comparison cuffcompare_wrapper.xml @ 10:f648e5180e40 draft default tip

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/cufflinks/cuffcompare commit a0b0845a9d1b3e7ecdeacd1e606133617e3918bd"

9:e66b9b5b8580

<tool id="cuffcompare" name="Cuffcompare" version="@VERSION@.1">
    <description>compare assembled transcripts to a reference annotation and track Cufflinks transcripts across multiple experiments</description>
    <macros>
      <import>cuff_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <version_command>cuffcompare 2>&amp;1 | head -n 1</version_command>
    <command detect_errors="aggressive"><![CDATA[
        python '$__tool_directory__/cuffcompare_wrapper.py'
            ## Use annotation reference?
            #if $annotation.use_ref_annotation == "Yes":
                -r '$annotation.reference_annotation'
                #if $annotation.ignore_nonoverlapping_reference:
                    -R
                #end if
                #if $annotation.ignore_nonoverlapping_transfrags:
                    -Q
                #end if

            #end if

            ## Use sequence data?
            #if $seq_data.use_seq_data == "Yes":
            -s
                #if $seq_data.seq_source.index_source == "history":
                    --ref_file '$seq_data.seq_source.ref_file'
                #else:
                    --index '${seq_data.seq_source.index.fields.path}'
                #end if
            #end if

            $discard_single_exon

            -e $max_dist_exon
            -d $max_dist_group

            #if $discard_intron_redundant_transfrags:
                -F
            #end if

            ## Outputs.
            --combined-transcripts '${transcripts_combined}'

            @CUFFLINKS_GTF_INPUTS@
    ]]></command>
    <inputs>
        <expand macro="cufflinks_gtf_inputs" />
        <conditional name="annotation">
            <param name="use_ref_annotation" type="select" label="Use Reference Annotation">
                <option value="No">No</option>

                  </when>
                </conditional>
            </when>
        </conditional>
        <param type="select" name="discard_single_exon" label="discard (ignore) single-exon transcripts">
                <option value="" selected="True">No</option>
                <option value="-M">Discard single-exon transfrags and reference transcripts</option>
                <option value="-N">Discard single-exon reference transcripts</option>
        </param>
        <param type="integer" name="max_dist_exon" value="100" label="Max. Distance for assessing exon accuracy"
            help="max. distance (range) allowed from free ends of terminal exons of reference transcripts when assessing exon accuracy. Default: 100" />
        <param type="integer" name="max_dist_group" value="100" label="Max.Distance for transcript grouping"
            help="max. distance (range) for grouping transcript start sites. Default: 100" />
        <param type="boolean" name="discard_intron_redundant_transfrags" label="discard intron-redundant transfrags sharing 5'"
            help="Discard intron-redundant transfrags if they share the 5' end (if they differ only at the 3' end)" />
    </inputs>

    <outputs>
        <data format="txt" name="transcripts_accuracy" label="${tool.name} on ${on_string}: transcript accuracy"
            from_work_dir="cc_output.stats" />
        <data format="tabular" name="input1_tmap" label="${tool.name} on ${on_string}: data ${inputs[0].hid} tmap file"
            from_work_dir="cc_output.input1.tmap" />
        <data format="tabular" name="input1_refmap"
              label="${tool.name} on ${on_string}: data ${inputs[0].hid} refmap file"
              from_work_dir="cc_output.input1.refmap">
            <filter>annotation['use_ref_annotation'] == 'Yes'</filter>
        </data>
        <data format="tabular" name="input2_tmap" label="${tool.name} on ${on_string}: data ${inputs[1].hid} tmap file" from_work_dir="cc_output.input2.tmap">
            <filter>@HAS_MULTIPLE_INPUTS@</filter>
        </data>
        <data format="tabular" name="input2_refmap"
              label="${tool.name} on ${on_string}: data ${inputs[1].hid} refmap file"
              from_work_dir="cc_output.input2.refmap">
            <filter>annotation['use_ref_annotation'] == 'Yes' and @HAS_MULTIPLE_INPUTS@</filter>
        </data>
        <data format="tabular" name="transcripts_tracking" label="${tool.name} on ${on_string}: transcript tracking" from_work_dir="cc_output.tracking">
            <filter>@HAS_MULTIPLE_INPUTS@</filter>
        </data>
        <data format="gtf" name="transcripts_combined" label="${tool.name} on ${on_string}: combined transcripts"/>
    </outputs>

    <tests>
        <!--
            cuffcompare -r cuffcompare_in3.gtf -R cuffcompare_in1.gtf cuffcompare_in2.gtf
        -->
        <test>
            <param name="inputs" value="cuffcompare_in1.gtf,cuffcompare_in2.gtf" ftype="gtf"/>
            <param name="use_ref_annotation" value="Yes"/>
            <param name="reference_annotation" value="cuffcompare_in3.gtf" ftype="gtf"/>
            <param name="ignore_nonoverlapping_reference" value="Yes"/>
            <param name="ignore_nonoverlapping_transfrags" value="No"/>
            <param name="use_seq_data" value="No"/>
            <param name="discard_single_exon" value="" />
            <param name="max_dist_exon" value="100" />
            <param name="max_dist_group" value="100" />
            <param name="discard_intron_redundant_transfrags" value="No" />
            <!-- Line diffs are the result of different locations for input files; this cannot be fixed as cuffcompare outputs
                full input path for each input. -->
            <output name="transcripts_accuracy" file="cuffcompare_out7.txt" lines_diff="2"/>
            <output name="input1_tmap" file="cuffcompare_out1.tmap"/>
            <output name="input1_refmap" file="cuffcompare_out2.refmap"/>
            <output name="input2_tmap" file="cuffcompare_out3.tmap"/>
            <output name="input2_refmap" file="cuffcompare_out4.refmap"/>
            <output name="transcripts_tracking" file="cuffcompare_out6.tracking"/>

This is a list of implemented Cuffcompare options::

  -r    An optional "reference" annotation GTF. Each sample is matched against this file, and sample isoforms are tagged as overlapping, matching, or novel where appropriate. See the refmap and tmap output file descriptions below.
  -R    If -r was specified, this option causes cuffcompare to ignore reference transcripts that are not overlapped by any transcript in one of cuff1.gtf,...,cuffN.gtf. Useful for ignoring annotated transcripts that are not present in your RNA-Seq samples and thus adjusting the "sensitivity" calculation in the accuracy report written in the transcripts_accuracy file
    </help>
    <citations>
        <citation type="doi">10.1038/nbt.1621</citation>
    </citations>
</tool>

10:f648e5180e40

<tool id="cuffcompare" name="Cuffcompare" version="@VERSION@.2">
    <description>compare assembled transcripts to a reference annotation and track Cufflinks transcripts across multiple experiments</description>
    <macros>
      <import>cuff_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <version_command><![CDATA[
cuffcompare 2>&1 | head -n 1
    ]]></version_command>
    <command detect_errors="aggressive"><![CDATA[
        @CUFFLINKS_LINK_GTF_INPUTS@
        cuffcompare
            -o output
            ## Use annotation reference?
            #if $annotation.use_ref_annotation == "Yes":
            -r '$annotation.reference_annotation'
                #if $annotation.ignore_nonoverlapping_reference:
                    -R
                #end if
                #if $annotation.ignore_nonoverlapping_transfrags:
                    -Q
                #end if
            #end if

            ## Use sequence data?
            #if $seq_data.use_seq_data == "Yes":
            -s
                #if $seq_data.seq_source.index_source == "history":
                    '$seq_data.seq_source.ref_file'
                #else:
                    '${seq_data.seq_source.index.fields.path}'
                #end if
            #end if

            $discard_single_exon

            -e $max_dist_exon
            -d $max_dist_group

            $discard_intron_redundant_transfrags

            @CUFFLINKS_GTF_INPUTS@
]]></command>
    <inputs>
        <expand macro="cufflinks_gtf_inputs" />
        <conditional name="annotation">
            <param name="use_ref_annotation" type="select" label="Use Reference Annotation">
                <option value="No">No</option>

                  </when>
                </conditional>
            </when>
        </conditional>
        <param type="select" name="discard_single_exon" label="discard (ignore) single-exon transcripts">
            <option value="" selected="True">No</option>
            <option value="-M">Discard single-exon transfrags and reference transcripts</option>
            <option value="-N">Discard single-exon reference transcripts</option>
        </param>
        <param type="integer" name="max_dist_exon" value="100" label="Max. Distance for assessing exon accuracy"
            help="max. distance (range) allowed from free ends of terminal exons of reference transcripts when assessing exon accuracy. Default: 100" />
        <param type="integer" name="max_dist_group" value="100" label="Max.Distance for transcript grouping"
            help="max. distance (range) for grouping transcript start sites. Default: 100" />
        <param type="boolean" name="discard_intron_redundant_transfrags" label="discard intron-redundant transfrags sharing 5'"
            value="false" truevalue="-F" falsevalue=""
            help="Discard intron-redundant transfrags if they share the 5' end (if they differ only at the 3' end)" />
    </inputs>

    <outputs>
        <data format="txt" name="transcripts_accuracy" label="${tool.name} on ${on_string}: transcript accuracy"
            from_work_dir="output.stats" />
        <data format="tabular" name="input1_tmap" label="${tool.name} on ${on_string}: data ${inputs[0].hid} tmap file"
            from_work_dir="output.input_0.tmap" />
        <data format="tabular" name="input1_refmap"
              label="${tool.name} on ${on_string}: data ${inputs[0].hid} refmap file"
              from_work_dir="output.input_0.refmap">
            <filter>annotation['use_ref_annotation'] == 'Yes'</filter>
        </data>
        <data format="tabular" name="input2_tmap" label="${tool.name} on ${on_string}: data ${inputs[1].hid} tmap file" from_work_dir="output.input_1.tmap">
            <filter>@HAS_MULTIPLE_INPUTS@</filter>
        </data>
        <data format="tabular" name="input2_refmap"
              label="${tool.name} on ${on_string}: data ${inputs[1].hid} refmap file"
              from_work_dir="output.input_1.refmap">
            <filter>annotation['use_ref_annotation'] == 'Yes' and @HAS_MULTIPLE_INPUTS@</filter>
        </data>
        <data format="tabular" name="transcripts_tracking" label="${tool.name} on ${on_string}: transcript tracking" from_work_dir="output.tracking">
            <filter>@HAS_MULTIPLE_INPUTS@</filter>
        </data>
        <data format="gtf" name="transcripts_combined" label="${tool.name} on ${on_string}: combined transcripts" from_work_dir="output.combined.gtf"/>
    </outputs>

    <tests>
        <!--
            cuffcompare -r cuffcompare_in3.gtf -R cuffcompare_in1.gtf cuffcompare_in2.gtf
        -->
        <test expect_num_outputs="7">
            <param name="inputs" value="cuffcompare_in1.gtf,cuffcompare_in2.gtf" ftype="gtf"/>
            <param name="use_ref_annotation" value="Yes"/>
            <param name="reference_annotation" value="cuffcompare_in3.gtf" ftype="gtf"/>
            <param name="ignore_nonoverlapping_reference" value="Yes"/>
            <param name="ignore_nonoverlapping_transfrags" value="No"/>
            <param name="use_seq_data" value="No"/>
            <param name="discard_single_exon" value="" />
            <param name="max_dist_exon" value="100" />
            <param name="max_dist_group" value="100" />
            <param name="discard_intron_redundant_transfrags" value="false" />
            <!-- Line diffs are the result of different locations for input files; this cannot be fixed as cuffcompare outputs
                full input path for each input. -->
            <output name="transcripts_accuracy" file="cuffcompare_out7.txt" lines_diff="6"/>
            <output name="input1_tmap" file="cuffcompare_out1.tmap"/>
            <output name="input1_refmap" file="cuffcompare_out2.refmap"/>
            <output name="input2_tmap" file="cuffcompare_out3.tmap"/>
            <output name="input2_refmap" file="cuffcompare_out4.refmap"/>
            <output name="transcripts_tracking" file="cuffcompare_out6.tracking"/>

This is a list of implemented Cuffcompare options::

  -r    An optional "reference" annotation GTF. Each sample is matched against this file, and sample isoforms are tagged as overlapping, matching, or novel where appropriate. See the refmap and tmap output file descriptions below.
  -R    If -r was specified, this option causes cuffcompare to ignore reference transcripts that are not overlapped by any transcript in one of cuff1.gtf,...,cuffN.gtf. Useful for ignoring annotated transcripts that are not present in your RNA-Seq samples and thus adjusting the "sensitivity" calculation in the accuracy report written in the transcripts_accuracy file
    </help>
    <expand macro="citations"/>
</tool>