view abims_xcms_retcor.xml @ 9:e4e0254a3c0a draft

planemo upload for repository https://github.com/workflow4metabolomics/xcms commit 4897a06ef248e2e74e57a496dd68adbda3c828f1

<tool id="abims_xcms_retcor" name="xcms.retcor" version="2.1.1">

    <description>Retention Time Correction using retcor function from xcms R package </description>

    <macros>
        <import>macros.xml</import>
    </macros>

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

    <command><![CDATA[
        @COMMAND_XCMS_SCRIPT@
        image '$image'
        xfunction retcor

        xsetRdataOutput '$xsetRData'
        ticspdf '$ticsCorPdf'
        bicspdf '$bpcsCorPdf'
        rplotspdf '$rplotsPdf'

        method $methods.method
        #if $methods.method == "obiwarp":
            profStep $methods.profStep
        #else
            smooth $methods.smooth
            extra $methods.extra
            missing $methods.missing
            #if $methods.options.option == "show":
                span $methods.options.span
                family $methods.options.family
                plottype $methods.options.plottype
            #end if
        #end if

        @COMMAND_FILE_LOAD@

        @COMMAND_LOG_EXIT@
    ]]></command>

    <inputs>
        <param name="image" type="data" format="rdata.xcms.raw,rdata.xcms.group,rdata" label="xset RData file" help="output file from another function xcms (xcmsSet, retcor etc.)" />
        <conditional name="methods">
            <param name="method" type="select" label="Method to use for retention time correction" help="[method] See the help section below" >
                <option value="obiwarp" >obiwarp</option>
                <option value="peakgroups" selected="true">peakgroups</option>
            </param>
            <when value="obiwarp">
                <param name="profStep" type="float" value="1" label="Step size (in m/z)" help="[profStep] to use for profile generation from the raw data files" />
            </when>
            <when value="peakgroups">
                <param name="smooth" type="select" label="Smooth method" help="[smooth] either 'loess’ for non-linear alignment or ‘linear’ for linear alignment" >
                    <option value="loess">loess</option>
                    <option value="linear">linear</option>
                </param>
                <param name="extra" type="integer" value="1" label="Number of extra peaks to allow in retention time correction correction groups" help="[extra]" />
                <param name="missing" type="integer" value="1" label="Number of missing samples to allow in retention time correction groups" help="[missing]" />

                <conditional name="options">
                    <param name="option" type="select" label="Advanced options">
                        <option value="show">show</option>
                        <option value="hide" selected="true">hide</option>
                    </param>
                    <when value="show">
                        <param name="span" type="float" value="0.2" label="Degree of smoothing for local polynomial regression fitting" help="[span]"/>

                        <param name="family" type="select" label="Family" help="[family] if gaussian fitting is by least-squares with no outlier removal, and if symmetric a re descending M estimator is used with Tukey's biweight function, allowing outlier removal">
                            <option value="gaussian" selected="true">gaussian</option>
                            <option value="symmetric">symmetric</option>
                        </param>

                        <param name="plottype" type="select" help="[plottype] if deviation plot retention time deviation points and regression fit, and if mdevden also plot peak overall peak density and retention time correction peak density">
                            <option value="none" selected="true">none</option>
                            <option value="deviation">deviation</option>
                            <option value="mdevden">mdevden</option>
                        </param>

                    </when>
                    <when value="hide">
                    </when>
                </conditional>
            </when>
        </conditional>

        <expand macro="input_file_load"/>

    </inputs>

    <outputs>
        <data name="xsetRData" format="rdata.xcms.retcor" label="${image.name[:-6]}.retcor.RData" />
        <data name="rplotsPdf" format="pdf"  label="${image.name[:-6]}.retcor.Rplots.pdf">
            <filter>(methods['method'] == 'peakgroups')</filter>
            <filter>(options['option'] == 'show')</filter>
            <filter>(family == 'symmetric')</filter>
            <filter>(plottype != 'none')</filter>
        </data>
        <data name="ticsCorPdf"   format="pdf"  label="${image.name[:-6]}.retcor.TICs_corrected.pdf" />
        <data name="bpcsCorPdf"   format="pdf" label="${image.name[:-6]}.retcor.BPCs_corrected.pdf" />
        <data name="log" format="txt" label="xset.log.txt"  hidden="true" />
    </outputs>

    <tests>
        <!--<test>
            <param name="image" value="xset.group.RData"/>
            <param name="methods|method" value="peakgroups"/>
            <param name="methods|smooth" value="loess"/>
            <param name="methods|extra" value="1"/>
            <param name="methods|missing" value="1"/>
            <param name="methods|options|option" value="show"/>
            <param name="methods|options|span" value="0.2"/>
            <param name="methods|options|family" value="gaussian"/>
            <param name="methods|options|plottype" value="deviation"/>
            <param name="zipfile_load_conditional|zipfile_load_select" value="yes" />
            <param name="zipfile_load_conditional|zip_file" value="sacuri_dir_root.zip"  ftype="zip" />
            <output name="log">
                <assert_contents>
                    <has_text text="object with 4 samples" />
                    <has_text text="Time range: 0.2-1140.1 seconds (0-19 minutes)" />
                    <has_text text="Mass range: 50.0021-999.9863 m/z" />
                    <has_text text="Peaks: 59359 (about 14840 per sample)" />
                    <has_text text="Peak Groups: 0" />
                    <has_text text="Sample classes: bio, blank" />
                </assert_contents>
            </output>
        </test>-->
        <test>
            <param name="image" value="faahKO.xset.group.RData"/>
            <param name="methods|method" value="peakgroups"/>
            <param name="methods|smooth" value="loess"/>
            <param name="methods|extra" value="1"/>
            <param name="methods|missing" value="1"/>
            <param name="methods|options|option" value="show"/>
            <param name="methods|options|span" value="0.2"/>
            <param name="methods|options|family" value="gaussian"/>
            <param name="methods|options|plottype" value="deviation"/>
            <expand macro="test_file_load_zip"/>
            <output name="log">
                <assert_contents>
                    <has_text text="object with 4 samples" />
                    <has_text text="Time range: 2507.7-4481.7 seconds (41.8-74.7 minutes)" />
                    <has_text text="Mass range: 200.1-600 m/z" />
                    <has_text text="Peaks: 9251 (about 2313 per sample)" />
                    <has_text text="Peak Groups: 0" />
                    <has_text text="Sample classes: KO, WT" />
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="image" value="faahKO-single-class.xset.group.RData"/>
            <param name="methods|method" value="peakgroups"/>
            <param name="methods|smooth" value="loess"/>
            <param name="methods|extra" value="1"/>
            <param name="methods|missing" value="1"/>
            <param name="methods|options|option" value="show"/>
            <param name="methods|options|span" value="0.2"/>
            <param name="methods|options|family" value="gaussian"/>
            <param name="methods|options|plottype" value="deviation"/>
            <expand macro="test_file_load_single"/>
            <output name="log">
                <assert_contents>
                    <has_text text="object with 4 samples" />
                    <has_text text="Time range: 2507.7-4481.7 seconds (41.8-74.7 minutes)" />
                    <has_text text="Mass range: 200.1-600 m/z" />
                    <has_text text="Peaks: 9251 (about 2313 per sample)" />
                    <has_text text="Peak Groups: 0" />
                    <has_text text="Sample classes: KO, WT" />
                </assert_contents>
            </output>
        </test>
    </tests>

    <help><![CDATA[

@HELP_AUTHORS@

===========
Xcms.retcor
===========

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

After matching peaks into groups, xcms can use those groups to identify and correct
correlated drifts in retention time from run to run. The aligned peaks can then be
used for a second pass of peak grouping which will be more accurate than the first.
The whole process can be repeated in an iterative fashion. Not all peak groups will be helpful
for identifying retention time drifts. Some groups may be missing peaks from a large
fraction of samples and thus provide an incomplete picture of the drift at that time point.
Still others may contain multiple peaks from the same sample, which is a sign of impropper grouping.

.. class:: warningmark

**After an retcor step, it is mandatory to do a group step, otherwise the rest of the workflow will not work with the RData file. (the initial peak grouping becomes invalid and is
discarded)**



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


**Upstream tools**

========================= ================= ======= ==========
Name                      output file       format  parameter
========================= ================= ======= ==========
xcms.group                xset.group.RData  RData   RData file
========================= ================= ======= ==========


**Downstream tools**

+---------------------------+------------------+--------+
| Name                      | Output file      | Format |
+===========================+==================+========+
|xcms.group                 | xset.retcor.RData| RData  |
+---------------------------+------------------+--------+

The output file **xset.retcor.RData** is an RData file. You can continue your analysis using it in **xcms.group** tool as an next step.


**General schema of the metabolomic workflow**

.. image:: xcms_retcor_workflow.png


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

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


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

Method
------

**peakgroups**

    | xcms ignores those groups by only considering well-behaved peak groups which are missing at most one sample and have at most one extra peak. (Those values can be changed with the **missing** and **extra** arguments.)
    | For each of those well-behaved groups, the algorithm calculates a median retention time and, for every sample, a deviation from that median. Within a sample, the observed deviation generally changes over time in a nonlinear fashion. Those changes are approximated using a local polynomial regression technique implemented in the **loess** function. By default, the curve fitting is done using least-squares on all data points.
    | However, it is possible to enable outlier detection and removal by setting the **family** argument to **symmetric**.

**obiwarp**

    | Calculate retention time deviations for each sample using the obiwarp code at "http://obi-warp.sourceforge.net/". This function is able to align multiple samples by a center-star strategy. Ordered Bijective Interpolated Warping (OBI-Warp) aligns matrices along a single axis using Dynamic Time Warping (DTW) and a one-to-one (bijective) interpolated warp function. OBI-Warp harnesses the non-linear, comprehensive alignment power of DTW and builds on the discrete, non-bijective output of DTW to give natural interpolants that can be used across multiple datasets.
    | For the original publication see :**Chromatographic Alignment of ESI-LC-MS Proteomics Data Sets by Ordered Bijective Interpo-lated Warping John T. Prince and, Edward M. Marcotte Analytical Chemistry 2006 78 (17), 6140-6152.**


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

xset.group.retcor.TICs_corrected.pdf

    | "Total Ion Chromatograms" graph in pdf format,corrected after a retcor step.

xset.group.retcor.BPCs_corrected.pdf

    | "Total Io"Base Peak Chromatograms" graph in pdf format,corrected after a retcor step

xset.group.retcor.RData: rdata.xcms.retcor format

    | Rdata file that will be necessary in the **xcms.group** step of the workflow.


------

.. class:: infomark

The output file is an xset.retcor.RData file. You can continue your analysis using it in **xcms.fillPeaks** tool.


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

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

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

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

Parameters
----------

    | Method: -> **peakgroups**
    | smooth: -> **loess**
    | extra: -> **1**
    | missing -> **1**
    | Advanced options: -> **show**
    | span -> **0.2**
    | family -> **gaussian**
    | plottype -> **deviation**


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

    | **1) xset.group.retcor.RData: RData file**

    | **2) Example of an xset.group.retcor.TICs_corrected pdf file**

.. image:: xcms_retcor.png


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

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

**Version 2.1.1 - 29/11/2017**

- BUGFIX: To avoid issues with accented letter in the parentFile tag of the mzXML files, we changed a hidden mechanim to LC_ALL=C

**Version 2.1.0 - 03/02/2017**

- IMPROVEMENT: xcms.retcor can deal with merged individual data

**Version 2.0.8 - 22/12/2016**

- BUGFIX: when having only one group (i.e. one folder of raw data) the BPC and TIC pdf files do not contain any graph

**Version 2.0.7 - 06/07/2016**

- UPGRADE: upgrate the xcms version from 1.44.0 to 1.46.0

**Version 2.0.6 - 04/04/2016**

- TEST: refactoring to pass planemo test using conda dependencies


**Version 2.0.5 - 10/02/2016**

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

- BUGFIX: some pdf remained empty even when the process succeed

- UPDATE: refactoring of internal management of inputs/outputs

- UPDATE: refactoring to feed the new report tool


**Version 2.0.2 - 02/06/2015**

- IMPROVEMENT: new datatype/dataset formats (rdata.xcms.raw, rdata.xcms.group, rdata.xcms.retcor ...) will facilitate the sequence of tools and so avoid incompatibility errors.

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


    ]]></help>


    <expand macro="citation" />

</tool>