--- a/gstf_preparation.xml	Mon Apr 16 14:05:09 2018 -0400
+++ b/gstf_preparation.xml	Wed Apr 25 11:00:33 2018 -0400
@@ -20,8 +20,12 @@
 #if $longestCDS
     -l
 #end if
+#if $regions
+    --regions '$regions'
+#end if
 -o '$output_db'
 --of '$output_fasta'
+--ff '$filtered_fasta'
 ]]>
     </command>
 
@@ -36,11 +40,13 @@
         <param name="fasta_inputs" type="data" format="fasta" multiple="true" label="Corresponding FASTA datasets" help="Each FASTA header line should start with a transcript id" />
         <param name="longestCDS" type="boolean" checked="false" label="Keep only the longest CDS per gene" />
         <param name="headers" type="boolean" checked="true" label="Change the header line of the FASTA sequences to the &gt;TranscriptId_species format" help="As required by TreeBest, part of the GeneSeqToFamily workflow" />
+        <param name="regions" type="text" optional="true" label="Comma-separated list of region IDs (e.g. chromosomes or scaffolds) for which FASTA sequences should be filtered" help="Region IDs are in the `seqid` column for GFF3 and in the `seq_region_name` field in JSON. This is typically used to filter chromosomes with a non-standard genetic code, like mitochondria, to be analysed separately" />
     </inputs>
 
     <outputs>
          <data name="output_db" format="sqlite" label="${tool.name} on ${on_string}: SQLite" />
          <data name="output_fasta" format="fasta" label="${tool.name} on ${on_string}: FASTA" />
+         <data name="filtered_fasta" format="fasta" label="${tool.name} on ${on_string}: filtered sequences" />
     </outputs>
 
     <tests>
@@ -53,6 +59,7 @@
 
             <output name="output_db" file="test1.sqlite" compare="sim_size" />
             <output name="output_fasta" file="test1.fasta" />
+            <output name="filtered_fasta" file="test1.ns.fasta" />
         </test>
         <test>
             <param name="fasta_inputs" ftype="fasta" value="Caenorhabditis_elegans.WBcel235.cds.all.shortened.fa" />
@@ -63,6 +70,7 @@
 
             <output name="output_db" file="test1.sqlite" compare="sim_size" />
             <output name="output_fasta" file="test1_longest.fasta" />
+            <output name="filtered_fasta" file="test1.ns.fasta" />
         </test>
         <test>
             <param name="fasta_inputs" ftype="fasta" value="Caenorhabditis_elegans.WBcel235.cds.all.shortened.fa" />
@@ -73,6 +81,7 @@
 
             <output name="output_db" file="test1.sqlite" compare="sim_size" />
             <output name="output_fasta" file="Caenorhabditis_elegans.WBcel235.cds.all.shortened.fa" />
+            <output name="filtered_fasta" file="test1.ns.fasta" />
         </test>
         <test>
             <param name="fasta_inputs" ftype="fasta" value="CDS.fasta" />
@@ -80,8 +89,20 @@
             <param name="longestCDS" value="false" />
             <param name="headers" value="true" />
 
-            <output name="output_db" file="test2.sqlite" compare="sim_size" />
-            <output name="output_fasta" file="test2.fasta" />
+            <output name="output_db" file="test4.sqlite" compare="sim_size" />
+            <output name="output_fasta" file="test4.fasta" />
+            <output name="filtered_fasta" file="test4.ns.fasta" />
+        </test>
+        <test>
+            <param name="fasta_inputs" ftype="fasta" value="CDS.fasta" />
+            <param name="json" ftype="json" value="gene.json" />
+            <param name="longestCDS" value="false" />
+            <param name="headers" value="true" />
+            <param name="regions" value="X" />
+
+            <output name="output_db" file="test5.sqlite" compare="sim_size" />
+            <output name="output_fasta" file="test5_filtered.fasta" />
+            <output name="filtered_fasta" file="test5.ns.fasta" />
         </test>
     </tests>
     <help>