|
0
|
1 <?xml version="1.1"?>
|
|
|
2 <tool id="edu.tamu.cpt2.phage.intron_detection" name="Interrupted gene detection tool" version="19.1.0.0">
|
|
|
3 <description>based on nearby protein blast results</description>
|
|
|
4 <macros>
|
|
|
5 <import>macros.xml</import>
|
|
|
6 <import>cpt-macros.xml</import>
|
|
|
7 </macros>
|
|
|
8 <requirements>
|
|
2
|
9 <requirement type="package" version="3.8.13">python</requirement>
|
|
0
|
10 <requirement type="package" version="1.77">biopython</requirement>
|
|
2
|
11 <requirement type="package" version="1.2.2">cpt_gffparser</requirement>
|
|
0
|
12 </requirements>
|
|
|
13 <command detect_errors="aggressive"><![CDATA[
|
|
|
14 python $__tool_directory__/intron_detection.py
|
|
|
15
|
|
|
16 "$gff3_data"
|
|
|
17 "$blast"
|
|
|
18 --minimum $minimum
|
|
|
19 --maximum $maximum
|
|
|
20 --idThresh $idThresh
|
|
|
21 > $output]]></command>
|
|
|
22 <inputs>
|
|
|
23 <expand macro="gff3_input" />
|
|
|
24 <param label="Blastp Results" name="blast" type="data" format="blastxml"/>
|
|
|
25 <param label="Separation Minimum" name="minimum" type="text" value="-1"
|
|
|
26 help="Minimum number of amino acids a CDS pair must be separated by to detect an intron. Set to a negative number to instead allow CDS to overlap by up to that many AAs."/>
|
|
|
27 <param label="Separation Maximum" name="maximum" type="integer" value="10000"
|
|
|
28 help="Maximum number of bases a CDS pair may be separated by to detect an intron (eg, distance from end of 1 cds to the start of another)."/>
|
|
|
29 <param label="Percent Identity Threshold" name="idThresh" type="float" value=".30"
|
|
|
30 help="Minimum Identity Percentage for HSP to be considered for intron comparison (0.00 to 1.00)"/>
|
|
|
31 </inputs>
|
|
|
32 <outputs>
|
|
|
33 <data format="gff3" name="output" label="Potential interrupted genes"/>
|
|
|
34 </outputs>
|
|
|
35 <tests>
|
|
|
36 <test>
|
|
|
37 <param name="gff3_data" value="T7_CLEAN.gff3"/>
|
|
|
38 <param name="blast" value="T7_NR.blastxml"/>
|
|
|
39 <param name="minimum" value="10" />
|
|
|
40 <param name="maximum" value="2000" />
|
|
|
41 <param name="idThresh" value="0.3" />
|
|
|
42 <output name="output" file="T7_INTRON.gff3"/>
|
|
|
43 </test>
|
|
|
44 </tests>
|
|
|
45 <help><![CDATA[
|
|
|
46 **What it does**
|
|
|
47
|
|
|
48 This tool parses BLAST XML results and returns potential intron regions by
|
|
|
49 identifying query proteins with BLAST hits to the same target protein within
|
|
|
50 the maximum number of bases set above. This distance will also wraparound the
|
|
|
51 ends of the genome. The list of hits is returned as a gff3.
|
|
|
52
|
|
|
53 (Tool formerly named Intron Detection, updated Nov 2020)
|
|
|
54
|
|
|
55 ]]></help>
|
|
|
56 <expand macro="citations-2020" />
|
|
|
57 </tool>
|
