comparison variant_select.xml @ 6:35c00763cb5c draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gatk2 commit cf399638ebca4250bcc15f468238a9964de97b33

5:84584664264c

<tool id="gatk2_variant_select" name="Select Variants" version="@VERSION@.0">
  <description>from VCF files</description>
  <expand macro="requirements" />
  <macros>
    <import>gatk2_macros.xml</import>
  </macros>
  <command interpreter="python">
    #from binascii import hexlify

    gatk2_wrapper.py
   --stdout "${output_log}"

    -T "SelectVariants"
    \$GATK2_SITE_OPTIONS

    @THREADS@
    -o "${output_vcf}"
    
    #if $reference_source.reference_source_selector != "history":
        -R "${reference_source.ref_file.fields.path}"
    #end if
    '
    -p '

        --concordance "${input_concordance}"
    #end if
    #if $input_discordance:
        --discordance "${input_discordance}"
    #end if
    
    #for $exclude_sample_name in $exclude_sample_name_repeat:
        --exclude_sample_name "${exclude_sample_name.exclude_sample_name}"
    #end for
    
    ${exclude_filtered}
    
    #for $sample_name in $sample_name_repeat:
        --sample_name "${sample_name.sample_name}"
    #end for
    '
    
    #for $select_expressions in $select_expressions_repeat:
        #set $select_expression = "--select_expressions '%s'" % ( str( $select_expressions.select_expressions ) )
        -o '${ hexlify( $select_expression ) }'
    #end for
    
    ##start tool specific options
    #if str( $analysis_param_type.analysis_param_type_selector ) == 'advanced':
        -p '
          #for $exclude_sample_file in $analysis_param_type.exclude_sample_file_repeat:
              --exclude_sample_file "${exclude_sample_file.exclude_sample_file}"
          #end for
          
          #for $sample_file in $analysis_param_type.sample_file_repeat:
              --sample_file "${ample_file.sample_file}"
          #end for
          
          #if $analysis_param_type.input_keep_ids:
              --keepIDs "${analysis_param_type.input_keep_ids}"
          #end if
          
          ${analysis_param_type.keep_original_AC}
          
          ${analysis_param_type.mendelian_violation}
          
          --mendelianViolationQualThreshold "${analysis_param_type.mendelian_violation_qual_threshold}"
          
          --remove_fraction_genotypes "${analysis_param_type.remove_fraction_genotypes}"
          
          --restrictAllelesTo "${analysis_param_type.restrict_alleles_to}"
          
          #if str( $analysis_param_type.select_random_type.select_random_type_selector ) == 'select_random_fraction':
              --select_random_fraction "${analysis_param_type.select_random_type.select_random_fraction}"
          #elif str( $analysis_param_type.select_random_type.select_random_type_selector ) == 'select_random_number':
              --select_random_number "${analysis_param_type.select_random_type.select_random_number}"
          #end if
          
          #if $analysis_param_type.select_type_to_include:
              #for $type_to_include in str( $analysis_param_type.select_type_to_include ).split( ',' ):
                  --selectTypeToInclude "${type_to_include}"
              #end for
          #end if
          
          ${analysis_param_type.exclude_non_variants}
        '
        
        #for $sample_expressions in $analysis_param_type.sample_expressions_repeat:
            #set $sample_expression = "--sample_expressions '%s'" % ( str( $sample_expressions.sample_expressions ) )
            -o '${ hexlify( $sample_expression ) }'
        #end for
        
    #end if
    ##end tool specific options
    
    #include source=$standard_gatk_options#
    
    
  </command>
  <inputs>
    <conditional name="reference_source">
      <expand macro="reference_source_selector_param" />
      <when value="cached">

      <when value="history"> <!-- FIX ME!!!! -->
        <param name="input_variant" type="data" format="vcf" label="Variant file to select" help="-V,--variant &amp;lt;variant&amp;gt;" />
        <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" />
      </when>
    </conditional>
    
    <repeat name="select_expressions_repeat" title="Criteria to use when selecting the data" help="-select,--select_expressions &amp;lt;select_expressions&amp;gt;">
        <param name="select_expressions" type="text" label="JEXL expression">
            <sanitizer>
              <valid initial="string.printable">
               <remove value="&apos;"/>
             </valid>
              <mapping initial="none"/>
            </sanitizer>
        </param>
    </repeat>
    
    <param name="input_concordance" type="data" format="vcf" label="Output variants that were also called in this comparison track" optional="True" help="-conc,--concordance &amp;lt;concordance&amp;gt;"/>
    <param name="input_discordance" type="data" format="vcf" label="Output variants that were not called in this comparison track" optional="True" help="-disc,--discordance &amp;lt;discordance&amp;gt;"/>
    
    <repeat name="sample_name_repeat" title="Include Samples by name" help="-sn,--sample_name &amp;lt;sample_name&amp;gt;">
        <param name="sample_name" type="text" label="Include genotypes from this sample"/>
    </repeat>
    
    <repeat name="exclude_sample_name_repeat" title="Exclude Samples by name" help="-xl_sn,--exclude_sample_name &amp;lt;exclude_sample_name&amp;gt;">
        <param name="exclude_sample_name" type="text" label="Exclude genotypes from this sample"/>
    </repeat>
    
    <param name="exclude_filtered" type="boolean" truevalue="--excludeFiltered" falsevalue="" label="Don't include filtered loci in the analysis" help="-ef,--excludeFiltered" />
    
    <expand macro="gatk_param_type_conditional" />
    
    
    <expand macro="analysis_type_conditional">
        
        <repeat name="exclude_sample_file_repeat" title="Exclude Samples by file" help="-xl_sf,--exclude_sample_file &amp;lt;exclude_sample_file&amp;gt;">
            <param name="exclude_sample_file" type="data" format="txt" label="File containing a list of samples (one per line) to exclude"/>
        </repeat>
        
        <repeat name="sample_file_repeat" title="Samples by file" help="-sf,--sample_file &amp;lt;sample_file&amp;gt;">
            <param name="sample_file" type="data" format="txt" label="File containing a list of samples (one per line) to include" />
        </repeat>
        
        <param name="input_keep_ids" type="data" format="text" label="Only emit sites whose ID is found in this file" optional="True" help="-IDs,--keepIDs &amp;lt;keepIDs&amp;gt;"/>
        
        <param name="keep_original_AC" type="boolean" truevalue="--keepOriginalAC" falsevalue="" label="Don't update the AC, AF, or AN values in the INFO field after selecting" help="-keepOriginalAC,--keepOriginalAC" />
        
        <param name="mendelian_violation" type="boolean" truevalue="--mendelianViolation" falsevalue="" label="output mendelian violation sites only" help="-mv,--mendelianViolation" />
        
        <param name="mendelian_violation_qual_threshold" type="float" label="Minimum genotype QUAL score for each trio member required to accept a site as a mendelian violation" value="0" help="-mvq,--mendelianViolationQualThreshold &amp;lt;mendelianViolationQualThreshold&amp;gt;" />
        
        <param name="remove_fraction_genotypes" type="float" label="Selects a fraction (a number between 0 and 1) of the total genotypes at random from the variant track and sets them to nocall" value="0" min="0" max="1" help="-fractionGenotypes,--remove_fraction_genotypes &amp;lt;remove_fraction_genotypes&amp;gt;" />
        
        <param name="restrict_alleles_to" type="select" label="Select only variants of a particular allelicity" help="-restrictAllelesTo,--restrictAllelesTo &amp;lt;restrictAllelesTo&amp;gt;">
            <option value="ALL" selected="True">ALL</option>
            <option value="MULTIALLELIC">MULTIALLELIC</option>
            <option value="BIALLELIC">BIALLELIC</option>
        </param>
        
        <repeat name="sample_expressions_repeat" title="Regular expression to select many samples from the ROD tracks provided" help="-se,--sample_expressions &amp;lt;sample_expressions&amp;gt;">
            <param name="sample_expressions" type="text" label="Regular expression">
                <sanitizer>
                  <valid initial="string.printable">
                   <remove value="&apos;"/>
                 </valid>
                  <mapping initial="none"/>
                </sanitizer>
            </param>
        </repeat>
        
        <conditional name="select_random_type">
          <param name="select_random_type_selector" type="select" label="Select a random subset of variants">
            <option value="select_all" selected="True">Use all variants</option>
            <option value="select_random_fraction">Select random fraction</option>
            <option value="select_random_number">Select random number</option>

          </when>
          <when value="select_random_number">
            <param name="select_random_number" type="integer" value="0" label="Count" help="-number,--select_random_number &amp;lt;select_random_number&amp;gt;" />
          </when>
        </conditional>
        
        <param name="exclude_non_variants" type="boolean" truevalue="--excludeNonVariants" falsevalue="" label="Don't include loci found to be non-variant after the subsetting procedure" help="-env,--excludeNonVariants" />
        
        <param name="select_type_to_include" type="select" label="Select only a certain type of variants from the input file" multiple="True" display="checkboxes" help="-selectType,--selectTypeToInclude &amp;lt;selectTypeToInclude&amp;gt;">
            <option value="INDEL">INDEL</option>
            <option value="SNP">SNP</option>
            <option value="MIXED">MIXED</option>
            <option value="MNP">MNP</option>
            <option value="SYMBOLIC">SYMBOLIC</option>
            <option value="NO_VARIATION">NO_VARIATION</option>
        </param>
    </expand>
    
  </inputs>
  <outputs>
    <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (Variant File)" />
    <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
  </outputs>

          <param name="exclude_sample_name_repeat" value="0" />
          <param name="exclude_filtered" />
          <param name="sample_name_repeat" value="0" />
          <param name="gatk_param_type_selector" value="basic" />
          <param name="analysis_param_type_selector" value="basic" />
          <output name="output_vcf" file="gatk/gatk_variant_select/gatk_variant_select_out_1.vcf" lines_diff="4" /> 
          <output name="output_log" file="gatk/gatk_variant_select/gatk_variant_select_out_1.log.contains" compare="contains" />
      </test>
  </tests>
  <help>
**What it does**

Often, a VCF containing many samples and/or variants will need to be subset in order to facilitate certain analyses (e.g. comparing and contrasting cases vs. controls; extracting variant or non-variant loci that meet certain requirements, displaying just a few samples in a browser like IGV, etc.). SelectVariants can be used for this purpose. Given a single VCF file, one or more samples can be extracted from the file (based on a complete sample name or a pattern match). Variants can be further selected by specifying criteria for inclusion, i.e. "DP &gt; 1000" (depth of coverage greater than 1000x), "AF &lt; 0.25" (sites with allele frequency less than 0.25). These JEXL expressions are documented in the `Using JEXL expressions section &lt;http://gatkforums.broadinstitute.org/discussion/1255/what-are-jexl-expressions-and-how-can-i-use-them-with-the-gatk&gt;`_. One can optionally include concordance or discordance tracks for use in selecting overlapping variants. 

For more information on using the SelectVariants module, see this `tool specific page &lt;http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_variantutils_SelectVariants.html&gt;`_.

To learn about best practices for variant detection using GATK, see this `overview &lt;http://www.broadinstitute.org/gatk/guide/topic?name=best-practices&gt;`_.

6:35c00763cb5c

<tool id="gatk2_variant_select" name="Select Variants" version="@VERSION@.2">
  <description>from VCF files</description>
  <macros>
    <import>gatk2_macros.xml</import>
  </macros>
  <expand macro="requirements" />
  <expand macro="version_command" />
  <command interpreter="python">
    #from binascii import hexlify

    gatk2_wrapper.py
   --stdout "${output_log}"

    -T "SelectVariants"
    \$GATK2_SITE_OPTIONS

    @THREADS@
    -o "${output_vcf}"

    #if $reference_source.reference_source_selector != "history":
        -R "${reference_source.ref_file.fields.path}"
    #end if
    '
    -p '

        --concordance "${input_concordance}"
    #end if
    #if $input_discordance:
        --discordance "${input_discordance}"
    #end if

    #for $exclude_sample_name in $exclude_sample_name_repeat:
        --exclude_sample_name "${exclude_sample_name.exclude_sample_name}"
    #end for

    ${exclude_filtered}

    #for $sample_name in $sample_name_repeat:
        --sample_name "${sample_name.sample_name}"
    #end for
    '

    #for $select_expressions in $select_expressions_repeat:
        #set $select_expression = "--select_expressions '%s'" % ( str( $select_expressions.select_expressions ) )
        -o '${ hexlify( $select_expression ) }'
    #end for

    ##start tool specific options
    #if str( $analysis_param_type.analysis_param_type_selector ) == 'advanced':
        -p '
          #for $esf in $analysis_param_type.exclude_sample_file:
              --exclude_sample_file "${esf}"
          #end for

          #for $sf in $analysis_param_type.sample_file:
              --sample_file "${sf}"
          #end for

          #if $analysis_param_type.input_keep_ids:
              --keepIDs "${analysis_param_type.input_keep_ids}"
          #end if

          ${analysis_param_type.keep_original_AC}

          ${analysis_param_type.mendelian_violation}

          --mendelianViolationQualThreshold "${analysis_param_type.mendelian_violation_qual_threshold}"

          --remove_fraction_genotypes "${analysis_param_type.remove_fraction_genotypes}"

          --restrictAllelesTo "${analysis_param_type.restrict_alleles_to}"

          #if str( $analysis_param_type.select_random_type.select_random_type_selector ) == 'select_random_fraction':
              --select_random_fraction "${analysis_param_type.select_random_type.select_random_fraction}"
          #elif str( $analysis_param_type.select_random_type.select_random_type_selector ) == 'select_random_number':
              --select_random_number "${analysis_param_type.select_random_type.select_random_number}"
          #end if

          #if $analysis_param_type.select_type_to_include:
              #for $type_to_include in str( $analysis_param_type.select_type_to_include ).split( ',' ):
                  --selectTypeToInclude "${type_to_include}"
              #end for
          #end if

          ${analysis_param_type.exclude_non_variants}
        '

        #for $sample_expressions in $analysis_param_type.sample_expressions_repeat:
            #set $sample_expression = "--sample_expressions '%s'" % ( str( $sample_expressions.sample_expressions ) )
            -o '${ hexlify( $sample_expression ) }'
        #end for

    #end if
    ##end tool specific options

    #include source=$standard_gatk_options#
  </command>
  <inputs>
    <conditional name="reference_source">
      <expand macro="reference_source_selector_param" />
      <when value="cached">

      <when value="history"> <!-- FIX ME!!!! -->
        <param name="input_variant" type="data" format="vcf" label="Variant file to select" help="-V,--variant &amp;lt;variant&amp;gt;" />
        <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;" />
      </when>
    </conditional>

    <repeat name="select_expressions_repeat" title="Criteria to use when selecting the data" help="-select,--select_expressions &amp;lt;select_expressions&amp;gt;">
        <param name="select_expressions" type="text" label="JEXL expression">
            <sanitizer>
              <valid initial="string.printable">
               <remove value="&apos;"/>
             </valid>
              <mapping initial="none"/>
            </sanitizer>
        </param>
    </repeat>

    <param name="input_concordance" type="data" format="vcf" label="Output variants that were also called in this comparison track" optional="True" help="-conc,--concordance &amp;lt;concordance&amp;gt;"/>
    <param name="input_discordance" type="data" format="vcf" label="Output variants that were not called in this comparison track" optional="True" help="-disc,--discordance &amp;lt;discordance&amp;gt;"/>

    <repeat name="sample_name_repeat" title="Include Samples by name" help="-sn,--sample_name &amp;lt;sample_name&amp;gt;">
        <param name="sample_name" type="text" label="Include genotypes from this sample"/>
    </repeat>

    <repeat name="exclude_sample_name_repeat" title="Exclude Samples by name" help="-xl_sn,--exclude_sample_name &amp;lt;exclude_sample_name&amp;gt;">
        <param name="exclude_sample_name" type="text" label="Exclude genotypes from this sample"/>
    </repeat>

    <param name="exclude_filtered" type="boolean" truevalue="--excludeFiltered" falsevalue="" label="Don't include filtered loci in the analysis" help="-ef,--excludeFiltered" />

    <expand macro="gatk_param_type_conditional" />

    <expand macro="analysis_type_conditional">

        <param name="exclude_sample_file" type="data" format="txt" multiple="True" label="Exclude Samples by file" help="File containing a list of samples (one per line) to exclude (-xl_sf,--exclude_sample_file &amp;lt;exclude_sample_file&amp;gt;)"/>

        <param name="sample_file" type="data" format="txt" multiple="True" label="Samples by file"  help="File containing a list of samples (one per line) to include (-sf,--sample_file &amp;lt;sample_file&amp;gt;)"/>

        <param name="input_keep_ids" type="data" format="txt" label="Only emit sites whose ID is found in this file" optional="True" help="-IDs,--keepIDs &amp;lt;keepIDs&amp;gt;"/>

        <param name="keep_original_AC" type="boolean" truevalue="--keepOriginalAC" falsevalue="" label="Don't update the AC, AF, or AN values in the INFO field after selecting" help="-keepOriginalAC,--keepOriginalAC" />

        <param name="mendelian_violation" type="boolean" truevalue="--mendelianViolation" falsevalue="" label="output mendelian violation sites only" help="-mv,--mendelianViolation" />

        <param name="mendelian_violation_qual_threshold" type="float" label="Minimum genotype QUAL score for each trio member required to accept a site as a mendelian violation" value="0" help="-mvq,--mendelianViolationQualThreshold &amp;lt;mendelianViolationQualThreshold&amp;gt;" />

        <param name="remove_fraction_genotypes" type="float" label="Selects a fraction (a number between 0 and 1) of the total genotypes at random from the variant track and sets them to nocall" value="0" min="0" max="1" help="-fractionGenotypes,--remove_fraction_genotypes &amp;lt;remove_fraction_genotypes&amp;gt;" />

        <param name="restrict_alleles_to" type="select" label="Select only variants of a particular allelicity" help="-restrictAllelesTo,--restrictAllelesTo &amp;lt;restrictAllelesTo&amp;gt;">
            <option value="ALL" selected="True">ALL</option>
            <option value="MULTIALLELIC">MULTIALLELIC</option>
            <option value="BIALLELIC">BIALLELIC</option>
        </param>

        <repeat name="sample_expressions_repeat" title="Regular expression to select many samples from the ROD tracks provided" help="-se,--sample_expressions &amp;lt;sample_expressions&amp;gt;">
            <param name="sample_expressions" type="text" label="Regular expression">
                <sanitizer>
                  <valid initial="string.printable">
                   <remove value="&apos;"/>
                 </valid>
                  <mapping initial="none"/>
                </sanitizer>
            </param>
        </repeat>

        <conditional name="select_random_type">
          <param name="select_random_type_selector" type="select" label="Select a random subset of variants">
            <option value="select_all" selected="True">Use all variants</option>
            <option value="select_random_fraction">Select random fraction</option>
            <option value="select_random_number">Select random number</option>

          </when>
          <when value="select_random_number">
            <param name="select_random_number" type="integer" value="0" label="Count" help="-number,--select_random_number &amp;lt;select_random_number&amp;gt;" />
          </when>
        </conditional>

        <param name="exclude_non_variants" type="boolean" truevalue="--excludeNonVariants" falsevalue="" label="Don't include loci found to be non-variant after the subsetting procedure" help="-env,--excludeNonVariants" />

        <param name="select_type_to_include" type="select" label="Select only a certain type of variants from the input file" multiple="True" display="checkboxes" help="-selectType,--selectTypeToInclude &amp;lt;selectTypeToInclude&amp;gt;">
            <option value="INDEL">INDEL</option>
            <option value="SNP">SNP</option>
            <option value="MIXED">MIXED</option>
            <option value="MNP">MNP</option>
            <option value="SYMBOLIC">SYMBOLIC</option>
            <option value="NO_VARIATION">NO_VARIATION</option>
        </param>
    </expand>

  </inputs>
  <outputs>
    <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (Variant File)" />
    <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
  </outputs>

          <param name="exclude_sample_name_repeat" value="0" />
          <param name="exclude_filtered" />
          <param name="sample_name_repeat" value="0" />
          <param name="gatk_param_type_selector" value="basic" />
          <param name="analysis_param_type_selector" value="basic" />
          <output name="output_vcf" file="gatk/gatk_variant_select/gatk_variant_select_out_1.vcf" lines_diff="4" />
          <output name="output_log" file="gatk/gatk_variant_select/gatk_variant_select_out_1.log.contains" compare="contains" />
      </test>
  </tests>
  <help>
**What it does**

Often, a VCF containing many samples and/or variants will need to be subset in order to facilitate certain analyses (e.g. comparing and contrasting cases vs. controls; extracting variant or non-variant loci that meet certain requirements, displaying just a few samples in a browser like IGV, etc.). SelectVariants can be used for this purpose. Given a single VCF file, one or more samples can be extracted from the file (based on a complete sample name or a pattern match). Variants can be further selected by specifying criteria for inclusion, i.e. "DP &gt; 1000" (depth of coverage greater than 1000x), "AF &lt; 0.25" (sites with allele frequency less than 0.25). These JEXL expressions are documented in the `Using JEXL expressions section &lt;http://gatkforums.broadinstitute.org/discussion/1255/what-are-jexl-expressions-and-how-can-i-use-them-with-the-gatk&gt;`_. One can optionally include concordance or discordance tracks for use in selecting overlapping variants.

For more information on using the SelectVariants module, see this `tool specific page &lt;http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_variantutils_SelectVariants.html&gt;`_.

To learn about best practices for variant detection using GATK, see this `overview &lt;http://www.broadinstitute.org/gatk/guide/topic?name=best-practices&gt;`_.