annotate fasta_merge_files_and_filter_unique_sequences.xml @ 2:379c41d859aa draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/fasta_merge_files_and_filter_unique_sequences commit 240d1baaa04767c7d6ad6e36c854c2b54093e92f

<tool id="fasta_merge_files_and_filter_unique_sequences" name="FASTA Merge Files and Filter Unique Sequences" version="1.1">
    <description>Concatenate FASTA database files together</description>
    <requirements>
        <requirement type="package" version="2.7.12">python</requirement>
    </requirements>
    <command>
        python '$__tool_directory__/fasta_merge_files_and_filter_unique_sequences.py'
        '$output' $uniqueness_criterion
        #for $input in $inputs:
            '$input'
        #end for
    </command>
    <inputs>
        <param name="inputs" format="fasta" multiple="True" type="data" label="Input FASTA files"/>
        <param name="uniqueness_criterion" type="select" label="How are sequences judged to be unique?">
            <option value="sequence" selected="true">Accession and Sequence</option>
            <option value="accession">Accession Only</option>
        </param>
    </inputs>
    <outputs>
        <data format="fasta" name="output" label="Merged and Filtered FASTA from ${on_string}"/>
    </outputs>
    <tests>
        <test>
          <param name="inputs" value="1.fa,2.fa" ftype="fasta" />
          <param name="uniqueness_criterion" value="sequence" />
          <output name="output" file="res-sequence.fa" ftype="fasta" />
          <assert_stdout>
            <has_line line="Skipping protein '&gt;one_2' with duplicate sequence (first seen as '&gt;one')" />
            <has_line line="Skipping protein '&gt;two_2' with duplicate sequence (first seen as '&gt;two')" />
            <has_line line="Skipping protein '&gt;three_2' with duplicate header" />
          </assert_stdout>
        </test>
        <test>
          <param name="inputs" value="1.fa,2.fa" ftype="fasta" />
          <param name="uniqueness_criterion" value="accession" />
          <output name="output" file="res-accession.fa" ftype="fasta" />
          <assert_stdout>
            <has_line line="Skipping protein '&gt;three_2' with duplicate header" />
          </assert_stdout>
        </test>
    </tests>
    <help>
<![CDATA[
**What it does**

Concatenate FASTA database files together.

If the uniqueness criterion is "Accession and Sequence", only the first appearence of each unique sequence will appear in the output.
Otherwise, duplicate sequences are allowed, but only the first appearance of each accession will appear in the output.

In the context of this script, the accession is the entire header line.

------

**Citation**

If you use this tool in Galaxy, please the GalaxyP developers at: https://github.com/galaxyproteomics/

]]>
    </help>
</tool>