view haplotype_caller.xml @ 1:f760c0de8e3a draft

Uploaded
author bgruening
date Mon, 02 Dec 2013 10:36:02 -0500
parents 340633249b3d
children 8bcc13094767
line wrap: on
line source

<tool id="gatk2_haplotype_caller" name="Haplotype Caller" version="0.0.7">
  <description>Call SNPs and indels simultaneously via local de-novo assembly of haplotypes in an active region</description>
  <expand macro="requirements" />
  <macros>
    <import>gatk2_macros.xml</import>
  </macros>
  <command interpreter="python">
    gatk2_wrapper.py
    --stdout "${output_log}"
    -d "-I" "${reference_source.input_bam}" "${reference_source.input_bam.ext}" "gatk_input"
    #if str( $reference_source.input_bam.metadata.bam_index ) != "None":
        -d "" "${reference_source.input_bam.metadata.bam_index}" "bam_index" "gatk_input" ##hardcode galaxy ext type as bam_index
    #end if
    -p '
    @JAR_PATH@
    -T "HaplotypeCaller"
    -o "${output_vcf}"

    \$GATK2_SITE_OPTIONS

    @THREADS@

    #if $reference_source.reference_source_selector != "history":
        -R "${reference_source.ref_file.fields.path}"
    #end if
    #if str($input_recal) != 'None':
        --BQSR "${input_recal}"
    #end if
   '
    #include source=$standard_gatk_options#
    
    ##start analysis specific options
    #if $analysis_param_type.analysis_param_type_selector == "advanced":
        -p '
        #if $analysis_param_type.p_nonref_model.__str__ != "None" and len($analysis_param_type.p_nonref_model.__str__) > 0:
          --p_nonref_model $analysis_param_type.p_nonref_model
        #end if
        #if $analysis_param_type.heterozygosity.__str__.strip() != '':
            --heterozygosity $analysis_param_type.heterozygosity
        #end if
        --genotyping_mode "${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
        #if $analysis_param_type.output_mode.__str__ != "None" and len($analysis_param_type.output_mode.__str__) > 0:
          --output_mode $analysis_param_type.output_mode
        #end if

        ## files
        #if str($analysis_param_type.activeRegionIn) != 'None':
            --activeRegionIn "$analysis_param_type.activeRegionIn"
        #end if
        #if str($analysis_param_type.comp) != 'None':
            --comp "$analysis_param_type.comp"
        #end if
        #if str($analysis_param_type.dbsnp) != 'None':
            --dbsnp "$analysis_param_type.dbsnp"
        #end if
        ##  
        #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

        ## value setings
        #if $analysis_param_type.contamination_fraction_to_filter.__str__.strip() != '':
            --contamination_fraction_to_filter $analysis_param_type.contamination_fraction_to_filter
        #end if
        #if $analysis_param_type.downsampleRegion.__str__.strip() != '':
            --downsampleRegion $analysis_param_type.downsampleRegion
        #end if
        #if $analysis_param_type.minPruning.__str__.strip() != '':
            --minPruning $analysis_param_type.minPruning
        #end if
        #if $analysis_param_type.standard_min_confidence_threshold_for_calling.__str__.strip() != '':
            --standard_min_confidence_threshold_for_calling $analysis_param_type.standard_min_confidence_threshold_for_calling
        #end if
        #if $analysis_param_type.standard_min_confidence_threshold_for_emitting.__str__.strip() != '':
            --standard_min_confidence_threshold_for_emitting $analysis_param_type.standard_min_confidence_threshold_for_emitting
        #end if
        #if $analysis_param_type.gcpHMM.__str__.strip() != '':
            --gcpHMM $analysis_param_type.gcpHMM
        #end if
        #if $analysis_param_type.max_alternate_alleles.__str__.strip() != '':
            --max_alternate_alleles $analysis_param_type.max_alternate_alleles
        #end if
        ## mode selections
        #if $analysis_param_type.genotyping_mode.__str__ != "None" and len($analysis_param_type.genotyping_mode.__str__) > 0:
          --genotyping_mode $analysis_param_type.genotyping_mode
        #end if
        #if $analysis_param_type.pair_hmm_implementation.__str__ != "None" and len($analysis_param_type.pair_hmm_implementation.__str__) > 0:
          --pair_hmm_implementation $analysis_param_type.pair_hmm_implementation
        #end if
        ## optional outputs
        #if $analysis_param_type.activeRegionOut:
            --activeRegionOut $active_region_out
        #end if
        #if $analysis_param_type.graphOutput:
            --graphOutput $graph_out
        #end if
        ## flags
        $analysis_param_type.useAllelesTrigger
        $analysis_param_type.fullHaplotype
        $analysis_param_type.genotypeFullActiveRegion
        $analysis_param_type.debug
        '
    #end if
  </command>
  <inputs>
    <param name="input_recal" type="data" format="gatk_report" optional="true" label="Covariates table recalibration file" help="-BQSR,--BQSR &amp;lt;recal_file&amp;gt;" >
      <help>The input covariates table file which enables on-the-fly base quality score recalibration. 
            Enables on-the-fly recalibrate of base qualities. The covariates tables are produced by the BaseQualityScoreRecalibrator tool. 
            Please be aware that one should only run recalibration with the covariates file created on the same input bam(s).
      </help>
    </param>
    <conditional name="reference_source">
      <expand macro="reference_source_selector_param" />
      <when value="cached">
        <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &amp;lt;input_file&amp;gt;">
          <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>
        <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"/>
          </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">
        <param name="input_bam" type="data" format="bam" label="BAM file" help="-I,--input_file &amp;lt;input_file&amp;gt;" />
        <param name="ref_file" type="data" format="fasta" label="Using reference file" help="-R,--reference_sequence &amp;lt;reference_sequence&amp;gt;">
          <options>
            <filter type="data_meta" key="dbkey" ref="input_bam" />
          </options>
        </param>
      </when>
    </conditional>
    
    <expand macro="gatk_param_type_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">

        <param name="activeRegionIn" type="data" format="bed,gatk_interval,picard_interval_list,vcf" optional="true" label="activeRegionIn" help="--activeRegionIn / -AR  Use this interval list file as the active regions to process"/>
        <param name="activeRegionOut" type="boolean" checked="False" truevalue="" falsevalue="" label="activeRegionOut" help="--activeRegionOut / -ARO  Output the active region to an interval list file"/>

        <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="comp" type="data" format="vcf" optional="true" label="comp" help="--comp / -comp  comparison VCF file"/>
        <param name="contamination_fraction_to_filter" type="float" value="0.05" optional="true" label="contamination_fraction_to_filter" help="--contamination_fraction_to_filter / -contamination  Fraction of contamination in sequencing data (for all samples) to aggressively remove">
            <validator type="in_range" message="value between 0.00 and 1.00" min="0" max="1"/>
        </param>
        <param name="dbsnp" type="data" format="vcf" optional="true" label="dbsnp" help="--dbsnp / -D  dbSNP file"/>
        <param name="debug" type="boolean" checked="False" truevalue="-debug" falsevalue="" label="debug" help="--debug / -debug  If specified, print out very verbose debug information about each triggering active region"/>
        <param name="downsampleRegion" type="integer" value="1000" optional="true" label="downsampleRegion" help="--downsampleRegion / -dr  coverage, per-sample, to downsample each active region to"/>

        <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="graphOutput" type="boolean" checked="False" truevalue="" falsevalue="" label="graphOutput" help="--graphOutput / -graph  File to which debug assembly graph information should be written"/>
        <param name="heterozygosity" type="float" value="0.0010" optional="true" label="heterozygosity" help="--heterozygosity / -hets  Heterozygosity value used to compute prior likelihoods for any locus"/>
        <param name="minPruning" type="integer" value="1" optional="true" label="minPruning" help="--minPruning / -minPruning  The minimum allowed pruning factor in assembly graph. Paths with &gt;= X supporting kmers are pruned from the graph">
            <validator type="in_range" message="value between 0 and 127" min="0" max="127"/>
        </param>
        <param name="output_mode" type="select" optional="true" label="output_mode" help="--output_mode / -out_mode  Specifies which type of calls we should output">
              <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="pair_hmm_implementation" type="select" optional="true" label="pair_hmm_implementation" help="--pair_hmm_implementation / -pairHMM  The PairHMM implementation to use for genotype likelihood calculations">
              <option value="EXACT">EXACT</option>
              <option value="ORIGINAL">ORIGINAL</option>
              <option value="CACHING">CACHING</option>
              <option value="LOGLESS_CACHING" selected="True">LOGLESS_CACHING</option>
        </param>
        <param name="standard_min_confidence_threshold_for_calling" type="float" value="30.0" optional="true" label="standard_min_confidence_threshold_for_calling" help="--standard_min_confidence_threshold_for_calling / -stand_call_conf  The minimum phred-scaled confidence threshold at which variants should be called"/>
        <param name="standard_min_confidence_threshold_for_emitting" type="float" value="30.0" optional="true" label="standard_min_confidence_threshold_for_emitting" help="--standard_min_confidence_threshold_for_emitting / -stand_emit_conf  The minimum phred-scaled confidence threshold at which variants should be emitted (and filtered with LowQual if less than the calling threshold)"/>
        <param name="useAllelesTrigger" type="boolean" checked="False" truevalue="-allelesTrigger" falsevalue="" label="useAllelesTrigger" help="--useAllelesTrigger / -allelesTrigger  If specified, use additional trigger on variants found in an external alleles file"/>
        <param name="fullHaplotype" type="boolean" checked="False" truevalue="-fullHaplotype" falsevalue="" label="fullHaplotype" help="--fullHaplotype / -fullHaplotype  If specified, output the full haplotype sequence instead of converting to individual variants w.r.t. the reference"/>
        <param name="gcpHMM" type="integer" value="10" optional="true" label="gcpHMM" help="--gcpHMM / -gcpHMM  Flat gap continuation penalty for use in the Pair HMM"/>
        <param name="genotypeFullActiveRegion" type="boolean" checked="False" truevalue="-genotypeFullActiveRegion" falsevalue="" label="genotypeFullActiveRegion" help="--genotypeFullActiveRegion / -genotypeFullActiveRegion  If specified, alternate alleles are considered to be the full active region for the purposes of genotyping"/>
        <param name="max_alternate_alleles" type="integer" value="6" optional="true" label="max_alternate_alleles" help="--max_alternate_alleles / -maxAltAlleles  Maximum number of alternate alleles to genotype"/>
        <param name="p_nonref_model" type="select" optional="true" label="p_nonref_model" help="--p_nonref_model / -pnrm  Non-reference probability calculation model to employ">
              <option value="EXACT_INDEPENDENT" selected="True">EXACT_INDEPENDENT experimental implementation - for testing only</option>
              <option value="EXACT_REFERENCE">EXACT_REFERENCE reference implementation of multi-allelic EXACT model. Extremely slow for many alternate alleles</option>
              <option value="EXACT_ORIGINAL">EXACT_ORIGINAL original biallelic exact model, for testing only</option>
              <option value="EXACT_GENERAL_PLOIDY">implementation that supports any sample ploidy</option>
        </param>

      </when>
    </conditional>
  </inputs>
  <outputs>
    <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (VCF)" />
    <data format="vcf" name="graph_out" label="${tool.name} on ${on_string} graph" >
      <filter>analysis_param_type['analysis_param_type_selector'] == "advanced" and analysis_param_type['graphOutput'] == True</filter>
    </data>
    <data format="vcf" name="active_region_out" label="${tool.name} on ${on_string} activeRegion" >
      <filter>analysis_param_type['analysis_param_type_selector'] == "advanced" and analysis_param_type['activeRegionOut'] == True</filter>
    </data>
    <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" />
  </outputs>
  <tests>
      <test>
          <param name="input_recal" value="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" ftype="csv" /> 
          <param name="reference_source_selector" value="history" />
          <param name="ref_file" value="phiX.fasta" ftype="fasta" />
          <param name="input_bam" value="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" />
          <param name="gatk_param_type_selector" value="basic" />
          <param name="analysis_param_type_selector" value="basic" />
          <output name="output_bam" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" lines_diff="4" />
          <output name="output_log" file="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.log.contains" compare="contains" />
      </test>
  </tests>
  <help>
**What it does**

**HaplotypeCaller**
calls SNPs and indels simultaneously via local de-novo assembly of haplotypes in an active region.
Haplotypes are evaluated using an affine gap penalty Pair HMM.

For more information on using read based compression in the GATK, see this `tool specific page &lt;http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_haplotypecaller_HaplotypeCaller.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: PrintReads accepts aligned BAM files.


**Outputs**

The output is a VCF file with raw, unrecalibrated SNP and indel calls.


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

-------

**Settings**::

 activeRegionIn              Use this interval list file as the active regions to process
 activeRegionOut             Output the active region to this interval list file
 alleles                     The set of alleles at which to genotype when --genotyping_mode is GENOTYPE_GIVEN_ALLELES
 annotation                  One or more specific annotations to apply to variant calls
 comp                        comparison VCF file
 contamination               Fraction of contamination in sequencing data (for all samples) to aggressively remove
 dbsnp                       dbSNP file
 debug                       If specified, print out very verbose debug information about each triggering active region
 downsampleRegion            coverage, per-sample, to downsample each active region to
 excludeAnnotation           One or more specific annotations to exclude
 genotyping_mode             Specifies how to determine the alternate alleles to use for genotyping
 graphOutput                 File to which debug assembly graph information should be written
 group                       One or more classes/groups of annotations to apply to variant calls
 heterozygosity              Heterozygosity value used to compute prior likelihoods for any locus
 minPruning                  The minimum allowed pruning factor in assembly graph. Paths with less than or equal supporting kmers are pruned from the graph
 output_mode                 Specifies which type of calls we should output
 pair_hmm_implementation     The PairHMM implementation to use for genotype likelihood calculations
 stand_call_conf             The minimum phred-scaled confidence threshold at which variants should be called
 stand_emit_conf             The minimum phred-scaled confidence threshold at which variants should be emitted (and filtered with LowQual if less than the calling threshold)
 useAllelesTrigger           If specified, use additional trigger on variants found in an external alleles file
 fullHaplotype               If specified, output the full haplotype sequence instead of converting to individual variants w.r.t. the reference
 gcpHMM                      Flat gap continuation penalty for use in the Pair HMM
 genotypeFullActiveRegion    If specified, alternate alleles are considered to be the full active region for the purposes of genotyping
 max_alternate_alleles       Maximum number of alternate alleles to genotype
 p_nonref_model              Non-reference probability calculation model to employ

------

@CITATION_SECTION@
  </help>
</tool>