comparison stringtie.xml @ 2:520e0988ec1c draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/stringtie commit b03fd81ed11744f119608d4884c24fa182eb605a

1:9f80c71f1779

<tool id="stringtie" name="StringTie" version="1.0.1">
    <description>RNA-Seq assembler</description>
    <requirements>
        <requirement type="package" version="1.0.1">stringtie</requirement>
    </requirements>
    <command><![CDATA[
stringtie "$input_bam"
-o "$output_gtf"
-p "\${GALAXY_SLOTS:-1}"

    -M "$option_set.bundle_fraction" $option_set.sensitive $option_set.disable_trimming
#end if
]]>
</command>
    <inputs>
        <param format="bam" label="BAM file to assemble" name="input_bam" type="data" />
        <conditional name="guide">
            <param label="Use GFF file to guide assembly" name="use_guide" type="select">
                <option value="yes">Use GFF</option>
                <option selected="True" value="no">Do not use GFF</option>
            </param>
            <when value="no" />
            <when value="yes">
                <param format="gtf,gff3" help="(-G)" label="Reference annotation to use for guiding the assembly process" name="guide_gff" type="data" />
                <param falsevalue="" help="(-e)" label="Perform abundance estimation only of input transcripts" name="input_estimation" truevalue="-e" type="boolean" />
                <param falsevalue="" help="(-b)" label="Output additional files for use in Ballgown" name="output_ballgown" truevalue="-b" type="boolean" />
            </when>
        </conditional>
        <conditional name="option_set">
            <param label="Options" name="options" type="select">
                <option selected="True" value="default">Use defaults</option>
                <option value="advanced">Specify advanced options</option>
            </param>
            <when value="default" />
            <when value="advanced">
                <param falsevalue="" help="(-t)" label="Disable trimming of predicted transcripts based on coverage" name="disable_trimming" truevalue="-t" type="boolean" />
                <param falsevalue="" help="(-S)" label="Increase sensitivity" name="sensitive" truevalue="-S" type="boolean" />
                <param help="(-l)" label="Name prefix for output transcripts" name="name_prefix" type="text" value="STRG" />
                <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" />

            <output file="stringtie_out_coverage.gtf" ftype="gff3" name="coverage" />
        </test>
    </tests>
    <help>
<![CDATA[
StringTie v1.0.1 usage:
 stringtie <input.bam> [-G <guide_gff>] [-l <label>] [-o <out_gtf>] [-p <cpus>]
  [-v] [-a <min_anchor_len>] [-m <min_tlen>] [-j <min_anchor_cov>] [-n sens]
  [-C <coverage_file_name>] [-s <maxcov>] [-c <min_bundle_cov>] [-g <bdist>]
  {-B | -b <dir_path>} [-e]

Assemble RNA-Seq alignments into potential transcripts.
 
 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)

2:520e0988ec1c

<tool id="stringtie" name="StringTie" version="1.0.3">
    <description>transcript assembly and quantification</description>
    <requirements>
        <requirement type="package" version="1.0.3">stringtie</requirement>
    </requirements>
    <command><![CDATA[
stringtie "$input_bam"
-o "$output_gtf"
-p "\${GALAXY_SLOTS:-1}"

    -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" />
        <conditional name="guide">
            <param label="Use GFF file to guide assembly" name="use_guide" type="select">
                <option value="yes">Use GFF</option>
                <option selected="True" value="no">Do not use GFF</option>
            </param>
            <when value="no" />
            <when value="yes">
                <param format="gtf,gff3" help="-G" label="Reference annotation to use for guiding the assembly process" name="guide_gff" type="data" />
                <param falsevalue="" help="-e" label="Perform abundance estimation only of input transcripts" name="input_estimation" truevalue="-e" type="boolean" />
                <param falsevalue="" help="-b" label="Output additional files for use in Ballgown" name="output_ballgown" truevalue="-b" type="boolean" />
            </when>
        </conditional>
        <conditional name="option_set">
            <param label="Options" name="options" type="select">
                <option selected="True" value="default">Use defaults</option>
                <option value="advanced">Specify advanced options</option>
            </param>
            <when value="default" />
            <when value="advanced">
                <param falsevalue="" help="-t" label="Disable trimming of predicted transcripts based on coverage" name="disable_trimming" truevalue="-t" type="boolean" />
                <param falsevalue="" help="-S" label="Increase sensitivity" name="sensitive" truevalue="-S" type="boolean" />
                <param help="-l" label="Name prefix for output transcripts" name="name_prefix" type="text" value="STRG" />
                <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" />

            <output file="stringtie_out_coverage.gtf" ftype="gff3" name="coverage" />
        </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/

------

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)