comparison tin.xml @ 60:1421603cc95b draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rseqc commit 1dfe55ca83685cadb0ce8f6ebbd8c13232376d1d

59:dbedfc5f5a3c

<tool id="rseqc_tin" name="Transcript Integrity Number" version="@TOOL_VERSION@.1">
    <description>
        evaluates RNA integrity at a transcript level
    </description>
    <expand macro="bio_tools"/>
    <macros>

    <!-- Generate output files here because tin.py removes all instances of "bam"
    in the filename -->
    <command><![CDATA[
        #import re
        ln -sf '${input}' 'input.bam' &&
        ln -sf '${input.metadata.bam_index}' 'input.bam.bai' &&
        tin.py -i 'input.bam' --refgene='${refgene}' --minCov=${minCov}
        --sample-size=${samplesize} ${subtractbackground}
        ]]>
    </command>

    <inputs>
        <expand macro="bam_param" />
        <expand macro="refgene_param" />
        <param name="minCov" type="integer" value="10" label="Minimum coverage (default=10)"
            help="Minimum number of reads mapped to a transcript (--minCov)." />
        <param name="samplesize" type="integer" value="100" label="Sample size (default=100)"
            help="Number of equal-spaced nucleotide positions picked from mRNA.

            intronic reads). Only use this option if there are substantial
            intronic reads (--subtract-background)." />
    </inputs>

    <outputs>
        <data name="outputsummary" format="tabular" from_work_dir="input.summary.txt" label="TIN on ${on_string} (summary)" />
        <data name="outputxls" format="xls" from_work_dir="input.tin.xls" label="TIN on ${on_string} (tin)" />
    </outputs>

    <!-- PDF Files contain R version, must avoid checking for diff -->
    <tests>
        <test>
            <param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
            <param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed" ftype="bed12"/>
            <output name="outputsummary">
                <assert_contents>
                    <has_line_matching expression="^Bam_file\tTIN\(mean\)\tTIN\(median\)\tTIN\(stdev\)$" />
                    <has_line_matching expression="^input\.bam\t8\.8709677419\d+\t8\.8709677419\d+\t0\.0$" />
                </assert_contents>
            </output>
            <output name="outputxls" file="output.tin.xls"/>
        </test>
    </tests>

    <help><![CDATA[
## tin.py

60:1421603cc95b

<tool id="rseqc_tin" name="Transcript Integrity Number" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@GALAXY_VERSION@">
    <description>
        evaluates RNA integrity at a transcript level
    </description>
    <expand macro="bio_tools"/>
    <macros>

    <!-- Generate output files here because tin.py removes all instances of "bam"
    in the filename -->
    <command><![CDATA[
        #import re
        #set $input_list = []
        #for $i, $input in enumerate($input):
            #set $safename = re.sub('[^\w\-_]', '_', $input.element_identifier)
            #if $safename in $input_list:
                #set $safename = str($safename) + "." + str($i)
            #end if
            $input_list.append($safename)
            ln -sf '${input}' '${safename}.bam' &&
            ln -sf '${input.metadata.bam_index}' '${safename}.bam.bai' &&
            echo '${safename}.bam' >> 'input_list.txt' &&
        #end for
        tin.py -i 'input_list.txt' --refgene='${refgene}' --minCov=${minCov}
        --sample-size=${samplesize} ${subtractbackground}
        && mv *summary.txt summary.tab
        && mv *tin.xls tin.xls
        ]]>
    </command>

    <inputs>
        <param name="input" type="data" format="bam" multiple="true" label="Input BAM file" help="(--input-file)"/>
        <expand macro="refgene_param" />
        <param name="minCov" type="integer" value="10" label="Minimum coverage (default=10)"
            help="Minimum number of reads mapped to a transcript (--minCov)." />
        <param name="samplesize" type="integer" value="100" label="Sample size (default=100)"
            help="Number of equal-spaced nucleotide positions picked from mRNA.

            intronic reads). Only use this option if there are substantial
            intronic reads (--subtract-background)." />
    </inputs>

    <outputs>
        <data name="outputsummary" format="tabular" from_work_dir="summary.tab" label="TIN on ${on_string} (summary)" />
        <data name="outputxls" format="xls" from_work_dir="tin.xls" label="TIN on ${on_string} (tin)" />
    </outputs>

    <!-- PDF Files contain R version, must avoid checking for diff -->
    <tests>
        <test expect_num_outputs="2">
            <param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
            <param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed" ftype="bed12"/>
            <output name="outputsummary" file="summary.tin.txt" ftype="tabular"/>
            <output name="outputxls" file="output.tin.xls" ftype="xls"/>
        </test>
    </tests>

    <help><![CDATA[
## tin.py