Mercurial > repos > nick > sequence_content_trimmer

comparison trimmer.xml @ 0:7f170cb06e2e draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit d76a1cf04f3e4bc735d320ccccbf7aecbc193395
author nick
date Tue, 01 Dec 2015 21:33:27 -0500
parents
children 464aee13e2df
comparison
equal deleted inserted replaced
-1:000000000000 0:7f170cb06e2e
1 <tool id="sequence_content_trimmer" version="0.1" name="Sequence Content Trimmer">
2 <description>trim reads based on certain bases</description>
3 <command interpreter="python">
4 trimmer.py $input1
5 #if $paired.is_paired:
6 $input2 $output1 $output2
7 #if ('fasta' in $input1.extension and 'fastq' in $input2.extension) or ('fastq' in $input1.extension and 'fasta' in $input2.extension)
8 --error 'Both input files must be either fastq or fasta (no mixing the two).'
9 #end if
10 #end if
11 #if $input1.extension == 'fastq' or $input1.extension == 'fastqsanger' or $input1.extension == 'fastqillumina' or $input1.extension == 'fastqsolexa'
12 -f fastq
13 #elif $input1.extension == 'fasta'
14 -f fasta
15 #else
16 -f $input1.extension
17 #end if
18 -b $bases -t $thres -w $win_len $invert
19 #if $min_len.has_min_len:
20 -m $min_len.value
21 #end if
22 #if not $paired.is_paired:
23 &gt; $output1
24 #end if
25 </command>
26 <inputs>
27 <conditional name="paired">
28 <param name="is_paired" type="select" label="Paired reads?">
29 <option value="" selected="True">Unpaired</option>
30 <option value="true">Paired</option>
31 </param>
32 <when value="true">
33 <param name="input1" type="data" format="fasta,fastq" label="Input reads (mate 1)"/>
34 <param name="input2" type="data" format="fasta,fastq" label="Input reads (mate 2)"/>
35 </when>
36 <when value="">
37 <param name="input1" type="data" format="fasta,fastq" label="Input reads"/>
38 </when>
39 </conditional>
40 <param name="bases" type="text" value="N" label="Bases to filter on"/>
41 <param name="thres" type="float" value="0.5" min="0" max="1" label="Frequency threshold" help="Trim when the frequency of filter bases (or non-filter bases, if inverting) exceeds this value."/>
42 <param name="win_len" type="integer" value="10" min="1" label="Size of the window"/>
43 <param name="invert" type="boolean" truevalue="--invert" falsevalue="" checked="False" label="Invert filter bases" help="Trim when the frequency of bases NOT in the &quot;filter bases&quot; list exceeds the threshold."/>
44 <conditional name="min_len">
45 <param name="has_min_len" type="boolean" truevalue="true" falsevalue="" checked="False" label="Set a minimum read length"/>
46 <when value="true">
47 <param name="value" type="integer" value="10" min="0" label="Minimum read length" help="Reads trimmed to less than this length will be omitted from the output. Pairs will be preserved: both must exceed this threshold to be kept."/>
48 </when>
49 </conditional>
50 </inputs>
51 <outputs>
52 <data name="output1" format_source="input1"/>
53 <data name="output2" format_source="input2">
54 <filter>paired['is_paired']</filter>
55 </data>
56 </outputs>
57
58 <help>
59
60 .. class:: infomark
61
62 **What it does**
63
64 This tool trims the 3' ends of reads based on the presence of the given bases. For instance, trim when N's are encountered or when the GC content exceeds a certain frequency.
65
66
67 .. class:: infomark
68
69 **How it works**
70
71 This will slide along the read with a window, and trim once the frequency of filter bases exceeds the frequency threshold (unless "Invert filter bases" is enabled, when it will trim once non-filter bases exceed the threshold).
72
73 The trim point will be just before the first (leftmost) filter base in the final window (the one where the frequency exceeded the threshold).
74
75
76 .. class:: infomark
77
78 **Input**
79
80 The inputs can be in the following formats: fasta, fastq, fastqsanger, fastqillumina, and fastqsolexa. Both must be either a fasta or fastq type (no mixing fastq and fasta).
81
82 </help>
83
84 </tool>