|
0
|
1 <tool id ="pyBarcodeFilter" name="pyBarcodeFilter" force_history_refresh="True">
|
|
|
2 <requirements>
|
|
|
3 <requirement type="package">pyCRAC</requirement>
|
|
|
4 </requirements>
|
|
|
5 <command interpreter="perl">
|
|
|
6 /usr/local/bin/pyBarcodeFilter.pl
|
|
|
7 --file_type $ftype.type
|
|
|
8 -f $ftype.f
|
|
|
9 -b $barcode
|
|
|
10 -m $mismatch
|
|
|
11 $index
|
|
|
12 --out $out
|
|
|
13 --id $out.id
|
|
|
14 --output_path $__new_file_path__
|
|
|
15 #if $ftype.reverse.rev == "yes":
|
|
|
16 -r=$ftype.reverse.r
|
|
|
17 $ftype.reverse.both
|
|
|
18 #end if#
|
|
|
19 </command>
|
|
|
20 <version_command>pyBarcodeFilter.py --version</version_command>
|
|
|
21 <inputs>
|
|
|
22 <conditional name="ftype">
|
|
|
23 <param name="type" type="select" label="File type">
|
|
|
24 <option value="fastq" selected="true">FASTQ</option>
|
|
|
25 <option value="fasta">FASTA</option>
|
|
|
26 </param>
|
|
|
27 <when value="fastq">
|
|
|
28 <param format="fastq" name="f" type="data" label="FastQ File -f" help="FastQ format" />
|
|
|
29 <conditional name="reverse">
|
|
|
30 <param name="rev" type="select" label="Add a reverse or paired FastQ file">
|
|
|
31 <option value="no" selected="true">NO</option>
|
|
|
32 <option value="yes">YES</option>
|
|
|
33 </param>
|
|
|
34 <when value="yes">
|
|
|
35 <param format="fastq" name="r" type="data" label="Reverse FastQ File -f" help="FastQ format" />
|
|
|
36 <param name="both" type="select" label="Search for barcode in both reads">
|
|
|
37 <option value="" selected="true">NO</option>
|
|
|
38 <option value="--both">YES</option>
|
|
|
39 </param>
|
|
|
40 </when>
|
|
|
41 <when value="no">
|
|
|
42 </when>
|
|
|
43 </conditional>
|
|
|
44 </when>
|
|
|
45 <when value="fasta">
|
|
|
46 <param format="fasta" name="f" type="data" label="FastA File -f" help="FastA format" />
|
|
|
47 <conditional name="reverse">
|
|
|
48 <param name="rev" type="select" label="Add a reverse or paired FastA file">
|
|
|
49 <option value="no" selected="true">NO</option>
|
|
|
50 <option value="yes">YES</option>
|
|
|
51 </param>
|
|
|
52 <when value="yes">
|
|
|
53 <param format="fasta" name="r" type="data" label="Reverse FastA File -f" help="FastA format" />
|
|
|
54 <param name="both" type="select" label="Search for barcode in both reads">
|
|
|
55 <option value="" selected="true">NO</option>
|
|
|
56 <option value="--both">YES</option>
|
|
|
57 </param>
|
|
|
58 </when>
|
|
|
59 <when value="no">
|
|
|
60 </when>
|
|
|
61 </conditional>
|
|
|
62 </when>
|
|
|
63 </conditional>
|
|
|
64 <param format="tabular" name="barcode" type="data" label="Barcode File -f" help="Tab delimited file with barcodes and barcode names" />
|
|
|
65 <param format="integer" name="mismatch" type="integer" label="Mismatches -m" value="0" size="3" help="Set the number of allowed mismatches in a barcode">
|
|
|
66 <validator type="in_range" min="0" max="100" message="Please enter a value between 0 and 100"/>
|
|
|
67 </param>
|
|
|
68 <param name="index" type="select" label="Split data using Illumina indexing barcode information -i">
|
|
|
69 <option value="" selected="true">NO</option>
|
|
|
70 <option value="-i">YES</option>
|
|
|
71 </param>
|
|
|
72 </inputs>
|
|
|
73 <outputs>
|
|
|
74 <data format="text" name="out" label="pyBarcodeFilter"/>
|
|
|
75 </outputs>
|
|
|
76 <help>
|
|
|
77
|
|
|
78 .. class:: infomark
|
|
|
79
|
|
|
80 **pySolexaBarcodeFilter**
|
|
|
81
|
|
|
82 pySolexaBarcodeFilter is part of the pyCRAC_ package. Filters sequence files by barcodes.
|
|
|
83
|
|
|
84 This tool requires FASTA or FASTQ input files containing the raw data and a text file containing barcode information.
|
|
|
85 To process paired end data, use -f and the -r flags to indicate the path to the forward and reverse sequencing reactions, respectively.
|
|
|
86 The barcodes file should two columns separated by a tab (see the table below). The first column should contain the barcode nucleotide sequences.
|
|
|
87 The second column should contain an identifier, for example, the name of the barcode or the name of the experiment.
|
|
|
88 The ’N’ in the barcode sequence indicates a random nucleotide. Make sure to use a simple text editor like TextEdit (MacOS X), gedit (Linux/Unix) or use a text editor in the terminal.
|
|
|
89 The program is case sensitive: all the nucleotide sequences should be upper case.
|
|
|
90 You can freely combine different barcodes but if you are mixing samples containing random nucleotide barcodes and normal barcodes.
|
|
|
91 **NOTE!** make sure to place the regular barcode sequence below the sequence with random nucleotides and make sure the shortest sequence is ALWAYS at the bottom in the column (see below)
|
|
|
92
|
|
|
93 Example of a barcode text file::
|
|
|
94
|
|
|
95 NNNCGCTTAGC mutant2
|
|
|
96 NNNGCGCAGC mutant1
|
|
|
97 NNNATTAG control
|
|
|
98 NNNTAAGC myfavprotein
|
|
|
99 AGC oldcontrol
|
|
|
100 AC veryfirstbarcodedsample
|
|
|
101
|
|
|
102 .. _pyCRAC: http://sandergranneman.bio.ed.ac.uk/Granneman_Lab/pyCRAC_software.html
|
|
|
103
|
|
|
104 ------
|
|
|
105
|
|
|
106 **Parameter list**
|
|
|
107
|
|
|
108 Options::
|
|
|
109
|
|
|
110 -f FILE, --input_file=FILE
|
|
|
111 name of the FASTQ or FASTA input file
|
|
|
112 -r FILE, --reverse_input_file=FILE
|
|
|
113 name of the paired (or reverse) FASTQ or FASTA input file
|
|
|
114 --file_type=FASTQ
|
|
|
115 type of file, uncompressed (fasta or fastq) or compressed (fasta.gz or fastq.gz, gzip/gunzip
|
|
|
116 compressed). Default is fastq
|
|
|
117 -b FILE, --barcode_list=FILE
|
|
|
118 name of tab-delimited file containing barcodes and barcode names
|
|
|
119 -m 1, --mismatches=1
|
|
|
120 to set the number of allowed mismatches in a barcode. A maximum of one mismatch is allowed. Default = 0
|
|
|
121 -i, --index
|
|
|
122 use this option if you want to split the data using the Illumina indexing barcode information
|
|
|
123
|
|
|
124 </help>
|
|
|
125 </tool>
|
