<tool id="stringtie" name="StringTie" version="1.3.3">
    <description>transcript assembly and quantification</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="stdio" />
    <expand macro="version_command" />
    <command><![CDATA[
        mkdir -p ./special_de_output/sample1/ &&
        #if str($guide.use_guide) == 'yes':
            ln -s '$guide.guide_gff' ./special_de_output/sample1/guide.gtf &&
        #end if

        #if $input_bam.metadata.ftype == 'sam':
            samtools sort -@ \${GALAXY_SLOTS:-1} '$input_bam' | stringtie
        #else
            stringtie '$input_bam'
        #end if

        -o "$output_gtf"
        -p "\${GALAXY_SLOTS:-1}"
        #if str($guide.use_guide) == 'yes':
            -C '$coverage'
            -G '$guide.guide_gff'
            $guide.input_estimation
            #if $guide.special_outputs != 'no':
                -b ./special_de_output/sample1/
            #end if
        #end if
        #if str($option_set.options) == 'advanced':
            -l '$option_set.name_prefix'
            -f '$option_set.fraction'
            -m '$option_set.min_tlen'
            -a '$option_set.min_anchor_len'
            -j '$option_set.min_anchor_cov'
            -c '$option_set.min_bundle_cov'
            -g '$option_set.bdist'
            -M '$option_set.bundle_fraction' $option_set.sensitive $option_set.disable_trimming $option_set.multi_mapping
            #if $option_set.abundance_estimation:
                -A "$gene_abundance_estimation"
            #end if
            #if str($option_set.omit_sequences).strip() != "":
                -x '$option_set.omit_sequences'
            #end if
        #end if

        #if str($guide.use_guide) == 'yes':
            #if $guide.special_outputs.special_outputs_select == 'deseq2':
                &&
                prepDE.py
                    -i ./special_de_output/
                    -g gene_cout_matrix.tsv
                    -t transcripts_count_matrix.tsv
                    -l $guide.special_outputs.read_length
                    #if str($option_set.options) == 'advanced':
                        -s '$option_set.name_prefix'
                    #end if
                    #if $guide.special_outputs.clustering:
                        -c
                        --legend ./legend.tsv

                        &&
                        sed -i.bak 's/,/\t/g' ./legend.tsv

                    #end if
                &&
                sed -i.bak 's/,/\t/g' transcripts_count_matrix.tsv
                &&
                sed -i.bak 's/,/\t/g' gene_cout_matrix.tsv
            #end if
        #end if
    ]]></command>
    <inputs>
        <param name="input_bam" type="data" format="sam,bam" label="Mapped reads to assemble transcripts from" />
        <conditional name="guide">
            <param name="use_guide" type="select" label="Use GFF file to guide assembly">
                <option value="yes">Use GFF/GTF</option>
                <option selected="True" value="no">Do not use GFF/GTF</option>
            </param>
            <when value="no" />
            <when value="yes">
                <param name="guide_gff" argument="-G" type="data" format="gtf,gff3"
                       label="Reference annotation to use for guiding the assembly process" />
                <param name="input_estimation" argument="-e" type="boolean" truevalue="-e" falsevalue=""
                       label="Perform abundance estimation only of input transcripts" />
                <conditional name="special_outputs">
                    <param name="special_outputs_select" type="select" label="Output additional files for use in...">
                        <option value="ballgown">Ballgown</option>
                        <option selected="True" value="deseq2">DESeq2/EdgeR</option>
                        <option value="no">No addional output</option>
                    </param>
                    <when value="ballgown" />
                    <when value="deseq2">
                        <param name="read_length" type="integer" value="75" label="Average read length" />
                        <param name="clustering" type="boolean" truevalue="--cluster" falsevalue="" label="Whether to cluster genes that overlap with different gene IDs" help="ignoring ones with geneID pattern" />
                    </when>
                    <when value="no" />
                </conditional>
            </when>
        </conditional>
        <conditional name="option_set">
            <param name="options" type="select" label="Options">
                <option selected="True" value="default">Use defaults</option>
                <option value="advanced">Specify advanced options</option>
            </param>
            <when value="default" />
            <when value="advanced">
                <param name="disable_trimming" argument="-t" type="boolean" truevalue="-t" falsevalue=""
                    label="Disable trimming of predicted transcripts based on coverage" />
                <param name="sensitive" argument="-S" type="boolean" truevalue="-S" falsevalue=""
                    label="Increase sensitivity" />
                <param name="name_prefix" argument="-l" type="text" value="STRG" label="Name prefix for output transcripts" />
                <param name="fraction" argument="-f" type="float" value="0.15" min="0.0" max="1.0" label="Minimum isoform fraction" />
                <param name="min_tlen" argument="-m" type="integer" value="200" label="Minimum assembled transcript length" />
                <param name="min_anchor_len" argument="-a" type="integer" value="10" label="Minimum anchor length for junctions" />
                <param name="min_anchor_cov" argument="-j" type="integer" value="1" label="Minimum junction coverage" />
                <param name="min_bundle_cov" argument="-c" type="integer" value="2" label="Minimum bundle reads per bp coverage to consider for assembly" />
                <param name="bdist" argument="-g" type="integer" value="50" label="Gap between read mappings triggering a new bundle" />
                <param name="bundle_fraction" argument="-M" type="float" value="0.95" label="Fraction of bundle allowed to be covered by multi-hit reads" />
                <param name="omit_sequences" argument="-x" type="text" value=""
                    label="Do not assemble any transcripts on these reference sequence(s)" help="e.g. chrM,chrX" />
                <param name="abundance_estimation" argument="-A" type="boolean" truevalue="-A" falsevalue=""
                    label="Additional gene abundance estimation output file" />
                <param name="multi_mapping" argument="-u" type="boolean" truevalue="-u" falsevalue=""
                    label="Disable multi-mapping correction" />
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data name="output_gtf" format="gtf" label="${tool.name} on ${on_string}: Assembled transcripts" />
        <data name="gene_abundance_estimation" format="gtf" label="${tool.name} on ${on_string}: Gene abundance estimates">
            <filter>option_set['options'] == 'advanced' and option_set['abundance_estimation']</filter>
        </data>
        <data name="coverage" format="gff3" label="${tool.name} on ${on_string}: Coverage">
            <filter>guide['use_guide'] == 'yes'</filter>
        </data>
        <data name="exon_expression" format="tabular" from_work_dir="special_de_output/sample1/e_data.ctab"
            label="${tool.name} on ${on_string}: exon-level expression measurements">
            <filter>guide['use_guide'] == 'yes' and guide['special_outputs']['special_outputs_select'] == 'ballgown'</filter>
        </data>
        <data name="intron_expression" format="tabular" from_work_dir="special_de_output/sample1/i_data.ctab"
            label="${tool.name} on ${on_string}: intron-level expression measurements">
            <filter>guide['use_guide'] == 'yes' and guide['special_outputs']['special_outputs_select'] == 'ballgown'</filter>
        </data>
        <data name="transcript_expression" format="tabular" from_work_dir="special_de_output/sample1/t_data.ctab"
            label="${tool.name} on ${on_string}: transcript-level expression measurements">
            <filter>guide['use_guide'] == 'yes' and guide['special_outputs']['special_outputs_select'] == 'ballgown'</filter>
        </data>
        <data name="exon_transcript_mapping" format="tabular" from_work_dir="special_de_output/sample1/e2t.ctab"
            label="${tool.name} on ${on_string}: exon to transcript mapping">
            <filter>guide['use_guide'] == 'yes' and guide['special_outputs']['special_outputs_select'] == 'ballgown'</filter>
        </data>
        <data name="intron_transcript_mapping" format="tabular" from_work_dir="special_de_output/sample1/i2t.ctab"
            label="${tool.name} on ${on_string}: intron to transcript mapping">
            <filter>guide['use_guide'] == 'yes' and guide['special_outputs']['special_outputs_select'] == 'ballgown'</filter>
        </data>
        <data name="gene_counts" format="tabular" from_work_dir="gene_cout_matrix.tsv"
            label="${tool.name} on ${on_string}: Gene counts">
            <filter>guide['use_guide'] == 'yes' and guide['special_outputs']['special_outputs_select'] == 'deseq2'</filter>
        </data>
        <data name="transcript_counts" format="tabular" from_work_dir="transcripts_count_matrix.tsv"
            label="${tool.name} on ${on_string}: Transcript counts">
            <filter>guide['use_guide'] == 'yes' and guide['special_outputs']['special_outputs_select'] == 'deseq2'</filter>
        </data>
        <data name="legend" format="tabular" from_work_dir="legend.tsv"
            label="${tool.name} on ${on_string}: legend">
            <filter>guide['use_guide'] == 'yes' and guide['special_outputs']['special_outputs_select'] == 'deseq2' and guide['special_outputs']['clustering'] is True</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            <param name="use_guide" value="no" />
            <param name="options" value="default" />
            <output name="output_gtf" file="stringtie_out1.gtf" ftype="gtf" lines_diff="2" />
        </test>
        <test>
            <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            <param name="use_guide" value="no" />
            <param name="options" value="advanced" />
            <param name="fraction" value="0.17" />
            <output name="output_gtf" file="stringtie_out2.gtf" ftype="gtf" lines_diff="2" />
        </test>
        <test>
            <param ftype="bam" name="input_bam" value="stringtie_in1.bam" />
            <param name="use_guide" value="yes" />
            <param name="special_outputs_select" value="no" />
            <param name="guide_gff" value="stringtie_in.gtf" />
            <param name="options" value="default" />
            <output file="stringtie_out3.gtf" ftype="gtf" lines_diff="2" name="output_gtf" />
        </test>
        <test>
            <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            <param name="use_guide" value="yes" />
            <param name="special_outputs_select" value="no" />
            <param name="guide_gff" value="stringtie_in.gtf" />
            <param name="options" value="advanced" />
            <param name="fraction" value="0.17" />
            <output name="output_gtf" file="stringtie_out4.gtf" ftype="gtf" lines_diff="2" />
        </test>
        <test>
            <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            <param name="use_guide" value="yes" />
            <param name="special_outputs_select" value="ballgown" />
            <param name="guide_gff" value="stringtie_in.gtf" />
            <param name="options" value="default" />
            <output name="exon_expression" file="./ballgown/e_data.ctab" ftype="tabular" />
            <output name="intron_expression" file="./ballgown/i_data.ctab" ftype="tabular" />
            <output name="transcript_expression" file="./ballgown/t_data.ctab" ftype="tabular" />
            <output name="exon_transcript_mapping" file="./ballgown/e2t.ctab" ftype="tabular" />
            <output name="intron_transcript_mapping" file="./ballgown/i2t.ctab" ftype="tabular" />
            <output name="output_gtf" file="stringtie_out5.gtf" ftype="gtf" lines_diff="2" />
            <output name="coverage" file="stringtie_out_coverage.gtf" ftype="gff3" />
        </test>
        <test>
            <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            <param name="use_guide" value="yes" />
            <param name="special_outputs_select" value="deseq2" />
            <param name="input_estimation" value="True" />
            <param name="guide_gff" value="stringtie_in.gtf" />
            <param name="options" value="default" />
            <param name="clustering" value="True" />
            <output name="gene_counts" file="./deseq2/gene_counts.tsv" ftype="tabular" lines_diff="2" />
            <output name="transcript_counts" file="./deseq2/transcript_counts.tsv" ftype="tabular" />
            <output name="legend" file="./deseq2/legend.tsv" ftype="tabular" />
            <output name="output_gtf" file="stringtie_out6.gtf" ftype="gtf" lines_diff="2" />
            <output name="coverage" file="stringtie_out_coverage.gtf" ftype="gff3" />
        </test>
        <test>
            <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            <param name="use_guide" value="yes" />
            <param name="guide_gff" value="stringtie_in.gtf" />
            <param name="options" value="advanced" />
            <param name="fraction" value="0.17" />
            <param name="abundance_estimation" value="True" />
            <output name="output_gtf" file="stringtie_out4.gtf" ftype="gtf" lines_diff="2" />
            <output name="gene_abundance_estimation" file="stringtie_out7.gtf" ftype="gtf" lines_diff="2" />
        </test>
        <test>
            <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            <param name="use_guide" value="yes" />
            <param name="special_outputs_select" value="no" />
            <param name="guide_gff" value="stringtie_in.gtf" />
            <param name="options" value="advanced" />
            <param name="fraction" value="0.15" />
            <param name="c" value="test_chromosome" />
            <output name="output_gtf" file="stringtie_out8.gtf" ftype="gtf" lines_diff="2" />
        </test>
    </tests>
    <help><![CDATA[
**What it does?**

StringTie_ is a fast and highly efficient assembler of RNA-Seq alignments into potential transcripts. It uses a novel network flow algorithm as well as an optional *de novo* assembly step to assemble and quantitate full-length transcripts representing multiple splice variants for each gene locus. Its input can include not only the alignments of raw reads used by other transcript assemblers, but also alignments longer sequences that have been assembled from those reads.To identify differentially expressed genes between experiments, StringTie's output can be processed either by the Cuffdiff or Ballgown programs.

.. _StringTie: http://ccb.jhu.edu/software/stringtie/
    ]]></help>
    <expand macro="citations" />
</tool>