|
0
|
1 <tool id="redup" name="Redup" version="1.0">
|
|
|
2 <description>Remove exact duplicate reads from paired-end fastq files</description>
|
|
|
3 <command interpreter="perl">
|
|
|
4 ## Need to handle file names, probably should fix redup.pl
|
|
|
5 redup.pl
|
|
|
6 #if $opt_n:
|
|
|
7 -n $opt_n
|
|
|
8 #end if
|
|
|
9 $fastq1_in $fastq2_in $unique1_out $unique2_out
|
|
|
10 #if $opt_n:
|
|
|
11 > $duplicates
|
|
|
12 #end if
|
|
|
13 </command>
|
|
|
14 <inputs>
|
|
|
15 <param name="fastq1_in" type="data" format="fastq" label="Fastq Input 1"/>
|
|
|
16 <param name="fastq2_in" type="data" format="fastq" label="Fastq Input 2"/>
|
|
|
17 <param name="opt_n" type="integer" value="20" optional="true" label="Number of most duplicated sequences printed out. (default 20)">
|
|
|
18 <validator type="in_range" message="Value can not be negative" min="0"/>
|
|
|
19 </param>
|
|
|
20 </inputs>
|
|
|
21 <stdio>
|
|
|
22 <exit_code range="1:" level="fatal"/>
|
|
|
23 </stdio>
|
|
|
24 <outputs>
|
|
|
25 <data format_source="fastq1_in" name="unique1_out" label="${tool.name} on ${on_string}: fastq1.unique" />
|
|
|
26 <data format_source="fastq2_in" name="unique2_out" label="${tool.name} on ${on_string}: fastq2.unique" />
|
|
|
27 <data format="fasta" name="duplicates" label="${tool.name} on ${on_string}: top duplicates" >
|
|
|
28 <filter>opt_n != None</filter>
|
|
|
29 </data>
|
|
|
30 </outputs>
|
|
|
31 <tests>
|
|
|
32 <test>
|
|
|
33 <param name="fastq1_in" ftype="fastq" value="input1.fastq" />
|
|
|
34 <param name="fastq2_in" ftype="fastq" value="input2.fastq" />
|
|
|
35 <param name="opt_n" value="20" />
|
|
|
36 <output name="unique1_out" file="output1.fastq" />
|
|
|
37 <output name="unique2_out" file="output2.fastq" />
|
|
|
38 <output name="duplicates" file="duplicates.fasta" />
|
|
|
39 </test>
|
|
|
40 </tests>
|
|
|
41
|
|
|
42 <help>
|
|
|
43 This script removes duplicate paired-end reads from the input files sample1_R1.fastq and sample1_R2.fastq and prints out unique reads to the files sample1_R1.fastq.unique and sample2_R2.fastq.unique. Reads must have the exact same sequence to be called duplicates, quality scores are ignored. The top N (default 20) most duplicated sequences are printed out in fasta format, making it convenient for using BLAST to identify them.
|
|
|
44 </help>
|
|
|
45 </tool>
|
