xcms_xcmsset: abims_xcms_xcmsSet.xml comparison

comparison abims_xcms_xcmsSet.xml @ 31:e93153c07be0 draft

planemo upload for repository https://github.com/workflow4metabolomics/xcms commit 73791d74546087b2a872d9279df960f5bc207298

author	lecorguille
date	Tue, 13 Feb 2018 04:42:24 -0500
parents	d71827ecd22c
children	2bf1cb023c94

comparison

equal deleted inserted replaced

-:d71827ecd22c
+:e93153c07be0
-<tool id="abims_xcms_xcmsSet" name="xcms.xcmsSet" version="2.2.0">
+<tool id="abims_xcms_xcmsSet" name="xcms.xcmsSet" version="2.1.1">
 <description>Filtration and Peak Identification using xcmsSet function from xcms R package to preprocess LC/MS data for relative quantification and statistical analysis </description>
 <macros>
 <import>macros.xml</import>
 </macros>
 xfunction xcmsSet
 xsetRdataOutput '$xsetRData'
 sampleMetadataOutput '$sampleMetadata'
+ticspdf '$ticsRawPdf'
+bicspdf '$bpcsRawPdf'
 #if $options_scanrange.option == "show":
 scanrange "c($options_scanrange.scanrange)"
 #end if
 winSize.noise $methods.winSize_noise
 amp.Th $methods.amp_Th
 scales "c($methods.scales)"
 SNR.method "$methods.SNR_method"
 #end if
+@COMMAND_LOG_EXIT@
-#if $input.is_of_type("mzxml") or $input.is_of_type("mzml") or $input.is_of_type("mzdata") or $input.is_of_type("netcdf"):
-&& mv *-TIC_mqc.out $ticsRawTab
-&& mv *-BPC_mqc.out $bpcsRawTab
-#end if
-@COMMAND_LOG_EXIT@;
 ]]></command>
 <inputs>
 <param name="input" type="data" format="mzxml,mzml,mzdata,netcdf,no_unzip.zip,zip" label="File(s) from your history containing your chromatograms" help="Single file mode for the format: mzxml, mzml, mzdata and netcdf. Zip file mode for the format: no_unzip.zip, zip. See the help section below." />
 <param name="amp_Th" type="float" value="0.002" label="Minimum required relative amplitude of the peak" help="[amp.Th] Ratio to the maximum of CWT coefficients" />
 <param name="scales" type="text" value="seq(1,22,3)" label="Scales for the Continuous Wavelet Transform (CWT)" help="[scales] Scales are linked to the width of the peaks that are to be detected. Tape as indicaded seq('n,n,n') or c(n,n) : seq(from, to, by steps), c - linear vector " />
 <param name="SNR_method" type="text" value="data.mean" label="SNR (Signal to Noise Ratio) method" help="[SNR.method] Method to estimate noise level. Currently, only 95 percentage quantile is supported." />
 </when>
 </conditional>
-<expand macro="input_tic_bpc_pdf"/>
 </inputs>
 <outputs>
 <data name="xsetRData" format="rdata.xcms.raw" label="${input.name.rsplit('.',1)[0]}.xset.RData" />
-<data name="log" format="txt" label="${input.name.rsplit('.',1)[0]}.xset.log.txt" />
-<!-- SINGLE MODE -->
-<data name="ticsRawTab" format="tabular" label="${input.name.rsplit('.',1)[0]}.xset.TICs_raw.tabular">
-<filter>input.extension in ["mzxml","mzml","mzdata","netcdf"]</filter>
-</data>
-<data name="bpcsRawTab" format="tabular" label="${input.name.rsplit('.',1)[0]}.xset.BPCs_raw.tabular">
-<filter>input.extension in ["mzxml","mzml","mzdata","netcdf"]</filter>
-</data>
-<!-- ZIP MODE -->
 <data name="sampleMetadata" format="tabular" label="${input.name.rsplit('.',1)[0]}.sampleMetadata.tsv">
 <filter>input.extension not in ["mzxml","mzml","mzdata","netcdf"]</filter>
 </data>
-<data name="ticsRawPdf" format="pdf" from_work_dir="TICs.pdf" label="${input.name.rsplit('.',1)[0]}.xset.TICs_raw.pdf">
+<data name="ticsRawPdf"   format="pdf" label="${input.name.rsplit('.',1)[0]}.xset.TICs_raw.pdf" />
-<filter>input.extension not in ["mzxml","mzml","mzdata","netcdf"]</filter>
+<data name="bpcsRawPdf"   format="pdf" label="${input.name.rsplit('.',1)[0]}.xset.BPCs_raw.pdf" />
-<filter>tic_bpc_pdf</filter>
+<data name="log" format="txt" label="${input.name.rsplit('.',1)[0]}.xset.log.txt" />
-</data>
-<data name="bpcsRawPdf" format="pdf" from_work_dir="BPCs.pdf" label="${input.name.rsplit('.',1)[0]}.xset.BPCs_raw.pdf">
-<filter>input.extension not in ["mzxml","mzml","mzdata","netcdf"]</filter>
-<filter>tic_bpc_pdf</filter>
-</data>
-<collection name="ticsRawTabCollection" type="list" label="TIC raw tabular">
-<filter>input.extension not in ["mzxml","mzml","mzdata","netcdf"]</filter>
-<discover_datasets pattern="(?P&lt;designation&gt;.+)-TIC_mqc\.out" ext="tabular" />
-</collection>
-<collection name="bpcsRawTabCollection" type="list" label="BPC raw tabular">
-<filter>input.extension not in ["mzxml","mzml","mzdata","netcdf"]</filter>
-<discover_datasets pattern="(?P&lt;designation&gt;.+)-BPC_mqc\.out" ext="tabular" />
-</collection>
 </outputs>
 <tests>
-<!--
+<!--<test>
+<param name="input" value="sacuri_dir_root.zip"  ftype="zip" />
+<param name="methods|method" value="matchedFilter" />
+<param name="methods|step" value="0.01" />
+<param name="methods|fwhm" value="4" />
+<param name="methods|options_m|option" value="show" />
+<param name="methods|options_m|max" value="50" />
+<param name="methods|options_m|snthresh" value="1" />
+<param name="methods|options_m|steps" value="2" />
+<output name="log">
+<assert_contents>
+<has_text text="object with 4 samples" />
+<has_text text="Time range: 0.7-1139.7 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="input" value="sacuri_current_root.zip"  ftype="zip" />
 <param name="methods|method" value="centWave" />
 <param name="methods|ppm" value="25" />
 <param name="methods|peakwidth" value="20,50" />
 <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>
-<output_collection name="ticsRawTabCollection" type="list">
-<element name="ko15" value="ko15-TIC_mqc.out" />
-<element name="ko16" value="ko16-TIC_mqc.out" />
-<element name="wt15" value="wt15-TIC_mqc.out" />
-<element name="wt16" value="wt16-TIC_mqc.out" />
-</output_collection>
-<output_collection name="bpcsRawTabCollection" type="list">
-<element name="ko15" value="ko15-BPC_mqc.out" />
-<element name="ko16" value="ko16-BPC_mqc.out" />
-<element name="wt15" value="wt15-BPC_mqc.out" />
-<element name="wt16" value="wt16-BPC_mqc.out" />
-</output_collection>
 </test>
 <!-- Passed but disable to save time for Travis" -->
-<!--
+<!--<test>
+<param name="input" value="ko15.CDF"  ftype="netcdf" />
+<param name="methods|method" value="centWave" />
+<param name="methods|ppm" value="25" />
+<param name="methods|peakwidth" value="20,50" />
+<output name="log">
+<assert_contents>
+<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_contents>
+</output>
+</test>
+<test>
+<param name="input" value="ko16.CDF"  ftype="netcdf" />
+<param name="methods|method" value="centWave" />
+<param name="methods|ppm" value="25" />
+<param name="methods|peakwidth" value="20,50" />
+<output name="log">
+<assert_contents>
+<has_text text="object with 1 samples" />
+<has_text text="Time range: 2521.7-4477.9 seconds (42-74.6 minutes)" />
+<has_text text="Mass range: 200.1-600 m/z" />
+<has_text text="Peaks: 2408 (about 2408 per sample)" />
+<has_text text="Peak Groups: 0" />
+<has_text text="Sample classes: ." />
+</assert_contents>
+</output>
+</test>
+<test>
+<param name="input" value="wt15.CDF"  ftype="netcdf" />
+<param name="methods|method" value="centWave" />
+<param name="methods|ppm" value="25" />
+<param name="methods|peakwidth" value="20,50" />
+<output name="log">
+<assert_contents>
+<has_text text="object with 1 samples" />
+<has_text text="Time range: 2517-4473.2 seconds (42-74.6 minutes)" />
+<has_text text="Mass range: 200.2-599.8 m/z" />
+<has_text text="Peaks: 2278 (about 2278 per sample)" />
+<has_text text="Peak Groups: 0" />
+<has_text text="Sample classes: ." />
+</assert_contents>
+</output>
+</test>
 <test>
 <param name="inputs|input" value="single_file" />
 <param name="inputs|single_file" value="wt16.CDF"  ftype="netcdf" />
 <param name="methods|method" value="centWave" />
 <param name="methods|ppm" value="25" />
 <has_text text="Peaks: 380 (about 380 per sample)" />
 <has_text text="Peak Groups: 0" />
 <has_text text="Sample classes: ." />
 </assert_contents>
 </output>
-<output name="ticsRawTab" value="HU_neg_017-TIC_mqc.out" />
-<output name="bpcsRawTab" value="HU_neg_017-BPC_mqc.out" />
 </test>
 <test>
 <param name="input" value="MM14.mzML"  ftype="mzxml" />
 <param name="methods|method" value="centWave" />
 <param name="methods|ppm" value="56" />
 <has_text text="Peaks: 222 (about 222 per sample)" />
 <has_text text="Peak Groups: 0" />
 <has_text text="Sample classes: ." />
 </assert_contents>
 </output>
-<output name="ticsRawTab" value="MM14-TIC_mqc.out" />
-<output name="bpcsRawTab" value="MM14-BPC_mqc.out" />
 </test>
 </tests>
 <help><![CDATA[
 ============
 Xcms.xcmsSet
 ============
+-----------
 Description
 -----------
 This tool is used for preprocessing analyte data from multiple LC/MS files (formats NetCDF, mzXML and mzData). It extracts ion from each sample independently and using a statistic model, peaks are filtered and integrated.
 You can read a tutorial on how to perform xcms preprocessing which is available here_.
 .. _here: http://web11.sb-roscoff.fr/download/w4m/howto/w4m_HowToPerformXcmsPreprocessing_v02.pdf
+-----------------
 Workflow position
 -----------------
 **Upstream tools**
-+------------------------+--------------------+-----------------------------+-----------+
+========================= ================= ======= =========
-| Name                   | output file        | format                      | parameter |
+Name                      output file       format  parameter
-+------------------------+--------------------+-----------------------------+-----------+
+========================= ================= ======= =========
-| Upload File            | Dataset Collection | mzXML, mzML, mzData, netCDF | NA        |
+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
 -----------
-Choose your inputs
-------------------
 +---------------------------+----------------------------------+
-| Parameter                 |   Format                         |
+| Parameter : num + label   |   Format                         |
 +===========================+==================================+
+| OR : Zip file             |   zip                            |
++---------------------------+----------------------------------+
 | OR : Single file          |   mzXML, mzML, mzData, netCDF    |
 +---------------------------+----------------------------------+
-| OR : Zip file             |   zip                            |
-+---------------------------+----------------------------------+
+**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"
+| 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: 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
-Single file
+-----------------------------------------
------------
-This method is recommended because:
-* Since files are uploaded indivudially, they are smaller. And so they should be able to be uploaded using the Get Data tools.
-* It allow you to launch your xcmsSet in parallele.
-You just have to create a Dataset Collection as explain in this video_
-.. _video: http://download.workflow4metabolomics.org/docs/170510_galaxy_xcms_dataset_collection.m4v
-Zip file
---------
-This method isn't recommended because zip file aren't really well integrated
-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).
+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
+Your zip should contain all your conditions as sub-directories. For example, two conditions (mutant and wild):
-| - arabidopsis/mutant/01.raw
+arabidopsis/wild/01.raw
+arabidopsis/mutant/01.raw
 **Step2: Creating a zip file**
-| Create your zip file (e.g.: arabidopsis.zip).
+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.
+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).
+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).
-| Advices for converting your files for the XCMS input
+For more informations, don't hesitate to send us an email at supportATworkflow4metabolomics.org).
-Raw file format
----------------
+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 xcms centWave method.
+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 Filtering: **True**
-| **Use Peak Picking**: True
-| **Peak Peaking**: -Apply to MS Levels: All Levels (1-) : Centroid Mode
+Use Peak Picking: **True**
-| **Use zlib**: 64
-| **Binary Encoding**: 64
+Peak Peaking -Apply to MS Levels: **All Levels (1-)** : Centroid Mode
-| **m/z Encoding**: 64
-| **Intensity Encoding**: 64
+Use zlib: **64**
+Binary Encoding: **64**
+m/z Encoding: **64**
+Intensity Encoding: **64**
 ----------
 Parameters
 ----------
 ------------
 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".
-@HELP_BCP_TIC@
+------
-sampleMetadata.tsv [if using zip]
+.. class:: infomark
-| Tabular file that contains for each sample, it's associated class and polarity (positive,negative and mixed).
+The output file is an xset.RData file. You can continue your analysis using it in **xcms.group** tool.
-| This file is necessary in the Batch correction and statictics steps of the workflow.
 ---------------------------------------------------
 ---------------
 Working example
 ---------------
 Input files
 -----------
-| Dataset Collection -> build using this dataset_
+| zip_file -> **sacuri.zip**
-.. _dataset: http://download.workflow4metabolomics.org/datasets/sacurine-neg-subset_mzXML.zip
 Parameters
 ----------
-| **Method**: centWave
+| Method -> **matchedFilter**
-| **Max tolerated ppm m/z deviation in consecutive scans in ppm**: 25
+| step   -> **0.01**
-| **Min,Max peak width in seconds**: 10,40
+| fwhm   -> **4**
-| **Advanced option**: show
+| Advanced option -> **show**
-| **Signal/Noise threshold**: 50
+| max: -> **50**
-| **Minimum difference in m/z for peaks with overlapping retention times**: 1
+| snthresh -> **1**
-| **Prefilter step for the first phase**: 3,100
+| 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 2.2.0 - 19/10/2017**
+**Version 2.1.1 - 29/11/2017**
-- NEW: The TIC and BPC is new exported as tabular files to be visualized using MultiQC.
+- 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 - 22/02/2017**
 - NEW: The W4M tools will be able now to take as input a single file. It will allow to submit in parallel several files and merge them afterward using "xcms.xcmsSet Merger" before "xcms.group".

Mercurial > repos > lecorguille > xcms_xcmsset

comparison abims_xcms_xcmsSet.xml @ 31:e93153c07be0 draft