comparison pick_rep_set.xml @ 0:c1bd0c560018 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/qiime commit bcbe76277f3e60303faf826f8ce7f018bc663a9a-dirty

0:c1bd0c560018

<tool id="qiime_pick_rep_set" name="pick rep set" version="1.9.1galaxy1">
    <description>Pick representative set of sequences</description>
    
    <macros>
        <import>macros.xml</import>
    </macros>

    <expand macro="requirements" />

    <command>
<![CDATA[
        pick_rep_set.py 
            -i $input_file
            -m $rep_set_picking_method
            -s $sort_by
            #if str($fasta_file) != 'None':
             -f $fasta_file
            #end if
             -o $result_fp -l rep_set.log

            #if str($reference_seqs_fp) != 'None':
             -r $reference_seqs_fp
            #end if
]]>
    </command>

    <inputs>
        <param label="-i/--input_file: Path to input otu mapping file [REQUIRED]" name="input_file" optional="False" type="data"/>
        <param label="-f/--fasta_file: Path to input fasta file [REQUIRED if not picking against a reference set; default: None]" name="fasta_file" optional="True" type="data"/>
        <param label="-m/--rep_set_picking_method: Method for picking representative sets.  Valid choices are random, longest, most_abundant, first [default: first (first chooses cluster seed when picking otus with uclust)]" name="rep_set_picking_method" optional="True" type="select">
            <option value="random">random</option>
            <option value="longest">longest</option>
            <option value="most_abundant">most_abundant</option>
            <option value="first">first</option>
        </param>
        <param label="-s/--sort_by: sort by otu or seq_id [default: otu]" name="sort_by" optional="True" type="select">
            <option value="otu">otu</option>
            <option value="seq_id">seq_id</option>
        </param>
        <param label="-r/--reference_seqs_fp: collection of preferred representative sequences [default: None]" name="reference_seqs_fp" optional="True" type="data"/>
    </inputs>

    <outputs>
        <data format="fasta" name="result_fp" label="rep_set_seqs.fasta"/>
    </outputs>

    <tests>
        <test>
        </test>
    </tests>

    <help><![CDATA[
**How it does?**

After picking OTUs, you can then pick a representative set of sequences. For each OTU, you will end up with one sequence that can be used in subsequent analyses.

The output from pick_rep_set.py is a single FASTA file containing one sequence per OTU. The FASTA header lines will be the OTU identifier (from here on used as the unique sequence identifier) followed by a space, followed by the sequence identifier originally associated with the representative sequence. The name of the output FASTA file will be <input_sequences_filepath>_rep_set.fasta by default, or can be specified via the "-o" parameter.
]]>
    </help>

    <citations>
        <expand macro="citations" />
    </citations>
</tool>