<tool id="stringtie_merge" name="StringTie" version="0.1.0">
    <description>merge transcripts</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="stdio" />
    <expand macro="version_command" />
    <command>
    <![CDATA[
        stringtie --merge
        -p \${GALAXY_SLOTS:-1}
        #if $guide_gff:
            -G "$guide_gff"
        #end if
        -m $min_len
        -c $min_cov
        -F $min_fpkm
        -T $min_tpm
        -f $min_iso
        -g $gap_len
        $keep_introns
        #set inputs = '" "'.join(str($input_gtf).split(','))
        -o $out_gtf "$inputs"
    ]]>
    </command>
    <inputs>
        <param type="data" name="input_gtf" multiple="True" format="gtf,gff3" />
        <param type="data" name="guide_gff" optional="True" format="gtf,gff3" />
        <param argument="-m" type="integer" name="min_len" value="50" help="Minimum input transcript length to include in the merge" />
        <param argument="-c" type="integer" name="min_cov" value="0" help="Minimum input transcript coverage to include in the merge" />
        <param argument="-F" type="float" name="min_fpkm" value="1.0" help="Minimum input transcript FPKM to include in the merge" />
        <param argument="-T" type="float" name="min_tpm" value="1.0" help="Minimum input transcript TPM to include in the merge" />
        <param argument="-f" type="float" name="min_iso" value="0.01" help="Minimum isoform fraction" />
        <param argument="-g" type="integer" name="gap_len" value="250" help="Gap between transcripts to merge together" />
        <param argument="-i" type="boolean" truevalue="-i" falsevalue="" name="keep_introns" help="Keep merged transcripts with retained introns" />
    </inputs>
    <outputs>
        <data name="out_gtf" format="gtf" />
    </outputs>
    <tests>
        <test>
            <param ftype="gtf" name="input_gtf" value="stringtie_out1.gtf,stringtie_out2.gtf,stringtie_out3.gtf,stringtie_out4.gtf" />
            <param ftype="gtf" name="guide_gff" value="stringtie_in.gtf" />
            <output file="stringtie_merge_out1.gtf" ftype="gtf" lines_diff="2" name="out_gtf" />
        </test>
        <test>
            <param ftype="gtf" name="input_gtf" value="stringtie_merge_in1.gtf,stringtie_merge_in2.gtf" />
            <param ftype="gtf" name="guide_gff" value="stringtie_merge_in3.gtf" />
            <output file="stringtie_merge_out2.gtf" ftype="gtf" lines_diff="2" name="out_gtf" />
        </test>
        <test>
            <param ftype="gtf" name="input_gtf" value="stringtie_merge_in1.gtf,stringtie_merge_in2.gtf" />
            <output ftype="gtf" name="out_gtf">
                <assert_contents>
                    <has_text text="stringtie --merge" />
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[

**What it does?**

This is a special usage mode of StringTie_, distinct from the assembly usage mode. In the merge mode, StringTie takes as input a list of GTF/GFF files and merges/assembles these transcripts into a non-redundant set of transcripts. This mode is used in the new differential analysis pipeline to generate a global, unified set of transcripts (isoforms) across multiple RNA-Seq samples. 

If a reference annotation is provided, StringTie will assemble the transfrags from the input GTF files with the reference transcripts. 

.. _StringTie: http://ccb.jhu.edu/software/stringtie/

------

StringTie --merge has the following options::

  -G <guide_gff>   reference annotation to include in the merging (GTF/GFF3)
  -o <out_gtf>     output file name for the merged transcripts GTF
                    (default: stdout)
  -m <min_len>     minimum input transcript length to include in the merge
                    (default: 50)
  -c <min_cov>     minimum input transcript coverage to include in the merge
                    (default: 0)
  -F <min_fpkm>    minimum input transcript FPKM to include in the merge
                    (default: 1.0)
  -T <min_tpm>     minimum input transcript TPM to include in the merge
                    (default: 1.0)
  -f <min_iso>     minimum isoform fraction (default: 0.01)
  -g <gap_len>     gap between transcripts to merge together (default: 250)
  -i               keep merged transcripts with retained introns; by default
                   these are not kept unless there is strong evidence for them
  -l <label>       name prefix for output transcripts (default: MSTRG)
    ]]></help>
    <expand macro="citations" />
</tool>