annotate bicodon_counts_from_fasta.xml @ 0:e13169dca7c8 draft default tip

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/naltorfs/ commit cbedf7b5968b45a08df88d4ad799951d6f50a2bd"

<tool id="bicodon_counts_from_fasta" name="Get Codon and Bicodon frequency" version="@TOOL_VERSION@" profile="20.05">
    <description>from FASTA files</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="edam_ontology"/>
    <expand macro="requirements"/>
    <version_command>bicodon_counts_from_fasta.py --version</version_command>
    <command detect_errors="exit_code"><![CDATA[
        bicodon_counts_from_fasta.py
            #if $ref.ref_source == 'cached':
                --seq '${ref.ref_loc.fields.path}'
            #elif $ref.ref_source == 'history':
                --seq '${ref.ref_file}'
            #end if

            --taxid '$taxid'

            --organelle '$organelle'

            --division '$division'

            --assembly '$assembly'

            --species '$species'

            --translation_table '$translation_table'

            --codon_out '$codon_out'

            --bicodon_out '$bicodon_out'
    ]]></command>
    <inputs>
        <conditional name="ref">
            <param name="ref_source" type="select" label="Source for Sequence Data">
                <option value="cached">Locally cached FASTA</option>
                <option value="history" selected="True">History dataset FASTA</option>
            </param>
            <when value="cached">
                <param argument="--seq" name="ref_loc" type="select" label="Select FASTA nucleotide sequences">
                    <options from_data_table="all_fasta"/>
                </param>
            </when>
            <when value="history">
                <param argument="--seq" name="ref_file" type="data" format="fasta" label="FASTA nucleotide sequences"/>
            </when>
        </conditional>
        <param argument="--taxid" type="text" value="9606" label="Taxonomy ID to list in output" help="9606 is Homo sapiens (human)"/>
        <param argument="--organelle" type="text" value="genomic" label="Organelle to list in output" help="genomic is default"/>
        <param argument="--division" type="text" value="custom" label="Division to list in output" help="custom is default"/>
        <param argument="--assembly" type="text" value="hg38" label="Assembly to list in output" help="hg38 is default"/>
        <param argument="--species" type="text" value="Homo sapiens" label="Species to list in output" help="Homo sapiens is default"/>
        <expand macro="translation_table_select_parameter"/>
    </inputs>
    <outputs>
        <data name="codon_out" format="tabular" label="Get Codon and Bicodon frequency on ${on_string}: #if $ref.ref_source == 'cached' then $ref.ref_loc.fields.name else $ref.ref_file.name# codon usage output"/>
        <data name="bicodon_out" format="tabular" label="Get Codon and Bicodon frequency on ${on_string}: #if $ref.ref_source == 'cached' then $ref.ref_loc.fields.name else $ref.ref_file.name# bicodon usage"/>
    </outputs>
    <tests>
        <test>
            <conditional name="ref">
                <param name="ref_source" value="history"/>
                <param name="ref_file" value="naltorfs_fasta_out.fasta" dbkey="hg38" ftype="fasta"/>
            </conditional>
            <param name="taxid" value="9606"/>
            <param name="organelle" value="genomic"/>
            <param name="division" value="custom"/>
            <param name="assembly" value="hg38"/>
            <param name="species" value="Homo sapiens"/>
            <param name="translation_table" value="1"/>
            <output name="codon_out" value="codon_out.tabular"/>
            <output name="bicodon_out" value="bicodon_out.tabular"/>
        </test>
    </tests>
    <help><![CDATA[
Calculate Codon and Bicodon (Codon Pair) usage frequency from FASTA files.

Output is designed to mimic that from CoCoPUTs (https://dnahive.fda.gov/dna.cgi?cmd=codon_usage&id=537&mode=cocoputs; e.g. https://dnahive.fda.gov/dna.cgi?cmd=objFile&ids=537&filename=Refseq_Bicod.tsv&raw=1).

Translation table identifiers are based upon NCBI standards (https://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi).

Example of CoCoPUTs style codon output, the majority of codons have been removed in this example, for brevity:

  +-----------+-----------+-------+--------------+-----------+-------------------+-------+----------+-----+-----+-----+-----+-----+
  | Division  | Assembly  | Taxid | Species      | Organelle | Translation Table | # CDS | # Codons | aaa | aac | aag | aat | ... |
  +===========+===========+=======+==============+===========+===================+=======+==========+=====+=====+=====+=====+=====+
  | custom    | hg38      | 9606  | Homo sapiens | genomic   | 1                 | 4     | 859      | 14  | 13  |  29 | 8   | ... |
  +-----------+-----------+-------+--------------+-----------+-------------------+-------+----------+-----+-----+-----+-----+-----+

Example of CoCoPUTs style bicodon output, the majority of bicodons (codon pairs) have been removed in this example, for brevity:

  +-----------+-----------+-------+--------------+-----------+-------------------+-------+---------------+--------+--------+--------+--------+-----+
  | Division  | Assembly  | Taxid | Species      | Organelle | Translation Table | # CDS | # Codon Pairs | aaaaaa | aaaaac | aaaaag | aaaaat | ... |
  +===========+===========+=======+==============+===========+===================+=======+===============+========+========+========+========+=====+
  | custom    | hg38      | 9606  | Homo sapiens | genomic   | 1                 | 4     | 859           | 0      | 0      |     0  | 1      | ... |
  +-----------+-----------+-------+--------------+-----------+-------------------+-------+---------------+--------+--------+--------+--------+-----+
    ]]></help>
    <expand macro="citations"/>
</tool>