SlackBuild b/academic/muscle/muscle.SlackBuild index 9e69c5b702..2258892211 100644 --- a/academic/muscle/muscle.SlackBuild +++ b/academic/muscle/muscle.SlackBuild @@ -2,7 +2,7 @@ # Slackware build script for muscle -# Copyright 2011-2019 Petar Petrov slackalaxy@gmail.com +# Copyright 2011-2020 Petar Petrov slackalaxy@gmail.com # All rights reserved. # # Redistribution and use of this script, with or without modification, is @@ -24,9 +24,11 @@ PRGNAM=muscle VERSION=${VERSION:-3.8.1551} -BUILD=${BUILD:-1} +BUILD=${BUILD:-2} TAG=${TAG:-_SBo} +MANUAL=muscle_userguide3.8.pdf + if [ -z "$ARCH" ]; then case "$( uname -m )" in i?86) ARCH=i586 ;; @@ -63,6 +65,7 @@ rm -rf ${PRGNAM}-${VERSION} mkdir -p ${PRGNAM}-${VERSION} cd ${PRGNAM}-${VERSION} tar xvf $CWD/${PRGNAM}_src_${VERSION}.tar.gz +tar xvf $CWD/stable.tar.gz chown -R root:root . find -L . \ @@ -78,12 +81,21 @@ CFLAGS="$SLKCFLAGS" \ make install -D -m755 $PRGNAM $PKG/usr/bin/$PRGNAM +install -D -m755 stable.py $PKG/usr/bin/$PRGNAM-stable.py + +# Thanks to Debian for the man page +mkdir -p $PKG/usr/man/man1 +cp $CWD/$PRGNAM.1 $PKG/usr/man/man1/$PRGNAM.1 find $PKG -print0 | xargs -0 file | grep -e "executable" -e "shared object" | grep ELF \ | cut -f 1 -d : | xargs strip --strip-unneeded 2> /dev/null || true +find $PKG/usr/man -type f -exec gzip -9 {} \; +for i in $( find $PKG/usr/man -type l ) ; do ln -s $( readlink $i ).gz $i.gz ; rm $i ; done + mkdir -p $PKG/usr/doc/$PRGNAM-$VERSION cat $CWD/$PRGNAM.SlackBuild > $PKG/usr/doc/$PRGNAM-$VERSION/$PRGNAM.SlackBuild +cat $CWD/$MANUAL > $PKG/usr/doc/$PRGNAM-$VERSION/$MANUAL cat $CWD/References > $PKG/usr/doc/$PRGNAM-$VERSION/References mkdir -p $PKG/install diff --git a/academic/muscle/muscle.info b/academic/muscle/muscle.info index e7671cd1bc..e747bd6443 100644 --- a/academic/muscle/muscle.info +++ b/academic/muscle/muscle.info @@ -1,8 +1,12 @@ PRGNAM="muscle" VERSION="3.8.1551" HOMEPAGE="http://www.drive5.com/muscle/" -DOWNLOAD="http://www.drive5.com/muscle/muscle_src_3.8.1551.tar.gz" -MD5SUM="1b7c9661f275a82d3cf708f923736bf8" +DOWNLOAD="http://www.drive5.com/muscle/muscle_src_3.8.1551.tar.gz \ + http://www.drive5.com/muscle/stable.tar.gz \ + http://www.drive5.com/muscle/muscle_userguide3.8.pdf" +MD5SUM="1b7c9661f275a82d3cf708f923736bf8 \ + fceeab190ff13576bfd681a601e7859b \ + 58bb1b7989cf6f2c197dd46552759a40" DOWNLOAD_x86_64="" MD5SUM_x86_64="" REQUIRES="" diff --git a/academic/muscle/slack-desc b/academic/muscle/slack-desc index 5e4e7da441..d3d95c0c28 100644 --- a/academic/muscle/slack-desc +++ b/academic/muscle/slack-desc @@ -13,7 +13,7 @@ muscle: or nucleotide sequences. A range of options is provided that give muscle: you the choice of optimizing accuracy, speed, or some compromise muscle: between the two. muscle: -muscle: Home: http://www.drive5.com/muscle/ -muscle: References: /usr/doc/muscle-3.8.31/References +muscle: http://www.drive5.com/muscle/ +muscle: http://www.drive5.com/muscle/stable.html muscle: muscle: -- cgit v1.2.3