Mercurial > repos > cpt > cpt_shinefind

comparison shinefind.xml @ 4:5004ddb62700 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 02:53:31 +0000
parents
children 6a5aac2a4c89
comparison
equal deleted inserted replaced
3:4d4a4b603d33 4:5004ddb62700
1 <tool id="edu.tamu.cpt.genbank.shinefind" name="Shine Find" version="21.1.0.0">
2 <description>Identify shine-dalgarno sequences</description>
3 <macros>
4 <import>macros.xml</import>
5 <import>cpt-macros.xml</import>
6 </macros>
7 <expand macro="requirements"/>
8 <command detect_errors="aggressive"><![CDATA[
9 @GENOME_SELECTOR_PRE@
10
11 python '$__tool_directory__/shinefind.py'
12
13 @GENOME_SELECTOR@
14 '$gff3_data'
15
16 --table_output '$default_output'
17 --gff3_output '$gff3_output'
18
19 --lookahead_min '$lookahead_min'
20 --lookahead_max '$lookahead_max'
21 '$add'
22 '$top_only'
23
24
25 > '$stdout'
26
27 ]]></command>
28 <inputs>
29 <expand macro="genome_selector"/>
30 <expand macro="gff3_input"/>
31 <param label="Minimum number of bases upstream of CDS for gap (--lookahead_min)" name="lookahead_min" type="integer" value="3"/>
32 <param label="Maximum number of bases upstream of CDS for gap (--lookahead_max)" name="lookahead_max" type="integer" value="17"/>
33 <param checked="true" label="Automatically add RBSs to input GFF3" name="add" type="boolean" truevalue="--add" falsevalue=""/>
34 <param checked="true" label="Only report best hits (--top_only)" name="top_only" type="boolean" falsevalue="" truevalue="--top_only"/>
35 </inputs>
36 <outputs>
37 <data format="tabular" name="default_output" label="ShineFind RBS list from $gff3_data.name"/>
38 <data format="gff3" name="gff3_output" label="ShineFind GFF3 RBSs from $gff3_data.name"/>
39 <data format="gff3" name="stdout" label="$gff3_data.name with RBSs"/>
40 </outputs>
41 <tests>
42 <test>
43 <param name="genome_fasta" value="Miro_ShineFindIn.fa"/>
44 <param name="reference_genome_source" value="history"/>
45 <param name="gff3_data" value="Miro_ShineFindIn.gff3"/>
46 <param name="lookahead_max" value="15"/>
47 <param name="lookahead_min" value="5"/>
48 <param name="add" value="True"/>
49 <param name="top_only" value="False"/>
50 <output name="default_output" file="Miro_ShineFindOut.tbl"/>
51 <output name="gff3_output" file="Miro_ShineFindOut1.gff3"/>
52 <output name="stdout" file="Miro_ShineFindOut2.gff3"/>
53 </test>
54 </tests>
55 <help><![CDATA[
56 **What it does**
57
58 From an input GFF3 and FASTA file, the upstream sequence within user-specified bounds is
59 extracted for all CDS features. Input CDS features with an RBS are not re-analyzed. For
60 the remaining CDS features, the upstream sequence is searched against the following
61 possible Shine-Dalgarno sequences:
62 - AGGAGGT
63 - GGAGGT
64 - AGGAGG
65 - AGGAG
66 - GAGGT
67 - GGAGG
68 - AGGT
69 - GGGT
70 - GAGG
71 - GGGG
72 - AGGA
73 - GGAG
74 - GGA
75 - GAG
76 - AGG
77 - GGT
78
79 **Gap Min/Max Settings**
80 In previous versions of this tool, the min/max was set for the window to find a Shine-Dalgarno sequence, but
81 currently we specify the minimum and maxium GAP between the end of the SD and the start of the closest CDS.
82
83 By default, only the first (closest to consensus) hit to the list is returned to the GFF3. In the case of a tie, it will select the smaller gap.
84 By selecting ‘No’ for ‘Only report best hits’, **all hits** to the possible SD list will
85 be added to the GFF3 file.
86
87 **March 10, 2021 Update**
88 Previous to this date, when using "Only report best hits" option the algorithm would pick the "first" one (moving downstream) found in the case of tied sequence length. After this date, it now will report the sequence with the smaller gap between the END of the SD sequence and the START of the CDS.
89
90 ]]></help>
91 <expand macro="citations">
92 <expand macro="sl-citations-clm"/>
93 </expand>
94 </tool>