comparison variant_select.xml @ 0:135e8721ffc5 draft

Imported from capsule None

0:135e8721ffc5

<tool id="gatk_variant_select" name="Select Variants" version="0.0.2">
  <description>from VCF files</description>
  <requirements>
      <requirement type="package" version="1.4">gatk</requirement>
  </requirements>
  <macros>
    <import>gatk_macros.xml</import>
  </macros>
  <command interpreter="python">gatk_wrapper.py
   #from binascii import hexlify
   --max_jvm_heap_fraction "1"
   --stdout "${output_log}"
   -d "--variant:variant,%(file_type)s" "${reference_source.input_variant}" "${reference_source.input_variant.ext}" "input_variant"
   -p 'java 
    -jar "\$JAVA_JAR_PATH/GenomeAnalysisTK.jar"
    -T "SelectVariants"
    --num_threads \${GALAXY_SLOTS:-4}
    -et "NO_ET" ##ET no phone home
    -o "${output_vcf}"
    
    #if $reference_source.reference_source_selector != "history":
        -R "${reference_source.ref_file.fields.path}"
    #end if
    '
    -p '
    #if $input_concordance:
        --concordance "${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">
        <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="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
          <options from_data_table="gatk_picard_indexes">
            <filter type="data_meta" key="dbkey" ref="input_variant" column="dbkey"/>
          </options>
          <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
        </param>
      </when>
      <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>
          </param>
          <when value="select_all">
            <!-- Do nothing here -->
          </when>
          <when value="select_random_fraction">
            <param name="select_random_fraction" type="float" value="0" label="Fraction" min="0" max="1" help="-fraction,--select_random_fraction &amp;lt;select_random_fraction&amp;gt;"/>
          </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>
  <tests>
      <test>
          <param name="reference_source_selector" value="history" />
          <param name="ref_file" value="phiX.fasta" ftype="fasta" />
          <param name="input_variant" value="gatk/gatk_variant_annotator/gatk_variant_annotator_out_1.vcf" ftype="vcf" />
          <param name="select_expressions_repeat" value="0" />
          <param name="input_concordance" />
          <param name="input_discordance" />
          <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 (http://www.broadinstitute.org/gsa/wiki/index.php/Using_JEXL_expressions). 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/gsa/wiki/index.php/SelectVariants&gt;`_.

To learn about best practices for variant detection using GATK, see this `overview &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Best_Practice_Variant_Detection_with_the_GATK_v3&gt;`_.

If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Frequently_Asked_Questions&gt;`_.

------

**Inputs**

GenomeAnalysisTK: SelectVariants accepts a VCF input file.


**Outputs**

The output is in VCF format.


Go `here &lt;http://www.broadinstitute.org/gsa/wiki/index.php/Input_files_for_the_GATK&gt;`_ for details on GATK file formats.

-------

**Settings**::


 out                         VCFWriter  stdout  File to which variants should be written
 variant                     RodBinding[VariantContext]  NA  Input VCF file
 concordance                 RodBinding[VariantContext]  none  Output variants that were also called in this comparison track
 discordance                 RodBinding[VariantContext]  none  Output variants that were not called in this comparison track
 exclude_sample_file         Set[File]  []  File containing a list of samples (one per line) to exclude. Can be specified multiple times
 exclude_sample_name         Set[String]  []  Exclude genotypes from this sample. Can be specified multiple times
 excludeFiltered             boolean  false  Don't include filtered loci in the analysis
 excludeNonVariants          boolean  false  Don't include loci found to be non-variant after the subsetting procedure
 keepIDs                     File  NA  Only emit sites whose ID is found in this file (one ID per line)
 keepOriginalAC              boolean  false  Don't update the AC, AF, or AN values in the INFO field after selecting
 mendelianViolation          Boolean  false  output mendelian violation sites only
 mvq                         double  0.0  Minimum genotype QUAL score for each trio member required to accept a site as a violation
 remove_fraction_genotypes   double  0.0  Selects a fraction (a number between 0 and 1) of the total genotypes at random from the variant track and sets them to nocall
 restrictAllelesTo           NumberAlleleRestriction  ALL  Select only variants of a particular allelicity. Valid options are ALL (default), MULTIALLELIC or BIALLELIC
 sample_expressions          Set[String]  NA  Regular expression to select many samples from the ROD tracks provided. Can be specified multiple times
 sample_file                 Set[File]  NA  File containing a list of samples (one per line) to include. Can be specified multiple times
 sample_name                 Set[String]  []  Include genotypes from this sample. Can be specified multiple times
 select_expressions          ArrayList[String]  []  One or more criteria to use when selecting the data
 select_random_fraction      double  0.0  Selects a fraction (a number between 0 and 1) of the total variants at random from the variant track
 select_random_number        int  0  Selects a number of variants at random from the variant track
 selectTypeToInclude         List[Type]  []  Select only a certain type of variants from the input file. Valid types are INDEL, SNP, MIXED, MNP, SYMBOLIC, NO_VARIATION. Can be specified multiple times

@CITATION_SECTION@
  </help>
</tool>