annotate msnbase_readmsdata.xml @ 13:226fb89cacc4 draft

"planemo upload for repository https://github.com/workflow4metabolomics/xcms commit f1caf2a3bf23cf319a75dd12c86402555dd02617"

<tool id="msnbase_readmsdata" name="MSnbase readMSData" version="@WRAPPER_VERSION@.2">
    <description>Imports mass-spectrometry data files</description>

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

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

    <command><![CDATA[
        @COMMAND_RSCRIPT@/msnbase_readmsdata.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"):
            #if $os.path.islink(str($input))
                #set $source = $os.readlink(str($input))
                singlefile_galaxyPath '$source' singlefile_sampleName '$os.path.basename($source)'
            #else
                singlefile_galaxyPath '$input' singlefile_sampleName '$input.name'
            #end if
        #else
            zipfile '$input'
        #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 following formats: mzxml, mzml, mzdata and netcdf. Zip file mode for the following formats: no_unzip.zip, zip. See the help section below." />

    </inputs>

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

    <tests>

        <test>
            <param name="input" value="faahKO_reduce.zip"  ftype="zip" />
            <assert_stdout>
                <has_text text="rowNames: faahKO_reduce/KO/ko15.CDF faahKO_reduce/KO/ko16.CDF" />
                <has_text text="faahKO_reduce/WT/wt15.CDF faahKO_reduce/WT/wt16.CDF" />
                <has_text text="featureNames: F1.S0001 F1.S0002 ... F4.S1278 (5112 total)" />
                <has_text text="fvarLabels: fileIdx spIdx ... spectrum (28 total)" />
                <has_text text="faahKO_reduce/KO/ko15.CDF        ko15           KO" />
                <has_text text="faahKO_reduce/KO/ko16.CDF        ko16           KO" />
                <has_text text="faahKO_reduce/WT/wt15.CDF        wt15           WT" />
                <has_text text="faahKO_reduce/WT/wt16.CDF        wt16           WT" />
            </assert_stdout>
            <output name="sampleMetadata" value="sampleMetadata.tsv" />
        </test>
        <test>
            <param name="input" value="ko15.CDF"  ftype="netcdf" />
            <assert_stdout>
                <has_text text="rowNames: ko15.CDF" />
                <has_text text="ko15.CDF" />
                <has_text text="featureNames: F1.S0001 F1.S0002 ... F1.S1278 (1278 total)" />
                <has_text text="fvarLabels: fileIdx spIdx ... spectrum (28 total)" />
                <has_text text="ko15.CDF        ko15            ." />
            </assert_stdout>
        </test>
        <!-- DISABLE FOR TRAVIS
        Useful to generate test-data for the further steps
        <test>
            <param name="input" value="ko16.CDF"  ftype="netcdf" />
            <assert_stdout>
                <has_text text="rowNames: ./ko16.CDF" />
                <has_text text="ko16.CDF" />
                <has_text text="./ko16.CDF        ko16            ." />
            </assert_stdout>
        </test>
        <test>
            <param name="input" value="wt15.CDF"  ftype="netcdf" />
            <assert_stdout>
                <has_text text="rowNames: ./wt15.CDF" />
                <has_text text="wt15.CDF" />
                <has_text text="./wt15.CDF        wt15            ." />
            </assert_stdout>
        </test>
        <test>
            <param name="input" value="wt16.CDF"  ftype="netcdf" />
            <assert_stdout>
                <has_text text="rowNames: ./wt16.CDF" />
                <has_text text="wt16.CDF" />
                <has_text text="./wt16.CDF        wt16            ." />
            </assert_stdout>
        </test>
        -->
    </tests>

    <help><![CDATA[

@HELP_AUTHORS@

==================
MSnbase readMSData
==================

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

Reads as set of XML-based mass-spectrometry data files and
generates an MSnExp object. This function uses the functionality
provided by the ‘mzR’ package to access data and meta data in
‘mzData’, ‘mzXML’ and ‘mzML’.

.. _xcms: https://bioconductor.org/packages/release/bioc/html/xcms.html


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

**Upstream tools**

========================= ==========================================
Name                      Format
========================= ==========================================
Upload File               mzxml,mzml,mzdata,netcdf,no_unzip.zip,zip
========================= ==========================================

The easier way to process is to create a Dataset Collection of the type List

**Downstream tools**

=========================== ==================== ====================
Name                        Output file          Format
=========================== ==================== ====================
xcms.findChromPeaks         ``*``.raw.RData      rdata.msnbase.raw
=========================== ==================== ====================



**Example of a metabolomic workflow**

.. image:: msnbase_readmsdata_workflow.png

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



-----------
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 readMSData and findChromPeaks in parallel and use "findChromPeaks Merger" before groupChromPeaks.
    | 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 W4M platform (corrupted zip 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 can 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 information, do not hesitate to send us an email at supportATworkflow4metabolomics.org.

Advices for converting your files into mzXML format (XCMS input)
----------------------------------------------------------------

We recommend you to convert your raw files into **mzXML** in centroid mode (smaller files); this way the files will be compatible with the xmcs centWave algorithm.

**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**


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

xset.RData: rdata.msnbase.raw format

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

sampleMetadata.tsv (only when a zip is used)

    | Tabular file that contains for each sample its associated class and polarity (positive,negative and mixed).
    | This file is necessary in further steps of the workflow, as the Anova and PCA steps for example.
    | You get a sampleMetadata.tsv only if you use a zip. Otherwise, you have to provide one for the findChromPeaks Merger step.

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

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

.. _News: https://bioconductor.org/packages/release/bioc/news/MSnbase/NEWS

**Version 2.8.2.1 - 30/04/2019**

- BUGFIX: remove the pre-compute of the chromatograms which was memory consuming. Now, only xcms plot chromatogram will generate the Chromatograms.

**Version 2.8.2.0 - 08/04/2019**

- UPGRADE: upgrade the MSnbase version from 2.4.0 to 2.8.2 (see MSnbase News_). Almost all the new features may not concern our usage of MSnbase.

**Version 2.4.0.0 - 29/03/2018**

- NEW: a new dedicated tool to read the raw data. This function was previously included in xcms.findChromPeaks. This way, you will now be able to display TICs and BPCs before xcms.findChromPeaks.

    ]]></help>

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