comparison freebayes.xml @ 16:6d9407020066 draft

Uploaded

15:59731e950e23

<?xml version="1.0"?>
<tool id="freebayes" name="FreeBayes" version="freebayes-0.9.14">
  <requirements>
    <requirement type="package" version="freebayes-0.9.14_8a407cf5f4">freebayes</requirement>
    <requirement type="package" version="0.1.18">samtools</requirement>
  </requirements>
  <description> - Bayesian genetic variant detector</description>
  <command>
    ##set up input files

    #set $reference_fasta_filename = "localref.fa"
    

        ln -s "${input_bam.input_bam.metadata.bam_index}" "localbam_${bam_count}.bam.bai" &&
    #end for
    
    ## Tabixize optional input_varinat_vcf file (for --variant-input option)
    
    #if ( str( $options_type.options_type_selector ) == 'cline' or str( $options_type.options_type_selector ) == 'full' ) and str( $options_type.optional_inputs.optional_inputs_selector ) == 'set' and str( $options_type.optional_inputs.input_variant_type.input_variant_type_selector ) == "provide_vcf":
        ln -s "${options_type.optional_inputs.input_variant_type.input_variant_vcf}" input_variant_vcf.vcf.gz &&
        ln -s "${Tabixized_input}" input_variant_vcf.vcf.gz.tbi &&
    #end if
    
    ##finished setting up inputs
    
    ##COMMAND LINE STARTS HERE

      --min-alternate-fraction 0
      --pooled-continuous
      --report-monomorphic
      --standard-filters
      --min-coverage "${options_type.min_coverage}"
      
    #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
 

    
  </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"
      
      #if $options_type.optional_inputs.optional_inputs_selector:
        
          #if $options_type.optional_inputs.output_trace_option:
            --trace "${output_trace}"

          #if $options_type.optional_inputs.A:
            --cnv-map "${options_type.optional_inputs.A}"
          #end if
          
          #if str( $options_type.optional_inputs.input_variant_type.input_variant_type_selector ) == "provide_vcf":
            --variant-input input_variant_vcf.vcf.gz  ## input_variant_vcf.vcf.gz is symlinked to a galaxy-generated dataset in "Tabixize optional input_varinat_vcf file" section of the command line above
            ${options_type.optional_inputs.input_variant_type.only_use_input_alleles}
          #end if
          
          #if $options_type.optional_inputs.haplotype_basis_alleles:
            --haplotype-basis-alleles "${options_type.optional_inputs.haplotype_basis_alleles}"

      </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="sam_fa_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="sam_fa_indexes">
            <!-- <filter type="sam_fa_indexes" key="dbkey" ref="input_bam" column="value"/> 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="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 folloing 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="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>
        <option value="cline">6:Input parameters on the command line</option>
      </param>
      <when value="full">
   
        <expand macro="optional_file_inputs" /> <!-- see macros section -->
        

  </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>
  <when value="cline">
    
    <expand macro="optional_file_inputs" /> <!-- see macros section -->
    
    <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;"/>

          <add source="&apos;" target="__sq__"/>
        </mapping>
      </sanitizer>
    </param>
  </when>

</conditional>

  </inputs>
  <outputs>

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 8a407cf5f4416b5eba5bf27ca80144cd5e75bb80

------

**Description**

 1. *Simple diploid calling*: The simples possible FreeBayes application. Equvalent of using FreeBayes with only a BAM input and no other parameter options.
 2. *Simple diploid calling with filtering and coverage*: Same as #1 plus two additional options: -0 (standard filters: --min-mapping-quality 30 --min-base-quality 20 --min-supporting-allele-qsum 0 --genotype-varinat-threshold 0) and --min-coverage. 
 3. *Frequency-based pooled calling*: This is equivalent to using FreeBayes with the following options: --haplotype-length 0 --min-alternate-count 1 --min-alternate-fraction 0 --pooled-continuous --report-monomorphic. This is the best choice for calling varinats in mixtures such as viral, bacterial, or organellar genomes. 
 4. *Frequency-based pooled calling with filtering and coverage*: Same as #3 but adds -0 and --min-coverage like in #2.
 5. *Complete list of all options*: Gives you full control by exposing all FreeBayes options as Galaxy widgets.
 6. *Input parameters on the command line*: Similar to the choice above but for those who does not like clicking. Here options can be directly typed into a text box.

-----

**FreeBayes options**

For the underlying tool, please cite `Erik Garrison and Gabor Marth. Haplotype-based variant detection from short-read sequencing <http://arxiv.org/abs/1207.3907>`_.

The initial version of the wrapper was produced by Dan Blankenberg and upgraded by Anton Nekrutenko.

  </help>
</tool>

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

    #set $reference_fasta_filename = "localref.fa"
    

        ln -s "${input_bam.input_bam.metadata.bam_index}" "localbam_${bam_count}.bam.bai" &&
    #end for
    
    ## Tabixize optional input_varinat_vcf file (for --variant-input option)
    
    #if ( str( $options_type.options_type_selector ) == 'cline' or str( $options_type.options_type_selector ) == 'full' ) and $options_type.optional_inputs.optional_inputs_selector and str( $options_type.optional_inputs.input_variant_type.input_variant_type_selector ) == "provide_vcf":
        ln -s "${options_type.optional_inputs.input_variant_type.input_variant_vcf}" "input_variant_vcf.vcf.gz" &&
        ln -s "${Tabixized_input}" "input_variant_vcf.vcf.gz.tbi" &&
    #end if
    
    ##finished setting up inputs
    
    ##COMMAND LINE STARTS HERE

      --min-alternate-fraction 0
      --pooled-continuous
      --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
 

    
  </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}"

          #if $options_type.optional_inputs.A:
            --cnv-map "${options_type.optional_inputs.A}"
          #end if
          
          #if str( $options_type.optional_inputs.input_variant_type.input_variant_type_selector ) == "provide_vcf":
            --variant-input "input_variant_vcf.vcf.gz"  ## input_variant_vcf.vcf.gz is symlinked to a galaxy-generated dataset in "Tabixize optional input_varinat_vcf file" section of the command line above
            ${options_type.optional_inputs.input_variant_type.only_use_input_alleles}
          #end if
          
          #if $options_type.optional_inputs.haplotype_basis_alleles:
            --haplotype-basis-alleles "${options_type.optional_inputs.haplotype_basis_alleles}"

      </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="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 -->
        

  </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;"/>

          <add source="&apos;" target="__sq__"/>
        </mapping>
      </sanitizer>
    </param>
  </when>
  -->

</conditional>

  </inputs>
  <outputs>

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**

 1. *Simple diploid calling*: The simples possible FreeBayes application. Equvalent of using FreeBayes with only a BAM input and no other parameter options.
 2. *Simple diploid calling with filtering and coverage*: Same as #1 plus two additional options: -0 (standard filters: --min-mapping-quality 30 --min-base-quality 20 --min-supporting-allele-qsum 0 --genotype-varinat-threshold 0) and --min-coverage. 
 3. *Frequency-based pooled calling*: This is equivalent to using FreeBayes with the following options: --haplotype-length 0 --min-alternate-count 1 --min-alternate-fraction 0 --pooled-continuous --report-monomorphic. This is the best choice for calling varinats in mixtures such as viral, bacterial, or organellar genomes. 
 4. *Frequency-based pooled calling with filtering and coverage*: Same as #3 but adds -0 and --min-coverage like in #2.
 5. *Complete list of all options*: Gives you full control by exposing all FreeBayes options as Galaxy widgets.

-----

**FreeBayes options**

For the underlying tool, please cite `Erik Garrison and Gabor Marth. Haplotype-based variant detection from short-read sequencing <http://arxiv.org/abs/1207.3907>`_.

The initial version of the wrapper was produced by Dan Blankenberg and upgraded by Anton Nekrutenko.

  </help>
  
  <citations>
    <citation type="bibtex">@misc{1207.3907,
Author = {Erik Garrison},
Title = {Haplotype-based variant detection from short-read sequencing},
Year = {2012},
Eprint = {arXiv:1207.3907},
url = {http://arxiv.org/abs/1207.3907},
}</citation>
  </citations>
</tool>