PageRenderTime 19ms CodeModel.GetById 15ms app.highlight 1ms RepoModel.GetById 1ms app.codeStats 0ms

/tools/ilmn_pacbio/smrtpipe_filter.xml

https://bitbucket.org/cistrome/cistrome-harvard/
XML | 67 lines | 57 code | 10 blank | 0 comment | 0 complexity | 7e82e83b490db634038d748537adf6dc MD5 | raw file
 1<tool id="smrtpipe_filter" name="SMRTpipe Filter" version="1.0.0">
 2  <description>Produce filtered reads from a set of PacBio primary analysis outputs.</description>
 3  <command interpreter="python">
 4    smrtpipe_galaxy.py --output=data/filtered_subreads.fasta --galaxy_output=${outfile} ${iniFile}
 5  </command>
 6  <inputs>
 7    <conditional name="source">
 8      <param name="input_source" type="select" label="Choose the source for the analysis inputs">
 9        <option value="path">Path to fofn or multiple bas.h5 paths</option>
10        <option value="history">History</option>
11      </param>
12      <when value="path">
13        <repeat name="inputFiles" title="Input files">
14          <param name="path" type="text" label="File path" size="75"/>
15        </repeat>
16      </when>
17      <when value="history">
18        <param name="input1" type="data" format="tabular" label="File containing input paths" />
19      </when>
20    </conditional>
21    <param name="minimum_readlength" type="integer" value="50" label="Minimum raw readlength" />
22    <param name="minimum_readscore" type="float" value="0.75" label="Minimum read quality" />
23  </inputs>
24  <configfiles>
25    <configfile name="iniFile">
26[input]
27#if $source.input_source=="history":
28#for $l in open($source.input1.file_name,'r'):
29$l
30#end for
31#else
32#for $p in $source.inputFiles
33${p.path}
34#end for
35#end if
36
37[S_Filter]
38filters=MinRL=${minimum_readlength},MinReadScore=${minimum_readscore}
39    </configfile>
40  </configfiles>
41  <outputs>
42    <data name="outfile" format="fasta" label="Filtered subreads" />
43  </outputs>
44  <help>
45
46**What it does**
47
48Filters PacBio bas.h5 files and produces a FASTA file of filtered subreads.
49
50In PacBio SMRT sequencing, the template format is a SMRTbell: a circular
51molecule with adapters at two locations in the circle.  The subreads are the
52portions of the read between adapters.
53
54**Parameter list**
55
56Minimum readlength
57    Only keep reads from ZMWs that produced this many bases or more.
58
59Minimum read quality
60    Only keep reads with overall quality scores of this value or more.  The read quality score is a *de novo* prediction of the accuracy of the read.
61
62**Output**
63
64FASTA file of filtered reads.
65
66  </help>
67</tool>