Mercurial > repos > cpt > cpt_sar_finder

annotate SAR_finder.xml @ 1:112751823323 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
author cpt
date Mon, 05 Jun 2023 02:52:57 +0000
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
1
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
1 <tool id="edu.tamu.cpt.sar.sar_finder" name="SAR Finder" version="1.0">
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
2 <description>SAR Domain Finder</description>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
3 <macros>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
4 <import>macros.xml</import>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
5 </macros>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
6 <expand macro="requirements">
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
7 </expand>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
8 <command detect_errors="aggressive"><![CDATA[
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
9 python '$__tool_directory__/SAR_finder.py'
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
10 '$fa'
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
11 --sar_min '$sar_min'
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
12 --sar_max '$sar_max'
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
13 --out_fa '$out_fa'
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
14 --out_gff3 '$out_gff3'
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
15 --out_stat '$out_stat'
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
16 ]]></command>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
17 <inputs>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
18 <param label="Multi FASTA File" name="fa" type="data" format="fasta"/>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
19 <param label="SAR domain minimal size" name="sar_min" type="integer" value="15"/>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
20 <param label="SAR domain maximum size" name="sar_max" type="integer" value="20"/>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
21 </inputs>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
22 <outputs>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
23 <data format="tabular" name="out_stat" label="candidate_SAR_stats.tsv"/>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
24 <data format="fasta" name="out_fa" label="candidate_SAR.fa"/>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
25 <data format="gff3" name="out_gff3" label="candidate_SAR.gff3"/>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
26 </outputs>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
27 <tests>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
28 <test>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
29 <param name="fa" value="simple-proteins.fa"/>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
30 <param name="sar_min" value="15"/>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
31 <param name="sar_max" value="20"/>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
32 <output name="out_stat" file="candidate_SAR_stats.tsv"/>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
33 <output name="out_fa" file="candidate_SAR.fa"/>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
34 <output name="out_gff3" file="candidate_SAR.gff3"/>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
35 </test>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
36 </tests>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
37 <help><![CDATA[
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
38
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
39 **What it does**
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
40 A tool that analyzes the sequence within the first 50 residues of a protein for a weakly hydrophobic domain called Signal-Anchor-Release (aka SAR).
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
41 The tool finds proteins that contain a stretch (default 15-20 residues) of hydrophobic residues (Ile, Leu, Val, Phe, Tyr, Trp, Met, Gly, Ala, Ser) and
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
42 calculates the % Gly/Ala/Ser/Thr residues in the hydrophobic stretch. The net charge on the N-terminus is also displayed to aid in determining the
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
43 SAR orientation in the membrane.[2]
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
44
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
45 Definition: A Signal-Anchor-Release (SAR) domain is an N-terminal, weakly hydrophobic transmembrane region rich in Gly/Ala and/or Ser (and sometimes Thr) residues.
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
46 The SAR domain is sometimes found in phage lysis proteins, including endolysins and holins. The SAR domain can be released from the membrane in a proton
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
47 motive force-dependent manner. Known SAR domains in phage endolysins often have >50-60% Gly/Ala/Ser/Thr content. SAR endolysins are expected to have a net positive
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
48 charge on the N-terminus by the positive-inside rule.
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
49
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
50 **INPUT** --> Protein Multi FASTA
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
51
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
52 **OUTPUT** -->
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
53
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
54 * Multi FASTA with candidate proteins that pass the SAR domain criteria
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
55
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
56 * Tabular summary file that lists every subdomain fitting the criteria for each potential SAR domain-containing protein with the following: protein name/sequence/length, SAR length/start/sequence/end, individual and total GAST% content in SAR, and N-terminal sequence/net charge
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
57
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
58 * Multi GFF3 for unique candidate SAR domain-containing proteins
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
59
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
60 ]]></help>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
61 <citations>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
62 <citation type="doi">10.1371/journal.pcbi.1008214</citation>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
63 <citation type="doi">https://dx.doi.org/10.1016/bs.aivir.2018.09.003</citation>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
64 <citation type="bibtex">
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
65 @unpublished{galaxyTools,
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
66 author = {C. Ross},
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
67 title = {CPT Galaxy Tools},
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
68 year = {2020-},
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
69 note = {https://github.com/tamu-cpt/galaxy-tools/}
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
70 }
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
71 </citation>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
72 </citations>
112751823323 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
73 </tool>