comparison msnbase_readmsdata.xml @ 0:24f7d4e5c186 draft

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

0:24f7d4e5c186

<tool id="msnbase_readmsdata" name="MSnbase readMSData" version="@WRAPPER_VERSION@.0">
    <description>Imports mass-spectrometry raw 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 $input.is_of_type("netcdf"):
            singlefile_galaxyPath '$input' singlefile_sampleName '$input.name'
        #else
            zipfile '$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 format: mzxml, mzml, mzdata and netcdf. Zip file mode for the format: 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 (27 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 (27 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
.. _here: http://web11.sb-roscoff.fr/download/w4m/howto/w4m_HowToPerformXcmsPreprocessing_v02.pdf


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

**Upstream tools**

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


**Downstream tools**

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



**Example of a metabolomic workflow**

.. image:: mnsbase_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 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**


------------
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.msnbase.raw format

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

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

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


**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>