view ipo4xcmsSet.xml @ 7:dd0a593dded1 draft

planemo upload commit c3ffcc9ea76a0e143e11613e6841ee59a28578fd

<tool id="ipo4xcmsSet" name="IPO for xcmsSet" version="0.0.3">

    <description>IPO optimization process for xcms.xcmsSet</description>

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

        <macro name="centwave_ppm_fixed">
            <param name="ppm" type="integer" value="25" label="Max tolerated ppm m/z deviation in consecutive scans in ppm" help="[ppm]" />
        </macro>
        <macro name="centwave_peakwidth_fixed">
            <param name="min_peakwidth" type="float" value="20" label="Min peak width range in seconds" optional="true" help="[min_peakwidth]" />
            <param name="max_peakwidth" type="float" value="50" label="Max peak width range in seconds" optional="true" help="[max_peakwidth]" />
        </macro>
        <macro name="centwave_mzdiff_fixed">
            <param name="mzdiff" type="float" value="-0.001" label="Minimum difference in m/z for peaks with overlapping Retention Times" help="[mzdiff] Can be negative to allow overlap" />
        </macro>

        <macro name="matchedfilter_fwhm_fixed">
            <param name="fwhm" type="integer" value="30" label="Full width at half maximum of matched filtration gaussian model peak" help="[fwhm] Only used to calculate the actual sigma" />
        </macro>
        <macro name="matchedfilter_mzdiff_fixed">
            <param name="mzdiff" type="float" value="0.6" label="Minimum difference in m/z for peaks with overlapping Retention Times" help="[mzdiff] By default: 0.8-step*steps " />
        </macro>
    </macros>

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

    <command><![CDATA[
        LANG=C Rscript $__tool_directory__/ipo4xcmsSet.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

        parametersOutput $parametersOutput
        xsetRdataOutput $xsetRData

        samplebyclass $samplebyclass

        ## profmethod $profmethod
        @COMMAND_NSLAVES@
        method $methods.method
        #if $methods.method == "centWave":
            ppm "c($methods.section_centwave_optiomizable.conditional_parameter.ppm)"
            min_peakwidth "c($methods.section_centwave_optiomizable.conditional_parameter.min_peakwidth)"
            max_peakwidth "c($methods.section_centwave_optiomizable.conditional_parameter.max_peakwidth)"
            mzdiff "c($methods.section_centwave_optiomizable.conditional_parameter.mzdiff)"

            snthresh $methods.section_centwave_non_optiomizable.snthresh
            integrate $methods.section_centwave_non_optiomizable.integrate
            noise $methods.section_centwave_non_optiomizable.noise
            prefilter "c($methods.section_centwave_non_optiomizable.prefilter)"

        #elif $methods.method == "matchedFilter":
            fwhm "c($methods.section_matchedfilter_optiomizable.conditional_parameter.fwhm)"
            mzdiff "c($methods.section_matchedfilter_optiomizable.conditional_parameter.mzdiff)"

            step $methods.section_matchedfilter_non_optimizable.step
            steps $methods.section_matchedfilter_non_optimizable.steps
            max $methods.section_matchedfilter_non_optimizable.max
            snthresh $methods.section_matchedfilter_non_optimizable.snthresh
        #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." />

        <param name="samplebyclass" type="integer" value="2" label="Number of samples used per class to estimate the best parameters" help="Set to 0 to use the whole dataset. To save time, reduce this number" />

        <conditional name="methods">
            <param name="method" type="select" label="Extraction method for peaks detection" help="[method] See the help section below">
                <option value="centWave" >centWave</option>
                <option value="matchedFilter" selected="true">matchedFilter</option>
            </param>

            <!-- centWave Filter options -->
            <when value="centWave">
                <section name="section_centwave_optiomizable"  title="Optimizable parameters" expanded="True">
                    <conditional name="conditional_parameter">
                        <param name="select_parameter" type="select" label="Which parameter do you want to optimize?" help="Only one paramter can be optimized at once. The other will require fixed values">
                            <option value="ppm">Max tolerated ppm m/z deviation in consecutive scans in ppm [ppm]</option>
                            <option value="peakwidth">Min,Max peak width in seconds [peakwidth]</option>
                            <option value="mzdiff">Minimum difference in m/z for peaks with overlapping Retention Times [mzdiff]</option>
                        </param>
                        <when value="ppm">
                            <param name="ppm" type="text" value="17,32" label="Range for Max tolerated ppm m/z deviation in consecutive scans in ppm" optional="false" help="[ppm] (ex: 25 or 17,32)">
                                <validator type="regex" message="Should be this format XX,YY">[0-9]+,[0-9]+</validator>
                            </param>
                            <expand macro="centwave_peakwidth_fixed" />
                            <expand macro="centwave_mzdiff_fixed" />
                        </when>
                        <when value="peakwidth">
                            <param name="min_peakwidth" type="text" value="12,18" label="Range for Min peak width range in seconds" optional="true" help="[min_peakwidth] (ex: 12,18)">
                                <validator type="regex" message="Should be one combinaison of those format: XX,YY or XX.XX,YY.YY">[0-9]+[\.]?[0-9]*,[0-9]+[\.]?[0-9]*</validator>
                            </param>
                            <param name="max_peakwidth" type="text" value="35,65" label="Range for Max peak width range in seconds" optional="true" help="[max_peakwidth] (ex: 35,65)">
                                <validator type="regex" message="Should be one combinaison of those format: XX,YY or XX.XX,YY.YY">[0-9]+[\.]?[0-9]*,[0-9]+[\.]?[0-9]*</validator>
                            </param>
                            <expand macro="centwave_ppm_fixed" />
                            <expand macro="centwave_mzdiff_fixed" />
                        </when>
                        <when value="mzdiff">
                            <param name="mzdiff" type="text" value="-0.001,0.010" label="Range for Minimum difference in m/z for peaks with overlapping retention times" help="[mzdiff] Can be negative to allow overlap (ex: -0.001,0.010)">
                                <validator type="regex" message="Should be one combinaison of those format: XX,YY or -XX,YY or XX.XX,YY.YY">[\-]?[0-9]+[\.]?[0-9]*,[\-]?[0-9]+[\.]?[0-9]*</validator>
                            </param>
                            <expand macro="centwave_ppm_fixed" />
                            <expand macro="centwave_peakwidth_fixed" />
                        </when>
                    </conditional>
                </section>

                <section name="section_centwave_non_optiomizable"  title="Non optimizable parameters" expanded="True">
                    <param name="snthresh" type="integer" value="10" label="Signal/Noise threshold" help="[snthresh] Signal to noise ratio cutoff" />
                    <param name="integrate" type="select" label="Peak limits method" help="[integrate]" >
                        <option value="1">peak limits based on smoothed 2nd derivative (less precise)</option>
                        <option value="2">peak limits based on real data (more sensitive to noise)</option>
                    </param>
                    <param name="prefilter" type="text" value="3,100" label="Prefilter step for the first phase" help="[prefilter] Separate by coma k,I. Mass traces are only retained if they contain at least ‘k’ peaks with intensity >= ‘I’"/>
                    <param name="noise" type="integer" value="0" label="Noise filter" help="[noise] optional argument which is useful for data that was centroided without any intensity threshold, centroids with intensity smaller than ‘noise’ are omitted from ROI detection"/>
                </section>
            </when>

            <!-- matched Filter options -->
            <when value="matchedFilter">
                <section name="section_matchedfilter_optiomizable"  title="Optimizable parameters" expanded="True">
                    <conditional name="conditional_parameter">
                        <param name="select_parameter" type="select" label="Which parameter do you want to optimize?" help="Only one paramter can be optimized at once. The other will require fixed values">
                            <option value="fwhm">Full width at half maximum of matched filtration gaussian model peak [fwhm]</option>
                            <option value="mzdiff">Minimum difference in m/z for peaks with overlapping Retention Times [mzdiff]</option>
                        </param>
                        <when value="fwhm">
                            <param name="fwhm" type="text" value="25,35" label="Range for Full width at half maximum of matched filtration gaussian model peak" optional="true" help="[fwhm] Only used to calculate the actual sigma (ex: 25,35)">
                                <validator type="regex" message="Should be this format: XX,YY">[0-9]+,[0-9]+</validator>
                            </param>
                            <expand macro="matchedfilter_mzdiff_fixed" />
                        </when>
                        <when value="mzdiff">
                            <param name="mzdiff" type="text" value="0.4,0.7" label="Range for Minimum difference in m/z for peaks with overlapping Retention Times" help="[mzdiff] By default: 0.8-step*steps (ex: 0.4,0.7)">
                                <validator type="regex" message="Should be one combinaison of those format: XX,YY or -XX,YY or XX.XX,YY.YY">[\-]?[0-9]+[\.]?[0-9]*,[\-]?[0-9]+[\.]?[0-9]*</validator>
                            </param>
                            <expand macro="matchedfilter_fwhm_fixed" />
                        </when>
                    </conditional>
                </section>

                <section name="section_matchedfilter_non_optimizable" title="Non optimizable parameters"  expanded="True">
                    <param name="step" type="float" value="0.1" label="Step size to use for profile generation" help="[step] The peak detection algorithm creates extracted ion base peak chromatograms (EIBPC) on a fixed step size" />
                    <param name="steps" type="integer" value="2" label="Number of steps to merge prior to filtration" help="[steps] The peak identification algorithm combines a given number of EIBPCs prior to filtration and peak detection, as defined by the steps argument" />
                    <param name="max" type="integer" value="5" label="Maximum number of peaks per extracted ion chromatogram" help="[max]" />
                    <param name="snthresh" type="integer" value="10" label="Signal to noise ratio cutoff" help="[snthresh]" />
                </section>
            </when>
        </conditional>


    </inputs>

    <outputs>
        <data name="xsetRData" format="rdata.xcms.raw" label="xset.RData" />
        <data name="parametersOutput" format="tabular" label="IPO_parameters4xcmsSet.tsv" />
        <data name="log" format="txt" label="ipo4xcmsSet.log.txt" />
    </outputs>

    <tests>
        <test>
            <param name="input" value="MM14.mzML"  ftype="mzxml" />
            <param name="samplebyclass" value="0" />
            <conditional name="methods">
                <param name="method" value="centWave" />
                <section name="section_centwave_optiomizable" >
                    <conditional name="conditional_parameter">
                        <param name="select_parameter" value="peakwidth" />
                        <param name="min_peakwidth" value="3,9.5" />
                        <param name="max_peakwidth" value="10,20" />
                        <param name="ppm" value="56" />
                        <param name="mzdiff" value="-0.001" />
                    </conditional>
                </section>
            </conditional>
            <output name="parametersOutput" file="MM14_IPO_parameters4xcmsSet_peakwidth.tsv" />
        </test>
        <test>
            <param name="input" value="MM14.mzML"  ftype="mzxml" />
            <param name="samplebyclass" value="0" />
            <conditional name="methods">
                <param name="method" value="centWave" />
                <section name="section_centwave_optiomizable" >
                    <conditional name="conditional_parameter">
                        <param name="select_parameter" value="ppm" />
                        <param name="ppm" value="50,60" />
                        <param name="min_peakwidth" value="3.325" />
                        <param name="max_peakwidth" value="11" />
                        <param name="mzdiff" value="-0.001" />
                    </conditional>
                </section>
            </conditional>
            <output name="parametersOutput" file="MM14_IPO_parameters4xcmsSet_ppm.tsv" />
        </test>
        <!-- Too long for Travis CI -->
        <!--<test>
            <param name="inputs|input" value="zip_file" />
            <param name="inputs|zip_file" value="sacuri_2files.zip"  ftype="zip" />
            <param name="samplebyclass" value="1" />
            <param name="methods|method" value="centWave" />
            <param name="methods|ppm" value="25" />
            <param name="methods|min_peakwidth" value="20,30" />
            <param name="methods|max_peakwidth" value="45,55" />
            <output name="parametersOutput" file="sacuri_2files_centWave_IPO_parameters4xcmsSet.tsv" />
        </test>-->
        <!-- Too long for Travis CI -->
        <!--<test>
            <param name="inputs|input" value="zip_file" />
            <param name="inputs|zip_file" value="sacuri_2files.zip"  ftype="zip" />
            <param name="samplebyclass" value="1" />
            <param name="methods|method" value="matchedFilter" />
            <param name="methods|step" value="0.05,0.15" />
            <param name="methods|fwhm" value="25,35" />
            <output name="parametersOutput" file="sacuri_2files_matchedFilter_IPO_parameters4xcmsSet.tsv" />
        </test>-->
        <!--Failed:
                Error in resultIncreased(history) :
                        No isotopes have been detected, peak picking not optimizable by IPO!-->
        <!--<test>
            <param name="inputs|input" value="zip_file" />
            <param name="inputs|zip_file" value="faahKO_reduce.zip"  ftype="zip" />
            <param name="methods|method" value="centWave" />
            <param name="methods|ppm" value="25" />
            <param name="methods|min_peakwidth" value="15,25" />
            <param name="methods|min_peakwidth" value="20,30" />
            <param name="methods|max_peakwidth" value="45,55" />
            <output name="parametersOutput" file="faahKO_IPO_parameters4xcmsSet.tsv" />
        </test>-->
    </tests>

    <help><![CDATA[

@HELP_AUTHORS@

===============
IPO.ipo4xcmsSet
===============

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

A Tool for automated Optimization of XCMS Parameters


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

**Upstream tools**

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


**Downstream tools**

+---------------------------+----------------------+-----------------+
| Name                      | Output file          | Format          |
+===========================+======================+=================+
|xcms.xcmsSet               | parametersOutput.tsv | Tabular         |
+---------------------------+--------------------+-------------------+



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

+---------------------------+------------+
| Parameter : num + label   |   Format   |
+===========================+============+
| 1 : Choose your inputs    |   zip      |
+---------------------------+------------+

**Choose your inputs**

You have two methods for your inputs:

    | Zip file (recommended): You can put a zip file containing your inputs: myinputs.zip (containing all your conditions as sub-directories).
    | library folder: You must specify the name of your "library" (folder) created within your space project (for example: /projet/externe/institut/login/galaxylibrary/yourlibrary). Your library must contain all your conditions as sub-directories.

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 (http://www.7-zip.org/), otherwise your zip will not be well unzipped on the platform W4M (zip corrupted bug).

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 (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
-------------------------------------

**Matched Filter**

    | One parameter to consider is the Gaussian model peak width used for matched filtration,an integral part of the peak detection algorithm.
    | For a discussion of how model peak width affects the signal to noise ratio, see Danielsson et al. (2002).


**cent Wave**

    | This algorithm is most suitable for high resolution LC/{TOF,OrbiTrap,FTICR}-MS data in centroid mode.
    | 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.


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

IPO_parameters4xcmsSet.tsv

    | Optimal parameters for xcmsSet


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

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



    ]]></help>

    <expand macro="citation" />
</tool>