|
0
|
1 <?xml version="1.0"?>
|
|
|
2 <tool id="edu.tamu.cpt.fasta.lipory" name="Identify Lipoboxes" version="19.1.0.0">
|
|
|
3 <description> in protein sequences</description>
|
|
|
4 <macros>
|
|
|
5 <import>macros.xml</import>
|
|
|
6 <import>cpt-macros.xml</import>
|
|
|
7 </macros>
|
|
|
8 <expand macro="requirements">
|
|
|
9 <requirement type="package" version="2019.06.08">regex</requirement>
|
|
|
10 </expand>
|
|
|
11 <command interpreter="python" detect_errors="aggressive"><![CDATA[lipory.py
|
|
|
12 $positional_1
|
|
|
13 $positional_2
|
|
|
14
|
|
|
15 --lipobox_mindist $lipobox_mindist
|
|
|
16 --lipobox_maxdist $lipobox_maxdist
|
|
|
17
|
|
|
18 > $default]]></command>
|
|
|
19 <inputs>
|
|
|
20 <param label="Naive orf calls" name="positional_1" type="data" format="gff3"/>
|
|
|
21 <param label="Genome" name="positional_2" type="data" format="fasta"/>
|
|
|
22
|
|
|
23 <param label="Minimum distance in codons to start of lipobox" name="lipobox_mindist" type="integer" value="10"/>
|
|
|
24 <param label="Maximum distance in codons to start of lipobox" name="lipobox_maxdist" type="integer" value="40"/>
|
|
|
25 </inputs>
|
|
|
26 <outputs>
|
|
|
27 <data format="gff3" name="default" label="Lipoboxes from ${on_string}"/>
|
|
|
28 </outputs>
|
|
|
29 <tests>
|
|
|
30 <test>
|
|
|
31 <param name="positional_1" value="T7_LiporyIn.gff3" />
|
|
|
32 <param name="positional_2" value="T7_LiporyIn.fasta" />
|
|
|
33 <param name="lipobox_mindist" value="10" />
|
|
|
34 <param name="lipobox_maxdist" value="60" />
|
|
|
35 <output name="default" value="T7_LiporyOut.gff3" />
|
|
|
36 </test>
|
|
|
37 </tests>
|
|
|
38 <help><![CDATA[
|
|
|
39 **What it does**
|
|
|
40
|
|
|
41 Identifies possible LipoBoxes from an input GFF3 and FASTA.
|
|
|
42
|
|
|
43 **How it works**
|
|
|
44
|
|
|
45 Searches in the first 10-40 amino acids of an input protein sequence using regular expressions
|
|
|
46 for a 4-amino acid motif based on the consensus sequences described in (**Babu** et al. 2006. *J
|
|
|
47 Bacteriol.* 188(8):2761-2773 and **Kongari** *et al.* 2018 *BMC Bioinformatics*. 19:326). The
|
|
|
48 amino acids allowed here are relaxed to allow for the diversity of amino acids known to occur in lipoboxes.
|
|
|
49
|
|
|
50 Position 1: ILMFTV or only A
|
|
|
51
|
|
|
52 Position 2: any residue except REKD or only W
|
|
|
53
|
|
|
54 Position 3: GAS
|
|
|
55
|
|
|
56 Position 4: C
|
|
|
57
|
|
|
58 ]]></help>
|
|
|
59 <expand macro="citations-2020" />
|
|
|
60 </tool>
|
