annotate recover_samples_discarded_by_subsample.xml @ 0:607c5e7e0a64 draft

planemo upload for repository https://github.com/ErasmusMC-Bioinformatics/galaxytools-emc/tree/master/tools/mycrobiota commit 1c4c58018b64ff3531a719e789ce71cb0a1244c5

<tool id="mycrobiota_subsample_add_discarded_samples" name="Recover samples" version="0.1" profile="16.07">
    <description> discarded by sub.sample</description>
    <requirements>
        <requirement type="package" version="1.36.1">mothur</requirement>
    </requirements>
    <command detect_errors="aggressive"><![CDATA[
        ln -s "$in_fasta" fasta.dat &&
        ln -s "$in_group" group.dat &&
        ln -s "$in_fasta_subsampled" fasta2.dat &&
        ln -s "$in_group_subsampled" group2.dat

        ## mothur count.groups on in_fasta
        && echo 'count.groups(group=group.dat)' | sed 's/ //g' | mothur

        ## get group names with fewer than threshold reads and make a dash-separated list
        && samples=`python -c "print('-'.join([g[0] for g in [ l.strip().split('\t') for l in open('group.count.summary').readlines() ] if int(g[1]) < $threshold]))"`

        ## get.groups on in_fasta with this list of groups, if list not empty, otherwise create empty file
        &&
        if [ -z "\$samples"];
            then
                touch fasta.pick.dat;
                touch group.pick.dat;
            else
                echo "get.groups(fasta=fasta.dat, group=group.dat, groups=\$samples)" | sed 's/ //g' | mothur;
        fi

        ## merge selected reads (fasta.pick.dat) with the fasta file from after sub.sample
        && echo "merge.files(input=fasta2.dat-fasta.pick.dat, output=final_fasta)" | sed 's/ //g' | mothur

        ## merge group files
        && echo "merge.files(input=group2.dat-group.pick.dat, output=final_group)" | sed 's/ //g' | mothur

    ]]></command>
    <inputs>
        <param name="in_fasta" type="data" format="fasta" label="Fasta before subsample"/>
        <param name="in_fasta_subsampled" type="data" format="fasta" label="Fasta after subsample"/>
        <param name="in_group" type="data" format="mothur.groups" label="Group file before subsample"/>
        <param name="in_group_subsampled" type="data" format="mothur.groups" label="Group file after subsample"/>
        <param name="threshold" type="integer" value="" min="0" label="Subsample level - cutoff value used in the subsampling" help="any samples with fewer reads than this value would have been discarded by sub.sample, but we want to add them back in" />
    </inputs>
    <outputs>
        <data name="out_fasta" format="fasta" from_work_dir="final_fasta" label="${tool.name} on ${on_string}: fasta"/>
        <data name="out_group" format="mothur.groups" from_work_dir="final_group" label="${tool.name} on ${on_string}: group"/>
    </outputs>
    <tests>
        <test>
            <param name="in_fasta" value="fasta_before_subsample_small.fasta" ftype="fasta"/>
            <param name="in_fasta_subsampled" value="fasta_after_subsample_small.fasta" ftype="fasta"/>
            <param name="in_group" value="groups_before_subsample_small.groups" ftype="mothur.groups"/>
            <param name="in_group_subsampled" value="groups_after_subsample_small.groups" ftype="mothur.groups"/>
            <param name="threshold" value="3"/>
            <output name="out_fasta" file="recovered.fasta"/>
            <output name="out_group" file="recovered.groups"/>
        </test>
    </tests>
    <help><![CDATA[
**What it does**
filter fasta file by group based on number of sequences in the group.
    ]]></help>
    <citations>
    </citations>
</tool>