Mercurial > repos > devteam > clustalw

changeset 3:d6694932c5e0 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/clustalw commit 31dd2ec1d105282421df5d6801c65cdcfd589f59
author devteam
date Mon, 22 May 2017 21:02:45 -0400
parents f8aad74cc8c1
children d9c2b2fde6a3
files rgClustalw.py rgClustalw.xml test-data/rgClustal_testin.dnd test-data/rgClustal_testout.log tool_dependencies.xml
diffstat 5 files changed, 119 insertions(+), 321 deletions(-) [+]
line wrap: on
line diff
--- a/rgClustalw.py	Fri Oct 09 15:45:22 2015 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,60 +0,0 @@
-"""
-rgclustalw.py
-wrapper for clustalw necessitated by bad choice of output path for .dnd file based on input file. Naughty.
-Copyright ross lazarus march 2011
-All rights reserved
-Licensed under the LGPL
-"""
-
-import sys,optparse,os,subprocess,tempfile,shutil
-
-class Clustrunner:
-    """
-    """
-    def __init__(self,opts=None):
-        self.opts = opts
-        self.iname = 'infile_copy'
-        shutil.copy(self.opts.input,self.iname) 
-
-    def run(self):
-        tlf = open(self.opts.outlog,'w')
-        cl = ['clustalw2 -INFILE=%s -OUTFILE=%s -OUTORDER=%s -TYPE=%s -OUTPUT=%s' % (self.iname,self.opts.output,self.opts.out_order,self.opts.dnarna,self.opts.outform)]
-        if self.opts.seq_range_end <> None and self.opts.seq_range_start <> None:
-            cl.append('-RANGE=%s,%s' % (self.opts.seq_range_start,self.opts.seq_range_end))
-        if self.opts.outform=='CLUSTAL' and self.opts.outseqnos <> None:
-            cl.append('-SEQNOS=ON')
-        process = subprocess.Popen(' '.join(cl), shell=True, stderr=tlf, stdout=tlf)
-        rval = process.wait()
-        dndf = '%s.dnd' % self.iname
-        if os.path.exists(dndf):
-            tlf.write('\nClustal created the following dnd file for your information:\n')
-            dnds = open('%s.dnd' % self.iname,'r').readlines()
-	    for row in dnds:
-                tlf.write(row)
-            tlf.write('\n')
-        tlf.close()
-        os.unlink(self.iname)
-    
-
-
-if __name__ == "__main__":
-    op = optparse.OptionParser()
-    op.add_option('-i', '--input', default=None)
-    op.add_option('-o', '--output', default=None)
-    op.add_option('-t', '--outname', default="rgClustal")
-    op.add_option('-s', '--out_order', default='ALIGNMENT')
-    op.add_option('-f', '--outform', default='CLUSTAL')
-    op.add_option('-e', '--seq_range_end',default=None)
-    op.add_option('-b', '--seq_range_start',default=None)
-    op.add_option('-l','--outlog',default='rgClustalw.log')
-    op.add_option('-q', '--outseqnos',default=None)    
-    op.add_option('-d', '--dnarna',default='DNA')    
-    
-    opts, args = op.parse_args()
-    assert opts.input <> None
-    assert os.path.isfile(opts.input)
-    c = Clustrunner(opts)
-    c.run()
-    
-            
-
--- a/rgClustalw.xml	Fri Oct 09 15:45:22 2015 -0400
+++ b/rgClustalw.xml	Mon May 22 21:02:45 2017 -0400
@@ -1,133 +1,110 @@
-<tool id="clustalw" name="ClustalW" version="0.1">
-   <requirements>
-      <requirement type="package" version="2.1">clustalw2</requirement>
-   </requirements>
-   <description>multiple sequence alignment program for DNA or proteins</description>
-   <command interpreter="python"> 
-    rgClustalw.py -i "$input" -o "$output" -s "$out_order" -l "$outlog" -t "$outname" -d "$dnarna"
-    #if   ($range.mode=="part")
--b "$range.seq_range_start" -e "$range.seq_range_end"
-    #end if
-    #if ($outcontrol.outform=="clustal")
--f "CLUSTAL"
-    #if ($outcontrol.out_seqnos=="ON")
--q "ON"
-    #end if
-    #end if
-    #if ($outcontrol.outform=="phylip")
--f "PHYLIP"
-    #end if
-    #if ($outcontrol.outform=="fasta")
--f "FASTA"
+<tool id="clustalw" name="ClustalW" version="2.1">
+    <description>multiple sequence alignment program for DNA or proteins</description>
+    <requirements>
+        <requirement type="package" version="2.1">clustalw</requirement>
+    </requirements>
+    <command detect_errors="exit_code"><![CDATA[
+ln -s '$input' input.fasta &&
+clustalw2 -INFILE=input.fasta -OUTFILE='$output' -OUTORDER=$out_order -TYPE=$dnarna
+#if $outcontrol.outform == "clustal"
+    -OUTPUT=CLUSTAL
+    #if $outcontrol.out_seqnos == "ON"
+        -SEQNOS=ON
     #end if
-   </command>
-  <inputs>
-   <page>
-    <param format="fasta" name="input" type="data" label="Fasta File" />
-    <param name="outname" label="Name for output files to make it easy to remember what you did" type="text" value="Clustal_run" />
-    <param name="dnarna" type="select" label="Data Type">
-      <option value="DNA" selected="True">DNA nucleotide sequences</option>
-      <option value="PROTEIN">Protein sequences</option>
-    </param>
-    <conditional name="outcontrol">
-      <param name="outform" type="select" label="Output alignment format">
-        <option value="clustal" selected="True">Native Clustal output format</option>
-        <option value="phylip">Phylip format</option>
-        <option value="fasta">Fasta format</option>
-      </param>
-      <when value="fasta" />
-      <when value="phylip" />
-      <when value="clustal">
-       <param name="out_seqnos" type="select" label="Show residue numbers in clustal format output">
-         <option value="ON">yes</option>
-         <option value="OFF" selected="true">no</option>
-       </param>
-      </when>
-    </conditional>
-    <param name="out_order" type="select" label="Output Order">
-      <option value="ALIGNED">aligned</option>
-      <option value="INPUT">same order as input file</option>
-    </param>
-
-    <conditional name="range">
-        <param name="mode" type="select" label="Output complete alignment (or specify part to output)">
-          <option value="complete">complete alignment</option>
-          <option value="part">only part of the alignment</option>
+#end if
+#if $outcontrol.outform == "phylip"
+    -OUTPUT=PHYLIP
+#end if
+#if $outcontrol.outform == "fasta"
+    -OUTPUT=FASTA
+#end if
+#if $range.mode == "part"
+    -RANGE=${range.seq_range_start},${range.seq_range_end}
+#end if
+    ]]></command>
+    <inputs>
+        <param name="input" type="data" format="fasta" label="FASTA file" />
+        <param name="dnarna" type="select" label="Data type">
+            <option value="DNA" selected="True">DNA nucleotide sequences</option>
+            <option value="PROTEIN">Protein sequences</option>
+        </param>
+        <conditional name="outcontrol">
+            <param name="outform" type="select" label="Output alignment format">
+                <option value="clustal" selected="True">Native Clustal output format</option>
+                <option value="phylip">PHYLIP format</option>
+                <option value="fasta">FASTA format</option>
+            </param>
+            <when value="fasta" />
+            <when value="phylip" />
+            <when value="clustal">
+                <param name="out_seqnos" type="boolean" truevalue="ON" falsevalue="OFF" label="Show residue numbers in clustal format output" />
+            </when>
+        </conditional>
+        <param name="out_order" type="select" label="Output order">
+            <option value="ALIGNED">Aligned</option>
+            <option value="INPUT">Same order as input file</option>
         </param>
-        <when value="complete">
-        </when>
-        <when value="part">    
-           <param name="seq_range_start" type="integer" value="1" label="start point" help="sequence range to write">
-           </param>
-           <param name="seq_range_end" type="integer" value="99999" label="end point" >
-           </param> 
-        </when>
-    </conditional>
-   </page>
-  </inputs>
-  <outputs>
-    <data format="clustal" name="output"  label="${outname}_output.${outcontrol.outform}">
-       <change_format>
-           <when input="outcontrol.outform" value="phylip" format="phylip" />
-           <when input="outcontrol.outform" value="fasta" format="fasta" />
-       </change_format>
-    </data>
-    <data format="txt" name="outlog"  label="${outname}_clustal_log.txt"/>
-  </outputs>
-  <tests>
-     <test>
-      <param name="input" value="rgClustal_testin.fasta" />
-      <param name="outname" value="" />
-      <param name="outform" value="fasta" />
-      <param name="dnarna" value="DNA" />
-      <param name="mode" value="complete" />
-      <param name="out_order" value="ALIGNED" />
-      <output name="output" file="rgClustal_testout.fasta" ftype="fasta" />
-      <output name="outlog" file="rgClustal_testout.log" ftype="txt" lines_diff="5" />
-     </test>
-  </tests>
-  <help>
-
+        <conditional name="range">
+            <param name="mode" type="select" label="Output complete alignment (or specify part to output)">
+                <option value="complete">Complete alignment</option>
+                <option value="part">Only part of the alignment</option>
+            </param>
+            <when value="complete" />
+            <when value="part">
+                <param name="seq_range_start" type="integer" value="1" label="Start point" help="Sequence range to write" />
+                <param name="seq_range_end" type="integer" value="99999" label="End point" />
+            </when>
+        </conditional>
+    </inputs>
+    <outputs>
+        <data name="output" format="clustal" label="${tool.name} on ${on_string}: ${outcontrol.outform}">
+            <change_format>
+                <when input="outcontrol.outform" value="phylip" format="phylip" />
+                <when input="outcontrol.outform" value="fasta" format="fasta" />
+            </change_format>
+        </data>
+        <data name="dnd" format="nhx" label="${tool.name} on ${on_string}: dnd" from_work_dir="input.dnd" />
+    </outputs>
+    <tests>
+        <test>
+            <param name="input" value="rgClustal_testin.fasta" />
+            <param name="outform" value="fasta" />
+            <param name="dnarna" value="DNA" />
+            <param name="mode" value="complete" />
+            <param name="out_order" value="ALIGNED" />
+            <output name="output" file="rgClustal_testout.fasta" ftype="fasta" />
+            <output name="dnd" file="rgClustal_testin.dnd" ftype="nhx" />
+        </test>
+    </tests>
+    <help><![CDATA[
 **Note**
 
-This tool allows you to run a multiple sequence alignment with ClustalW2 (see Clustsrc_) using the default options.
- 
-For a tutorial introduction, see ClustalW2_
+This tool allows you to run a multiple sequence alignment with ClustalW_ using the default options.
 
-You can align DNA or protein sequences in the input file which should be multiple sequences to be aligned in a fasta file
+You can align DNA or protein sequences in the input file which should be multiple sequences to be aligned in a FASTA file.
 
-A log will be output to your history showing the output Clustal would normally write to standard output.
-
-The alignments will appear as a clustal format file or optionally, as phylip or fasta format files in your history. If you choose fasta as 
+The alignments will appear as a clustal format file or optionally, as PHYLIP or FASTA format files in your history. If you choose FASTA as
 the output format, you can create a 'Logo' image using the Sequence Logo tool.
 
-If Clustal format is chosen, you have the option of adding basepair counts to the output
+If Clustal format is chosen, you have the option of adding basepair counts to the output.
 
-A subsequence of the alignment can be output by setting the Output complete parameter to "Partial" and defining the offset and end of the subsequence to be output 
+A subsequence of the alignment can be output by setting the Output complete parameter to "Partial" and defining the offset and end of the subsequence to be output.
 
 ----
 
 **Attribution**
 
-Clustal attribution and associated documentation are available at Clustsrc_
-
-The first iteration of this Galaxy wrapper was written by Hans-Rudolf Hotz - see Clustfirst_
+The first iteration of this Galaxy wrapper was written by Hans-Rudolf Hotz.
 
-It was modified by Ross Lazarus for the rgenetics project - tests and some additional parameters were added
-
-This wrapper is released licensed under the LGPL_
+It was modified by Ross Lazarus for the rgenetics project - tests and some additional parameters were added.
 
-.. _ClustalW2: http://www.ebi.ac.uk/2can/tutorials/protein/clustalw.html  
-
-.. _Clustsrc: http://www.clustal.org
+This wrapper is released licensed under the LGPL_.
 
-.. _Clustfirst: http://lists.bx.psu.edu/pipermail/galaxy-dev/2010-November/003732.html
+.. _ClustalW: http://www.clustal.org/clustal2/
 
-.. _LGPL: http://www.gnu.org/copyleft/lesser.html
-
-    </help>
+.. _LGPL: https://www.gnu.org/copyleft/lesser.html
+    ]]></help>
     <citations>
         <citation type="doi">10.1093/bioinformatics/btm404</citation>
     </citations>
 </tool>
-
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/rgClustal_testin.dnd	Mon May 22 21:02:45 2017 -0400
@@ -0,0 +1,31 @@
+(
+(
+c_briggsae-chrII_+_/43862-46313:0.07349,
+c_brenneri-Cbre_Contig60_+_/627772-630087:0.04317)
+:0.02387,
+(
+c_remanei-Crem_Contig172_-_/123228-124941:0.06114,
+c_elegans-II_+_/9706834-9708803:0.07219)
+:0.01779,
+(
+(
+(
+c_briggsae-chrIfooI_+_/43862-46313:0.10368,
+c_brenneri-Cbre_Contig60gak_+_/627772-630087:0.06298)
+:0.01654,
+(
+c_remanei-Crem_Contig172foo_-_/123228-124941:0.05765,
+c_elegans-II_+_more/9706834-9708803:0.05902)
+:0.06262)
+:0.31533,
+(
+(
+c_briggsae-chrII_+_bar/43862-46313:0.02327,
+c_brenneri-Cbre_Contig60fee_+_/627772-630087:0.13463)
+:0.05016,
+(
+c_remanei-Crem_Contig172zot_-_/123228-124941:0.11667,
+c_elegans-II_+_meh/9706834-9708803:0.11737)
+:0.12013)
+:0.20951)
+:0.30133);
--- a/test-data/rgClustal_testout.log	Fri Oct 09 15:45:22 2015 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,144 +0,0 @@
-
-
-
- CLUSTAL 2.1 Multiple Sequence Alignments
-
-
-Sequence type explicitly set to DNA
-Sequence format is Pearson
-Sequence 1: c_briggsae-chrII_+_/43862-46313                 60 bp
-Sequence 2: c_remanei-Crem_Contig172_-_/123228-124941       60 bp
-Sequence 3: c_brenneri-Cbre_Contig60_+_/627772-630087       60 bp
-Sequence 4: c_elegans-II_+_/9706834-9708803                 60 bp
-Sequence 5: c_briggsae-chrIfooI_+_/43862-46313              60 bp
-Sequence 6: c_remanei-Crem_Contig172foo_-_/123228-124941    60 bp
-Sequence 7: c_brenneri-Cbre_Contig60gak_+_/627772-630087    60 bp
-Sequence 8: c_elegans-II_+_more/9706834-9708803             60 bp
-Sequence 9: c_briggsae-chrII_+_bar/43862-46313              60 bp
-Sequence 10: c_remanei-Crem_Contig172zot_-_/123228-124941    60 bp
-Sequence 11: c_brenneri-Cbre_Contig60fee_+_/627772-630087    60 bp
-Sequence 12: c_elegans-II_+_meh/9706834-9708803              60 bp
-Start of Pairwise alignments
-Aligning...
-
-Sequences (1:2) Aligned. Score:  80
-Sequences (1:3) Aligned. Score:  88
-Sequences (1:4) Aligned. Score:  83
-Sequences (1:5) Aligned. Score:  21
-Sequences (1:6) Aligned. Score:  20
-Sequences (1:7) Aligned. Score:  23
-Sequences (1:8) Aligned. Score:  18
-Sequences (1:9) Aligned. Score:  21
-Sequences (1:10) Aligned. Score:  16
-Sequences (1:11) Aligned. Score:  25
-Sequences (1:12) Aligned. Score:  10
-Sequences (2:3) Aligned. Score:  85
-Sequences (2:4) Aligned. Score:  86
-Sequences (2:5) Aligned. Score:  21
-Sequences (2:6) Aligned. Score:  20
-Sequences (2:7) Aligned. Score:  25
-Sequences (2:8) Aligned. Score:  20
-Sequences (2:9) Aligned. Score:  36
-Sequences (2:10) Aligned. Score:  16
-Sequences (2:11) Aligned. Score:  22
-Sequences (2:12) Aligned. Score:  17
-Sequences (3:4) Aligned. Score:  85
-Sequences (3:5) Aligned. Score:  13
-Sequences (3:6) Aligned. Score:  20
-Sequences (3:7) Aligned. Score:  25
-Sequences (3:8) Aligned. Score:  20
-Sequences (3:9) Aligned. Score:  36
-Sequences (3:10) Aligned. Score:  16
-Sequences (3:11) Aligned. Score:  18
-Sequences (3:12) Aligned. Score:  25
-Sequences (4:5) Aligned. Score:  13
-Sequences (4:6) Aligned. Score:  11
-Sequences (4:7) Aligned. Score:  20
-Sequences (4:8) Aligned. Score:  10
-Sequences (4:9) Aligned. Score:  31
-Sequences (4:10) Aligned. Score:  17
-Sequences (4:11) Aligned. Score:  29
-Sequences (4:12) Aligned. Score:  14
-Sequences (5:6) Aligned. Score:  73
-Sequences (5:7) Aligned. Score:  83
-Sequences (5:8) Aligned. Score:  80
-Sequences (5:9) Aligned. Score:  31
-Sequences (5:10) Aligned. Score:  14
-Sequences (5:11) Aligned. Score:  14
-Sequences (5:12) Aligned. Score:  12
-Sequences (6:7) Aligned. Score:  80
-Sequences (6:8) Aligned. Score:  88
-Sequences (6:9) Aligned. Score:  26
-Sequences (6:10) Aligned. Score:  16
-Sequences (6:11) Aligned. Score:  25
-Sequences (6:12) Aligned. Score:  12
-Sequences (7:8) Aligned. Score:  78
-Sequences (7:9) Aligned. Score:  31
-Sequences (7:10) Aligned. Score:  10
-Sequences (7:11) Aligned. Score:  12
-Sequences (7:12) Aligned. Score:  12
-Sequences (8:9) Aligned. Score:  31
-Sequences (8:10) Aligned. Score:  10
-Sequences (8:11) Aligned. Score:  14
-Sequences (8:12) Aligned. Score:  12
-Sequences (9:10) Aligned. Score:  63
-Sequences (9:11) Aligned. Score:  84
-Sequences (9:12) Aligned. Score:  78
-Sequences (10:11) Aligned. Score:  64
-Sequences (10:12) Aligned. Score:  76
-Sequences (11:12) Aligned. Score:  46
-Guide tree file created:   [infile_copy.dnd]
-
-There are 11 groups
-Start of Multiple Alignment
-
-Aligning...
-Group 1: Sequences:   2      Score:1045
-Group 2: Sequences:   2      Score:1016
-Group 3: Sequences:   4      Score:1001
-Group 4: Sequences:   2      Score:313
-Group 5: Sequences:   2      Score:731
-Group 6: Sequences:   4      Score:516
-Group 7: Sequences:   8      Score:344
-Group 8: Sequences:   2      Score:1016
-Group 9: Sequences:   2      Score:1054
-Group 10: Sequences:   4      Score:945
-Group 11: Sequences:  12      Score:380
-Alignment Score 6283
-
-CLUSTAL-Alignment file created  [/share/shared/galaxy/database/files/002/dataset_2801.dat]
-
-
-Clustal created the following dnd file for your information:
-(
-(
-c_briggsae-chrII_+_/43862-46313:0.07349,
-c_brenneri-Cbre_Contig60_+_/627772-630087:0.04317)
-:0.02387,
-(
-c_remanei-Crem_Contig172_-_/123228-124941:0.06114,
-c_elegans-II_+_/9706834-9708803:0.07219)
-:0.01779,
-(
-(
-(
-c_briggsae-chrIfooI_+_/43862-46313:0.10368,
-c_brenneri-Cbre_Contig60gak_+_/627772-630087:0.06298)
-:0.01654,
-(
-c_remanei-Crem_Contig172foo_-_/123228-124941:0.05765,
-c_elegans-II_+_more/9706834-9708803:0.05902)
-:0.06262)
-:0.31533,
-(
-(
-c_briggsae-chrII_+_bar/43862-46313:0.02327,
-c_brenneri-Cbre_Contig60fee_+_/627772-630087:0.13463)
-:0.05016,
-(
-c_remanei-Crem_Contig172zot_-_/123228-124941:0.11667,
-c_elegans-II_+_meh/9706834-9708803:0.11737)
-:0.12013)
-:0.20951)
-:0.30133);
-
--- a/tool_dependencies.xml	Fri Oct 09 15:45:22 2015 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,6 +0,0 @@
-<?xml version="1.0"?>
-<tool_dependency>
-  <package name="clustalw2" version="2.1">
-      <repository changeset_revision="09243d89e7a4" name="package_clustalw_2_1" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" />
-    </package>
-</tool_dependency>