|
0
|
1 <tool id="cshl_fastx_barcode_splitter" name="Barcode Splitter">
|
|
|
2 <description></description>
|
|
|
3 <requirements><requirement type="package">fastx_toolkit</requirement></requirements>
|
|
|
4 <command interpreter="bash">fastx_barcode_splitter_galaxy_wrapper.sh $BARCODE $input "$input.name" "$output.files_path" --mismatches $mismatches --partial $partial $EOL > $output </command>
|
|
|
5
|
|
|
6 <inputs>
|
|
|
7 <param format="txt" name="BARCODE" type="data" label="Barcodes to use" />
|
|
|
8 <param format="fasta,fastqsanger,fastqsolexa,fastqillumina" name="input" type="data" label="Library to split" />
|
|
|
9
|
|
|
10 <param name="EOL" type="select" label="Barcodes found at">
|
|
|
11 <option value="--bol">Start of sequence (5' end)</option>
|
|
|
12 <option value="--eol">End of sequence (3' end)</option>
|
|
|
13 </param>
|
|
|
14
|
|
|
15 <param name="mismatches" type="integer" size="3" value="2" label="Number of allowed mismatches" />
|
|
|
16
|
|
|
17 <param name="partial" type="integer" size="3" value="0" label="Number of allowed barcodes nucleotide deletions" />
|
|
|
18
|
|
|
19 </inputs>
|
|
|
20
|
|
|
21 <tests>
|
|
|
22 <test>
|
|
|
23 <!-- Split a FASTQ file -->
|
|
|
24 <param name="BARCODE" value="fastx_barcode_splitter1.txt" />
|
|
|
25 <param name="input" value="fastx_barcode_splitter1.fastq" ftype="fastqsolexa" />
|
|
|
26 <param name="EOL" value="Start of sequence (5' end)" />
|
|
|
27 <param name="mismatches" value="2" />
|
|
|
28 <param name="partial" value="0" />
|
|
|
29 <output name="output" file="fastx_barcode_splitter1.out" />
|
|
|
30 </test>
|
|
|
31 </tests>
|
|
|
32
|
|
|
33 <outputs>
|
|
|
34 <data format="html" name="output" />
|
|
|
35 </outputs>
|
|
|
36 <help>
|
|
|
37
|
|
|
38 **What it does**
|
|
|
39
|
|
|
40 This tool splits a Solexa library (FASTQ file) or a regular FASTA file into several files, using barcodes as the split criteria.
|
|
|
41
|
|
|
42 --------
|
|
|
43
|
|
|
44 **Barcode file Format**
|
|
|
45
|
|
|
46 Barcode files are simple text files.
|
|
|
47 Each line should contain an identifier (descriptive name for the barcode), and the barcode itself (A/C/G/T), separated by a TAB character.
|
|
|
48 Example::
|
|
|
49
|
|
|
50 #This line is a comment (starts with a 'number' sign)
|
|
|
51 BC1 GATCT
|
|
|
52 BC2 ATCGT
|
|
|
53 BC3 GTGAT
|
|
|
54 BC4 TGTCT
|
|
|
55
|
|
|
56 For each barcode, a new FASTQ file will be created (with the barcode's identifier as part of the file name).
|
|
|
57 Sequences matching the barcode will be stored in the appropriate file.
|
|
|
58
|
|
|
59 One additional FASTQ file will be created (the 'unmatched' file), where sequences not matching any barcode will be stored.
|
|
|
60
|
|
|
61 The output of this tool is an HTML file, displaying the split counts and the file locations.
|
|
|
62
|
|
|
63 **Output Example**
|
|
|
64
|
|
|
65 .. image:: ./static/fastx_icons/barcode_splitter_output_example.png
|
|
|
66
|
|
|
67 </help>
|
|
|
68 </tool>
|
|
|
69 <!-- FASTX-barcode-splitter is part of the FASTX-toolkit, by A.Gordon (gordon@cshl.edu) -->
|
