<?xml version="1.0"?>

<tool id="hgvs_annotation_1" name="Functionally annotate an HGVS table ">
  <requirements>
  	<requirement type="package">genesplicer</requirement>
	<requirement type="package">human</requirement>
	<requirement type="package">score3.pl</requirement>
	<requirement type="package">score5.pl</requirement>
  </requirements>


  <description>with deleterious change prediction, gene names, pathways, etc.</description>
  <version_string>hgvs_table_annotate -v</version_string>
  <command interpreter="perl">hgvs_table_annotate $__tool_data_path__ -q sift/$sift_dir polyphen2/$polyphen_file\.txt.gz gerp/$gerp_dir TissueDistributionDBs/$tissue_dist_file\.tab pathways/$pathways_file\.txt $refFlat_bed $input_hgvs_table $out_hgvs_annotated_table $keep_synonymous</command>
  <inputs>
    <param format="achri_snp_table" name="input_hgvs_table" type="data" label="Variant calls table with HGVS syntax"/>
    <param name="keep_synonymous" type="boolean" label="Report synonymous variants?" default="false" truevalue="true" falsevalue="false"/>
    <param name="sift_dir" type="select" display="radio" dynamic_options="SIFT_fileOptions()" label="SIFT precalculated tables" help="SIFT scores below 0.05 generally indicate a harmful variant"/>
    <param name="polyphen_file" type="select" display="radio" dynamic_options="PolyPhen_fileOptions()" label="PolyPhen2 precalculated tables" help="Makes a call of deleterious, possibly deleterious, or benign"/>
    <param name="gerp_dir" type="select" display="radio" dynamic_options="GERP_fileOptions()" label="GERP precalculated tables" help="GERP scores far from zero generally indicate a harmful variant"/>
    <param name="tissue_dist_file" type="select" display="radio" dynamic_options="TissueDist_fileOptions()" label="Gene tissue distribution DB" help="Lists in descending order the major tissue types in which each gene is expressed"/>
    <!--<param name="pseudogene_file" type="select" display="radio" dynamic_options="Pseudogene_fileOptions()" label="Pseudogene DB" help="Genes with pseudogenes are more likely to generate variant false positives through mismapping"/>-->
    <param name="pathways_file" type="select" display="radio" dynamic_options="Pathway_fileOptions()" label="Biochemical Pathway DB" help="Gives an idea of processes in which the gene is involved"/>
    <param name="refFlat_bed" type="data" format="bed" label="Gene Names DB" help="Import a refFlat file from the 'Genomic coding sequence regions' folder under Shared Data. Alternatively, provide a BED format file which defined exons and has the gene name in the 4th column"/>
  </inputs>
  <outputs>
    <data format="achri_annotated_snp_table" name="out_hgvs_annotated_table" type="data" label="Functionally annotated HGVS variant table"/>
  </outputs>

  <!-- the following code populates the dbSNP selection from the public dbSNP datasets available in the local Galaxy installation -->
  <code file="sift_datasets.py"/>
  <code file="polyphen_datasets.py"/>
  <code file="gerp_datasets.py"/>
  <code file="tissuedist_datasets.py"/>
  <!-- <code file="pseudogene_datasets.py"/>-->
  <code file="pathways_datasets.py"/>

  <tests>
  </tests>

  <help>
This tool reports several functional attributes, and potential for functional disturbance, based on genes that have declared sequence variants. 
These results can be used to help find the genetic cause of a clinical phenotype.
  </help>

</tool>