comparison plot_comparative_clustering_summary.xml @ 17:d14b68e9fd1d draft

Uploaded - new tools added

17:d14b68e9fd1d

<tool id="plot_comparative" name="Visualization of comparative clustering" version="1.0.0">
  <description> Simple utility to create visualization of RepeatExplorer conmparative analysis</description>
  <requirements>
    <requirement type="package">r-optparse</requirement>
  </requirements>
  
    <command interpreter="Rscript" detect_errors="exit_code" >
    $__tool_directory__/plot_comparative_clustering_summary.R
    --cluster_table=$cluster_table
    --comparative_counts=$counts
    --number_of_colors=$number_of_colors
    --output=$outpdf
    $nuclear_only

    #if $normalization.use_genome_size:
      --genome_size $normalization.genome_size_table
    #end if
    </command>

    <inputs>
      <param format="txt" type="data" name="cluster_table" label="file from RepeatExplorer2 clustering - CLUSTER_TABLE.csv"/>
      <param format="txt" type="data" name="counts" label="file from RepeatExplorer2 output - COMPARATIVE_ANALYSIS_COUNTS.csv"/>
      <param value="10" min="2" max="20" type="integer" name="number_of_colors" label="Maximum number of color used for plottting"/>
      <param value="false"  type="boolean" truevalue="--nuclear_only" falsevalue="" name="nuclear_only" label="Remove all non-nuclear sequences (organel and contamination)"/>
      <conditional name="normalization">
        <param name="use_genome_size" type="boolean" checked="False" label="Normalize to genome size" help="Note that if this option is used, non-nuclear sequences are always removed."/>
        <when value="false">
          <!-- pass -->
        </when>
        <when value="true">
          <param name="genome_size_table" type="data" format="txt" label="table with genome sizes"/>

        </when>

      </conditional>
    </inputs>

    <outputs>
         	<data format="pdf" name="outpdf" label="Comparative analysis summary"/>
    </outputs>
    <help>
      **Visualization of comparative clustering**
      Visualization can be created two output files from RepeatExplorer pipeline.
      
      Input file CLUSTER_TABLE.csv contains automatic annotation, information about cluster sizes and the total number of reads used for analysis
      Example of CLUSTER_TABLE.csv: ::

          "Number_of_reads_in_clusters"	3002
          "Number_of_clusters"	895
          "Number_of_superclusters"	895
          "Number_of_singlets"	6998

          "Number_of_analyzed_reads"	10000
          
          "Cluster"	"Supercluster"	"Size"	"Size_adjusted"	"Automatic_annotation"	"TAREAN_classification"	"Final_annotation"
          1	1	61	61	"All"	"Other"
          2	2	59	59	"All/repeat/satellite"	"Putative satellites (high confidence)"
          3	3	45	45	"All/repeat/satellite"	"Putative satellites (low confidence)"
          4	4	38	38	"All"	"Other"
          5	5	32	32	"All"	"Other"
          6	6	28	28	"All"	"Other"
          7	7	25	25	"All"	"Other"
          8	8	24	24	"All"	"Other"
          9	9	23	23	"All"	"Other"
          10	10	22	22	"All/repeat/mobile_element/Class_I/LTR/Ty3_gypsy/non-chromovirus/OTA/Tat/Ogre"	"Other"
          11	11	20	20	"All"	"Other"
          12	12	20	20	"All"	"Other"


    </help>
</tool>