|
2
|
1 <tool id="trimming3" name="Trim 3' adapter">
|
|
|
2 <description> using FASTX Toolkit</description>
|
|
|
3
|
|
|
4 <command>
|
|
|
5 fastx_clipper -a $adapterSeq -l $discardShorterThan $discardNonclipped $discardClipped $adapterOnly $keepUnknown
|
|
|
6 #if $minAdapterAlignment.minOverlapRequired =="yes":
|
|
|
7 -M $minAdapterAlignment.minLen
|
|
|
8 #end if
|
|
|
9 -v -i $input 2>/dev/null | fastq_quality_trimmer -v -l $discardShorterThan -t $qualityThreshold -o $output
|
|
|
10 </command>
|
|
|
11
|
|
|
12 <inputs>
|
|
|
13 <param name="input" type="data" format="fastq" label="Input FASTQ file"/>
|
|
|
14
|
|
|
15 <param name="adapterSeq" type="text" value="" label="Adapter sequence (the 3' adapter will vary for different CLIP protocol variations)"/>
|
|
|
16 <param name="discardShorterThan" type="integer" value="" label="Discard sequences shorter than N nucleotides (see help below for parameter suggestion)"/>
|
|
|
17 <param name="discardNonclipped" type="boolean" truevalue="-c" falsevalue="" checked="no" label="Discard non-trimmed sequences (i.e. - keep only sequences which contained the adapter)" />
|
|
|
18 <param name="discardClipped" type="boolean" truevalue="-C" falsevalue="" checked="no" label="Discard trimmed sequences (i.e. - keep only sequences which did not contained the adapter)" />
|
|
|
19 <param name="adapterOnly" type="boolean" truevalue="-k" falsevalue="" checked="no" label="Report Adapter-Only sequences"/>
|
|
|
20 <param name="keepUnknown" type="boolean" truevalue="-n" falsevalue="" checked="yes" label="Keep sequences with unknown nucleotides"/>
|
|
|
21 <conditional name="minAdapterAlignment">
|
|
|
22 <param name="minOverlapRequired" type="select" label="Require minimum adapter alignment length of N. If less than N nucleotides aligned with the adapter - don't trim it.">
|
|
|
23 <option value="yes">Yes</option>
|
|
|
24 <option value="no" selected="True">No</option>
|
|
|
25 </param>
|
|
|
26 <when value="yes">
|
|
|
27 <param name="minLen" type="integer" value="" label="Input the length"/>
|
|
|
28 </when>
|
|
|
29 <when value="no">
|
|
|
30 </when>
|
|
|
31 </conditional>
|
|
|
32 <param name="qualityThreshold" type="integer" value="5" label="Quality threshold - nucleotides with lower quality will be trimmed (from the end of the sequence)"/>
|
|
|
33 <!--<param name="CompressOutput" type="boolean" truevalue="-z" falsevalue="" checked="no" label="Compress output with GZIP"/> -->
|
|
|
34
|
|
|
35 </inputs>
|
|
|
36
|
|
|
37 <outputs>
|
|
|
38 <data name="output" format="fastq" label="Trim 3' adapter on ${on_string} "/>
|
|
|
39 </outputs>
|
|
|
40 <help>
|
|
|
41
|
|
|
42 .. class:: infomark
|
|
|
43
|
|
|
44 **What this tool does**
|
|
|
45
|
|
|
46
|
|
|
47 This tool takes as input FASTQ files and output FASTQ files with 3' adapters and extremely low quality bases (e.g. score less than 5) removed.
|
|
|
48
|
|
|
49 It is a wrapper of fastx_clipper and fastq_quality_trimmer that are a part of the FASTX Toolkit (http://hannonlab.cshl.edu/fastx_toolkit/).
|
|
|
50
|
|
|
51 -----
|
|
|
52
|
|
|
53 **Parameter suggestion for discarding sequences**
|
|
|
54
|
|
|
55 We typically require high quality score in barcode and 15 nt of CLIP tags.
|
|
|
56 * For standard CLIP: discard sequences shorter than 20 nt (5 nt barcode + 15 nt CLIP tag).
|
|
|
57 * For BrdU CLIP: discard sequences shorter than 29 nucleotides (14 nt barcode + 15 nt CLIP tag).
|
|
|
58
|
|
|
59 </help>
|
|
|
60
|
|
|
61 </tool>
|
