comparison stringtie.xml @ 5:f504b3b7e49d draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/stringtie commit 65c9ce2fdc2b4ce892df8e456f18b859a85c410a

4:df42808cc33a

<tool id="stringtie" name="StringTie" version="1.0.4">
    <description>transcript assembly and quantification</description>
    <requirements>
        <requirement type="package" version="1.0.4">stringtie</requirement>
    </requirements>
    <command><![CDATA[
stringtie "$input_bam"
-o "$output_gtf"
-p "\${GALAXY_SLOTS:-1}"

    -f "$option_set.fraction"
    -m "$option_set.min_tlen"
    -a "$option_set.min_anchor_len"
    -j "$option_set.min_anchor_cov"
    -c "$option_set.min_bundle_cov"
    -s "$option_set.maxcov"
    -g "$option_set.bdist"
    -M "$option_set.bundle_fraction" $option_set.sensitive $option_set.disable_trimming
#end if
]]>
</command>
    <inputs>
        <param format="bam" label="Mapped reads to assemble transcripts from" name="input_bam" type="data" />

                <param help="-f" label="Minimum isoform fraction" max="1.0" min="0.0" name="fraction" type="float" value="0.15" />
                <param help="-m" label="Minimum assembled transcript length" name="min_tlen" type="integer" value="200" />
                <param help="-a" label="Minimum anchor length for junctions" name="min_anchor_len" type="integer" value="10" />
                <param help="-j" label="Minimum junction coverage" name="min_anchor_cov" type="integer" value="1" />
                <param help="-c" label="Minimum bundle reads per bp coverage to consider for assembly" name="min_bundle_cov" type="integer" value="2" />
                <param help="-s" label="Coverage saturation threshold" name="maxcov" type="integer" value="1000000" />
                <param help="-g" label="Gap between read mappings triggering a new bundle" name="bdist" type="integer" value="50" />
                <param help="-M" label="Fraction of bundle allowed to be covered by multi-hit reads" name="bundle_fraction" type="float" value="0.95" />
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data format="gtf" label="${tool.name} on ${on_string}: Assembled transcripts" name="output_gtf" />
        <data format="gff3" label="${tool.name} on ${on_string}: Coverage" name="coverage">
            <filter>guide['use_guide'] == "yes"</filter>
        </data>
        <data format="tabular" from_work_dir="e_data.ctab" label="${tool.name} on ${on_string}: exon-level expression measurements" name="exon_expression">
            <filter>guide['output_ballgown']</filter>

            <output file="ballgown/e2t.ctab" ftype="tabular" name="exon_transcript_mapping" />
            <output file="ballgown/i2t.ctab" ftype="tabular" name="intron_transcript_mapping" />
            <output file="stringtie_out5.gtf" ftype="gtf" name="output_gtf" lines_diff="2" />
            <output file="stringtie_out_coverage.gtf" ftype="gff3" name="coverage" />
        </test>
    </tests>
    <help>
<![CDATA[

**What it does?**

StringTie has the following options::

 -G reference annotation to use for guiding the assembly process (GTF/GFF3)
 -l name prefix for output transcripts (default: STRG)
 -f minimum isoform fraction (default: 0.1)
 -m minimum assembled transcript length to report (default 200bp)
 -o output path/file name for the assembled transcripts GTF (default: stdout)
 -a minimum anchor length for junctions (default: 10)
 -j minimum junction coverage (default: 1)
 -t disable trimming of predicted transcripts based on coverage
    (default: coverage trimming is enabled)
 -c minimum reads per bp coverage to consider for transcript assembly (default: 2.5)
 -s coverage saturation threshold; further read alignments will be
    ignored in a region where a local coverage depth of <maxcov> 
    is reached (default: 1,000,000);
 -v verbose (log bundle processing details)
 -g gap between read mappings triggering a new bundle (default: 50)
 -C output file with reference transcripts that are covered by reads
 -M fraction of bundle allowed to be covered by multi-hit reads (default:0.95)
 -p number of threads (CPUs) to use (default: 1)
 -B enable output of Ballgown table files which will be created in the
    same directory as the output GTF (requires -G, -o recommended)
 -b enable output of Ballgown table files but these files will be 
    created under the directory path given as <dir_path>
 -e only estimates the abundance of given reference transcripts (requires -G)
 ]]>
    </help>
    <citations>
        <citation type="doi">doi:10.1038/nbt.3122</citation>
    </citations>

5:f504b3b7e49d

<tool id="stringtie" name="StringTie" version="1.1.0">
    <description>transcript assembly and quantification</description>
    <requirements>
        <requirement type="package" version="1.1.0">stringtie</requirement>
    </requirements>
    <command><![CDATA[
stringtie "$input_bam"
-o "$output_gtf"
-p "\${GALAXY_SLOTS:-1}"

    -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
    #if $option_set.A:
        -A "$gene_abundance_estimation"
    #end if
    #if str($option_set.x).strip() != "":
        -x "$option_set.x"
    #end if
#end if
]]>
</command>
    <inputs>
        <param format="bam" label="Mapped reads to assemble transcripts from" name="input_bam" type="data" />

                <param help="-f" label="Minimum isoform fraction" max="1.0" min="0.0" name="fraction" type="float" value="0.15" />
                <param help="-m" label="Minimum assembled transcript length" name="min_tlen" type="integer" value="200" />
                <param help="-a" label="Minimum anchor length for junctions" name="min_anchor_len" type="integer" value="10" />
                <param help="-j" label="Minimum junction coverage" name="min_anchor_cov" type="integer" value="1" />
                <param help="-c" label="Minimum bundle reads per bp coverage to consider for assembly" name="min_bundle_cov" type="integer" value="2" />
                <param help="-g" label="Gap between read mappings triggering a new bundle" name="bdist" type="integer" value="50" />
                <param help="-M" label="Fraction of bundle allowed to be covered by multi-hit reads" name="bundle_fraction" type="float" value="0.95" />
                <param argument="-x" type="text" value="" label="Do not assemble any transcripts on these reference sequence(s)" help="e.g. chrM,chrX" />
                <param argument="-A" truevalue="-A" falsevalue="" type="boolean" help="" label="Additional gene abundance estimation output file" />
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data format="gtf" label="${tool.name} on ${on_string}: Assembled transcripts" name="output_gtf" />
        <data format="tabular" label="${tool.name} on ${on_string}: Gene abundance estimates" name="gene_abundance_estimation">
            <filter>option_set['A']</filter>
        </data>
        <data format="gff3" label="${tool.name} on ${on_string}: Coverage" name="coverage">
            <filter>guide['use_guide'] == "yes"</filter>
        </data>
        <data format="tabular" from_work_dir="e_data.ctab" label="${tool.name} on ${on_string}: exon-level expression measurements" name="exon_expression">
            <filter>guide['output_ballgown']</filter>

            <output file="ballgown/e2t.ctab" ftype="tabular" name="exon_transcript_mapping" />
            <output file="ballgown/i2t.ctab" ftype="tabular" name="intron_transcript_mapping" />
            <output file="stringtie_out5.gtf" ftype="gtf" name="output_gtf" lines_diff="2" />
            <output file="stringtie_out_coverage.gtf" ftype="gff3" name="coverage" />
        </test>
        <test>
            <param ftype="bam" name="input_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="A" value="True" />
            <output file="stringtie_out4.gtf" ftype="gtf" name="output_gtf" lines_diff="2" />
            <output file="stringtie_out6.gtf" ftype="tabular" name="gene_abundance_estimation" />
        </test>
        <test>
            <param ftype="bam" name="input_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="0.15" />
            <param name="c" value="test_chromosome" />
            <output file="stringtie_out7.gtf" ftype="gtf" name="output_gtf" lines_diff="2" />
        </test>
    </tests>
    <help>
<![CDATA[

**What it does?**

StringTie has the following options::

 -G reference annotation to use for guiding the assembly process (GTF/GFF3)
 -l name prefix for output transcripts (default: STRG)
 -f minimum isoform fraction (default: 0.1)
 -m minimum assembled transcript length (default: 200)
 -o output path/file name for the assembled transcripts GTF (default: stdout)
 -a minimum anchor length for junctions (default: 10)
 -j minimum junction coverage (default: 1)
 -t disable trimming of predicted transcripts based on coverage
    (default: coverage trimming is enabled)
 -c minimum reads per bp coverage to consider for transcript assembly (default: 2.5)
 -v verbose (log bundle processing details)
 -g gap between read mappings triggering a new bundle (default: 50)
 -C output file with reference transcripts that are covered by reads
 -M fraction of bundle allowed to be covered by multi-hit reads (default:0.95)
 -p number of threads (CPUs) to use (default: 1)
 -B enable output of Ballgown table files which will be created in the
    same directory as the output GTF (requires -G, -o recommended)
 -b enable output of Ballgown table files but these files will be 
    created under the directory path given as <dir_path>
 -e only estimates the abundance of given reference transcripts (requires -G)
 -A gene abundance estimation output file
 -x do not assemble any transcripts on these reference sequence(s)


 ]]>
    </help>
    <citations>
        <citation type="doi">doi:10.1038/nbt.3122</citation>
    </citations>