<tool id="pipmir" name="PIPmiR PIPELINE" version="0.1.0">

    <description>a method to identify novel plant miRNA</description>

    <requirements>
        <!-- conda dependency -->
        <requirement type="package" version="1.1">pipmir</requirement>
        <requirement type="package" version="324">ucsc-fatotwobit</requirement>
    </requirements>

    <command>
<![CDATA[

    #if $refGenomeSource.genomeSource == "history":
        faToTwoBit '$refGenomeSource.ownFile' ownFile.2bit
        &&
    #end if

    samtools sort

    ## output in BAM format
    -O BAM

    ## output file name
    -o test_sorted.bam

    '$input_bam'

    &&
    samtools index test_sorted.bam test_sorted.bai

    ## the tool requires the location of RNAfold binary
    &&
    RNAfold_location=\$(which RNAfold)

    &&
    PIPmiR PIPELINE

    -a test_sorted.bam

    ## genome source
    #if $refGenomeSource.genomeSource == "history":
        -t ownFile.2bit
    #else
        -t '$refGenomeSource.builtin.fields.path'
    #end if

    -o test

    ## optional parameters
    #if $params.settingsType == "custom":
        ## default: 50
        -l $params.min_precursor

        ## default: 500
        -L $params.max_precursor

        ## default: 2
        -s $params.step_size

        ## default: 10
        -m $params.min_read
    #end if

    ## default: 1
    -p \${GALAXY_SLOTS:-1}

    -R \$RNAfold_location

]]>
    </command>
    <inputs>
        <param name="input_bam" type="data"
            format="sam,bam" label="Alignment"
            help="The bam or sam file containing alignment of the read data."/>

        <!-- Genome source. -->
        <conditional name="refGenomeSource">
            <param name="genomeSource" type="select"
                label="Will you select a reference genome from your
                history or use a built-in genome?"
                help="The version of genome against which the reads were aligned.">
                <option value="2bit" selected="True">
                    Use a built-in genome</option>
                <option value="history">
                    Use a genome from my current history</option>
            </param>
            <when value="2bit">
            <param name="builtin" type="select"
                label="Select a reference genome">
                <options from_data_table="lastz_seqs">
                    <filter type="sort_by" column="1" />
                    <validator type="no_options"
                    message="A built-in reference genome is not available
                    for the build associated with the selected input file"/>
                </options>
            </param>
            </when>
            <when value="history">
                <param name="ownFile" type="data" format="fasta"
                label="Select the reference genome" />
            </when>
        </conditional>

        <!-- optional parameters -->
        <conditional name="params">
            <param name="settingsType" type="select"
                label="Optional parameters"
                help="You can use the default settings or
                set custom values for any of pipmir's parameters.">
              <option value="default">Use defaults</option>
              <option value="custom">Full parameter list</option>
            </param>
            <when value="default" />
            <!-- Full/advanced params. -->
            <when value="custom">
                <param name="min_precursor" type="integer"
                    value="50" label="Minimum size"
                    help="Minimum size of a precursor sequence (Default: 50)">
                    <validator type="in_range"
                        message="Minimum allowed value is 1" min="1"/>
                </param>

                <param name="max_precursor" type="integer"
                    value="500" label="Maximum size"
                    help="Maximum size of a precursor sequence (Default: 500)">
                    <validator type="in_range"
                        message="Minimum allowed value is 1" min="1"/>
                </param>

                <param name="step_size" type="integer"
                    value="2" label="Step size"
                    help="The step size used to identifiy the precursor
                    from the minimum to the maximum possible
                    size of precursor (Default: 2)">
                    <validator type="in_range"
                        message="Minimum allowed value is 1" min="1"/>
                </param>

                <param name="min_read" type="integer"
                    value="10" label="Minimum read count"
                    help="Minimum read count for a mature to be
                    considered expressed (Default: 10)">
                    <validator type="in_range"
                        message="Minimum allowed value is 1" min="1"/>
                </param>
            </when>  <!-- full -->
        </conditional>
    </inputs>
    <outputs>
        <data name="putativeMatures" format="bed"
        from_work_dir="test_putativeMatures.bed"
        label="${tool.name} on ${on_string}: putative mature miRNAs"/>

        <data name="predictedPrecursors" format="txt"
        from_work_dir="test_predictedPrecursors.txt"
        label="${tool.name} on ${on_string}: predicted precursor"/>

        <data name="predicted_miRNA" format="txt"
        from_work_dir="test_predicted_miRNAs.txt"
        label="${tool.name} on ${on_string}: predicted miRNAs"/>
    </outputs>
    <tests>
        <test>
            <param name="input_bam" value="Aligned.out.sam" ftype="sam" />
            <param name="genomeSource" value="history" />
            <param name="ownFile" value="test_seq.fa" />
            <param name="settingsType" value="custom" />
            <param name="step_size" value="10" />
            <output name="putativeMatures" file="test_putativeMatures.bed"
            ftype="bed"/>
            <output name="predictedPrecursors" file="test_predictedPrecursors.txt"
            ftype="txt"/>
            <output name="predicted_miRNA" file="test_predicted_miRNAs.txt"
            ftype="txt"/>
        </test>
    </tests>
    <help>
<![CDATA[
.. class:: infomark

**What it does**

`pipmir`_ is an algorithm to identify novel plant miRNA genes from a combination
of deep sequencing data and genomic features.

.. _pipmir: https://ohlerlab.mdc-berlin.de/software/Pipeline_for_the_Identification_of_Plant_miRNAs_84/

.. class:: infomark

**Optional parameters**

Minimum size
 * The MINIMUM size the precursor predictor can search.
 * 50 is recommended (and is the default).

Maximum size
 * The MAXIMUM size the precursor predictor can search.

 * The larger you make this, the longer PIPmiR will take as folding time is exponential with increased size.

 * 500 is what was used in the manuscript and will include almost all currently known Arabidopsis Thaliana miRNAs.

 * 300 is a limit that will include most known miRNAs and still have a reasonable search time.

Step size
 * The step size used to identify the precursor from the minimum to the maximum possible size of a precursor.

 * Increasing this value will speed up the precursor prediction step but limit the number of possible precursor sequences.

 * 2 is the default and is what was used in the manuscript, however 5 still works well enough, and is only slightly less accurate

.. class:: infomark

**Outputs**

A `bed`_ file of putative mature miRNAs
 * 'name' column = an arbitrary name given to the putative mature
 * 'score' column = the read count

 .. _bed: https://genome.ucsc.edu/FAQ/FAQformat#format1

A text file of predicted precursors
 * Form: Chromosome,Strand,Precursor_Start,Precursor_End,Sequence,Fold_Structure,Normalized_Minimum_Free_Energy,Mature_miRNA_Location

 * Chromosome = chromosome that the precursor is on

 * Strand = strand that the precursor is on

 * Precursor_Start = start nucleotide (1 based) of the precursor

 * Precursor_End = last nucleotide (1 based, inclusive) of the precursor

 * Sequence = sequence of the precursor

 * Fold_Structure = dot-bracket notation of the precursor fold centroid secondary structure (generated from RNAfold -p -d2 -noLP -noPS)

 * Normalized_Minimum_Free_Energy = minimum free energy of the centroid structure divided by the length of the sequence

 * Mature_miRNA_location = name & location of the mature miRNA within the precursor sequence

A text file of predicted miRNAs
 * This file will contain the miRNAs that had a positive classifier score, meaning that PIPmiR believes that they may be novel miRNA genes.

 * This file contains the genomic coordinates of the predicted precursor as well as for the mature and star sequences.

 * The file also contains the precursor sequence and the dot-bracket notation of its secondary structure.
]]></help>
    <citations>
        <citation type="doi">10.1101/gr.123547.111</citation>
    </citations>
</tool>