Skip to content

Commit

Permalink
Add tsebra (#5483)
Browse files Browse the repository at this point in the history
* Add tsebra

* error typo

* add .shed.yml

* Update .shed.yml

* add column names and number-test

* size test inputs + modify test section

* modify test 2

* new output.gtf

* test

* Add tsebra

* modify test 2

* Modify test 2

* test 2

* test 2

* test 2

* small changes

* modify tsebra.xml

* change tsebra.xml

* News modifications

---------

Co-authored-by: Björn Grüning <[email protected]>
  • Loading branch information
rlibouba and bgruening authored Oct 19, 2023
1 parent 07802a6 commit 7dadb01
Show file tree
Hide file tree
Showing 7 changed files with 22,122 additions and 0 deletions.
10 changes: 10 additions & 0 deletions tools/tsebra/.shed.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
categories:
- Genome annotation
description: This tool has been developed to combine BRAKER predictions.
long_description: |
TSEBRA is a combinatorial tool that selects transcripts from genetic predictions based on support by extrinsic evidence
in the form of introns and start/stop codpns.
homepage_url: https://github.com/Gaius-Augustus/TSEBRA
owner: iuc
remote_repository_url: https://github.com/galaxyproject/tools-iuc/tree/master/tools/tsebra
type: unrestricted
8 changes: 8 additions & 0 deletions tools/tsebra/macros.xml
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
<macros>
<token name="@TOOL_VERSION@">1.1.1</token>
<xml name="citation">
<citations>
<citation type="doi">/10.1186/s12859-021-04482-0</citation>
</citations>
</xml>
</macros>
10,700 changes: 10,700 additions & 0 deletions tools/tsebra/test-data/braker.gtf

Large diffs are not rendered by default.

2,582 changes: 2,582 additions & 0 deletions tools/tsebra/test-data/hintsfile.gff

Large diffs are not rendered by default.

8,060 changes: 8,060 additions & 0 deletions tools/tsebra/test-data/output.txt

Large diffs are not rendered by default.

668 changes: 668 additions & 0 deletions tools/tsebra/test-data/output_tab.txt

Large diffs are not rendered by default.

94 changes: 94 additions & 0 deletions tools/tsebra/tsebra.xml
Original file line number Diff line number Diff line change
@@ -0,0 +1,94 @@
<?xml version="1.0"?>
<tool id="tsebra" name="TSEBRA" version="@TOOL_VERSION@+galaxy0" profile="21.05">
<description>tanscript selector for BRAKER</description>
<macros>
<import>macros.xml</import>
</macros>
<requirements>
<requirement type="package" version="@TOOL_VERSION@">tsebra</requirement>
</requirements>
<command detect_errors="exit_code"><![CDATA[
tsebra.py
#if str( $gtf_file_param ) == "GTF":
-g '$gtf_input'
#elif str( $gtf_file_param ) == "KEEP_GTF":
-k '$gtf_input'
#end if
#if $hint_file
-e '$hint_file'
#end if
#if $cfg_file
-c '$cfg_file'
#end if
$ignore_tx_phase
#if $filter_exon
--filter_single_exon_genes
#end if
#if $score_tab
--score_tab '$output_tab'
#end if
-o '$output'
]]></command>
<inputs>
<param name="gtf_input" type="data" format="gtf" label="GTF input"/>
<param name="gtf_file_param" type="select" label="Choose the analysis parameter for the gtf file">
<option value="GTF" selected="true">List of gene prediciton files</option>
<option value="KEEP_GTF">All transcripts from these gene sets will be included in the output</option>
</param>
<param name="hint_file" argument="-e" type="data" format="gff" optional="true" label="List of files containing extrinsic evidence"/>
<param name="cfg_file" argument="-c" type="data" format="txt" optional="true" label="Configuration file" help="Find the recommanded parameter at config/default.cfg"/>
<param name="score_tab" argument="-s" type="boolean" checked="false" label="Print the transcript scores as a table to the specified file"/>
<param name="ignore_transcrpts" type="boolean" label="Ignore the phase transcripts while detecting clusters of overlapping transcripts"/>
<param name="filter_exon" type="boolean" label="Filter out all single-exon genes"/>
<param argument="--ignore_tx_phase" type="boolean" truevalue="--ignore_tx_phase" falsevalue="" label="Ignore the phase transcripts while detecting clusters of overlapping transcripts"/>
</inputs>

<outputs>
<data name="output" format="gtf" label="TSEBRA on ${on_string}"/>
<data name="output_tab" format="txt" label="TSEBRA on ${on_string} : tab">
<actions>
<action name="column_names" type="metadata" default="TX_ID,intron_support,stasto_support,s1,s2,s3,s4" />
</actions>
<filter>score_tab</filter>
</data>
</outputs>

<tests>
<test expect_num_outputs="1">
<param name="gtf_input" value="braker.gtf" ftype="gtf"/>
<param name="hint_file" value="hintsfile.gff" ftype="gff"/>
<param name="score_tab" value="false"/>
<param name="gtf_file_param" value="GTF"/>
<output name="output" ftype="gtf" file="output.gtf" lines_diff="2"/>
</test>

<test expect_num_outputs="2">
<param name="gtf_input" value="braker.gtf" ftype="gtf"/>
<param name="hint_file" value="hintsfile.gff" ftype="gff"/>
<param name="score_tab" value="true"/>
<param name="gtf_file_param" value="GTF"/>
<output name="output" ftype="gtf" file="output.gtf" lines_diff="2"/>
<output name="output_tab" ftype="txt" file="output_tab.txt">
<assert_contents>
<has_text text="anno1;g1.t1"/>
<has_text text="anno1;g84.t1"/>
</assert_contents>
</output>
</test>
</tests>

<help><![CDATA[
tsebra_ TSEBRA is a combinatorial tool that selects transcripts from genetic predictions based on support by extrinsic evidence
in the form of introns and start/stop codpns. This tool has been developed to combine BRAKER predictions.
.. _tsebra: https://github.com/Gaius-Augustus/TSEBRA
]]></help>
<expand macro="citation"></expand>
</tool>

0 comments on commit 7dadb01

Please sign in to comment.