comparison freebayes.xml @ 17:4c80a1387285 draft

Uploaded

16:6d9407020066

<?xml version="1.0"?>
<tool id="freebayes" name="FreeBayes" version="0.3">
  <requirements>
    <requirement type="package" version="0.9.18_0059bdf">freebayes</requirement>
    <requirement type="package" version="0.1.18">samtools</requirement>
  </requirements>
  <description> - bayesian genetic variant detector</description>
  <command>
    ##set up input files

      --report-monomorphic
      --standard-filters
      --min-coverage "${options_type.min_coverage}"

##    Command line direct text entry is not allowed at this time for security reasons

##    #elif str( $options_type.options_type_selector ) == "cline":
    
##      ${options_type.cline}
  
##      @optional_inputs_outputs@
    
    #elif str( $options_type.options_type_selector ) == "full":
    
##optional inputs and outputs
 
        @optional_inputs_outputs@
        
## REPORTING
        
        #if str( $options_type.reporting.reporting_selector ) == "True":
            --pvar ${options_type.reporting.pvar}
        #end if
        
## POPULATION MODEL

        #if str( $options_type.population_model.population_model_selector ) == "True":
            --theta "${options_type.population_model.T}"
            --ploidy "${options_type.population_model.P}"
            ${options_type.population_model.J}
            ${options_type.population_model.K}
            
        #end if
        
## REFERENCE ALLELE
        
        #if str( $options_type.reference_allele.reference_allele_selector ) == "True":
            ${options_type.reference_allele.Z}
            --reference-quality "${options_type.reference_allele.reference_quality}"
        #end if
        
## ALLELE SCOPE
        
        #if str( $options_type.allele_scope.allele_scope_selector ) == "True":
            ${options_type.allele_scope.I}
            ${options_type.allele_scope.i}
            ${options_type.allele_scope.X}
            ${options_type.allele_scope.u}
            -n "${options_type.allele_scope.n}"
            --haplotype-length "${options_type.allele_scope.haplotype_length}"
            --min-repeat-size "${options_type.allele_scope.min_repeat_length}"
            --min-repeat-entropy "${options_type.allele_scope.min_repeat_entropy}"
            ${options_type.allele_scope.no_partial_observations}
        #end if
        
## REALIGNMENT
 
        ${options_type.O}
        
##INPUT FILTERS

        #if str( $options_type.input_filters.input_filters_selector ) == "True":
            ${options_type.input_filters.use_duplicate_reads}
            -m "${options_type.input_filters.m}"
            -q "${options_type.input_filters.q}"
            -R "${options_type.input_filters.R}"
            -Y "${options_type.input_filters.Y}"
            
            #if str( $options_type.input_filters.mismatch_filters.mismatch_filters_selector ) == "True":
              -Q "${options_type.input_filters.mismatch_filters.Q}"
              -U "${options_type.input_filters.mismatch_filters.U}"
              -z "${options_type.input_filters.mismatch_filters.z}"
              --read-snp-limit "${options_type.input_filters.mismatch_filters.read_snp_limit}"
            #end if
            
            -e "${options_type.input_filters.e}"
            -F "${options_type.input_filters.F}"
            -C "${options_type.input_filters.C}"
            --min-alternate-qsum "${options_type.input_filters.min_alternate_qsum}"
            -G "${options_type.input_filters.G}"
            --min-coverage "${options_type.input_filters.min_coverage}"
        #end if
        
## POPULATION AND MAPPABILITY PRIORS
        
        #if str( $options_type.population_mappability_priors.population_mappability_priors_selector ) == "True":
            ${options_type.population_mappability_priors.k}
            ${options_type.population_mappability_priors.w}
            ${options_type.population_mappability_priors.V}
            ${options_type.population_mappability_priors.a}
        #end if
        
## GENOTYPE LIKELIHOODS
        
        #if str( $options_type.genotype_likelihoods.genotype_likelihoods_selector ) == "True":
          --base-quality-cap "${$options_type.genotype_likelihoods.base_quality_cap}"
          ${$options_type.genotype_likelihoods.experimental_gls}
          --prob-contamination "${$options_type.genotype_likelihoods.prob_contamination}"
        #end if
        
## ALGORITHMIC FEATURES
        
        #if str( $options_type.algorithmic_features.algorithmic_features_selector ) == "True":
            ${options_type.algorithmic_features.report_genotype_likelihood_max}
            -B "${options_type.algorithmic_features.B}"
            --genotyping-max-banddepth "${options_type.algorithmic_features.genotyping_max_banddepth}"
            -W "${options_type.algorithmic_features.W}"
            ${options_type.algorithmic_features.N}
            
            #if str( $options_type.algorithmic_features.genotype_variant_threshold.genotype_variant_threshold_selector ) == "True":
                -S "${options_type.algorithmic_features.genotype_variant_threshold.S}"
            #end if
          
            ${options_type.algorithmic_features.j}
            ${options_type.algorithmic_features.H}
            -D "${options_type.algorithmic_features.D}"
            ${options_type.algorithmic_features.genotype_qualities}
        #end if
    #end if
    
  </command>
  
  <macros>
      <token name="@optional_inputs_outputs@">     
      ## This token gets injected in commane in two instances: when options_type.options_type_selector == "full" and "cline" ( cline is not supported at this time )
      
      #if $options_type.optional_inputs.optional_inputs_selector:
        
          #if $options_type.optional_inputs.output_trace_option:
            --trace "${output_trace}"
          #end if
          

          #if $options_type.optional_inputs.contamination_estimates:
            --contamination-estimates "${options_type.optional_inputs.contamination_estimates}"
          #end if
          
        #end if
    </token>
    <xml name="optional_file_inputs">
      <conditional name="optional_inputs">
          <param name="optional_inputs_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Do you want to provide additional inputs?" help="Sets --samples, --populations, --cnv-map, --trace, --failed-alleles, --varinat-input, --only-use-input-alleles, --haplotype-basis-alleles, --report-all-haplotype-alleles, --report-monomorphic options, --observation-bias, and --contamination-estimates" />
          <when value="set">
            <param name="output_failed_alleles_option" type="boolean" truevalue="--failed-alleles" falsevalue="" checked="False" label="Write out failed alleles file" help="--failed-alleles" />
            <param name="output_trace_option" type="boolean" truevalue="--trace" falsevalue="" checked="False" label="Write out algorithm trace file" help="--trace"/>
            <param name="samples" type="data" format="txt" label="Limit analysis to samples listed (one per line) in the FILE" optional="True" help="-s --samples; default=By default FreeBayes will analyze all samples in its input BAM files"/>

            <param name="contamination_estimates" optional="True" type="data" format="tabular" label="Upload per-sample estimates of contamination from" help="--contamination-estimates; The format should be: sample p(read=R|genotype=AR) p(read=A|genotype=AA) Sample '*' can be used to set default contamination estimates." />
          </when>
          <when value="do_not_set">
            <!-- do nothing -->
          </when>
      </conditional>
    </xml>
  </macros>
  
  <inputs>
    <conditional name="reference_source">
      <param name="reference_source_selector" type="select" label="Load reference genome from">
        <option value="cached">Local cache</option>
        <option value="history">History</option>
      </param>
      <when value="cached">
        <repeat name="input_bams" title="Sample BAM file" min="1">
            <param name="input_bam" type="data" format="bam" label="BAM file">
              <validator type="unspecified_build" />
              <validator type="dataset_metadata_in_data_table" table_name="fasta_indexes" metadata_name="dbkey" metadata_column="1" message="Sequences are not currently available for the specified build." />
            </param>
        </repeat>
        
        <param name="ref_file" type="select" label="Using reference genome">
          <options from_data_table="fasta_indexes"></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="Sample BAM file" min="1">
          <param name="input_bam" type="data" format="bam" label="BAM file" />
        </repeat>
        <param name="ref_file" type="data" format="fasta" label="Use the following dataset as the reference sequence" help="You can upload a FASTA sequence to the history and use it as reference" />
      </when>
    </conditional>
    
    <conditional name="target_limit_type">
      <param name="target_limit_type_selector" type="select" label="Limit variant calling to a set of regions?" help="Sets --targets or --region options">
        <option value="do_not_limit" selected="True">Do not limit</option>
        <option value="limit_by_target_file">Limit by target file</option>
        <option value="limit_by_region">Limit to region</option>
      </param>
      <when value="do_not_limit">
        <!-- Do nothing here -->
      </when>
      <when value="limit_by_target_file">
        <param name="input_target_bed" type="data" format="bed" label="Limit analysis to targets listed in the BED-format FILE." help="-t --targets"/>
      </when>
      <when value="limit_by_region">
        <param name="region_chromosome" type="text" label="Region Chromosome" value="" help="-r --region"/> <!--only once? -->
        <param name="region_start" type="integer" label="Region Start" value="" />
        <param name="region_end" type="integer" label="Region End" value="" />
      </when>
    </conditional>
    
    <conditional name="options_type">
      <param name="options_type_selector" type="select" label="Choose parameter selection level" help="Select how much control over the freebayes run you need" >
        <option value="simple" selected="True">1:Simple diploid calling</option>
        <option value="simple_w_filters">2:Simple diploid calling with filtering and coverage</option>
        <option value="naive">3:Frequency-based pooled calling</option>
        <option value="naive_w_filters">4:Frequency-based pooled calling with filtering and coverage</option>
        <option value="full">5:Complete list of all options</option>
        <!-- We will not alloow command line text boxes at this time
        <option value="cline">6:Input parameters on the command line</option>
        -->
      </param>
      <when value="full">
   
        <expand macro="optional_file_inputs" /> <!-- see macros section -->
        
        <!-- reporting -->
        
        <conditional name="reporting">
          <param name="reporting_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Set reporting option?" help="Sets -P --pvar option" />

  </when>
  <when value="naive_w_filters">
    <!-- do nothing build command line using haplotype-length 0 min-alternate-count 1 min-alternate-fraction 0 pooled-continuous report-monomorphic standard-filters-->
    <param name="min_coverage" type="integer" value="0" label="Require at least this coverage to process a site" help="-! --min-coverage; default=0  " />
  </when>
  
  <!-- We will not allow command line textboxes at this time
  <when value="cline">
    
    <expand macro="optional_file_inputs" /> 
    
    <param name="cline" size="60" type="text" value="-m 20 -q 30" label="Type command line tags here" help="All paremeters that DO NOT involve filenames can be typed here. Use &quot;Do you want to provide additional inputs?&quot; section above to control input and output files. For full syntax check help section below">
      <sanitizer>
        <valid initial="string.printable">
         <remove value="&apos;"/>
        </valid>
        <mapping initial="none">
          <add source="&apos;" target="__sq__"/>
        </mapping>
      </sanitizer>
    </param>
  </when>
  -->

</conditional>

  </inputs>
  <outputs>
    <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (variants)" />
    <data format="bed" name="output_failed_alleles_bed" label="${tool.name} on ${on_string} (failed alleles)">
      <filter>( options_type['options_type_selector'] == 'cline' or options_type['options_type_selector'] == 'full' ) and options_type['optional_inputs']['optional_inputs_selector'] is True and options_type['optional_inputs']['output_failed_alleles_option'] is True</filter>
    </data>

      <param name="ref_file" ftype="fasta" value="freebayes-phix174.fasta"/>
      <param name="input_bam" ftype="bam" value="freebayes-phix174.bam"/>
      <param name="options_type_selector" value="simple"/>
      <output name="output_vcf" file="freebayes-phix174-test1.vcf" compare="contains"/>
    </test>
  </tests>
  <stdio>
    <exit_code range="1:" />
  </stdio>
  <help>

FreeBayes is a Bayesian genetic variant detector designed to find small polymorphisms, specifically SNPs (single-nucleotide polymorphisms), indels (insertions and deletions), MNPs (multi-nucleotide polymorphisms), and complex events (composite insertion and substitution events) smaller than the length of a short-read sequencing alignment.

See https://github.com/ekg/freebayes for details on FreeBayes.

This Galaxy instance of FreeBayes corresponds to release 0.9.18

------

**Description**

17:4c80a1387285

<?xml version="1.0"?>
<tool id="freebayes" name="FreeBayes" version="0.4">
  <requirements>
    <requirement type="package" version="0_9_20_b040236">freebayes</requirement>
    <requirement type="package" version="0.1.18">samtools</requirement>
  </requirements>
  <description> - bayesian genetic variant detector</description>
  <command>
    ##set up input files

      --report-monomorphic
      --standard-filters
      --min-coverage "${options_type.min_coverage}"

##    Command line direct text entry is not allowed at this time for security reasons
    
    #elif str( $options_type.options_type_selector ) == "full":
 
        #if $options_type.optional_inputs.optional_inputs_selector:
        
          #if $options_type.optional_inputs.output_trace_option:
            --trace "${output_trace}"
          #end if
          

          #if $options_type.optional_inputs.contamination_estimates:
            --contamination-estimates "${options_type.optional_inputs.contamination_estimates}"
          #end if
          
        #end if
        
## REPORTING
        
        #if str( $options_type.reporting.reporting_selector ) == "True":
            --pvar ${options_type.reporting.pvar}
        #end if
        
## POPULATION MODEL

        #if str( $options_type.population_model.population_model_selector ) == "True":
            --theta "${options_type.population_model.T}"
            --ploidy "${options_type.population_model.P}"
            ${options_type.population_model.J}
            ${options_type.population_model.K}
            
        #end if
        
## REFERENCE ALLELE
        
        #if str( $options_type.reference_allele.reference_allele_selector ) == "True":
            ${options_type.reference_allele.Z}
            --reference-quality "${options_type.reference_allele.reference_quality}"
        #end if
        
## ALLELE SCOPE
        
        #if str( $options_type.allele_scope.allele_scope_selector ) == "True":
            ${options_type.allele_scope.I}
            ${options_type.allele_scope.i}
            ${options_type.allele_scope.X}
            ${options_type.allele_scope.u}
            -n "${options_type.allele_scope.n}"
            --haplotype-length "${options_type.allele_scope.haplotype_length}"
            --min-repeat-size "${options_type.allele_scope.min_repeat_length}"
            --min-repeat-entropy "${options_type.allele_scope.min_repeat_entropy}"
            ${options_type.allele_scope.no_partial_observations}
        #end if
        
## REALIGNMENT
 
        ${options_type.O}
        
##INPUT FILTERS

        #if str( $options_type.input_filters.input_filters_selector ) == "True":
            ${options_type.input_filters.use_duplicate_reads}
            -m "${options_type.input_filters.m}"
            -q "${options_type.input_filters.q}"
            -R "${options_type.input_filters.R}"
            -Y "${options_type.input_filters.Y}"
            
            #if str( $options_type.input_filters.mismatch_filters.mismatch_filters_selector ) == "True":
              -Q "${options_type.input_filters.mismatch_filters.Q}"
              -U "${options_type.input_filters.mismatch_filters.U}"
              -z "${options_type.input_filters.mismatch_filters.z}"
              --read-snp-limit "${options_type.input_filters.mismatch_filters.read_snp_limit}"
            #end if
            
            -e "${options_type.input_filters.e}"
            -F "${options_type.input_filters.F}"
            -C "${options_type.input_filters.C}"
            --min-alternate-qsum "${options_type.input_filters.min_alternate_qsum}"
            -G "${options_type.input_filters.G}"
            --min-coverage "${options_type.input_filters.min_coverage}"
        #end if
        
## POPULATION AND MAPPABILITY PRIORS
        
        #if str( $options_type.population_mappability_priors.population_mappability_priors_selector ) == "True":
            ${options_type.population_mappability_priors.k}
            ${options_type.population_mappability_priors.w}
            ${options_type.population_mappability_priors.V}
            ${options_type.population_mappability_priors.a}
        #end if
        
## GENOTYPE LIKELIHOODS
        
        #if str( $options_type.genotype_likelihoods.genotype_likelihoods_selector ) == "True":
          --base-quality-cap "${$options_type.genotype_likelihoods.base_quality_cap}"
          ${$options_type.genotype_likelihoods.experimental_gls}
          --prob-contamination "${$options_type.genotype_likelihoods.prob_contamination}"
        #end if
        
## ALGORITHMIC FEATURES
        
        #if str( $options_type.algorithmic_features.algorithmic_features_selector ) == "True":
            ${options_type.algorithmic_features.report_genotype_likelihood_max}
            -B "${options_type.algorithmic_features.B}"
            --genotyping-max-banddepth "${options_type.algorithmic_features.genotyping_max_banddepth}"
            -W "${options_type.algorithmic_features.W}"
            ${options_type.algorithmic_features.N}
            
            #if str( $options_type.algorithmic_features.genotype_variant_threshold.genotype_variant_threshold_selector ) == "True":
                -S "${options_type.algorithmic_features.genotype_variant_threshold.S}"
            #end if
          
            ${options_type.algorithmic_features.j}
            ${options_type.algorithmic_features.H}
            -D "${options_type.algorithmic_features.D}"
            ${options_type.algorithmic_features.genotype_qualities}
        #end if
    #end if
    
  </command>
  
  <inputs>
    <conditional name="reference_source">
      <param name="reference_source_selector" type="select" label="Load reference genome from">
        <option value="cached">Local cache</option>
        <option value="history">History</option>
      </param>
      <when value="cached">
        <repeat name="input_bams" title="Sample BAM file" min="1">
            <param name="input_bam" type="data" format="bam" label="BAM file">
              <validator type="unspecified_build" />
              <validator type="dataset_metadata_in_data_table" table_name="fasta_indexes" metadata_name="dbkey" metadata_column="1" message="Sequences are not currently available for the specified build." />
            </param>
        </repeat>
        
        <param name="ref_file" type="select" label="Using reference genome">
          <options from_data_table="fasta_indexes"></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="Sample BAM file" min="1">
          <param name="input_bam" type="data" format="bam" label="BAM file" />
        </repeat>
        <param name="ref_file" type="data" format="fasta" label="Use the following dataset as the reference sequence" help="You can upload a FASTA sequence to the history and use it as reference" />
      </when>
    </conditional>
    
    <conditional name="target_limit_type">
      <param name="target_limit_type_selector" type="select" label="Limit variant calling to a set of regions?" help="Sets --targets or --region options">
        <option value="do_not_limit" selected="True">Do not limit</option>
        <option value="limit_by_target_file">Limit by target file</option>
        <option value="limit_by_region">Limit to region</option>
      </param>
      <when value="do_not_limit">
        <!-- Do nothing here -->
      </when>
      <when value="limit_by_target_file">
        <param name="input_target_bed" type="data" format="bed" label="Limit analysis to targets listed in the BED-format FILE." help="-t --targets"/>
      </when>
      <when value="limit_by_region">
        <param name="region_chromosome" type="text" label="Region Chromosome" value="" help="-r --region"/> <!--only once? -->
        <param name="region_start" type="integer" label="Region Start" value="" />
        <param name="region_end" type="integer" label="Region End" value="" />
      </when>
    </conditional>
    
    <conditional name="options_type">
      <param name="options_type_selector" type="select" label="Choose parameter selection level" help="Select how much control over the freebayes run you need" >
        <option value="simple" selected="True">1:Simple diploid calling</option>
        <option value="simple_w_filters">2:Simple diploid calling with filtering and coverage</option>
        <option value="naive">3:Frequency-based pooled calling</option>
        <option value="naive_w_filters">4:Frequency-based pooled calling with filtering and coverage</option>
        <option value="full">5:Complete list of all options</option>
        <!-- We will not alloow command line text boxes at this time
        <option value="cline">6:Input parameters on the command line</option>
        -->
      </param>
      <when value="full">
        
        <conditional name="optional_inputs">
          <param name="optional_inputs_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Do you want to provide additional inputs?" help="Sets --samples, --populations, --cnv-map, --trace, --failed-alleles, --varinat-input, --only-use-input-alleles, --haplotype-basis-alleles, --report-all-haplotype-alleles, --report-monomorphic options, --observation-bias, and --contamination-estimates" />
          <when value="set">
            <param name="output_failed_alleles_option" type="boolean" truevalue="--failed-alleles" falsevalue="" checked="False" label="Write out failed alleles file" help="--failed-alleles" />
            <param name="output_trace_option" type="boolean" truevalue="--trace" falsevalue="" checked="False" label="Write out algorithm trace file" help="--trace"/>
            <param name="samples" type="data" format="txt" label="Limit analysis to samples listed (one per line) in the FILE" optional="True" help="-s --samples; default=By default FreeBayes will analyze all samples in its input BAM files"/>

            <param name="contamination_estimates" optional="True" type="data" format="tabular" label="Upload per-sample estimates of contamination from" help="--contamination-estimates; The format should be: sample p(read=R|genotype=AR) p(read=A|genotype=AA) Sample '*' can be used to set default contamination estimates." />
          </when>
          <when value="do_not_set">
            <!-- do nothing -->
          </when>
        </conditional>
        
        <!-- reporting -->
        
        <conditional name="reporting">
          <param name="reporting_selector" type="boolean" truevalue="set" falsevalue="do_not_set" label="Set reporting option?" help="Sets -P --pvar option" />

  </when>
  <when value="naive_w_filters">
    <!-- do nothing build command line using haplotype-length 0 min-alternate-count 1 min-alternate-fraction 0 pooled-continuous report-monomorphic standard-filters-->
    <param name="min_coverage" type="integer" value="0" label="Require at least this coverage to process a site" help="-! --min-coverage; default=0  " />
  </when>
</conditional>

  </inputs>
  
  <outputs>
    <data format="vcf" name="output_vcf" label="${tool.name} on ${on_string} (variants)" />
    <data format="bed" name="output_failed_alleles_bed" label="${tool.name} on ${on_string} (failed alleles)">
      <filter>( options_type['options_type_selector'] == 'cline' or options_type['options_type_selector'] == 'full' ) and options_type['optional_inputs']['optional_inputs_selector'] is True and options_type['optional_inputs']['output_failed_alleles_option'] is True</filter>
    </data>

      <param name="ref_file" ftype="fasta" value="freebayes-phix174.fasta"/>
      <param name="input_bam" ftype="bam" value="freebayes-phix174.bam"/>
      <param name="options_type_selector" value="simple"/>
      <output name="output_vcf" file="freebayes-phix174-test1.vcf" compare="contains"/>
    </test>
    <test>
     <param name="reference_source_selector" value="history" />
      <param name="ref_file" ftype="fasta" value="freebayes-phix174.fasta"/>
      <param name="input_bam" ftype="bam" value="freebayes-phix174.bam"/>
      <param name="options_type_selector" value="naive_w_filters"/>
      <param name="min_coverage" value="14"/>
      <output name="output_vcf" file="freebayes-phix174-test2.vcf" compare="contains"/>
    </test>
  </tests>
  <stdio>
    <exit_code range="1:" />
  </stdio>
  <help>

FreeBayes is a Bayesian genetic variant detector designed to find small polymorphisms, specifically SNPs (single-nucleotide polymorphisms), indels (insertions and deletions), MNPs (multi-nucleotide polymorphisms), and complex events (composite insertion and substitution events) smaller than the length of a short-read sequencing alignment.

See https://github.com/ekg/freebayes for details on FreeBayes.

This Galaxy instance of FreeBayes corresponds to release 0.9.20

------

**Description**