diff gff3_rebase.xml @ 0:e54940ea270c draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gff3_rebase commit 350ab347625ed5941873ba0deb3e1cf219d60052

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/gff3_rebase.xml	Thu Apr 20 08:12:49 2017 -0400
@@ -0,0 +1,93 @@
+<tool id="gff3.rebase" name="Rebase GFF3 features" version="1.2">
+  <description>against parent features</description>
+  <macros>
+    <import>macros.xml</import>
+  </macros>
+  <expand macro="requirements"/>
+  <version_command>python gff3_rebase.py --version</version_command>
+  <command detect_errors="aggressive"><![CDATA[
+    python '$__tool_directory__/gff3_rebase.py'
+    '$parent'
+    '$child'
+
+    $interpro
+    $protein2dna
+    > '$output']]>
+  </command>
+  <inputs>
+    <param label="Parent GFF3 annotations" name="parent" format="gff3" type="data"/>
+    <param label="Child GFF3 annotations to rebase against parent" name="child" format="gff3" type="data"/>
+
+    <param label="Interpro specific modifications" name="interpro" type="boolean" truevalue="--interpro" falsevalue=""/>
+    <param label="Map protein translated results to original DNA data" name="protein2dna" type="boolean" truevalue="--protein2dna" falsevalue=""/>
+  </inputs>
+  <outputs>
+    <data format="gff3" name="output"/>
+  </outputs>
+  <tests>
+      <test>
+          <param name="parent" value="parent.gff"/>
+          <param name="child" value="child.gff"/>
+          <param name="protein2dna" value="True" />
+          <output name="output" file="proteins.gff"/>
+      </test>
+  </tests>
+  <help><![CDATA[
+**What it does**
+
+Often the genomic data processing/analysis process requires a workflow like the following:
+
+-  select some features from a genome
+-  export the sequences associated with those regions
+-  analyse those exports with some tool like Blast
+
+For display, especially in software like JBrowse, it is convenient to know
+where in the original genome the analysis results would fall. E.g. if a
+transmembrane domain is detected at bases 10-20 of an analysed protein, where
+should this be displayed relative to the parent genome?
+
+This tool helps fill that gap, by rebasing some analysis results against the
+parent features which were originally analysed.
+
+**Example Inputs**
+
+For a "child" set of annotations like::
+
+    #gff-version 3
+    cds42	blastp	match_part	1	50	1e-40	.	.	ID=m00001;Notes=RNAse A Protein
+
+And a parent set of annotations like::
+
+    #gff-version 3
+    PhageBob	maker	cds	300	600	.	+	.	ID=cds42
+
+One could imagine that during the analysis process, the user had exported the parent annotation into some sequence::
+
+    >cds42
+    M......
+
+and then analysed those results, producing the "child" annotation file. This
+tool will then localize the results properly against the parent::
+
+    #gff-version 3
+    PhageBob	blastp	match_part	300	449	1e-40	+	.	ID=m00001;Notes=RNAse A Protein
+
+which will allow you to display the results in the correct location in visualizations.
+
+**Options**
+
+There are two optional flags which can be passed.
+
+The Interpro flag selectively ignores features which shouldn't be included in
+the output (i.e. ``polypeptide``), and a couple of qualifiers that aren't
+useful (``status``, ``Target``)
+
+The "Map Protein..." flag says that you translated the sequences during the
+genomic export process, analysing protein sequences. This indicates to the
+software that the bases should be multiplied by three to obtain the correct DNA
+locations.
+]]></help>
+    <citations>
+        <citation type="doi">10.1093/bioinformatics/btp163</citation>
+    </citations>
+</tool>