|
0
|
1 <tool id="cshl_fastq_masker" name="Mask nucleotides">
|
|
|
2 <description>(based on quality)</description>
|
|
|
3 <command>
|
|
|
4 cat '$input' |
|
|
|
5 fastq_masker
|
|
|
6 #if $input.ext == "fastqsanger":
|
|
|
7 -Q 33
|
|
|
8 #elif $input.ext == "fastq":
|
|
|
9 -Q 64
|
|
|
10 #end if
|
|
|
11 -v -q $cutoff -r '$maskchar' -o '$output'</command>
|
|
|
12 <inputs>
|
|
|
13 <param format="fastq,fastqsanger" name="input" type="data" label="Library to clip" />
|
|
|
14
|
|
|
15 <param name="cutoff" size="4" type="integer" value="20">
|
|
|
16 <label>Minimum quality score</label>
|
|
|
17 <help>Nucleotides below this quality will be masked</help>
|
|
|
18 </param>
|
|
|
19
|
|
|
20 <param name="maskchar" size="1" type="text" value="N">
|
|
|
21 <label>Mask character</label>
|
|
|
22 <help>Replace low-quality nucleotides with this character. Common values: 'N' or '.'</help>
|
|
|
23 </param>
|
|
|
24 </inputs>
|
|
|
25
|
|
|
26 <tests>
|
|
|
27 <test>
|
|
|
28 <param name="input" value="fastq_masker.fastq" ftype="fastq" />
|
|
|
29 <param name="cutoff" value="29"/>
|
|
|
30 <param name="maskchar" value="x"/>
|
|
|
31 <output name="output" file="fastq_masker.out" />
|
|
|
32 </test>
|
|
|
33 </tests>
|
|
|
34
|
|
|
35 <outputs>
|
|
|
36 <data format="input" name="output" metadata_source="input"
|
|
|
37 />
|
|
|
38 </outputs>
|
|
|
39 <help>
|
|
|
40 **What it does**
|
|
|
41
|
|
|
42 This tool masks low-quality nucleotides in a FASTQ file, and replaces them with the specifed mask character (**N** by default).
|
|
|
43
|
|
|
44 --------
|
|
|
45
|
|
|
46 **Example**
|
|
|
47
|
|
|
48 Input FASTQ file::
|
|
|
49
|
|
|
50 @1
|
|
|
51 TATGGTCAGAAACCATATGC
|
|
|
52 +1
|
|
|
53 40 40 40 40 40 40 40 40 40 40 40 20 19 19 19 19 19 19 19 19
|
|
|
54 @2
|
|
|
55 CAGCGAGGCTTTAATGCCAT
|
|
|
56 +2
|
|
|
57 40 40 40 40 40 40 40 40 30 20 19 20 19 19 19 19 19 19 19 19
|
|
|
58 @3
|
|
|
59 CAGCGAGGCTTTAATGCCAT
|
|
|
60 +3
|
|
|
61 40 40 40 40 40 40 40 40 20 19 19 19 19 19 19 19 19 19 19 19
|
|
|
62
|
|
|
63 After Masking nucleotides with quality lower than 20 with the character **N**::
|
|
|
64
|
|
|
65 @1
|
|
|
66 TATGGTCAGAAANNNNNNNN
|
|
|
67 +1
|
|
|
68 40 40 40 40 40 40 40 40 40 40 40 20 19 19 19 19 19 19 19 19
|
|
|
69 @2
|
|
|
70 CAGCGAGGCTNTNNNNNNNN
|
|
|
71 +2
|
|
|
72 40 40 40 40 40 40 40 40 30 20 19 20 19 19 19 19 19 19 19 19
|
|
|
73 @3
|
|
|
74 CAGCGAGGCNNNNNNNNNNN
|
|
|
75 +3
|
|
|
76 40 40 40 40 40 40 40 40 20 19 19 19 19 19 19 19 19 19 19 19
|
|
|
77
|
|
|
78
|
|
|
79 ------
|
|
|
80
|
|
|
81 This tool is based on `FASTX-toolkit`__ by Assaf Gordon.
|
|
|
82
|
|
|
83 .. __: http://hannonlab.cshl.edu/fastx_toolkit/
|
|
|
84
|
|
|
85 </help>
|
|
|
86 </tool>
|
|
|
87 <!-- FASTQ-Masker part of the FASTX-toolkit, by A.Gordon (gordon@cshl.edu) -->
|
