<tool id="snvmix2" name="SNVMix at selected positions" version="0.12.1-rc1">
  <requirements>
    <requirement type="package">SNVMix</requirement>
  </requirements>
  <description>performs SNV calling on a bam file only at the positions provided</description>
  <command interpreter="python">
    snvmix.py
      -i $input1
      -d ${input1.metadata.dbkey}
      -o $output_snvmix
      -t $type
      -l $pos
      -x ${GALAXY_DATA_INDEX_DIR}
      -q $q
      -Q $Q
      -f $full
      -R $keep_dups
      -c $keep_chastity
  </command>
 <inputs>
   <param name="type" type="select" label="model used">
     <option value="MB">Filter on map quality AND base quality (MB)</option>
     <option value="SNVMix1">SNVMix1</option>
     <option value="mb">Lowest between map and base quality is used (mb)</option>
     <option value="m">Filter on map quality and use as a surrogate for base quality (m)</option>
     <option value="b">Filter on base quality and set map quality to 1 (b)</option>
     <option value="Mb">Filter on map quality and use both map and base qualities (Mb)</option>
    </param> 
    <conditional name="refOrHistory">
      <param name="reference" type="select" label="Will you select a reference genome from your history or use a built-in index?">
        <option value="indexed">Use a built-in index</option>
        <option value="history">Use one from the history</option>
      </param>
      <when value="indexed">
        <param name="input1" type="data" format="bam" label="Select the BAM file to generate the pileup file for">
           <validator type="unspecified_build" />
           <validator type="dataset_metadata_in_file" filename="sam_fa_indices.loc" metadata_name="dbkey" metadata_column="1" message="Sequences are not currently available for the specified build." line_startswith="index" />
        </param>
      </when>
      <when value="history">
        <param name="input1" type="data" format="bam" label="Select the BAM file to generate the pileup file for" />
        <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select a reference genome" />
      </when>
    </conditional>
    <param name="q" type="integer" value="19" label="Cutoff Phred value for Base Quality, anything less than or equal to this value is ignored" />
    <param name="Q" type="integer" value="19" label="Cutoff Phred value for Map Quality, anything less than or equal to this value is ignored" />
    <param name="pos" type="data" format="tabular" label="select the tab-delimited file containing positions" />
    <param name="full" type="select" label="Do you want SNVMix to calculate probabilities for each of these positions? (only works when a set of positions has been provided)">
      <option value="yes">Yes (I know this could generate a huge file)</option>
      <option value="no">No, I just want possible variants output</option>
    </param>
    <param name="keep_dups" type="select" label="Do you want SNVMix to include reads flagged as duplicates? (only works if Picard or some other tool has set this bit in your bam file">
      <option value="no">No (ignore duplicates for variant calling)</option>
      <option value="yes">Yes (use all reads)</option>
    </param>
    <param name="keep_chastity" type="select" label="Do you want SNVMix to include reads flagged as failing the chastity filter? (only works if Picard or some other tool has set this bit in your bam file">
      <option value="no">No (ignore filtered reads for variant calling)</option>
      <option value="yes">Yes (use all reads)</option>
    </param>
</inputs>

  <outputs>
    <data format="tabular" name="output_snvmix" label="${tool.name}: Raw SNVMix calls" />
  </outputs>
  <help>

**What it does**

This tool uses the SNVMix model (Rodrigo Goya et al, 2010) to call single nucleotide variants (SNVs) from a bam file at a restricted set of positions, similar to samtools pileup -l.  This tools is typically used on a matched normal library for the identification of somatic mutations in combination with the SNVMix -f option (report probabilities at all positions).  The input must be two columns, the first being the chromosome name and the second being the position.  

  </help>
</tool>