Mercurial > repos > iuc > evidencemodeler

comparison evidencemodeler.xml @ 0:92d95470befc draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/evidencemodeler commit 982fe890ba21272719fe6f5cb04707c4c91fca0d
author iuc
date Sun, 15 Sep 2024 10:12:13 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:92d95470befc
1 <tool id="evidencemodeler" name="EVidenceModeler" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
2 <description>combines ab intio gene predictions, protein and transcript alignments into gene structures</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <xrefs>
7 <xref type="bio.tools">EvidenceModeler</xref>
8 </xrefs>
9 <expand macro="requirements"/>
10
11 <command detect_errors="exit_code"><![CDATA[
12
13 ln -s '$input_genome' ./input_genome.fasta &&
14 ln -s '$input_predictions' ./input_predictions.gff &&
15 ln -s '$input_weights' ./input_weights.txt &&
16 ln -s '$input_proteins' ./input_proteins.gff &&
17 ln -s '$input_transcript' ./input_transcript.gff &&
18
19 EVidenceModeler
20 --sample_id galaxy
21 --genome './input_genome.fasta'
22 --gene_predictions './input_predictions.gff'
23 --weights './input_weights.txt'
24 --protein_alignments './input_proteins.gff'
25 --segmentSize $segmentsize
26 --overlapSize $overlapsize
27
28 #if $input_transcript:
29 --transcript_alignments './input_transcript.gff'
30 #end if
31
32 #if $opt.input_repeat:
33 --repeats '$opt.input_repeat'
34 #end if
35
36 #if $opt.input_terminalexon:
37 --terminalExons '$opt.input_terminalexon'
38 #end if
39
40 --stop_codons $opt.stop_codon
41 --min_intron_length $opt.min_intron_length
42 --search_long_introns $opt.search_long_introns
43 --re_search_intergenic $opt.re_search_intergenic
44 --terminal_intergenic_re_search $opt.terminal_intergenic_re_search
45
46 ]]></command>
47
48 <inputs>
49 <param name="input_genome" type="data" format="fasta" label="Genome input"/>
50 <param name="input_predictions" type="data" format="gff3" label="Gene predictions input"/>
51 <param name="input_weights" type="data" format="gff3" label="Weights for evidence types file" help="See documentation for formatting: 'Weights' section"/>
52 <param name="input_proteins" type="data" format="gff3" label="Protein alignments input" help="Optional but recommended"/>
53 <param name="input_transcript" type="data" optional="true" format="gff3" label="Transcript alignments input" help="Optional but recommended"/>
54 <param argument="--segmentSize" name="segmentsize" value="100000" type="integer" label="Length of a single sequence" help="This value must be less than 1 MB" />
55 <param argument="--overlapSize" name="overlapsize" value="10000" type="integer" label="Length of sequence overlap between segmented sequences" help="The length must be at least equivalent to one or two expected gene lengths" />
56 <section name="opt" title="Advanced option" expanded="false">
57 <param name="input_repeat" type="data" optional="true" format="gff3" label="Masked genome repeats"/>
58 <param name="input_terminalexon" type="data" optional="true" format="gff3" label="Additional file of terminal exons to be taken into account" help="From long-orfs PASA"/>
59 <param name="stop_codon" argument="--stop_codons" type="select" multiple="true" optional="true" label="List of stop codon" help="For Tetrahymena, set TGA">
60 <option value="TAA,TGA,TAG" selected="true">TAA,TGA,TAG</option>
61 <option value="TAA">TAA</option>
62 <option value="TGA">TGA</option>
63 <option value="TAG">TAG</option>
64 </param>
65 <param argument="--min_intron_length" type="integer" value="20" label="Minimum length for an intron" help="Default 20 bp" />
66 <param argument="--search_long_introns" type="select" label="Reexamine long introns" help="Can find nested genes, but also can result in false positives">
67 <option value="0" selected="true">Off</option>
68 <option value="1">On</option>
69 </param>
70 <param argument="--re_search_intergenic" type="select" label="Reexamines intergenic regions of minimum length">
71 <option value="0" selected="true">Off</option>
72 <option value="1">On</option>
73 </param>
74 <param argument="--terminal_intergenic_re_search" type="select" label="Reexamines intergenic regions of minimum length">
75 <option value="0" selected="true">Off</option>
76 <option value="1">On</option>
77 </param>
78 </section>
79 </inputs>
80
81 <outputs>
82 <data name='evm_gff' format='gff' label="${tool.name} on ${on_string}: GFF3" from_work_dir="galaxy.EVM.gff3"/>
83 <data name='evm_pep' format='fasta' label="${tool.name} on ${on_string}: PEP" from_work_dir="galaxy.EVM.pep"/>
84 </outputs>
85
86 <tests>
87 <test expect_num_outputs="2">
88 <param name="input_genome" value="genome.fasta"/>
89 <param name="input_predictions" value="gene_predictions.gff3"/>
90 <param name="input_weights" value="weights.txt"/>
91 <param name="input_proteins" value="protein_alignments.gff3"/>
92 <param name="input_transcript" value="transcript_alignments.gff3"/>
93 <param name="segmentsize" value="100000"/>
94 <param name="overlapsize" value="10000"/>
95 <conditional name="opt">
96 <param name="adv" value="true"/>
97 <param name="min_intron_length" value="20"/>
98 <param name="search_long_introns" value="0"/>
99 <param name="re_search_intergenic" value="0"/>
100 <param name="terminal_intergenic_re_search" value="0"/>
101 </conditional>
102 <output name="evm_pep" ftype="fasta">
103 <assert_contents>
104 <has_text text="evm.model.Contig1.3 evm.TU.Contig1.3 EVM prediction Contig1.3 Contig1:7611-9749(-)"/>
105 <has_text text="evm.model.Contig1.10 evm.TU.Contig1.10 EVM prediction Contig1.10 Contig1:57371-59941(+)"/>
106 <has_n_lines n="108" delta="0"/>
107 <has_n_columns n="1" delta="0"/>
108 </assert_contents>
109 </output>
110 <output name="evm_gff" ftype="gff">
111 <assert_contents>
112 <has_text text="ID=evm.TU.Contig1.1;Name=EVM%20prediction%20Contig1.1"/>
113 <has_text text="ID=evm.TU.Contig1.4;Name=EVM%20prediction%20Contig1.4"/>
114 <has_n_lines n="191" delta="0"/>
115 <has_n_columns n="9" delta="0"/>
116 <!-- the sep=";" is used to count the gff properties -->
117 <has_n_columns n="2" delta="0" sep=";"/>
118 </assert_contents>
119 </output>
120 </test>
121 </tests>
122
123 <help><![CDATA[
124 EvidenceModeler_: EVidenceModeler (aka EVM) is a software package that combines ab intio
125 gene predictions and protein and transcript alignments into weighted consensus gene structures.
126 EVM provides a flexible and intuitive framework for combining various types of evidence into a
127 single automated gene structure annotation system.
128
129 .. _EvidenceModeler: https://github.com/EVidenceModeler/EVidenceModeler.github.io
130 ]]></help>
131 <expand macro="citation"></expand>
132 </tool>