view pangenomeCogAnalysis.xml @ 9:ede0f548b6ec draft

Uploaded

<tool id="pangenome_cog_analysis" name="Pangenome COG Analysis" version="1.0">
  <description>Provide statistics from pangenome matrix and COG annotations </description>
 <!-- <requirements>
  <requirement type="package" version=""></requirement>
</requirements> -->
    <command detect_errors="aggressive"><![CDATA[
        #import re

        ## Creates symlinks for each input file based on the Galaxy 'element_identifier'
        ## Used so that a human-readable name appears in the output table (instead of 'dataset_xyz.dat')
        #set $named_input_files = ''
        #for $input_file in $input_files
            ## Add single quotes around each input file identifier
            #set $_input_file = "'{}'".format($input_file.element_identifier)
            ##ln -s '${input_file}' ${_input_file} &&
            #set $named_input_files = $named_input_files + ',' + $_input_file
        #end for

	perl ${__tool_directory__}/pangenomeCogAnalysis_V1.pl $input $input2 $input_files $named_input_files $gff_files $output $output2 $output3 $output4

	]]></command>



  <inputs>
  <param format="tabular" name="input" type="data" label="Pangenome Matrix" help="Headers must be: Cluster,genes_strain1,genes_strain2..."/>
  <param format="tabular" name="input2" type="data" label="Strains group file (example species information)" help="Headers must be: strain1,groupinfo"/>
  <param type="data" name="input_files" format="txt" multiple="true" label="Collection of COG files" help="Each files must be named with the same strain name as defined in Strain group file. Headers must be Gene,COG,COGcategory"/>
  <param type="data" name="gff_files" format="gff3" multiple="true" label="Collection of GFF files for preparing Circos track" help="Not necessarily annotations from all strains, only those that you want to be represented as Circos tracks"/>
  <!--<param format="tabular" name="input_files" type="data" multiple="true" label="Annotation files"/>-->
 </inputs>

 <outputs>
	 <data format="txt" name="output" label="List of group-specific clusters"/>
	 <data format="tabular" name="output2" label="COG category count average per group"/>
	 <data format="tabular" name="output3" label="Detailed COG category count values per group"/>
	 <data format="tabular" name="output4" label="COG category count average"/>
	 <!--<data format="tabular" name="output5" label="Core-genes coordinates"/>-->
	 <collection name="output5" type="list" label="Core-genes coordinates">
    		<discover_datasets pattern="__name_and_ext__" directory="Core" />
	</collection>
	<collection name="output6" type="list" label="Group specific genes coordinates">
        <discover_datasets pattern="__name_and_ext__" directory="GroupSpecific" />
  </collection>
</outputs>

</tool>