annotate fastx_barcode_splitter.xml @ 2:e958c1e00122 draft

Added customized version of fastx_barcode_splitter.pl
author lparsons
date Thu, 07 Nov 2013 16:44:53 -0500
parents 8dc0438702c7
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
1 <tool id="cshl_princeton_fastx_barcode_splitter" version="1.1" name="Barcode Splitter" force_history_refresh="True">
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
2 <description></description>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
3 <command interpreter="bash">
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
4 fastx_barcode_splitter_galaxy_wrapper.sh $BARCODE $input "primary_$output.id" "$output.files_path" $input.extension --mismatches $mismatches --partial $partial
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
5 #if $refBarcodeLocation.barcodeLocation == "idxfile":
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
6 --idxfile $refBarcodeLocation.idxfile
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
7 #else:
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
8 $refBarcodeLocation.EOL
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
9 #end if
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
10 > $output
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
11 </command>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
12
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
13 <inputs>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
14 <param format="txt" version="1.1" name="BARCODE" type="data" label="Barcodes to use" />
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
15 <param format="fasta,fastqsanger,fastqsolexa,fastqillumina" version="1.1" name="input" type="data" label="Library to split" />
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
16
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
17 <conditional name="refBarcodeLocation">
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
18 <param version="1.1" name="barcodeLocation" type="select" label="Barcodes found at">
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
19 <option value="bol">Start of sequence (5' end)</option>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
20 <option value="eol">End of sequence (3' end)</option>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
21 <option value="idxfile">Separate index file</option>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
22 </param>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
23 <when value="bol">
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
24 <param version="1.1" name="EOL" type="hidden" value="--bol" />
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
25 </when>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
26 <when value="eol">
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
27 <param version="1.1" name="EOL" type="hidden" value="--eol" />
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
28 </when>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
29 <when value="idxfile">
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
30 <param version="1.1" name="idxfile" type="data" format="fasta,fastq,fastqsanger" label="Select index read file" />
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
31 </when>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
32 </conditional>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
33
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
34 <param version="1.1" name="mismatches" type="integer" size="3" value="0" label="Number of allowed mismatches" />
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
35
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
36 <param version="1.1" name="partial" type="integer" size="3" value="0" label="Number of allowed barcodes nucleotide deletions" />
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
37
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
38 </inputs>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
39
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
40 <tests>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
41 <test>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
42 <!-- Split a FASTQ file -->
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
43 <param version="1.1" name="BARCODE" value="fastx_barcode_splitter1.txt" />
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
44 <param version="1.1" name="input" value="fastx_barcode_splitter1.fastq" ftype="fastqsolexa" />
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
45 <param version="1.1" name="EOL" value="Start of sequence (5' end)" />
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
46 <param version="1.1" name="mismatches" value="2" />
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
47 <param version="1.1" name="partial" value="0" />
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
48 <output version="1.1" name="output" file="fastx_barcode_splitter1.out" />
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
49 </test>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
50 </tests>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
51
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
52 <outputs>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
53 <data version="1.1" format="html" name="output" />
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
54 </outputs>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
55 <help>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
56
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
57 **What it does**
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
58
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
59 This tool splits a FASTQ or FASTA file into several files, using barcodes as the split criteria.
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
60
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
61 --------
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
62
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
63 **Barcode file Format**
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
64
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
65 Barcode files are simple text files.
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
66 Each line should contain an identifier (descriptive name for the barcode), and the barcode itself (A/C/G/T), separated by a TAB character.
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
67 Example::
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
68
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
69 #This line is a comment (starts with a 'number' sign)
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
70 BC1 GATCT
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
71 BC2 ATCGT
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
72 BC3 GTGAT
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
73 BC4 TGTCT
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
74
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
75 For each barcode, a new FASTQ file will be created (with the barcode's identifier as part of the file name).
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
76 Sequences matching the barcode will be stored in the appropriate file.
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
77
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
78 One additional FASTQ file will be created (the 'unmatched' file), where sequences not matching any barcode will be stored.
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
79
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
80 The output of this tool is an HTML file, displaying the split counts and the file names.
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
81 In addition, each fastq file produced will be loaded into the galaxy history automatically.
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
82
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
83
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
84 ------
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
85
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
86 This tool is based on `FASTX-toolkit`__ by Assaf Gordon.
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
87
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
88 .. __: http://hannonlab.cshl.edu/fastx_toolkit/
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
89
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
90 </help>
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
91 <!-- FASTX-barcode-splitter is part of the FASTX-toolkit, by A.Gordon (gordon@cshl.edu) -->
8dc0438702c7 Uploaded
lparsons
parents:
diff changeset
92 </tool>