Adding EMBOSS v5 tools coderet cpgplot diffseq digest dotmatcher dotpath dottup dreg and associated wrapper files

This commit is contained in:
Chinmay Rao
2007-12-17 13:58:30 +00:00
parent 737bdf23f9
commit d009d08342
9 changed files with 361 additions and 0 deletions
+70
View File
@@ -0,0 +1,70 @@
<tool id="EMBOSS_coderet13" name="coderet">
<description>Extract CDS, mRNA and translations from feature tables</description>
<!-- <command>coderet -seqall $input1 -outfile $out_file1 -osformat2 $out_format1 -cds $cds -mrna $mrna -translation $translation -auto</command>-->
<command>coderet -seqall $input1 -outfile $out_file1 -auto</command>
<inputs>
<param format="data" name="input1" type="data">
<label>On query</label>
</param>
<!-- <param name="cds" type="boolean" truevalue="yes" falsevalue="no" checked="true">
<label>Extract CDS sequences</label>
</param>
<param name="mrna" type="select">
<label>Extract mRNA sequences</label>
<option value="yes">Yes</option>
<option value="no">No</option>
</param>
<param name="translation" type="select">
<label>Extract translated sequences</label>
<option value="yes">Yes</option>
<option value="no">No</option>
</param>
<param name="out_format1" type="select">
<label>Output Sequence File Format</label>
<option value="fasta">FASTA (m)</option>
<option value="acedb">ACeDB (m)</option>
<option value="asn1">ASN.1 (m)</option>
<option value="clustal">Clustal (m)</option>
<option value="codata">CODATA (m)</option>
<option value="embl">EMBL (m)</option>
<option value="fitch">Fitch (m)</option>
<option value="gcg">Wisconsin Package GCG 9.x and 10.x (s)</option>
<option value="genbank">GENBANK (m)</option>
<option value="gff">GFF (m)</option>
<option value="hennig86">Hennig86 (m)</option>
<option value="ig">Intelligenetics (m)</option>
<option value="jackknifer">Jackknifer (m)</option>
<option value="jackknifernon">Jackknifernon (m)</option>
<option value="mega">Mega (m)</option>
<option value="meganon">Meganon (m)</option>
<option value="msf">Wisconsin Package GCG's MSF (m)</option>
<option value="pir">NBRF (PIR) (m)</option>
<option value="ncbi">NCBI style FASTA (m)</option>
<option value="nexus">Nexus/PAUP (m)</option>
<option value="nexusnon">Nexusnon/PAUPnon (m)</option>
<option value="phylip">PHYLIP interleaved (m)</option>
<option value="phylipnon">PHYLIP non-interleaved (m)</option>
<option value="selex">SELEX (m)</option>
<option value="staden">Staden (s)</option>
<option value="strider">DNA strider (m)</option>
<option value="swiss">SwisProt entry (m)</option>
<option value="text">Plain sequence (s)</option>
<option value="treecon">Treecon (m)</option>
</param> -->
</inputs>
<outputs>
<data format="coderet" name="out_file1" />
</outputs>
<tests>
<test>
<param name="input1" value="2.fasta"/>
<output name="out_file1" file="emboss_coderet_out.coderet"/>
</test>
</tests>
<code file="emboss_format_corrector.py" />
<help>
You can view the original documentation here_.
.. _here: http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/coderet.html
</help>
</tool>
+42
View File
@@ -0,0 +1,42 @@
<tool id="EMBOSS_cpgplot15" name="cpgplot">
<description>Plot CpG rich areas</description>
<command interpreter="perl">emboss_cpgplot_wrapper.pl cpgplot -sequence $input1 -window $window -minlen $minlen -minpc $minpc -outfile $out_file1 -graph png -goutfile3 $out_file2
-outfeat $out_file3 -offormat4 $out_format3 -minoe $minoe -auto</command>
<inputs>
<param format="data" name="input1" type="data">
<label>On query</label>
</param>
<param name="window" size="4" type="text" value="100">
<label>Window Size</label>
</param>
<!-- <param name="shift" size="4" type="text" value="1">
<label>Step size (shift)</label>
</param> -->
<param name="minlen" size="4" type="text" value="200">
<label>Minimum length</label>
</param>
<param name="minoe" size="4" type="text" value="0.6">
<label>Minimum average observed to expected ratio</label>
</param>
<param name="minpc" size="4" type="text" value="50.0">
<label>Minimum average percentage of G plus C</label>
</param>
<param name="out_format3" type="select">
<label>Output Feature File Format</label>
<option value="gff">GFF</option>
<option value="embl">EMBL</option>
<option value="swiss">SwissProt</option>
</param>
</inputs>
<outputs>
<data format="txt" name="out_file1" />
<data format="png" name="out_file2" />
<data format="gff" name="out_file3" />
</outputs>
<code file="emboss_format_corrector.py" />
<help>
You can view the original documentation here_.
.. _here: http://emboss.sourceforge.net/apps/release/4.0/emboss/apps/cpgplot.html
</help>
</tool>
+9
View File
@@ -0,0 +1,9 @@
#! /usr/bin/perl -w
use strict;
use File::Copy;
my $cmd_string = join (" ",@ARGV);
my $results = `$cmd_string`;
my @files = split("\n",$results);
my $fileNameOut = $ARGV[16];
move($fileNameOut.".1.png",$fileNameOut);
+63
View File
@@ -0,0 +1,63 @@
<tool id="EMBOSS_diffseq22" name="diffseq">
<description>Find differences between nearly identical sequences</description>
<command>diffseq -asequence $input1 -bsequence $input2 -outfile $out_file1 -aoutfeat $out_file2 -boutfeat $out_file3 -wordsize $wordsize -globaldifferences $globaldifferences -rformat3
$out_format1 -offormat4 $out_format2 -offormat5 $out_format3 -auto</command>
<inputs>
<param format="data" name="input1" type="data">
<label>Sequence 1</label>
</param>
<param format="data" name="input2" type="data">
<label>Sequence 2</label>
</param>
<param name="wordsize" size="4" type="text" value="20">
<label>Wordsize</label>
</param>
<param name="globaldifferences" type="select">
<label>Report differences at the ends</label>
<option value="no">No</option>
<option value="yes">Yes</option>
</param>
<param name="out_format1" type="select">
<label>Output Report File Format</label>
<option value="diffseq">Diffseq</option>
<option value="embl">EMBL</option>
<option value="genbank">GENBANK</option>
<option value="gff">GFF</option>
<option value="pir">PIR</option>
<option value="swiss">SwissProt</option>
<option value="dbmotif">DbMotif</option>
<option value="excel">Excel (tab delimited)</option>
<option value="feattable">FeatTable</option>
<option value="motif">Motif</option>
<option value="regions">Regions</option>
<option value="seqtable">SeqTable</option>
<option value="simple">SRS Simple</option>
<option value="srs">SRS</option>
<option value="table">Table</option>
<option value="tagseq">TagSeq</option>
</param>
<param name="out_format2" type="select">
<label>Sequence 1 Output Feature File Format</label>
<option value="gff">GFF</option>
<option value="embl">EMBL</option>
<option value="swiss">SwissProt</option>
</param>
<param name="out_format3" type="select">
<label>Sequence 2 Output Feature File Format</label>
<option value="gff">GFF</option>
<option value="embl">EMBL</option>
<option value="swiss">SwissProt</option>
</param>
</inputs>
<outputs>
<data format="diffseq" name="out_file1" />
<data format="gff" name="out_file2" />
<data format="gff" name="out_file3" />
</outputs>
<code file="emboss_format_corrector.py" />
<help>
You can view the original documentation here_.
.. _here: http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/diffseq.html
</help>
</tool>
+64
View File
@@ -0,0 +1,64 @@
<tool id="EMBOSS_digest23" name="digest">
<description>Protein proteolytic enzyme or reagent cleavage digest</description>
<command>digest -sequence $input1 -outfile $out_file1 -menu $menu -unfavoured $unfavoured -overlap $overlap -allpartials $allpartials -rformat2 $out_format1 -auto</command>
<inputs>
<param format="data" name="input1" type="data">
<label>Sequence</label>
</param>
<param name="menu" type="select">
<label>Enzyme/Reagent</label>
<option value="1">Trypsin</option>
<option value="2">Lys-C</option>
<option value="3">Arg-C</option>
<option value="4">Asp-N</option>
<option value="5">V8-bicarb</option>
<option value="6">V8-phosph</option>
<option value="7">Chymotrypsin</option>
<option value="8">CNBr</option>
</param>
<param name="unfavoured" type="select">
<label>Trypsin will not normally cut after a K if it is followed by (e.g.) another K or a P. Specifying this shows those cuts, as well as the favoured ones.</label>
<option value="no">No</option>
<option value="yes">Yes</option>
</param>
<param name="overlap" type="select">
<label>Used for partial digestion. Shows all cuts from favoured cut sites plus 1..3, 2..4, 3..5 etc but not (e.g.) 2..5. Overlaps are therefore fragments with exactly one potential cut site
within it.</label>
<option value="no">No</option>
<option value="yes">Yes</option>
</param>
<param name="allpartials" type="select">
<label>As for overlap but fragments containing more than one potential cut site are included.</label>
<option value="no">No</option>
<option value="yes">Yes</option>
</param>
<param name="out_format1" type="select">
<label>Output Report File Format</label>
<option value="seqtable">SeqTable</option>
<option value="embl">EMBL</option>
<option value="genbank">GENBANK</option>
<option value="gff">GFF</option>
<option value="pir">PIR</option>
<option value="swiss">SwissProt</option>
<option value="dbmotif">DbMotif</option>
<option value="diffseq">Diffseq</option>
<option value="excel">Excel (tab delimited)</option>
<option value="feattable">FeatTable</option>
<option value="motif">Motif</option>
<option value="regions">Regions</option>
<option value="simple">SRS Simple</option>
<option value="srs">SRS</option>
<option value="table">Table</option>
<option value="tagseq">TagSeq</option>
</param>
</inputs>
<outputs>
<data format="digest" name="out_file1" />
</outputs>
<code file="emboss_format_corrector.py" />
<help>
You can view the original documentation here_.
.. _here: http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/digest.html
</help>
</tool>
+28
View File
@@ -0,0 +1,28 @@
<tool id="EMBOSS_dotmatcher24" name="dotmatcher">
<description>Displays a thresholded dotplot of two sequences</description>
<command interpreter="perl">emboss_single_outputfile_wrapper.pl dotmatcher -asequence $input1 -bsequence $input2 -goutfile $out_file1 -windowsize $windowsize -threshold $threshold -graph png -xygraph png
-auto</command>
<inputs>
<param format="data" name="input1" type="data">
<label>Sequence 1</label>
</param>
<param format="data" name="input2" type="data">
<label>Sequence 2</label>
</param>
<param name="windowsize" size="4" type="text" value="10">
<label>Window size</label>
</param>
<param name="threshold" size="4" type="text" value="23">
<label>Threshold</label>
</param>
</inputs>
<outputs>
<data format="png" name="out_file1" />
</outputs>
<!-- functional tests not possible since image output contains file name information and timestamp -->
<help>
You can view the original documentation here_.
.. _here: http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/dotmatcher.html
</help>
</tool>
+35
View File
@@ -0,0 +1,35 @@
<tool id="EMBOSS: dotpath25" name="dotpath">
<description>Non-overlapping wordmatch dotplot of two sequences</description>
<command interpreter="perl">emboss_single_outputfile_wrapper.pl dotpath -asequence $input1 -bsequence $input2 -goutfile $out_file1 -wordsize $wordsize -overlaps $overlaps -boxit $boxit -graph png
-auto</command>
<inputs>
<param format="data" name="input1" type="data">
<label>Sequence 1</label>
</param>
<param format="data" name="input2" type="data">
<label>Sequence 2</label>
</param>
<param name="wordsize" size="4" type="text" value="4">
<label>Word size (Integer 2 or more)</label>
</param>
<param name="overlaps" type="select">
<label>Display the overlapping matches (in red) as well as the minimal set of non-overlapping matches</label>
<option value="no">No</option>
<option value="yes">Yes</option>
</param>
<param name="boxit" type="select">
<label>Draw a box around dotplot</label>
<option value="yes">Yes</option>
<option value="no">No</option>
</param>
</inputs>
<outputs>
<data format="png" name="out_file1" />
</outputs>
<!-- functional tests not possible since image output contains file name information and timestamp -->
<help>
You can view the original documentation here_.
.. _here: http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/dotpath.html
</help>
</tool>
+29
View File
@@ -0,0 +1,29 @@
<tool id="EMBOSS_dottup26" name="dottup">
<description>Displays a wordmatch dotplot of two sequences</description>
<command interpreter="perl">emboss_single_outputfile_wrapper.pl dottup -asequence $input1 -bsequence $input2 -goutfile $out_file1 -wordsize $wordsize -boxit $boxit -graph png -xygraph png -auto</command>
<inputs>
<param format="data" name="input1" type="data">
<label>Sequence 1</label>
</param>
<param format="data" name="input2" type="data">
<label>Sequence 2</label>
</param>
<param name="wordsize" size="4" type="text" value="4">
<label>Word size</label>
</param>
<param name="boxit" type="select">
<label>Draw a box around dotplot</label>
<option value="yes">Yes</option>
<option value="no">No</option>
</param>
</inputs>
<outputs>
<data format="png" name="out_file1" />
</outputs>
<!-- functional tests not possible since image output contains file name information and timestamp -->
<help>
You can view the original documentation here_.
.. _here: http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/dottup.html
</help>
</tool>
+21
View File
@@ -0,0 +1,21 @@
<tool id="EMBOSS_dreg27" name="dreg">
<description>Regular expression search of a nucleotide sequence</description>
<command>dreg -sequence $input1 -outfile $out_file1 -pattern "$pattern" -raccshow3 "no" -rusashow3 "no" -rdesshow3 "no" -auto</command>
<inputs>
<param format="data" name="input1" type="data">
<label>Sequence 1</label>
</param>
<param name="pattern" size="50" type="text" value="(AUG)">
<label>Regular expression pattern</label>
</param>
</inputs>
<outputs>
<data format="dreg" name="out_file1" />
</outputs>
<!-- tests not possible since dreg timestamps output file -->
<help>
You can view the original documentation here_.
.. _here: http://emboss.sourceforge.net/apps/release/5.0/emboss/apps/dreg.html
</help>
</tool>