annotate cpt_intron_detect/intron_detection.xml @ 4:0a98d5259ef0 draft default tip

Uploaded
author cpt
date Fri, 20 May 2022 08:56:06 +0000
parents 41117b5ba508
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
1a19092729be Uploaded
cpt
parents:
diff changeset
1 <?xml version="1.1"?>
1a19092729be Uploaded
cpt
parents:
diff changeset
2 <tool id="edu.tamu.cpt2.phage.intron_detection" name="Interrupted gene detection tool" version="19.1.0.0">
1a19092729be Uploaded
cpt
parents:
diff changeset
3 <description>based on nearby protein blast results</description>
1a19092729be Uploaded
cpt
parents:
diff changeset
4 <macros>
1a19092729be Uploaded
cpt
parents:
diff changeset
5 <import>macros.xml</import>
1a19092729be Uploaded
cpt
parents:
diff changeset
6 <import>cpt-macros.xml</import>
1a19092729be Uploaded
cpt
parents:
diff changeset
7 </macros>
1a19092729be Uploaded
cpt
parents:
diff changeset
8 <requirements>
2
e0e294a1ccdd Uploaded
cpt
parents: 0
diff changeset
9 <requirement type="package" version="3.8.13">python</requirement>
3
41117b5ba508 Uploaded
cpt
parents: 2
diff changeset
10 <requirement type="package" version="1.79">biopython</requirement>
2
e0e294a1ccdd Uploaded
cpt
parents: 0
diff changeset
11 <requirement type="package" version="1.2.2">cpt_gffparser</requirement>
0
1a19092729be Uploaded
cpt
parents:
diff changeset
12 </requirements>
1a19092729be Uploaded
cpt
parents:
diff changeset
13 <command detect_errors="aggressive"><![CDATA[
1a19092729be Uploaded
cpt
parents:
diff changeset
14 python $__tool_directory__/intron_detection.py
1a19092729be Uploaded
cpt
parents:
diff changeset
15
1a19092729be Uploaded
cpt
parents:
diff changeset
16 "$gff3_data"
1a19092729be Uploaded
cpt
parents:
diff changeset
17 "$blast"
1a19092729be Uploaded
cpt
parents:
diff changeset
18 --minimum $minimum
1a19092729be Uploaded
cpt
parents:
diff changeset
19 --maximum $maximum
1a19092729be Uploaded
cpt
parents:
diff changeset
20 --idThresh $idThresh
1a19092729be Uploaded
cpt
parents:
diff changeset
21 > $output]]></command>
1a19092729be Uploaded
cpt
parents:
diff changeset
22 <inputs>
1a19092729be Uploaded
cpt
parents:
diff changeset
23 <expand macro="gff3_input" />
1a19092729be Uploaded
cpt
parents:
diff changeset
24 <param label="Blastp Results" name="blast" type="data" format="blastxml"/>
1a19092729be Uploaded
cpt
parents:
diff changeset
25 <param label="Separation Minimum" name="minimum" type="text" value="-1"
1a19092729be Uploaded
cpt
parents:
diff changeset
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."/>
1a19092729be Uploaded
cpt
parents:
diff changeset
27 <param label="Separation Maximum" name="maximum" type="integer" value="10000"
1a19092729be Uploaded
cpt
parents:
diff changeset
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)."/>
1a19092729be Uploaded
cpt
parents:
diff changeset
29 <param label="Percent Identity Threshold" name="idThresh" type="float" value=".30"
1a19092729be Uploaded
cpt
parents:
diff changeset
30 help="Minimum Identity Percentage for HSP to be considered for intron comparison (0.00 to 1.00)"/>
1a19092729be Uploaded
cpt
parents:
diff changeset
31 </inputs>
1a19092729be Uploaded
cpt
parents:
diff changeset
32 <outputs>
1a19092729be Uploaded
cpt
parents:
diff changeset
33 <data format="gff3" name="output" label="Potential interrupted genes"/>
1a19092729be Uploaded
cpt
parents:
diff changeset
34 </outputs>
1a19092729be Uploaded
cpt
parents:
diff changeset
35 <tests>
1a19092729be Uploaded
cpt
parents:
diff changeset
36 <test>
1a19092729be Uploaded
cpt
parents:
diff changeset
37 <param name="gff3_data" value="T7_CLEAN.gff3"/>
1a19092729be Uploaded
cpt
parents:
diff changeset
38 <param name="blast" value="T7_NR.blastxml"/>
1a19092729be Uploaded
cpt
parents:
diff changeset
39 <param name="minimum" value="10" />
1a19092729be Uploaded
cpt
parents:
diff changeset
40 <param name="maximum" value="2000" />
1a19092729be Uploaded
cpt
parents:
diff changeset
41 <param name="idThresh" value="0.3" />
1a19092729be Uploaded
cpt
parents:
diff changeset
42 <output name="output" file="T7_INTRON.gff3"/>
1a19092729be Uploaded
cpt
parents:
diff changeset
43 </test>
1a19092729be Uploaded
cpt
parents:
diff changeset
44 </tests>
1a19092729be Uploaded
cpt
parents:
diff changeset
45 <help><![CDATA[
1a19092729be Uploaded
cpt
parents:
diff changeset
46 **What it does**
1a19092729be Uploaded
cpt
parents:
diff changeset
47
1a19092729be Uploaded
cpt
parents:
diff changeset
48 This tool parses BLAST XML results and returns potential intron regions by
1a19092729be Uploaded
cpt
parents:
diff changeset
49 identifying query proteins with BLAST hits to the same target protein within
1a19092729be Uploaded
cpt
parents:
diff changeset
50 the maximum number of bases set above. This distance will also wraparound the
1a19092729be Uploaded
cpt
parents:
diff changeset
51 ends of the genome. The list of hits is returned as a gff3.
1a19092729be Uploaded
cpt
parents:
diff changeset
52
1a19092729be Uploaded
cpt
parents:
diff changeset
53 (Tool formerly named Intron Detection, updated Nov 2020)
1a19092729be Uploaded
cpt
parents:
diff changeset
54
1a19092729be Uploaded
cpt
parents:
diff changeset
55 ]]></help>
1a19092729be Uploaded
cpt
parents:
diff changeset
56 <expand macro="citations-2020" />
1a19092729be Uploaded
cpt
parents:
diff changeset
57 </tool>