changeset 5:e331e475e854 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ppanggolin commit e21d81020b381293e58e72ad54b782ce4a30ab56
author iuc
date Thu, 14 Aug 2025 17:09:07 +0000
parents 7a09c51a14be
children
files macros.xml ppanggolin_msa.xml test-data/fasta/PROJECT1_984801_1194801.fasta.gz test-data/fasta/PROJECT5_1290693_1440693.fasta.gz test-data/fasta/PROJECT8_1022972_1232972.fasta.gz test-data/genbank/PROJECT1_984801_1194801.gb.gz test-data/genbank/PROJECT5_1290693_1440693.gb.gz test-data/genbank/PROJECT8_1022972_1232972.gb.gz
diffstat 8 files changed, 74 insertions(+), 36 deletions(-) [+]
line wrap: on
line diff
--- a/macros.xml	Mon Jul 14 07:49:02 2025 +0000
+++ b/macros.xml	Thu Aug 14 17:09:07 2025 +0000
@@ -1,6 +1,6 @@
 <macros>
     <token name="@TOOL_VERSION@">2.2.4</token>
-    <token name="@VERSION_SUFFIX@">0</token>
+    <token name="@VERSION_SUFFIX@">1</token>
     <xml name="citation">
         <citations>
             <citation type="doi">10.1371/journal.pcbi.1007732</citation> 
@@ -17,4 +17,70 @@
             <xref type="bio.tools">ppanggolin</xref>
         </xrefs>
     </xml>
+    <token name="@ORGANISM_LIST@"><![CDATA[
+        touch ./tmp_ppanggolin/organism_list/organism.list &&
+        #set extension_input_files = ""
+        #for $counter_input_files, $file in enumerate($genomes):
+            #if $counter_input_files == 0:
+            	#set extension_input_files = $file.ext
+            #else:
+                #if $file.ext != $extension_input_files:
+                    #raise Exception("All the genome files must be of the same datatype, either all genbank files or all fasta files.")
+            	#end if
+            #end if
+            
+            #set base_name = re.sub('[^\w\-_\.]', '_', str($file.element_identifier))
+            echo -e '${base_name}\t${file}' >> ./tmp_ppanggolin/organism_list/organism.list &&
+        #end for
+    ]]></token>
+    <xml name="inputs_identity_coverage_do_defrag">
+        <param argument="--identity" type="float" value="0.8" min="0" max="1" label="Minimum alignment identity"/>
+        <param argument="--coverage" type="float" value="0.8" min="0" max="1" label="Minimum alignment coverage"/>
+        <param name="do_defrag" type="boolean" checked="true" label="Gene family defragmentation" truevalue="" falsevalue="--no_defrag" help="Realign gene families to link fragments with their non-fragmented gene family. (--no_defrag)"/>
+    </xml>
+    <xml name="inputs_nb_of_partitions">
+        <param argument="--nb_of_partitions" type="integer" max="20" label="Number of classes used to partition the pangenome" optional="true" help="If empty value (default), it will be automatically determined. Otherwise, the value needs to be between 2 and 20 and it is advised to set a value of 3. See the link for the documentation in the help section for more details.">
+            <validator type="expression" message="Value needs to be empty or an integer between 2 and 20">value == "" or int(value) >= 2</validator>
+        </param>
+    </xml>
+    <xml name="inputs_translation_table">
+        <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>
+    </xml>
+    <xml name="inputs_pangenome">
+        <param argument="--pangenome" name="pangenome_h5" type="data" format="h5" label="Input pangenome h5 file"/>
+    </xml>
+    <xml name="inputs_soft_core">
+        <param argument="--soft_core" type="float" value="0.95" min="0" max="1" label="Soft core threshold used when generating general statistics on the projected genome" help="Default=0.95 .This threshold does not influence PPanGGOLiN's partitioning. The value determines the minimum fraction of genomes that must possess a gene family for it to be considered part of the soft core."/>
+    </xml>
+    <xml name="inputs_genomes" token_min="1" token_extratexthelp="">
+        <param name="genomes" type="data" multiple="true"  min="@MIN@" label="Genome files" format="fasta,genbank" help="All the genome files must be of the same format, either all genbank files or all fasta files. A minimum of @MIN@ genome file(s) is mandatory.@EXTRATEXTHELP@ Special characters and spaces are replaced by underscore."/>
+    </xml>
 </macros>
--- a/ppanggolin_msa.xml	Mon Jul 14 07:49:02 2025 +0000
+++ b/ppanggolin_msa.xml	Thu Aug 14 17:09:07 2025 +0000
@@ -8,8 +8,8 @@
     
     <command detect_errors="exit_code"><![CDATA[
         
-        mkdir -p "./tmp_ppanggolin/msa" &&
-        mkdir -p "./tmp_ppanggolin/tmpdir_msa" &&
+        mkdir -p ./tmp_ppanggolin/msa &&
+        mkdir -p ./tmp_ppanggolin/tmpdir_msa &&
         
         ppanggolin msa
         --pangenome '$pangenome_h5'
@@ -46,7 +46,7 @@
 
     <inputs>
     
-        <param argument="--pangenome" name="pangenome_h5" type="data" format="h5" label="Input pangenome h5 file"/>
+        <expand macro="inputs_pangenome"/>
 
         <conditional name="input_choose_partition">
             <param argument="--partition" name="choice_partition" type="select" label="Partition">
@@ -63,7 +63,7 @@
             <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"/>
+                <expand macro="inputs_soft_core"/>
             </when>
             <when value="accessory"/>
             <when value="all"/>
@@ -77,42 +77,14 @@
         <param argument="--phylo" name="do_phylo" type="boolean" checked="true" label="Writes a whole genome msa file for additional phylogenetic analysis (recommended)" truevalue="--phylo" falsevalue=""/>
 
         <param argument="--single_copy" name="do_single_copy" type="boolean" checked="false" label="Report gene families that are considered 'single copy'" truevalue="--single_copy" falsevalue=""/>
-            
-        <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>
+
+        <expand macro="inputs_translation_table"/>
         
     </inputs>
 
     <outputs>
         <data name="archive_msa_partition_source" format="tar.gz" label="PPanGGOLiN msa on ${on_string}: archive msa ${choice_partition} ${choice_source}" />
-        <data name="partition_genome_alignment" format="aln" label="PPanGGOLiN msa on ${on_string}: ${choice_partition} genome alignment" >
+        <data name="partition_genome_alignment" format="maf" label="PPanGGOLiN msa on ${on_string}: ${choice_partition} genome alignment" >
           <filter>do_phylo is True</filter>
         </data>
     </outputs>
Binary file test-data/fasta/PROJECT1_984801_1194801.fasta.gz has changed
Binary file test-data/fasta/PROJECT5_1290693_1440693.fasta.gz has changed
Binary file test-data/fasta/PROJECT8_1022972_1232972.fasta.gz has changed
Binary file test-data/genbank/PROJECT1_984801_1194801.gb.gz has changed
Binary file test-data/genbank/PROJECT5_1290693_1440693.gb.gz has changed
Binary file test-data/genbank/PROJECT8_1022972_1232972.gb.gz has changed