comparison gff3_rebase.xml @ 1:4f4b413056f6 draft

planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
author cpt
date Mon, 05 Jun 2023 02:44:12 +0000
parents
children d0b52c1d6b25
comparison
equal deleted inserted replaced
0:6e7e20cb1fc7 1:4f4b413056f6
1 <tool id="gff3.rebase" name="Rebase GFF3 features" version="19.1.0.0">
2 <description>against parent features</description>
3 <macros>
4 <import>macros.xml</import>
5 <import>cpt-macros.xml</import>
6 </macros>
7 <expand macro="requirements"/>
8 <command interpreter="python" detect_errors="aggressive"><![CDATA[gff3_rebase.py
9 '$parent'
10 '$child'
11
12 '$interpro'
13 '$protein2dna'
14 --map_by "$map_by"
15 > '$default']]></command>
16 <inputs>
17 <param label="Parent GFF3 annotations" name="parent" format="gff3" type="data"/>
18 <param label="Child GFF3 annotations to rebase against parent" name="child" format="gff3" type="data"/>
19 <param label="Interpro specific modifications" name="interpro" type="boolean" truevalue="--interpro" falsevalue=""/>
20 <param label="Map protein translated results to original DNA data" name="protein2dna" type="boolean" truevalue="--protein2dna" falsevalue=""/>
21 <param label="Mapping Key" name="map_by" type="text" value="ID"/>
22 </inputs>
23 <outputs>
24 <data format="gff3" name="default"/>
25 </outputs>
26 <tests>
27 <test>
28 <param name="parent" value="T7_CLEAN.gff3"/>
29 <param name="child" value="T7_TMHMM.gff3"/>
30 <param name="interpro" value=""/>
31 <param name="protein2dna" value="--protein2dna"/>
32 <param name="map_by" value="ID"/>
33 <output name="default" file="T7_TMHMM_REBASE.gff3"/>
34 </test>
35 <test>
36 <param name="parent" value="parent.gff"/>
37 <param name="child" value="child.gff"/>
38 <param name="interpro" value=""/>
39 <param name="protein2dna" value="--protein2dna"/>
40 <param name="map_by" value="ID"/>
41 <output name="default" file="proteins.gff"/>
42 </test>
43 <test>
44 <param name="parent" value="parent.gff"/>
45 <param name="child" value="child.gff"/>
46 <param name="interpro" value=""/>
47 <param name="protein2dna" value=""/>
48 <param name="map_by" value="ID"/>
49 <output name="default" file="nonprotein.gff"/>
50 </test>
51 </tests>
52 <help><![CDATA[
53 **What it does**
54
55 The workflow in a genomic data analysis typically follows a process of feature
56 export, analysis and then mapping the results of the analysis back to the genome.
57
58 For meaningful display in JBrowse, it is necessary to accurately map
59 analysis results back to their corresponding positions in the context of the entire
60 genome.
61
62 This tool fills that gap, by *rebasing* (calculating parent genome coordinates)
63 features from analysis results against the parent features which
64 were originally used for the analysis.
65
66 **Example Input/Output**
67
68 For a *parent* set of annotations::
69
70 #gff-version 3
71 PhageBob maker cds 300 600 . + . ID=cds42
72
73 Where the analysis had exported the CDS (child) FASTA sequence::
74
75 >cds42
76 MRTNASC
77
78 Then analyzed that feature, producing the *child* annotation file::
79
80 #gff-version 3
81 cds42 blastp match_part 1 50 1e-40 . . ID=m00001;Notes=RNAse A Protein
82
83 This tool will then localize the results properly against the parent and permit
84 proper visualization of the results in the correct location::
85
86 #gff-version 3
87 PhageBob blastp match_part 300 449 1e-40 + . ID=m00001;Notes=RNAse A Protein
88
89 **Options**
90
91 The **Interpro specific modifications** option selectively ignores *features* (*i.e.* polypeptide) and
92 qualifiers (status, Target) not needed in the output.
93
94 The **Map protein translated results to original DNA data** option indicates that the DNA sequences were translated into
95 protein sequence during the genomic export process. When this option is selected,
96 the tool will multiply the bases by three to obtain the correct DNA locations.
97
98 ]]></help>
99 <expand macro="citations"/>
100 </tool>