comparison roary.xml @ 4:809e42326fc2 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/roary commit d2e1ee6304af1062175ca87aab59c4042ace3116"

3:15ca041134a9

<tool id="roary" name="Roary" version="3.12.0+galaxy0">
    <description>the pangenome pipeline - Quickly generate a core gene alignment from gff3 files</description>
    
    <requirements>
      <requirement type="package" version="3.12.0">roary</requirement>
    </requirements>
    
    <command detect_errors="exit_code"><![CDATA[
        
        #for $gff in $gff_input.gffs
          cp $gff '${gff.element_identifier}'.gff &&
        #end for

        roary
          -f out
          -p \${GALAXY_SLOTS:-1}

          -g '$advanced.maxclust'
          $advanced.split_para
          -t '$advanced.trans_tab'
          -iv '$advanced.mcl'

          *.gff
          
    ]]></command>
    
    <inputs>
      <conditional name="gff_input">
        <param name="gff_input_selector" type="select" label="Individual gff files or a dataset collection" help="Select between individual gff files or a collection of gff files">
          <option value="individual">Individual</option>
          <option value="collection">Collection</option>

          <param name="gffs" type="data_collection" collection_type="list" format="gff,gff3" label="Dataset collection to submit to Roary" help="A dataset list collection of gff3 files to send to Roary for analysis." />
        </when>
      </conditional>
      <param name="percent_ident" type="integer" label="minimum percentage identity for blastp" help="Sets the minimum percentage identity for protein matches" value="95"/>
      <param name="core_diff" type="float" label="percentage of isolates a gene must be in to be core" help="The total percentage of the isolates that must have the gene for it to be considered a core gene." value="99.0"/>
      
      <param name="outputs" type="select" multiple="true" display="checkboxes" label="Additional outputs" help="Summary statistics, core gene alignments and Gene Presence/Absence tables are always produced.">
        <option value="abg_nw">Accessory binary genes in newick format</option>
        <option value="abg_fa">Accessory binary genes in fasta format</option>
        <option value="accgraph">Accessory graph in dot format</option>
        <option value="acchead_embl">Accessory header file in embl format</option>

        <option value="numcons_rtab">Number of Conserved Genes in Rtab format</option>
        <option value="numpangene_rtab">Number of Genes in Pan Genome in Rtab format</option>
        <option value="numnew_rtab">Number of New Genes in Rtab format</option>
        <option value="numuniq_rtab">Number of Unique Genes in Rtab format</option>
      </param>
      
      <section name="advanced" title="Advanced options" expanded="false">
        <param name="maxclust" type="integer" value="50000" label="Maximum number of clusters" help="The maximum number of clusters to assign proteins" />
        <param name="split_para" type="boolean" checked="False" truevalue="-s" falsevalue="" label="Don't split paralogs" help="Click yes so that paralogs aren't split."/>
        <param name="trans_tab" type="integer" value="11" label="Translation table to use [1 or 4 or 11]" help="DNA -> RNA translation table to use. Roary is designed for prokaryotes and so tables 1, 4 or 11 will work, others could be problematic." />
        <param name="mcl" type="float" value="1.5" label="MCL inflation value" help="This is an advanced setting, change only if you know what you are doing and then at your own risk!" />
      </section>
      
    </inputs>
    
    <outputs>
      <data format="tabular" name="sumstats" label="${tool.name} on ${on_string} Summary statistics" from_work_dir="out/summary_statistics.txt" />
      <data format="fasta" name="core_gene_aln" label="${tool.name} on ${on_string} Core Gene Alignment" from_work_dir="out/core_gene_alignment.aln" />
      <data format="csv" name="gene_p_a" label="${tool.name} on ${on_string} Gene Presence Absence" from_work_dir="out/gene_presence_absence.csv" />
      <data format="fasta" name="acc_bin" label="${tool.name} on ${on_string} Accessory Binary Genes" from_work_dir="out/accessory_binary_genes.fa" >

      </data>
      <data format="txt" name="num_uniq_rtab" label="${tool.name} on ${on_string} Number of Unique Genes" from_work_dir="out/number_of_unique_genes.Rtab" >
        <filter>outputs and 'numuniq_rtab' in outputs</filter>
      </data>
    </outputs>
    
    <tests>
      <test>
        <param name="gff_input_selector" value="individual"/>
        <param name="gffs" value="ex1.gff,ex2.gff" ftype="gff3"/>
        <output name="sumstats" file="out/summary_statistics.txt" ftype="tabular"/>

        <param name="percent_ident" value="50"/>
        <param name="core_diff" value="50.0"/>
        <output name="sumstats" file="test2/summary_statistics.txt" ftype="tabular"/>
      </test>
    </tests>
    
    <help><![CDATA[
**Roary**

Roary is a high speed stand alone pan genome pipeline, which takes annotated assemblies in GFF3 format (produced by Prokka) and calculates the pan genome. Using a standard desktop PC, it can analyse datasets with thousands of samples, something which is computationally infeasible with existing methods, without compromising the quality of the results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a single processor. To perform this analysis using existing methods would take weeks and hundreds of GB of RAM.

To use Roary, select two or more gff3 files OR a collection of gff3 files

**Options**: 


       - Minimum percentage identity for blastp - an integer, default is [95]

       
       - Percentage of isolates a gene must be in to be core - a float, default is [99.0]
       
       
**Advanced Options**:
       
       - Maximum number of clusters - integer, default is [50000]

       
       - Don't split paralogs - check box

       
       - Translation table - which translation table to use, an integer, default is [11]

       
       - Change the MCL inflation value - a float, default is [1.5]
       

For further info see: http://sanger-pathogens.github.io/Roary/
    
    ]]></help>
    
    <citations>
        <citation type="doi">10.1093/bioinformatics/btv421</citation>
    </citations>
    
</tool>

4:809e42326fc2

<tool id="roary" name="Roary" version="3.12.0+galaxy0">
    <description>the pangenome pipeline - Quickly generate a core gene alignment from gff3 files</description>

    <requirements>
      <requirement type="package" version="3.12.0">roary</requirement>
    </requirements>

    <command detect_errors="exit_code"><![CDATA[
        #set $filenames = list()
        #for $gff in $gff_input.gffs
          cp '$gff' '${gff.element_identifier}.gff' &&
          #set $filename = str($gff.element_identifier) + '.gff'
          $filenames.append(str($filename))
        #end for

        roary
          -f out
          -p \${GALAXY_SLOTS:-1}

          -g '$advanced.maxclust'
          $advanced.split_para
          -t '$advanced.trans_tab'
          -iv '$advanced.mcl'

          #for $f in $filenames
            '$f'
          #end for

    ]]></command>

    <inputs>
      <conditional name="gff_input">
        <param name="gff_input_selector" type="select" label="Individual gff files or a dataset collection" help="Select between individual gff files or a collection of gff files">
          <option value="individual">Individual</option>
          <option value="collection">Collection</option>

          <param name="gffs" type="data_collection" collection_type="list" format="gff,gff3" label="Dataset collection to submit to Roary" help="A dataset list collection of gff3 files to send to Roary for analysis." />
        </when>
      </conditional>
      <param name="percent_ident" type="integer" label="minimum percentage identity for blastp" help="Sets the minimum percentage identity for protein matches" value="95"/>
      <param name="core_diff" type="float" label="percentage of isolates a gene must be in to be core" help="The total percentage of the isolates that must have the gene for it to be considered a core gene." value="99.0"/>

      <param name="outputs" type="select" multiple="true" display="checkboxes" label="Additional outputs" help="Summary statistics, core gene alignments and Gene Presence/Absence tables are always produced.">
        <option value="abg_nw">Accessory binary genes in newick format</option>
        <option value="abg_fa">Accessory binary genes in fasta format</option>
        <option value="accgraph">Accessory graph in dot format</option>
        <option value="acchead_embl">Accessory header file in embl format</option>

        <option value="numcons_rtab">Number of Conserved Genes in Rtab format</option>
        <option value="numpangene_rtab">Number of Genes in Pan Genome in Rtab format</option>
        <option value="numnew_rtab">Number of New Genes in Rtab format</option>
        <option value="numuniq_rtab">Number of Unique Genes in Rtab format</option>
      </param>

      <section name="advanced" title="Advanced options" expanded="false">
        <param name="maxclust" type="integer" value="50000" label="Maximum number of clusters" help="The maximum number of clusters to assign proteins" />
        <param name="split_para" type="boolean" checked="False" truevalue="-s" falsevalue="" label="Don't split paralogs" help="Click yes so that paralogs aren't split."/>
        <param name="trans_tab" type="integer" value="11" label="Translation table to use [1 or 4 or 11]" help="DNA -> RNA translation table to use. Roary is designed for prokaryotes and so tables 1, 4 or 11 will work, others could be problematic." />
        <param name="mcl" type="float" value="1.5" label="MCL inflation value" help="This is an advanced setting, change only if you know what you are doing and then at your own risk!" />
      </section>

    </inputs>

    <outputs>
      <data format="tabular" name="sumstats" label="${tool.name} on ${on_string} Summary statistics" from_work_dir="out/summary_statistics.txt" />
      <data format="fasta" name="core_gene_aln" label="${tool.name} on ${on_string} Core Gene Alignment" from_work_dir="out/core_gene_alignment.aln" />
      <data format="csv" name="gene_p_a" label="${tool.name} on ${on_string} Gene Presence Absence" from_work_dir="out/gene_presence_absence.csv" />
      <data format="fasta" name="acc_bin" label="${tool.name} on ${on_string} Accessory Binary Genes" from_work_dir="out/accessory_binary_genes.fa" >

      </data>
      <data format="txt" name="num_uniq_rtab" label="${tool.name} on ${on_string} Number of Unique Genes" from_work_dir="out/number_of_unique_genes.Rtab" >
        <filter>outputs and 'numuniq_rtab' in outputs</filter>
      </data>
    </outputs>

    <tests>
      <test>
        <param name="gff_input_selector" value="individual"/>
        <param name="gffs" value="ex1.gff,ex2.gff" ftype="gff3"/>
        <output name="sumstats" file="out/summary_statistics.txt" ftype="tabular"/>

        <param name="percent_ident" value="50"/>
        <param name="core_diff" value="50.0"/>
        <output name="sumstats" file="test2/summary_statistics.txt" ftype="tabular"/>
      </test>
    </tests>

    <help><![CDATA[
**Roary**

Roary is a high speed stand alone pan genome pipeline, which takes annotated assemblies in GFF3 format (produced by Prokka) and calculates the pan genome. Using a standard desktop PC, it can analyse datasets with thousands of samples, something which is computationally infeasible with existing methods, without compromising the quality of the results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a single processor. To perform this analysis using existing methods would take weeks and hundreds of GB of RAM.

To use Roary, select two or more gff3 files OR a collection of gff3 files

**Options**:


       - Minimum percentage identity for blastp - an integer, default is [95]


       - Percentage of isolates a gene must be in to be core - a float, default is [99.0]


**Advanced Options**:

       - Maximum number of clusters - integer, default is [50000]


       - Don't split paralogs - check box


       - Translation table - which translation table to use, an integer, default is [11]


       - Change the MCL inflation value - a float, default is [1.5]


For further info see: http://sanger-pathogens.github.io/Roary/

    ]]></help>

    <citations>
        <citation type="doi">10.1093/bioinformatics/btv421</citation>
    </citations>

</tool>