view variant_eval.xml @ 37:dd9f8ea2b718 draft

unified_genotyper - indelGap penalty param need to be integer values

<tool id="gatk2_variant_eval" name="Eval Variants" version="0.0.7">
  <description></description>
  <requirements>
      <requirement type="package" version="2.3">gatk</requirement>
  </requirements>
  <command interpreter="python">gatk2_wrapper.py
   #from binascii import hexlify
   --max_jvm_heap_fraction "1"
   --stdout "${output_log}"
   #for $var_count, $variant in enumerate( $reference_source.variants ):
      -d "--eval:input_${var_count},%(file_type)s" "${variant.input_variant}" "${variant.input_variant.ext}" "input_variants_${var_count}"
   #end for
   -p 'java 
    -jar "\$GATK2_PATH/GenomeAnalysisTK.jar"
    -T "VariantEval"
    --out "${output_report}"
    \$GATK2_SITE_OPTIONS
    \$GATK2_NUM_THREADS
    ##--num_threads 4 ##hard coded, for now
    ##-et "NO_ET" -K "\$GATK2_BASE/gatk2_key_file" ##ET no phone home
    ##-log "${output_log}" ##don't use this to log to file, instead directly capture stdout
    #if $reference_source.reference_source_selector != "history":
        -R "${reference_source.ref_file.fields.path}"
    #end if
   '
   
    #for $rod_binding in $comp_rod_bind:
        -d "--comp:${rod_binding.comp_rod_name},%(file_type)s" "${rod_binding.comp_input_rod}" "${rod_binding.comp_input_rod.ext}" "input_comp_${rod_binding.comp_rod_name}"
        #if str( $rod_binding.comp_known_names ):
            -p '--known_names "${rod_binding.comp_rod_name}"'
        #end if
    #end for
    
    #if str( $dbsnp_rod_bind_type.dbsnp_rod_bind_type_selector ) == 'set_dbsnp':
        -d "--dbsnp:${dbsnp_rod_bind_type.dbsnp_rod_name},%(file_type)s" "${dbsnp_rod_bind_type.dbsnp_input_rod}" "${dbsnp_rod_bind_type.dbsnp_input_rod.ext}" "input_dbsnp_${dbsnp_rod_bind_type.dbsnp_rod_name}"
        #if str( $dbsnp_rod_bind_type.dbsnp_known_names ):
            -p '--known_names "${dbsnp_rod_bind_type.dbsnp_rod_name}"'
        #end if
    #end if
   
    ##start standard gatk options
    #if $gatk_param_type.gatk_param_type_selector == "advanced":
        #for $pedigree in $gatk_param_type.pedigree:
            -p '--pedigree "${pedigree.pedigree_file}"'
        #end for
        #for $pedigree_string in $gatk_param_type.pedigree_string_repeat:
            -p '--pedigreeString "${pedigree_string.pedigree_string}"'
        #end for
        -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"'
        #set default_read_filters = ['DuplicateRead','FailsVendorQualityCheck','NotPrimaryAlignment','MalformedRead','UnmappedRead']
        #for $read_filter in $gatk_param_type.read_filter:
            -p '
            #if $read_filter.read_filter_type.read_filter_type_selector not in $default_read_filters:
                --read_filter "${read_filter.read_filter_type.read_filter_type_selector}"
            #end if
            #for $name, $param in $read_filter.read_filter_type.iteritems():
                #if $name not in [ "__current_case__", "read_filter_type_selector" ]:
                    #if hasattr( $param.input, 'truevalue' ):
                        ${param}
                    #else:
                        --${name} "${param}"
                    #end if
                #end if
            #end for
            '
        #end for
        #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_interval_repeat ):
            -d "--intervals" "${input_intervals.input_intervals}" "${input_intervals.input_intervals.ext}" "input_intervals_${interval_count}"
        #end for
        
        #for $interval_count, $input_intervals in enumerate( $gatk_param_type.input_exclude_interval_repeat ):
            -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}"
        #end for

        -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"'
        
        -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"'
        #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE":
            -p '--${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_type_selector} "${gatk_param_type.downsampling_type.downsample_to_type.downsample_to_value}"'
        #end if
        -p '
        --baq "${gatk_param_type.baq}"
        --baqGapOpenPenalty "${gatk_param_type.baq_gap_open_penalty}"
        ${gatk_param_type.use_original_qualities}
        --defaultBaseQualities "${gatk_param_type.default_base_qualities}"
        --validation_strictness "${gatk_param_type.validation_strictness}"
        --interval_merging "${gatk_param_type.interval_merging}"
        ${gatk_param_type.disable_experimental_low_memory_sharding}
        ${gatk_param_type.fix_misencoded_quality_scores}
        ${gatk_param_type.non_deterministic_random_seed}
        '
        #for $rg_black_list_count, $rg_black_list in enumerate( $gatk_param_type.read_group_black_list_repeat ):
            #if $rg_black_list.read_group_black_list_type.read_group_black_list_type_selector == "file":
                -d "--read_group_black_list" "${rg_black_list.read_group_black_list_type.read_group_black_list}" "txt" "input_read_group_black_list_${rg_black_list_count}"
            #else
                -p '--read_group_black_list "${rg_black_list.read_group_black_list_type.read_group_black_list}"'
            #end if
        #end for
    #end if
    
    #if $reference_source.reference_source_selector == "history":
        -d "-R" "${reference_source.ref_file}" "${reference_source.ref_file.ext}" "gatk_input"
    #end if
    ##end standard gatk options
    
    
    ##start analysis specific options
    #if $analysis_param_type.analysis_param_type_selector == "advanced":
        #for $stratification in $analysis_param_type.stratifications:
            #set $select_string = "--select_exps '%s' --select_names '%s'" % ( str( $stratification.select_exps ), str( $stratification.select_name )  )
            -o '${ hexlify( $select_string ) }'
        #end for
        -p '
        
        #for $sample in $analysis_param_type.samples:
            --sample "${sample.sample}"
        #end for
        
        #if str( $analysis_param_type.stratification_modules ) != "None":
            #for $stratification_module in str( $analysis_param_type.stratification_modules).split( ',' ):
                --stratificationModule "${stratification_module}"
            #end for
        #end if
        
        ${analysis_param_type.do_not_use_all_standard_stratifications}
        
        #for $variant_type in $analysis_param_type.only_variants_of_type:
            --onlyVariantsOfType "${variant_type.variant_type}"
        #end for
        
        #if str( $analysis_param_type.eval_modules ) != "None":
            #for $eval_module in str( $analysis_param_type.eval_modules).split( ',' ):
                --evalModule "${eval_module}"
            #end for
        #end if
        
        ${analysis_param_type.do_not_use_all_standard_modules}
        
        #if str( $analysis_param_type.num_samples ) != "0":
            --numSamples "${analysis_param_type.num_samples}"
        #end if
        
        --minPhaseQuality "${analysis_param_type.min_phase_quality}"
        
        #if str( $analysis_param_type.family ):
            --family_structure "${analysis_param_type.family}"
        #end if
        
        --mendelianViolationQualThreshold "${analysis_param_type.mendelian_violation_qual_threshold}"
        
        #if str( $analysis_param_type.ancestral_alignments ) != "None":
            --ancestralAlignments "${analysis_param_type.ancestral_alignments}"
        #end if
        '
        #if str( $analysis_param_type.known_cnvs ) != "None":
            -d "--knownCNVs" "${analysis_param_type.known_cnvs}" "${analysis_param_type.known_cnvs.ext}" "input_known_cnvs"
        #end if
        
        #if str( $analysis_param_type.strat_intervals ) != "None":
            -d "--stratIntervals" "${analysis_param_type.strat_intervals}" "${analysis_param_type.strat_intervals.ext}" "input_strat_intervals"
        #end if
    #end if
  </command>
  <inputs>
    
    <conditional name="reference_source">
      <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
        <option value="cached">Locally cached</option>
        <option value="history">History</option>
      </param>
      <when value="cached">
        <repeat name="variants" title="Variant" min="1" help="-eval,--eval &amp;lt;eval&amp;gt;">
          <param name="input_variant" type="data" format="vcf" label="Input variant file" />
        </repeat>
        <param name="ref_file" type="select" label="Using reference genome" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
          <options from_data_table="gatk2_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!!!! -->
        <repeat name="variants" title="Variant" min="1" help="-eval,--eval &amp;lt;eval&amp;gt;">
          <param name="input_variant" type="data" format="vcf" label="Input variant file" />
        </repeat>
        <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="comp_rod_bind" title="Binding for reference-ordered comparison data" help="-comp,--comp &amp;lt;comp&amp;gt;">
      <param name="comp_input_rod" type="data" format="vcf" label="Comparison ROD file" />
      <param name="comp_rod_name" type="text" value="Unnamed" label="Comparison ROD Name"/>
      <param name="comp_known_names" type="boolean" truevalue="--known_names" falsevalue="" label="Use Comparison ROD as known_names" help="-knownName,--known_names &amp;lt;known_names&amp;gt;"/>
    </repeat>
    
    <conditional name="dbsnp_rod_bind_type">
      <param name="dbsnp_rod_bind_type_selector" type="select" label="Provide a dbSNP reference-ordered data file" help="-D,--dbsnp &amp;lt;dbsnp&amp;gt;">
        <option value="set_dbsnp" selected="True">Set dbSNP</option>
        <option value="exclude_dbsnp">Don't set dbSNP</option>
      </param>
      <when value="exclude_dbsnp">
        <!-- Do nothing here -->
      </when>
      <when value="set_dbsnp">
        <param name="dbsnp_input_rod" type="data" format="vcf" label="dbSNP ROD file" />
        <param name="dbsnp_rod_name" type="hidden" value="dbsnp" label="dbSNP ROD Name"/>
        <param name="dbsnp_known_names" type="boolean" truevalue="--known_names" falsevalue="" label="Use dbSNP ROD as known_names" help="-knownName,--known_names &amp;lt;known_names&amp;gt;" />
      </when>
    </conditional>
    
    <conditional name="gatk_param_type">
      <param name="gatk_param_type_selector" type="select" label="Basic or Advanced GATK options">
        <option value="basic" selected="True">Basic</option>
        <option value="advanced">Advanced</option>
      </param>
      <when value="basic">
        <!-- Do nothing here -->
      </when>
      <when value="advanced">
        <repeat name="pedigree" title="Pedigree file" help="-ped,--pedigree &amp;lt;pedigree&amp;gt;">
            <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples"/>
        </repeat>
        <repeat name="pedigree_string_repeat" title="Pedigree string" help="-pedString,--pedigreeString &amp;lt;pedigreeString&amp;gt;">
            <param name="pedigree_string" type="text" value="" label="Pedigree string for samples"/>
        </repeat>
        <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information" help="-pedValidationType,--pedigreeValidationType &amp;lt;pedigreeValidationType&amp;gt;">
          <option value="STRICT" selected="True">STRICT</option>
          <option value="SILENT">SILENT</option>
        </param>
        <repeat name="read_filter" title="Read Filter" help="-rf,--read_filter &amp;lt;read_filter&amp;gt;">
            <conditional name="read_filter_type">
              <param name="read_filter_type_selector" type="select" label="Read Filter Type">
                <option value="BadCigar">BadCigar</option>
                <option value="BadMate">BadMate</option>
                <option value="DuplicateRead">DuplicateRead</option>
                <option value="FailsVendorQualityCheck">FailsVendorQualityCheck</option>
                <option value="MalformedRead">MalformedRead</option>
                <option value="MappingQuality">MappingQuality</option>
                <option value="MappingQualityUnavailable">MappingQualityUnavailable</option>
                <option value="MappingQualityZero">MappingQualityZero</option>
                <option value="MateSameStrand">MateSameStrand</option>
                <option value="MaxInsertSize">MaxInsertSize</option>
                <option value="MaxReadLength" selected="True">MaxReadLength</option>
                <option value="MissingReadGroup">MissingReadGroup</option>
                <option value="NoOriginalQualityScores">NoOriginalQualityScores</option>
                <option value="NotPrimaryAlignment">NotPrimaryAlignment</option>
                <option value="Platform454">Platform454</option>
                <option value="Platform">Platform</option>
                <option value="PlatformUnit">PlatformUnit</option>
                <option value="ReadGroupBlackList">ReadGroupBlackList</option>
                <option value="ReadName">ReadName</option>
                <option value="ReadStrand">ReadStrand</option>
                <option value="ReassignMappingQuality">ReassignMappingQuality</option>
                <option value="Sample">Sample</option>
                <option value="SingleReadGroup">SingleReadGroup</option>
                <option value="UnmappedRead">UnmappedRead</option>
              </param>
              <when value="BadCigar">
                  <!-- no extra options -->
              </when>
              <when value="BadMate">
                  <!-- no extra options -->
              </when>
              <when value="DuplicateRead">
                  <!-- no extra options -->
              </when>
              <when value="FailsVendorQualityCheck">
                  <!-- no extra options -->
              </when>
              <when value="MalformedRead">
                  <param name="filter_mismatching_base_and_quals" type="boolean" truevalue="--filter_mismatching_base_and_quals" falsevalue="" checked="false" label="filter out the reads with mismatching number of bases and base qualities" help="filter out the mismatch reads instead of quitting with an error"/>
              </when>
              <when value="MappingQuality">
                  <param name="min_mapping_quality_score" type="integer" value="10" label="Minimum read mapping quality required to consider a read for calling"/>
              </when>
              <when value="MappingQualityUnavailable">
                  <!-- no extra options -->
              </when>
              <when value="MappingQualityZero">
                  <!-- no extra options -->
              </when>
              <when value="MateSameStrand">
                  <!-- no extra options -->
              </when>
              <when value="MaxInsertSize">
                  <param name="maxInsertSize" type="integer" value="1000000" label="Discard reads with insert size greater than the specified value"/>
              </when>
              <when value="MaxReadLength">
                  <param name="maxReadLength" type="integer" value="76" label="Max Read Length"/>
              </when>
              <when value="MissingReadGroup">
                  <!-- no extra options -->
              </when>
              <when value="NoOriginalQualityScores">
                  <!-- no extra options -->
              </when>
              <when value="NotPrimaryAlignment">
                  <!-- no extra options -->
              </when>
              <when value="Platform454">
                  <!-- no extra options -->
              </when>
              <when value="Platform">
                  <param name="PLFilterName" type="text" value="" label="Discard reads with RG:PL attribute containing this string"/>
              </when>
              <when value="PlatformUnit">
                  <!-- no extra options -->
              </when>
              <when value="ReadGroupBlackList">
                  <!-- no extra options -->
              </when>
              <when value="ReadName">
                  <param name="readName" type="text" value="" label="Filter out all reads except those with this read name"/>
              </when>
              <when value="ReadStrand">
                  <param name="filterPositive" type="boolean" truevalue="--filterPositive" falsevalue="" label="Discard reads on the forward strand"/>
              </when>
              <when value="ReassignMappingQuality">
                  <param name="default_mapping_quality" type="integer" value="60" label="Default read mapping quality to assign to all reads"/>
              </when>
              <when value="Sample">
                  <param name="sample_to_keep" type="text" value="" label="The name of the sample(s) to keep, filtering out all others"/>
              </when>
              <when value="SingleReadGroup">
                  <param name="read_group_to_keep" type="integer" value="76" label="The name of the read group to keep, filtering out all others"/>
              </when>
              <when value="UnmappedRead">
                  <!-- no extra options -->
              </when>
            </conditional>
        </repeat>
        <repeat name="input_interval_repeat" title="Operate on Genomic intervals" help="-L,--intervals &amp;lt;intervals&amp;gt;">
          <param name="input_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" />
        </repeat>
        <repeat name="input_exclude_interval_repeat" title="Exclude Genomic intervals" help="-XL,--excludeIntervals &amp;lt;excludeIntervals&amp;gt;">
          <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list,vcf" label="Genomic intervals" />
        </repeat>
        
        <param name="interval_set_rule" type="select" label="Interval set rule" help="-isr,--interval_set_rule &amp;lt;interval_set_rule&amp;gt;">
          <option value="UNION" selected="True">UNION</option>
          <option value="INTERSECTION">INTERSECTION</option>
        </param>
        
        <conditional name="downsampling_type">
          <param name="downsampling_type_selector" type="select" label="Type of reads downsampling to employ at a given locus" help="-dt,--downsampling_type &amp;lt;downsampling_type&amp;gt;">
            <option value="NONE" selected="True">NONE</option>
            <option value="ALL_READS">ALL_READS</option>
            <option value="BY_SAMPLE">BY_SAMPLE</option>
          </param>
          <when value="NONE">
              <!-- no more options here -->
          </when>
          <when value="ALL_READS">
              <conditional name="downsample_to_type">
                  <param name="downsample_to_type_selector" type="select" label="Downsample method">
                      <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option>
                      <option value="downsample_to_coverage">Downsample by Coverage</option>
                  </param>
                  <when value="downsample_to_fraction">
                      <param name="downsample_to_value" type="float" label="Fraction [0.0-1.0] of reads to downsample to" value="1" min="0" max="1" help="-dfrac,--downsample_to_fraction &amp;lt;downsample_to_fraction&amp;gt;"/>
                  </when>
                  <when value="downsample_to_coverage">
                      <param name="downsample_to_value" type="integer" label="Coverage to downsample to at any given locus" value="0" help="-dcov,--downsample_to_coverage &amp;lt;downsample_to_coverage&amp;gt;"/>
                  </when>
              </conditional>
          </when>
          <when value="BY_SAMPLE">
              <conditional name="downsample_to_type">
                  <param name="downsample_to_type_selector" type="select" label="Downsample method">
                      <option value="downsample_to_fraction" selected="True">Downsample by Fraction</option>
                      <option value="downsample_to_coverage">Downsample by Coverage</option>
                  </param>
                  <when value="downsample_to_fraction">
                      <param name="downsample_to_value" type="float" label="Fraction [0.0-1.0] of reads to downsample to" value="1" min="0" max="1" help="-dfrac,--downsample_to_fraction &amp;lt;downsample_to_fraction&amp;gt;"/>
                  </when>
                  <when value="downsample_to_coverage">
                      <param name="downsample_to_value" type="integer" label="Coverage to downsample to at any given locus" value="0" help="-dcov,--downsample_to_coverage &amp;lt;downsample_to_coverage&amp;gt;"/>
                  </when>
              </conditional>
          </when>
        </conditional>
        <param name="baq" type="select" label="Type of BAQ calculation to apply in the engine" help="-baq,--baq &amp;lt;baq&amp;gt;">
          <option value="OFF" selected="True">OFF</option>
          <option value="CALCULATE_AS_NECESSARY">CALCULATE_AS_NECESSARY</option>
          <option value="RECALCULATE">RECALCULATE</option>
        </param>
        <param name="baq_gap_open_penalty" type="float" label="BAQ gap open penalty (Phred Scaled)" value="40" help="Default value is 40. 30 is perhaps better for whole genome call sets. -baqGOP,--baqGapOpenPenalty &amp;lt;baqGapOpenPenalty&amp;gt;" />
        <param name="use_original_qualities" type="boolean" truevalue="--useOriginalQualities" falsevalue="" label="Use the original base quality scores from the OQ tag" help="-OQ,--useOriginalQualities" />
        <param name="default_base_qualities" type="integer" label="Value to be used for all base quality scores, when some are missing" value="-1" help="-DBQ,--defaultBaseQualities &amp;lt;defaultBaseQualities&amp;gt;"/>
        <param name="validation_strictness" type="select" label="How strict should we be with validation" help="-S,--validation_strictness &amp;lt;validation_strictness&amp;gt;">
          <option value="STRICT" selected="True">STRICT</option>
          <option value="LENIENT">LENIENT</option>
          <option value="SILENT">SILENT</option>
          <!-- <option value="DEFAULT_STRINGENCY">DEFAULT_STRINGENCY</option> listed in docs, but not valid value...-->
        </param>
        <param name="interval_merging" type="select" label="Interval merging rule" help="-im,--interval_merging &amp;lt;interval_merging&amp;gt;">
          <option value="ALL" selected="True">ALL</option>
          <option value="OVERLAPPING_ONLY">OVERLAPPING_ONLY</option>
        </param>
        
        <repeat name="read_group_black_list_repeat" title="Read group black list" help="-rgbl,--read_group_black_list &amp;lt;read_group_black_list&amp;gt;">
          <conditional name="read_group_black_list_type">
            <param name="read_group_black_list_type_selector" type="select" label="Type of reads read group black list">
              <option value="file" selected="True">Filters in file</option>
              <option value="text">Specify filters as a string</option>
            </param>
            <when value="file">
              <param name="read_group_black_list" type="data" format="txt" label="Read group black list file" />
            </when>
            <when value="text">
              <param name="read_group_black_list" type="text" value="tag:string" label="Read group black list tag:string" />
            </when>
          </conditional>
        </repeat>
        
        <param name="disable_experimental_low_memory_sharding" type="boolean" truevalue="--disable_experimental_low_memory_sharding" falsevalue="" label="Disable experimental low-memory sharding functionality." checked="False" help="--disable_experimental_low_memory_sharding"/>
        <param name="non_deterministic_random_seed" type="boolean" truevalue="--nonDeterministicRandomSeed" falsevalue="" label="Makes the GATK behave non deterministically, that is, the random numbers generated will be different in every run" checked="False"  help="-ndrs,--nonDeterministicRandomSeed"/>
        <param name="fix_misencoded_quality_scores" type="boolean" truevalue="--fix_misencoded_quality_scores" falsevalue="" label="Fix mis-encoded base quality scores. Q0 == ASCII 33 according to the SAM specification, whereas Illumina encoding starts at Q64. The idea here is simple: we just iterate over all reads and subtract 31 from every quality score." checked="False"  help="-fixMisencodedQuals / --fix_misencoded_quality_scores"/>
        
      </when>
    </conditional>
    
    
    <conditional name="analysis_param_type">
      <param name="analysis_param_type_selector" type="select" label="Basic or Advanced Analysis options">
        <option value="basic" selected="True">Basic</option>
        <option value="advanced">Advanced</option>
      </param>
      <when value="basic">
        <!-- Do nothing here -->
      </when>
      <when value="advanced">
        <repeat name="stratifications" title="Stratification">
          <param name="select_exps" value="" type="text" label="Stratification Expression" help="-select,--select_exps &amp;lt;select_exps&amp;gt;">
            <sanitizer>
              <valid initial="string.printable">
               <remove value="&apos;"/>
             </valid>
              <mapping initial="none"/>
            </sanitizer>
          </param>
          <param name="select_name" value="" type="text" label="Name" help="-selectName,--select_names &amp;lt;select_names&amp;gt;"/>
        </repeat>
        
        <repeat name="samples" title="Sample" help="-sn,--sample &amp;lt;sample&amp;gt;">
          <param name="sample" value="" type="text" label="Derive eval and comp contexts using only these sample genotypes, when genotypes are available in the original context"/>
        </repeat>
        
        <param name="stratification_modules" type="select" multiple="True" display="checkboxes" label="Stratification modules to apply to the eval track(s)" help="-ST,--stratificationModule &amp;lt;stratificationModule&amp;gt;" >
          <!-- do these need individual options also? gatk wiki has little info -->
          <option value="AlleleFrequency" />
          <option value="AlleleCount" />
          <option value="CompRod" />
          <option value="Contig" />
          <option value="CpG" />
          <option value="Degeneracy" />
          <option value="EvalRod" />
          <option value="Filter" />
          <option value="FunctionalClass" />
          <option value="JexlExpression" />
          <option value="Sample" />
          <option value="IntervalStratification" />
        </param>
        <param name="do_not_use_all_standard_stratifications" checked="false" type="boolean" truevalue="--doNotUseAllStandardStratifications" falsevalue="" label="Do not use the standard stratification modules by default" help="-noST,--doNotUseAllStandardStratifications" />
        
        <repeat name="only_variants_of_type" title="only Variants Of Type" help="--onlyVariantsOfType">
          <param name="variant_type" type="text" value="" label="only variants of these types will be considered during the evaluation"/>
        </repeat>
        
        <param name="eval_modules" type="select" multiple="True" display="checkboxes" label="Eval modules to apply to the eval track(s)" help="-EV,--evalModule &amp;lt;evalModule&amp;gt;" >
          <!-- do these need individual options also? gatk wiki has little info -->
          <option value="ACTransitionTable" />
          <option value="AlleleFrequencyComparison" />
          <option value="AminoAcidTransition" />
          <option value="CompOverlap" />
          <option value="CountVariants" />
          <option value="GenotypeConcordance" />
          <option value="GenotypePhasingEvaluator" />
          <option value="IndelMetricsByAC" />
          <option value="IndelStatistics" />
          <option value="MendelianViolationEvaluator" />
          <option value="PrintMissingComp" />
          <option value="PrivatePermutations" />
          <option value="SimpleMetricsByAC" />
          <option value="ThetaVariantEvaluator" />
          <option value="TiTvVariantEvaluator" />
          <option value="VariantQualityScore" />
        </param>
        <param name="do_not_use_all_standard_modules" checked="false" type="boolean" truevalue="--doNotUseAllStandardModules" falsevalue="" label="Do not use the standard eval modules by default" help="-noEV,--doNotUseAllStandardModules" />
        
        <param name="num_samples" type="integer" label="Number of samples (used if no samples are available in the VCF file" value="0" help="-ns,--numSamples &amp;lt;numSamples&amp;gt;"/>
        <param name="min_phase_quality" type="float" label="Minimum phasing quality " value="10.0" help="-mpq,--minPhaseQuality &amp;lt;minPhaseQuality&amp;gt;"/>
        <param name="family" type="text" value="" label="If provided, genotypes in will be examined for mendelian violations: this argument is a string formatted as dad+mom=child where these parameters determine which sample names are examined" help="--family_structure"/>
        <param name="mendelian_violation_qual_threshold" type="integer" label="Minimum genotype QUAL score for each trio member required to accept a site as a violation" value="50" help="-mvq,--mendelianViolationQualThreshold &amp;lt;mendelianViolationQualThreshold&amp;gt;"/>
        <param name="ancestral_alignments" type="data" format="fasta" optional="True" label="Fasta file with ancestral alleles" help="-aa,--ancestralAlignments &amp;lt;ancestralAlignments&amp;gt;" />
        <param name="known_cnvs" type="data" format="bed,gatk_interval,picard_interval_list" optional="True" label="File containing tribble-readable features describing a known list of copy number variants" help="-knownCNVs,--knownCNVs &amp;lt;knownCNVs&amp;gt;" />
        <param name="strat_intervals" type="data" format="bed,gatk_interval,picard_interval_list" optional="True" label="File containing tribble-readable features for the IntervalStratificiation" help="-stratIntervals,--stratIntervals &amp;lt;stratIntervals&amp;gt;" />
        
      </when>
    </conditional>
    
    
  </inputs>
  <outputs>
    <data format="gatk_report" name="output_report" label="${tool.name} on ${on_string} (report)" />
    <data format="txt" name="output_log" label="${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="dbsnp_rod_bind_type_selector" value="set_dbsnp" />
          <param name="dbsnp_input_rod" value="gatk/fake_phiX_variant_locations.vcf" ftype="vcf" />
          <param name="dbsnp_known_names" value="True"/>
          <param name="comp_rod_bind" value="0" />
          <param name="gatk_param_type_selector" value="basic" />
          <param name="analysis_param_type_selector" value="basic" />
          <output name="output_report" file="gatk/gatk_variant_eval/gatk_variant_eval_out_1.gatk_report" />
          <output name="output_log" file="gatk/gatk_variant_eval/gatk_variant_eval_out_1.log.contains" compare="contains" />
      </test>
  </tests>
  <help>
**What it does**

General-purpose tool for variant evaluation (% in dbSNP, genotype concordance, Ti/Tv ratios, and a lot more)

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

If you encounter errors, please view the `GATK FAQ &lt;http://www.broadinstitute.org/gatk/guide/topic?name=faqs&gt;`_.

------

**Inputs**

GenomeAnalysisTK: VariantEval accepts variant files as input.


**Outputs**

The output is a table of variant evaluation.


Go `here &lt;http://www.broadinstitute.org/gatk/guide/topic?name=intro&gt;`_ for details on GATK file formats.

-------

**Settings**::

 out                                   An output file presented to the walker. Will overwrite contents if file exists.
 list                                  List the available eval modules and exit
 select_exps                           One or more stratifications to use when evaluating the data
 select_names                          Names to use for the list of stratifications (must be a 1-to-1 mapping)
 sample                                Derive eval and comp contexts using only these sample genotypes, when genotypes are available in the original context
 known_names                           Name of ROD bindings containing variant sites that should be treated as known when splitting eval rods into known and novel subsets
 stratificationModule                  One or more specific stratification modules to apply to the eval track(s) (in addition to the standard stratifications, unless -noS is specified)
 doNotUseAllStandardStratifications    Do not use the standard stratification modules by default (instead, only those that are specified with the -S option)
 onlyVariantsOfType                    If provided, only variants of these types will be considered during the evaluation, in 
 evalModule                            One or more specific eval modules to apply to the eval track(s) (in addition to the standard modules, unless -noE is specified)
 doNotUseAllStandardModules            Do not use the standard modules by default (instead, only those that are specified with the -E option)
 numSamples                            Number of samples (used if no samples are available in the VCF file
 minPhaseQuality                       Minimum phasing quality
 family_structure                      If provided, genotypes in will be examined for mendelian violations: this argument is a string formatted as dad+mom=child where these parameters determine which sample names are examined
 mendelianViolationQualThreshold       Minimum genotype QUAL score for each trio member required to accept a site as a violation
 ancestralAlignments                   Fasta file with ancestral alleles

------

**Citation**

For the underlying tool, please cite `DePristo MA, Banks E, Poplin R, Garimella KV, Maguire JR, Hartl C, Philippakis AA, del Angel G, Rivas MA, Hanna M, McKenna A, Fennell TJ, Kernytsky AM, Sivachenko AY, Cibulskis K, Gabriel SB, Altshuler D, Daly MJ. A framework for variation discovery and genotyping using next-generation DNA sequencing data. Nat Genet. 2011 May;43(5):491-8. &lt;http://www.ncbi.nlm.nih.gov/pubmed/21478889&gt;`_

Please also site `McKenna A, Hanna M, Banks E, Sivachenko A, Cibulskis K, Kernytsky A, Garimella K, Altshuler D, Gabriel S, Daly M, DePristo MA (2010). The Genome Analysis Toolkit: a MapReduce framework for analyzing next-generation DNA sequencing data. Genome Res. 20:1297-303. Epub 2010 Jul 19. &lt;http://www.ncbi.nlm.nih.gov/pubmed/20644199&gt;`_

If you use this tool in Galaxy, please cite `Blankenberg D, Von Kuster G, Coraor N, Ananda G, Lazarus R, Mangan M, Nekrutenko A, Taylor J. Galaxy: a web-based genome analysis tool for experimentalists. Curr Protoc Mol Biol. 2010 Jan;Chapter 19:Unit 19.10.1-21. &lt;http://www.ncbi.nlm.nih.gov/pubmed/20069535&gt;`_

  </help>
</tool>