wrappers for ppanggolin all and ppanggolin msa

tools/ppanggolin/.shed.yml

@@ -0,0 +1,11 @@
+name: ppanggolin
+owner: iuc
+description: Microbial Partitioned PanGenome.
+homepage_url: https://ppanggolin.readthedocs.io/en/latest/
+long_description: |
+  Depicting microbial species diversity via a Partitioned PanGenome Graph Of Linked Neighbors.
+remote_repository_url: https://github.com/labgem/PPanGGOLiN
+type: unrestricted
+categories:
+- Genome annotation
+

tools/ppanggolin/macros.xml

@@ -0,0 +1,19 @@
+<macros>
+    <token name="@TOOL_VERSION@">2.2.1</token>
+    <token name="@VERSION_SUFFIX@">0</token>
+    <xml name="citation">
+        <citations>
+            <citation type="doi">10.1371/journal.pcbi.1007732</citation> 
+        </citations>
+    </xml>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="@TOOL_VERSION@">ppanggolin</requirement>
+        </requirements>
+    </xml>
+    <xml name="xrefs">
+        <xrefs>
+            <xref type="bio.tools">ppanggolin</xref>
+        </xrefs>
+    </xml>
+</macros>

tools/ppanggolin/ppanggolin_msa.xml

@@ -0,0 +1,155 @@
+<tool id="ppanggolin_msa" name="PPanGGOLiN msa" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
+    <description>computes multiple sequence alignment of the gene / protein families in any partition of the pangenome.</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="xrefs"/>
+    <expand macro="requirements"/>
+
+    <command detect_errors="exit_code"><![CDATA[
+
+        mkdir -p "./tmp_ppanggolin/msa" &&
+        mkdir -p "./tmp_ppanggolin/tmpdir_msa" &&
+
+        ppanggolin msa
+        --pangenome $pangenome_h5
+        --output ./tmp_ppanggolin/msa
+        --tmpdir ./tmp_ppanggolin/tmpdir_msa
+        --force
+        --cpu "\${GALAXY_SLOTS:-4}"
+        --disable_prog_bar
+        --partition $choice_partition
+        #if str($input_choose_partition.choice_partition) == "softcore"
+            --soft_core $choice_soft_core
+        #end if
+
+        --source $choice_source        
+        #if str($do_phylo) == "true"
+            --phylo
+        #end if     
+        #if str($do_single_copy) == "true"
+            --single_copy
+        #end if
+        --translation_table $translation_table
+
+        #set base_msa_protein = "msa_" + str($input_choose_partition.choice_partition) + "_protein"
+        #set base_genome_alignment = str($input_choose_partition.choice_partition) + "_genome_alignment.aln"
+        #if str($input_choose_partition.choice_partition) == "softcore"
+            #set base_genome_alignment = str($input_choose_partition.choice_partition) + "_" + str($choice_soft_core) + "_genome_alignment.aln"
+        #end if
+
+        && tar -cvf ./tmp_ppanggolin/msa/archive_${base_msa_protein}.tar ./tmp_ppanggolin/msa/${base_msa_protein}
+        && gzip ./tmp_ppanggolin/msa/archive_${base_msa_protein}.tar
+        && mv ./tmp_ppanggolin/msa/archive_${base_msa_protein}.tar.gz '${archive_msa_partition_protein}'
+
+        #if str($do_phylo) == "true"
+            && mv ./tmp_ppanggolin/msa/${base_genome_alignment} '${partition_genome_alignment}'
+        #end if     
+
+    ]]></command>
+
+    <inputs>
+
+        <param argument="--pangenome" name="pangenome_h5" type="data" format="h5" label="Input pangenome h5 file"/>
+
+        <conditional name="input_choose_partition">
+            <param argument="--partition" name="choice_partition" type="select" label="Partition">
+                <option value="core" selected="true">Core</option>
+                <option value="persistent">Persistent</option>
+                <option value="shell">Shell</option>
+                <option value="cloud">Cloud</option>
+                <option value="softcore">Softcore</option>
+                <option value="accessory">Accessory</option>
+                <option value="all">All</option>
+            </param>
+            <when value="core"/>
+            <when value="persistent"/>
+            <when value="shell"/>
+            <when value="cloud"/>
+            <when value="softcore">
+                <param argument="--soft_core" name="choice_soft_core" type="float" value="0.95" min="0" max="1" label="Soft core threshold to use if 'softcore' partition is chosen"/>
+            </when>
+            <when value="accessory"/>
+            <when value="all"/>
+        </conditional>
+
+        <param argument="--source" name="choice_source" type="select" label="Source">
+            <option value="protein" selected="true">Protein</option>
+            <option value="dna">DNA</option>
+        </param>
+
+        <param argument="--phylo" name="do_phylo" type="boolean" checked="true" label="Writes a whole genome msa file for additional phylogenetic analysis (recommended)"/>
+
+        <param argument="--single_copy" name="do_single_copy" type="boolean" checked="false" label="Report gene families that are considered 'single copy'"/>
+
+        <param argument="--translation_table" type="select" label="Translation table">
+            <option value="1" selected="true">1 - Standard Code</option>
+            <option value="2">2 - Vertebrate Mitochondrial</option>
+            <option value="3">3 - Yeast Mitochondrial</option>
+            <option value="4">4 - Mold, Protozoan, and Coelenterate Mitochondrial</option>
+            <option value="5">5 - Invertebrate Mitochondrial</option>
+            <option value="6">6 - Ciliate Nuclear</option>
+            <option value="9">9 - Echinoderm Mitochondrial</option>
+            <option value="10">10 - Euplotid Nuclear</option>
+            <option value="11">11 - Bacterial and Plant Plastid</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 Nuclear</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</option>
+            <option value="26">26 - Pachysolen tannophilus Nuclear</option>
+            <option value="27">27 - Karyorelict Nuclear</option>
+            <option value="28">28 - Condylostoma Nuclear</option>
+            <option value="29">29 - Mesodinium Nuclear</option>
+            <option value="30">30 - Peritrich Nuclear</option>
+            <option value="31">31 - Blastocrithidia Nuclear</option>
+            <option value="32">32 - Balanophoraceae Plastid</option>
+            <option value="33">33 - Cephalodiscidae Mitochondrial</option>
+        </param>
+
+    </inputs>
+
+    <outputs>
+        <data name="archive_msa_partition_protein" format="tar.gz" label="PPanGGOLiN msa on ${on_string}: archive msa ${choice_partition} protein" />
+        <data name="partition_genome_alignment" format="aln" label="PPanGGOLiN msa on ${on_string}: ${choice_partition} genome alignment" >
+          <filter>do_phylo is True</filter>
+        </data>
+    </outputs>
+
+    <tests>
+        <test expect_num_outputs="2">
+            <param name="do_phylo" value="true"/>
+            <param name="pangenome_h5" value="h5/test_data.h5" ftype="fasta"/>
+
+            <output name="partition_genome_alignment" >
+                <assert_contents>
+                    <has_text text=">" />
+                </assert_contents>
+            </output>
+
+        </test>
+    </tests>
+
+    <help><![CDATA[
+
+        PPanGGOLiN_ (Gautreau et al. 2020) is a software suite used to create and manipulate prokaryotic pangenomes from a set of either assembled 
+        genomic DNA sequences or provided genome annotations. PPanGGOLiN builds pangenomes through a graphical model and a statistical method to partition gene 
+        families in persistent, shell and cloud genomes. It integrates both information on protein-coding genes and their genomic neighborhood to build a graph 
+        of gene families where each node is a gene family, and each edge is a relation of genetic contiguity. 
+
+	The `ppanggolin msa` command computes multiple sequence alignment of any partition of the pangenome. The command uses mafft with default options to perform the alignment. Please see the documentation_ on how parameters can be tuned for this command.
+
+        .. _PPanGGOLiN: https://github.com/labgem/PPanGGOLiN
+        .. _documentation: https://ppanggolin.readthedocs.io/en/latest/user/MSA.html
+
+    ]]></help>
+
+    <expand macro="citation"/>
+
+</tool>
+