comparison stringtie.xml @ 18:258d696dbd7e draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/stringtie commit 999b45e8bcf810f871cda58cb66573f7d6ae37f3"

17:1ebd14235b92

<tool id="stringtie" name="StringTie" version="@TOOL_VERSION@">
    <description>transcript assembly and quantification</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="stdio" />

    #elif $guide.guide_source.guide_gff_select == "cached":
        ln -s '$guide.guide_source.ref_builtin.fields.path' guide.gff &&
    #end if
#end if

#if $input_bam.metadata.ftype == 'sam':
    samtools sort -@ \${GALAXY_SLOTS:-1} '$input_bam' -T "\${TMPDIR:-.}" | stringtie
#else
    stringtie '$input_bam'
#end if

$long_reads

-o '$output_gtf'
-p "\${GALAXY_SLOTS:-1}"

$rna_strandness

        tail -n +2 transcript_counts.csv | sort -t"\${TAB}" -k1,1 >> '$transcript_counts'
    #end if
#end if
    ]]></command>
    <inputs>
        <param name="input_bam" type="data" format="sam,bam" label="Input mapped reads" help="Input BAM/SAM file containing reads you want to assemble into transcripts"/>
        <param name="long_reads" argument="-L" type="boolean" truevalue="-L" falsevalue="" checked="false" label="Input contains long reads?" help="Select if the input contains long error-prone reads, e.g. from Oxford Nanopore or PacBio sequencing."/>
        <param name="rna_strandness" type="select" label="Specify strand information"
            help="Select 'Forward (FR)' if your reads are from a forward-stranded library, 'Reverse (RF)' if your reads are from a reverse-stranded library, or 'Unstranded' if your reads are not from a stranded library. See Help section below for more information. Default: Unstranded">
                <option value="" selected="true">Unstranded</option>
                <option value="--fr">Forward (FR)</option>
                <option value="--rf">Reverse (RF)</option>

            <param name="min_bundle_cov" argument="-c" type="integer" min="0" value="2" label="Minimum bundle reads per bp coverage to consider for assembly" help="Sets the minimum read coverage allowed for the predicted transcripts. A transcript with a lower coverage than this value is not shown in the output. Default: 2"/>
            <param name="bdist" argument="-g" type="integer" min="0" value="50" label="Gap between read mappings triggering a new bundle" help="Minimum locus gap separation value. Reads that are mapped closer than this distance are merged together in the same processing bundle. Default: 50 (bp)"/>
            <param name="bundle_fraction" argument="-M" type="float" min="0.0" max="1.0" value="0.95" label="Fraction of bundle allowed to be covered by multi-hit reads"  help="Sets the maximum fraction of muliple-location-mapped reads that are allowed to be present at a given locus. Default: 0.95"/>
            <param name="disable_trimming" argument="-t" type="boolean" truevalue="-t" falsevalue="" checked="false" label="Disable trimming of predicted transcripts based on coverage" help="This parameter disables trimming at the ends of the assembled transcripts. By default StringTie adjusts the predicted transcript's start and/or stop coordinates based on sudden drops in coverage of the assembled transcript. Default: No" />
            <param name="multi_mapping" argument="-u" type="boolean" truevalue="-u" falsevalue="" checked="false" label="Disable multi-mapping correction" help="Default: No"/>
        </section>
    </inputs>
    <outputs>
        <data name="output_gtf" format="gtf" label="${tool.name} on ${on_string}: Assembled transcripts" />
        <data name="gene_abundance_estimation" format="tabular" label="${tool.name} on ${on_string}: Gene abundance estimates">

        </data>
    </outputs>
    <tests>
         <!--Ensure default GTF output works -->
        <test expect_num_outputs="1">
            <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            <output name="output_gtf" file="stringtie_out1.gtf" ftype="gtf" lines_diff="4" />
        </test>
        <!--Ensure fraction option works -->
        <test expect_num_outputs="1">
            <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            <param name="fraction" value="0.17" />
            <output name="output_gtf" file="stringtie_out2.gtf" ftype="gtf" lines_diff="4" />
        </test>
        <!--Ensure guide option works -->
        <test expect_num_outputs="1">
            <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
            <output name="output_gtf" file="stringtie_out3.gtf" ftype="gtf" lines_diff="4"  />
        </test>
        <!--Ensure guide with fraction works -->
        <test expect_num_outputs="1">
            <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
            <param name="fraction" value="0.17" />
            <output name="output_gtf" file="stringtie_out4.gtf" ftype="gtf" lines_diff="4" />
        </test>
        <!--Ensure coverage and output for Ballgown works -->
        <test expect_num_outputs="7">
            <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
            <param name="special_outputs_select" value="ballgown" />
            <param name="coverage_file" value="true" />

            <output name="output_gtf" file="stringtie_out5.gtf" ftype="gtf" lines_diff="4" />
            <output name="coverage" file="stringtie_out_coverage.gtf" ftype="gtf" />
        </test>
        <!--Ensure output for edgeR works -->
        <test expect_num_outputs="5">
            <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_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />

            <output name="output_gtf" file="stringtie_out6.gtf" ftype="gtf" lines_diff="4" />
            <output name="coverage" file="stringtie_out_coverage.gtf" ftype="gtf" />
        </test>
        <!--Ensure gene abundances output works -->
        <test expect_num_outputs="2">
            <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
            <param name="fraction" value="0.17" />
            <param name="abundance_estimation" value="true" />
            <output name="output_gtf" file="stringtie_out4.gtf" ftype="gtf" lines_diff="4" />
            <output name="gene_abundance_estimation" file="stringtie_out7.tsv" ftype="tabular" lines_diff="2" />
        </test>
        <!--Ensure another fraction value works -->
        <test expect_num_outputs="1">
            <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
            <param name="fraction" value="0.15" />
            <output name="output_gtf" file="stringtie_out8.gtf" ftype="gtf" lines_diff="4" />
        </test>
        <!--Ensure built-in GTFs work -->
        <test expect_num_outputs="1">
            <param name="input_bam" ftype="bam" dbkey="hg38" value="stringtie_in1.bam" />
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="cached" />
            <param name="fraction" value="0.15" />
            <output name="output_gtf" file="stringtie_out8.gtf" ftype="gtf" lines_diff="4" />
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

.. _edgeR: https://bioconductor.org/packages/release/bioc/html/edgeR.html
.. _limma: https://bioconductor.org/packages/release/bioc/html/limma.html
.. _Bioconductor: https://www.bioconductor.org/
.. _SAM: http://samtools.github.io/hts-specs/SAMv1.pdf
.. _HISAT2: http://ccb.jhu.edu/software/hisat2
.. _`GTF/GFF3`: https://ccb.jhu.edu/software/stringtie/gff.shtml
.. _`this link`: https://github.com/alyssafrazee/ballgown#ballgown-readable-expression-output
.. _`Ensembl site here`: http://useast.ensembl.org/info/website/upload/gff.html
.. _here: http://www.rna-seqblog.com/rpkm-fpkm-and-tpm-clearly-explained/
.. _`by B. Li and C. Dewey here`: http://bmcbioinformatics.biomedcentral.com/articles/10.1186/1471-2105-12-323
.. _`GFF utilities page`: https://ccb.jhu.edu/software/stringtie/gff.shtml#gffcompare
.. _`protocol paper`: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5032908/
.. _`StringTie manual here`: https://ccb.jhu.edu/software/stringtie/index.shtml?t=manual

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

18:258d696dbd7e

<tool id="stringtie" name="StringTie" version="@TOOL_VERSION@">
    <description>transcript assembly and quantification</description>
    <xrefs>
        <xref type="bio.tools">stringtie</xref>
    </xrefs>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="stdio" />

    #elif $guide.guide_source.guide_gff_select == "cached":
        ln -s '$guide.guide_source.ref_builtin.fields.path' guide.gff &&
    #end if
#end if

#if $input_options.input_mode in ['short_reads','long_reads']:
    #if $input_options.input_bam.metadata.ftype == 'sam':
        samtools sort -@ \${GALAXY_SLOTS:-1} '$input_options.input_bam' -T "\${TMPDIR:-.}" | stringtie
    #else
        stringtie '$input_options.input_bam'
    #end if
    #if $input_options.input_mode == 'long_reads'
        -L
        -E $input_options.error_splice
    #end if
#else
    #if $input_options.input_bam_short.metadata.ftype == 'bam' and $input_options.input_bam_long.metadata.ftype == 'bam':
        strigtie '$input_options.input_bam_short' '$input_options.input_bam_long'
    #else if $input_options.input_bam_short.metadata.ftype == 'sam' and $input_options.input_bam_long.metadata.ftype == 'bam':
        samtools sort -@ \${GALAXY_SLOTS:-1} '$input_options.input_bam_short' -T "\${TMPDIR:-.}" -o short_sorted.sam
        && stringtie short_sorted.sam '$input_options.input_bam_long'
    #else if $input_options.input_bam_short.metadata.ftype == 'bam' and $input_options.input_bam_long.metadata.ftype == 'sam':
        samtools sort -@ \${GALAXY_SLOTS:-1} '$input_options.input_bam_long' -T "\${TMPDIR:-.}" -o long_sorted.sam
        && stringtie'$input_options.input_bam_short' long_sorted.sam
    #else
        samtools sort -@ \${GALAXY_SLOTS:-1} '$input_options.input_bam_short' -T "\${TMPDIR:-.}" -o short_sorted.sam
        && samtools sort -@ \${GALAXY_SLOTS:-1} '$input_options.input_bam_long' -T "\${TMPDIR:-.}" -o long_sorted.sam
        && stringtie short_sorted.sam long_sorted.sam
    #end if
    -E $input_options.error_splice
#end if

-o '$output_gtf'
-p "\${GALAXY_SLOTS:-1}"

$rna_strandness

        tail -n +2 transcript_counts.csv | sort -t"\${TAB}" -k1,1 >> '$transcript_counts'
    #end if
#end if
    ]]></command>
    <inputs>
        <conditional name="input_options">
            <param name="input_mode" type="select" label="Input options">
                <option value="short_reads">Short reads</option>
                <option value="long_reads">Long reads</option>
                <option value="mixed_reads">Mixed mode: short and long reads</option>
            </param>
            <when value="short_reads">
                <param name="input_bam" type="data" format="sam,bam" label="Input short mapped reads" help="Input BAM/SAM file containing the short reads you want to assemble into transcripts"/>
            </when>
            <when value="long_reads">
                <param name="input_bam" type="data" format="sam,bam" label="Input long mapped reads" help="Input BAM/SAM file containing the long reads you want to assemble into transcripts"/>
                <param name="error_splice" argument="-E" type="integer" min="0" max="50" value="25" label="Window around possibly erroneous splice sites" help="This option allows to define window around possibly erroneous splice sites from long reads to look out for correct splice sites. Default: 25" />
            </when>
            <when value="mixed_reads">
                <param name="input_bam_short" type="data" format="sam,bam" label="Input short mapped reads" help="Input BAM/SAM file containing the short reads you want to assemble into transcripts"/>
                <param name="input_bam_long" type="data" format="sam,bam" label="Input long mapped reads" help="Input BAM/SAM file containing the long reads you want to assemble into transcripts"/>
                <param name="error_splice" argument="-E" type="integer" min="0" max="50" value="25" label="Window around possibly erroneous splice sites" help="This option allows to define window around possibly erroneous splice sites from long reads to look out for correct splice sites. Default: 25" />
            </when>
        </conditional>
        <param name="rna_strandness" type="select" label="Specify strand information"
            help="Select 'Forward (FR)' if your reads are from a forward-stranded library, 'Reverse (RF)' if your reads are from a reverse-stranded library, or 'Unstranded' if your reads are not from a stranded library. See Help section below for more information. Default: Unstranded">
                <option value="" selected="true">Unstranded</option>
                <option value="--fr">Forward (FR)</option>
                <option value="--rf">Reverse (RF)</option>

            <param name="min_bundle_cov" argument="-c" type="integer" min="0" value="2" label="Minimum bundle reads per bp coverage to consider for assembly" help="Sets the minimum read coverage allowed for the predicted transcripts. A transcript with a lower coverage than this value is not shown in the output. Default: 2"/>
            <param name="bdist" argument="-g" type="integer" min="0" value="50" label="Gap between read mappings triggering a new bundle" help="Minimum locus gap separation value. Reads that are mapped closer than this distance are merged together in the same processing bundle. Default: 50 (bp)"/>
            <param name="bundle_fraction" argument="-M" type="float" min="0.0" max="1.0" value="0.95" label="Fraction of bundle allowed to be covered by multi-hit reads"  help="Sets the maximum fraction of muliple-location-mapped reads that are allowed to be present at a given locus. Default: 0.95"/>
            <param name="disable_trimming" argument="-t" type="boolean" truevalue="-t" falsevalue="" checked="false" label="Disable trimming of predicted transcripts based on coverage" help="This parameter disables trimming at the ends of the assembled transcripts. By default StringTie adjusts the predicted transcript's start and/or stop coordinates based on sudden drops in coverage of the assembled transcript. Default: No" />
            <param name="multi_mapping" argument="-u" type="boolean" truevalue="-u" falsevalue="" checked="false" label="Disable multi-mapping correction" help="Default: No"/>
            <param name="point_features" type="data" format="tabular" optional="True" label="Input point-features dataset" help="Loads a list of point-features from a text feature file to guide the transcriptome assembly. Accepted point features are transcription start sites (TSS) and polyadenylation sites (CPAS). There are four tab-delimited columns in the feature file. The first three define the location of the point feature on the cromosome (sequence name, coordinate and strand), and the last is the type of the feature (TSS or CPAS)."/>
        </section>
    </inputs>
    <outputs>
        <data name="output_gtf" format="gtf" label="${tool.name} on ${on_string}: Assembled transcripts" />
        <data name="gene_abundance_estimation" format="tabular" label="${tool.name} on ${on_string}: Gene abundance estimates">

        </data>
    </outputs>
    <tests>
         <!--Ensure default GTF output works -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>
            <output name="output_gtf" file="stringtie_out1.gtf" ftype="gtf" lines_diff="4" />
        </test>
        <!--Ensure fraction option works -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="fraction" value="0.17" />
            <output name="output_gtf" file="stringtie_out2.gtf" ftype="gtf" lines_diff="4" />
        </test>
        <!--Ensure guide option works -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
            <output name="output_gtf" file="stringtie_out3.gtf" ftype="gtf" lines_diff="4"  />
        </test>
        <!--Ensure guide with fraction works -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
            <param name="fraction" value="0.17" />
            <output name="output_gtf" file="stringtie_out4.gtf" ftype="gtf" lines_diff="4" />
        </test>
        <!--Ensure coverage and output for Ballgown works -->
        <test expect_num_outputs="7">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
            <param name="special_outputs_select" value="ballgown" />
            <param name="coverage_file" value="true" />

            <output name="output_gtf" file="stringtie_out5.gtf" ftype="gtf" lines_diff="4" />
            <output name="coverage" file="stringtie_out_coverage.gtf" ftype="gtf" />
        </test>
        <!--Ensure output for edgeR works -->
        <test expect_num_outputs="5">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="special_outputs_select" value="deseq2" />
            <param name="input_estimation" value="true" />
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />

            <output name="output_gtf" file="stringtie_out6.gtf" ftype="gtf" lines_diff="4" />
            <output name="coverage" file="stringtie_out_coverage.gtf" ftype="gtf" />
        </test>
        <!--Ensure gene abundances output works -->
        <test expect_num_outputs="2">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
            <param name="fraction" value="0.17" />
            <param name="abundance_estimation" value="true" />
            <output name="output_gtf" file="stringtie_out4.gtf" ftype="gtf" lines_diff="4" />
            <output name="gene_abundance_estimation" file="stringtie_out7.tsv" ftype="tabular" lines_diff="2" />
        </test>
        <!--Ensure another fraction value works -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="history" />
            <param name="ref_hist" ftype="gtf" value="stringtie_in.gtf" />
            <param name="fraction" value="0.15" />
            <output name="output_gtf" file="stringtie_out8.gtf" ftype="gtf" lines_diff="4" />
        </test>
        <!--Ensure built-in GTFs work -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="short_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="cached" />
            <param name="fraction" value="0.15" />
            <output name="output_gtf" file="stringtie_out9.gtf" ftype="gtf" lines_diff="4" />
        </test>
        <!-- Test long reads input -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="long_reads"/>
                <param name="input_bam" ftype="bam" value="stringtie_in1.bam" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="cached" />
            <param name="fraction" value="0.15" />
            <output name="output_gtf" file="stringtie_out10.gtf" ftype="gtf" lines_diff="4" />
        </test>
        <!-- Test error splice option -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="long_reads"/>
                <param name="input_bam" ftype="bam" value="long_reads.bam" />
                <param name="error_splice" value="30" />
            </conditional>            
            <param name="use_guide" value="yes" />
            <param name="guide_gff_select" value="cached" />
            <param name="fraction" value="0.15" />
            <output name="output_gtf" file="stringtie_out11.gtf" ftype="gtf" lines_diff="4" />
        </test>
        <!-- Test mixed reads input -->
        <test expect_num_outputs="1">
            <conditional name="input_options">
                <param name="input_mode" value="mixed_reads"/>
                <param name="input_bam_short" ftype="bam" value="short_reads.bam" />
                <param name="input_bam_long" ftype="bam" value="long_reads.bam" />
            </conditional>            
            <output name="output_gtf" file="stringtie_out12.gtf" ftype="gtf" lines_diff="4" />
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

.. _edgeR: https://bioconductor.org/packages/release/bioc/html/edgeR.html
.. _limma: https://bioconductor.org/packages/release/bioc/html/limma.html
.. _Bioconductor: https://www.bioconductor.org/
.. _SAM: http://samtools.github.io/hts-specs/SAMv1.pdf
.. _HISAT2: http://ccb.jhu.edu/software/hisat2
.. _`GTF/GFF3`: http://ccb.jhu.edu/software/stringtie/gff.shtml
.. _`this link`: https://github.com/alyssafrazee/ballgown#ballgown-readable-expression-output
.. _`Ensembl site here`: http://useast.ensembl.org/info/website/upload/gff.html
.. _here: http://www.rna-seqblog.com/rpkm-fpkm-and-tpm-clearly-explained/
.. _`by B. Li and C. Dewey here`: http://bmcbioinformatics.biomedcentral.com/articles/10.1186/1471-2105-12-323
.. _`GFF utilities page`: http://ccb.jhu.edu/software/stringtie/gff.shtml#gffcompare
.. _`protocol paper`: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5032908/
.. _`StringTie manual here`: http://ccb.jhu.edu/software/stringtie/index.shtml?t=manual

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