comparison recover_samples_discarded_by_subsample.xml @ 1:e93e39c121b1 draft default tip

planemo upload for repository https://github.com/ErasmusMC-Bioinformatics/galaxytools-emc/tree/master/tools/mycrobiota commit aadbfac9c48191cac625f10590082a6d1a0bfd09

0:607c5e7e0a64

        ## 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_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>

1:e93e39c121b1

        ## get.groups on in_fasta with this list of groups, if list not empty, otherwise create empty file
        &&
        if [ -z "\$samples"];
            then
                cp fasta2.dat final_fasta;
                cp group2.dat final_group;
            else
                echo "get.groups(fasta=fasta.dat, group=group.dat, groups=\$samples)" | sed 's/ //g' | mothur;

                ## 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;
        fi

    ]]></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_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>
        <test><!-- test case where nothing was discarded -->
            <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="1"/>
            <output name="out_fasta" file="fasta_after_subsample_small.fasta"/>
            <output name="out_group" file="groups_after_subsample_small.groups"/>
        </test>
    </tests>
    <help><![CDATA[
**What it does**
filter fasta file by group based on number of sequences in the group.
    ]]></help>