From: pvtroshin Date: Tue, 21 Jun 2011 10:57:18 +0000 (+0000) Subject: New Mafft binaries for 64 bit linux system X-Git-Url: http://source.jalview.org/gitweb/?p=jabaws.git;a=commitdiff_plain;h=a65c48a75f164b6ad0e577bd33168904328ce625 New Mafft binaries for 64 bit linux system git-svn-id: link to svn.lifesci.dundee.ac.uk/svn/barton/ptroshin/JABA2@4288 e3abac25-378b-4346-85de-24260fe3988d --- diff --git a/binaries/linuxAMD64/mafft/contrafoldwrap b/binaries/linuxAMD64/mafft/contrafoldwrap index 39bf811..d08b233 100644 Binary files a/binaries/linuxAMD64/mafft/contrafoldwrap and b/binaries/linuxAMD64/mafft/contrafoldwrap differ diff --git a/binaries/linuxAMD64/mafft/countlen b/binaries/linuxAMD64/mafft/countlen index dcfe8a8..6813415 100644 Binary files a/binaries/linuxAMD64/mafft/countlen and b/binaries/linuxAMD64/mafft/countlen differ diff --git a/binaries/linuxAMD64/mafft/disttbfast b/binaries/linuxAMD64/mafft/disttbfast index 33d25a3..f874945 100644 Binary files a/binaries/linuxAMD64/mafft/disttbfast and b/binaries/linuxAMD64/mafft/disttbfast differ diff --git a/binaries/linuxAMD64/mafft/dndblast b/binaries/linuxAMD64/mafft/dndblast index 2427b3a..ce94114 100644 Binary files a/binaries/linuxAMD64/mafft/dndblast and b/binaries/linuxAMD64/mafft/dndblast differ diff --git a/binaries/linuxAMD64/mafft/dndfast7 b/binaries/linuxAMD64/mafft/dndfast7 index d632041..0d5ec67 100644 Binary files a/binaries/linuxAMD64/mafft/dndfast7 and b/binaries/linuxAMD64/mafft/dndfast7 differ diff --git a/binaries/linuxAMD64/mafft/dndpre b/binaries/linuxAMD64/mafft/dndpre index 119bbe9..3490c6d 100644 Binary files a/binaries/linuxAMD64/mafft/dndpre and b/binaries/linuxAMD64/mafft/dndpre differ diff --git a/binaries/linuxAMD64/mafft/dndpre2 b/binaries/linuxAMD64/mafft/dndpre2 index 8cc8e67..f75796d 100644 Binary files a/binaries/linuxAMD64/mafft/dndpre2 and b/binaries/linuxAMD64/mafft/dndpre2 differ diff --git a/binaries/linuxAMD64/mafft/dvtditr b/binaries/linuxAMD64/mafft/dvtditr index 90036dc..2c138ab 100644 Binary files a/binaries/linuxAMD64/mafft/dvtditr and b/binaries/linuxAMD64/mafft/dvtditr differ diff --git a/binaries/linuxAMD64/mafft/f2cl b/binaries/linuxAMD64/mafft/f2cl index 7509d1e..6a76dcc 100644 Binary files a/binaries/linuxAMD64/mafft/f2cl and b/binaries/linuxAMD64/mafft/f2cl differ diff --git a/binaries/linuxAMD64/mafft/getlag b/binaries/linuxAMD64/mafft/getlag index 645ff71..5a8a5fe 100644 Binary files a/binaries/linuxAMD64/mafft/getlag and b/binaries/linuxAMD64/mafft/getlag differ diff --git a/binaries/linuxAMD64/mafft/mafft b/binaries/linuxAMD64/mafft/mafft new file mode 100644 index 0000000..16b6660 --- /dev/null +++ b/binaries/linuxAMD64/mafft/mafft @@ -0,0 +1,1658 @@ +#! /bin/sh + + +er=0; +myself=`dirname "$0"`/`basename "$0"`; export myself +version="v6.857b (2011/05/30)"; export version +LANG=C; export LANG +os=`uname` +progname=`basename "$0"` +if [ `echo $os | grep -i cygwin` ]; then + os="cygwin" +elif [ `echo $os | grep -i darwin` ]; then + os="darwin" +elif [ `echo $os | grep -i sunos` ]; then + os="sunos" +elif [ `echo $os | grep -i linux` ]; then + os="linux" +else + os="unix" +fi +export os + +if [ "$MAFFT_BINARIES" ]; then + prefix="$MAFFT_BINARIES" +else + prefix=/usr/libexec/mafft +fi +export prefix + +if [ $# -gt 0 ]; then + if [ "$1" = "--man" ]; then + man "$prefix/mafft.1" + exit 0; + fi +fi + +if [ ! -x "$prefix/tbfast" ]; then + echo "" 1>&2 + echo "correctly installed?" 1>&2 + echo "mafft binaries have to be installed in \$MAFFT_BINARIES" 1>&2 + echo "or the $prefix directory". 1>&2 + echo "" 1>&2 + exit 1 + er=1 +fi + +defaultiterate=0 +defaultcycle=2 +defaultgop="1.53" +#defaultaof="0.123" +defaultaof="0.000" +defaultlaof="0.100" +defaultlgop="-2.00" +defaultfft=1 +defaultrough=0 +defaultdistance="sixtuples" +#defaultdistance="local" +defaultweighti="2.7" +defaultweightr="0.0" +defaultweightm="1.0" +defaultmccaskill=0 +defaultcontrafold=0 +defaultalgopt=" " +defaultalgoptit=" " +defaultsbstmodel=" -b 62 " +defaultfmodel=" " +defaultkappa=" " +if [ $progname = "xinsi" -o $progname = "mafft-xinsi" ]; then + defaultfft=1 + defaultcycle=1 + defaultiterate=1000 + defaultdistance="scarna" + defaultweighti="3.2" + defaultweightr="8.0" + defaultweightm="2.0" + defaultmccaskill=1 + defaultcontrafold=0 + defaultalgopt=" -A " + defaultalgoptit=" -AB " ## chui + defaultaof="0.0" + defaultsbstmodel=" -b 62 " + defaultkappa=" " + defaultfmodel=" -a " +elif [ $progname = "qinsi" -o $progname = "mafft-qinsi" ]; then + defaultfft=1 + defaultcycle=1 + defaultiterate=1000 + defaultdistance="global" + defaultweighti="3.2" + defaultweightr="8.0" + defaultweightm="2.0" + defaultmccaskill=1 + defaultcontrafold=0 + defaultalgopt=" -A " + defaultalgoptit=" -AB " ## chui + defaultaof="0.0" + defaultsbstmodel=" -b 62 " + defaultkappa=" " + defaultfmodel=" -a " +elif [ $progname = "linsi" -o $progname = "mafft-linsi" ]; then + defaultfft=0 + defaultcycle=1 + defaultiterate=1000 + defaultdistance="local" +elif [ $progname = "ginsi" -o $progname = "mafft-ginsi" ]; then + defaultfft=1 + defaultcycle=1 + defaultiterate=1000 + defaultdistance="global" +elif [ $progname = "einsi" -o $progname = "mafft-einsi" ]; then + defaultfft=0 + defaultcycle=1 + defaultiterate=1000 + defaultdistance="localgenaf" +elif [ $progname = "fftns" -o $progname = "mafft-fftns" ]; then + defaultfft=1 + defaultcycle=2 + defaultdistance="sixtuples" +elif [ $progname = "fftnsi" -o $progname = "mafft-fftnsi" ]; then + defaultfft=1 + defaultcycle=2 + defaultiterate=2 + defaultdistance="sixtuples" +elif [ $progname = "nwns" -o $progname = "mafft-nwns" ]; then + defaultfft=0 + defaultcycle=2 + defaultdistance="sixtuples" +elif [ $progname = "nwnsi" -o $progname = "mafft-nwnsi" ]; then + defaultfft=0 + defaultcycle=2 + defaultiterate=2 + defaultdistance="sixtuples" +fi +outputfile="" +namelength=15 +anysymbol=0 +parallelizationstrategy="BAATARI2" +kappa=$defaultkappa +sbstmodel=$defaultsbstmodel +fmodel=$defaultfmodel +gop=$defaultgop +aof=$defaultaof +cycle=$defaultcycle +iterate=$defaultiterate +fft=$defaultfft +rough=$defaultrough +distance=$defaultdistance +forcefft=0 +memopt=" " +weightopt=" " +GGOP="-6.00" +LGOP="-6.00" +LEXP="-0.000" +GEXP="-0.000" +lgop=$defaultlgop +lexp="-0.100" +laof=$defaultlaof +pggop="-2.00" +pgexp="-0.10" +pgaof="0.10" +rgop="-1.530" +rgep="-0.000" +seqtype=" " +weighti=$defaultweighti +weightr=$defaultweightr +weightm=$defaultweightm +rnaalifold=0 +mccaskill=$defaultmccaskill +contrafold=$defaultcontrafold +quiet=0 +debug=0 +sw=0 +algopt=$defaultalgopt +algoptit=$defaultalgoptit +scorecalcopt=" " +coreout=0 +corethr="0.5" +corewin="100" +coreext=" " +outputformat="pir" +outorder="input" +seed="x" +seedtable="x" +auto=0 +groupsize=-1 +partsize=50 +partdist="sixtuples" +partorderopt=" -x " +treeout=0 +distout=0 +treein=0 +topin=0 +treeinopt=" " +seedfiles="/dev/null" +seedtablefile="/dev/null" +aamatrix="/dev/null" +treeinfile="/dev/null" +rnascoremtx=" " +laraparams="/dev/null" +foldalignopt=" " +treealg=" -X " +scoreoutarg=" " +numthreads=0 +randomseed=0 +addfile="/dev/null" +addarg0=" " +outnum=" " +if [ $# -gt 0 ]; then + while [ $# -gt 1 ]; + do + if [ "$1" = "--auto" ]; then + auto=1 + elif [ "$1" = "--anysymbol" ]; then + anysymbol=1 + elif [ "$1" = "--preservecase" ]; then + anysymbol=1 + elif [ "$1" = "--clustalout" ]; then + outputformat="clustal" + elif [ "$1" = "--phylipout" ]; then + outputformat="phylip" + elif [ "$1" = "--reorder" ]; then + outorder="aligned" + partorderopt=" " + elif [ "$1" = "--inputorder" ]; then + outorder="input" + partorderopt=" -x " + elif [ "$1" = "--unweight" ]; then + weightopt=" -u " + elif [ "$1" = "--algq" ]; then + algopt=" -Q " + algoptit=" -QB " + elif [ "$1" = "--namelength" ]; then + shift + namelength=`expr "$1" - 0` + elif [ "$1" = "--groupsize" ]; then + shift + groupsize=`expr "$1" - 0` + elif [ "$1" = "--partsize" ]; then + shift + partsize=`expr "$1" - 0` + elif [ "$1" = "--parttree" ]; then + distance="parttree" + partdist="sixtuples" + elif [ "$1" = "--dpparttree" ]; then + distance="parttree" + partdist="localalign" + elif [ "$1" = "--fastaparttree" ]; then + distance="parttree" + partdist="fasta" + elif [ "$1" = "--treeout" ]; then + treeout=1 + elif [ "$1" = "--distout" ]; then + distout=1 + elif [ "$1" = "--fastswpair" ]; then + distance="fasta" + sw=1 + elif [ "$1" = "--fastapair" ]; then + distance="fasta" + sw=0 + elif [ "$1" = "--averagelinkage" ]; then + treealg=" -E " + elif [ "$1" = "--minimumlinkage" ]; then + treealg=" -q " + elif [ "$1" = "--noscore" ]; then + scorecalcopt=" -Z " + elif [ "$1" = "--6merpair" ]; then + distance="sixtuples" + elif [ "$1" = "--blastpair" ]; then + distance="blast" + elif [ "$1" = "--globalpair" ]; then + distance="global" + elif [ "$1" = "--localpair" ]; then + distance="local" + elif [ "$1" = "--scarnapair" ]; then + distance="scarna" + elif [ "$1" = "--larapair" ]; then + distance="lara" + elif [ "$1" = "--slarapair" ]; then + distance="slara" + elif [ "$1" = "--foldalignpair" ]; then + distance="foldalignlocal" + elif [ "$1" = "--foldalignlocalpair" ]; then + distance="foldalignlocal" + elif [ "$1" = "--foldalignglobalpair" ]; then + distance="foldalignglobal" + elif [ "$1" = "--globalgenafpair" ]; then + distance="globalgenaf" + elif [ "$1" = "--localgenafpair" ]; then + distance="localgenaf" + elif [ "$1" = "--genafpair" ]; then + distance="localgenaf" + elif [ "$1" = "--memsave" ]; then + memopt=" -M -B " # -B (bunkatsunashi no riyu ga omoidasenai) + elif [ "$1" = "--nomemsave" ]; then + memopt=" -N " + elif [ "$1" = "--nuc" ]; then + seqtype=" -D " + elif [ "$1" = "--amino" ]; then + seqtype=" -P " + elif [ "$1" = "--fft" ]; then + fft=1 + forcefft=1 + elif [ "$1" = "--nofft" ]; then + fft=0 + elif [ "$1" = "--quiet" ]; then + quiet=1 + elif [ "$1" = "--debug" ]; then + debug=1 + elif [ "$1" = "--coreext" ]; then + coreext=" -c " + elif [ "$1" = "--core" ]; then + coreout=1 + elif [ "$1" = "--out" ]; then + shift + outputfile="$1" + elif [ "$1" = "--thread" ]; then + shift + numthreads=`expr "$1" - 0` + elif [ "$1" = "--randomseed" ]; then + shift + randomseed=`expr "$1" - 0` + elif [ "$1" = "--bestfirst" ]; then + parallelizationstrategy="BESTFIRST" + elif [ "$1" = "--adhoc0" ]; then + parallelizationstrategy="BAATARI0" + elif [ "$1" = "--adhoc1" ]; then + parallelizationstrategy="BAATARI1" + elif [ "$1" = "--adhoc2" ]; then + parallelizationstrategy="BAATARI2" + elif [ "$1" = "--simplehillclimbing" ]; then + parallelizationstrategy="BAATARI2" + elif [ "$1" = "--scoreout" ]; then + scoreoutarg="-S -B" + elif [ "$1" = "--outnum" ]; then + scoreoutarg="-n" + elif [ "$1" = "--addprofile" ]; then + shift + addarg0="-I" + addfile="$1" + elif [ "$1" = "--add" ]; then + shift + addarg0="-K -I" + addfile="$1" + elif [ "$1" = "--maxiterate" ]; then + shift + iterate=`expr "$1" - 0` + elif [ "$1" = "--retree" ]; then + shift + cycle=`expr "$1" - 0` + elif [ "$1" = "--aamatrix" ]; then + shift + sbstmodel=" -b -1 " + aamatrix="$1" + elif [ "$1" = "--treein" ]; then + shift + treeinopt=" -U " + treein=1 + treeinfile="$1" + elif [ "$1" = "--topin" ]; then + shift + treeinopt=" -V " + treein=1 + treeinfile="$1" + echo "The --topin option has been disabled." 1>&2 + echo "There was a bug in version < 6.530." 1>&2 + echo "This bug has not yet been fixed." 1>&2 + exit 1 + elif [ "$1" = "--kappa" ]; then + shift + kappa=" -k $1 " + elif [ "$1" = "--fmodel" ]; then + fmodel=" -a " + elif [ "$1" = "--jtt" ]; then + shift + sbstmodel=" -j $1" + elif [ "$1" = "--kimura" ]; then + shift + sbstmodel=" -j $1" + elif [ "$1" = "--tm" ]; then + shift + sbstmodel=" -m $1" + elif [ "$1" = "--bl" ]; then + shift + sbstmodel=" -b $1" + elif [ "$1" = "--weighti" ]; then + shift + weighti="$1" + elif [ "$1" = "--weightr" ]; then + shift + weightr="$1" + elif [ "$1" = "--weightm" ]; then + shift + weightm="$1" + elif [ "$1" = "--rnaalifold" ]; then + rnaalifold=1 + elif [ "$1" = "--mccaskill" ]; then + mccaskill=1 + contrafold=0 + elif [ "$1" = "--contrafold" ]; then + mccaskill=0 + contrafold=1 + elif [ "$1" = "--ribosum" ]; then + rnascoremtx=" -s " + elif [ "$1" = "--op" ]; then + shift + gop="$1" + elif [ "$1" = "--ep" ]; then + shift + aof="$1" + elif [ "$1" = "--rop" ]; then + shift + rgop="$1" + elif [ "$1" = "--rep" ]; then + shift + rgep="$1" + elif [ "$1" = "--lop" ]; then + shift + lgop="$1" + elif [ "$1" = "--LOP" ]; then + shift + LGOP="$1" + elif [ "$1" = "--lep" ]; then + shift + laof="$1" + elif [ "$1" = "--lexp" ]; then + shift + lexp="$1" + elif [ "$1" = "--LEXP" ]; then + shift + LEXP="$1" + elif [ "$1" = "--GEXP" ]; then + shift + GEXP="$1" + elif [ "$1" = "--GOP" ]; then + shift + GGOP="$1" + elif [ "$1" = "--gop" ]; then + shift + pggop="$1" + elif [ "$1" = "--gep" ]; then + shift + pgaof="$1" + elif [ "$1" = "--gexp" ]; then + shift + pgexp="$1" + elif [ "$1" = "--laraparams" ]; then + shift + laraparams="$1" + elif [ "$1" = "--corethr" ]; then + shift + corethr="$1" + elif [ "$1" = "--corewin" ]; then + shift + corewin="$1" + elif [ "$1" = "--seedtable" ]; then + shift + seedtable="y" + seedtablefile="$1" + elif [ "$1" = "--seed" ]; then + shift + seed="m" + seedfiles="$seedfiles $1" + elif [ $progname = "fftns" -o $progname = "nwns" ]; then + if [ "$1" -gt 0 ]; then + cycle=`expr "$1" - 0` + fi + else + echo "Unknown option: $1" 1>&2 + er=1; + fi + shift + done; + + + +# TMPFILE=/tmp/$progname.$$ + TMPFILE=`mktemp -dt $progname.XXXXXXXXXX` + if [ $? -ne 0 ]; then + echo "mktemp seems to be obsolete. Re-trying without -t" 1>&2 + TMPFILE=`mktemp -d /tmp/$progname.XXXXXXXXXX` + fi + umask 077 +# mkdir $TMPFILE || er=1 + if [ $debug -eq 1 ]; then + trap "tar cfvz debuginfo.tgz $TMPFILE; rm -rf $TMPFILE " 0 + else + trap "rm -rf $TMPFILE " 0 + fi + if [ $# -eq 1 ]; then + if [ -r "$1" -o "$1" = - ]; then + + if [ -r "$addfile" ]; then + printf ''; + else + echo "$0": Cannot open "$addfile". 1>&2 + exit 1; + fi + + cat "$1" | tr "\r" "\n" > $TMPFILE/infile + echo "" >> $TMPFILE/infile + cat "$addfile" | tr "\r" "\n" | grep -v "^$" >> $TMPFILE/infile + cat "$addfile" | tr "\r" "\n" | grep -v "^$" > $TMPFILE/_addfile + cat "$aamatrix" | tr "\r" "\n" | grep -v "^$" > $TMPFILE/_aamtx + cat "$treeinfile" | tr "\r" "\n" | grep -v "^$" > $TMPFILE/_guidetree + cat "$seedtablefile" | tr "\r" "\n" | grep -v "^$" > $TMPFILE/_seedtablefile + cat "$laraparams" | tr "\r" "\n" | grep -v "^$" > $TMPFILE/_lara.params +# echo $seedfiles + infilename="$1" + seedfilesintmp="/dev/null" + seednseq="0" + set $seedfiles > /dev/null + while [ $# -gt 1 ]; + do + shift + if [ -r "$1" ]; then + cat "$1" | tr "\r" "\n" > $TMPFILE/seed$# + else + echo "$0": Cannot open "$1". 1>&2 + exit 1; + fi + seednseq=$seednseq" "`grep -c '^[>|=]' $TMPFILE/seed$#` + seedfilesintmp=$seedfilesintmp" "seed$# + done +# ls $TMPFILE +# echo $seedfilesintmp +# echo $seednseq + + + else + echo "$0": Cannot open "$1". 1>&2 + er=1 +# exit 1; + fi + else + echo '$#'"=$#" 1>&2 + er=1 + fi + + + if [ $os != "linux" ]; then + numthreads=0 + fi + + if [ $numthreads -eq 0 -a $parallelizationstrategy = "BESTFIRST" ]; then + echo 'Impossible' 1>&2; + exit 1; + fi + + if [ $auto -eq 1 ]; then + "$prefix/countlen" < $TMPFILE/infile > $TMPFILE/size + nseq=`awk '{print $1}' $TMPFILE/size` + nlen=`awk '{print $3}' $TMPFILE/size` + if [ $nlen -lt 2000 -a $nseq -lt 100 ]; then + distance="local" + iterate=1000 + elif [ $nlen -lt 10000 -a $nseq -lt 500 ]; then + distance="sixtuples" + iterate=2 + else + distance="sixtuples" + iterate=0 + fi + if [ $quiet -eq 0 ]; then + echo "nseq = " $nseq 1>&2 + echo "nlen = " $nlen 1>&2 + echo "distance = " $distance 1>&2 + echo "iterate = " $iterate 1>&2 + fi + fi + + if [ $parallelizationstrategy = "BESTFIRST" -o $parallelizationstrategy = "BAATARI0" ]; then + iteratelimit=254 + else + iteratelimit=16 + fi + if [ $iterate -gt $iteratelimit ]; then #?? + iterate=$iteratelimit + fi + + if [ $rnaalifold -eq 1 ]; then + rnaopt=" -e $rgep -o $rgop -c $weightm -r $weightr -R $rnascoremtx " +# rnaoptit=" -o $rgop -BT -c $weightm -r $weightr -R " + rnaoptit=" -o $rgop -F -c $weightm -r $weightr -R " + elif [ $mccaskill -eq 1 -o $contrafold -eq 1 ]; then + rnaopt=" -o $rgop -c $weightm -r $weightr " +# rnaoptit=" -e $rgep -o $rgop -BT -c $weightm -r $weightr $rnascoremtx " + rnaoptit=" -e $rgep -o $rgop -F -c $weightm -r $weightr $rnascoremtx " + else + rnaopt=" " + rnaoptit=" -F " + fi + + model="$sbstmodel $kappa $fmodel" + + if [ $er -eq 1 ]; then + echo "------------------------------------------------------------------------------" 1>&2 + echo " MAFFT" $version 1>&2 +# echo "" 1>&2 +# echo " Input format: fasta" 1>&2 +# echo "" 1>&2 +# echo " Usage: `basename $0` [options] inputfile > outputfile" 1>&2 + echo " http://mafft.cbrc.jp/alignment/software/" 1>&2 + echo " NAR 30:3059-3066 (2002), Briefings in Bioinformatics 9:286-298 (2008)" 1>&2 +# echo "------------------------------------------------------------------------------" 1>&2 +# echo " % mafft in > out" 1>&2 + echo "------------------------------------------------------------------------------" 1>&2 +# echo "" 1>&2 + echo "High speed:" 1>&2 + echo " % mafft in > out" 1>&2 + echo " % mafft --retree 1 in > out (fast)" 1>&2 + echo "" 1>&2 + echo "High accuracy (for <~200 sequences x <~2,000 aa/nt):" 1>&2 + echo " % mafft --maxiterate 1000 --localpair in > out (% linsi in > out is also ok)" 1>&2 + echo " % mafft --maxiterate 1000 --genafpair in > out (% einsi in > out)" 1>&2 + echo " % mafft --maxiterate 1000 --globalpair in > out (% ginsi in > out)" 1>&2 + echo "" 1>&2 + echo "If unsure which option to use:" 1>&2 + echo " % mafft --auto in > out" 1>&2 + echo "" 1>&2 +# echo "Other options:" 1>&2 + echo "--op # : Gap opening penalty, default: 1.53" 1>&2 + echo "--ep # : Offset (works like gap extension penalty), default: 0.0" 1>&2 + echo "--maxiterate # : Maximum number of iterative refinement, default: 0" 1>&2 + echo "--clustalout : Output: clustal format, default: fasta" 1>&2 + echo "--reorder : Outorder: aligned, default: input order" 1>&2 + echo "--quiet : Do not report progress" 1>&2 + echo "--thread # : Number of threads. (# must be <= number of physical cores - 1)" 1>&2 +# echo "" 1>&2 +# echo " % mafft --maxiterate 1000 --localpair in > out (L-INS-i)" 1>&2 +# echo " most accurate in many cases, assumes only one alignable domain" 1>&2 +# echo "" 1>&2 +# echo " % mafft --maxiterate 1000 --genafpair in > out (E-INS-i)" 1>&2 +# echo " works well if many unalignable residues exist between alignable domains" 1>&2 +# echo "" 1>&2 +# echo " % mafft --maxiterate 1000 --globalpair in > out (G-INS-i)" 1>&2 +# echo " suitable for globally alignable sequences " 1>&2 +# echo "" 1>&2 +# echo " % mafft --maxiterate 1000 in > out (FFT-NS-i)" 1>&2 +# echo " accurate and slow, iterative refinement method " 1>&2 +# echo "" 1>&2 +# echo "If the input sequences are long (~1,000,000nt)," 1>&2 +# echo " % mafft --retree 1 --memsave --fft in > out (FFT-NS-1-memsave, new in v5.8)" 1>&2 +# echo "" 1>&2 +# echo "If many (~5,000) sequences are to be aligned," 1>&2 +# echo "" 1>&2 +# echo " % mafft --retree 1 [--memsave] --nofft in > out (NW-NS-1, new in v5.8)" 1>&2 +# echo "" 1>&2 +# echo " --localpair : All pairwise local alignment information is included" 1>&2 +# echo " to the objective function, default: off" 1>&2 +# echo " --globalpair : All pairwise global alignment information is included" 1>&2 +# echo " to the objective function, default: off" 1>&2 +# echo " --op # : Gap opening penalty, default: $defaultgop " 1>&2 +# echo " --ep # : Offset (works like gap extension penalty), default: $defaultaof " 1>&2 +# echo " --bl #, --jtt # : Scoring matrix, default: BLOSUM62" 1>&2 +# echo " Alternatives are BLOSUM (--bl) 30, 45, 62, 80, " 1>&2 +# echo " or JTT (--jtt) # PAM. " 1>&2 +# echo " --nuc or --amino : Sequence type, default: auto" 1>&2 +# echo " --retree # : The number of tree building in progressive method " 1>&2 +# echo " (see the paper for detail), default: $defaultcycle " 1>&2 +# echo " --maxiterate # : Maximum number of iterative refinement, default: $defaultiterate " 1>&2 +# if [ $defaultfft -eq 1 ]; then +# echo " --fft or --nofft: FFT is enabled or disabled, default: enabled" 1>&2 +# else +# echo " --fft or --nofft: FFT is enabled or disabled, default: disabled" 1>&2 +# fi +# echo " --memsave: Memory saving mode" 1>&2 +# echo " (for long genomic sequences), default: off" 1>&2 +# echo " --clustalout : Output: clustal format, default: fasta" 1>&2 +# echo " --reorder : Outorder: aligned, default: input order" 1>&2 +# echo " --quiet : Do not report progress" 1>&2 +# echo "-----------------------------------------------------------------------------" 1>&2 + exit 1; + fi + if [ $sw -eq 1 ]; then + swopt=" -A " + else + swopt=" " + fi + + if [ $distance = "fasta" -o $partdist = "fasta" ]; then + if [ ! "$FASTA_4_MAFFT" ]; then + FASTA_4_MAFFT=`which fasta34` + fi + + if [ ! -x "$FASTA_4_MAFFT" ]; then + echo "" 1>&2 + echo "== Install FASTA ========================================================" 1>&2 + echo "This option requires the fasta34 program (FASTA version x.xx or higher)" 1>&2 + echo "installed in your PATH. If you have the fasta34 program but have renamed" 1>&2 + echo "(like /usr/local/bin/myfasta), set the FASTA_4_MAFFT environment variable" 1>&2 + echo "to point your fasta34 (like setenv FASTA_4_MAFFT /usr/local/bin/myfasta)." 1>&2 + echo "=========================================================================" 1>&2 + echo "" 1>&2 + exit 1 + fi + fi + if [ $distance = "lara" -o $distance = "slara" ]; then + if [ ! -x "$prefix/mafft_lara" ]; then + echo "" 1>&2 + echo "== Install LaRA =========================================================" 1>&2 + echo "This option requires LaRA (Bauer et al. http://www.planet-lisa.net/)." 1>&2 + echo "The executable have to be renamed to 'mafft_lara' and installed into " 1>&2 + echo "the $prefix directory. " 1>&2 + echo "A configuration file of LaRA also have to be given" 1>&2 + echo "mafft-xinsi --larapair --laraparams parameter_file" 1>&2 + echo "mafft-xinsi --slarapair --laraparams parameter_file" 1>&2 + echo "=========================================================================" 1>&2 + echo "" 1>&2 + exit 1 + fi + if [ ! -s "$laraparams" ]; then + echo "" 1>&2 + echo "== Configure LaRA =======================================================" 1>&2 + echo "A configuration file of LaRA have to be given" 1>&2 + echo "mafft-xinsi --larapair --laraparams parameter_file" 1>&2 + echo "mafft-xinsi --slarapair --laraparams parameter_file" 1>&2 + echo "=========================================================================" 1>&2 + echo "" 1>&2 + exit 1 + fi + fi + if [ $distance = "foldalignlocal" -o $distance = "foldalignglobal" ]; then + if [ ! -x "$prefix/foldalign210" ]; then + echo "" 1>&2 + echo "== Install FOLDALIGN ====================================================" 1>&2 + echo "This option requires FOLDALIGN (Havgaard et al. http://foldalign.ku.dk/)." 1>&2 + echo "The executable have to be renamed to 'foldalign210' and installed into " 1>&2 + echo "the $prefix directory. " 1>&2 + echo "=========================================================================" 1>&2 + echo "" 1>&2 + exit 1 + fi + fi + if [ $distance = "scarna" ]; then + if [ ! -x "$prefix/mxscarnamod" ]; then + echo "" 1>&2 + echo "== Install MXSCARNA ======================================================" 1>&2 + echo "MXSCARNA (Tabei et al. BMC Bioinformatics 2008 9:33) is required." 1>&2 + echo "Please 'make' at the 'extensions' directory of the MAFFT source package," 1>&2 + echo "which contains the modified version of MXSCARNA." 1>&2 + echo "http://align.bmr.kyushu-u.ac.jp/mafft/software/source.html " 1>&2 + echo "==========================================================================" 1>&2 + echo "" 1>&2 + exit 1 + fi + fi + if [ $mccaskill -eq 1 ]; then + if [ ! -x "$prefix/mxscarnamod" ]; then + echo "" 1>&2 + echo "== Install MXSCARNA ======================================================" 1>&2 + echo "MXSCARNA (Tabei et al. BMC Bioinformatics 2008 9:33) is required." 1>&2 + echo "Please 'make' at the 'extensions' directory of the MAFFT source package," 1>&2 + echo "which contains the modified version of MXSCARNA." 1>&2 + echo "http://align.bmr.kyushu-u.ac.jp/mafft/software/source.html " 1>&2 + echo "==========================================================================" 1>&2 + echo "" 1>&2 + exit 1 + fi + fi + if [ $contrafold -eq 1 ]; then + if [ ! -x "$prefix/contrafold" ]; then + echo "" 1>&2 + echo "== Install CONTRAfold ===================================================" 1>&2 + echo "This option requires CONTRAfold" 1>&2 + echo "(Do et al. http://contra.stanford.edu/contrafold/)." 1>&2 + echo "The executable 'contrafold' have to be installed into " 1>&2 + echo "the $prefix directory. " 1>&2 + echo "=========================================================================" 1>&2 + echo "" 1>&2 + exit 1 + fi + fi + +#old +# if [ $treeout -eq 1 ]; then +# parttreeoutopt="-t" +# if [ $cycle -eq 0 ]; then +# treeoutopt="-t -T" +# groupsize=1 +# iterate=0 +# if [ $distance = "global" -o $distance = "local" -o $distance = "localgenaf" -o $distance = "globalgenaf" ]; then +# distance="distonly" +# fi +# else +# treeoutopt="-t" +# fi +# else +# parttreeoutopt=" " +# if [ $cycle -eq 0 ]; then +# treeoutopt="-t -T" +# iterate=0 +# if [ $distance = "global" -o $distance = "local" -o $distance = "localgenaf" -o $distance = "globalgenaf" ]; then +# distance="distonly" +# fi +# else +# treeoutopt=" " +# fi +# fi + +#new + if [ $cycle -eq 0 ]; then + treeoutopt="-t -T" + iterate=0 + if [ $distance = "global" -o $distance = "local" -o $distance = "localgenaf" -o $distance = "globalgenaf" ]; then + distance="distonly" + fi + if [ $treeout -eq 1 ]; then + parttreeoutopt="-t" + groupsize=1 + else + parttreeoutopt=" " + fi + if [ $distout -eq 1 ]; then + distoutopt="-y -T" + fi + else + if [ $treeout -eq 1 ]; then + parttreeoutopt="-t" + treeoutopt="-t" + else + parttreeoutopt=" " + treeoutopt=" " + fi + if [ $distout -eq 1 ]; then + distoutopt="-y" + fi + fi +# + + formatcheck=`grep -c '^[[:blank:]]\+>' $TMPFILE/infile | head -1 ` + if [ $formatcheck -gt 0 ]; then + echo "The first character of a description line must be " 1>&2 + echo "the greater-than (>) symbol, not a blank." 1>&2 + echo "Please check the format around the following line(s):" 1>&2 + grep -n '^[[:blank:]]\+>' $TMPFILE/infile 1>&2 + exit 1 + fi + + nseq=`grep -c '^[>|=]' $TMPFILE/infile | head -1 ` + if [ $nseq -eq 2 ]; then + cycle=1 + fi + if [ $cycle -gt 3 ]; then + cycle=3 + fi + + if [ $nseq -gt 4000 -a $iterate -gt 1 ]; then + echo "Too many sequences to perform iterative refinement!" 1>&2 + echo "Please use a progressive method." 1>&2 + exit 1 + fi + + + if [ $distance = "sixtuples" -a \( $seed = "x" -a $seedtable = "x" \) ]; then + localparam=" " + elif [ $distance = "sixtuples" -a \( $seed != "x" -o $seedtable != "x" \) ]; then + if [ $cycle -lt 2 ]; then + cycle=2 # nazeda + fi + if [ $iterate -lt 2 ]; then + echo "############################################################################" 1>&2 + echo "# Warning:" 1>&2 + echo "# Progressive alignment method is incompatible with the --seed option." 1>&2 + echo "# Automatically switched to the iterative refinement method." 1>&2 + echo "# " 1>&2 + echo "# Also consider using the '--add' option, which is compatible with" 1>&2 + echo "# the progressive method and FASTER than the '--seed' option." 1>&2 + echo "# Usage is:" 1>&2 + echo "# % mafft --add newSequences existingAlignment > output" 1>&2 + echo "############################################################################" 1>&2 + iterate=2 + fi + localparam="-l "$weighti + elif [ $distance = "parttree" ]; then + localparam=" " + if [ $groupsize -gt -1 ]; then + cycle=1 + fi + else + localparam=" -l "$weighti + if [ $cycle -gt 1 ]; then # 09/01/08 + cycle=1 + fi + fi + + if [ $distance = "localgenaf" -o $distance = "globalgenaf" ]; then + aof="0.000" + fi + + if [ "$memopt" = " -M -B " -a "$distance" != "sixtuples" ]; then + echo "Impossible" 1>&2 + exit 1 + fi +#exit + + if [ $distance = "parttree" ]; then + if [ $seed != "x" -o $seedtable != "x" ]; then + echo "Impossible" 1>&2 + exit 1 + fi + if [ $iterate -gt 1 ]; then + echo "Impossible" 1>&2 + exit 1 + fi + if [ $outorder = "aligned" ]; then + outorder="input" + fi + outorder="input" # partorder ga kiku + if [ $partdist = "localalign" ]; then + splitopt=" -L " # -L -l -> fast + elif [ $partdist = "fasta" ]; then + splitopt=" -S " + else + splitopt=" " + fi + fi + + +# if [ $nseq -gt 5000 ]; then +# fft=0 +# fi + if [ $forcefft -eq 1 ]; then + param_fft=" -G " + fft=1 + elif [ $fft -eq 1 ]; then + param_fft=" -F " + else + param_fft=" " + fi + + if [ $seed != "x" -a $seedtable != "x" ]; then + echo 'Use either one of seedtable and seed. Not both.' 1>&2 + exit 1 + fi +# if [ $seedtable != "x" -a $anysymbol -gt 0 ]; then +# echo 'The combination of --seedtable and --anysymbol is not supported.' 1>&2 +# exit 1 +# fi + + if [ $treein -eq 1 ]; then +# if [ $iterate -gt 0 ]; then +# echo 'Not supported yet.' 1>&2 +# exit 1 +# fi + cycle=1 + fi + + if [ "$addarg0" != " " ]; then + "$prefix/countlen" < $TMPFILE/_addfile > $TMPFILE/addsize + nadd=`awk '{print $1}' $TMPFILE/addsize` + if [ $nadd -eq "0" ]; then + echo Check $addfile 1>&2 + exit 1; + fi + addarg="$addarg0 $nadd" + cycle=1 + iterate=0 + if [ $seed != "x" -o $seedtable != "x" ]; then + echo 'Impossible' 1>&2; + echo 'Use either ONE of --seed, --seedtable, --addprofile and --add.' 1>&2 + exit 1; + fi + fi + + if [ $mccaskill -eq 1 -o $rnaalifold -eq 1 -o $contrafold -eq 1 ]; then + if [ $distance = "sixtuples" ]; then + echo 'Not supported.' 1>&2 + echo 'Please add --globalpair, --localpair, --scarnapair,' 1>&2 + echo '--larapair, --slarapair, --foldalignlocalpair or --foldalignglobalpair' 1>&2 + exit 1 + fi + fi + + if [ $mccaskill -eq 1 -o $rnaalifold -eq 1 -o $contrafold -eq 1 ]; then + if [ $distance = "scarna" -o $distance = "lara" -o $distance = "slara" -o $distance = "foldalignlocal" -o $distance = "foldalignglobal" ]; then + strategy="X-I" + elif [ $distance = "global" -o $distance = "local" -o $distance = "localgenaf" -o "globalgenaf" ]; then + strategy="Q-I" + fi + elif [ $distance = "fasta" -a $sw -eq 0 ]; then + strategy="F-I" + elif [ $distance = "fasta" -a $sw -eq 1 ]; then + strategy="H-I" + elif [ $distance = "blast" ]; then + strategy="B-I" + elif [ $distance = "global" -o $distance = "distonly" ]; then + strategy="G-I" + elif [ $distance = "local" ]; then + strategy="L-I" + elif [ $distance = "localgenaf" ]; then + strategy="E-I" + elif [ $distance = "globalgenaf" ]; then + strategy="K-I" + elif [ $fft -eq 1 ]; then + strategy="FFT-" + else + strategy="NW-" + fi + strategy=$strategy"NS-" + if [ $iterate -gt 0 ]; then + strategy=$strategy"i" + elif [ $distance = "parttree" ]; then + if [ $partdist = "fasta" ]; then + strategy=$strategy"FastaPartTree-"$cycle + elif [ $partdist = "localalign" ]; then + strategy=$strategy"DPPartTree-"$cycle + else + strategy=$strategy"PartTree-"$cycle + fi + else + strategy=$strategy$cycle + fi + + explanation='?' + performance='Not tested.' + if [ $strategy = "F-INS-i" ]; then + explanation='Iterative refinement method (<'$iterate') with LOCAL pairwise alignment information' + performance='Most accurate, but very slow' + elif [ $strategy = "L-INS-i" ]; then + explanation='Iterative refinement method (<'$iterate') with LOCAL pairwise alignment information' + performance='Probably most accurate, very slow' + elif [ $strategy = "E-INS-i" ]; then + explanation='Iterative refinement method (<'$iterate') with LOCAL pairwise alignment with generalized affine gap costs (Altschul 1998)' + performance='Suitable for sequences with long unalignable regions, very slow' + elif [ $strategy = "G-INS-i" ]; then + explanation='Iterative refinement method (<'$iterate') with GLOBAL pairwise alignment information' + performance='Suitable for sequences of similar lengths, very slow' + elif [ $strategy = "X-INS-i" ]; then + explanation='RNA secondary structure information is taken into account.' + performance='For short RNA sequences only, extremely slow' + elif [ $strategy = "F-INS-1" ]; then + explanation='Progressive method incorporating LOCAL pairwise alignment information' + elif [ $strategy = "L-INS-1" ]; then + explanation='Progressive method incorporating LOCAL pairwise alignment information' + elif [ $strategy = "G-INS-1" ]; then + explanation='Progressive method incorporating GLOBAL pairwise alignment information' + elif [ $strategy = "FFT-NS-i" -o $strategy = "NW-NS-i" ]; then + explanation='Iterative refinement method (max. '$iterate' iterations)' + if [ $iterate -gt 2 ]; then + performance='Accurate but slow' + else + performance='Standard' + fi + elif [ $strategy = "FFT-NS-2" -o $strategy = "NW-NS-2" ]; then + explanation='Progressive method (guide trees were built '$cycle' times.)' + performance='Fast but rough' + elif [ $strategy = "FFT-NS-1" -o $strategy = "NW-NS-1" ]; then + explanation='Progressive method (rough guide tree was used.)' + performance='Very fast but very rough' + fi + + if [ $outputformat = "clustal" -a $outorder = "aligned" ]; then + outputopt=" -c $strategy -r $TMPFILE/order " + elif [ $outputformat = "clustal" -a $outorder = "input" ]; then + outputopt=" -c $strategy " + elif [ $outputformat = "phylip" -a $outorder = "aligned" ]; then + outputopt=" -y -r $TMPFILE/order " + elif [ $outputformat = "phylip" -a $outorder = "input" ]; then + outputopt=" -y " + elif [ $outputformat = "pir" -a $outorder = "aligned" ]; then + outputopt=" -f -r $TMPFILE/order " + else + outputopt="null" + fi + + ( + cd $TMPFILE; + + if [ $quiet -gt 0 ]; then + + if [ $anysymbol -eq 1 ]; then + mv infile orig + "$prefix/replaceu" -i orig > infile 2>/dev/null || exit 1 + fi + + if [ $seed != "x" ]; then + mv infile infile2 + if [ $anysymbol -eq 1 ]; then + mv orig orig2 + cat /dev/null > orig + fi + cat /dev/null > infile + cat /dev/null > hat3.seed + seedoffset=0 +# echo "seednseq="$seednseq +# echo "seedoffset="$seedoffset + set $seednseq > /dev/null +# echo $# + while [ $# -gt 1 ] + do + shift +# echo "num="$# + + if [ $anysymbol -eq 1 ]; then + cat seed$# >> orig + "$prefix/replaceu" -i seed$# -o $seedoffset > clean 2>/dev/null || exit 1 + mv clean seed$# + fi + "$prefix/multi2hat3s" -t $nseq -o $seedoffset -i seed$# >> infile 2>/dev/null || exit 1 + cat hat3 >> hat3.seed +# echo "$1" + seedoffset=`expr $seedoffset + $1` +# echo "$1" +# echo "seedoffset="$seedoffset + done; +# echo "seedoffset="$seedoffset + if [ $anysymbol -eq 1 ]; then + "$prefix/replaceu" -i orig2 -o $seedoffset >> infile 2>/dev/null || exit 1 # yarinaoshi + cat orig2 >> orig + else + cat infile2 >> infile + fi + elif [ $seedtable != "x" ]; then + cat _seedtablefile > hat3.seed + else + cat /dev/null > hat3.seed + fi +# cat hat3.seed + + + if [ $mccaskill -eq 1 ]; then + "$prefix/mccaskillwrap" -C $numthreads -d "$prefix" -i infile > hat4 2>/dev/null || exit 1 + elif [ $contrafold -eq 1 ]; then + "$prefix/contrafoldwrap" -d "$prefix" -i infile > hat4 2>/dev/null || exit 1 + fi + if [ $distance = "fasta" ]; then + "$prefix/dndfast7" $swopt < infile > /dev/null 2>&1 || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null 2>&1 || exit 1 + elif [ $distance = "blast" ]; then + "$prefix/dndblast" < infile > /dev/null 2>&1 || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null 2>&1 || exit 1 + elif [ $distance = "foldalignlocal" ]; then + "$prefix/pairlocalalign" -C $numthreads $seqtype $foldalignopt $model -g $lexp -f $lgop -h $laof -H -d "$prefix" < infile > /dev/null 2>&1 || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null 2>&1 || exit 1 + elif [ $distance = "foldalignglobal" ]; then + "$prefix/pairlocalalign" -C $numthreads $seqtype $foldalignopt $model -g $pgexp -f $pggop -h $pgaof -H -o -global -d "$prefix" < infile > /dev/null 2>&1 || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null 2>&1 || exit 1 + elif [ $distance = "slara" ]; then + "$prefix/pairlocalalign" -C $numthreads -p $laraparams $seqtype $model -f $lgop -T -d "$prefix" < infile > /dev/null 2>&1 || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null 2>&1 || exit 1 + elif [ $distance = "lara" ]; then + "$prefix/pairlocalalign" -C $numthreads -p $laraparams $seqtype $model -f $lgop -B -d "$prefix" < infile > /dev/null 2>&1 || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null 2>&1 || exit 1 + elif [ $distance = "scarna" ]; then + "$prefix/pairlocalalign" -C $numthreads $seqtype $model -f $pggop -s -d "$prefix" < infile > /dev/null 2>&1 || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null 2>&1 || exit 1 + elif [ $distance = "global" ]; then + "$prefix/pairlocalalign" -C $numthreads $seqtype $model -g $pgexp -f $pggop -h $pgaof -F < infile > /dev/null 2>&1 || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null 2>&1 || exit 1 + elif [ $distance = "local" ]; then + "$prefix/pairlocalalign" -C $numthreads $seqtype $model -g $lexp -f $lgop -h $laof -L < infile > /dev/null 2>&1 || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null 2>&1 || exit 1 + elif [ $distance = "globalgenaf" ]; then + "$prefix/pairlocalalign" -C $numthreads $seqtype $model -g $pgexp -f $pggop -h $pgaof -O $GGOP -E $GEXP -K < infile > /dev/null 2>&1 || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null 2>&1 || exit 1 + elif [ $distance = "localgenaf" ]; then + "$prefix/pairlocalalign" -C $numthreads $seqtype $model -g $lexp -f $lgop -h $laof -O $LGOP -E $LEXP -N < infile > /dev/null 2>&1 || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null 2>&1 || exit 1 + elif [ $distance = "distonly" ]; then + "$prefix/pairlocalalign" -C $numthreads $seqtype $model -g $pgexp -f $pggop -h $pgaof -t < infile > /dev/null 2>&1 || exit 1 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null 2>&1 || exit 1 + elif [ $distance = "parttree" ]; then + "$prefix/splittbfast" -Q $splitopt $partorderopt $parttreeoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft -p $partsize -s $groupsize $treealg -i infile > pre 2>/dev/null || exit 1 + mv hat3.seed hat3 + else + "$prefix/disttbfast" -O $outnum $addarg -C $numthreads $memopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $algopt $treealg $scoreoutarg < infile > pre 2>/dev/null || exit 1 + mv hat3.seed hat3 + fi + while [ $cycle -gt 1 ] + do + if [ $distance = "parttree" ]; then + mv pre infile + "$prefix/splittbfast" -Z -Q $splitopt $partorderopt $parttreeoutopt $memopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft -p $partsize -s $groupsize $treealg -i infile > pre 2>/dev/null || exit 1 + else + "$prefix/tbfast" -O $outnum -C $numthreads $rnaopt $weightopt $treeoutopt $distoutopt $memopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt -J $treealg $scoreoutarg < pre > /dev/null 2>&1 || exit 1 + fi + cycle=`expr $cycle - 1` + done + if [ $iterate -gt 0 ]; then + if [ $distance = "sixtuples" ]; then + "$prefix/dndpre" -C $numthreads < pre > /dev/null 2>&1 || exit 1 + fi + "$prefix/dvtditr" -C $numthreads -t $randomseed $rnaoptit $memopt $scorecalcopt $localparam -z 50 $seqtype $model -f "-"$gop -h "-"$aof -I $iterate $weightopt $treeinopt $algoptit $treealg -p $parallelizationstrategy $scoreoutarg < pre > /dev/null 2>&1 || exit 1 + fi + else + + if [ $anysymbol -eq 1 ]; then + mv infile orig + "$prefix/replaceu" -i orig > infile || exit 1 + fi + + if [ $seed != "x" ]; then + mv infile infile2 + if [ $anysymbol -eq 1 ]; then + mv orig orig2 + cat /dev/null > orig + fi + cat /dev/null > infile + cat /dev/null > hat3.seed + seedoffset=0 +# echo "seednseq="$seednseq +# echo "seedoffset="$seedoffset + set $seednseq > /dev/null +# echo $# + while [ $# -gt 1 ] + do + shift +# echo "num="$# + + if [ $anysymbol -eq 1 ]; then + cat seed$# >> orig + "$prefix/replaceu" -i seed$# -o $seedoffset > clean || exit 1 + mv clean seed$# + fi + "$prefix/multi2hat3s" -t $nseq -o $seedoffset -i seed$# >> infile || exit 1 + cat hat3 >> hat3.seed +# echo "$1" + seedoffset=`expr $seedoffset + $1` +# echo "$1" +# echo "seedoffset="$seedoffset + done; +# echo "seedoffset="$seedoffset + if [ $anysymbol -eq 1 ]; then + "$prefix/replaceu" -i orig2 -o $seedoffset >> infile || exit 1 # yarinaoshi + cat orig2 >> orig + else + cat infile2 >> infile + fi + elif [ $seedtable != "x" ]; then + cat _seedtablefile > hat3.seed + else + cat /dev/null > hat3.seed + fi +# cat hat3.seed + + if [ $mccaskill -eq 1 ]; then + "$prefix/mccaskillwrap" -C $numthreads -d "$prefix" -i infile > hat4 || exit 1 + elif [ $contrafold -eq 1 ]; then + "$prefix/contrafoldwrap" -d "$prefix" -i infile > hat4 || exit 1 + fi + if [ $distance = "fasta" ]; then + "$prefix/dndfast7" $swopt < infile > /dev/null || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null || exit 1 + elif [ $distance = "blast" ]; then + "$prefix/dndblast" < infile > /dev/null || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null || exit 1 + elif [ $distance = "foldalignlocal" ]; then + "$prefix/pairlocalalign" -C $numthreads $seqtype $foldalignopt $model -g $lexp -f $lgop -h $laof -H -d "$prefix" < infile > /dev/null || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null 2>&1 || exit 1 + elif [ $distance = "foldalignglobal" ]; then + "$prefix/pairlocalalign" -C $numthreads $seqtype $foldalignopt $model -g $pgexp -f $pggop -h $pgaof -H -o -global -d "$prefix" < infile > /dev/null || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null 2>&1 || exit 1 + elif [ $distance = "slara" ]; then + "$prefix/pairlocalalign" -C $numthreads -p $laraparams $seqtype $model -f $lgop -T -d "$prefix" < infile > /dev/null || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null 2>&1 || exit 1 + elif [ $distance = "lara" ]; then + "$prefix/pairlocalalign" -C $numthreads -p $laraparams $seqtype $model -f $lgop -B -d "$prefix" < infile > /dev/null || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null 2>&1 || exit 1 + elif [ $distance = "scarna" ]; then + "$prefix/pairlocalalign" -C $numthreads $seqtype $model -f $pggop -s -d "$prefix" < infile > /dev/null || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null 2>&1 || exit 1 + elif [ $distance = "global" ]; then + "$prefix/pairlocalalign" -C $numthreads $seqtype $model -g $pgexp -f $pggop -h $pgaof -F < infile > /dev/null || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null || exit 1 + elif [ $distance = "local" ]; then + "$prefix/pairlocalalign" -C $numthreads $seqtype $model -g $lexp -f $lgop -h $laof -L < infile > /dev/null || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null || exit 1 + elif [ $distance = "globalgenaf" ]; then + "$prefix/pairlocalalign" -C $numthreads $seqtype $model -g $pgexp -f $pggop -h $pgaof -O $GGOP -E $GEXP -K < infile > /dev/null || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null || exit 1 + elif [ $distance = "localgenaf" ]; then + "$prefix/pairlocalalign" -C $numthreads $seqtype $model -g $lexp -f $lgop -h $laof -O $LGOP -E $LEXP -N < infile > /dev/null || exit 1 + cat hat3.seed hat3 > hatx + mv hatx hat3 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null || exit 1 + elif [ $distance = "distonly" ]; then + "$prefix/pairlocalalign" -C $numthreads $seqtype $model -g $pgexp -f $pggop -h $pgaof -t < infile > /dev/null || exit 1 + "$prefix/tbfast" $outnum $addarg -C $numthreads $rnaopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt $treealg $scoreoutarg < infile > /dev/null || exit 1 + elif [ $distance = "parttree" ]; then + "$prefix/splittbfast" -Q $splitopt $partorderopt $parttreeoutopt $memopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft -p $partsize -s $groupsize $treealg -i infile > pre || exit 1 + mv hat3.seed hat3 + else + "$prefix/disttbfast" -O $outnum $addarg -C $numthreads $memopt $weightopt $treeinopt $treeoutopt $distoutopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $algopt $treealg $scoreoutarg < infile > pre || exit 1 + mv hat3.seed hat3 + fi + + while [ $cycle -gt 1 ] + do + if [ $distance = "parttree" ]; then + mv pre infile + "$prefix/splittbfast" -Z -Q $splitopt $partorderopt $parttreeoutopt $memopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft -p $partsize -s $groupsize $treealg -i infile > pre || exit 1 + else + "$prefix/tbfast" -O $outnum -C $numthreads $rnaopt $weightopt $treeoutopt $distoutopt $memopt $seqtype $model -f "-"$gop -h "-"$aof $param_fft $localparam $algopt -J $treealg $scoreoutarg < pre > /dev/null || exit 1 + fi + cycle=`expr $cycle - 1` + done + if [ $iterate -gt 0 ]; then + if [ $distance = "sixtuples" ]; then + "$prefix/dndpre" -C $numthreads < pre > /dev/null 2>&1 || exit 1 + fi + "$prefix/dvtditr" -C $numthreads -t $randomseed $rnaoptit $memopt $scorecalcopt $localparam -z 50 $seqtype $model -f "-"$gop -h "-"$aof -I $iterate $weightopt $treeinopt $algoptit $treealg -p $parallelizationstrategy $scoreoutarg < pre > /dev/null || exit 1 + fi + fi + + if [ $coreout -eq 1 ]; then + "$prefix/setcore" -w $corewin -i $corethr $coreext < pre > pre2 + mv pre2 pre + elif [ $anysymbol -eq 1 ]; then + "$prefix/restoreu" -a pre -i orig > restored || exit 1 + mv restored pre + fi + + if [ $quiet -eq 0 ]; then + echo '' 1>&2 + if [ $mccaskill -eq 1 ]; then + echo "RNA base pairing probaility was calculated by the McCaskill algorithm (1)" 1>&2 + echo "implemented in Vienna RNA package (2) and MXSCARNA (3), and then" 1>&2 + echo "incorporated in the iterative alignment process (4)." 1>&2 + echo "(1) McCaskill, 1990, Biopolymers 29:1105-1119" 1>&2 + echo "(2) Hofacker et al., 2002, J. Mol. Biol. 319:3724-3732" 1>&2 + echo "(3) Tabei et al., 2008, BMC Bioinformatics 9:33" 1>&2 + echo "(4) Katoh and Toh, 2008, BMC Bioinformatics 9:212" 1>&2 + echo "" 1>&2 + elif [ $contrafold -eq 1 ]; then + echo "RNA base pairing probaility was calculated by the CONTRAfold algorithm (1)" 1>&2 + echo "and then incorporated in the iterative alignment process (4)." 1>&2 + echo "(1) Do et al., 2006, Bioinformatics 22:e90-98" 1>&2 + echo "(2) Katoh and Toh, 2008, BMC Bioinformatics 9:212" 1>&2 + echo "" 1>&2 + fi + if [ $distance = "fasta" -o $partdist = "fasta" ]; then + echo "Pairwise alignments were computed by FASTA" 1>&2 + echo "(Pearson & Lipman, 1988, PNAS 85:2444-2448)" 1>&2 + fi + if [ $distance = "blast" ]; then + echo "Pairwise alignments were computed by BLAST" 1>&2 + echo "(Altschul et al., 1997, NAR 25:3389-3402)" 1>&2 + fi + if [ $distance = "scarna" ]; then + echo "Pairwise alignments were computed by MXSCARNA" 1>&2 + echo "(Tabei et al., 2008, BMC Bioinformatics 9:33)." 1>&2 + fi + if [ $distance = "lara" -o $distance = "slara" ]; then + echo "Pairwise alignments were computed by LaRA" 1>&2 + echo "(Bauer et al., 2007, BMC Bioinformatics 8:271)." 1>&2 + fi + if [ $distance = "foldalignlocal" ]; then + echo "Pairwise alignments were computed by FOLDALIGN (local)" 1>&2 + echo "(Havgaard et al., 2007, PLoS Computational Biology 3:e193)." 1>&2 + fi + if [ $distance = "foldalignglobal" ]; then + echo "Pairwise alignments were computed by FOLDALIGN (global)" 1>&2 + echo "(Havgaard et al., 2007, PLoS Computational Biology 3:e193)." 1>&2 + fi + printf "\n" 1>&2 + echo 'Strategy:' 1>&2 + printf ' '$strategy 1>&2 + echo ' ('$performance')' 1>&2 + echo ' '$explanation 1>&2 + echo '' 1>&2 + echo "If unsure which option to use, try 'mafft --auto input > output'." 1>&2 +# echo "If long gaps are expected, try 'mafft --ep 0.0 --auto input > output'." 1>&2 + echo "If the possibility of long gaps can be excluded, add '--ep 0.123'." 1>&2 + echo "For more information, see 'mafft --help', 'mafft --man' and the mafft page." 1>&2 + echo '' 1>&2 + fi + ) + + if [ "$outputfile" = "" ]; then + if [ "$outputopt" = "null" ]; then + cat < $TMPFILE/pre || exit 1 + else + "$prefix/f2cl" -n $namelength $outputopt < $TMPFILE/pre || exit 1 + fi + else + if [ "$outputopt" = "null" ]; then + cat < $TMPFILE/pre > "$outputfile" || exit 1 + else + "$prefix/f2cl" -n $namelength $outputopt < $TMPFILE/pre > "$outputfile" || exit 1 + fi + fi + + if [ $treeout -eq 1 ]; then + cp $TMPFILE/infile.tree "$infilename.tree" + fi + + if [ $distout -eq 1 ]; then + cp $TMPFILE/hat2 "$infilename.hat2" + fi + + exit 0; +fi + +prog="awk" + +tmpawk=`which nawk 2>/dev/null | awk '{print $1}'` +if [ -x "$tmpawk" ]; then + prog="$tmpawk" +fi + +tmpawk=`which gawk 2>/dev/null | awk '{print $1}'` +if [ -x "$tmpawk" ]; then + prog="$tmpawk" +fi + +#echo "prog="$prog 1>&2 + +umask 077 +( +$prog ' +BEGIN { + prefix = ENVIRON["prefix"]; + version = ENVIRON["version"]; + myself = ENVIRON["myself"]; + while( 1 ) + { + options = "" + printf( "\n" ) > "/dev/tty"; + printf( "---------------------------------------------------------------------\n" ) > "/dev/tty"; + printf( "\n" ) > "/dev/tty"; + printf( " MAFFT %s\n", version ) > "/dev/tty"; + printf( "\n" ) > "/dev/tty"; + printf( " Copyright (c) 2011 Kazutaka Katoh\n" ) > "/dev/tty"; + printf( " NAR 30:3059-3066, NAR 33:511-518\n" ) > "/dev/tty"; + printf( " http://mafft.cbrc.jp/alignment/software/\n" ) > "/dev/tty"; + printf( "---------------------------------------------------------------------\n" ) > "/dev/tty"; + printf( "\n" ) > "/dev/tty"; + + while( 1 ) + { + printf( "\n" ) > "/dev/tty"; + printf( "Input file? (fasta format)\n@ " ) > "/dev/tty"; + res = getline < "/dev/tty"; + close( "/dev/tty" ) + if( res == 0 || NF == 0 ) + continue; + infile = sprintf( "%s", $0 ); + + res = getline < infile; + close( infile ); + if( res == -1 ) + { + printf( "%s: No such file.\n\n", infile ) > "/dev/tty"; + printf( "Filename extension (eg., .txt) must be typed, if any.\n\n" ) > "/dev/tty"; + } + else if( res == 0 ) + printf( "%s: Empty.\n", infile ) > "/dev/tty"; + else + { + printf( "OK. infile = %s\n\n", infile ) > "/dev/tty"; + break; + } + } + nseq = 0; + + while( 1 ) + { + printf( "\n" ) > "/dev/tty"; + printf( "Output file?\n" ) > "/dev/tty"; + printf( "@ " ) > "/dev/tty"; + res = getline < "/dev/tty"; + close( "/dev/tty" ); + if( res == 0 || NF == 0 ) + continue; + else + { + outfile = sprintf( "%s", $0 ); + printf( "OK. outfile = %s\n\n", outfile ) > "/dev/tty"; + break; + } + } + + while( 1 ) + { + outargs = ""; + printf( "\n" ) > "/dev/tty"; + printf( "Output format?\n" ) > "/dev/tty"; + printf( " 1. Clustal format / Sorted\n" ) > "/dev/tty"; + printf( " 2. Clustal format / Input order\n" ) > "/dev/tty"; + printf( " 3. Fasta format / Sorted\n" ) > "/dev/tty"; + printf( " 4. Fasta format / Input order\n" ) > "/dev/tty"; + printf( " 5. Phylip format / Sorted\n" ) > "/dev/tty"; + printf( " 6. Phylip format / Input order\n" ) > "/dev/tty"; + printf( "@ " ) > "/dev/tty"; + res = getline < "/dev/tty"; + close( "/dev/tty" ); +# printf( "res=%d, NF=%d\n", res, NF ); + + resnum = 0 + $1; +# printf( "resnum=%d\n", resnum ); + + if( resnum < 1 || 6 < resnum ) + continue; + else + { + if( resnum == 1 ) + outargs = "--clustalout --reorder"; + else if( resnum == 2 ) + outargs = "--clustalout --inputorder"; + else if( resnum == 3 ) + outargs = "--reorder"; + else if( resnum == 4 ) + outargs = "--inputorder"; + else if( resnum == 5 ) + outargs = "--phylipout --reorder"; + else if( resnum == 6 ) + outargs = "--phylipout --inputorder"; + else + continue; + printf( "OK. arguments = %s\n\n", outargs ) > "/dev/tty"; + break; + } + } + + while( 1 ) + { + arguments = ""; + printf( "\n" ) > "/dev/tty"; + printf( "Strategy?\n" ) > "/dev/tty"; + printf( " 1. --auto\n" ) > "/dev/tty"; + printf( " 2. FFT-NS-1 (fast)\n" ) > "/dev/tty"; + printf( " 3. FFT-NS-2 (default)\n" ) > "/dev/tty"; + printf( " 4. G-INS-i (accurate)\n" ) > "/dev/tty"; + printf( " 5. L-INS-i (accurate)\n" ) > "/dev/tty"; + printf( " 6. E-INS-i (accurate)\n" ) > "/dev/tty"; + printf( "@ " ) > "/dev/tty"; + res = getline < "/dev/tty"; + close( "/dev/tty" ); +# printf( "res=%d, NF=%d\n", res, NF ); + + resnum = 0 + $1; +# printf( "resnum=%d\n", resnum ); + + if( resnum < 1 || 6 < resnum ) + continue; + else + { + if( resnum == 1 ) + arguments = "--auto"; + else if( resnum == 2 ) + arguments = "--retree 1"; + else if( resnum == 3 ) + arguments = "--retree 2"; + else if( resnum == 4 ) + arguments = "--globalpair --maxiterate 16"; + else if( resnum == 5 ) + arguments = "--localpair --maxiterate 16"; + else if( resnum == 6 ) + arguments = "--genafpair --maxiterate 16"; + else + arguments = sprintf( "%s", $0 ); + printf( "OK. arguments = %s %s\n\n", arguments, outargs ) > "/dev/tty"; + break; + } + } + + + while( 1 ) + { + printf( "\n" ) > "/dev/tty"; + printf( "Additional arguments? (--ep #, --op #, --kappa #, etc)\n" ) > "/dev/tty"; + printf( "@ " ) > "/dev/tty"; + res = getline < "/dev/tty"; + close( "/dev/tty" ); + if( res == 0 || NF == 0 ) + { + break; + } + else + { + addargs = sprintf( "%s", $0 ); + printf( "OK. arguments = %s %s %s\n\n", addargs, arguments, outargs ) > "/dev/tty"; + break; + } + } + + arguments = sprintf( "%s %s %s", addargs, arguments, outargs ); + + print "" + command = sprintf( "\"%s\" %s \"%s\" > \"%s\"", myself, arguments, infile, outfile ); + gsub( /\\/, "/", command ); + + + printf( "command=\n%s\n", command ) > "/dev/tty"; + + + while( 1 ) + { + go = 0; + printf( "OK?\n" ) > "/dev/tty"; + printf( "@ [Y] " ) > "/dev/tty"; + res = getline < "/dev/tty"; + close( "/dev/tty" ); + if( res == 0 ) + continue; + else if( NF == 0 || $0 ~ /^[Yy]/ ) + { + go=1; + break; + } + else + break; + } + if( go ) break; + printf( "\n" ) > "/dev/tty"; + printf( "\n" ) > "/dev/tty"; + } + system( command ); + command = sprintf( "less \"%s\"", outfile ); + system( command ); + printf( "Press Enter to exit." ) > "/dev/tty"; + res = getline < "/dev/tty"; +} +' +) +exit 0; diff --git a/binaries/linuxAMD64/mafft/mafft-distance b/binaries/linuxAMD64/mafft/mafft-distance index 59add95..b4f35d7 100644 Binary files a/binaries/linuxAMD64/mafft/mafft-distance and b/binaries/linuxAMD64/mafft/mafft-distance differ diff --git a/binaries/linuxAMD64/mafft/mafft-homologs.rb b/binaries/linuxAMD64/mafft/mafft-homologs.rb new file mode 100644 index 0000000..c1a2468 --- /dev/null +++ b/binaries/linuxAMD64/mafft/mafft-homologs.rb @@ -0,0 +1,374 @@ +#!/usr/bin/env ruby + +localdb = "sp" +# database name from which homologues are collected +# by locally installed blast. Leave this if you do +# not use the '-l' option. + +mafftpath = "/usr/bin/mafft" +# path of mafft. "/usr/local/bin/mafft" +# if mafft is in your command path, "mafft" is ok. + +blastpath = "blastall" +# path of blastall. +# if blastall is in your command path, "blastall" is ok. + +# mafft-homologs.rb v. 2.1 aligns sequences together with homologues +# automatically collected from SwissProt via NCBI BLAST. +# +# mafft > 5.58 is required +# +# Usage: +# mafft-homologs.rb [options] input > output +# Options: +# -a # the number of collected sequences (default: 50) +# -e # threshold value (default: 1e-10) +# -o "xxx" options for mafft +# (default: " --op 1.53 --ep 0.123 --maxiterate 1000") +# -l locally carries out blast searches instead of NCBI blast +# (requires locally installed blast and a database) +# -f outputs collected homologues also (default: off) +# -w entire sequences are subjected to BLAST search +# (default: well-aligned region only) + +require 'getopts' +require 'tempfile' + +# mktemp +GC.disable +temp_vf = Tempfile.new("_vf").path +temp_if = Tempfile.new("_if").path +temp_pf = Tempfile.new("_pf").path +temp_af = Tempfile.new("_af").path +temp_qf = Tempfile.new("_qf").path +temp_bf = Tempfile.new("_bf").path +temp_rid = Tempfile.new("_rid").path +temp_res = Tempfile.new("_res").path + + +system( mafftpath + " --help > #{temp_vf} 2>&1" ) +pfp = File.open( "#{temp_vf}", 'r' ) +while pfp.gets + break if $_ =~ /MAFFT v/ +end +pfp.close +if( $_ ) then + mafftversion = sub( /^\D*/, "" ).split(" ").slice(0).strip.to_s +else + mafftversion = "0" +end +if( mafftversion < "5.58" ) then + puts "" + puts "======================================================" + puts "Install new mafft (v. >= 5.58)" + puts "======================================================" + puts "" + exit +end + +srand ( 0 ) + +def readfasta( fp, name, seq ) + nseq = 0 + tmpseq = "" + while fp.gets + if $_ =~ /^>/ then + name.push( $_.sub(/>/,"").strip ) + seq.push( tmpseq ) if nseq > 0 + nseq += 1 + tmpseq = "" + else + tmpseq += $_.strip + end + end + seq.push( tmpseq ) + return nseq +end + +nadd = 50 +eval = 1e-10 +local = 0 +fullout = 0 +entiresearch = 0 +corewin = 50 +corethr = 0.3 +mafftopt = " --op 1.53 --ep 0.123 --localpair --maxiterate 1000 --reorder " +if getopts( "s", "f", "w", "l", "h", "e:", "a:", "o:", "c:", "d:" ) == nil || ARGV.length == 0 || $OPT_h then + puts "Usage: #{$0} [-h -l -e# -a# -o\"[options for mafft]\"] input_file" + exit +end + +if $OPT_c then + corewin = $OPT_c.to_i +end +if $OPT_d then + corethr = $OPT_d.to_f +end +if $OPT_w + entiresearch = 1 +end +if $OPT_f + fullout = 1 +end +if $OPT_s + fullout = 0 +end +if $OPT_l + local = 1 +end +if $OPT_e then + eval = $OPT_e.to_f +end +if $OPT_a then + nadd = $OPT_a.to_i +end +if $OPT_o then + mafftopt += " " + $OPT_o + " " +end + +system "cat " + ARGV.to_s + " > #{temp_if}" +ar = mafftopt.split(" ") +nar = ar.length +for i in 0..(nar-1) + if ar[i] == "--seed" then + system "cat #{ar[i+1]} >> #{temp_if}" + end +end + +nseq = 0 +ifp = File.open( "#{temp_if}", 'r' ) + while ifp.gets + nseq += 1 if $_ =~ /^>/ + end +ifp.close + +if nseq >= 100 then + STDERR.puts "The number of input sequences must be <100." + exit +elsif nseq == 1 then + system( "cp #{temp_if}" + " #{temp_pf}" ) +else + STDERR.puts "Performing preliminary alignment .. " + if entiresearch == 1 then +# system( mafftpath + " --maxiterate 1000 --localpair #{temp_if} > #{temp_pf}" ) + system( mafftpath + " --maxiterate 0 --retree 2 #{temp_if} > #{temp_pf}" ) + else + system( mafftpath + " --maxiterate 1000 --localpair --core --coreext --corethr #{corethr.to_s} --corewin #{corewin.to_s} #{temp_if} > #{temp_pf}" ) + end +end + +pfp = File.open( "#{temp_pf}", 'r' ) +inname = [] +inseq = [] +slen = [] +act = [] +nin = 0 +nin = readfasta( pfp, inname, inseq ) +for i in 0..(nin-1) + slen.push( inseq[i].gsub(/-/,"").length ) + act.push( 1 ) +end +pfp.close + +pfp = File.open( "#{temp_if}", 'r' ) +orname = [] +orseq = [] +nin = 0 +nin = readfasta( pfp, orname, orseq ) +pfp.close + +allen = inseq[0].length +for i in 0..(nin-2) + for j in (i+1)..(nin-1) + next if act[i] == 0 + next if act[j] == 0 + pid = 0.0 + total = 0 + for a in 0..(allen-1) + next if inseq[i][a,1] == "-" || inseq[j][a,1] == "-" + total += 1 + pid += 1.0 if inseq[i][a,1] == inseq[j][a,1] + end + pid /= total +# puts "#{i.to_s}, #{j.to_s}, #{pid.to_s}" + if pid > 0.5 then + if slen[i] < slen[j] + act[i] = 0 + else + act[j] = 0 + end + end + end +end +#p act + + +afp = File.open( "#{temp_af}", 'w' ) + +STDERR.puts "Searching .. \n" +ids = [] +add = [] +sco = [] +for i in 0..(nin-1) + inseq[i].gsub!(/-/,"") + afp.puts ">" + orname[i] + afp.puts orseq[i] + +# afp.puts ">" + inname[i] +# afp.puts inseq[i] + + STDERR.puts "Query (#{i+1}/#{nin})\n" + inname[i] + if act[i] == 0 then + STDERR.puts "Skip.\n\n" + next + end + + if local == 0 then + command = "lynx -source 'http://www.ncbi.nlm.nih.gov/blast/Blast.cgi?QUERY=" + inseq[i] + "&DATABASE=swissprot&HITLIST_SIZE=" + nadd.to_s + "&FILTER=L&EXPECT='" + eval.to_s + "'&FORMAT_TYPE=TEXT&PROGRAM=blastp&SERVICE=plain&NCBI_GI=on&PAGE=Proteins&CMD=Put' > #{temp_rid}" + system command + + ridp = File.open( "#{temp_rid}", 'r' ) + while ridp.gets + break if $_ =~ / RID = (.*)/ + end + ridp.close + rid = $1.strip + STDERR.puts "Submitted to NCBI. rid = " + rid + + STDERR.printf "Waiting " + while 1 + STDERR.printf "." + sleep 10 + command = "lynx -source 'http://www.ncbi.nlm.nih.gov/blast/Blast.cgi?RID=" + rid + "&DESCRIPTIONS=500&ALIGNMENTS=" + nadd.to_s + "&ALIGNMENT_TYPE=Pairwise&OVERVIEW=no&CMD=Get&FORMAT_TYPE=XML' > #{temp_res}" + system command + resp = File.open( "#{temp_res}", 'r' ) +# resp.gets +# if $_ =~ /WAITING/ then +# resp.close +# next +# end + while( resp.gets ) + break if $_ =~ /QBlastInfoBegin/ + end + resp.gets + if $_ =~ /WAITING/ then + resp.close + next + else + resp.close + break + end + end + else +# puts "Not supported" +# exit + qfp = File.open( "#{temp_qf}", 'w' ) + qfp.puts "> " + qfp.puts inseq[i] + qfp.close + command = blastpath + " -p blastp -e #{eval} -b 1000 -m 7 -i #{temp_qf} -d #{localdb} > #{temp_res}" + system command + resp = File.open( "#{temp_res}", 'r' ) + end + STDERR.puts " Done.\n\n" + + resp = File.open( "#{temp_res}", 'r' ) + while 1 + while resp.gets + break if $_ =~ /(.*)<\/Hit_id>/ || $_ =~ /()/ + end + id = $1 + break if $_ =~ // +# p id + while resp.gets + break if $_ =~ /(.*)<\/Hsp_bit-score>/ + end + score = $1.to_f +# p score + + known = ids.index( id ) + if known != nil then + if sco[known] >= score then + next + else + ids.delete_at( known ) + add.delete_at( known ) + sco.delete_at( known ) + end + end + while resp.gets + break if $_ =~ /(.*)<\/Hsp_hseq>/ + end +# break if $1 == nil + target = $1.sub( /-/, "" ).sub( /U/, "X" ) +# p target +# STDERR.puts "adding 1 seq" + ids.push( id ) + sco.push( score ) + add.push( target ) + end + resp.close +end + +n = ids.length + +outnum = 0 +while n > 0 && outnum < nadd + m = rand( n ) + afp.puts ">_addedbymaffte_" + ids[m] + afp.puts add[m] + ids.delete_at( m ) + add.delete_at( m ) + n -= 1 + outnum += 1 +end +afp.close + +STDERR.puts "Performing alignment .. " +system( mafftpath + mafftopt + " #{temp_af} > #{temp_bf}" ) +STDERR.puts "done." + +bfp = File.open( "#{temp_bf}", 'r' ) +outseq = [] +outnam = [] +readfasta( bfp, outnam, outseq ) +bfp.close + +outseq2 = [] +outnam2 = [] + +len = outseq.length +for i in 0..(len-1) +# p outnam[i] + if fullout == 0 && outnam[i] =~ /_addedbymaffte_/ then + next + end + outseq2.push( outseq[i] ) + outnam2.push( outnam[i].sub( /_addedbymaffte_/, "_ho_" ) ) +end + +nout = outseq2.length +len = outseq[0].length +p = len +while p>0 + p -= 1 + allgap = 1 + for j in 0..(nout-1) + if outseq2[j][p,1] != "-" then + allgap = 0 + break + end + end + if allgap == 1 then + for j in 0..(nout-1) + outseq2[j][p,1] = "" + end + end +end +for i in 0..(nout-1) + puts ">" + outnam2[i] + puts outseq2[i].gsub( /.{1,60}/, "\\0\n" ) +end + + +system( "rm -rf #{temp_if} #{temp_vf} #{temp_af} #{temp_bf} #{temp_pf} #{temp_qf} #{temp_res} #{temp_rid}" ) diff --git a/binaries/linuxAMD64/mafft/mafft-profile b/binaries/linuxAMD64/mafft/mafft-profile index ddf711a..06f69b1 100644 Binary files a/binaries/linuxAMD64/mafft/mafft-profile and b/binaries/linuxAMD64/mafft/mafft-profile differ diff --git a/binaries/linuxAMD64/mafft/mafft.1 b/binaries/linuxAMD64/mafft/mafft.1 index 87ac748..8636334 100644 --- a/binaries/linuxAMD64/mafft/mafft.1 +++ b/binaries/linuxAMD64/mafft/mafft.1 @@ -1,5 +1,5 @@ .\" Title: MAFFT -.\" Author: Kazutaka Katoh +.\" Author: Kazutaka Katoh .\" Generator: DocBook XSL Stylesheets v1.72.0 .\" Date: 2007-08-14 .\" Manual: Mafft Manual @@ -10,8 +10,13 @@ .nh .\" disable justification (adjust text to left margin only) .ad l +.SH "THIS MANUAL IS FOR V6.2XX (2007)" +Recent versions (v6.8xx; 2010 Nov.) have more features than those described below. +See also the tips page at +http://mafft.cbrc.jp/alignment/software/tips0.html .SH "NAME" .RS 0 +.sp mafft \- Multiple alignment program for amino acid or nucleotide sequences .RE .SH "SYNOPSIS" @@ -198,7 +203,7 @@ FASTA is required. Default: off (6mer distance is used) \fB\-\-weighti\fR \fInumber\fR .RS 4 Weighting factor for the consistency term calculated from pairwise alignments. Valid when -either of \-\-blobalpair, \-\-localpair, \-\-genafpair, \-\-fastapair or +either of \-\-globalpair, \-\-localpair, \-\-genafpair, \-\-fastapair or \-\-blastpair is selected. Default: 2.7 .RE .PP @@ -273,7 +278,7 @@ Gap opening penalty at group\-to\-group alignment. Default: 1.53 \fB\-\-ep\fR \fInumber\fR .RS 4 Offset value, which works like gap extension penalty, for -group\-to\-group alignment. Deafult: 0.123 +group\-to\-group alignment. Default: 0.123 .RE .PP \fB\-\-lop\fR \fInumber\fR @@ -331,7 +336,7 @@ the same to that of BLAST. Ignored when nucleotide sequences are input. Defau \fB\-\-fmodel\fR .RS 4 Incorporate the AA/nuc composition information into -the scoring matrix. Deafult: off +the scoring matrix. Default: off .RE .RE .SS "Output" @@ -367,12 +372,12 @@ Do not report progress. Default: off .PP \fB\-\-nuc\fR .RS 4 -Assume the sequences are nucleotide. Deafult: auto +Assume the sequences are nucleotide. Default: auto .RE .PP \fB\-\-amino\fR .RS 4 -Assume the sequences are amino acid. Deafult: auto +Assume the sequences are amino acid. Default: auto .RE .PP \fB\-\-seed\fR \fIalignment1\fR [\fB--seed\fR \fIalignment2\fR \fB--seed\fR \fIalignment3\fR ...] @@ -436,7 +441,7 @@ This variable can be set to indicate to mafft the location to the fasta34 progra .SH "AUTHORS" .RS 0 .PP -\fBKazutaka Katoh\fR <\&katoh_at_bioreg.kyushu\-u.ac.jp\&> +\fBKazutaka Katoh\fR <\&kazutaka.katoh_at_aist.go.jp\&> .sp -1n .IP "" 4 Wrote Mafft. diff --git a/binaries/linuxAMD64/mafft/mccaskillwrap b/binaries/linuxAMD64/mafft/mccaskillwrap index b629a19..7e9a3b2 100644 Binary files a/binaries/linuxAMD64/mafft/mccaskillwrap and b/binaries/linuxAMD64/mafft/mccaskillwrap differ diff --git a/binaries/linuxAMD64/mafft/multi2hat3s b/binaries/linuxAMD64/mafft/multi2hat3s index f0eaf68..fc7d2fc 100644 Binary files a/binaries/linuxAMD64/mafft/multi2hat3s and b/binaries/linuxAMD64/mafft/multi2hat3s differ diff --git a/binaries/linuxAMD64/mafft/mxscarnamod b/binaries/linuxAMD64/mafft/mxscarnamod index c4086bf..7111459 100644 Binary files a/binaries/linuxAMD64/mafft/mxscarnamod and b/binaries/linuxAMD64/mafft/mxscarnamod differ diff --git a/binaries/linuxAMD64/mafft/pair2hat3s b/binaries/linuxAMD64/mafft/pair2hat3s index cc9dfe1..9921054 100644 Binary files a/binaries/linuxAMD64/mafft/pair2hat3s and b/binaries/linuxAMD64/mafft/pair2hat3s differ diff --git a/binaries/linuxAMD64/mafft/pairash b/binaries/linuxAMD64/mafft/pairash index 28f8330..4bd88e5 100644 Binary files a/binaries/linuxAMD64/mafft/pairash and b/binaries/linuxAMD64/mafft/pairash differ diff --git a/binaries/linuxAMD64/mafft/pairlocalalign b/binaries/linuxAMD64/mafft/pairlocalalign index 0a99073..570cb5d 100644 Binary files a/binaries/linuxAMD64/mafft/pairlocalalign and b/binaries/linuxAMD64/mafft/pairlocalalign differ diff --git a/binaries/linuxAMD64/mafft/regtable2seq b/binaries/linuxAMD64/mafft/regtable2seq index 2224dff..724a475 100644 Binary files a/binaries/linuxAMD64/mafft/regtable2seq and b/binaries/linuxAMD64/mafft/regtable2seq differ diff --git a/binaries/linuxAMD64/mafft/replaceu b/binaries/linuxAMD64/mafft/replaceu new file mode 100644 index 0000000..7be4453 Binary files /dev/null and b/binaries/linuxAMD64/mafft/replaceu differ diff --git a/binaries/linuxAMD64/mafft/restoreu b/binaries/linuxAMD64/mafft/restoreu new file mode 100644 index 0000000..4fb4424 Binary files /dev/null and b/binaries/linuxAMD64/mafft/restoreu differ diff --git a/binaries/linuxAMD64/mafft/rnatest b/binaries/linuxAMD64/mafft/rnatest index cb3e8ae..eff3b0a 100644 Binary files a/binaries/linuxAMD64/mafft/rnatest and b/binaries/linuxAMD64/mafft/rnatest differ diff --git a/binaries/linuxAMD64/mafft/score b/binaries/linuxAMD64/mafft/score index 4298283..af81a10 100644 Binary files a/binaries/linuxAMD64/mafft/score and b/binaries/linuxAMD64/mafft/score differ diff --git a/binaries/linuxAMD64/mafft/seq2regtable b/binaries/linuxAMD64/mafft/seq2regtable index befc9ba..9d78d9c 100644 Binary files a/binaries/linuxAMD64/mafft/seq2regtable and b/binaries/linuxAMD64/mafft/seq2regtable differ diff --git a/binaries/linuxAMD64/mafft/setcore b/binaries/linuxAMD64/mafft/setcore index 89cd961..3528923 100644 Binary files a/binaries/linuxAMD64/mafft/setcore and b/binaries/linuxAMD64/mafft/setcore differ diff --git a/binaries/linuxAMD64/mafft/sextet5 b/binaries/linuxAMD64/mafft/sextet5 index 5ee262f..9573728 100644 Binary files a/binaries/linuxAMD64/mafft/sextet5 and b/binaries/linuxAMD64/mafft/sextet5 differ diff --git a/binaries/linuxAMD64/mafft/splittbfast b/binaries/linuxAMD64/mafft/splittbfast index f9e76d7..419a7f2 100644 Binary files a/binaries/linuxAMD64/mafft/splittbfast and b/binaries/linuxAMD64/mafft/splittbfast differ diff --git a/binaries/linuxAMD64/mafft/tbfast b/binaries/linuxAMD64/mafft/tbfast index 10d1246..c3fe683 100644 Binary files a/binaries/linuxAMD64/mafft/tbfast and b/binaries/linuxAMD64/mafft/tbfast differ