<tool id="flair_collapse" name="FLAIR collapse" version="@TOOL_VERSION@" profile="20.01">
    <description>defines high-confidence isoforms from flair-corrected reads</description>

    <macros>
        <import>flair_macros.xml</import>
    </macros>

    <expand macro="requirements" />
    <expand macro="version_command" />

    <command detect_errors="exit_code"><![CDATA[

@PREPARE_REF@

ln -s '$input_query' query.bed &&

flair.py collapse

###########
## Input ##
###########

-q query.bed
-r '$input_reads'
-g reference.fa
-f '$input_gtf'

#if $input_promotors:
    -p '$input_promotors'
#end if

########################
## Additional Options ##
########################

-w $additional_options.window
-s $additional_options.support
$additional_options.stringent

#if str($additional_options.select_uniqueness):
    -n str($additional_options.select_uniqueness)
#end if

$additional_options.isoform
--max_ends $additional_options.maxends
$additional_options.trustends

#if str($additional_options.select_filter):
    -e str($additional_options.select_filter)
#end if

#########
## END ##
#########

    ]]></command>
    <inputs>
        <param name="input_query" argument="-q" type="data" format="bed" label="Corrected Reads as BED file"/>
        <param name="input_reads" argument="-r" type="data" format="fasta,fastq" label="FASTA/FASTQ file of raw reads"/>
        <expand macro="reference_interface" />
        <param name="input_gtf" argument="-f" type="data" format="gtf" label="GTF annotation file"/>
        <param name="input_promotors" optional="true" argument="-p" type="data" format="bed" label="Promotor BED file to identify full-length reads" />

        <!-- Additional Options -->
        <section name="additional_options" title="Additional Options">
            <param name="window" argument="-w" type="integer" min="1" value="100" label="Window Size" help="Window size for comparing TSS/TES (Default=100)" />
            <param name="support" argument="-s" type="integer" min="1" value="3" label="Supporting Reads" help="Minimum number of supporting reads for an isoform (Default=3)" />
            <param name="stringent" argument="--stringent" type="boolean" checked="false" truevalue="--stringent" falsevalue="" label="Use Stringent Mode" help="Specify if all supporting reads need to be full-length (80% coverage and spanning 25 bp of the first and last exons) (Default=false)"/>
            <param name="select_uniqueness" argument="-n" type="select" label="Choose the TSS/TES for each unique set of splice junction." >
                <option value="" selected="true">No Selection</option>
                <option value="none">Best TSSs/TESs</option>
                <option value="longest">Single TSS/TES chosen to maximize length</option>
                <option value="best_only">Single most supported TSS/TES used in conjunction chosen</option>
            </param>
            <param name="isoform" argument="-i" type="boolean" checked="false" truevalue="-i" falsevalue="" label="Use Isoform Mode" help="TSS/TES for each isoform will be determined from supporting reads for individual isoforms (Default=false)"/>
            <param name="maxends" argument="--max_ends" type="integer" min="0" value="2" label="Maximum Number of TSS/TES picked per isoform" help="(Default=2)" />
            <param name="trustends" argument="--trust_ends" type="boolean" checked="false" truevalue="--trust_ends" falsevalue="" label="Reads are generated from a long read method with minimal fragmentation?" />
            <param name="select_filter" argument="-e" type="select" label="Filter for isoforms." >
                <option value="" selected="true">No Filter</option>
                <option value="nosubset">Any isoforms that are a proper set of another isoform are removed</option>
                <option value="default">Subset isoforms are removed based on support</option>
                <option value="comprehensive">Default set + all subset isoforms</option>
                <option value="ginormous">Comprehensive set + single exon subset isoforms</option>
            </param>
            <param name="mapq" argument="--quality" type="integer" min="0" value="1" label="Minimum MAPQ of read assignment to an isoform" help="(Default=1)" />
        </section>

        <section name="additional_outputs" title="Output Options">
            <param name="out_format" type="select" multiple="true" optional="true" display="checkboxes" label="Data types">
                <option value="bed">BED</option>
                <option value="fasta">FASTA</option>
            </param>
        </section>
    </inputs>

    <outputs>
        <data name="outfile_isoforms_gtf" from_work_dir="flair.collapse.isoforms.gtf" format="gtf" label="${tool.name} on ${on_string}: Isoforms GTF" />
        <data name="outfile_isoforms_bed" from_work_dir="flair.collapse.isoforms.bed" format="bed" label="${tool.name} on ${on_string}: Isoforms BED">
            <filter>additional_outputs['out_format'] and 'bed' in additional_outputs['out_format']</filter>
        </data>
        <data name="outfile_isoforms_fasta" from_work_dir="flair.collapse.isoforms.fa" format="fasta" label="${tool.name} on ${on_string}: Isoforms FASTA">
            <filter>additional_outputs['out_format'] and 'fasta' in additional_outputs['out_format']</filter>
        </data>
    </outputs>

    <tests>
        <test expect_num_outputs="3">
            <param name="input_query" ftype="bed" value="flair_all_corrected.bed" />
            <param name="input_reads" ftype="fastq.gz" value="chrM.fastq.gz" />
            <param name="ref_selector_genome" value="history" />
            <param name="reffile" ftype="fasta" value="chrM.fa" />
            <param name="input_gtf" ftype="gtf" value="UCSC_Main_on_Human_knownGene_region_chrM.gtf" />
            <param name="out_format" value="bed,fasta" />
            <output name="outfile_isoforms_gtf" ftype="gtf" file="flair.collapse.isoforms.gtf" />
            <output name="outfile_isoforms_bed" ftype="bed" file="flair.collapse.isoforms.bed" />
            <output name="outfile_isoforms_fasta" ftype="fasta" file="flair.collapse.isoforms.fa" />
        </test>
        <!-- Test with cached genome -->
        <test expect_num_outputs="3">
            <param name="input_query" ftype="bed" value="flair_all_corrected.bed" />
            <param name="input_reads" ftype="fastq.gz" value="chrM.fastq.gz" />
            <param name="ref_selector_genome" value="cached" />
            <param name="reffile" value="chrM" />
            <param name="input_gtf" ftype="gtf" value="UCSC_Main_on_Human_knownGene_region_chrM.gtf" />
            <param name="out_format" value="bed,fasta" />
            <output name="outfile_isoforms_gtf" ftype="gtf" file="flair.collapse.isoforms.gtf" />
            <output name="outfile_isoforms_bed" ftype="bed" file="flair.collapse.isoforms.bed" />
            <output name="outfile_isoforms_fasta" ftype="fasta" file="flair.collapse.isoforms.fa" />
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

**What it does**

-------------------

@description@

**flair collapse**
Defines high-confidence isoforms from corrected reads.

-------------------

**Inputs**

-------------------

(1) Corrected Reads as Bed12 File.
(2) FASTA/FASTQ file of raw reads. All raw read fastq/fasta files should be concatenated into a single file.
(3) FASTA of Reference Genome.
(4) GTF annotation file.
(5) Promoter regions bed file to identify full-length reads.

-----------

**Outputs**

-----------

Outputs the high-confidence isoforms in several formats:
(1) bed,
(2) gtf,
(3) FASTA.

--------------------

**More Information**

--------------------

See the excellent `FLAIR documentation`_

.. _`FLAIR documentation`: https://github.com/BrooksLabUCSC/flair


--------------------

**Galaxy Wrapper Development**

--------------------

@citation@

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