view unified_genotyper.xml @ 4:f244b8209eb8 draft

bug fix release
author iuc
date Mon, 25 Aug 2014 17:43:11 -0400
parents 2553f84b8174
children 35c00763cb5c
line wrap: on
line source

<tool id="gatk2_unified_genotyper" name="Unified Genotyper" version="@VERSION@.0">
  <description>SNP and indel caller</description>
  <expand macro="requirements" />
  <macros>
    <import>gatk2_macros.xml</import>
  </macros>
  <command interpreter="python">
    gatk2_wrapper.py
    --stdout "${output_log}"
    #for $i, $input_bam in enumerate( $reference_source.input_bams ):
        -d "-I" "${input_bam.input_bam}" "${input_bam.input_bam.ext}" "gatk_input_${i}"
        #if str( $input_bam.input_bam.metadata.bam_index ) != "None":
            -d "" "${input_bam.input_bam.metadata.bam_index}" "bam_index" "gatk_input_${i}" ##hardcode galaxy ext type as bam_index
        #end if
    #end for
    -p '
    @JAR_PATH@
    -T "UnifiedGenotyper"
    @THREADS@
    --out "${output_vcf}"
    --metrics_file "${output_metrics}"
    \$GATK2_SITE_OPTIONS

    ## according to http://www.broadinstitute.org/gatk/guide/article?id=1975
    --num_cpu_threads_per_data_thread 1

    #if $reference_source.reference_source_selector != "history":
        -R "${reference_source.ref_file.fields.path}"
    #end if
    --genotype_likelihoods_model "${genotype_likelihoods_model}"
    --standard_min_confidence_threshold_for_calling "${standard_min_confidence_threshold_for_calling}"
    --standard_min_confidence_threshold_for_emitting "${standard_min_confidence_threshold_for_emitting}"
   '
    @DBSNP_OPTIONS@

    #include source=$standard_gatk_options#
    ##start analysis specific options
    #if $analysis_param_type.analysis_param_type_selector == "advanced":
        -p '
        --heterozygosity "${analysis_param_type.heterozygosity}"
        --pcr_error_rate "${analysis_param_type.pcr_error_rate}"
        --genotyping_mode "${analysis_param_type.genotyping_mode_type.genotyping_mode}"
        #if str( $analysis_param_type.genotyping_mode_type.genotyping_mode ) == 'GENOTYPE_GIVEN_ALLELES':
            --alleles "${analysis_param_type.genotyping_mode_type.input_alleles_rod}"
        #end if
        --output_mode "${analysis_param_type.output_mode}"
        ${analysis_param_type.compute_SLOD}
        --min_base_quality_score "${analysis_param_type.min_base_quality_score}"
        --max_deletion_fraction "${analysis_param_type.max_deletion_fraction}"
        --max_alternate_alleles "${analysis_param_type.max_alternate_alleles}"
        --min_indel_count_for_genotyping "${analysis_param_type.min_indel_count_for_genotyping}"
        --indel_heterozygosity "${analysis_param_type.indel_heterozygosity}"
        --indelGapContinuationPenalty "${analysis_param_type.indelGapContinuationPenalty}"
        --indelGapOpenPenalty "${analysis_param_type.indelGapOpenPenalty}"
        --indelHaplotypeSize "${analysis_param_type.indelHaplotypeSize}"
        ${analysis_param_type.doContextDependentGapPenalties}
        #if str( $analysis_param_type.annotation ) != "None":
            #for $annotation in str( $analysis_param_type.annotation.fields.gatk_value ).split( ','):
                --annotation "${annotation}"
            #end for
        #end if
        #for $additional_annotation in $analysis_param_type.additional_annotations:
            --annotation "${additional_annotation.additional_annotation_name}"
        #end for
        #if str( $analysis_param_type.group ) != "None":
            #for $group in str( $analysis_param_type.group ).split( ','):
                --group "${group}"
            #end for
        #end if
        #if str( $analysis_param_type.exclude_annotations ) != "None":
            #for $annotation in str( $analysis_param_type.exclude_annotations.fields.gatk_value ).split( ','):
                --excludeAnnotation "${annotation}"
            #end for
        #end if
        #if str( $analysis_param_type.sample_ploidy ) != '':
          --sample_ploidy "$analysis_param_type.sample_ploidy"
        #end if
        '
##        #if str( $analysis_param_type.snpEff_rod_bind_type.snpEff_rod_bind_type_selector ) == 'set_snpEff':
##            -p '--annotation "SnpEff"'
##            -d "--snpEffFile:${analysis_param_type.snpEff_rod_bind_type.snpEff_rod_name},%(file_type)s" "${analysis_param_type.snpEff_rod_bind_type.snpEff_input_rod}" "${analysis_param_type.snpEff_rod_bind_type.snpEff_input_rod.ext}" "input_snpEff_${analysis_param_type.snpEff_rod_bind_type.snpEff_rod_name}"
##        #else:
##            -p '--excludeAnnotation "SnpEff"'
##        #end if
    #end if
  </command>
  <inputs>
    <conditional name="reference_source">
      <expand macro="reference_source_selector_param" />
      <when value="cached">
        <repeat name="input_bams" title="BAM file" min="1" help="-I,--input_file &amp;lt;input_file&amp;gt;">
            <param name="input_bam" type="data" format="bam" label="BAM file">
              <validator type="unspecified_build" />
              <validator type="dataset_metadata_in_data_table" table_name="gatk2_picard_indexes" metadata_name="dbkey" metadata_column="dbkey" message="Sequences are not currently available for the specified build." /> <!-- fixme!!! this needs to be a select -->
            </param>
        </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_bam" column="dbkey"/> does not yet work in a repeat...--> 
          </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="input_bams" title="BAM file" min="1" help="-I,--input_file &amp;lt;input_file&amp;gt;">
            <param name="input_bam" type="data" format="bam" label="BAM file" >
            </param>
        </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>
    <expand macro="dbsnp_param" />
    
    <param name="genotype_likelihoods_model" type="select" label="Genotype likelihoods calculation model to employ" help="-glm,--genotype_likelihoods_model &amp;lt;genotype_likelihoods_model&amp;gt;">
      <option value="BOTH" selected="True">BOTH</option>
      <option value="SNP">SNP</option>
      <option value="INDEL">INDEL</option>
    </param>
    
    <param name="standard_min_confidence_threshold_for_calling" type="float" value="30.0" label="The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be called" help="-stand_call_conf,--standard_min_confidence_threshold_for_calling &amp;lt;standard_min_confidence_threshold_for_calling&amp;gt;" />
    <param name="standard_min_confidence_threshold_for_emitting" type="float" value="30.0" label="The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be emitted (and filtered if less than the calling threshold)" help="-stand_emit_conf,--standard_min_confidence_threshold_for_emitting &amp;lt;standard_min_confidence_threshold_for_emitting&amp;gt;" />

    
    <expand macro="gatk_param_type_conditional" />
    
    <expand macro="analysis_type_conditional">
        <param name="heterozygosity" type="float" value="1e-3" label="Heterozygosity value used to compute prior likelihoods for any locus" help="-hets,--heterozygosity &amp;lt;heterozygosity&amp;gt;" />
        <param name="pcr_error_rate" type="float" value="1e-4" label="The PCR error rate to be used for computing fragment-based likelihoods" help="-pcr_error,--pcr_error_rate &amp;lt;pcr_error_rate&amp;gt;" />
        <conditional name="genotyping_mode_type">
          <param name="genotyping_mode" type="select" label="How to determine the alternate allele to use for genotyping" help="-gt_mode,--genotyping_mode &amp;lt;genotyping_mode&amp;gt;">
            <option value="DISCOVERY" selected="True">DISCOVERY</option>
            <option value="GENOTYPE_GIVEN_ALLELES">GENOTYPE_GIVEN_ALLELES</option>
          </param>
          <when value="DISCOVERY">
            <!-- Do nothing here -->
          </when>
          <when value="GENOTYPE_GIVEN_ALLELES">
            <param name="input_alleles_rod" type="data" format="vcf" label="Alleles ROD file" help="-alleles,--alleles &amp;lt;alleles&amp;gt;" />
          </when>
        </conditional>
        <param name="output_mode" type="select" label="Should we output confident genotypes (i.e. including ref calls) or just the variants?" help="-out_mode,--output_mode &amp;lt;output_mode&amp;gt;">
          <option value="EMIT_VARIANTS_ONLY" selected="True">EMIT_VARIANTS_ONLY</option>
          <option value="EMIT_ALL_CONFIDENT_SITES">EMIT_ALL_CONFIDENT_SITES</option>
          <option value="EMIT_ALL_SITES">EMIT_ALL_SITES</option>
        </param>
        <param name="compute_SLOD" type="boolean" truevalue="--computeSLOD" falsevalue="" label="Compute the SLOD" help="--computeSLOD" />
        <param name="min_base_quality_score" type="integer" value="17" label="Minimum base quality required to consider a base for calling" help="-mbq,--min_base_quality_score &amp;lt;min_base_quality_score&amp;gt;" />
        <param name="max_deletion_fraction" type="float" value="0.05" label="Maximum fraction of reads with deletions spanning this locus for it to be callable" help="to disable, set to &lt; 0 or &gt; 1 (-deletions,--max_deletion_fraction &amp;lt;max_deletion_fraction&amp;gt;)" />
        <param name="max_alternate_alleles" type="integer" value="6" label="Maximum number of alternate alleles to genotype" help="-maxAlleles,--max_alternate_alleles &amp;lt;max_alternate_alleles&amp;gt;" />
        <param name="min_indel_count_for_genotyping" type="integer" value="5" label="Minimum number of consensus indels required to trigger genotyping run" help="-minIndelCnt,--min_indel_count_for_genotyping &amp;lt;min_indel_count_for_genotyping&amp;gt;" />
        <param name="indel_heterozygosity" type="float" value="0.000125" label="Heterozygosity for indel calling" help="1.0/8000==0.000125 (-indelHeterozygosity,--indel_heterozygosity &amp;lt;indel_heterozygosity&amp;gt;)"/>
        <param name="indelGapContinuationPenalty" type="integer" value="10" label="Indel gap continuation penalty" help="As Phred-scaled probability, i.e. 30 => 10^-30/10 (--indelGapContinuationPenalty)">
          <validator type="in_range" message="value between 0 and 255" min="0" max="255" />
        </param>
        <param name="indelGapOpenPenalty" type="integer" value="45" label="Indel gap open penalty" help="As Phred-scaled probability, i.e. 30 => 10^-30/10 (--indelGapOpenPenalty)">
          <validator type="in_range" message="value between 0 and 255" min="0" max="255" />
        </param>
        <!-- indelHaplotypeSize - Gone in GATK 2.4? -->
        <param name="indelHaplotypeSize" type="integer" value="80" label="Indel haplotype size" help="--indelHaplotypeSize" />
        <param name="doContextDependentGapPenalties" type="boolean" truevalue="--doContextDependentGapPenalties" falsevalue="" label="Vary gap penalties by context" help="--doContextDependentGapPenalties" />
        <param name="annotation" type="select" multiple="True" display="checkboxes" label="Annotation Types" help="-A,--annotation &amp;lt;annotation&amp;gt;">
          <!-- load the available annotations from an external configuration file, since additional ones can be added to local installs -->
          <options from_data_table="gatk2_annotations">
            <filter type="multiple_splitter" column="tools_valid_for" separator=","/>
            <filter type="static_value" value="UnifiedGenotyper" column="tools_valid_for"/>
          </options>
        </param>
        <repeat name="additional_annotations" title="Additional annotation" help="-A,--annotation &amp;lt;annotation&amp;gt;">
          <param name="additional_annotation_name" type="text" value="" label="Annotation name" />
        </repeat>
<!--
        <conditional name="snpEff_rod_bind_type">
          <param name="snpEff_rod_bind_type_selector" type="select" label="Provide a snpEff reference-ordered data file">
            <option value="set_snpEff">Set snpEff</option>
            <option value="exclude_snpEff" selected="True">Don't set snpEff</option>
          </param>
          <when value="exclude_snpEff">
          </when>
          <when value="set_snpEff">
            <param name="snpEff_input_rod" type="data" format="vcf" label="ROD file" />
            <param name="snpEff_rod_name" type="hidden" value="snpEff" label="ROD Name"/>
          </when>
        </conditional>
-->
        <param name="group" type="select" multiple="True" display="checkboxes" label="Annotation Interfaces/Groups" help="-G,--group &amp;lt;group&amp;gt;">
            <option value="RodRequiringAnnotation">RodRequiringAnnotation</option>
            <option value="Standard">Standard</option>
            <option value="Experimental">Experimental</option>
            <option value="WorkInProgress">WorkInProgress</option>
            <option value="RankSumTest">RankSumTest</option>
            <!-- <option value="none">none</option> -->
        </param>
    <!--     <param name="family_string" type="text" value="" label="Family String"/> -->
        <param name="exclude_annotations" type="select" multiple="True" display="checkboxes" label="Annotations to exclude" help="-XA,--excludeAnnotation &amp;lt;excludeAnnotation&amp;gt;" >
          <!-- load the available annotations from an external configuration file, since additional ones can be added to local installs -->
          <options from_data_table="gatk2_annotations">
            <filter type="multiple_splitter" column="tools_valid_for" separator=","/>
            <filter type="static_value" value="UnifiedGenotyper" column="tools_valid_for"/>
          </options>
        </param>
        <param name="sample_ploidy" type="integer" value="2" label="Ploidy (number of chromosomes) per sample. For pooled data, set to (Number of samples in each pool * Sample Ploidy)" help="-ploidy,--sample_ploidy" />
    </expand>
  </inputs>
  <outputs>
    <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (VCF)" />
    <data format="txt" name="output_metrics" label="${tool.name} on ${on_string} (metrics)" />
    <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
  </outputs>
  <trackster_conf/>
  <tests>
      <test>
          <param name="reference_source_selector" value="history" />
          <param name="ref_file" value="phiX.fasta" ftype="fasta" />
          <param name="input_bam" value="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" />
          <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_rod_name" value="dbsnp" />
          <param name="standard_min_confidence_threshold_for_calling" value="0" />
          <param name="standard_min_confidence_threshold_for_emitting" value="4" />
          <param name="gatk_param_type_selector" value="basic" />
          <param name="analysis_param_type_selector" value="advanced" />
          <param name="genotype_likelihoods_model" value="BOTH" />
          <param name="heterozygosity" value="0.001" />
          <param name="pcr_error_rate" value="0.0001" />
          <param name="genotyping_mode" value="DISCOVERY" />
          <param name="output_mode" value="EMIT_ALL_CONFIDENT_SITES" />
          <param name="compute_SLOD" />
          <param name="min_base_quality_score" value="17" />
          <param name="max_deletion_fraction" value="-1" />
          <param name="min_indel_count_for_genotyping" value="2" />
          <param name="indel_heterozygosity" value="0.000125" />
          <param name="indelGapContinuationPenalty" value="10" />
          <param name="indelGapOpenPenalty" value="3" />
          <param name="indelHaplotypeSize" value="80" />
          <param name="doContextDependentGapPenalties" />
          <!-- <param name="annotation" value="" />
          <param name="group" value="" /> -->
          <output name="output_vcf" file="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.vcf" lines_diff="4" /> 
          <output name="output_metrics" file="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.metrics" /> 
          <output name="output_log" file="gatk/gatk_unified_genotyper/gatk_unified_genotyper_out_1.log.contains" compare="contains" />
      </test>
  </tests>
  <help>
**What it does**

A variant caller which unifies the approaches of several disparate callers.  Works for single-sample and multi-sample data.  The user can choose from several different incorporated calculation models.

For more information on the GATK Unified Genotyper, see this `tool specific page &lt;http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_genotyper_UnifiedGenotyper.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: UnifiedGenotyper accepts an aligned BAM input file.


**Outputs**

The output is in VCF format.


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

-------

**Settings**::

 genotype_likelihoods_model                        Genotype likelihoods calculation model to employ -- BOTH is the default option, while INDEL is also available for calling indels and SNP is available for calling SNPs only (SNP|INDEL|BOTH)
 heterozygosity                                    Heterozygosity value used to compute prior likelihoods for any locus
 pcr_error_rate                                    The PCR error rate to be used for computing fragment-based likelihoods
 genotyping_mode                                   Should we output confident genotypes (i.e. including ref calls) or just the variants? (DISCOVERY|GENOTYPE_GIVEN_ALLELES)
 output_mode                                       Should we output confident genotypes (i.e. including ref calls) or just the variants? (EMIT_VARIANTS_ONLY|EMIT_ALL_CONFIDENT_SITES|EMIT_ALL_SITES)
 standard_min_confidence_threshold_for_calling     The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be called
 standard_min_confidence_threshold_for_emitting    The minimum phred-scaled confidence threshold at which variants not at 'trigger' track sites should be emitted (and filtered if less than the calling threshold)
 noSLOD                                            If provided, we will not calculate the SLOD
 min_base_quality_score                            Minimum base quality required to consider a base for calling
 max_deletion_fraction                             Maximum fraction of reads with deletions spanning this locus for it to be callable [to disable, set to &lt; 0 or &gt; 1; default:0.05]
 min_indel_count_for_genotyping                    Minimum number of consensus indels required to trigger genotyping run
 indel_heterozygosity                              Heterozygosity for indel calling
 indelGapContinuationPenalty                       Indel gap continuation penalty
 indelGapOpenPenalty                               Indel gap open penalty
 indelHaplotypeSize                                Indel haplotype size
 doContextDependentGapPenalties                    Vary gap penalties by context
 indel_recal_file                                  Filename for the input covariates table recalibration .csv file - EXPERIMENTAL, DO NO USE
 indelDebug                                        Output indel debug info
 out                                               File to which variants should be written
 annotation                                        One or more specific annotations to apply to variant calls
 group                                             One or more classes/groups of annotations to apply to variant calls

@CITATION_SECTION@
  </help>
  <expand macro="citations" />
</tool>