Merge pull request #118 from mthang/panaroo

add panaroo tool

tools/panaroo/.shed.yml

@@ -0,0 +1,10 @@
+name: panaroo
+owner: galaxy-australia
+categories:
+- Pangenome
+description: A Bacterial Pangenome Analysis Pipeline
+homepage_url: https://gthlab.au/panaroo/#/
+long_description: |
+  a graph-based pangenome clustering tool that is able to account for many of the sources of error introduced during the annotation of prokaryotic genome assemblies.
+remote_repository_url: https://github.com/usegalaxy-au/tools-au/tree/master/tools/panaroo 
+type: unrestricted

tools/panaroo/macros.xml

@@ -0,0 +1,69 @@
+<macros>
+	<token name="@TOOL_VERSION@">1.5.0</token>
+        <token name="@VERSION_SUFFIX@">0</token>
+	<token name="@PROFILE@">22.05</token>
+	<xml name="edam_ontology">
+	  <edam_topics>
+	     <edam_topic>topic_0194</edam_topic>
+     	  </edam_topics>
+  	</xml>
+        <xml name="biotools">
+            <xrefs>
+               <xref type="bio.tools">panaroo</xref>
+            </xrefs>
+    	</xml>
+	<xml name="requirements">
+           <requirements>
+	       <requirement type="package" version="@TOOL_VERSION@">panaroo</requirement>
+	       <requirement type="package" version="170427">prank</requirement>	
+    	   </requirements>
+        </xml>
+        <xml name="clean_mode">
+            <option value="strict">strict</option>
+	    <option value="moderate">moderate</option>
+	    <option value="sensitive">sensitive</option>
+    	</xml>
+	<xml name="genetic_code">
+             <option value="1">1. Standard</option>
+             <option value="2">2. Vertebrate Mitochondrial</option>
+             <option value="3">3. Yeast Mitochondrial</option>
+	     <option value="4">4. Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code</option>
+             <option value="5">5. Invertebrate Mitochondrial</option>
+             <option value="6">6. Ciliate, Dasycladacean and Hexamita Nuclear Code</option>
+             <option value="9">9. Echinoderm Mitochondrial</option>
+             <option value="10">10. Euplotid Nuclear</option>
+             <option value="11" selected="True">11. Bacteria and Archaea</option>
+             <option value="12">12. Alternative Yeast Nuclear</option>
+             <option value="13">13. Ascidian Mitochondrial</option>
+             <option value="14">14. Flatworm Mitochondrial</option>
+             <option value="15">15. Blepharisma Macronuclear</option>
+             <option value="16">16. Chlorophycean Mitochondrial</option>
+             <option value="21">21. Trematode Mitochondrial</option>
+             <option value="22">22. Scenedesmus obliquus mitochondrial</option>
+             <option value="23">23. Thraustochytrium Mitochondrial</option>
+	     <option value="24">24. Pterobranchia mitochondrial</option>
+	     <option value="25">25. Candidate Division SR1 and Gracilibacteria Code</option>
+	     <option value="26">26. Pachysolen tannophilus Nuclear Code</option>
+	     <option value="27">27. Karyorelict Nuclear Code</option>
+	     <option value="28">28. Condylostoma Nuclear Code</option>
+	     <option value="29">29. Mesodinium Nuclear Code</option>
+	     <option value="30">30. Peritrich Nuclear Code</option>
+	     <option value="31">31. Blastocrithidia Nuclear Code</option>
+	     <option value="33">33. Cephalodiscidae Mitochondrial UAA-Tyr Code</option>
+     	</xml>
+	<xml name="refind_mode_option">
+	   <option value="default" selected="True">default</option>
+	   <option value="strict">strict</option>
+	   <option value="off">off</option>
+	</xml>
+	<xml name="gene_alignment">
+	    <option value="None" selected="True">None</option>
+	    <option value="core">core</option>
+	    <option value="pan">pan</option>
+    	</xml>
+	<xml name="gene_aligner">
+	    <option value="mafft" selected="True">mafft</option>
+	    <option value="prank">prank</option>
+	    <option value="clustal">clustal</option>
+	</xml>
+</macros>

tools/panaroo/panaroo.xml

@@ -0,0 +1,235 @@
+<tool id="panaroo" name="Panaroo" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+    <description>A Bacterial Pangenome Analysis Pipeline</description>
+    <macros>
+          <import>macros.xml</import>
+    </macros>
+    <expand macro="edam_ontology"/>
+    <expand macro="biotools"/>
+    <expand macro="requirements"/>
+    <stdio>
+        <exit_code range="1:" />
+        <regex match="System..*Exception"
+           source="both"
+           level="fatal"
+           description="Error encountered" />
+    </stdio>
+    <command><![CDATA[
+
+         mkdir outdir &&
+	    
+	 #import re
+	 #set input_directory = 'input_directory'
+	 mkdir $input_directory &&
+	 #for $gff in $gff_input_collection:
+	    #set identifier = re.sub('[^\s\w\-\\.]','_',str($gff.element_identifier))
+	    ln -fs '$gff' '$input_directory/$identifier' &&
+	 #end for
+
+	 panaroo 
+	 -t \${GALAXY_SLOTS:-2}
+         #if str($gen_code) != 'None':
+           --codon-table $gen_code
+	 #end if
+         #if str($advanced.adv_options_selector) == "set":
+	     #if $advanced.remove_invalid_gene
+		 $advanced.remove_invalid_gene
+	     #end if
+	     -c '$advanced.matching_option.seq_threshold'
+	     -f '$advanced.matching_option.peptide_threshold'
+	     --len_dif_percent '$advanced.matching_option.length_diff_cutoff'
+	     $advanced.matching_option.merge_paralogs
+	     --search_radius '$advanced.refind_option.search_radius'
+	     --refind_prop_match '$advanced.refind_option.refind_prop_match'
+	     --refind-mode '$advanced.refind_option.refind_mode'
+	     --min_trailing_support '$advanced.graph_correction_option.min_trailing_support'
+	     --trailing_recursive '$advanced.graph_correction_option.trailing_recursive'
+	     --edge_support_threshold '$advanced.graph_correction_option.edge_support_threshold'
+	     --remove_by_consensus '$advanced.graph_correction_option.remove_by_consensus'
+	     --high_var_flag '$advanced.graph_correction_option.high_var_flag'
+	     --min_edge_support_sv '$advanced.graph_correction_option.min_edge_support_sv'
+	     $advanced.graph_correction_option.all_seq_in_graph
+	     $advanced.graph_correction_option.no_clean_edges
+	
+	     #if $advanced.gene_alignment_option.a != 'None'
+		-a '$advanced.gene_alignment_option.a'
+	     #end if
+
+	     #if '$advanced.gene_alignment_option.aligner' == 'mafft'
+                --aligner mafft
+	     #else
+               --aligner '$advanced.gene_alignment_option.aligner'
+	     #end if
+	     #if $advanced.gene_alignment_option.core_subset != ''
+		--core_subset $advanced.gene_alignment_option.core_subset
+	     #end if
+         #end if
+	 -i $input_directory/*.gff 
+	 -o outdir 
+	 --clean-mode $mode 
+	 > '$log' &&
+	 mv outdir/gene_presence_absence.Rtab outdir/gene_presence_absence_rtab.Rtab &&
+	 2>&1  
+
+    ]]></command>
+    <inputs>
+	<param name="gff_input_collection" type="data_collection" format="gff" collection_type="list" label="GFF Input Collection" help="A list of gff files (i.e prokka)"/>
+	<param name="mode" type="select" label="The stringency mode at which to run panaroo" help="--clean-mode">
+            <expand macro="clean_mode"/>
+    	</param>
+	<param name="gen_code" type="select" label="the codon table user for translation" help="default: 11">
+            <expand macro="genetic_code"/>
+    	</param>
+        <conditional name="advanced">
+            <param name="adv_options_selector" type="select" label="Set advanced options?" help="Provides additional controls">
+                <option value="set">Set</option>
+                <option value="do_not_set" selected="True">Do not set</option>
+            </param>
+	    <when value="set">
+		 <param name="remove_invalid_gene" argument="--remove-invalid-genes" type="boolean" truevalue="--remove-invalid-genes" falsevalue=""  label="removes annotations that do not conform to the expected Prokka format such as those including premature stop codons" help="--remove-invalid-genes"/>
+
+                 <section name="matching_option" title="Matching" expanded="false">
+                   <param name="seq_threshold" argument="--threshold" type="float" value="0.98" label="sequence identity threshold" help="default: 0.98"/>
+                   <param name="peptide_threshold" argument="--family_threshold" type="float" value="0.7" label="protein family sequence identity threshold" help="default: 0.7"/>
+                   <param name="length_diff_cutoff" argument="--len_dif_percent" type="float" value="0.98" label="length difference cutoff" help="default: 0.98"/>
+                   <param name="merge_paralogs" type="boolean" truevalue="--merge_paralogs" falsevalue="" checked="false" label="do not split paralogs" help="--merge_paralogs"/>
+	   	 </section>
+
+                 <section name="refind_option" title="Refind" expanded="false">
+                   <param argument="--search_radius" type="integer" value="5000" label="Search radius" help="--search_radius (default: 5000)"/>
+                   <param argument="--refind_prop_match" type="float" value="0.75" label="Gene proportion match" help="default: 0.75"/>
+		   <param argument="--refind_mode" type="select" label="The stringency mode at which to re-find genes" help="default: default">
+			  <expand macro="refind_mode_option"/>
+	   	   </param>
+                 </section>
+
+                 <section name="graph_correction_option" title="Graph Correction" expanded="false">
+                   <param argument="--min_trailing_support" type="integer" value="2" label="Minimum cluster size to keep a gene called at the end of a contig" help="--min_traiiing_support [relexed mode : 2 is used]"/>
+                   <param argument="--trailing_recursive" type="integer" value="1" label="Number of times to perform recursive trimming of low support nodes near the end of contigs" help="--trailing_recursive [relaxed mode: 1 is used]"/>
+                   <param name="edge_support_threshold" type="integer" value="1" label="Edge support threshold" help="--edge_support_threshold [ Minimal edge 1 is used ]"/>
+		   <param name="len_outlier_proportion" type="float" value="0.01" label="Length outlier support proportion" help="--length_outlier_support_proportion [default: 0.01]"/>
+		   <param name="remove_by_consensus" type="boolean" truevalue="True" falsevalue="False" checked="False" label="Remove consensus" help="--remove_by_consensus [default: False]"/>
+		   <param name="high_var_flag" type="integer" value="5" label="Highly variable gene region" help="--high_var_flag [default: 5]"/>
+		   <param name="min_edge_support_sv" type="integer" value="2" label="Minimum edge support structural variants" help="--min_edge_support_sv [relaxed mode: 2 is used]"/>
+		   <param argument="--all_seq_in_graph" type="boolean" truevalue="--all_seq_in_graph" falsevalue="" label="Retains all DNA sequence" help="--all_seq_in_graph [default: off]"/>
+		   <param argument="--no_clean_edges" type="boolean" truevalue="--no_clean_edges" falsevalue="" label="Edge filtering in the final output graph" help="--no_clean_edges [default: off]"/>
+	   	</section>
+
+		<section name="gene_alignment_option" title="Gene Alignment" expanded="false">
+		    <param argument="-a" type="select" label="Output alignments of core genes or all genes." help="-a [optional: core or pan; default: None">
+                        <expand macro="gene_alignment"/>
+                   </param>
+		   <param argument="--aligner" type="select" label="Specify an aligner" help="--aligner [mafft|prank|clustal][default: mafft]">
+			<expand macro="gene_aligner"/>
+		   </param>
+		   <param name="codons" type="boolean" truevalue="true" falsevalue="false"  checked="false" label="Generate codon alignments" help="--codons"/>
+		   <param name="core_threshold" type="float" value="0.95" label="Core-genome sample threshold" help="--core_threshold [default: 0.95]"/>
+		   <param argument="--core_subset" type="integer" value=""  optional="true" label="Subset of the core genome to these many genes" help="--core_subset [default: all]"/>
+		   <param name="core_entropy" type="float" value="0.1" label="Set the Block Mapping and Gathering with Entropy" help="--core_entropy_filter (threshold can be between 0.0 and 1.0) [default: Tukey outlier method]"/>
+		</section>
+	    </when>
+            <when value="do_not_set"/>
+        </conditional>
+    </inputs>
+    <outputs>
+	<collection name="output" type="list" label="${tool.name} on ${on_string}: Pangenome output">
+	     <discover_datasets pattern="(?P&lt;designation&gt;.+)\.(?P&lt;ext&gt;clstr)" directory="outdir" format="txt" visible="false" />
+	     <discover_datasets pattern="(?P&lt;designation&gt;.+)\.(?P&lt;ext&gt;txt)" directory="outdir" format="txt" visible="false" />
+	     <discover_datasets pattern="(?P&lt;designation&gt;.+)\.(?P&lt;ext&gt;gml)" directory="outdir" format="txt" visible="false" />
+	     <discover_datasets pattern="(?P&lt;designation&gt;.+)\.(?P&lt;ext&gt;Rtab)" directory="outdir" format="tabular" visible="false" />
+	     <discover_datasets pattern="(?P&lt;designation&gt;.+)\.(?P&lt;ext&gt;csv)" directory="outdir" format="csv" visible="false" />
+	     <discover_datasets pattern="(?P&lt;designation&gt;.+)\.(?P&lt;ext&gt;fasta)" directory="outdir" format="fasta" visible="false" />
+	     <discover_datasets pattern="(?P&lt;designation&gt;.+)\.(?P&lt;ext&gt;fa)" directory="outdir" format="fasta" visible="false" />
+	     <filter>advanced['gene_alignment_option']['a'] == 'None' </filter>
+       </collection>
+        <collection name="output_pangenome" type="list" label="${tool.name} on ${on_string}: Pangenome alignment output">
+             <discover_datasets pattern="(?P&lt;designation&gt;.+)\.(?P&lt;ext&gt;clstr)" directory="outdir" format="txt" visible="false" />
+             <discover_datasets pattern="(?P&lt;designation&gt;.+)\.(?P&lt;ext&gt;txt)" directory="outdir" format="txt" visible="false" />
+             <discover_datasets pattern="(?P&lt;designation&gt;.+)\.(?P&lt;ext&gt;gml)" directory="outdir" format="txt" visible="false" />
+             <discover_datasets pattern="(?P&lt;designation&gt;.+)\.(?P&lt;ext&gt;Rtab)" directory="outdir" format="tabular" visible="false" />
+             <discover_datasets pattern="(?P&lt;designation&gt;.+)\.(?P&lt;ext&gt;csv)" directory="outdir" format="csv" visible="false" />
+             <discover_datasets pattern="(?P&lt;designation&gt;.+)\.(?P&lt;ext&gt;fasta)" directory="outdir" format="fasta" visible="false" />
+	     <discover_datasets pattern="(?P&lt;designation&gt;.+)\.(?P&lt;ext&gt;fa)" directory="outdir" format="fasta" visible="false" />
+	     <discover_datasets pattern="(?P&lt;designation&gt;.+)\.(?P&lt;ext&gt;aln)" directory="outdir" format="aln" visible="false" />
+	     <discover_datasets pattern="(?P&lt;designation&gt;.+)\.(?P&lt;ext&gt;embl)" directory="outdir" format="embl" visible="false" />
+             <filter>advanced['gene_alignment_option']['a'] != 'None' </filter>
+       </collection>
+       <collection name="output_pangenome_fasta" type="list" label="${tool.name} on ${on_string}: Pangenom alignment fasta">
+	     <discover_datasets pattern="(?P&lt;designation&gt;.+)\.(?P&lt;ext&gt;fas)" directory="outdir/aligned_gene_sequences" format="fasta" visible="false" />  
+             <filter>advanced['gene_alignment_option']['a'] != 'None' </filter>
+       </collection>
+
+	<data name="log" format="txt" label="${tool.name} on ${on_string}: log"/>
+    </outputs>
+    <tests>
+	<!-- run panaroo with default parameters (i.e panaroo -t 2 -i *.gff -o default \-\-clean-mode strict \-\-remove-invalid-genes) -->
+	 <test expect_num_outputs="2">
+	    <param name="gen_code" value="11"/>
+	    <param name="mode" value="strict"/>
+	    <param name="adv_options_selector" value="set"/>
+	    <param name="a" value="None"/>
+	    <param name="gff_input_collection">
+		<collection type="list">
+		    <element name="gff10.gff" value="10_small.gff"/>
+		    <element name="gff11.gff" value="11_small.gff"/>
+		</collection>
+	    </param>
+	    <output_collection name="output" count="13"/>
+	    <output name="log">
+		 <assert_contents>
+		      <has_text text="pre-processing gff3 files..."/>
+		 </assert_contents>
+            </output>
+    	</test>
+	<test expect_num_outputs="3">
+	   <param name="gen_code" value="11"/>
+	   <param name="mode" value="strict"/>
+	   <param name="adv_options_selector" value="set"/>
+	   <param name="a" value="core"/>
+	   <param name="gff_input_collection">
+		<collection type="list">
+		    <element name="gff10.gff" value="10_small.gff"/>
+		    <element name="gff11.gff" value="11_small.gff"/>
+	        </collection>
+           </param>
+	   <output_collection name="output_pangenome" count="18"/>
+	   <output_collection name="output_pangenome_fasta" count="251"/>
+	   <output name="log">
+		  <assert_contents>
+		       <has_text text="pre-processing gff3 files..."/>
+		 </assert_contents>
+	   </output>
+	</test>
+    </tests>
+    <help><![CDATA[
+Panaroo_ is A Bacterial Pangenome Analysis Pipeline.
+
+**INPUTS**
+Panaroo now supports multiple input formats. To use non-standard GFF3 files you must profile the input file as a list in a text file (one per line). Separate GFF and FASTA files can be provided per isolate by providing each file delimited by a space or a tab. Genbank file formats are also supported with extensions '.gbk', '.gb' or '.gbff'. These must compliant with Genbank/ENA/DDJB. This can be forced in Prokka by specifying the --compliance parameter.
+
+  - data file in gff format
+
+**OUTPUTS**
+
+  - combined_protein_cdhit_out.txt
+  - combined_protein_cdhit_out.txt.clstr
+  - pre_filt_graph.gml
+  - gene_data.csv
+  - combined_protein_CDS.fasta
+  - combined_DNA_CDS.fasta
+  - gene_presence_absence.Rtab
+  - gene_presence_absence_roary.csv
+  - gene_presence_absence.csv
+  - summary_statistics.txt
+  - pan_genome_reference.fa
+  - struct_presence_absence.Rtab
+  - final_graph.gml
+
+
+.. _Panaroo: https://gthlab.au/panaroo/#/gettingstarted/quickstart
+
+    ]]></help>
+    <citations>
+        <citation type="doi">10.1186/s13059-020-02090-4</citation>
+    </citations>
+</tool>
+