Mercurial > repos > cpt > cpt_shinefind

annotate 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
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
4
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
1 <tool id="edu.tamu.cpt.genbank.shinefind" name="Shine Find" version="21.1.0.0">
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
2 <description>Identify shine-dalgarno sequences</description>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
3 <macros>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
4 <import>macros.xml</import>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
5 <import>cpt-macros.xml</import>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
6 </macros>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
7 <expand macro="requirements"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
8 <command detect_errors="aggressive"><![CDATA[
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
9 @GENOME_SELECTOR_PRE@
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
10
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
11 python '$__tool_directory__/shinefind.py'
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
12
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
13 @GENOME_SELECTOR@
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
14 '$gff3_data'
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
15
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
16 --table_output '$default_output'
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
17 --gff3_output '$gff3_output'
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
18
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
19 --lookahead_min '$lookahead_min'
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
20 --lookahead_max '$lookahead_max'
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
21 '$add'
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
22 '$top_only'
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
23
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
24
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
25 > '$stdout'
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
26
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
27 ]]></command>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
28 <inputs>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
29 <expand macro="genome_selector"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
30 <expand macro="gff3_input"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
31 <param label="Minimum number of bases upstream of CDS for gap (--lookahead_min)" name="lookahead_min" type="integer" value="3"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
32 <param label="Maximum number of bases upstream of CDS for gap (--lookahead_max)" name="lookahead_max" type="integer" value="17"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
33 <param checked="true" label="Automatically add RBSs to input GFF3" name="add" type="boolean" truevalue="--add" falsevalue=""/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
34 <param checked="true" label="Only report best hits (--top_only)" name="top_only" type="boolean" falsevalue="" truevalue="--top_only"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
35 </inputs>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
36 <outputs>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
37 <data format="tabular" name="default_output" label="ShineFind RBS list from $gff3_data.name"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
38 <data format="gff3" name="gff3_output" label="ShineFind GFF3 RBSs from $gff3_data.name"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
39 <data format="gff3" name="stdout" label="$gff3_data.name with RBSs"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
40 </outputs>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
41 <tests>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
42 <test>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
43 <param name="genome_fasta" value="Miro_ShineFindIn.fa"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
44 <param name="reference_genome_source" value="history"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
45 <param name="gff3_data" value="Miro_ShineFindIn.gff3"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
46 <param name="lookahead_max" value="15"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
47 <param name="lookahead_min" value="5"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
48 <param name="add" value="True"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
49 <param name="top_only" value="False"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
50 <output name="default_output" file="Miro_ShineFindOut.tbl"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
51 <output name="gff3_output" file="Miro_ShineFindOut1.gff3"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
52 <output name="stdout" file="Miro_ShineFindOut2.gff3"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
53 </test>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
54 </tests>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
55 <help><![CDATA[
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
56 **What it does**
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
57
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
58 From an input GFF3 and FASTA file, the upstream sequence within user-specified bounds is
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
59 extracted for all CDS features. Input CDS features with an RBS are not re-analyzed. For
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
60 the remaining CDS features, the upstream sequence is searched against the following
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
61 possible Shine-Dalgarno sequences:
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
62 - AGGAGGT
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
63 - GGAGGT
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
64 - AGGAGG
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
65 - AGGAG
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
66 - GAGGT
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
67 - GGAGG
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
68 - AGGT
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
69 - GGGT
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
70 - GAGG
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
71 - GGGG
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
72 - AGGA
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
73 - GGAG
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
74 - GGA
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
75 - GAG
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
76 - AGG
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
77 - GGT
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
78
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
79 **Gap Min/Max Settings**
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
80 In previous versions of this tool, the min/max was set for the window to find a Shine-Dalgarno sequence, but
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
81 currently we specify the minimum and maxium GAP between the end of the SD and the start of the closest CDS.
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
82
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
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.
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
84 By selecting ‘No’ for ‘Only report best hits’, **all hits** to the possible SD list will
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
85 be added to the GFF3 file.
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
86
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
87 **March 10, 2021 Update**
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
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.
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
89
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
90 ]]></help>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
91 <expand macro="citations">
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
92 <expand macro="sl-citations-clm"/>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
93 </expand>
5004ddb62700 planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c
cpt
parents:
diff changeset
94 </tool>