view fpfilter.xml @ 1:0f17ca98338e draft default tip

Uploaded

<tool id="fpfilter" name="fpfilter" version="0.0.1">
  <description></description>
  <requirements>
    <requirement type="package" version="0.8" >bam-readcount</requirement>
    <requirement type="package" >samtools</requirement>
    <requirement type="package" version="1.0" >openssl</requirement>
  </requirements>
  <command>
	perl  $__tool_directory__/fpfilter.pl
	--vcf-file ${vcf}
	--bam-file ${bam}
	--bam-index  ${bam.metadata.bam_index}
	--sample ${sample}


         #if $reference_source.reference_source_selector == "history"
         --reference $reference_source.reference
        #end if
        #if $reference_source.reference_source_selector == "cached"
         --reference  $reference_source.ref_file.fields.path
        #end if

	--output ${output}
	--min-read-pos ${min_read_pos}
	--min-var-freq ${min_var_freq}
	--min-var-count ${min_var_count}
	--min-strandedness ${min_strandness}
	--max-mm-qualsum-diff ${max_mm_qualsum_diff}
	--max-var-mm-qualsum ${max_var_mm_qualsum}
	--max-mapqual-diff ${max_mapqual_diff}
	--max-readlen-diff ${max_readlen_diff}
	--min-var-dist-3 ${min_var_dist_3}
  </command>

  <inputs>
    <param name="vcf" format="vcf" type="data" label="VCF File" help="The input VCF file. Must have a GT field." />
    <param name="bam" format="bam" type="data" label="bam file" help="The BAM file of the sample you are filtering on. Typically the tumor." />
    <param name="sample" type="text" label="Sample" value="sample" help="The sample name of the sample you want to filter on in the VCF file." />
      <conditional name="reference_source">
            <param name="reference_source_selector" type="select" label="Will you select a reference genome from your history or use a built-in index?">
                <option value="cached">Use a built-in genome</option>
                <option value="history">Use a genome from history as reference</option>
            </param>
            <when value="cached">
                <param name="ref_file" type="select" label="Using reference genome" help="Select genome from the list">
                    <options from_data_table="fpf_index">
                        <filter type="sort_by" column="2" />
                        <validator type="no_options" message="No indexes are available" />
                    </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="reference" 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>
    <param name="min_read_pos" type="float" value="0.10" label="Min Read Pos" help="Minimum average relative distance from start/end of read." />
    <param name="min_var_freq" type="float" value="0.05" label="Min Var Freq" help="Minimum variant allele frequency." />
    <param name="min_var_count" type="integer" value="4" label="Min Var Count" help="Minimum number of variant-supporting reads." />

    <param name="min_strandness" type="float" value="0.01" label="Min Strandness" help="Minimum representation of variant allele on each strand." />
    <param name="max_mm_qualsum_diff" type="integer" value="50" label="Max mm qualsum diff" help="Maximum difference of mismatch quality sum between variant and reference reads (paralog filter)." />

    <param name="max_var_mm_qualsum" type="integer" value="100" label="Max var mm qualsum" help="Maximum mismatch quality sum of reference-supporting reads." />
    <param name="max_mapqual_diff" type="integer" value="30" label="Max mapqual diff" help="Maximum difference of mapping quality between variant and reference reads." />

    <param name="max_readlen_diff" type="integer" value="25" label="Max readlen diff" help="Maximum difference of average supporting read length between variant and reference reads (paralog filter)" />
    <param name="min_var_dist_3" type="float" value="0.20" label="Min var dist 3 " help="minimum average distance to effective 3prime end of read (real end or Q2) for variant-supporting reads" />

  </inputs>

  <outputs>
    <data format="vcf" name="output" label="FP Filtered VCF" />
  </outputs>
  <stdio>
    <exit_code range="1:" level="fatal" />
  </stdio>
  <help>
    --vcf-file              the input VCF file. Must have a GT field.
    --bam-file              the BAM file of the sample you are filtering on. Typically the tumor.
    --sample                the sample name of the sample you want to filter on in the VCF file.
    --reference-sequence    a fasta containing the reference sequence the BAM file was aligned to.
    --output                the filename of the output VCF file
    --min-read-pos          minimum average relative distance from start/end of read
    --min-var-freq          minimum variant allele frequency
    --min-var-count         minimum number of variant-supporting reads
    --min-strandedness      minimum representation of variant allele on each strand
    --max-mm-qualsum-diff   maximum difference of mismatch quality sum between variant and reference reads (paralog filter)
    --max_var_mm_qualsum    maximum mismatch quality sum of reference-supporting reads
    --max-mapqual-diff      maximum difference of mapping quality between variant and reference reads
    --max-readlen-diff      maximum difference of average supporting read length between variant and reference reads (paralog filter)
    --min-var-dist-3        minimum average distance to effective 3prime end of read (real end or Q2) for variant-supporting reads

this wrapper has been developed from the existing script at https://github.com/ucscCancer/fpfilter-tool/blob/master/fpfilter.xml , only the requirement and part of the command line have been changed in order to make it suitable for CONDA
  </help>

  <tests>
    <test>
    </test>
  </tests>

</tool>