comparison idpassemble.xml @ 15:4aa6a8331445 draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/bumbershoot commit 2d404b98b40ff043be71bea81c114ea3433c0751

14:87f2a3c9425b

<?xml version="1.0"?>
<tool id="idpassemble" name="idpAssemble" version="@VERSION@.1">
    <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" />

            #if $filter_at_gene_level_condition.FilterAtGeneLevel
            -FilterAtGeneLevel 1
            #end if
            -SummarizeSources 1
            
            #if $AssignSourceHierarchy
            -AssignSourceHierarchy '$AssignSourceHierarchy'
            #end if
            
            #if $IsobaricSampleMapping
            -IsobaricSampleMapping '$IsobaricSampleMapping'
            #end if
            
            #if len($input) > 1
                -MergedOutputFilepath output
                #for $i in $input

            </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." />
        <param argument="-AssignSourceHierarchy" type="data" format="tabular" optional="true" label="Assign source files to groups" help="A tab-delimited file that organizes source files (e.g. individual runs in a fractionated experiment) into groups. See below for more details." />
        <param argument="-IsobaricSampleMapping" type="data" format="tabular" optional="true" label="Assign sample names to reporter ions" help="A tab-delimited file that gives sample names to isobaric reporter ion channels (i.e. iTRAQ, TMT) across a given source group. See below for more details." />
    </inputs>
    <outputs>
        <data format="idpdb" name="output" from_work_dir="output" />
    </outputs>
    <tests>

            <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" />
            <param name="AssignSourceHierarchy" value="assembly.tsv" ftype="tabular" />
            <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="MaxProteinGroupsPerPeptide" value="10" />
            <output name="output" file="201208-378803.idpDB" compare="sim_size" delta="500000" />
        </test>
        <test>
            <param name="input" value="201208-378803-embeddedGenesAndQuantitation.idpDB" />
            <param name="IsobaricSampleMapping" value="mapping.tsv" ftype="tabular" />
            <param name="AssignSourceHierarchy" value="assembly.tsv" ftype="tabular" />
            <output name="output" file="201208-378803-embeddedGenesAndQuantitationWithMapping.idpDB" compare="sim_size" delta="500000" />
        </test>
    </tests>

<![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.


**AssignSourceHierarchy**
The assembly file is a tab-delimited file with two columns that organizes the sources (individual runs) into a hierarchy.
The first column is the name of a source group, the second column is the source path or name to assign to that group.
A forward slash in the group name adds another level to the hierarchy (just like a directory path).

*A simple example:*
======  ===========
/repA   repA1.idpDB
/repA   repA2.idpDB
/repB   repB1.idpDB
/repB   repB2.idpDB
======  ===========

*A multi-level example:*
=====  ===========
/A/1   A1_f1
/A/1   A1_f2
/A/2   A2_f1
/A/2   A2_f2
/B/1   B1_f1
/B/1   B1_f2
/B/2   B2_f1
/B/2   B2_f2
=====  ===========


**IsobaricSampleMapping**
The mapping file is a tab-delimited file with two columns. The first column is the full path to a source group,
the second column is a comma-delimited list of sample names, in ascending order of reporter ion mass. The special
sample name *Reference*, if present, will be used to normalize the other channels. Samples named *Empty* will be
ignored.

*iTRAQ-4plex example:*
===============================  ==========================
/Case/Group1_A123_B456_C789      A123,B456,C789,Reference
/Case/Group2_D123_E456_F789      D123,E456,F789,Reference
/Control/Group3_X123_Y456_Z789   Reference,X123,Y456,Z789
/Control/Group4_U123_V456        U123,Reference,V456,Empty
===============================  ==========================

*TMT-10plex example:*
=============================  ================================================================================
/Group1_Cases1-4_Controls1-4   Case1,Case2,Case3,Case4,Reference,Control1,Control2,Control3,Control4,Reference
/Group2_Cases5-8_Controls5-8   Case5,Case6,Case7,Case8,Reference,Control5,Control6,Control7,Control8,Reference
=============================  ================================================================================

]]>
    </help>
    <citations>
        <citation type="doi">10.1021/pr900360j</citation>

15:4aa6a8331445

<?xml version="1.0"?>
<tool id="idpassemble" name="idpAssemble" version="@VERSION@.2">
    <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" />

            #if $filter_at_gene_level_condition.FilterAtGeneLevel
            -FilterAtGeneLevel 1
            #end if
            -SummarizeSources 1
            
            #if $AssignSourceHierarchyCondition.HasAssignSourceHierarchy
            -AssignSourceHierarchy '$AssignSourceHierarchyCondition.AssignSourceHierarchy'
            #end if
            
            #if $IsobaricSampleMappingCondition.HasIsobaricSampleMapping
            -IsobaricSampleMapping '$IsobaricSampleMappingCondition.IsobaricSampleMapping'
            #end if
            
            #if len($input) > 1
                -MergedOutputFilepath output
                #for $i in $input

            </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." />

        <conditional name="AssignSourceHierarchyCondition">
            <param name="HasAssignSourceHierarchy" type="boolean" truevalue="1" falsevalue="0" label="Assign sources to a hierarchy?"/>
            <when value="1">
                <param argument="-AssignSourceHierarchy" type="data" format="tabular" optional="true" label="Assign source files to groups" help="A tab-delimited file that organizes source files (e.g. individual runs in a fractionated experiment) into groups. See below for more details." />
            </when>
            <when value="0">
            </when>
        </conditional>
        <conditional name="IsobaricSampleMappingCondition">
            <param name="HasIsobaricSampleMapping" type="boolean" truevalue="1" falsevalue="0" label="Assign sample names to reporter ions?"/>
            <when value="1">
                <param argument="-IsobaricSampleMapping" type="data" format="tabular" optional="true" label="Assign sample names to reporter ions" help="A tab-delimited file that gives sample names to isobaric reporter ion channels (i.e. iTRAQ, TMT) across a given source group. See below for more details." />
            </when>
            <when value="0">
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data format="idpdb" name="output" from_work_dir="output" />
    </outputs>
    <tests>

            <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" />
            <param name="HasAssignSourceHierarchy" value="1" />
            <param name="AssignSourceHierarchy" value="assembly.tsv" ftype="tabular" />
            <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="MaxProteinGroupsPerPeptide" value="10" />
            <output name="output" file="201208-378803.idpDB" compare="sim_size" delta="500000" />
        </test>
        <test>
            <param name="input" value="201208-378803-embeddedGenesAndQuantitation.idpDB" />
            <param name="HasAssignSourceHierarchy" value="1" />
            <param name="HasIsobaricSampleMapping" value="1" />
            <param name="IsobaricSampleMapping" value="mapping.tsv" ftype="tabular" />
            <param name="AssignSourceHierarchy" value="assembly.tsv" ftype="tabular" />
            <output name="output" file="201208-378803-embeddedGenesAndQuantitationWithMapping.idpDB" compare="sim_size" delta="500000" />
        </test>
    </tests>

<![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.

====

**AssignSourceHierarchy**

The assembly file is a tab-delimited file with two columns that organizes the sources (individual runs) into a hierarchy.
The first column is the name of a source group, the second column is the source path or name to assign to that group.
A forward slash in the group name adds another level to the hierarchy (just like a directory path).

*A simple example:*

::

/repA	repA1.idpDB
/repA	repA2.idpDB
/repB	repB1.idpDB
/repB	repB2.idpDB


*A multi-level example:*

::

/A/1	A1_f1
/A/1	A1_f2
/A/2	A2_f1
/A/2	A2_f2
/B/1	B1_f1
/B/1	B1_f2
/B/2	B2_f1
/B/2	B2_f2

====

**IsobaricSampleMapping**

The mapping file is a tab-delimited file with two columns. The first column is the full path to a source group,
the second column is a comma-delimited list of sample names, in ascending order of reporter ion mass. The special
sample name *Reference*, if present, will be used to normalize the other channels. Samples named *Empty* will be
ignored.


*iTRAQ-4plex example:*

::

/Case/Group1_A123_B456_C789	A123,B456,C789,Reference
/Case/Group2_D123_E456_F789	D123,E456,F789,Reference
/Ctrl/Group3_X123_Y456_Z789	Reference,X123,Y456,Z789
/Ctrl/Group4_U123_V456_None	U123,Reference,V456,Empty


*TMT-10plex example:*

::

/Group1_Cases1-4_Controls1-4	Case1,Case2,Case3,Case4,Reference,Control1,Control2,Control3,Control4,Reference
/Group2_Cases5-8_Controls5-8	Case5,Case6,Case7,Case8,Reference,Control5,Control6,Control7,Control8,Reference

]]>
    </help>
    <citations>
        <citation type="doi">10.1021/pr900360j</citation>