annotate cmsearch-deoverlap.xml @ 1:3fd3be28a04c draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/rna_tools/cmsearch_deoverlap commit a9df96eec1bfb4e4d61926b02e8847babd1187ad-dirty

<tool id="cmsearch_deoverlap" name="CMsearch deoverlap" version="0.08+galaxy1" profile="21.05">
    <description>removes lower scoring overlaps from cmsearch results</description>
    <requirements>
        <requirement type="package" version="5.26">perl</requirement>
    </requirements>
    <command><![CDATA[
        ln -s '$clan_information' clan_info &&
        ln -s '$cmsearch_matches' cmsearch_matches &&
        LC_ALL=C perl '$__tool_directory__/cmsearch-deoverlap.pl'
        --clanin clan_info cmsearch_matches
        #if $maxkeep:
            $maxkeep
        #end if
        #if $dirty:
            $dirty &&
            sed 's/[:blank:]+/,/g' cmsearch_matches.sort > cmsearch_matches.sort.tabular &&
            mv cmsearch_matches.sort.tabular '$matches_sort'
        #end if
        &&
        sed 's/[:blank:]+/,/g' cmsearch_matches.deoverlapped > cmsearch_matches.deoverlapped.tabular &&
        mv cmsearch_matches.deoverlapped.tabular '$deoverlapped_matches'

    ]]></command>
    <inputs>
        <param name="clan_information" type="data" format="txt" label="Clan information" help="Each row in the file contains an RNA clan and its corresponding family members"/>
        <param name="cmsearch_matches" type="data" format="tabular" label="The tabular result file from cmsearch"/>
        <param argument="--maxkeep" type="boolean" truevalue="--maxkeep" falsevalue="" label="Keep hits that only overlap with other hits that are not kept" help="If this option is not set, all hits with higher scoring overlap will be removed." />
        <param argument="--dirty" type="boolean" truevalue="--dirty" falsevalue="" label="Keep the intermediate sorted tblout file"/>
    </inputs>
    <outputs>
        <data name="deoverlapped_matches" format="tabular" label="Deoverlapped matches" />
        <data name="matches_sort" format="tabular" label="Sorted matches">
            <filter>dirty</filter>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="2">
            <param name="clan_information" value="ribo.claninfo" />
            <param name="cmsearch_matches" value="1.cmsearch.tblout" />
            <param name="dirty" value="--dirty"/>
            <output name="deoverlapped_matches" file="1.cmsearch.tblout.deoverlapped" />
            <output name="matches_sort" file="1.cmsearch.tblout.sort" />
        </test>
        <test expect_num_outputs="1">
            <param name="clan_information" value="ribo.claninfo" />
            <param name="cmsearch_matches" value="1.cmsearch.tblout" />
            <param name="dirty" value=""/>
            <output name="deoverlapped_matches" file="1.cmsearch.tblout.deoverlapped" />
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

**What this tool does**

This tool removes lower-scoring overlaps from cmsearch results. Given information about the clans and the cmsearch tbl output this tool returns a filtered cmsearch tbl output.

**clan.info:**

CL00111	SSU_rRNA_bacteria SSU_rRNA_archaea SSU_rRNA_eukarya SSU_rRNA_microsporidia SSU_trypano_mito

CL00112	LSU_rRNA_archaea LSU_rRNA_bacteria LSU_rRNA_eukarya LSU_trypano_mito 5_8S_rRNA

CL99999 5S_rRNA mtPerm-5S

**cmsearch.tblout:**

contig--2249925      -         SSU_rRNA_bacteria    RF00177   hmm       19      914        2      898      +     -    6 0.50   5.7  638.4  1.1e-189 !   -

contig--2255364      -         SSU_rRNA_bacteria    RF00177   hmm      325     1084      765        1      -     -    6 0.52   3.9  624.0  2.5e-185 !   -

contig--2369838      -         SSU_rRNA_bacteria    RF00177   hmm       90      938       20      855      +     -    6 0.52   7.0  609.3  6.6e-181 !   -

contig--2271497      -         SSU_rRNA_bacteria    RF00177   hmm        4      812      835        2      -     -    6 0.51   5.0  597.5  2.5e-177 !   -

contig--2369838      -         SSU_rRNA_archaea     RF01959   hmm       70      894       17      855      +     -    6 0.52   5.4  346.7  9.9e-102 !   -

**cmsearch.tblout.deoverlapped:**

contig--2249925      -         SSU_rRNA_bacteria    RF00177   hmm       19      914        2      898      +     -    6 0.50   5.7  638.4  1.1e-189 !   -

contig--2255364      -         SSU_rRNA_bacteria    RF00177   hmm      325     1084      765        1      -     -    6 0.52   3.9  624.0  2.5e-185 !   -

contig--2271497      -         SSU_rRNA_bacteria    RF00177   hmm        4      812      835        2      -     -    6 0.51   5.0  597.5  2.5e-177 !   -

contig--2369838      -         SSU_rRNA_bacteria    RF00177   hmm       90      938       20      855      +     -    6 0.52   7.0  609.3  6.6e-181 !   -


    ]]></help>
    <citations>
        <citation type="bibtex">
            @software{nawrocki_nawrockiecmsearch_tblout_deoverlap_2019,
	        title = {nawrockie/cmsearch\_tblout\_deoverlap},
	        url = {https://github.com/nawrockie/cmsearch_tblout_deoverlap},
	        abstract = {Script that removes lower scoring overlaps from cmsearch v1.1x --tblout files.},
	        author = {Nawrocki, Eric},
	        year = {2019}}
        </citation>
    </citations>
</tool>