Mercurial > repos > iuc > find_nested_alt_orfs

comparison find_nested_alt_orfs.xml @ 0:14f4c7a8a962 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/naltorfs/ commit cbedf7b5968b45a08df88d4ad799951d6f50a2bd"
author iuc
date Mon, 11 Apr 2022 20:37:19 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:14f4c7a8a962
1 <tool id="find_nested_alt_orfs" name="Find Nested Alternate ORFs (nAlt-ORFs)" version="@TOOL_VERSION@" profile="20.05">
2 <description>from BED and 2bit/FASTA</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="edam_ontology"/>
7 <expand macro="requirements">
8 <requirement type="package" version="377">ucsc-fatotwobit</requirement>
9 </expand>
10 <version_command>find_nested_alt_orfs.py --version</version_command>
11 <command detect_errors="exit_code"><![CDATA[
12 #if $ref.ref_source == 'history':
13 #if $ref.ref_file.is_of_type('fasta'):
14 #set $twobit_filename = "out.2bit"
15 faToTwoBit '${ref.ref_file}' '$twobit_filename' -stripVersion &&
16 #else:
17 #set $twobit_filename = $ref.ref_file
18 #end if
19 #else:
20 #set $twobit_filename = $ref.ref_loc.fields.path
21 #end if
22 find_nested_alt_orfs.py
23 --twobit '$twobit_filename'
24
25 --min_length '$min_length'
26
27 --reference '${input.metadata.dbkey}'
28
29 --bed '$input'
30
31 #if $no_canonical_cds:
32 --no_canonical_cds '$no_canonical_cds'
33 #end if
34
35 --translation_table '$translation_table'
36
37 --bed_out '$bed_out'
38
39 --peptide_fasta_out '$peptide_fasta_out'
40
41 --naltorfs_fasta_out '$naltorfs_fasta_out'
42
43 --cds_fasta_out '$cds_fasta_out'
44
45 $unique_sequences
46
47 #if $write_log:
48 --log '$log'
49 #end if
50 ]]></command>
51 <inputs>
52 <param argument="--bed" name="input" type="data" format="bed" label="Gene BED" help="A BED file with 12 columns"/>
53 <conditional name="ref">
54 <param name="ref_source" type="select" label="Source for Genomic Sequence Data">
55 <option value="cached">Locally cached genome</option>
56 <option value="history">History dataset genome</option>
57 </param>
58 <when value="cached">
59 <param argument="--twobit" name="ref_loc" type="select" label="Select reference genome">
60 <options from_data_table="twobit"/>
61 </param>
62 </when>
63 <when value="history">
64 <param argument="--twobit" name="ref_file" type="data" format="twobit,fasta" label="Reference genome"/>
65 </when>
66 </conditional>
67 <param argument="--min_length" type="integer" value="150" min="1" label="Minimum length of peptide translation to report"/>
68 <param argument="--unique_sequences" type="boolean" truevalue="--unique_sequences" falsevalue="" checked="True" label="Only report the first unique occurrence of an alternate sequence"/>
69 <param argument="--no_canonical_cds" type="data" format="bed" optional="True" label="Do not report any alternate sequences that match a provided canonical CDS" help="A BED file with 12 columns"/>
70 <expand macro="translation_table_select_parameter"/>
71 <param name="write_log" type="boolean" truevalue="true" falsevalue="false" checked="True" label="Create log file"/>
72 </inputs>
73 <outputs>
74 <data name="bed_out" format="bed" label="Find Nested nAlt-ORFs on ${on_string}: nAlt-ORFs.proBed">
75 <actions>
76 <action name="column_names" type="metadata" default="chrom,chromStart,chromEnd,name,score,strand,thickStart,thickEnd,itemRgb,blockCount,blockSizes,blockStarts,proteinAccession,peptideSequence,uniqueness,genomeReferenceVersion,psmScore,fdr,modifications,charge,expMassToCharge,calcMassToCharge,psmRank,datasetID,uri"/>
77 </actions>
78 </data>
79 <data name="peptide_fasta_out" format="fasta" label="Find nAlt-ORFs on ${on_string}: peptide.fasta"/>
80 <data name="naltorfs_fasta_out" format="fasta" label="Find nAlt-ORFs on ${on_string}: nAlt-ORFs.fasta"/>
81 <data name="cds_fasta_out" format="fasta" label="Find nAlt-ORFs on ${on_string}: canonical CDS.fasta"/>
82 <data name="log" format="txt" label="Find nAlt-ORFs on ${on_string}: log.txt">
83 <filter>write_log</filter>
84 </data>
85 </outputs>
86 <tests>
87 <test>
88 <param name="input" value="gencode_canonical.hg38.chr6_GL0002508.bed" dbkey="hg38" ftype="bed12"/>
89 <conditional name="ref">
90 <param name="ref_source" value="history"/>
91 <param name="ref_file" value="hg38.chr6_GL000250v2_alt.2bit.gz" dbkey="hg38" ftype="twobit"/>
92 </conditional>
93 <param name="min_length" value="150"/>
94 <param name="unique_sequences" value="true"/>
95 <param name="no_canonical_cds" value="gencode_canonical.hg38.chr6_GL0002508.bed" dbkey="hg38" ftype="bed12"/>
96 <param name="translation_table" value="1"/>
97 <param name="write_log" value="true"/>
98 <output name="bed_out" value="bed_out.bed"/>
99 <output name="peptide_fasta_out" value="peptide_fasta_out.fasta"/>
100 <output name="naltorfs_fasta_out" value="naltorfs_fasta_out.fasta"/>
101 <output name="cds_fasta_out" value="cds_fasta_out.fasta"/>
102 <output name="log" value="find_naltorfs_log.txt"/>
103 </test>
104 </tests>
105 <help><![CDATA[
106 Find Nested Alternate Open Reading Frames (nAlt-ORFs).
107
108 Using a BED12 file containing the location of genes, and a matching reference genome,
109 this tool searches in the alternate reading frames of the provided canonical coding sequence,
110 and outputs nested alternate ORFs which match the provided thresholds.
111
112 Translation table identifiers are based upon NCBI standards (https://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi).
113 ]]></help>
114 <expand macro="citations"/>
115 </tool>