comparison abims_xcms_xcmsSet.xml @ 35:7f636ad1162b draft

planemo upload for repository https://github.com/workflow4metabolomics/xcms commit f01148783819c37e474790dbd56619862960448a

34:efd23113d5f4

<tool id="abims_xcms_xcmsSet" name="xcms findChromPeaks (xcmsSet)" version="@WRAPPER_VERSION@.0">
    <description>Chromatographic peak detection</description>

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

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

    <command><![CDATA[
        @COMMAND_XCMS_SCRIPT@/xcms_xcmsSet.r

        #if $input.is_of_type("mzxml") or $input.is_of_type("mzml") or $input.is_of_type("mzdata") or $input.is_of_type("netcdf"):
            singlefile_galaxyPath '$input' singlefile_sampleName '$input.name'
        #else
            zipfile '$input'
        #end if

        BPPARAM \${GALAXY_SLOTS:-1}

        #if $filterSection.filterAcquisitionNum != "":
            filterAcquisitionNum "c($filterSection.filterAcquisitionNum)"

        #end if

        method $methods.method

        #if $methods.method == "CentWave":
            ppm $methods.ppm
            peakwidth "c($methods.peakwidth)"
            ## Advanced
            snthresh $methods.CentWaveAdv.snthresh
            prefilter "c($methods.CentWaveAdv.prefilter)"
            mzCenterFun $methods.CentWaveAdv.mzCenterFun
            integrate $methods.CentWaveAdv.integrate
            mzdiff $methods.CentWaveAdv.mzdiff
            fitgauss $methods.CentWaveAdv.fitgauss
            noise $methods.CentWaveAdv.noise
            verboseColumns $methods.CentWaveAdv.verboseColumns
        #elif $methods.method == "MatchedFilter":
            fwhm $methods.fwhm
            binSize $methods.binSize
            impute $methods.impute_cond.impute
            #if $methods.impute_cond.impute == "linbase":

            verboseColumns $methods.verboseColumns
            scales "c($methods.scales)"
            nearbyPeak $methods.nearbyPeak
            ampTh $methods.ampTh
        #end if
        @COMMAND_LOG_EXIT@
    ]]></command>

    <inputs>

        <param name="input" type="data" format="mzxml,mzml,mzdata,netcdf,no_unzip.zip,zip" label="File(s) from your history containing your chromatograms" help="Single file mode for the format: mzxml, mzml, mzdata and netcdf. Zip file mode for the format: no_unzip.zip, zip. See the help section below." />

        <section name="filterSection" title="Spectra Filters" expanded="False">
            <param argument="filterAcquisitionNum" type="text" value="" optional="true" label="Filter on Acquisition Numbers" help="min,max">
                <expand macro="input_validator_range_integer"/>
            </param>

        <conditional name="methods">
            <param name="method" type="select" label="Extraction method for peaks detection" help="See the help section below">
                <option value="MatchedFilter" selected="true">MatchedFilter - peak detection in chromatographic space</option>
                <option value="CentWave">CentWave - chromatographic peak detection using the centWave method</option>
                <option value="MSW">MSW - single-spectrum non-chromatography MS data peak detection</option>
            </param>

            <!-- centWave Filter options -->
            <when value="CentWave">
                <param argument="ppm" type="integer" value="25" label="Max tolerated ppm m/z deviation in consecutive scans in ppm" help="for the initial ROI definition." />
                <param argument="peakwidth" type="text" value="20,50" label="Min,Max peak width in seconds" help="with the expected approximate peak width in chromatographic space.">
                    <expand macro="input_validator_range_float"/>
                </param>

                <section name="CentWaveAdv" title="Advanced Options" expanded="False">
                    <param argument="snthresh" type="integer" value="10" label="Signal to Noise ratio cutoff" />
                    <param argument="prefilter" type="text" value="3,100" label="Prefilter step for for the first analysis step (ROI detection)" help="Separate by coma k, I. Mass traces are only retained if they contain at least ‘k‘ peaks with intensity ‘>= I‘.">
                        <expand macro="input_validator_range_integer"/>
                    </param>
                    <param argument="mzCenterFun" type="select" label="Name of the function to calculate the m/z center of the chromatographic peak" >
                        <option value="wMean">intensity weighted mean of the peak's m/z values</option>
                        <option value="mean">mean of the peak's m/z values</option>
                        <option value="apex">use the m/z value at the peak apex</option>
                        <option value="wMeanApex3">ntensity weighted mean of the m/z value at the peak apex and the m/z values left and right of it</option>
                        <option value="meanApex3">mean of the m/z value of the peak apex and the m/z values left and right of it</option>
                    </param>
                    <param argument="integrate" type="select" label="Integration method" >
                        <option value="1">peak limits are found through descent on the mexican hat filtered data (more robust, but less exact)</option>
                        <option value="2">peak limits based on real data (more accurate but prone to noise)</option>
                    </param>
                    <param argument="mzdiff" type="float" value="-0.001" label="Minimum difference in m/z for peaks with overlapping retention times" help="can be negative to allow overlap" />
                    <param argument="fitgauss" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="fitgauss" help="whether or not a Gaussian should be fitted to each peak" />
                    <param argument="noise" type="integer" value="0" label="Noise filter" help="allowing to set a minimum intensity required for centroids to be considered in the first analysis step (centroids with intensity lower than ‘noise’ are omitted from ROI detection)." />
                    <param argument="verboseColumns" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="verbose Columns" help="whether additional peak meta data columns should be returned" />
                    <!-- roiList -->
                    <!-- firstBaselineCheck -->
                    <!-- roiScales -->
                </section>
            </when>

            <!-- matched Filter options -->
            <when value="MatchedFilter">
                <param argument="fwhm" type="integer" value="30" label="Full width at half maximum of matched filtration gaussian model peak" help="Only used to calculate the actual sigma" />
                <param argument="binSize" type="float" value="0.1" label="Step size to use for profile generation" help="The peak detection algorithm creates extracted ion base peak chromatograms (EIBPC) on a fixed step size. (Previously step)" />
                <conditional name="impute_cond">
                    <param argument="impute" type="select" label="Method to be used for missing value imputation" help="(previously profmethod)">

                    <param argument="mzdiff" type="float" value="0.6" label="Minimum difference in m/z for peaks with overlapping Retention Times" help="By default: 0.8-step*steps " />
                    <!-- index -->
                </section>
            </when>

            <!-- MSW Filter options -->
            <when value="MSW">
                <!---@TODO <param argument="winSize_noise" type="integer" value="500" label="The local window size to estimate the noise level" help="[winSize.noise]" />-->
                <param argument="snthresh" type="integer" value="3" label="Signal to Noise ratio cutoff" help="" />
                <param argument="verboseColumns" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="verbose Columns" help="whether additional peak meta data columns should be returned" />
                <param argument="scales" type="text" value="1,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,36,40,44,48,52,56,60,64" label="Scales of the Continuous Wavelet Transform (CWT)" help="Scales are linked to the width of the peaks that are to be detected." >

                <!-- peakThr -->
                <!-- tuneIn -->
                <!---@TODO <param argument="SNR_method" type="text" value="data.mean" label="SNR (Signal to Noise Ratio) method" help="[SNR.method] Method to estimate noise level. Currently, only 95 percentage quantile is supported." />-->
            </when>
        </conditional>
    </inputs>

    <outputs>
        <data name="xsetRData" format="rdata.xcms.raw" label="${input.name.rsplit('.',1)[0]}.xset.RData" from_work_dir="xcmsSet.RData" />
        <data name="sampleMetadata" format="tabular" label="${input.name.rsplit('.',1)[0]}.sampleMetadata.tsv" from_work_dir="sampleMetadata.tsv" >
            <filter>input.extension not in ["mzxml","mzml","mzdata","netcdf"]</filter>
        </data>
        <data name="log" format="txt" label="${input.name.rsplit('.',1)[0]}.xset.log.txt" from_work_dir="log.txt" />
    </outputs>

    <tests>

        <test>
            <param name="input" value="faahKO_reduce.zip"  ftype="zip" />
            <section name="filterSection">
                <param name="filterAcquisitionNum" value="100,5000" />
                <param name="filterRt" value="3000,4000" />
                <param name="filterMz" value="300,400" />
            </section>
            <conditional name="methods">
                <param name="method" value="CentWave" />
                <param name="ppm" value="25" />
                <param name="peakwidth" value="20,50" />
            </conditional>
            <assert_stdout>
                <has_text text="ppm: 25" />
                <has_text text="peakwidth: 20, 50" />
                <has_text text="object with 4 samples" />
                <has_text text="Time range: 3006.9-3978.7 seconds (50.1-66.3 minutes)" />
                <has_text text="Mass range: 300-400 m/z" />
                <has_text text="Peaks: 1311 (about 328 per sample)" />
                <has_text text="Peak Groups: 0" />
                <has_text text="Sample classes: KO, WT" />
            </assert_stdout>
        </test>
        <test>
            <param name="input" value="MM14.mzML"  ftype="mzxml" />
            <conditional name="methods">
                <param name="method" value="CentWave" />
                <param name="ppm" value="56" />
                <param name="peakwidth" value="5.275,13.5" />
            </conditional>
            <assert_stdout>
                <has_text text="ppm: 56" />
                <has_text text="peakwidth: 5.275, 13.5" />
                <has_text text="object with 1 samples" />
                <has_text text="Time range: 271-307.3 seconds (4.5-5.1 minutes)" />
                <has_text text="Mass range: 117.0357-936.7059 m/z" />
                <has_text text="Peaks: 222 (about 222 per sample)" />
                <has_text text="Peak Groups: 0" />
                <has_text text="Sample classes: ." />
            </assert_stdout>
        </test>
        <!-- DISABLE FOR TRAVIS
        Useful to generate test-data for the further steps
        <test>
            <param name="input" value="ko15.CDF"  ftype="netcdf" />
            <conditional name="methods">
                <param name="method" value="CentWave" />
                <param name="ppm" value="25" />
                <param name="peakwidth" value="20,50" />
            </conditional>
            <assert_stdout>
                <has_text text="object with 1 samples" />
                <has_text text="Time range: 2506.1-4471.7 seconds (41.8-74.5 minutes)" />
                <has_text text="Mass range: 200.2-600 m/z" />
                <has_text text="Peaks: 2262 (about 2262 per sample)" />
                <has_text text="Peak Groups: 0" />
                <has_text text="Sample classes: ." />
            </assert_stdout>
        </test>
        <test>
            <param name="input" value="ko16.CDF"  ftype="netcdf" />
            <conditional name="methods">
                <param name="method" value="CentWave" />
                <param name="ppm" value="25" />
                <param name="peakwidth" value="20,50" />
            </conditional>

                <has_text text="Peak Groups: 0" />
                <has_text text="Sample classes: ." />
            </assert_stdout>
        </test>
        <test>
            <param name="input" value="wt15.CDF"  ftype="netcdf" />
            <conditional name="methods">
                <param name="method" value="CentWave" />
                <param name="ppm" value="25" />
                <param name="peakwidth" value="20,50" />
            </conditional>

                <has_text text="Peak Groups: 0" />
                <has_text text="Sample classes: ." />
            </assert_stdout>
        </test>
        <test>
            <param name="input" value="wt16.CDF"  ftype="netcdf" />
            <conditional name="methods">
                <param name="method" value="CentWave" />
                <param name="ppm" value="25" />
                <param name="peakwidth" value="20,50" />
            </conditional>

        </test>
        -->
        <!-- DISABLE FOR TRAVIS
        Test to test the different methods parameters
        <test>
            <param name="input" value="MM8.mzML" ftype="mzxml" />
            <conditional name="methods">
                <param name="method" value="MatchedFilter" />
                <param name="fwhm" value="35" />
                <conditional name="impute_cond">
                    <param name="impute" value="linbase" />

                <has_text text="baseValue: 0.1" />
                <has_text text="distance: 1" />
            </assert_stdout>
        </test>
        <test>
            <param name="input" value="MM8.mzML" ftype="mzxml" />
            <conditional name="methods">
                <param name="method" value="MSW" />
                <param name="snthresh" value="4" />
                <param name="verboseColumns" value="true" />
            </conditional>

        </test>
        -->
        <!-- DISABLE FOR TRAVIS
        No more test-data/sacuri_dir_root.zip
        <test>
            <param name="input" value="sacuri_dir_root.zip"  ftype="zip" />
            <conditional name="methods">
                <param name="method" value="MatchedFilter" />
                <param name="step" value="0.01" />
                <param name="fwhm" value="4" />
                <conditional name="options_m">

        </test>
        -->
        <!--  DISABLE FOR TRAVIS
        No more test-data/sacuri_current_root.zip
        <test>
            <param name="input" value="sacuri_current_root.zip"  ftype="zip" />
            <conditional name="methods">
                <param name="method" value="CentWave" />
                <param name="ppm" value="25" />
                <param name="peakwidth" value="20,50" />
            </conditional>

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

**Upstream tools**

========================= ================= ======= =========
Name                      output file       format  parameter
========================= ================= ======= =========
NA                        NA                zip     NA
========================= ================= ======= =========


**Downstream tools**

+---------------------------+--------------------+-----------------+
| Name                      | Output file        | Format          |
+===========================+====================+=================+
|xcms.group                 | xset.RData         | rdata.xcms.raw  |
+---------------------------+--------------------+-----------------+
|PCA ellipsoid by factors   | sampleMetadata.tsv | Tabular         |
+---------------------------+--------------------+-----------------+
|Anova                      | sampleMetadata.tsv | Tabular         |
+---------------------------+--------------------+-----------------+


**Example of a metabolomic workflow**

.. image:: xcms_xcmsset_workflow.png


------

.. class:: infomark

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

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



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

+---------------------------+----------------------------------+
| Parameter : num + label   |   Format                         |
+===========================+==================================+
| OR : Zip file             |   zip                            |
+---------------------------+----------------------------------+
| OR : Single file          |   mzXML, mzML, mzData, netCDF    |
+---------------------------+----------------------------------+

**Choose your inputs**

You have two methods for your inputs:

    | Single file (recommended): You can put a single file as input. That way, you will be able to launch several xcmsSet in parallel and use "xcms.xcmsSet Merger" before "xcms.group"
    | Zip file: You can put a zip file containing your inputs: myinputs.zip (containing all your conditions as sub-directories).

Zip file: Steps for creating the zip file
-----------------------------------------

**Step1: Creating your directory and hierarchize the subdirectories**


VERY IMPORTANT: If you zip your files under Windows, you must use the 7Zip_ software, otherwise your zip will not be well unzipped on the platform W4M (zip corrupted bug).

.. _7Zip: http://www.7-zip.org/

Your zip should contain all your conditions as sub-directories. For example, two conditions (mutant and wild):
arabidopsis/wild/01.raw
arabidopsis/mutant/01.raw

**Step2: Creating a zip file**

Create your zip file (e.g.: arabidopsis.zip).

**Step 3 : Uploading it to our Galaxy server**

If your zip file is less than 2Gb, you get use the Get Data tool to upload it.

Otherwise if your zip file is larger than 2Gb, please refer to the HOWTO_ on workflow4metabolomics.org.

.. _HOWTO: http://application.sb-roscoff.fr/download/w4m/howto/galaxy_upload_up_2Go.pdf

For more informations, don't hesitate to send us an email at supportATworkflow4metabolomics.org).

Advices for converting your files for the XCMS input
----------------------------------------------------

We recommend you to convert your raw files to **mzXML** in centroid mode (smaller files) and the files will be compatible with the xmcs centWave method.

**We recommend you the following parameters:**

Use Filtering: **True**

Use Peak Picking: **True**

Peak Peaking -Apply to MS Levels: **All Levels (1-)** : Centroid Mode

Use zlib: **64**

Binary Encoding: **64**

m/z Encoding: **64**

Intensity Encoding: **64**


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

Extraction method for peaks detection
-------------------------------------

**CentWave**

    | The centWave algorithm perform peak density and wavelet based chromatographic peak detection for high resolution LC/MS data in centroid mode [Tautenhahn 2008].
    | Due to the fact that peak centroids are used, a binning step is not necessary.
    | The method is capable of detecting close-by-peaks and also overlapping peaks. Some efforts are made to detect the exact peak boundaries to get precise peak integrals.
    | See the CentWave_manual_

**MatchedFilter**

    | The _matchedFilter_ algorithm identifies peaks in the chromatographic time domain as described in [Smith 2006]. The intensity values are binned by cutting The LC/MS data into slices (bins) of a mass unit (‘binSize’ m/z) wide. Within each bin the maximal intensity is selected. The chromatographic peak detection is then performed in each bin by extending it based on the ‘steps’ parameter to generate slices comprising bins ‘current_bin - steps +1’ to ‘current_bin + steps - 1’. Each of these slices is then filtered with matched filtration using a second-derative Gaussian as the model peak shape. After filtration peaks are detected using a signal-to-ratio cut-off. For more details and illustrations see [Smith 2006].
    | See the MatchedFilter_manual_

**MSW**

    | Wavelet based, used for direct infusion data. Continuous wavelet transform (CWT) can be used to locate chromatographic peaks on different scales.
    | See the MSW_manual_

.. _CentWave_manual: https://rdrr.io/bioc/xcms/man/findChromPeaks-centWave.html#heading-2
.. _MatchedFilter_manual: https://rdrr.io/bioc/xcms/man/findChromPeaks-matchedFilter.html#heading-2
.. _MSW_manual: https://rdrr.io/bioc/xcms/man/findPeaks-MSW.html#heading-2

@HELP_XCMS_MANUAL@

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

xset.TICs_raw.pdf

    | "Total Ion Chromatograms" graph in pdf format.

xset.BPCs_raw.pdf

    | "Base Peak Chromatograms" graph in pdf format with each class samples opposed.

sampleMetadata.tsv

    | Tabular file that contains for each sample, it's associated class and polarity (positive,negative and mixed).
    | This file is necessary in the Anova and PCA step of the workflow.

xset.RData: rdata.xcms.raw format

    | Rdata file that is necessary in the second step of the workflow "xcms.group".

------

.. class:: infomark

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

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

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

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

    | zip_file -> **sacuri.zip**

Parameters
----------

    | Method -> **matchedFilter**
    | step   -> **0.01**
    | fwhm   -> **4**
    | Advanced option -> **show**
    | max: -> **50**
    | snthresh -> **1**
    | steps -> **2**


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

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

    | **2) Example of a sampleMetadata.tsv  :**


+---------------------------+------------+---------+
| sampleMetadata            |   class    | polarity|
+===========================+============+=========+
|HU_neg_017                 |   bio      |negative |
+---------------------------+------------+---------+
|HU_neg_028                 |   bio      |negative |
+---------------------------+------------+---------+
|HU_neg_034                 |   bio      |negative |
+---------------------------+------------+---------+
|Blanc04                    |   blank    |negative |
+---------------------------+------------+---------+
|Blanc06                    |   blank    |negative |
+---------------------------+------------+---------+
|Blanc09                    |   blank    |negative |
+---------------------------+------------+---------+



    | **3) Example of xset.TICs_raw.pdf (Total Ion Chromatograms) :**

.. image:: xcms_tics.png


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

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

**Version 3.0.0.0 - 08/03/2018**

- UPGRADE: upgrade the xcms version from 1.46.0 to 3.0.0. So refactoring of a lot of underlying codes and methods. Some parameters may have been renamed.

- NEW: a bunch of new options: Spectra Filters (previously scanrange), CentWave.(mzCenterFun, fitgauss, verboseColumns), MatchedFilter.(sigma, impute, baseValue, max), MSW.(verboseColumns), ...

- UPDATE: since xcms 3.0.0, some options are no more available: scanrange (replace by filters), profmethod, MatchedFilter.step, MatchedFilter.sigma, MSW.winSize.noise, MSW.SNR.method

- IMPROVEMENT: the advanced options are now in sections. It will allow you to access to all the parameters and to know their default values.

35:7f636ad1162b

<tool id="abims_xcms_xcmsSet" name="xcms findChromPeaks (xcmsSet)" version="@WRAPPER_VERSION@.0">
    <description>Chromatographic peak detection</description>

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

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

    <command><![CDATA[
        @COMMAND_RSCRIPT@/xcms_xcmsSet.r

        image '$image'

        BPPARAM \${GALAXY_SLOTS:-1}

        #if $filterSection.filterAcquisitionNum != "":
            filterAcquisitionNum "c($filterSection.filterAcquisitionNum)"

        #end if

        method $methods.method

        #if $methods.method == "CentWave":
            @COMMAND_CENTWAVE@
            ## List of regions-of-interest (ROI)
            #set $sectionROI = $methods.CentWaveAdv.CentWaveAdvROI
            @COMMAND_CENTWAVEADVROI@
        #elif $methods.method == "CentWavePredIso":
            @COMMAND_CENTWAVE@
            ## List of regions-of-interest (ROI)
            #set $sectionROI = $methods.CentWaveAdvROI
            @COMMAND_CENTWAVEADVROI@
            snthreshIsoROIs $sectionROI.snthreshIsoROIs
            maxCharge $sectionROI.maxCharge
            maxIso $sectionROI.maxIso
            mzIntervalExtension $sectionROI.mzIntervalExtension
            polarity $sectionROI.polarity
        #elif $methods.method == "MatchedFilter":
            fwhm $methods.fwhm
            binSize $methods.binSize
            impute $methods.impute_cond.impute
            #if $methods.impute_cond.impute == "linbase":

            verboseColumns $methods.verboseColumns
            scales "c($methods.scales)"
            nearbyPeak $methods.nearbyPeak
            ampTh $methods.ampTh
        #end if

        @COMMAND_FILE_LOAD@

        @COMMAND_LOG_EXIT@
    ]]></command>

    <inputs>

        <param name="image" type="data" format="rdata.msnbase.raw,rdata" label="@INPUT_IMAGE_LABEL@" help="@INPUT_IMAGE_HELP@ from MSnbase readMSData" />

        <section name="filterSection" title="Spectra Filters" expanded="False">
            <param argument="filterAcquisitionNum" type="text" value="" optional="true" label="Filter on Acquisition Numbers" help="min,max">
                <expand macro="input_validator_range_integer"/>
            </param>

        <conditional name="methods">
            <param name="method" type="select" label="Extraction method for peaks detection" help="See the help section below">
                <option value="MatchedFilter" selected="true">MatchedFilter - peak detection in chromatographic space</option>
                <option value="CentWave">CentWave - chromatographic peak detection using the centWave method</option>
                <option value="CentWavePredIso">CentWaveWithPredIsoROIs - performs a two-step centWave-based chromatographic peak detection</option>
                <option value="MSW">MSW - single-spectrum non-chromatography MS data peak detection</option>
            </param>

            <!-- CentWave -->
            <when value="CentWave">
                <expand macro="input_centwave"/>
                <section name="CentWaveAdv" title="Advanced Options" expanded="False">
                    <expand macro="input_centwaveAdv"/>
                    <section name="CentWaveAdvROI" title="List of regions-of-interest (ROI)" expanded="False">
                        <expand macro="input_centwaveAdvROI"  optional="true"/>
                    </section>
                </section>
            </when>

            <!-- MatchedFilter -->
            <when value="MatchedFilter">
                <param argument="fwhm" type="integer" value="30" label="Full width at half maximum of matched filtration gaussian model peak" help="Only used to calculate the actual sigma" />
                <param argument="binSize" type="float" value="0.1" label="Step size to use for profile generation" help="The peak detection algorithm creates extracted ion base peak chromatograms (EIBPC) on a fixed step size. (Previously step)" />
                <conditional name="impute_cond">
                    <param argument="impute" type="select" label="Method to be used for missing value imputation" help="(previously profmethod)">

                    <param argument="mzdiff" type="float" value="0.6" label="Minimum difference in m/z for peaks with overlapping Retention Times" help="By default: 0.8-step*steps " />
                    <!-- index -->
                </section>
            </when>

            <!-- CentWaveWithPredIsoROIs -->
            <when value="CentWavePredIso">
                <expand macro="input_centwave"/>
                <section name="CentWaveAdv" title="Advanced Options" expanded="False">
                    <expand macro="input_centwaveAdv"/>
                </section>
                <section name="CentWaveAdvROI" title="List of regions-of-interest (ROI)" expanded="True">
                    <expand macro="input_centwaveAdvROI" optional="false" />
                    <param argument="snthreshIsoROIs" type="float" value="6.25" label="Signal to noise ratio cutoff" help="used in the second centWave run to identify peaks for predicted isotope ROIs." />
                    <param argument="maxCharge" type="integer" value="3" label="Maximal isotope charge" help="Isotopes will be defined for charges ‘1:maxCharge’." />
                    <param argument="maxIso" type="integer" value="5" label="Number of isotope peaks that should be predicted for each peak identified in the first centWave run" />
                    <param argument="mzIntervalExtension" type="boolean" checked="true" truevalue="TRUE" falsevalue="FALSE" label="Is the mz range for the predicted isotope ROIs should be extended to increase detection of low intensity peaks" />
                    <param argument="polarity" type="select" label="Polarity of the data">
                        <option value="unknown">unknown</option>
                        <option value="positive">positive</option>
                        <option value="negative">negative</option>
                    </param>
                </section>
            </when>

            <!-- MSW -->
            <when value="MSW">
                <!---@TODO <param argument="winSize_noise" type="integer" value="500" label="The local window size to estimate the noise level" help="[winSize.noise]" />-->
                <param argument="snthresh" type="integer" value="3" label="Signal to Noise ratio cutoff" help="" />
                <param argument="verboseColumns" type="boolean" checked="false" truevalue="TRUE" falsevalue="FALSE" label="verbose Columns" help="whether additional peak meta data columns should be returned" />
                <param argument="scales" type="text" value="1,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,36,40,44,48,52,56,60,64" label="Scales of the Continuous Wavelet Transform (CWT)" help="Scales are linked to the width of the peaks that are to be detected." >

                <!-- peakThr -->
                <!-- tuneIn -->
                <!---@TODO <param argument="SNR_method" type="text" value="data.mean" label="SNR (Signal to Noise Ratio) method" help="[SNR.method] Method to estimate noise level. Currently, only 95 percentage quantile is supported." />-->
            </when>
        </conditional>

        <expand macro="input_file_load"/>
    </inputs>

    <outputs>
        <data name="xsetRData" format="rdata.xcms.findchrompeaks" label="${image.name.rsplit('.',1)[0]}.xset.RData" from_work_dir="xcmsSet.RData" />
        <data name="log" format="txt" label="${image.name.rsplit('.',1)[0]}.xset.log.txt" from_work_dir="log.txt" />
    </outputs>

    <tests>

        <!--<test>
            <param name="image" value="faahKO.raw.Rdata" ftype="rdata" />
            <section name="filterSection">
                <param name="filterAcquisitionNum" value="100,5000" />
                <param name="filterRt" value="3000,4000" />
                <param name="filterMz" value="300,400" />
            </section>
            <conditional name="methods">
                <param name="method" value="CentWave" />
                <param name="ppm" value="25" />
                <param name="peakwidth" value="20,50" />-->
                <!-- DISABLE: just for testing the arguments
                <section name="CentWaveAdv">
                    <section name="CentWaveAdvROI">
                        <param name="roiList" value="roiList.txt" ftype="tabular" />
                    </section>
                </section>-->
            <!--</conditional>
            <expand macro="test_file_load_zip"/>
            <assert_stdout>
                <has_text text="ppm: 25" />
                <has_text text="peakwidth: 20, 50" />
                <has_text text="object with 4 samples" />
                <has_text text="Time range: 3006.9-3978.7 seconds (50.1-66.3 minutes)" />
                <has_text text="Mass range: 300-400 m/z" />
                <has_text text="Peaks: 1311 (about 328 per sample)" />
                <has_text text="Peak Groups: 0" />
                <has_text text="Sample classes: KO, WT" />
            </assert_stdout>
        </test>-->
        <test>
            <param name="image" value="ko15-raw.Rdata" ftype="rdata" />
            <conditional name="methods">
                <param name="method" value="CentWave" />
                <param name="ppm" value="25" />
                <param name="peakwidth" value="20,50" />
            </conditional>
            <expand macro="test_file_load_single_ko15"/>
            <assert_stdout>
                <has_text text="ppm: 25" />
                <has_text text="peakwidth: 20, 50" />
                <has_text text="object with 1 samples" />
                <has_text text="Time range: 2506.1-4471.7 seconds (41.8-74.5 minutes)" />
                <has_text text="Mass range: 200.2-600 m/z" />
                <has_text text="Peaks: 2262 (about 2262 per sample)" />
                <has_text text="Peak Groups: 0" />
                <has_text text="Sample classes: ." />
            </assert_stdout>
        </test>
        <!-- DISABLE FOR TRAVIS
        Useful to generate test-data for the further steps
        <test>
            <param name="image" value="ko16-raw.Rdata" ftype="rdata" />
            <conditional name="methods">
                <param name="method" value="CentWave" />
                <param name="ppm" value="25" />
                <param name="peakwidth" value="20,50" />
            </conditional>

                <has_text text="Peak Groups: 0" />
                <has_text text="Sample classes: ." />
            </assert_stdout>
        </test>
        <test>
            <param name="image" value="wt15-raw.Rdata" ftype="rdata" />
            <conditional name="methods">
                <param name="method" value="CentWave" />
                <param name="ppm" value="25" />
                <param name="peakwidth" value="20,50" />
            </conditional>

                <has_text text="Peak Groups: 0" />
                <has_text text="Sample classes: ." />
            </assert_stdout>
        </test>
        <test>
            <param name="image" value="wt16-raw.Rdata" ftype="rdata" />
            <conditional name="methods">
                <param name="method" value="CentWave" />
                <param name="ppm" value="25" />
                <param name="peakwidth" value="20,50" />
            </conditional>

        </test>
        -->
        <!-- DISABLE FOR TRAVIS
        Test to test the different methods parameters
        <test>
            <param name="image" value="ko15-raw.Rdata" ftype="rdata" />
            <conditional name="methods">
                <param name="method" value="MatchedFilter" />
                <param name="fwhm" value="35" />
                <conditional name="impute_cond">
                    <param name="impute" value="linbase" />

                <has_text text="baseValue: 0.1" />
                <has_text text="distance: 1" />
            </assert_stdout>
        </test>
        <test>
            <param name="image" value="ko15-raw.Rdata" ftype="rdata" />
            <conditional name="methods">
                <param name="method" value="CentWavePredIso" />
                <param name="ppm" value="56" />
                <param name="peakwidth" value="5.275,13.5" />
                <section name="CentWaveAdvROI">
                    <param name="roiList" value="roiList.txt" ftype="tabular" />
                </section>
            </conditional>
            <assert_stdout>
                <has_text text="  scmin scmax mzmin mzmax length intensity" />
                <has_text text="1   200   300   300   350    100      5000" />
            </assert_stdout>
        </test>
        <test>
            <param name="image" value="ko15-raw.Rdata" ftype="rdata" />
            <conditional name="methods">
                <param name="method" value="MSW" />
                <param name="snthresh" value="4" />
                <param name="verboseColumns" value="true" />
            </conditional>

        </test>
        -->
        <!-- DISABLE FOR TRAVIS
        No more test-data/sacuri_dir_root.zip
        <test>
            <param name="image" value="sacuri_dir_root.zip"  ftype="zip" />
            <conditional name="methods">
                <param name="method" value="MatchedFilter" />
                <param name="step" value="0.01" />
                <param name="fwhm" value="4" />
                <conditional name="options_m">

        </test>
        -->
        <!--  DISABLE FOR TRAVIS
        No more test-data/sacuri_current_root.zip
        <test>
            <param name="image" value="sacuri_current_root.zip"  ftype="zip" />
            <conditional name="methods">
                <param name="method" value="CentWave" />
                <param name="ppm" value="25" />
                <param name="peakwidth" value="20,50" />
            </conditional>

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

**Upstream tools**

========================= ================= ============================== ==========
Name                      output file       format                         parameter
========================= ================= ============================== ==========
MSnbase readMSData        raw.RData         rdata.msnbase.raw              RData file
========================= ================= ============================== ==========


**Downstream tools**

=========================== ==================== =================
Name                        Output file          Format
=========================== ==================== =================
xcms.group                  xset.RData           rdata.xcms.raw
--------------------------- -------------------- -----------------
PCA ellipsoid by factors    sampleMetadata.tsv   Tabular
--------------------------- -------------------- -----------------
Anova                       sampleMetadata.tsv   Tabular
=========================== ==================== =================


**Example of a metabolomic workflow**

.. image:: xcms_xcmsset_workflow.png

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

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

Extraction method for peaks detection
-------------------------------------

**MatchedFilter**

    | The matchedFilter algorithm identifies peaks in the chromatographic time domain as described in [Smith 2006]. The intensity values are binned by cutting The LC/MS data into slices (bins) of a mass unit (‘binSize’ m/z) wide. Within each bin the maximal intensity is selected. The chromatographic peak detection is then performed in each bin by extending it based on the ‘steps’ parameter to generate slices comprising bins ‘current_bin - steps +1’ to ‘current_bin + steps - 1’. Each of these slices is then filtered with matched filtration using a second-derative Gaussian as the model peak shape. After filtration peaks are detected using a signal-to-ratio cut-off. For more details and illustrations see [Smith 2006].
    | See the MatchedFilter_manual_

**CentWave**

    | The centWave algorithm perform peak density and wavelet based chromatographic peak detection for high resolution LC/MS data in centroid mode [Tautenhahn 2008].
    | Due to the fact that peak centroids are used, a binning step is not necessary.
    | The method is capable of detecting close-by-peaks and also overlapping peaks. Some efforts are made to detect the exact peak boundaries to get precise peak integrals.
    | See the CentWave_manual_

**CentWaveWithPredIsoROIs**

    | This method performs a two-step centWave-based chromatographic peak detection: in a first centWave run peaks are identified for which then the location of their potential isotopes in the mz-retention time is predicted. A second centWave run is then performed on these regions of interest (ROIs). The final list of chromatographic peaks comprises all non-overlapping peaks from both centWave runs.
    | See the CentWaveWithPredIsoROIs_manual_

**MSW**

    | Wavelet based, used for direct infusion data. Continuous wavelet transform (CWT) can be used to locate chromatographic peaks on different scales.
    | See the MSW_manual_

.. _MatchedFilter_manual: https://rdrr.io/bioc/xcms/man/findChromPeaks-matchedFilter.html#heading-2
.. _CentWave_manual: https://rdrr.io/bioc/xcms/man/findChromPeaks-centWave.html#heading-2
.. _CentWaveWithPredIsoROIs_manual: https://rdrr.io/bioc/xcms/man/findChromPeaks-centWaveWithPredIsoROIs.html#heading-2
.. _MSW_manual: https://rdrr.io/bioc/xcms/man/findPeaks-MSW.html#heading-2

@HELP_XCMS_MANUAL@

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

sampleMetadata.tsv

    | Tabular file that contains for each sample, it's associated class and polarity (positive,negative and mixed).
    | This file is necessary in the Anova and PCA step of the workflow.

xset.RData: rdata.xcms.findchrompeaks format

    | Rdata file that is necessary in the second step of the workflow "xcms.group".

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

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


**Version 3.0.0.0 - 08/03/2018**

- UPGRADE: upgrade the xcms version from 1.46.0 to 3.0.0. So refactoring of a lot of underlying codes and methods. Some parameters may have been renamed.

- CHANGE: xcms.findChromPeaks no longer read the raw data. You have to run MSnbase readMSData first.

- NEW: a bunch of new options: Spectra Filters (previously scanrange), CentWave.(mzCenterFun, fitgauss, verboseColumns), MatchedFilter.(sigma, impute, baseValue, max), MSW.(verboseColumns), ...

- NEW: new Filters for Spectra

- NEW: new methods: CentWaveWithPredIsoROIs

- UPDATE: since xcms 3.0.0, some options are no more available: scanrange (replace by filters), profmethod, MatchedFilter.step, MatchedFilter.sigma, MSW.winSize.noise, MSW.SNR.method

- IMPROVEMENT: the advanced options are now in sections. It will allow you to access to all the parameters and to know their default values.