|
4
|
1 <?xml version="1.0"?>
|
|
|
2 <tool id="duplex" name="Du Novo: Make consensus reads" version="0.3">
|
|
|
3 <description>from duplex sequencing alignments</description>
|
|
|
4 <requirements>
|
|
|
5 <requirement type="package" version="0.3">duplex</requirement>
|
|
|
6 <requirement type="set_environment">DUPLEX_DIR</requirement>
|
|
|
7 <!-- TODO: require Python 2.7 -->
|
|
|
8 </requirements>
|
|
|
9 <command detect_errors="exit_code"><![CDATA[
|
|
|
10 python \$DUPLEX_DIR/dunovo.py -r $min_reads -q $qual_thres -F $qual_format $input
|
|
|
11 #if $keep_sscs:
|
|
|
12 --sscs-file $sscs
|
|
|
13 #end if
|
|
|
14 > duplex.fa
|
|
|
15 && awk -f \$DUPLEX_DIR/utils/outconv.awk -v target=1 duplex.fa > $output1
|
|
|
16 && awk -f \$DUPLEX_DIR/utils/outconv.awk -v target=2 duplex.fa > $output2
|
|
|
17 ]]>
|
|
|
18 </command>
|
|
|
19 <inputs>
|
|
|
20 <param name="input" type="data" format="tabular" label="Aligned input reads" />
|
|
|
21 <param name="min_reads" type="integer" value="3" min="1" label="Minimum reads per family" help="Single-strand families with fewer than this many reads will be skipped."/>
|
|
|
22 <param name="qual_thres" type="integer" value="25" min="1" label="Minimum base quality" help="Bases with a PHRED score less than this will not be counted in the consensus making."/>
|
|
|
23 <param name="qual_format" type="select" label="FASTQ format" help="Solexa should also work for Illumina 1.3+ and 1.5+, and Sanger should work for Illumina 1.8+">
|
|
|
24 <option value="sanger" selected="true">Sanger (PHRED 0 = "!")</option>
|
|
|
25 <option value="solexa">Solexa (PHRED 0 = "@")</option>
|
|
|
26 </param>
|
|
|
27 <param name="keep_sscs" type="boolean" truevalue="true" falsevalue="" label="Output single-strand consensus sequences" />
|
|
|
28 </inputs>
|
|
|
29 <outputs>
|
|
|
30 <data name="output1" format="fasta" label="$tool.name on $on_string (mate 1)"/>
|
|
|
31 <data name="output2" format="fasta" label="$tool.name on $on_string (mate 2)"/>
|
|
|
32 <data name="sscs" format="fasta" label="$tool.name on $on_string (SSCS)">
|
|
|
33 <filter>keep_sscs</filter>
|
|
|
34 </data>
|
|
|
35 </outputs>
|
|
|
36 <tests>
|
|
|
37 <test>
|
|
|
38 <param name="input" value="families.msa.tsv"/>
|
|
|
39 <output name="output1" file="families.cons_1.fa"/>
|
|
|
40 <output name="output2" file="families.cons_2.fa"/>
|
|
|
41 </test>
|
|
|
42 </tests>
|
|
|
43 <help>
|
|
|
44
|
|
|
45 **What it does**
|
|
|
46
|
|
|
47 This is for processing duplex sequencing data. It creates single-strand and duplex consensus reads from aligned read families.
|
|
|
48
|
|
|
49 -----
|
|
|
50
|
|
|
51 **Input**
|
|
|
52
|
|
|
53 This expects the output format of the "Align families" tool.
|
|
|
54
|
|
|
55 -----
|
|
|
56
|
|
|
57 **Output**
|
|
|
58
|
|
|
59 This will output final, duplex consensus reads in two FASTA files (first and second reads in the pairs). Optionally, you can save the single-strand reads too, in a separate FASTA file.
|
|
|
60
|
|
|
61 </help>
|
|
|
62 </tool>
|
