Mercurial > repos > mvdbeek > mismatch_frequencies

comparison mismatch_frequencies.xml @ 2:2974c382105c draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mismatch_frequencies commit 10a7e3877c2568d9c23de53fc97dc1c902ff0524-dirty
author mvdbeek
date Sat, 22 Dec 2018 04:15:47 -0500
parents 3613460e891e
children
comparison
equal deleted inserted replaced
1:3613460e891e 2:2974c382105c
1 <tool id="mismatch_frequencies" name="Mismatch Frequencies" version="0.1.0" hidden="false" > 1 <tool id="mismatch_frequencies" name="Mismatch Frequencies" version="0.1.0" hidden="false" >
2 <description>Analyze mismatch frequencies in BAM/SAM alignments</description> 2 <description>Analyze mismatch frequencies in BAM/SAM alignments</description>
3 <requirements> 3 <requirements>
4 <requirement type="package" version="0.7.7">pysam</requirement> 4 <requirement type="package" version="0.8.3">pysam</requirement>
5 <requirement type="package" version="0.14.1">pandas</requirement> 5 <requirement type="package" version="0.19.0">pandas</requirement>
6 <requirement type="package" version="1.2.1">matplotlib</requirement> 6 <requirement type="package" version="1.5.3">matplotlib</requirement>
7 </requirements> 7 </requirements>
8 <command interpreter="python">mismatch_frequencies.py --input 8 <command detect_errors="aggressive"><![CDATA[
9 #for i in $rep 9 python '$__tool_directory__'/mismatch_frequencies.py --input
10 "$i.input_file" 10 #for i in $rep
11 #end for 11 "$i.input_file"
12 --name 12 #end for
13 #for i in $rep 13 --name
14 "$i.input_file.element_identifier" 14 #for i in $rep
15 #end for 15 "$i.input_file.element_identifier"
16 --output_pdf $output_pdf --output_tab $output_tab --min $min_length --max $max_length 16 #end for
17 --n_mm $number_of_mismatches 17 --output_pdf '$output_pdf'
18 --five_p $five_p 18 --output_tab '$output_tab'
19 --three_p $three_p 19 --min $min_length
20 --expanded_output_tab $expanded_tab 20 --max $max_length
21 --possible_mismatches $possible_mismatches 21 --n_mm $number_of_mismatches
22 </command> 22 --five_p $five_p
23 --three_p $three_p
24 --expanded_output_tab '$expanded_tab'
25 --possible_mismatches $possible_mismatches
26 ]]></command>
23 <inputs> 27 <inputs>
24 <repeat name="rep" title="alignment files"> 28 <repeat name="rep" title="alignment files">
25 <param name="input_file" type="data" format="bam,sam" label="Alignment file" help="The input alignment file(s) for which to analyze the mismatches."/> 29 <param name="input_file" type="data" format="bam,sam" label="Alignment file" help="The input alignment file(s) for which to analyze the mismatches."/>
26 </repeat> 30 </repeat>
27 <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"/> 31 <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"/>
31 <param name="min_length" label="Minumum read length to analyse" type="integer" value="21"/> 35 <param name="min_length" label="Minumum read length to analyse" type="integer" value="21"/>
32 <param name="max_length" label="Maximum read length to analyse" type="integer" value="21"/> 36 <param name="max_length" label="Maximum read length to analyse" type="integer" value="21"/>
33 <param name="five_p" label="Ignore mismatches in the first N nucleotides of a read" type="integer" value="0"/> 37 <param name="five_p" label="Ignore mismatches in the first N nucleotides of a read" type="integer" value="0"/>
34 <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"/> 38 <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"/>
35 <param help="Output expanded tabular format" label="Nucleotide mismatches per reference sequence" name="expanded" type="select"> 39 <param help="Output expanded tabular format" label="Nucleotide mismatches per reference sequence" name="expanded" type="select">
36 <option select="true" value="false">No</option> 40 <option selected="true" value="false">No</option>
37 <option value="expanded">Yes</option> 41 <option value="expanded">Yes</option>
38 </param> 42 </param>
39 </inputs> 43 </inputs>
40 <outputs> 44 <outputs>
41 <data format="tabular" name="output_tab" /> 45 <data format="tabular" name="output_tab" />
64 .. class:: infomark 68 .. class:: infomark
65 69
66 70
67 ***What it does*** 71 ***What it does***
68 72
69 This tool reconstitues for each aligned read of an alignment file in SAM/BAM format whether 73 This tool reconstitues for each aligned read of an alignment file in SAM/BAM
70 a mismatch is annotated in the MD tag, and if that is the case counts the identity of the 74 format whether a mismatch is annotated in the MD tag, and if that is the case
71 mismatch relative to the reference sequence. The output is a PDF document with the calculated 75 counts the identity of the mismatch relative to the reference sequence. The
72 frequency for each mismatch that occured relative to the total number of valid reads and a table 76 output is a PDF document with the calculated frequency for each mismatch that
73 with the corresponding values. Read length can be limited to a specific read length, and 5 prime and 77 occured relative to the total number of valid reads and a table with the
74 3 prime-most nucleotides of a read can be ignored. 78 corresponding values. Read length can be limited to a specific read length, and
79 5 prime and 3 prime-most nucleotides of a read can be ignored.
75 80
76 ---- 81 ----
77 82
78 .. class:: warningmark 83 .. class:: warningmark
79 84