annotate peptide_to_gff.xml @ 0:cec60c540546

Uploaded

<tool id="peptide_to_gff" name="Peptide to GFF" version="1.0">
  <description>Map peptide to reference genome</description>
  <requirements>
    <requirement type="package">kent_tools</requirement>
    <requirement type="package" version="master">peptide_to_gff</requirement>
  </requirements>
  <command>peptide_to_gff
    #if $peptide_src.inputFormat == 'protein_pilot' or $peptide_src.inputFormat == 'tabular':
      --skip_lines $peptide_src.input_file.metadata.comment_lines
      --input $peptide_src.input_file
      --peptide_column $peptide_src.peptide_col
      --accession_column $peptide_src.accession_col
    #end if
    #for $ref in $ref_mappings:
      #if $ref.mapping.ref_selector =='cdna_gtf':
        --cdna_fasta $ref.mapping.seqs
        --cdna_gtf $ref.mapping.feature_ref
      #elif $ref.mapping.ref_selector =='cdna_ref':
        --cdna_fasta $ref.mapping.seqs
        #if $ref.mapping.genome.ref_src == 'indexed':
          --reference $ref.mapping.genome.reference.fields.path
        #else :
          --reference $ref.mapping.genome.reference
        #end if
      #elif $ref.mapping.ref_selector =='cds_gff':
        --cds_fasta $ref.mapping.seqs
        --cds_gff $ref.mapping.feature_ref
      #elif $ref.mapping.ref_selector =='eej':
        --cdna_gtf $ref.mapping.feature_ref
      #end if
    #end for
    #if $show_unmapped:
      --unmapped $unmapped
    #end if
    --output $output_gff
  </command>
  <inputs>
    <conditional name="peptide_src" >
      <param name="inputFormat" type="select" label="Peptide Source Format">
        <option value="protein_pilot">Protein Pilot Tabular</option>
        <option value="tabular">Generic Tabular (with peptide and accession columns)</option>
        <!--  future formats -->
      </param>
      <when value="protein_pilot">
        <param name="input_file" type="data" format="tabular" label="Source File"
               help="A tabular file that contains a peptide in a column and a accession name in another column."/>
        <param name="peptide_col" type="hidden" value="13" label="Peptide Column"/>
        <param name="accession_col" type="hidden" value="7" label="Accession Identifier Column"/>
        <!--
        <param name="info_cols" type="data_column" data_ref="input_file" label="Columns to include in the GTF INFO" multiple="true" optional="true"/>
        -->
      </when>
      <when value="tabular">
        <param name="input_file" type="data" format="tabular" label="Source File"
               help="A tabular file that contains a peptide in a column and a accession name in another column."/>
        <param name="peptide_col" type="data_column" data_ref="input_file" label="Peptide Column"/>
        <param name="accession_col" type="data_column" data_ref="input_file" label="Accession Identifier Column"/>
        <!--
        <param name="info_cols" type="data_column" data_ref="input_file" label="Columns to include in the GTF INFO" multiple="true" optional="true"/>
        -->
      </when>
    </conditional>
    <repeat name="ref_mappings" title="Sequence and Feature References for mapping the peptides" min="1" help="" >
      <conditional name="mapping" >
        <param name="ref_selector" type="select" label="Select Peptide Mapping File Formats">
          <option value="cdna_gtf">cdna sequence with GTF feature reference (Ensembl)</option>
          <option value="cdna_ref">cdna sequence with genome sequence reference (ECgene)</option>
          <option value="cds_gff">protein sequence with GFF feature reference (Augustus)</option>
          <!-- Eventually may want to include putative exon-exon junctions 
          <option value="eej">putative exon exon junctions</option>
          -->
        </param>
        <when value="cdna_gtf">
          <param name="seqs" type="data" format="fasta" label="CDNA Transcripts Fasta"
               help="Example: ftp://ftp.ensembl.org/pub/release-71/fasta/homo_saPiens/cdna/Homo_sapiens.GRCh37.71.cdna.all.fa.gz"/>
          <param name="feature_ref" type="data" format="gtf" label=" GTF feature file for the cdna transcipts"
               help="Example: ftp://ftp.ensembl.org/pub/release-71/gtf/homo_sapiens/Homo_sapiens.GRCh37.71.gtf.gz"/>
        </when>
        <when value="cdna_ref">
          <param name="seqs" type="data" format="fasta" label="CDNA Transcripts Fasta"
               help="Example: http://genome.ewha.ac.kr/ECgene/download/hg18/hg18_b1_low_fasta.txt.gz"/>
          <conditional name="genome">
            <param name="ref_src" type="select" label="Reference Genome Source for mapping">
              <option value="indexed">Use a built-in index</option>
              <option value="history">Use one in your history </option>
            </param>
            <when value="indexed">
              <param name="reference" type="select" label="Genome Reference">
                <options from_data_table="all_fasta">
                </options>
              </param>
            </when>
            <when value="history">
              <param name="reference" type="data" format="fasta" label="Reference Genome Fasta"/>
            </when>
          </conditional>
        </when>
        <when value="cds_gff">
          <param name="seqs" type="data" format="fasta" label="Protein Sequence Fasta"
               help="Example: http://gbi.agrsci.dk/pig/sscrofa10_2_annotation/ssc10.2.RNA.hints.augustus.gff.prot.faa.gz"/>
          <param name="feature_ref" type="data" format="gff3,gtf" label="GFF Feature file for the Protein Sequences"
               help="Example: http://gbi.agrsci.dk/pig/sscrofa10_2_annotation/ssc10.2.RNA.hints.augustus.gff.gz"/>
        </when>
        <!-- Eventually may want to include putative exon-exon junctions 
        <when value="eej">
          <param name="feature_ref" type="data" format="gtf" label=" The Ensembl GTF feature file corresponding to the EEJ build"
               help="Example: ftp://ftp.ensembl.org/pub/release-71/gtf/homo_sapiens/Homo_sapiens.GRCh37.71.gtf.gz"/>
        </when>
        -->
      </conditional>
    </repeat>
    <param name="show_unmapped" type="boolean" truevalue="yes" falsevalue="no" checked="False" label="Show unmapped lines"/>
  </inputs>
  <outputs>
    <data format="gff3" metadata_source="input_file" name="output_gff" />
    <data format_source="input_file" metadata_source="input_file" name="unmapped">
      <filter>show_unmapped == True</filter>
    </data>
  </outputs>
  <stdio>
    <exit_code range="1:"  level="fatal"   description="Bad input dataset" />
  </stdio>
  <tests>
   <test>
     <param name="inputFormat" value="protein_pilot"/>
     <param name="input_file" value="ProtData.tsv" ftype="tabular"/>
     <!--
     <param name="info_cols" value=""/>
     -->
     <param name="ref_selector" value="cdna_gtf"/>
     <param name="seqs" value="GRCh37.69.cdna.19.fa" ftype="fasta"/>
     <param name="feature_ref" value="Homo_sapiens.GRCh37_19.71.gtf" ftype="gtf"/>
     <param name="show_unmapped" value="False"/>
     <output name="output_gff" file="ProtData.gff3" ftype="gff3"/>
   </test>
   <!-- These values work when entered into a history, but aren't handled correctly by the function test environment.
   <test>
     <param name="inputFormat" value="protein_pilot"/>
     <param name="input_file" value="ProtData.tsv" ftype="tabular"/>
     <param name="ref_selector" value="cdna_ref"/>
     <param name="seqs" value="GRCh37.69.cdna.19.fa" ftype="fasta"/>
     <param name="ref_src" value="history"/>
     <param name="reference" value="Homo_sapiens.GRCh37.71.dna.chromosome.19.fa" ftype="fasta"/>
     <param name="show_unmapped" value="False"/>
     <output name="output_gff" file="ProtData.gff3" ftype="gff3"/>
   </test>
   -->

  </tests>
  <help>
**Peptide to GFF**

Maps peptide sequences that have a known transcript or protein-coding sequence to a reference genome.

Inputs:

  - A tabular file that contains a peptide column and a sequence accession column. 

  - One or more fasta files of transcript or protein sequences that match the accession column entries

  - Either GTF, GFF, or a genome reference fasta for mapping the accession sequences to the genome. 

Output:
 
  - A GFF3 file with that gives the mapping of the peptide to the reference genome

  - Optionally, a dataset with the unmapped lines from the input file.
  
  </help>
</tool>