<tool id="qiime_pick_rep_set" name="Pick representative set of sequences" version="@WRAPPER_VERSION@.0">
    <description></description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <version_command>pick_rep_set.py --version</version_command>
    <command detect_errors="aggressive"><![CDATA[
        pick_rep_set.py
            --input_file '$input_file'
            #if $picking.type == "de_novo"
                --fasta_file '$picking.fasta_file'
            #else if $picking.type == "preferred"
                --reference_seqs_fp '$picking.reference_seqs_fp'
                #if $picking.fasta_file
                    --fasta_file '$picking.fasta_file'
                #end if
            #end if
            --rep_set_picking_method '$rep_set_picking_method'
            --sort_by '$sort_by'
            --result_fp '$result_fp'
            --log_fp '$log_fp'
    ]]></command>
    <inputs>
        <param argument="--input_file" type="data" format="txt" label="Input OTU mapping file"/>
        <conditional name="picking">
            <param name="type" type="select" label="Type of OTU picking">
                <option value="de_novo">Picking a representative set for de novo-picked OTUs</option>
                <option value="preferred">Picking OTUs with "preferred representative" sequence</option>
            </param>
            <when value="de_novo">
                <param argument="--fasta_file" type="data" format="fasta" label="Input fasta file with all of the sequences whose identifiers are listed in the OTU map"/>
            </when>
            <when value="preferred">
                <param argument="--reference_seqs_fp" type="data" format="fasta" label="Collection of preferred representative sequences "/>
                <param argument="--fasta_file" type="data" format="fasta" optional="True" label="Input fasta file with all of the sequences whose identifiers are listed in the OTU map" help="If new clusters were allowed"/>
            </when>
        </conditional>
        <param argument="--rep_set_picking_method" type="select" label="Method for picking representative sets">
            <option value="random">random</option>
            <option value="longest">longest</option>
            <option value="most_abundant">most_abundant</option>
            <option value="first" selected="true">first (chooses cluster seed when picking otus with uclust)</option>
        </param>
        <param argument="--sort_by" type="select" label="Sorting by">
            <option value="otu" selected="true">OTU</option>
            <option value="seq_id">Sequence id</option>
        </param>
    </inputs>
    <outputs>
        <data format="fasta" name="result_fp" label="${tool.name} on ${on_string}: Representative sequences"/>
        <data format="txt" name="log_fp" label="${tool.name} on ${on_string}: Log"/>
    </outputs>
    <tests>
        <test>
            <param name="input_file" value="pick_rep_set/seqs_otus.txt"/>
            <param name="type" value="de_novo"/>
            <param name="fasta_file" value="pick_rep_set/seqs.fna"/>
            <param name="rep_set_picking_method" value="first"/>
            <param name="sort_by" value="otu"/>
            <output name="result_fp" file="pick_rep_set/first_otu_fasta.fasta"/>
            <output name="log_fp">
                <assert_contents>
                    <has_text text="GenericRepSetPicker"/>
                    <has_text text="Algorithm:first"/>
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="input_file" value="pick_rep_set/seqs_otus.txt"/>
            <param name="type" value="preferred"/>
            <param name="fasta_file" value="pick_rep_set/seqs.fna"/>
            <param name="reference_seqs_fp" value="pick_rep_set/refseqs.fasta"/>
            <param name="rep_set_picking_method" value="first"/>
            <param name="sort_by" value="otu"/>
            <output name="result_fp" file="pick_rep_set/first_otu_fasta_ref.fasta"/>
            <output name="log_fp">
                <assert_contents>
                    <has_text text="ReferenceRepSetPicker"/>
                    <has_text text="Algorithm:first"/>
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="input_file" value="pick_rep_set/seqs_otus.txt"/>
            <param name="type" value="de_novo"/>
            <param name="fasta_file" value="pick_rep_set/seqs.fna"/>
            <param name="rep_set_picking_method" value="longest"/>
            <param name="sort_by" value="otu"/>
            <output name="result_fp" file="pick_rep_set/longest_otu_fasta.fasta"/>
            <output name="log_fp">
                <assert_contents>
                    <has_text text="GenericRepSetPicker"/>
                    <has_text text="Algorithm:longest"/>
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="input_file" value="pick_rep_set/seqs_otus.txt"/>
            <param name="type" value="de_novo"/>
            <param name="fasta_file" value="pick_rep_set/seqs.fna"/>
            <param name="rep_set_picking_method" value="most_abundant"/>
            <param name="sort_by" value="otu"/>
            <output name="result_fp" file="pick_rep_set/most_abundant_otu_fasta.fasta"/>
            <output name="log_fp">
                <assert_contents>
                    <has_text text="GenericRepSetPicker"/>
                    <has_text text="Algorithm:most_abundant"/>
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="input_file" value="pick_rep_set/seqs_otus.txt"/>
            <param name="type" value="de_novo"/>
            <param name="fasta_file" value="pick_rep_set/seqs.fna"/>
            <param name="rep_set_picking_method" value="random"/>
            <param name="sort_by" value="otu"/>
            <output name="result_fp">
                <assert_contents>
                    <has_text text="1 PC.636_263"/>
                    <has_text text="101 PC.634_99"/>
                </assert_contents>
            </output>
            <output name="log_fp">
                <assert_contents>
                    <has_text text="GenericRepSetPicker"/>
                    <has_text text="Algorithm:random"/>
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="input_file" value="pick_rep_set/seqs_otus.txt"/>
            <param name="type" value="de_novo"/>
            <param name="fasta_file" value="pick_rep_set/seqs.fna"/>
            <param name="rep_set_picking_method" value="first"/>
            <param name="sort_by" value="seq_id"/>
            <output name="result_fp" file="pick_rep_set/first_seq_id_fasta.fasta"/>
            <output name="log_fp">
                <assert_contents>
                    <has_text text="GenericRepSetPicker"/>
                    <has_text text="Algorithm:first"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
**What 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>