|
12
|
1 <tool id="mismatch_frequencies" name="Mismatch Frequencies" version="0.0.5" hidden="false" >
|
|
|
2 <description>Analyze mismatch frequencies in BAM/SAM alignments</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="0.8.1">pysam</requirement>
|
|
|
5 <requirement type="package" version="0.14.1">pandas</requirement>
|
|
|
6 <requirement type="package" version="1.4">matplotlib</requirement>
|
|
|
7 </requirements>
|
|
|
8 <command interpreter="python">mismatch_frequencies.py --input
|
|
|
9 #for i in $rep
|
|
|
10 "$i.input_file"
|
|
|
11 #end for
|
|
|
12 --name
|
|
|
13 #for i in $rep
|
|
|
14 "$i.input_file.name"
|
|
|
15 #end for
|
|
|
16 --output_pdf $output_pdf --output_tab $output_tab --min $min_length --max $max_length
|
|
|
17 --n_mm $number_of_mismatches
|
|
|
18 --five_p $five_p
|
|
|
19 --three_p $three_p
|
|
|
20 </command>
|
|
|
21 <inputs>
|
|
|
22 <repeat name="rep" title="alignment files" min="1">
|
|
|
23 <param name="input_file" type="data" format="bam,sam" label="Alignment file" help="The input alignment file(s) for which you want to calculate mismatch frequencies."/>
|
|
|
24 </repeat>
|
|
|
25 <param name="number_of_mismatches" label="Maximum number of allowed mismatches per read" help="Discard reads with more than the chosen number of mismatches from the frequency calculation" type="integer" value="3"/>
|
|
|
26 <param name="min_length" label="Minumum read length to analyse" type="integer" value="21"/>
|
|
|
27 <param name="max_length" label="Maximum read length to analyse" type="integer" value="21"/>
|
|
|
28 <param name="five_p" label="Ignore mismatches in the first N nucleotides of a read" type="integer" value="0"/>
|
|
|
29 <param name="three_p" label="Ignore mismatches in the last N nucleotides of a read" help="useful to discriminate between tailing events and editing events" type="integer" value="3"/>
|
|
|
30 </inputs>
|
|
|
31 <outputs>
|
|
|
32 <data format="tabular" name="output_tab" />
|
|
|
33 <data format="pdf" name="output_pdf" />
|
|
|
34 </outputs>
|
|
|
35 <tests>
|
|
|
36 <test>
|
|
|
37 <param name="rep_0|input_file" value="3mismatches_ago2ip_s2.bam" ftype="bam" />
|
|
|
38 <param name="rep_1|input_file" value="3mismatches_ago2ip_ovary.bam" ftype="bam" />
|
|
|
39 <param name="number_of_mismatches" value="1" />
|
|
|
40 <param name="min_length" value="21" />
|
|
|
41 <param name="max_length" value="21" />
|
|
|
42 <output name="tabular" file="mismatch.tab" ftype="tabular"/>
|
|
|
43 </test>
|
|
|
44 </tests>
|
|
|
45 <help>
|
|
|
46
|
|
|
47 .. class:: infomark
|
|
|
48
|
|
|
49
|
|
|
50 ***What it does***
|
|
|
51
|
|
|
52 This tool reconstitues for each aligned read of an alignment file in SAM/BAM format whether
|
|
|
53 a mismatch is annotated in the MD tag, and if that is the case counts the identity of the
|
|
|
54 mismatch relative to the reference sequence. The output is a PDF document with the calculated
|
|
|
55 frequency for each mismatch that occured relative to the total number of valid reads and a table
|
|
|
56 with the corresponding values. Read length can be limited to a specific read length, and 5 prime and
|
|
|
57 3 prime-most nucleotides of a read can be ignored.
|
|
|
58
|
|
|
59 ----
|
|
|
60
|
|
|
61 .. class:: warningmark
|
|
|
62
|
|
|
63 ***Warning***
|
|
|
64
|
|
|
65 This tool skips all read that have insertions and has been tested only with bowtie and bowtie2
|
|
|
66 generated alignment files.
|
|
|
67
|
|
|
68 Written by Marius van den Beek, m.vandenbeek at gmail . com
|
|
|
69 </help>
|
|
|
70 </tool>
|
