diff bp_genbank2gff3.xml @ 0:f79bcd53b9a3 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/bioperl commit 799339e22181d28cb2b145454d353d6025779636

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bp_genbank2gff3.xml	Fri Oct 09 09:19:49 2015 -0400
@@ -0,0 +1,122 @@
+<tool id="bp_genbank2gff3" name="Genbank to GFF3" version="1.0">
+  <description>converter</description>
+  <macros>
+      <import>macros.xml</import>
+  </macros>
+  <expand macro="stdio" />
+  <command><![CDATA[
+bp_genbank2gff3.pl
+$noinfer
+#if str($sofile.sofile) != "__none__":
+    --sofile
+    #if str($sofile.sofile) == "url":
+        "${sofile.so_url}"
+    #else:
+        live
+    #end if
+#end if
+--outdir -
+--ethresh $ethresh
+$model
+--typesource "${typesource}"
+
+$genbank
+> $gff3]]></command>
+  <inputs>
+    <param label="Genbank file" name="genbank" type="data" format="gb"/>
+    <param name="noinfer" truevalue="" falsevalue="--noinfer" checked="true" type="boolean" label="Infer exon/mRNA subfeatures"/>
+    <conditional name="sofile" label="Sequence Ontology">
+        <param name="sofile" label="Sequence Ontology File" type="select">
+            <option value="__none__" selected="True">None specified</option>
+            <option value="live">Latest Sequence Ontology</option>
+            <option value="url">User Specified</option>
+        </param>
+        <when value="__none__" />
+        <when value="live" />
+        <when value="url">
+            <param name="so_url" label="Sequence Ontology URL" type="text"/>
+        </when>
+    </conditional>
+    <param name="ethresh" label="Error threshold for unflattener" type="select">
+        <option value="0">Strict</option>
+        <option value="1" selected="True">Medium</option>
+        <option value="2">Loose</option>
+        <option value="3">Ignore Errors</option>
+    </param>
+    <param name="model" label="Gene Model" type="select">
+        <option value="--CDS" selected="True">Default GFF gene model</option>
+        <option value="--noCDS">Alternate gene-RNA-protein-exon model</option>
+    </param>
+    <param name="typesource" label="Sequence Ontology type for landmark feature" help="E.g. chromosome, region, contig" value="contig" type="text" />
+  </inputs>
+  <outputs>
+    <data format="gff3" name="gff3" label="${genbank.name} as GFF3"/>
+  </outputs>
+  <tests>
+      <test>
+          <param name="genbank" value="seq.gb" />
+          <param name="noinfer" value="True" />
+          <output name="gff3" file="seq.gb.0.gff" ftype="gff3" lines_diff="6"/>
+      </test>
+      <test>
+          <param name="genbank" value="seq.gb" />
+          <output name="gff3" file="seq.gb.1.gff" ftype="gff3" lines_diff="4"/>
+      </test>
+  </tests>
+  <help><![CDATA[
+**What it does**:
+
+This tool uses Bio::SeqFeature::Tools::Unflattener and
+Bio::Tools::GFF to convert GenBank flatfiles to GFF3 with gene
+containment hierarchies mapped for optimal display in gbrowse.
+
+The input files are assumed to be gzipped GenBank flatfiles for refseq
+contigs. The files may contain multiple GenBank records.
+
+**Designed for RefSeq**
+
+This script is designed for RefSeq genomic sequence entries.  It may
+work for third party annotations but this has not been tested.
+But see below, Uniprot/Swissprot works, EMBL and possibly EMBL/Ensembl
+if you don't mind some gene model unflattener errors (dgg).
+
+**G-R-P-E Gene Model**
+
+Don Gilbert worked this over with needs to produce GFF3 suited to
+loading to GMOD Chado databases.
+
+This writes GFF with an alternate, but useful Gene model,
+instead of the consensus model for GFF3
+
+  [ gene > mRNA> (exon,CDS,UTR) ]
+
+This alternate is
+
+  gene > mRNA > polypeptide > exon
+
+means the only feature with dna bases is the exon.  The others
+specify only location ranges on a genome. Exon of course is a child
+of mRNA and protein/peptide.
+
+The protein/polypeptide feature is an important one, having all the
+annotations of the GenBank CDS feature, protein ID, translation, GO
+terms, Dbxrefs to other proteins.
+
+UTRs, introns, CDS-exons are all inferred from the primary exon bases
+inside/outside appropriate higher feature ranges.  Other special gene
+model features remain the same.
+
+**Authors**
+
+Sheldon McKay ([e-mail])
+
+Copyright (c) 2004 Cold Spring Harbor Laboratory.
+
+**Author of hacks for GFF2Chado loading**
+
+Don Gilbert ([e-mail])
+      ]]></help>
+  <citations>
+    <citation type="doi">10.1101/gr.361602</citation>
+  </citations>
+</tool>