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

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

5:84584664264c

<tool id="gatk2_base_recalibrator" name="Base Recalibrator" version="@VERSION@.0">
  <description>calculates covariates used to recalibrate base quality scores of reads</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":

        #for $cov in str( $covariates ).split( ',' ):
            -cov "${cov}"
        #end for
    #end if
   '
    
    #set $snp_dataset_provided = False
    #set $rod_binding_names = dict()
    #for $rod_binding in $rod_bind:
        #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom':
            #set $rod_bind_name = $rod_binding.rod_bind_type.custom_rod_name

            #set $snp_dataset_provided = True
        #end if
        #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1
        -d "--knownSites:${rod_bind_name},%(file_type)s" "${rod_binding.rod_bind_type.input_rod}" "${rod_binding.rod_bind_type.input_rod.ext}" "input_${rod_bind_name}_${rod_binding_names[$rod_bind_name]}"
    #end for
    
    #include source=$standard_gatk_options#
    
    ##start analysis specific options
    #if $analysis_param_type.analysis_param_type_selector == "advanced":
        -p '
        #if $analysis_param_type.default_read_group_type.default_read_group_type_selector == "set":
            --default_read_group "${analysis_param_type.default_read_group_type.default_read_group}"

            --force_platform "${analysis_param_type.force_platform}"
        #end if
        ${analysis_param_type.exception_if_no_tile}
        #if str( $analysis_param_type.solid_options_type.solid_options_type_selector ) == "set":
            #if str( $analysis_param_type.solid_options_type.solid_recal_mode ) != "default":
                --solid_recal_mode "${analysis_param_type.solid_options_type.solid_recal_mode}" 
            #end if
            #if str( $analysis_param_type.solid_options_type.solid_nocall_strategy ) != "default":
                --solid_nocall_strategy "${analysis_param_type.solid_options_type.solid_nocall_strategy}" 
            #end if
        #end if
        --window_size_nqs "${analysis_param_type.window_size_nqs}"
        --homopolymer_nback "${analysis_param_type.homopolymer_nback}"
        '

      <option value="CycleCovariate" selected="true"/>
      <option value="RepeatLengthCovariate" />
      <option value="RepeatUnitCovariate" />
      <option value="RepeatUnitAndLengthCovariate" />
      <!--
      Note: ReadGroupCovariate and QualityScoreCovariate are required covariates and will 
      be added for the user regardless of whether or not they were specified.
      <option value="QualityScoreCovariate" />
      <option value="ReadGroupCovariate" />
      -->
    </param>
    
    <repeat name="rod_bind" title="Known Variants" help="Using data sets of known variants (-knownSites,--knownSites &amp;lt;knownSites&amp;gt;)">
        <conditional name="rod_bind_type">
          <param name="rod_bind_type_selector" type="select" label="Variant Type">
            <option value="dbsnp" selected="True">dbSNP</option>
            <option value="snps">SNPs</option>

          </when>
        </conditional>
    </repeat>

    <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>

          <param name="input_rod" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" />
          <param name="standard_covs" value="True" />
          <param name="covariates" value="ReadGroupCovariate,HomopolymerCovariate,MinimumNQSCovariate,PositionCovariate" />
          <param name="gatk_param_type_selector" value="basic" />
          <param name="analysis_param_type_selector" value="basic" />
          <output name="output_recal" file="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" /> 
          <output name="output_log" file="gatk/gatk_count_covariates/gatk_count_covariates_out_1.log.contains" compare="contains" />
      </test>
  </tests>
  <help>
.. class:: warningmark

"This calculation is critically dependent on being able to skip over known variant sites. Please provide a dbSNP ROD or a VCF file containing known sites of genetic variation."
However, if you do not provide this file, the '--run_without_dbsnp_potentially_ruining_quality' flag will be automatically used, and the command will be allowed to run.
  
**What it does**

This walker is designed to work as the first pass in a two-pass processing step. It does a by-locus traversal operating only at sites that are not in dbSNP. We assume that all reference mismatches we see are therefore errors and indicative of poor base quality. This walker generates tables based on various user-specified covariates (such as read group, reported quality score, cycle, and dinucleotide) Since there is a large amount of data one can then calculate an empirical probability of error given the particular covariates seen at this site, where p(error) = num mismatches / num observations The output file is a CSV list of (the several covariate values, num observations, num mismatches, empirical quality score) The first non-comment line of the output file gives the name of the covariates that were used for this calculation.  Note: ReadGroupCovariate and QualityScoreCovariate are required covariates and will be added for the user regardless of whether or not they were specified Note: This walker is designed to be used in conjunction with TableRecalibrationWalker.

For more information on base quality score recalibration using the GATK, see this `tool specific page &lt;http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_bqsr_BaseRecalibrator.html&gt;`_.

6:35c00763cb5c

<tool id="gatk2_base_recalibrator" name="Base Recalibrator" version="@VERSION@.0">
  <description>calculates covariates used to recalibrate base quality scores of reads</description>
  <macros>
    <import>gatk2_macros.xml</import>
  </macros>
  <expand macro="requirements" />
  <expand macro="version_command" />
  <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":

        #for $cov in str( $covariates ).split( ',' ):
            -cov "${cov}"
        #end for
    #end if
   '

    #set $snp_dataset_provided = False
    #set $rod_binding_names = dict()
    #for $rod_binding in $rod_bind:
        #if str( $rod_binding.rod_bind_type.rod_bind_type_selector ) == 'custom':
            #set $rod_bind_name = $rod_binding.rod_bind_type.custom_rod_name

            #set $snp_dataset_provided = True
        #end if
        #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1
        -d "--knownSites:${rod_bind_name},%(file_type)s" "${rod_binding.rod_bind_type.input_rod}" "${rod_binding.rod_bind_type.input_rod.ext}" "input_${rod_bind_name}_${rod_binding_names[$rod_bind_name]}"
    #end for

    #include source=$standard_gatk_options#

    ##start analysis specific options
    #if $analysis_param_type.analysis_param_type_selector == "advanced":
        -p '
        #if $analysis_param_type.default_read_group_type.default_read_group_type_selector == "set":
            --default_read_group "${analysis_param_type.default_read_group_type.default_read_group}"

            --force_platform "${analysis_param_type.force_platform}"
        #end if
        ${analysis_param_type.exception_if_no_tile}
        #if str( $analysis_param_type.solid_options_type.solid_options_type_selector ) == "set":
            #if str( $analysis_param_type.solid_options_type.solid_recal_mode ) != "default":
                --solid_recal_mode "${analysis_param_type.solid_options_type.solid_recal_mode}"
            #end if
            #if str( $analysis_param_type.solid_options_type.solid_nocall_strategy ) != "default":
                --solid_nocall_strategy "${analysis_param_type.solid_options_type.solid_nocall_strategy}"
            #end if
        #end if
        --window_size_nqs "${analysis_param_type.window_size_nqs}"
        --homopolymer_nback "${analysis_param_type.homopolymer_nback}"
        '

      <option value="CycleCovariate" selected="true"/>
      <option value="RepeatLengthCovariate" />
      <option value="RepeatUnitCovariate" />
      <option value="RepeatUnitAndLengthCovariate" />
      <!--
      Note: ReadGroupCovariate and QualityScoreCovariate are required covariates and will
      be added for the user regardless of whether or not they were specified.
      <option value="QualityScoreCovariate" />
      <option value="ReadGroupCovariate" />
      -->
    </param>

    <repeat name="rod_bind" title="Known Variants" help="Using data sets of known variants (-knownSites,--knownSites &amp;lt;knownSites&amp;gt;)">
        <conditional name="rod_bind_type">
          <param name="rod_bind_type_selector" type="select" label="Variant Type">
            <option value="dbsnp" selected="True">dbSNP</option>
            <option value="snps">SNPs</option>

          </when>
        </conditional>
    </repeat>

    <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>

          <param name="input_rod" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" />
          <param name="standard_covs" value="True" />
          <param name="covariates" value="ReadGroupCovariate,HomopolymerCovariate,MinimumNQSCovariate,PositionCovariate" />
          <param name="gatk_param_type_selector" value="basic" />
          <param name="analysis_param_type_selector" value="basic" />
          <output name="output_recal" file="gatk/gatk_count_covariates/gatk_count_covariates_out_1.csv" />
          <output name="output_log" file="gatk/gatk_count_covariates/gatk_count_covariates_out_1.log.contains" compare="contains" />
      </test>
  </tests>
  <help>
.. class:: warningmark

"This calculation is critically dependent on being able to skip over known variant sites. Please provide a dbSNP ROD or a VCF file containing known sites of genetic variation."
However, if you do not provide this file, the '--run_without_dbsnp_potentially_ruining_quality' flag will be automatically used, and the command will be allowed to run.

**What it does**

This walker is designed to work as the first pass in a two-pass processing step. It does a by-locus traversal operating only at sites that are not in dbSNP. We assume that all reference mismatches we see are therefore errors and indicative of poor base quality. This walker generates tables based on various user-specified covariates (such as read group, reported quality score, cycle, and dinucleotide) Since there is a large amount of data one can then calculate an empirical probability of error given the particular covariates seen at this site, where p(error) = num mismatches / num observations The output file is a CSV list of (the several covariate values, num observations, num mismatches, empirical quality score) The first non-comment line of the output file gives the name of the covariates that were used for this calculation.  Note: ReadGroupCovariate and QualityScoreCovariate are required covariates and will be added for the user regardless of whether or not they were specified Note: This walker is designed to be used in conjunction with TableRecalibrationWalker.

For more information on base quality score recalibration using the GATK, see this `tool specific page &lt;http://www.broadinstitute.org/gatk/gatkdocs/org_broadinstitute_sting_gatk_walkers_bqsr_BaseRecalibrator.html&gt;`_.