annotate idpassemble.xml @ 2:dd33125925d9 draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/bumbershoot commit 1e51bed3a1c10c67ef0404216608e9333db04c64

<?xml version="1.0"?>
<tool id="idpassemble" name="idpAssemble" version="@VERSION@.0">
    <description>Merge IDPicker databases from single files into a merged database, and filters the result at PSM/spectrum/peptide/protein/gene levels.</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <stdio>
        <exit_code range="1:" level="fatal" description="Job Failed" />
        <regex match="^Error:.*$" source="both" level="fatal" />
    </stdio>
    <command>
<![CDATA[
        #if len($input) < 2
        cp '${input}' output &&
        #end if

        idpAssemble
            -MaxFDRScore $MaxFDRScore
            -MinDistinctPeptides $filter_at_gene_level_condition.MinDistinctPeptides
            -MinSpectra $filter_at_gene_level_condition.MinSpectra
            -MinAdditionalPeptides $filter_at_gene_level_condition.MinAdditionalPeptides
            -MinSpectraPerDistinctMatch $MinSpectraPerDistinctMatch
            -MinSpectraPerDistinctPeptide $MinSpectraPerDistinctPeptide
            -MaxProteinGroupsPerPeptide $MaxProteinGroupsPerPeptide
            #if $filter_at_gene_level_condition.FilterAtGeneLevel
            -FilterAtGeneLevel 1
            #end if
            -SummarizeSources 1
            #if len($input) > 1
                -MergedOutputFilepath output
                #for $i in $input
                    '${i.file_name}'
                #end for
            #else
                output
            #end if
]]>
    </command>
    <inputs>
        <param name="input" type="data" format="idpdb" label="Input idpDB(s)" multiple="true"/>
        <param argument="-MaxFDRScore" type="float" label="Max FDR Score" min="0.00000001" value="0.05" help="Peptide-spectrum-matches (PSMs) with an FDR score (interpolated Q-value) higher than this will be excluded from the filtered data set." />
        <conditional name="filter_at_gene_level_condition">
            <param argument="-FilterAtGeneLevel" type="boolean" truevalue="1" falsevalue="0" label="Filter at Gene Level" help="Apply filters at the gene level (i.e. 'min distinct peptides per gene group' instead of 'min distinct peptides per protein group')"/>
            <when value="1">
                <param argument="-MinDistinctPeptides" type="integer" label="Min Distinct Peptides per Gene Group" min="1" value="2" help="Gene groups with fewer than this number of peptides will be excluded from the filtered data set." />
                <param argument="-MinSpectra" type="integer" label="Min Filtered Spectra per Gene Group" min="1" value="2" help="Gene groups with fewer than this number of spectra will be excluded from the filtered data set." />
                <param argument="-MinAdditionalPeptides" type="integer" label="Min Additional Peptides per Gene Group" min="0" value="1" help="Gene groups that are not necessary to explain the presence of at least this many extra peptides will be from the filtered data set. A value of 1 means that each gene group must explain at least 1 peptide that other gene groups do not explain." />
            </when>
            <when value="0">
                <param argument="-MinDistinctPeptides" type="integer" label="Min Distinct Peptides per Protein Group" min="1" value="2" help="Protein groups with fewer than this number of peptides will be excluded from the filtered data set." />
                <param argument="-MinSpectra" type="integer" label="Min Filtered Spectra per Protein Group" min="1" value="2" help="Protein groups with fewer than this number of spectra will be excluded from the filtered data set." />
                <param argument="-MinAdditionalPeptides" type="integer" label="Min Additional Peptides per Protein Group" min="0" value="1" help="Protein groups that are not necessary to explain the presence of at least this many extra peptides will be from the filtered data set. A value of 1 means that each protein group must explain at least 1 peptide that other protein groups do not explain." />
            </when>
        </conditional>
        <param argument="-MinSpectraPerDistinctMatch" type="integer" label="Min Filtered Spectra per Distinct Match" min="1" value="1" help="Distinct matches with fewer than this number of spectra will be excluded from the filtered data set." />
        <param argument="-MinSpectraPerDistinctPeptide" type="integer" label="Min Filtered Spectra per Distinct Peptide" min="1" value="1" help="Distinct peptides with fewer than this number of spectra will be excluded from the filtered data set." />
        <param argument="-MaxProteinGroupsPerPeptide" type="integer" label="Max Protein Groups per Distinct Peptide" min="0" value="10" help="Peptides that map to more than this number of protein groups will be excluded from the filtered data set. Highly ambiguous peptides are not very useful for quantitation." />
    </inputs>
    <outputs>
        <data format="idpdb" name="output" from_work_dir="output" />
    </outputs>
    <tests>
        <test>
            <param name="input" value="201208-378803-mm.idpDB" />
            <param name="MaxFDRScore" value="0.05" />
            <param name="filter_at_gene_level_condition.MinDistinctPeptides" value="2" />
            <param name="filter_at_gene_level_condition.MinSpectra" value="2" />
            <param name="filter_at_gene_level_condition.MinAdditionalPeptides" value="1" />
            <param name="MinSpectraPerDistinctMatch" value="1" />
            <param name="MinSpectraPerDistinctPeptide" value="1" />
            <param name="MaxProteinGroupsPerPeptide" value="10" />
            <output name="output" file="201208-378803-mm-filtered.idpDB" compare="sim_size" delta="500000" />
        </test>
        <test>
            <param name="input" value="201208-378803-msgf.idpDB" />
            <param name="MaxFDRScore" value="0.05" />
            <param name="filter_at_gene_level_condition.MinDistinctPeptides" value="2" />
            <param name="filter_at_gene_level_condition.MinSpectra" value="2" />
            <param name="filter_at_gene_level_condition.MinAdditionalPeptides" value="1" />
            <param name="MinSpectraPerDistinctMatch" value="1" />
            <param name="MinSpectraPerDistinctPeptide" value="1" />
            <param name="MaxProteinGroupsPerPeptide" value="10" />
            <output name="output" file="201208-378803-msgf-filtered.idpDB" compare="sim_size" delta="500000" />
        </test>
        <test>
            <param name="input" value="201208-378803-cm.idpDB" />
            <param name="MaxFDRScore" value="0.05" />
            <param name="filter_at_gene_level_condition.MinDistinctPeptides" value="2" />
            <param name="filter_at_gene_level_condition.MinSpectra" value="2" />
            <param name="filter_at_gene_level_condition.MinAdditionalPeptides" value="1" />
            <param name="MinSpectraPerDistinctMatch" value="1" />
            <param name="MinSpectraPerDistinctPeptide" value="1" />
            <param name="MaxProteinGroupsPerPeptide" value="10" />
            <output name="output" file="201208-378803-cm-filtered.idpDB" compare="sim_size" delta="500000" />
        </test>
        <test>
            <param name="input" value="201208-378803-mm.idpDB,201208-378803-msgf.idpDB,201208-378803-cm.idpDB" />
            <param name="MaxFDRScore" value="0.05" />
            <param name="filter_at_gene_level_condition.MinDistinctPeptides" value="2" />
            <param name="filter_at_gene_level_condition.MinSpectra" value="2" />
            <param name="filter_at_gene_level_condition.MinAdditionalPeptides" value="1" />
            <param name="MinSpectraPerDistinctMatch" value="1" />
            <param name="MinSpectraPerDistinctPeptide" value="1" />
            <param name="MaxProteinGroupsPerPeptide" value="10" />
            <output name="output" file="201208-378803.idpDB" compare="sim_size" delta="500000" />
        </test>
    </tests>
    <help>
<![CDATA[
**What it does**

Merges and filters one or more IDPicker 3 idpDB files into a combined idpDB file. Protein assembly (e.g. parsimony) is conducted on the combined set of proteins.
]]>
    </help>
    <citations>
        <citation type="doi">10.1021/pr900360j</citation>
        <citation type="bibtex">@misc{toolsGalaxyP, author = {Chilton, J, Chambers MC, et al.}, title = {Galaxy Proteomics Tools}, publisher = {GitHub}, journal = {GitHub repository},
          year = {2015}, url = {https://github.com/galaxyproteomics/tools-galaxyp}}</citation> <!-- TODO: fix substitution of commit ", commit = {$sha1$}" -->
    </citations>
</tool>