<?xml version="1.0"?>

<tool id="dedup_realign_bam_1" name="Deduplicate and realign a BAM file(s)">
  <description>using samtools and GATK</description>
  <version_string>echo 1.0.0</version_string>
  <command interpreter="perl">prep_bams $__tool_data_path__ $messages $ref_genome\.fa ${__new_file_path__} $prepped_bam_file $input_bam_file
      #for $i in $inputs
        ${i.input}
      #end for 
  </command>
  <inputs>
    <param name="ref_genome" type="genomebuild" label="Reference genome" help="against which the reads were mapped"/>
    <param format="bam" name="input_bam_file" type="data" label="Source BAM (mapped reads) file" help="Need to merge multiple input BAM files for one sample? Use controls below."/>
    <repeat name="inputs" title="Input BAM Files">
      <param name="input" label="Additional BAM file to merge" type="data" format="bam" />
    </repeat>

  </inputs>
  <outputs>
    <data name="prepped_bam_file" format="bam" type="data" label="Deduped and realigned mapped reads"/>
    <data name="messages" format="text" type="data" label="Prep process log messages"/>
  </outputs>

  <tests/>

  <help>
  This tool runs a set of processes to first optionally merge BAMs, then deduplicate (samtools) and realign (GATK) the reads mapped to a reference genome.  
  This is important for genotyping studies.  While these steps could be run independently in a workflow,
  an enormous amount of intermediate data files are generated.  This tool cleans up those intermediate files.
 </help>

</tool>