annotate SNPReports.xml @ 0:14e1cf728269 default tip

init commit

<?xml version="1.0"?>

<tool id="snp_reports_1" name="Compute protein coding SNP rates">
  <description>over targeted regions in a genome</description>
  <version_string>snp_reports -v</version_string>
  <command interpreter="perl">snp_reports -q $snp_table $target_bed $coding_gtf $depth_summary $out_snp_summary_table</command>
  <inputs>
    <param format="achri_snp_table" name="snp_table" type="data" label="SNP table" help="The output from running the tool 'Convert VCF file to table with HGVS cDNA and protein syntax'. If you have no selection available, please run that tool first in the current session, or import it from a previous analysis history."/>
    <param format="bed" name="target_bed" type="data" label="Target sequencing regions" help="e.g. a BED file from the Shared Data 'Exome target regions' folder, corresponding the to the capture kit used for sequencing the sample"/>
    <param format="gtf" name="coding_gtf" type="data" label="Coding sequences" help="e.g. a GTF file from the Shared Data 'Genomic coding sequence regions' folder, corresponding to the types of IDs desired (e.g. NCBI RefGene for NM_######)"/>
    <param format="achri_depth_summary_table" name="depth_summary" type="data" label="Depth report summary" help="The output from the tool 'Compute depth of sequencing coverage'. If you have no selection available, please run that tool first in the current session, or import it from a previous analysis history."/>
  </inputs>
  <outputs>
    <data name="out_snp_summary_table" format="achri_snp_summary_table" label="Summary of expected vs actual protein-coding SNP calls"/>
  </outputs>

  <tests>
    <test>
     <param name="snp_table" value="brca_depth_summary.txt" ftype="achri_annotated_snp_table"/>
     <param name="target_bed" value="brcas.bed" ftype="bed"/>
     <param name="depth_summary" value="brca_depth_summary.txt" ftype="achri_depth_summary_table"/>
     <param name="coding_gtf" value="brcas.gtf" ftype="gtf"/>
     <output name="out_snp_summary_table">
       <assert_contents>
         <has_text text="targeted nucleotide bases: 155091"/>
         <has_text text="bases mapped to targeted regions: 11473773"/>
         <has_text text="bases with less than 20-fold coverage: 19046"/>
       </assert_contents>
     </output>
    </test>
  </tests>

  <help>
This tool reports several statistics describing the rate of protein coding SNP calls from a next-gen sequencing analysis such as an exome capture. 
These results can be used to assess the quality of the SNP caller used, filtering thresholds, etc. Location with less than 10 fold coverage, and 
variants with caveat are ignored.
  </help>

</tool>