<tool id="plant_tribes_gene_family_classifier" name="GeneFamilyClassifier" version="1.0.0">
    <description>pipeline</description>
    <requirements>
        <requirement type="package" version="0.2">plant_tribes_gene_family_classifier</requirement>
    </requirements>
    <stdio>
        <!-- Anything other than zero is an error -->
        <exit_code range="1:" />
        <!-- In case the return code has not been set properly check stderr too -->
        <regex match="Error:" />
        <regex match="Exception:" />
    </stdio>
    <command>
        <![CDATA[
        #set create_ortho_sequences = str($options_type.options_type_selector) == 'advanced' and str($options_type.create_orthogroup_cond.create_orthogroup) == 'yes'
            #if create_ortho_sequences:
                #import os
                #set src_dir = $os.path.join('geneFamilyClassification_dir', 'orthogroups_fasta')
                #set dest_dir = $output.extra_files_path
                mkdir -p $dest_dir &&
            #end if
            GeneFamilyClassifier
            --proteins "$input"
            --scaffold "$scaffold"
            --method $method
            --classifier $classifier
            #if str($options_type.options_type_selector) == 'advanced':
                --super_orthogroups $options_type.super_orthogroups
                #if str($options_type.single_copy_cond) == 'taxa':
                    --single_copy_taxa $options_type.single_copy_cond.single_copy_taxa
                    --taxa_present $options_type.single_copy_cond.taxa_present
                #end if
                #if str($options_type.create_orthogroup_cond.create_orthogroup) == 'yes':
                    --orthogroup_fasta
                    --coding_sequences "$options_type.create_orthogroup_cond.coding_sequences"
                #end if
            #end if
            --scaffold_dir "${GALAXY_DATA_INDEX_DIR}/plant_tribes/scaffolds"
            --num_threads \${GALAXY_SLOTS:-4}
            #if create_ortho_sequences:
                echo "Sequences classified into pre-computed orthologous plant gene family clusters: `ls $src_dir | wc -l` files" > $output &&
                && mv $src_dir/* $dest_dir
            #end if
        ]]>
    </command>
    <inputs>
        <param name="input" format="fasta" type="data" label="Amino acids (proteins) sequences fasta file"/>
        <param name="scaffold" type="select" label="Orthogroups or gene families proteins scaffold">
            <options from_data_table="plant_tribes_scaffolds" />
            <validator type="no_options" message="No PlantTribes scaffolds are available.  Use the PlantTribes Scaffolds Download Data Manager tool to install and populate the PlantTribes scaffolds data table."/>
        </param>
        <param name="method" type="select" label="Protein clustering method">
            <option value="gfam" selected="true">GFam</option>
            <option value="orthofinder">OrthoFinder</option>
            <option value="orthomcl">OrthoMCL</option>
        </param>
        <param name="classifier" type="select" label="Protein classification method">
            <option value="blastp" selected="true">blastp</option>
            <option value="hmmscan">HMMScan</option>
            <option value="both">Both blastp and HMMScan</option>
        </param>
        <conditional name="options_type">
            <param name="options_type_selector" type="select" label="Options Configuration">
                <option value="basic" selected="true">Basic</option>
                <option value="advanced">Advanced</option>
            </param>
            <when value="basic" />
            <when value="advanced">
                <param name="super_orthogroups" type="select" label="SuperOrthogroups MCL clustering" help="blastp e-value matrix between all pairs of orthogroups">
                    <option value="min_evalue" selected="true">Minimum e-value</option>
                    <option value="avg_evalue">Average e-value</option>
                </param>
                <conditional name="single_copy_cond">
                    <param name="single_copy" type="select" label="Select single copy configuration">
                        <option value="custom" selected="true">Single copy orthogroup custom</option>
                        <option value="taxa">Minumum single copy taxa required in orthogroup</option>
                    </param>
                    <when value="custom" />
                    <when value="taxa">
                        <param name="single_copy_taxa" type="integer" value="20" label="Minumum single copy taxa required in orthogroup"/>
                        <param name="taxa_present" type="integer" value="21" label="Minumum taxa required in single copy orthogroup"/>
                    </when>
                </conditional>
                <conditional name="create_orthogroup_cond">
                    <param name="create_orthogroup" type="select" label="Create orthogroup fasta files?">
                        <option value="no" selected="true">No</option>
                        <option value="yes">Yes</option>
                    </param>
                    <when value="no" />
                    <when value="yes">
                        <param name="coding_sequences" format="fasta" type="data" label="Corresponding coding sequences (CDS) fasta file"/>
                    </when>
                </conditional>
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data name="output" format="txt" label="Sequences classified into gene family clusters on ${on_string}">
            <filter>options_type['options_type_selector'] == 'advanced' and options_type['create_orthogroup_cond']['create_orthogroup'] == 'yes'</filter>
        </data>
        <collection name="transcripts" type="list">
            <discover_datasets pattern="__name__" directory="geneFamilyClassification_dir" visible="false" ext="tabular" />
        </collection>
    </outputs>
    <tests>
        <test>
            <param name="input" value="" ftype="fasta" />
            <param name="prediction_method" value="transdecoder"/>
            <param name="target_gene_family_assembly" value="no"/>
            <param name="strand_specific" value="yes"/>
            <param name="dereplicate" value="yes"/>
            <param name="min_length" value="200"/>
            <output_collection name="orthos" type="list">

            </output_collection>
        </test>
    </tests>
    <help>
This tool is one of the PlantTribes' collection of automated modular analysis pipelines that utilize objective classifications of
complete protein sequences from sequenced plant genomes to perform comparative evolutionary studies. It performs gene family
classification of the post processed de novo transcripts using either blastp (faster), HMMScan (slower but more sensitive to remote
homologs) or both (more exhaustive).

-----

**Options**

 * **Orthogroups or gene families proteins scaffold** - PlantTribes scaffolds data.
 * **Protein clustering method** - One of GFam, OrthoFinder or OrthoMCL.
 * **Protein classification method** - One of blastp, HMMScan or both.
 * **SuperOrthogroups MCL clustering** - blastp e-value matrix between all pairs of orthogroups.
 * **Minumum single copy taxa required in orthogroup** - Used with "Minumum single copy taxa required in orthogroup" configuration only.
 * **Minumum taxa required in single copy orthogroup** - Used with "Minumum single copy taxa required in orthogroup" configuration only.
 * **Corresponding coding sequences (CDS) fasta file** - Used only when selecting "Create orthogroup fasta files?".
 
    </help>
    <citations>
            <citation type="bibtex">
                @unpublished{None,
                author = {None},
                title = {None},
                year = {None},
                eprint = {None},
                url = {None}
            }</citation>
    </citations>
</tool>