--- a/transdecoder.xml	Thu Oct 08 12:33:46 2020 +0000
+++ b/transdecoder.xml	Mon Feb 01 20:51:40 2021 +0000
@@ -2,10 +2,11 @@
     <description>finds coding regions within transcripts</description>
     <macros>
         <token name="@TOOL_VERSION@">5.5.0</token>
-        <token name="@VERSION_SUFFIX@">0</token>
+        <token name="@VERSION_SUFFIX@">1</token>
     </macros>
     <requirements>
         <requirement type="package" version="@TOOL_VERSION@">transdecoder</requirement>
+        <requirement type="package" version="3.0">zip</requirement>
     </requirements>
     <version_command><![CDATA[TransDecoder.LongOrfs --version 2>&1 | grep 'TransDecoder.LongOrfs' | cut -f 2 -d ' ']]></version_command>
     <command detect_errors="exit_code"><![CDATA[
@@ -52,6 +53,7 @@
 #if 'log' in $oo.out
     |& tee '$out_log'
 #end if
+&& if ls 'output/'*'.pdf' >/dev/null 2>&1; then zip 'seqlogo.zip' 'output/'*'.pdf' -q -j; fi
     ]]></command>
     <inputs>
         <param argument="-t" type="data" format="fasta" label="Select file with transcripts"/>
@@ -84,7 +86,7 @@
         <section name="lo" title="LongOrfs options" expanded="true">
             <param argument="--gene_trans_map" type="data" format="tabular" optional="true" label="Select gene-to-transcript identifier mapping file" help="gene_id&lt;tab&gt;trans_id&lt;return&gt;"/>
             <param argument="-m" type="integer" value="100" min="1" label="Set minimum protein length"/>
-            <param argument="-S" type="boolean" truevalue="-S" falsevalue="" label="Activate strand-specificity?" help="Only analyse top strand."/>
+            <param argument="-S" type="boolean" truevalue="-S" falsevalue="" label="Activate strand-specificity?" help="Only analyse top strand?"/>
         </section>
         <section name="po" title="Predict options" expanded="true">
             <!-- 
@@ -106,8 +108,8 @@
                             <param argument="--retain_long_orfs_length" type="integer" value="1000000" min="0" label="Set long ORFs length" help="Retain all ORFs found that are equal or longer than these many nucleotides even if no other evidence marks it as coding."/>
                         </when>
                     </conditional>
-                    <param argument="--retain_blastp_hits" type="data" format="tabular" optional="true" label="Select BlastP result file" help="Any ORF with a blast match will be retained in the final output. (outfmt 6 format)"/>
-                    <param argument="--retain_pfam_hits" type="data" format="tabular" optional="true" label="Select Pfam result file" help="Domain table output file from running hmmscan to search Pfam. Any ORF with a pfam domain hit will be retained in the final output. (domtblout file)"/>
+                    <param argument="--retain_blastp_hits" type="data" format="tabular" optional="true" label="Select BlastP result file" help="Any ORF with a blast match will be retained in the final output. (tabular outfmt6 file)"/>
+                    <param argument="--retain_pfam_hits" type="data" format="tabular" optional="true" label="Select Pfam result file" help="Domain table output file from running hmmscan to search Pfam. Any ORF with a pfam domain hit will be retained in the final output. (tabular domtblout file)"/>
                     <param argument="--single_best_only" type="boolean" truevalue="--single_best_only" falsevalue="" label="Retain only the single best ORF per transcript?" help="Prioritized by homology than ORF length."/>
                     <param argument="--no_refine_starts" type="boolean" truevalue="--no_refine_starts" falsevalue="" label="Start refinement that identifies potential start codons for 5' partial ORFs using a PWM?"/>
                     <param argument="-T" type="integer" value="500" min="1" label="Set top longest ORFs to train Markov Model" help="The first (10*value) elements are selected for removing redundancies. Then number of longst ORFs of this value are selected from the non-redundant set."/>
@@ -115,8 +117,8 @@
                 <when value="no"/>
             </conditional>
         </section>
-        <section name="oo" title="Output options">
-            <param name="out" type="select" multiple="true" optional="false" label="Select output file(s)" help="Only shown in history if selected here and generated by the specific NOVOplasty run.">
+        <section name="oo" title="Output options" expanded="true">
+            <param name="out" type="select" multiple="true" optional="false" label="Select output file(s)" help="Only shown in history if selected here and generated by the specific run.">
                 <!-- LongOrfs -->
                 <option value="lo_cds">Longest ORFs (CDS)</option>
                 <option value="lo_gff3">Longest ORFs (GFF3)</option>
@@ -126,6 +128,7 @@
                 <option value="cds" selected="true">Results (CDS)</option>
                 <option value="gff3" selected="true">Results (GFF3)</option>
                 <option value="pep" selected="true">Results (PEP)</option>
+                <option value="plot">Plots</option>
                 <!-- Others -->
                 <option value="log">Log</option>
             </param>
@@ -155,52 +158,53 @@
         <data name="out_pep" format="fasta" from_work_dir="transcripts.fasta.transdecoder.pep" label="${tool.name} on ${on_string}: Results (PEP/FASTA)">
             <filter>'pep' in oo['out'] and po['predict_cond']['predict_sel'] == 'yes'</filter>
         </data>
+        <data name="out_plot" format="zip" from_work_dir="seqlogo.zip" label="${tool.name} on ${on_string}: Plots">
+            <filter>'plot' in oo['out'] and po['predict_cond']['predict_sel'] == 'yes'</filter>
+        </data>
         <!-- Others -->
         <data name="out_log" format="txt" label="${tool.name} on ${on_string}: Log">
             <filter>'log' in oo['out']</filter>
         </data>
     </outputs>
     <tests>
-        <!-- no test implemented for: gene_trans_map, retain_blastp_hits, retain_pfam_hits -->
-
         <!-- #1 default -->
         <test expect_num_outputs="5">
             <param name="t" value="transcripts.fasta"/>
             <!-- LongOrfs -->
             <output name="out_lo_pep">
                 <assert_contents>
-                    <has_n_lines n="772"/>
-                    <has_text_matching expression=".+comp874.+"/>
+                    <has_n_lines n="190"/>
+                    <has_line line=">CUFF.20.1.p2 type:3prime_partial len:205 gc:Universal CUFF.20.1:612-1(-)"/>
                 </assert_contents>
             </output>
             <!-- Predict -->
             <output name="out_bed">
                 <assert_contents>
-                    <has_n_lines n="337"/>
-                    <has_text_matching expression="comp98\_c0\_seq1.+"/>
+                    <has_n_lines n="81"/>
+                    <has_text_matching expression="CUFF\.9\.1.+"/>
                 </assert_contents>
             </output>
             <output name="out_cds">
                 <assert_contents>
-                    <has_n_lines n="6959"/>
-                    <has_text_matching expression=">comp98\_c0\_seq1.+"/>
+                    <has_n_lines n="1578"/>
+                    <has_line line=">CUFF.9.1.p1 GENE.CUFF.9.1~~CUFF.9.1.p1  ORF type:complete len:156 (+),score=36.30 CUFF.9.1:173-640(+)"/>
                 </assert_contents>
             </output>
             <output name="out_gff3">
                 <assert_contents>
-                    <has_n_lines n="2165"/>
-                    <has_text_matching expression="comp98\_c0\_seq1.+"/>
+                    <has_n_lines n="542"/>
+                    <has_text_matching expression="CUFF\.9\.1.+"/>
                 </assert_contents>
             </output>
             <output name="out_pep">
                 <assert_contents>
-                    <has_n_lines n="2644"/>
-                    <has_text_matching expression="comp98\_c0\_seq1.+"/>
+                    <has_n_lines n="608"/>
+                    <has_text_matching expression="CUFF\.9\.1.+"/>
                 </assert_contents>
             </output>
         </test>
         <!-- #2 -->
-        <test expect_num_outputs="8">
+        <test expect_num_outputs="9">
             <param name="t" value="transcripts.fasta"/>
             <param name="G" value="Acetabularia"/>
             <section name="lo">
@@ -211,58 +215,66 @@
                 <conditional name="predict_cond">
                     <param name="predict_sel" value="yes"/>
                     <conditional name="mode_cond">
-                        <param name="mode_sel" value="dynamic"/>
+                        <param name="mode_sel" value="strict"/>
+                        <param name="retain_long_orfs_length" value="1000001"/>
                     </conditional>
+                    <param name="retain_blastp_hits" value="blastp.outfmt6"/>
+                    <param name="retain_pfam_hits" value="pfam.domtblout"/>
                     <param name="single_best_only" value="true"/>
                     <param name="no_refine_starts" value="true"/>
                     <param name="T" value="501"/>
                 </conditional>
             </section>
             <section name="oo">
-                <param name="out" value="lo_pep,lo_gff3,lo_cds,bed,cds,gff3,pep,log"/>
+                <param name="out" value="lo_pep,lo_gff3,lo_cds,bed,cds,gff3,pep,plot,log"/>
             </section>
             <!-- LongOrfs -->
             <output name="out_lo_cds">
                 <assert_contents>
-                    <has_n_lines n="1454"/>
-                    <has_text_matching expression=">comp874\_c0\_seq1.+"/>
+                    <has_n_lines n="398"/>
+                    <has_text_matching expression="CUFF\.20\.1.+"/>
                 </assert_contents>
             </output>
             <output name="out_lo_gff3">
                 <assert_contents>
-                    <has_n_lines n="4565"/>
-                    <has_text_matching expression="comp874\_c0\_seq1.+"/>
+                    <has_n_lines n="1330"/>
+                    <has_text_matching expression="CUFF\.20\.1.+"/>
                 </assert_contents>
             </output>
             <output name="out_lo_pep">
                 <assert_contents>
-                    <has_n_lines n="1454"/>
-                    <has_text_matching expression=">comp874\_c0\_seq1.+"/>
+                    <has_n_lines n="398"/>
+                    <has_text_matching expression="CUFF\.20\.1.+"/>
                 </assert_contents>
             </output>
             <!-- Predict -->
             <output name="out_bed">
                 <assert_contents>
-                    <has_n_lines n="340"/>
-                    <has_text_matching expression="comp98\_c0\_seq1.+"/>
+                    <has_n_lines n="62"/>
+                    <has_text_matching expression="CUFF\.9\.1.+"/>
                 </assert_contents>
             </output>
             <output name="out_cds">
                 <assert_contents>
-                    <has_n_lines n="7512"/>
-                    <has_text_matching expression=">comp98\_c0\_seq1.+"/>
+                    <has_n_lines n="1312"/>
+                    <has_text_matching expression="CUFF\.9\.1.+"/>
                 </assert_contents>
             </output>
             <output name="out_gff3">
                 <assert_contents>
-                    <has_n_lines n="2000"/>
-                    <has_text_matching expression="comp98\_c0\_seq1.+"/>
+                    <has_n_lines n="395"/>
+                    <has_text_matching expression="CUFF\.9\.1.+"/>
                 </assert_contents>
             </output>
             <output name="out_pep">
                 <assert_contents>
-                    <has_n_lines n="2833"/>
-                    <has_text_matching expression=">comp98\_c0\_seq1.+"/>
+                    <has_n_lines n="500"/>
+                    <has_text_matching expression="CUFF\.9\.1.+"/>
+                </assert_contents>
+            </output>
+            <output name="out_plot">
+                <assert_contents>
+                    <has_size value="0"/>
                 </assert_contents>
             </output>
             <!-- Others -->
@@ -273,62 +285,61 @@
             </output>
         </test>
         <!-- #3 -->
-        <test expect_num_outputs="8">
-            <param name="t" value="transcripts.fasta"/>
-            <section name="po">
-                <conditional name="predict_cond">
-                    <param name="predict_sel" value="yes"/>
-                    <conditional name="mode_cond">
-                        <param name="mode_sel" value="strict"/>
-                        <param name="retain_long_orfs_length" value="1000001"/>
-                    </conditional>
-                </conditional>
+        <test expect_num_outputs="9">
+            <param name="t" value="pasa_assemblies.fasta"/>
+            <section name="lo">
+                <param name="gene_trans_map" value="pasa_genetransmap.txt"/>
             </section>
             <section name="oo">
-                <param name="out" value="lo_pep,lo_gff3,lo_cds,bed,cds,gff3,pep,log"/>
+                <param name="out" value="lo_pep,lo_gff3,lo_cds,bed,cds,gff3,pep,plot,log"/>
             </section>
             <!-- LongOrfs -->
             <output name="out_lo_cds">
                 <assert_contents>
-                    <has_n_lines n="772"/>
-                    <has_text_matching expression=">comp874\_c0\_seq1.+"/>
+                    <has_n_lines n="534"/>
+                    <has_text_matching expression=">asmbl\_236\.p1.+"/>
                 </assert_contents>
             </output>
             <output name="out_lo_gff3">
                 <assert_contents>
-                    <has_n_lines n="2486"/>
-                    <has_text_matching expression="comp874\_c0\_seq1.+"/>
+                    <has_n_lines n="1742"/>
+                    <has_text_matching expression="asmbl\_236.+"/>
                 </assert_contents>
             </output>
             <output name="out_lo_pep">
                 <assert_contents>
-                    <has_n_lines n="772"/>
-                    <has_text_matching expression=">comp874\_c0\_seq1.+"/>
+                    <has_n_lines n="534"/>
+                    <has_text_matching expression=">asmbl\_236\.p1.+"/>
                 </assert_contents>
             </output>
             <!-- Predict -->
             <output name="out_bed">
                 <assert_contents>
-                    <has_n_lines n="337"/>
-                    <has_text_matching expression="comp98\_c0\_seq1.+"/>
+                    <has_n_lines n="204"/>
+                    <has_text_matching expression="asmbl\_99.+"/>
                 </assert_contents>
             </output>
             <output name="out_cds">
                 <assert_contents>
-                    <has_n_lines n="6959"/>
-                    <has_text_matching expression=">comp98\_c0\_seq1.+"/>
+                    <has_n_lines n="3560"/>
+                    <has_text_matching expression=">asmbl\_99\.p1.+"/>
                 </assert_contents>
             </output>
             <output name="out_gff3">
                 <assert_contents>
-                    <has_n_lines n="2165"/>
-                    <has_text_matching expression="comp98\_c0\_seq1.+"/>
+                    <has_n_lines n="1337"/>
+                    <has_text_matching expression="asmbl\_99.+"/>
                 </assert_contents>
             </output>
             <output name="out_pep">
                 <assert_contents>
-                    <has_n_lines n="2644"/>
-                    <has_text_matching expression=">comp98\_c0\_seq1.+"/>
+                    <has_n_lines n="1391"/>
+                    <has_text_matching expression=">asmbl\_99\.p1.+"/>
+                </assert_contents>
+            </output>
+            <output name="out_plot">
+                <assert_contents>
+                    <has_size value="714868" delta="1000"/>
                 </assert_contents>
             </output>
             <!-- Others -->
@@ -347,10 +358,10 @@
                 </conditional>
             </section>
             <!-- LongOrfs -->
-            <output name="out_lo_pep">
+            <output name="out_pep">
                 <assert_contents>
-                    <has_n_lines n="772"/>
-                    <has_text_matching expression="c"/>
+                    <has_n_lines n="190"/>
+                    <has_text_matching expression="CUFF\.9\.1.+"/>
                 </assert_contents>
             </output>
         </test>
@@ -403,6 +414,7 @@
 - Results (CDS/FASTA): nucleotide sequences for coding regions of the final candidate ORFs
 - Results (GFF3): positions within the target transcripts of the final selected ORFs
 - Results (BED): BED-formatted file describing ORF positions, best for viewing using GenomeView or IGV
+- Plots: sequence logos and scores (compressed PDF)
 
 *Other*