view abims_CAMERA_annotateDiffreport.xml @ 18:85b8351ded6c draft

planemo upload commit a57205d251bdebafdee164225fd03ac4d821e49c-dirty
author lecorguille
date Wed, 06 Jul 2016 17:28:55 -0400
parents af2d29943e97
children fa663873dc54
line wrap: on
line source

<tool id="abims_CAMERA_annotateDiffreport" name="CAMERA.annotate" version="2.1.6">

    <description>CAMERA annotate function. Returns annotation results (isotope peaks, adducts and fragments) and a diffreport if more than one condition.</description>
    
    <macros>
        <import>macros.xml</import>
    </macros>

    <expand macro="requirements"/>
    <expand macro="stdio"/>

    <command><![CDATA[
        @COMMAND_CAMERA_SCRIPT@
        xfunction annotatediff 
        image $image

        variableMetadataOutput $variableMetadata
        dataMatrixOutput $datamatrix
        xsetRdataOutput $rdata

        convert_param $convert_param num_digits $num_digits 
        nSlaves \${GALAXY_SLOTS:-1}
        sigma $sigma perfwhm $perfwhm 
        maxcharge $maxcharge maxiso $maxiso minfrac $minfrac
        ppm $ppm mzabs $mzabs intval $intval 
        max_peaks $max_peaks
        quick $quick_block.quick
        #if $quick_block.quick == "FALSE"
            polarity $quick_block.polarity
            cor_eic_th $quick_block.cor_eic_th
            graphMethod $quick_block.graphMethod 
            pval $quick_block.pval 
            calcCiS $quick_block.calcCiS
            calcIso $quick_block.calcIso
            calcCaS $quick_block.calcCaS
            #if $quick_block.rules_block.rules_select == "FALSE"
                multiplier $quick_block.rules_block.multiplier
            #else
                multiplier $quick_block.rules_block.rules
            #end if
        #end if

        #if $options.option == "show":
            runDiffreport TRUE
            eicmax $options.eicmax
            eicwidth $options.eicwidth
            value $options.value
            sortpval $options.sortpval 
            h $options.h
            w $options.w
            mzdec $options.mzdec
            new_file_path ${__new_file_path__}/primary_${output_diffreport.id}_
        #end if
            
        @COMMAND_ZIPFILE_LOAD@

    ]]></command>

    <inputs>
    
    
        <param name="image" type="data" label="RData file" format="rdata.xcms.fillpeaks,rdata" help="output file from another function xcms (fillPeaks)" />

        <param name="convert_param" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="Convert retention time (seconds) into minutes" help="Convert the columns rtmed, rtmin and rtmax into minutes"/>
        <param name="num_digits" type="integer" value="4" label="" help="Number of decimal places for mass values reported in ions identifiers. A minimum of 4 decimal places should be set" />

        <param name="sigma" type="integer" value="6" label="groupFWHM: multiplier of the standard deviation" help="[sigma]" />
        <param name="perfwhm" type="float" value="0.6" max="1" min="0" label="groupFWHM: percentage of FWHM width" help="[perfwhm]" />
        <param name="maxcharge" type="integer" value="3" label="findIsotopes: max. ion charge" help="[maxcharge]" />
        <param name="maxiso" type="integer" value="4" label="findIsotopes: max. number of expected isotopes" help="[maxiso]" />
        <param name="minfrac" type="float" value="0.5" max="1" min="0" label="findIsotopes: The percentage number of samples, which must satisfy the C12/C13 rule for isotope annotation" help="[minfrac]" />
        <param name="ppm" type="integer" value="5" label="General ppm error" help="[ppm]" />
        <param name="mzabs" type="float" value="0.015" label="mzabs" help="General absolut error in m/z" />
        <param name="intval" type="select" label="General used intensity value" help="[intval] See the help section below">
            <option value="into" selected="true">into</option>
            <option value="maxo" >maxo</option>
            <option value="intb">intb</option>
        </param> 
    

        <param name="max_peaks" type="integer" value="100" label="How much peaks will be calculated in every thread using the parallel mode" help="[max_peaks]" />
        <conditional name="quick_block">
            <param name="quick" type="select" label="Quick mode" help="[quick] If TRUE, use only groupFWHM and findIsotopes functions. Else if FALSE, use also groupCorr and findAdducts">
                <option value="TRUE">TRUE</option>
                <option value="FALSE" selected="true">FALSE</option>
            </param>
            <when value="FALSE">
                <param name="polarity" type="select" label="findAdducts: Which polarity mode was used for measuring of the ms sample" help="polarity">
                    <option value="positive" >positive</option>
                    <option value="negative" selected="true">negative</option>
                </param>		
                <param name="cor_eic_th" type="float" value="0.75" max="1" min="0" label="groupCorr: correlation threshold (0..1)" help="[cor_eic_th]" />
                <param name="graphMethod" type="select" label="groupCorr: Method selection for grouping peaks after correlation analysis into pseudospectra" help="[graphMethod]">
                    <option value="hcs" selected="true">hcs</option>
                    <option value="lpc">lpc</option>
                </param>
                <param name="pval" type="float" value="0.05" max="1" min="0" label="groupCorr: significant correlation threshold" help="[pval]" />
                <param name="calcCiS" type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE" label="groupCorr: Use correlation inside samples for peak grouping" help="[calcCiS]"/>
                <param name="calcIso" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="groupCorr: Use isotopic relationship for peak grouping" help="[calcIso]"/>
                <param name="calcCaS" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="groupCorr: Use correlation across samples for peak grouping" help="[calcCaS]"/>
                <conditional name="rules_block">
                    <param name="rules_select" type="select" label="Use a personal ruleset file">  
                        <option value="TRUE">TRUE</option>
                        <option value="FALSE" selected="true">FALSE</option>
                    </param>
                    <when value="FALSE">
                        <param name="multiplier" type="integer" value="3" label="findAdducts: If no ruleset is provided, calculate ruleset with max. number n of [nM+x] clusterions" help="[multiplier]" /> 
                    </when>
                    <when value="TRUE">
                        <param name="rules" type="data" format="csv" label="findAdducts: User defined ruleset" help="[rules]" />
                    </when>
                </conditional>
            </when>	
            <when value="TRUE">
                <param name="polarity" type="hidden" value="quick" label="for the output label" help="for the output label" />
            </when>	
        </conditional>

        <!-- Annotatediffreport specific parameters -->
        <conditional name="options">
            <param name="option" type="select" label="Number of condition">
                <option value="hide" selected="true">One condition</option>
                <option value="show">Two or more conditions</option>  
            </param>
            <when value="show">
                <param name="eicmax" type="integer" value="0" label="diffreport: number of the most significantly different analytes to create EICs for" help="[eicmax]" />
                <param name="eicwidth" type="integer" value="200" label="diffreport: width (in seconds) of EICs produced" help="[eicwidth]" />
                <param name="value" type="select" label="diffreport: Intensity values to be used for the diffreport" help="[value]">
                    <option value="into" selected="true">into</option>
                    <option value="maxo" >maxo</option>
                    <option value="intb">intb</option>
                </param> 
                <param name="h" type="integer" value="480" label="diffreport: Numeric variable for the height of the eic and boxplots that are printed out" help="[height]" /> 
                <param name="w" type="integer" value="640" label="diffreport: Numeric variable for the width of the eic and boxplots print out made" help="[width]" />
                <param name="mzdec" type="integer" value="2" label="diffreport: Number of decimal places of title m/z values in the eic plot" help="[mzdec]" />
                <param name="sortpval" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="diffreport: logical indicating whether the reports should be sorted by p-value" help="[sortpval]"/>
            </when>
            <when value="hide">
            </when>
        </conditional>
        
        <expand macro="zipfile_load"/>
    </inputs>

    <outputs>
        <data name="variableMetadata" format="tabular" label="${image.name[:-6]}.annotate.variableMetadata.tsv" />
        <data name="datamatrix" format="tabular" label="${image.name[:-6]}.annotate.dataMatrix.tsv" />
        <data name="rdata" format="rdata.camera.quick" label="${image.name[:-6]}.annotate.${$quick_block.polarity}.Rdata" >
            <change_format>
                <when input="quick_block.polarity" value="positive" format="rdata.camera.positive" />
                <when input="quick_block.polarity" value="negative" format="rdata.camera.negative" />
            </change_format>
        </data>
        <data name="output_diffreport" format="text" label="${image.name[:-6]}.annotateDiffreport" hidden="True">
		        <filter>(options['option'] == 'show')</filter>
	      </data>    
    </outputs>
    
    <tests>
        <!--<test>
            <param name="image" value="xset.group.retcor.group.fillPeaks.RData"/>
            <param name="convert_param" value="False"/>
            <param name="num_digits" value="0"/>
            <param name="sigma" value="6"/>
            <param name="perfwhm" value="0.6"/>
            <param name="maxcharge" value="3"/>
            <param name="maxiso" value="4"/>
            <param name="minfrac" value="0.5"/>
            <param name="ppm" value="5"/>
            <param name="mzabs" value="0.015"/>
            <param name="intval" value="into"/>
            <param name="max_peaks" value="100"/>
            <param name="quick_block|quick" value="FALSE"/>
            <param name="quick_block|polarity" value="negative"/>
            <param name="quick_block|cor_eic_th" value="0.75"/>
            <param name="quick_block|graphMethod" value="hcs"/>
            <param name="quick_block|pval" value="0.05"/>
            <param name="quick_block|calcCiS" value="True"/>
            <param name="quick_block|calcIso" value="False"/>
            <param name="quick_block|calcCaS" value="False"/>
            <param name="quick_block|multiplier" value="3"/>
            <param name="options|option" value="show"/>
            <param name="options|eicmax" value="200"/>
            <param name="options|eicwidth" value="200"/>
            <param name="options|value" value="into"/>
            <param name="options|h" value="480"/>
            <param name="options|w" value="640"/>
            <param name="options|mzdec" value="2"/>
            <param name="options|sortpval" value="False"/>
            <param name="zip_file" value="sacuri_dir_root.zip"  ftype="zip" />
            <output name="variableMetadata" file="xset.group.retcor.group.fillPeaks.annotate.variableMetadata.tsv" />
            <output name="datamatrix" file="xset.group.retcor.group.fillPeaks.annotate.dataMatrix.tsv" />
        </test>-->
        <test>
            <param name="image" value="faahKO.xset.group.retcor.group.fillpeaks.RData"/>
            <param name="convert_param" value="False"/>
            <param name="num_digits" value="0"/>
            <param name="sigma" value="6"/>
            <param name="perfwhm" value="0.6"/>
            <param name="maxcharge" value="3"/>
            <param name="maxiso" value="4"/>
            <param name="minfrac" value="0.5"/>
            <param name="ppm" value="5"/>
            <param name="mzabs" value="0.015"/>
            <param name="intval" value="into"/>
            <param name="max_peaks" value="100"/>
            <param name="quick_block|quick" value="FALSE"/>
            <param name="quick_block|polarity" value="negative"/>
            <param name="quick_block|cor_eic_th" value="0.75"/>
            <param name="quick_block|graphMethod" value="hcs"/>
            <param name="quick_block|pval" value="0.05"/>
            <param name="quick_block|calcCiS" value="True"/>
            <param name="quick_block|calcIso" value="False"/>
            <param name="quick_block|calcCaS" value="False"/>
            <param name="quick_block|multiplier" value="3"/>
            <param name="options|option" value="show"/>
            <param name="options|eicmax" value="200"/>
            <param name="options|eicwidth" value="200"/>
            <param name="options|value" value="into"/>
            <param name="options|h" value="480"/>
            <param name="options|w" value="640"/>
            <param name="options|mzdec" value="2"/>
            <param name="options|sortpval" value="False"/>
            <param name="zipfile_load_conditional|zipfile_load_select" value="yes" />
            <param name="zipfile_load_conditional|zip_file" value="faahKO_reduce.zip"  ftype="zip" />
            <output name="variableMetadata" file="faahKO.xset.group.retcor.group.fillPeaks.annotate.variableMetadata.tsv" />
            <output name="datamatrix" file="faahKO.xset.group.retcor.group.fillPeaks.annotate.dataMatrix.tsv" />
        </test>
    </tests>
    
    
    
    <help><![CDATA[
        
@HELP_AUTHORS@

================
CAMERA.annotate
================

-----------
Description
-----------

The R-package CAMERA is a Collection of Algorithms for MEtabolite
pRofile Annotation. Its primary purpose is the annotation and evaluation of
LC-MS data. It includes algorithms for annotation of isotope peaks, adducts
and fragments in peak lists. Additional methods cluster mass signals that
originate from a single metabolite, based on rules for mass differences and
peak shape comparison. To use the strength of already existing programs,
CAMERA is designed to interact directly with processed peak data from the
R-package **xcms**.

**What it does?**

The CAMERA annotation procedure can be split into two parts: We want to answer the questions which peaks occur from the same molecule and secondly compute its exact mass and annotate the ion species. Therefore CAMERA annotation workflow contains following primary functions: 1. peak grouping after retention time (**groupFWHM**) 2. peak group verification with peakshape correlation (**groupCorr**) Both methods separate peaks into different groups, which we define as ”pseu- dospectra”. Those pseudospectra can consists from one up to 100 ions, de- pending on the molecules amount and ionizability. Afterwards the exposure of the ion species can be performed with: 2 1. annotation of possible isotopes (**findIsotopes**) 2. annotation of adducts and calculating hypothetical masses for the group (**findAdducts**) This workflow results in a data-frame similar to a xcms peak table, that can be easily stored in a comma separated table .csv (Excel-readable). 

If you have two or more conditions, it will return a diffreport result within the annotation results.
The diffreport result shows the most significant differences between two sets of samples. Optionally
create extracted ion chromatograms for the most significant differences.


-----------------
Workflow position
-----------------


**Upstream tools**

========================= ==================== ====================== ==========
Name                      output file          format                 parameter
========================= ==================== ====================== ==========
xcms.fillPeaks            xset.fillPeaks.RData rdata.xcms.fillpeaks   RData file
========================= ==================== ====================== ==========


**Downstream tools**

+---------------------------+---------------------------------------+------------------------------------------------+
| Name                      | Output file                           | Format                                         |
+===========================+=======================================+================================================+
|CAMERA_combinexsAnnot      |xset.annotate.dataMatrix.tsv           | rdata.camera.positive or rdata.camera.negative |
+---------------------------+---------------------------------------+------------------------------------------------+
|Determine Vdk or Lowess    |xset.annotate.dataMatrix.tsv           | Tabular                                        |
+---------------------------+---------------------------------------+------------------------------------------------+
|Normalization Vdk/Lowess   |xset.annotate.dataMatrix.tsv           | Tabular                                        |
+---------------------------+---------------------------------------+------------------------------------------------+
|Anova                      |xset.annotate.dataMatrix.tsv           | Tabular                                        |
+---------------------------+---------------------------------------+------------------------------------------------+
|PCA                        |xset.annotate.dataMatrix.tsv           | Tabular                                        |
+---------------------------+---------------------------------------+------------------------------------------------+
|Hierarchical Clustering    |xset.annotate.dataMatrix.tsv           | Tabular                                        |
+---------------------------+---------------------------------------+------------------------------------------------+


The output file **xset.annotate.dataMatrix.tsv** is an tabular file. You can continue your analysis using it in the following tools:

    | Determine Vdk or Lowess
    | Normalization Vdk/Lowess
    | Anova
    | PCA
    | Hierarchical Clustering


**General schema of the metabolomic workflow**

.. image:: annotate_workflow.png

-----------
Input files
-----------

+---------------------------+---------------------------+
| Parameter : num + label   |   Format                  |
+===========================+===========================+
| 1 : RData file            |   rdata.xcms.fillpeaks    |
+---------------------------+---------------------------+


----------
Parameters
----------

diffreport: Intensity values to be used for the diffreport
----------------------------------------------------------

    | If **value="into"**, integrated peak intensities are used.
    | If **value="maxo"**, maximum peak intensities are used.
    | If **value="intb"**, baseline corrected integrated peak intensities are used (only available if peak detection was done by ‘findPeaks.centWave’).



------------
Output files
------------

xset.annotate.variableMetadata.tsv

    | For each metabolite (row) :
    | the value of the intensity in each sample, fold, anova, mzmed, mzmin, mzmax, rtmed, rtmin, rtmax, npeaks, isotopes, adduct and pcgroup

xset.annotate.dataMatrix.tsv

    | A tabular file which represents for each metabolite (row), the value of the intensity in each sample (column).
    
xset.annotate.zip

    | It contains filebase_eic, filebase_box and filebase.tsv for one conditon vs another (Anova analysis).

xset.annotate.Rdata rdata.camera.quick or rdata.camera.positive or rdata.camera.negative

    | Rdata file, that be used outside Galaxy in R.
    
------

.. class:: infomark 

The output **"xset.annotate.dataMatrix.tsv"** is a tabular file. You can continue your analysis using it in the following tools of the workflow:

    | Determine Vdk or Lowess (Data correction)
    | Normalization Vdk/Lowess (Data correction)
    | Anova (Statistical analysis)
    | PCA (Statistical analysis)
    | Hierarchical Clustering (Statistical analysis)

    
---------------------------------------------------

---------------
Working example
---------------

Input files
-----------

    | RData file -> **xset.fillPeaks.RData**

Parameters
----------

    | sortpval -> **false**
    | sigma -> **6 (default)**
    | perfwhm -> **0.6 (default)**
    | maxcharge -> **3 (default)**
    | maxiso -> **4 (default)**
    | minfrac -> **0.5 (default)**
    | ppm -> **500**
    | mzabs -> **0.015(default)**
    | Advanced options -> **hide**
    | Numver of condition -> Two or more conditioons
    | eicmax -> **200**
    | eicwidth -> **200 (default)**

    

Output files
------------

**Example of an xset.annotate.dataMatrix.tsv output**

.. image:: annotatediffreport_dataMatrix.png

**Example of a part of xset.annotate.variableMetadata.tsv output** 

.. image:: annotatediffreport_variableMetadata.png


---------------------------------------------------

Changelog/News
--------------

**Version 2.1.6 - 06/07/2016**

- IMPROVEMENT: add the possibility to use defined ruleset

**Version 2.1.5 - 21/04/2016**

- UPGRADE: upgrate the CAMERA version from 1.22.0 to 1.26.0


**Version 2.1.4 - 18/04/2016**

- TEST: refactoring to pass planemo test using conda dependencies


**Version 2.1.3 - 10/02/2016**

- BUGFIX: better management of errors. Datasets remained green although the process failed

- BUGFIX: the conversion into minutes of the retention time was applied to the diffreport outputs (several conditions)

- IMPROVEMENT: when there are several conditions, the tool will generate individual datasets (tsv, pdf) instead of a zip file. The usual png (eic, boxplot) will from now be integrated in two pdf.

- UPDATE: refactoring of internal management of inputs/outputs


VERSION 2.1.0 - 09/10/2015**

- BUGFIX: There was a bug with the CAMERA.annotate (generating a bad dataMatrix (intensities which don't match with the metabolites))


VERSION 2.1.0 - 07/06/2015**

- IMPROVEMENT: new datatype/dataset formats (rdata.camera.positive, rdata.camera.negative, rdata.camera.quick ...) will facilitate the sequence of tools and so avoid incompatibility errors.

- IMPROVEMENT: parameter labels have changed to facilitate their reading.

- UPDATE: merged with annotateDiffreport. Some parameters are dedicated to experiences with several conditions


    ]]></help>

    <expand macro="citation" />


</tool>